Merge remote-tracking branch 'origin/master' into feature/gui-first-run-welcome

# Conflicts: # packages/client/ui-settings-general/src/client/index.ts # packages/client/ui-settings-general/src/client/locales.ts # packages/client/ui-settings-general/tests/apply.spec.ts # packages/client/ui-settings/README.i18n.yaml # packages/client/ui-settings/README.md # packages/client/ui-settings/README.zh.md # packages/client/ui-settings/src/client/index.ts # packages/host/apiproxy/README.i18n.yaml # packages/host/apiproxy/src/api-proxy.ts
2026-07-31 12:48:39 +08:00
parent 10e0c2711f 4a061f33d0
commit 85d1c5e2ad
462 changed files with 12006 additions and 2484 deletions
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md
-2026-06-21-bounded-llm-request-recovery.md: 83d47e3a7d91bbcd2ceaf7b11cf13316142eb3ed
-2026-06-21-bounded-llm-request-recovery.zh.md: 00dcbad3d1023ad33a22297bfe938b94bce839d4
+2026-06-21-bounded-llm-request-recovery.md: 5c76ed5d754ea40f41dff78cb56ee7fc139a32b1
+2026-06-21-bounded-llm-request-recovery.zh.md: 1fa56f3fe0405cab663c2843d423a78d910170dd
@@ -60,11 +60,11 @@ For an eligible failure with budget remaining, the one-based transient retry cou

 The plugin owns a lifetime `AbortController` and tracks every active recovery callback, including delegated waterfall work and backoff. Effect cleanup first unregisters the listener, then aborts and awaits the active callbacks; abort wins over a late delegated retry decision, and a captured callback can neither retry nor enter the rest of its waterfall after disposal. This makes HMR disposal quiescent even though Cordis has already captured the listener.

-Before sleeping, `dsh-llm-retry` appends one non-surface `llm/retry` session event containing the turn, failed step, provider, policy mode, complete resolved-policy key, provider-policy retry number, mode-specific finite maximum when present, scheduled delay, and `LlmFailure`. The key sorts the code set and separates retry histories when a provider route is replaced by a behaviorally different same-mode policy. The plugin owns the `SessionEventMap` augmentation; `dsh-session` remains generic persistence and does not absorb the optional policy's vocabulary. The event says what was scheduled, not that the next request completed; cancellation during the delay is subsequently visible on `turn/end`. The event ships only with a production renderer and replay/snapshot coverage, because its purpose is operational state rather than trace collection.
+Before sleeping, `dsh-llm-retry` appends one non-surface `llm/retry` session event containing the turn, failed step, provider, policy mode, complete resolved-policy key, provider-policy retry number, mode-specific finite maximum when present, scheduled delay, and `LlmFailure`. The key sorts the code set and separates retry histories when a provider route is replaced by a behaviorally different same-mode policy. The plugin owns the `SessionEventMap` augmentation and exports the payload through its browser-safe `./types` subpath; `dsh-session` remains generic persistence and does not absorb the optional policy's vocabulary. The event says what was scheduled, not that the next request completed; cancellation during the delay is subsequently visible on `turn/end`. The event ships with production renderers and replay/snapshot coverage, because its purpose is operational state rather than trace collection.

 The listener calls `next()` for a non-transient code, an exhausted policy budget, or an over-cap provider delay. This preserves composition with context-overflow recovery and later policy plugins. For an owned failure it records and awaits the delay, then returns `{ kind: 'retry' }` without delegating. Turn cancellation and plugin disposal end the wait without returning a retry; the loop's cancellation/disposal checks remain authoritative.

-The agent-spine demo bundle loads the plugin so the shared stdio/TUI, one-shot CLI, and ACP example compositions use the same provider-routed policy. Library consumers retain explicit plugin composition: omitting the plugin leaves request failures terminal.
+The agent-spine demo bundle loads the plugin so the shared stdio/TUI, one-shot CLI, ACP, and headless example compositions use the same provider-routed policy. The shipped Web composition also loads it, so browser and command-line requests use the same provider defaults. Library consumers retain explicit plugin composition: omitting the plugin leaves request failures terminal.

 ### Make one layer own visible attempts

@@ -82,7 +82,7 @@ Boundary tests prove termination at both actual transports. The hand-written ada

 ### Keep attempts separate in the existing log

-A failed attempt may leave `assistant/chunk` events in its closed step, but it never appends `assistant/message` and never dispatches a tool. A retry closes the failed turn, opens the next numbered turn, reconstructs the request from the durable surface, and produces its own chunks. UIs may render live chunks while a step is open, then mark or clear that transient view when `llm/retry` identifies the failed step or `turn/end` records failure; message derivation continues to ignore the failed chunks.
+A failed attempt may leave `assistant/chunk` events in its closed step, but it never appends `assistant/message` and never dispatches a tool. A retry closes the failed turn, opens the next numbered turn, reconstructs the request from the durable surface, and produces its own chunks. UIs may render live chunks while a step is open, then mark or clear that transient view when `llm/retry` identifies the failed step or `turn/end` records failure. Web validates the complete retry payload contract, clears the failed partial at `llm/retry`, projects consecutive retry-turn events into one stable row updated to the latest attempt, and derives scheduled, started, or cancelled status from subsequent turn facts. Its countdown anchors the scheduled delay to browser receipt rather than the Host event clock, uses ceiling-rounded seconds with a one-second floor, animates only while unresolved, and keeps exact latest failure details collapsed behind the row. Retry nodes anchor their own trajectory turn even when the failed attempt has no assistant node. Message derivation continues to ignore the failed chunks, and Web applies the same projection during history rebuild so refreshing cannot resurrect discarded partials or duplicate retry rows.

 If recovery is exhausted, the final failure is stored once on `turn/end.reason` with the structured facts. If transient recovery continues, `llm/retry` is the durable home for that attempt's failure and delay. No standalone final-error event or response-id vocabulary is added.

@@ -116,7 +116,7 @@ If recovery is exhausted, the final failure is stored once on `turn/end.reason`
 - Pure unit tests cover transient-code selection, exponential backoff and jitter bounds, valid and over-cap `Retry-After`, exhausted budgets, deterministic timer/random seams, and abort during backoff.
 - Real agent-loop tests cover failure before chunks, partial chunks then failure, thrown and in-band failures, retry to success in a new turn, exhaustion to structured `turn/end.reason`, and composition with `dsh-compact-basic` context-overflow recovery.
 - The partial-chunk integration test proves failed chunks remain attributed to the failed step, no assistant message or tool side effect is committed for that step, and the successful retry has distinct provenance.
- The plugin-owned `llm/retry` event is non-surface, survives JSONL and SQLite round trips, is ignored by message derivation, and drives TUI retraction plus scheduled-retry rendering. Keyless snapshots cover scheduling, cancellation, success, and exhaustion; ACP automation snapshots confirm that a discarded attempt stays off the wire while the recovered reply is emitted.
+- The plugin-owned `llm/retry` event is non-surface, survives JSONL and SQLite round trips, is ignored by message derivation, and drives TUI and Web retraction plus scheduled-retry rendering. Client tests cover complete wire validation, clock-independent countdown, cancellation versus completed retry labels, and trajectory attribution; keyless UI snapshots cover Web scheduling and success, a real Web composition test covers partial transport failure through recovery, and ACP automation snapshots confirm that a discarded attempt stays off the wire while the recovered reply is emitted.
 - Idle-watchdog tests prove the stable signal is rearmed only while `next()` is outstanding, disarmed during consumer think time and in `finally`, and classified separately from a total-call deadline and an earlier caller abort; adapter tests prove the signal stops the underlying request rather than merely detaching it.
 - Direct `ctx.llm.stream()` callers remain single-attempt and receive the same structured failure facts.

@@ -60,11 +60,11 @@ agent loop（智能体循环）会保留 `RequestError` 作为该精确的错误

 插件拥有一个全生命期 `AbortController`，并跟踪每个活跃的恢复回调，包括委托的 waterfall（瀑布式事件）工作与退避。effect 清理会先注销监听器，再中止并等待活跃回调；中止会胜过较晚到达的委托重试决策，被捕获的回调在插件释放后既不能重试，也不能进入其 waterfall 的剩余部分。尽管 Cordis 已捕获该监听器，此设计仍能使 HMR（热模块替换）释放达到完全停稳。

-休眠前，`dsh-llm-retry` 会追加一条不进入表层的 `llm/retry` 会话事件，其中包含轮次、失败步骤、提供方、策略 mode、完整的解析策略 key、提供方策略重试编号、该 mode 存在时的有限上限、计划延迟和 `LlmFailure`。该 key 会对 code 集排序，并在提供方路由被行为不同但 mode 相同的策略替换时分隔重试历史。该插件拥有 `SessionEventMap` 声明合并；`dsh-session` 继续负责通用持久化，不会吸收可选策略的词汇。事件记录已安排的内容，而不是下一个请求已完成；延迟期间取消随后会在 `turn/end` 中可见。因为该事件的目的是表示运行状态，而不是收集跟踪数据，所以它仅与生产渲染器及回放／快照覆盖一起交付。
+休眠前，`dsh-llm-retry` 会追加一条不进入表层的 `llm/retry` 会话事件，其中包含轮次、失败步骤、提供方、策略 mode、完整的解析策略 key、提供方策略重试编号、该 mode 存在时的有限上限、计划延迟和 `LlmFailure`。该 key 会对 code 集排序，并在提供方路由被行为不同但 mode 相同的策略替换时分隔重试历史。该插件拥有 `SessionEventMap` 声明合并，并通过其浏览器安全的 `./types` 子路径导出载荷；`dsh-session` 继续负责通用持久化，不会吸收可选策略的词汇。事件记录已安排的内容，而不是下一个请求已完成；延迟期间取消随后会在 `turn/end` 中可见。因为该事件的目的是表示运行状态，而不是收集跟踪数据，所以它会与生产渲染器及回放／快照覆盖一起交付。

 对非暂时性 code、耗尽的策略预算或超出上限的提供方延迟，监听器会调用 `next()`。这保留了与上下文溢出恢复及后续策略插件的组合能力。对自身处理的失败，它会记录并等待延迟，然后在不委托的情况下返回 `{ kind: 'retry' }`。轮次取消和插件释放会结束等待且不返回重试动作，此后仍以循环的取消／释放检查为准。

-agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次性 CLI（命令行界面）和 ACP（Agent Client Protocol）示例组合使用同一套按提供方路由的策略。库消费方仍需显式组合插件：省略该插件时，请求失败保持终态。
+agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次性 CLI（命令行界面）、ACP（Agent Client Protocol）和 headless 示例组合使用同一套按提供方路由的策略。随产品交付的 Web 组合也会加载该插件，因此浏览器请求与命令行请求使用相同的提供方默认值。库消费方仍需显式组合插件：省略该插件时，请求失败保持终态。

 ### 由单一层负责可见的尝试

@@ -82,7 +82,7 @@ agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次

 ### 在现有日志中分隔尝试

-一次失败尝试可以在已关闭的步骤中留下 `assistant/chunk` 事件，但绝不会追加 `assistant/message`，也不会分发工具。重试会关闭失败轮次，开启下一个编号轮次，从持久表层重建请求，并生成自己的分片。步骤仍处于打开状态时，UI 可以渲染实时分片；当 `llm/retry` 标识失败步骤，或 `turn/end` 记录失败时，UI 再标记或清除这份暂时视图。消息派生仍会忽略失败分片。
+一次失败尝试可以在已关闭的步骤中留下 `assistant/chunk` 事件，但绝不会追加 `assistant/message`，也不会分发工具。重试会关闭失败轮次，开启下一个编号轮次，从持久表层重建请求，并生成自己的分片。步骤仍处于打开状态时，UI 可以渲染实时分片；当 `llm/retry` 标识失败步骤，或 `turn/end` 记录失败时，UI 再标记或清除这份暂时视图。Web 会验证完整的重试载荷契约，在 `llm/retry` 到达时清除失败的部分输出，将连续重试轮次的事件投影为稳定的一行，并用最新一次尝试更新该行，再从后续轮次事实派生 scheduled、started 或 cancelled 状态。倒计时以浏览器收到事件的时刻为计划延迟的起点，而不是使用 Host 事件时钟；它按向上取整且不低于 1 秒的秒数显示，仅在重试尚未结束时显示动画，并把最近一次失败的准确详情折叠在该行之后。即使失败尝试没有 assistant 节点，重试节点也会锚定自身的轨迹轮次。消息派生仍会忽略失败分片；Web 在重建历史时也会应用同一投影，因此刷新页面不会让已丢弃的部分输出重新出现，也不会生成重复的重试行。

 如果恢复预算耗尽，最终失败会连同结构化事实在 `turn/end.reason` 中存储一次。如果暂时性恢复继续，`llm/retry` 就是该次尝试的失败与延迟的持久归属位置。本决策不增加独立的最终错误事件或响应 id 词汇。

@@ -116,7 +116,7 @@ agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次
 - 纯单元测试覆盖暂时性 code 选择、指数退避和抖动边界、有效及超出上限的 `Retry-After`、耗尽的预算、确定性定时器／随机数 seam，以及退避期间中止。
 - 真实 agent-loop 测试覆盖分片前失败、部分分片后失败、抛出及带内失败、在新轮次中重试至成功、耗尽后写入结构化 `turn/end.reason`，以及与 `dsh-compact-basic` 上下文溢出恢复的组合。
 - 部分分片集成测试证明：失败分片仍归属于失败步骤，该步骤不会提交 assistant 消息或工具副作用，成功的重试具有不同的来源信息。
- 插件拥有的不进入表层的 `llm/retry` 事件可在 JSONL 和 SQLite 往返后保留，被消息派生忽略，并驱动 TUI 撤回和计划重试渲染。无密钥快照覆盖调度、取消、成功和耗尽；ACP 自动化快照确认，被丢弃的尝试不会通过协议发出，而恢复后的回复会正常发出。
+- 插件拥有的不进入表层的 `llm/retry` 事件可在 JSONL 和 SQLite 往返后保留，被消息派生忽略，并驱动 TUI 和 Web 撤回及计划重试渲染。客户端测试覆盖完整的 wire 验证、独立于时钟的倒计时、已取消与已完成重试标签的区别以及轨迹归属；无密钥 UI 快照覆盖 Web 的调度与成功，真实 Web 组合测试覆盖部分传输失败直至恢复，ACP 自动化快照确认，被丢弃的尝试不会通过协议发出，而恢复后的回复会正常发出。
 - 空闲看门狗测试证明：只有 `next()` 尚未完成时才会重新布防稳定信号；在消费方思考期间及 `finally` 中会解除布防；它与总调用 deadline 以及更早发生的调用方中止分开分类。适配器测试证明该信号会终止底层请求，而不只是与其脱离。
 - `ctx.llm.stream()` 的直接调用方仍只尝试一次，并收到相同的结构化失败事实。

@@ -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/2026-07-23-client-plugin-loading-model.md
-2026-07-23-client-plugin-loading-model.md: b0873b7aa7bccd3d613f3113fa18207770952e5d
-2026-07-23-client-plugin-loading-model.zh.md: f3472dbfc5a78924e77337bf92ce5983c8492c4c
+2026-07-23-client-plugin-loading-model.md: 02347f2964942b89ec1f0a6ec483f4c2b2f9e68c
+2026-07-23-client-plugin-loading-model.zh.md: ea927d35860fbbba567c47cea0ee3a45133ce0f4
@@ -56,8 +56,8 @@ What happens between `dsh web` starting and the UI appearing? Three stages: the

 **Host side — compose the graph.**

-1. The composing app (`apps/cli`) ships the roster as ordinary rows in its `cordis.yml` config tree — client plugin packages are entry rows like every host plugin, and `--dev` appends the `client-hmr` row in code (`AppCLIEntry`) before the settle/sweep so the fail-loud triple covers it. A roster row that fails to import is caught by the boot's `assertEntriesLoaded`.
-2. The `dsh-client-modules` node half (the package is dual-face: its browser half is the module table) scans loader entries' package.json `dshClient` declarations and composes `window.__DSH_BOOT__`: `{ rev, entries: [{ id, url, rev, inject?, immediately? }] }`. The `inject` edges and the `immediately` mark come from manifests, never hand-copied. It refuses a declared plugin without a built `./client` bundle, and any malformed declaration field — activation-time fail loud (a FAILED fiber the sweep reports).
+1. The composing app (`apps/cli`) ships the roster as ordinary rows in its `cordis.yml` config tree — client plugin packages are entry rows like every host plugin, and `--dev` appends the `client-hmr` row in code (`AppCLIEntry`) before the host activation audit so the same check covers it. A roster row that fails to import is caught by `assertEntriesLoaded`; a row whose fiber rejects is reported with its original stack by `assertEntriesActivated` ([host boot decision](2026-07-24-web-config-tree-boot-and-transport-layering.md)).
+2. The `dsh-client-modules` node half (the package is dual-face: its browser half is the module table) scans loader entries' package.json `dshClient` declarations and composes `window.__DSH_BOOT__`: `{ rev, entries: [{ id, url, rev, inject?, immediately? }] }`. The `inject` edges and the `immediately` mark come from manifests, never hand-copied. It refuses declared plugins without built `./client` bundles and groups their package/path rows under one required source-build instruction; malformed declaration fields also fail activation, and the host audit reports either error from the FAILED fiber.
 3. Scanning is incremental per package — there is no full-rescan code path. Each cordis `internal/plugin` emission marks the fiber's entry name dirty (entry-less fibers drop O(1)); a microtask flush reconciles each dirty name against live loader entries, with package metadata (including the negative "not a client package" verdict) cached per name forever and bundle re-hashing reachable only through `rebuilt(id)`. The activation pass seeds the same dirty set from current entries and flushes synchronously, so first scan and steady state share one implementation. Each bundle's content hash is its `rev` (cache busting + HMR diff anchor), the row set hashes into `graph.rev`, and every row is fetch-served: `/plugins/<id>/client.js?rev=…`. The graph types are single-sourced in the modules package's `./impl` export — the webserver knows nothing about the graph (it is a plain route-registration plugin; modules registers the bundle route and taps the index render itself).

 Why is the roster yml rows and not a scan? Because which plugins compose into a deployment is a composition decision, not a package property — a dshClient package existing in the repo does not mean this deployment mounts it, so discovery-by-scan cannot make that call; the node half scans only what the tree actually mounted.
@@ -56,8 +56,8 @@ vendored Loader 经其 `internal` seam 消费模块系统——唯一调用点

 **host 侧——组合这张图。**

-1. 负责组合的 app（`apps/cli`）把名册作为普通行放进它的 `cordis.yml` 配置树——client 插件包与每个 host 插件一样是 entry 行，`--dev` 由代码（`AppCLIEntry`）在 settle/sweep 之前追加 `client-hmr` 行，使 fail-loud 三件套一并覆盖它。名册行 import 失败由 boot 的 `assertEntriesLoaded` 捕获。
-2. `dsh-client-modules` 的 node 半（该包是双面的：浏览器半就是模块表）扫描 loader entry 的 package.json `dshClient` 声明，组合出 `window.__DSH_BOOT__`：`{ rev, entries: [{ id, url, rev, inject?, immediately? }] }`。`inject` 边与 `immediately` 标记都来自 manifest，永不人肉抄写。它拒绝声明了插件却没有已构建 `./client` bundle 的包，也拒绝任何畸形的声明字段——激活期大声失败（FAILED fiber，由 sweep 上报）。
+1. 负责组合的 app（`apps/cli`）把名册作为普通行放进它的 `cordis.yml` 配置树——client 插件包与每个 host 插件一样是 entry 行，`--dev` 由代码（`AppCLIEntry`）在 host 激活检查之前追加 `client-hmr` 行，使同一项检查覆盖它。名册行 import 失败由 `assertEntriesLoaded` 捕获；fiber reject 的行则由 `assertEntriesActivated` 报告原始 stack（[host boot 决策](2026-07-24-web-config-tree-boot-and-transport-layering.md)）。
+2. `dsh-client-modules` 的 node 半（该包是双面的：浏览器半就是模块表）扫描 loader entry 的 package.json `dshClient` 声明，组合出 `window.__DSH_BOOT__`：`{ rev, entries: [{ id, url, rev, inject?, immediately? }] }`。`inject` 边与 `immediately` 标记都来自 manifest，永不人肉抄写。它会拒绝没有已构建 `./client` bundle 的已声明插件，并把它们的 package/path 行归到一条源码构建要求下；畸形声明字段同样会让激活失败，host 检查会从 FAILED fiber 报告这两类错误。
 3. 扫描是单包增量——不存在全量重扫代码路径。每次 cordis `internal/plugin` 发射把该 fiber 的 entry 名标脏（无 entry 的 fiber O(1) 丢弃）；微任务 flush 把每个脏名对账 live loader entries，包元数据（含「非 client 包」的否定结论）按名永久缓存，bundle 重哈希只经 `rebuilt(id)` 可达。激活趟从当前 entries 灌同一脏集合并同步 flush，初扫与稳态共享一条实现。每个 bundle 的内容哈希是其 `rev`（缓存失效 + HMR diff 锚点），行集合哈希进 `graph.rev`，每一行都经 fetch 供给：`/plugins/<id>/client.js?rev=…`。图类型单源在 modules 包的 `./client` 出口——webserver 对图一无所知（它是朴素路由注册插件；bundle 路由和 index 渲染 tap 都由 modules 自己注册）。

 为什么名册是 yml 行而不是扫描？因为哪些插件组合进一次部署是组合决策，不是包属性——一个 dshClient 包存在于仓库里，不代表这次部署要挂载它，扫描发现无从替人做这个决定；node 半只扫描配置树实际挂载了的东西。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.md
-2026-07-24-web-config-tree-boot-and-transport-layering.md: a2080024d36d54162f4f4aa79896e51efd708f59
-2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: 1c430bf2939f9f556f378bdeb78872a0091a592d
+2026-07-24-web-config-tree-boot-and-transport-layering.md: 88f94b1f58ae7a3451c7772f4a9ff7d6564254c0
+2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: ea2a8f70a6c2d4207d4388a9303fbc6ce6e94238
@@ -12,9 +12,9 @@ English | [中文](2026-07-24-web-config-tree-boot-and-transport-layering.zh.md)

 ## Decision

-**Composition is one flat assembled tree.** `apps/cli/config/base.cordis.yml` plus `apps/cli/config/web.cordis.yml` holds every row — the host runtime (32 rows), the `api-gateway` row, the `webserver` row, and the `dshClient` rows (the browser roster; the modules row is simultaneously a host row). No spine bundle: every plugin is one row and every config field is yml-editable. That stance later became repository-wide, with the rows both surfaces share factored into `apps/cli/config/base.cordis.yml` and each surface reduced to an overlay ([shared-base overlays](../simplification/2026-07-29-shared-base-config-overlays.md)). `--dev` appends the `dsh-client-hmr` row in code before the settle sweep — prod and dev differ by exactly that row. Row order carries no load semantics; activation is service-availability driven, and the boot compensates with a fail-loud triple: `assertEntriesLoaded` (import failures), `installFailLoud` (late apply rejections), and an all-ACTIVE sweep (PENDING fibers — cordis inject waiting has no timeout).
+**Composition is one flat assembled tree.** `apps/cli/config/base.cordis.yml` plus `apps/cli/config/web.cordis.yml` holds every row — the host runtime (32 rows), the `api-gateway` row, the `webserver` row, and the `dshClient` rows (the browser roster; the modules row is simultaneously a host row). No spine bundle: every plugin is one row and every config field is yml-editable. That stance later became repository-wide, with the rows both surfaces share factored into `apps/cli/config/base.cordis.yml` and each surface reduced to an overlay ([shared-base overlays](../simplification/2026-07-29-shared-base-config-overlays.md)). `--dev` appends the `dsh-client-hmr` row in code before the settle audit — prod and dev differ by exactly that row. Row order carries no load semantics; activation is service-availability driven. The shared audit rejects imports with no fiber, awaits only failed fibers to recover original activation errors, and reports services that leave a fiber `PENDING`; before throwing, it marks those exact rejection reasons through one process checkpoint so `installFailLoud` coalesces Loader's duplicate notification while unrelated unhandled rejections remain fatal. The Node app-boot artifact embeds `@cordisjs/plugin-include` while leaving `@cordisjs/plugin-loader` external, so the include's `EntryTree` and the host bind to one Loader peer instead of splitting a config tree across two Loader implementations.

-**Boot glue is a class pair.** `AppCLIEntry` (apps/cli) and `AppWebEntry` (the shell kernel) hold only what must exist independently of cordis: argv facts, the composed patch set, the parsed boot manifest, the module system instance, loading-page handles — everything else lives in plugins. `AppCLIEntry.run()` is three stages: layered env (ambient > cwd `.env` > `$DSH_HOME/.env`, closing the defect above) → patch composition → Loader include boot plus the triple. `AppWebEntry.run()` mirrors it browser-side: parse `window.__DSH_BOOT__` into a `BootManifest` (two views: npm-package rows for the module table, cordis-plugin rows for entry composition; malformed wire throws), build the module system, render the loading page, prefetch the `immediately` tier in parallel with Context/Loader setup, **await the prefetch before creating entries** (materialization is `tree.import`'s synchronous require, unprotected by fiber inject waiting; cross-package require edges such as i18n → runtime/client need every immediately-tier factory registered first — an empirically found 10–25% boot race otherwise), adopt the modules entry, create the graph rows, settle, sweep.
+**Boot glue is a class pair.** `AppCLIEntry` (apps/cli) and `AppWebEntry` (the shell kernel) hold only what must exist independently of cordis: argv facts, the composed patch set, the parsed boot manifest, the module system instance, loading-page handles — everything else lives in plugins. `AppCLIEntry.run()` is three stages: layered env (ambient > cwd `.env` > `$DSH_HOME/.env`, closing the defect above) → patch composition → Loader include boot plus the activation audit. `AppWebEntry.run()` mirrors it browser-side: parse `window.__DSH_BOOT__` into a `BootManifest` (two views: npm-package rows for the module table, cordis-plugin rows for entry composition; malformed wire throws), build the module system, render the loading page, prefetch the `immediately` tier in parallel with Context/Loader setup, **await the prefetch before creating entries** (materialization is `tree.import`'s synchronous require, unprotected by fiber inject waiting; cross-package require edges such as i18n → runtime/client need every immediately-tier factory registered first — an empirically found 10–25% boot race otherwise), adopt the modules entry, create the graph rows, settle, sweep.

 **Config sources have one declaration place each.** yml static values are engineering defaults; the profile json (`./.dsh-tmp-profile/config.json`, read-only, never created, cwd-anchored until the `$DSH_HOME` migration) is user config mapped through a static `PROFILE_MAPPINGS` table onto target rows (`provider`/`model` → the `api-gateway` row, `persistenceRoot` → the jsonl row); CLI flags map onto the `webserver` row with a field set disjoint from the json's; env values enter through yml `!!js` expressions, never through the mapping table. Patches replace a row's config wholesale, so the entry class re-reads the yml row's static values (bypass parse) and merges overrides on top. An unmapped json key fails loud. The resolved frontend `distIndex` rides the same patch channel — an assembly fact, not user config.

@@ -12,9 +12,9 @@ Status: implemented

 ## 决策

-**组合结果是一棵平铺配置树。** `apps/cli/config/base.cordis.yml` 与 `apps/cli/config/web.cordis.yml` 共同持有全部行——host runtime（32 行）、`api-gateway` 行、`webserver` 行、`dshClient` 行（浏览器 roster；modules 行同时是 host 行）。不做 spine bundle：每插件一行、每个 config 字段 yml 可改。这一立场后来推广到全仓：两个 surface 共享的配置项被抽取进 `apps/cli/config/base.cordis.yml`，各 surface 则收敛为一份 overlay（[共享 base overlay](../simplification/2026-07-29-shared-base-config-overlays.md)）。`--dev` 在 settle sweep 之前由代码追加 `dsh-client-hmr` 行——prod 与 dev 的全部差异就是这一行。行序无装载语义；激活由服务可用性驱动，boot 以 fail-loud 三件套补偿：`assertEntriesLoaded`（import 失败）、`installFailLoud`（迟到的 apply 拒绝）、all-ACTIVE sweep（PENDING fiber——cordis inject 等待没有超时）。
+**组合结果是一棵平铺配置树。** `apps/cli/config/base.cordis.yml` 与 `apps/cli/config/web.cordis.yml` 共同持有全部行——host runtime（32 行）、`api-gateway` 行、`webserver` 行、`dshClient` 行（浏览器 roster；modules 行同时是 host 行）。不做 spine bundle：每插件一行、每个 config 字段 yml 可改。这一立场后来推广到全仓：两个 surface 共享的配置项被抽取进 `apps/cli/config/base.cordis.yml`，各 surface 则收敛为一份 overlay（[共享 base overlay](../simplification/2026-07-29-shared-base-config-overlays.md)）。`--dev` 在 settle audit 之前由代码追加 `dsh-client-hmr` 行——prod 与 dev 的全部差异就是这一行。行序无装载语义；激活由服务可用性驱动。共享 audit 会拒绝没有 fiber 的 import、仅等待失败的 fiber 以恢复原始激活错误，并报告让 fiber 停在 `PENDING` 的服务；抛出错误前，审计会通过一个进程级检查点标记这些 rejection 的确切原因，从而让 `installFailLoud` 将 Loader 的重复通知合并为一次，而无关的未处理 rejection 仍然致命。Node app-boot 产物内嵌 `@cordisjs/plugin-include`，但将 `@cordisjs/plugin-loader` 保持为外部依赖，因此 include 的 `EntryTree` 与 host 会绑定到同一个 Loader peer，而不会让一棵配置树横跨两个 Loader 实现。

-**boot 胶水是一对 class。** `AppCLIEntry`（apps/cli）与 `AppWebEntry`（壳内核）只持有独立于 cordis 必须提前存在的东西：argv 事实、合成的 patch 集、解析出的 boot manifest、模块系统实例、loading 页句柄——其余一律进插件。`AppCLIEntry.run()` 三段：分层 env（ambient > cwd `.env` > `$DSH_HOME/.env`，顺手关掉上述缺陷）→ patch 合成 → Loader include boot 加三件套。`AppWebEntry.run()` 在浏览器侧镜像它：把 `window.__DSH_BOOT__` 解析成 `BootManifest`（双视角：npm 包行给模块表、cordis 插件行给 entry 组合；畸形 wire 大声抛）、建模块系统、渲染 loading 页、immediately 层预取与 Context/Loader 准备并行、**create entry 之前等预取齐**（物化是 `tree.import` 的同步 require，不受 fiber inject 等待保护；i18n → runtime/client 这类跨包 require 边要求 immediately 层工厂全部注册完——否则有实测 10–25% 的 boot 竞态）、收编 modules entry、逐图行 create、settle、sweep。
+**boot 胶水是一对 class。** `AppCLIEntry`（apps/cli）与 `AppWebEntry`（壳内核）只持有独立于 cordis 必须提前存在的东西：argv 事实、合成的 patch 集、解析出的 boot manifest、模块系统实例、loading 页句柄——其余一律进插件。`AppCLIEntry.run()` 三段：分层 env（ambient > cwd `.env` > `$DSH_HOME/.env`，顺手关掉上述缺陷）→ patch 合成 → Loader include boot 加 activation audit。`AppWebEntry.run()` 在浏览器侧镜像它：把 `window.__DSH_BOOT__` 解析成 `BootManifest`（双视角：npm 包行给模块表、cordis 插件行给 entry 组合；畸形 wire 大声抛）、建模块系统、渲染 loading 页、immediately 层预取与 Context/Loader 准备并行、**create entry 之前等预取齐**（物化是 `tree.import` 的同步 require，不受 fiber inject 等待保护；i18n → runtime/client 这类跨包 require 边要求 immediately 层工厂全部注册完——否则有实测 10–25% 的 boot 竞态）、收编 modules entry、逐图行 create、settle、sweep。

 **每个配置源有唯一声明位置。** yml 静态值是工程默认；profile json（`./.dsh-tmp-profile/config.json`，只读、绝不创建、暂锚 cwd 直至 `$DSH_HOME` 迁移）是用户配置，经静态 `PROFILE_MAPPINGS` 表映射到目标行（`provider`/`model` → `api-gateway` 行，`persistenceRoot` → jsonl 行）；CLI flags 映射到 `webserver` 行、字段集与 json 不相交；env 值经 yml `!!js` 表达式进入，绝不进映射表。patch 整体替换行 config，故 entry 类旁路 parse 重读 yml 行静态值再叠加覆盖。未映射的 json 键 fail loud。解析出的前端 `distIndex` 走同一 patch 通道——装配事实，不是用户配置。

@@ -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: 92bb91c3e892d928cedf18ec57c725a116b6ffc8
-2026-07-25-web-input-machine-and-slash-pipeline.zh.md: 5bee6df52f16d935aa4f4ccff8627a2d43d44c8c
+2026-07-25-web-input-machine-and-slash-pipeline.md: c3deadb34d3a633525dde701c92bcc98c05e5d6e
+2026-07-25-web-input-machine-and-slash-pipeline.zh.md: 7a6988423dcdffebb0a28735146439c8ade0a862
@@ -63,7 +63,7 @@ Calls that stay un-evented (registry registration → explicit call → await):
 A trigger/menu/pick pipeline with zero knowledge of "commands":

 - The service holds only the source registry (`SlashSource{trigger: '/'|'@', name, order?, candidates, onPick, matchSpace?, matchEnter?}`; (trigger,name) unique; the optional `order` sorts the roster — lower first, default 0, ties keep registration order — and that sorted roster is both group order and polling order) and `sessionOf(sctx)`. Implementing a match hook IS the declaration of participation in space/enter adjudication; the pipeline polls in roster order, the first non-undefined answer wins, and no claimant means the default sink. matchSpace is synchronous (space fires mid-keystroke; hot cache only); matchEnter is asynchronous (it may await the source's own warmup, and a warmup failure rejects).
- The controller holds the single authoritative hit (span included; retained for Space after the menu closes), the per-session menu store, the candidate-fetch generation, keyboard arbitration (combobox mode: focus stays in the textarea, ↑↓/Enter/Escape are intercepted and all pass the IME composition guard, with the single exception Shift+Enter unconditionally going first), and pick orchestration (outcome → self-dispatched bail events); a `dismiss()` verb backs MenuView's injected `onDismiss` (a pointer down outside both the menu and the surrounding composer card closes the menu; MenuView also localizes group titles through the `slash.menu` locale namespace and clamps its height to the viewport space above the composer via ui-primitives' `useAnchoredMaxHeight`); at each session scope's birth it runs `warm(projection)` once over the source roster — within that scope the projection holds only the stable sessionId, with no published/capability transitions; the scope disposer tears down the controller.
+- The controller holds the single authoritative hit (span included; retained for Space after the menu closes), the per-session menu store, the candidate-fetch generation, keyboard arbitration (combobox mode: focus stays in the textarea, ↑↓/Enter/Escape are intercepted and all pass the IME composition guard, with the single exception Shift+Enter unconditionally going first), and pick orchestration (outcome → self-dispatched bail events). `toggleSource(name, syntheticHit)` is the chrome-launch path: it seeds only that registered source over the caller's textarea selection and publishes `launcher = name` until close; ordinary typed tracking clears the launcher and restores the full trigger roster. Both paths render the same MenuView and execute the same `onPick` chain. A `dismiss()` verb backs MenuView's injected `onDismiss` (a pointer down outside both the menu and the surrounding composer card closes the menu; MenuView also localizes group titles through the `slash.menu` locale namespace and clamps its height to the viewport space above the composer via ui-primitives' `useAnchoredMaxHeight`); at each session scope's birth it runs `warm(projection)` once over the source roster — within that scope the projection holds only the stable sessionId, with no published/capability transitions; the scope disposer tears down the controller.
 - Trigger-detection word boundaries (`user@host` and URL `/` never trigger) and the guard tiers (plain: `/` everywhere + `@` inline / claimed: `/` suppressed, `@` live / frozen: none) are the frozen pure core.

 ### hub / facade: the resident shell and the strict-session input body
@@ -101,7 +101,7 @@ skill/@subagent references skip the placeholder + occurrence identity chain —
 - `conversation.input.dock` — the stacked strip above the input (QueueDock's read-only queue list lands here), ordered by `order`.
 - `conversation.composer.dock` — the stats band on the composer's top edge.
 - `conversation.input.left` / `conversation.input.right` — the tool-row left and right regions.
- `conversation.input.plan` / `conversation.input.model` (single) — the tool row's two named control seats; the bar passes only `locked` (owner props), each stays empty until its owning plugin registers, no placeholder fallback.
+- `conversation.input.plan` / `conversation.input.model` (single) — the tool row's two named control seats; the bar passes only `locked` (owner props), each stays empty until its owning plugin registers, no placeholder fallback. The plan seat stays empty while inactive because the shared Command source owns entry; an effective plan target renders the warn-state `Plan ×` status button, whose only action is `/plan off`.
 - `conversation.hero.workspace` (root scope) — the Workspace picker shared by the no-session and blank Hero; a pick reuses or creates the target blank session through `connectWorkspace`, moving the draft where necessary before switching current.

 ### Testing discipline
@@ -122,6 +122,8 @@ The state machine's entire behavior is covered by pure-JS unit tests (event sequ
 | Space adjudication also claiming execute-kind commands | The misfire defense: after a space the whole line is an ordinary prompt; irreversible side effects keep explicit entry points only |
 | A generic tokenPattern decoration mechanism | Structured occurrence records replace pattern scanning |
 | A placeholder select resident in the tool row | Named seats stay empty until registration; a placeholder clashing with the real implementation is two sources of truth |
+| An always-visible Plan on/off toggle | The shared Command source already owns entry; a second entry point turns a status seat into redundant mode chrome |
+| A second plus-menu component/controller, or an Add/File group above Command | It would duplicate async candidates, keyboard highlight, focus retention, and pick state; the plus control is only a source-filtered launcher for the existing MenuView, and this scope has no file capability |
 | All references through U+FFFC chips (the pre-Decision-21 line) | Plain text + derived decoration carries zero identity state; the literal text IS the model projection, sparing undo/clipboard any special cases; the chip chain is kept for scenarios needing indivisible atomicity |

 ## Consequences
@@ -63,7 +63,7 @@ occurrence 表与 chip 三投影：
 对"命令"零知识的触发/菜单/pick 管线：

 - service 只有 source 注册表（`SlashSource{trigger: '/'|'@', name, order?, candidates, onPick, matchSpace?, matchEnter?}`；(trigger,name) 唯一；可选 `order` 对 roster 排序——越小越靠前、默认 0、同值保持注册序——排序后的 roster 同时是组序与轮询序）与 `sessionOf(sctx)`。实现 match 钩子即参与空格/回车裁决的声明；管线按 roster 序轮询，首个非 undefined 应答胜出，无人认领落 default sink。matchSpace 同步（空格在击键中触发，只许热缓存）；matchEnter 异步（可 await 源自身预热，预热失败即 reject）。
- controller 持有唯一权威 hit（含 span；菜单关闭后为 Space 保留）、per-session menu store、候选 fetch generation、键盘仲裁（combobox 模式：焦点始终在 textarea，↑↓/Enter/Escape 拦截且全程过 IME composition 守卫，唯一例外 Shift+Enter 无条件先行）、pick 编排（outcome → 自派 bail 事件）；`dismiss()` 动词支撑 MenuView 注入的 `onDismiss`（指针落在菜单与所在 composer 卡片之外即关闭菜单；MenuView 还经 `slash.menu` locale 命名空间本地化组标题，并经 ui-primitives 的 `useAnchoredMaxHeight` 把高度收敛到 composer 上方的视口空间）；每个 session scope 出生时对 source roster 做一次 `warm(projection)`，projection 在该 scope 内只有稳定的 sessionId，无 published/能力跃迁；scope disposer 拆除 controller。
+- controller 持有唯一权威 hit（含 span；菜单关闭后为 Space 保留）、per-session menu store、候选 fetch generation、键盘仲裁（combobox 模式：焦点始终在 textarea，↑↓/Enter/Escape 拦截且全程过 IME composition 守卫，唯一例外 Shift+Enter 无条件先行），以及 pick 编排（outcome → 自派 bail 事件）。`toggleSource(name, syntheticHit)` 是 chrome launcher 路径：它基于调用方的 textarea selection，只 seed 对应的已注册 source，并发布 `launcher = name` 直至关闭；普通的键入式 tracking 会清除 launcher 并恢复完整的 trigger roster。两条路径渲染同一个 MenuView，并执行同一条 `onPick` 链。`dismiss()` 动词支撑 MenuView 注入的 `onDismiss`（指针落在菜单与所在 composer 卡片之外即关闭菜单；MenuView 还经 `slash.menu` locale 命名空间本地化组标题，并经 ui-primitives 的 `useAnchoredMaxHeight` 把高度收敛到 composer 上方的视口空间）；每个 session scope 出生时对 source roster 做一次 `warm(projection)`，projection 在该 scope 内只有稳定的 sessionId，无 published/能力跃迁；scope disposer 拆除 controller。
 - 触发检测词边界（`user@host`、URL `/` 永不触发）、守卫分档（plain：`/` 到处 + `@` 行内 / claimed：`/` 抑制、`@` 活 / frozen：全无）为冻结纯核。

 ### hub / facade：常驻外壳与严格 session 输入体
@@ -101,7 +101,7 @@ skill/@subagent 引用不走占位符 + occurrence 身份链——pick 直接把
 - `conversation.input.dock`——输入上方堆叠条（QueueDock 的队列只读列表落此），order 定序。
 - `conversation.composer.dock`——composer 上沿统计带。
 - `conversation.input.left` / `conversation.input.right`——工具行左右区。
- `conversation.input.plan` / `conversation.input.model`（single）——工具行两具名控制位；bar 只传 `locked`（owner props），空到 owning 插件注册为止，无占位 fallback。
+- `conversation.input.plan` / `conversation.input.model`（single）——工具行两具名控制位；bar 只传 `locked`（owner props），空到 owning 插件注册为止，无占位 fallback。plan seat 未激活时保持为空，因为入口归共享 Command source 所有；有效 plan 目标会渲染 warn 状态的 `Plan ×` 状态按钮，其唯一动作是 `/plan off`。
 - `conversation.hero.workspace`（root scope）——无 session / blank Hero 共用的 Workspace picker；pick 经 `connectWorkspace` 复用或创建目标 blank session，必要时搬运 draft 后切 current。

 ### 测试纪律
@@ -122,6 +122,8 @@ skill/@subagent 引用不走占位符 + occurrence 身份链——pick 直接把
 | 空格裁决也认领即执行型命令 | 误触发防线：空格后整行是普通 prompt；不可逆副作用只留显式入口 |
 | 通用 tokenPattern 装饰机制 | 结构化 occurrence 记录取代模式扫描 |
 | 占位 select 常驻工具行 | 具名坑位空到注册为止；占位件与真实现冲突时是双真相源 |
+| 始终可见的 Plan 开／关切换 | 入口已归共享 Command source 所有；第二个入口会把状态 seat 变成冗余的 mode chrome |
+| 第二套加号菜单组件／controller，或在 Command 上方增加 Add/File 分组 | 这会重复异步候选、键盘高亮、焦点保留与 pick 状态；加号控件只是既有 MenuView 按 source 过滤的 launcher，且此 scope 没有文件能力 |
 | 引用一律走 U+FFFC chip（决策 21 前旧线） | 纯文本 + 派生装饰零身份状态；原文即模型投影，undo/剪贴板免特判；chip 链保留给需要不可分原子性的场景 |

 ## 后果
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-30-adapter-owned-max-token-defaults.md
+2026-07-30-adapter-owned-max-token-defaults.md: a522848fd4482f84859e587505b6a5e6f5c72d60
+2026-07-30-adapter-owned-max-token-defaults.zh.md: 8db6a06199fc1c4e73c86492d12dc86edafe8c7e
@@ -0,0 +1,33 @@
+# Agent Note: Adapter-owned max-token defaults
+
+Status: implemented
+
+English | [中文](2026-07-30-adapter-owned-max-token-defaults.zh.md)
+
+## Problem
+
+An LLM adapter could serialize an explicit `GenerateOptions.maxTokens`, but its Cordis configuration could not establish a reconstructable conversation default. Applying a fallback only inside provider serialization would make the wire request differ from the durable `request/header`; putting every provider's default in Agent Loop would instead transfer deployment and model policy into the provider-neutral driver.
+
+## Decision
+
+`LlmResolvedModelInfo.defaultMaxTokens` carries an optional adapter-configured per-request output cap for one exact provider/model route. `LlmService` validates it as a positive safe integer and materializes it into `LlmCallConfig.maxTokens` only when the caller omitted a value. A prepared call identifies materialized `maxTokens` and `reasoningEffort` fields as adapter defaults; explicit request or Agent options remain unmarked and therefore win without clamping.
+
+The agent loop continues to prepare calls before logging `request/header`, so the effective config and its adapter-default provenance become durable request facts before dispatch. Before the next `agent/request` waterfall, the loop removes marked fields from the proposal; exact-model resolution then materializes the current route's defaults again. A provider/model switch therefore cannot mistake a previous adapter's default for an explicit override, while explicit conversation values persist. Direct `LlmService.stream()` calls resolve the same default at the final adapter boundary. The field is a request default rather than a hard model output limit; adapters that preserve provider-owned defaults omit it.
+
+The native DeepSeek adapter exposes `maxTokens` in Cordis config with a 256,000-token default and maps the effective value to `max_tokens`. Its default context capacity is 1,000,000 tokens: both built-in V4 entries publish that exact capacity, while configured entries without capacity and unlisted pass-through ids inherit the same adapter-wide fallback.
+
+## Alternatives considered
+
+**Apply the default only in DeepSeek serialization.** Rejected because the provider wire would contain a model-visible value absent from the durable request header.
+
+**Set `AgentOptions.maxTokens` in every shipped application.** Rejected because applications would duplicate adapter deployment policy, direct LLM calls would behave differently, and selecting another provider would retain a DeepSeek-specific cap.
+
+**Represent 256,000 as a hard per-model maximum.** Rejected because the configured value is the desired request budget, not evidence that every configured endpoint rejects larger outputs. Explicit callers remain authoritative.
+
+**Leave the provider default in control.** Rejected for the native DeepSeek deployment because the product requires a stable 256,000-token conversation budget across compatible endpoints.
+
+## Consequences
+
+DeepSeek conversations send `max_tokens: 256000` by default, and the same value plus its adapter provenance appear in the session request header. Deployments can change the adapter default through `llm-deepseek.config.maxTokens`; per-agent and per-request values override it. Changing the route rematerializes the new exact adapter's default instead of carrying DeepSeek's derived value forward. Other adapters retain their existing behavior until they intentionally publish `defaultMaxTokens`.
+
+The 256,000-token output budget reserves a large part of the one-million-token context on endpoints that pre-allocate requested output. Deployments whose gateway or model supports a smaller budget must lower `maxTokens`; the explicit configuration is preferable to an undocumented provider fallback.
@@ -0,0 +1,33 @@
+# Agent Note: 适配器持有的最大 token 默认值
+
+Status: implemented
+
+[English](2026-07-30-adapter-owned-max-token-defaults.md) | 中文
+
+## Problem
+
+LLM（大语言模型）适配器可以序列化显式的 `GenerateOptions.maxTokens`，但无法通过 Cordis 配置建立可重建的对话默认值。仅在提供方序列化中应用回退，会导致协议请求与持久 `request/header` 不一致；若将各提供方默认值都放进 agent loop（智能体循环），则会把部署与模型策略转移到提供方无关的驱动器中。
+
+## Decision
+
+`LlmResolvedModelInfo.defaultMaxTokens` 携带一条确切提供方／模型路由的可选单次请求输出上限，该值由适配器配置。`LlmService` 将其校验为正安全整数，并且仅在调用方省略值时才填入 `LlmCallConfig.maxTokens`。准备后的调用会将已填入的 `maxTokens` 和 `reasoningEffort` 字段标记为适配器默认值；显式请求值或 Agent 选项不带该标记，因此优先且不会被自动调整。
+
+agent loop 仍在记录 `request/header` 前准备调用，因此生效配置及其适配器默认值来源会在分派前成为持久请求事实。下一次 `agent/request` waterfall（瀑布式事件）前，agent loop 会从提议中移除带标记字段，随后精确模型解析会再次填入当前路由的默认值。因此，切换提供方／模型不会把前一个适配器的默认值误当成显式覆盖，而显式对话值则会保留。直接调用 `LlmService.stream()` 时，也会在最终适配器边界解析同一默认值。该字段是请求默认值，而非模型输出硬上限；保留提供方持有默认值的适配器会省略它。
+
+原生 DeepSeek 适配器在 Cordis 配置中公开 `maxTokens`，默认值为 256,000 token，并将生效值映射为 `max_tokens`。其默认上下文容量为 1,000,000 token：两个内置 V4 配置项均公布这一精确容量；不含容量的已配置项和未列出的原样传递 id 则继承同一个适配器级回退值。
+
+## Alternatives considered
+
+**仅在 DeepSeek 序列化中应用默认值。** 不予采纳，因为提供方协议会包含持久请求 header 中缺失的模型可见值。
+
+**在每个已发布应用中设置 `AgentOptions.maxTokens`。** 不予采纳，因为应用会重复适配器部署策略，直接 LLM 调用的行为将不同，而且选择另一个提供方后仍会保留 DeepSeek 专用上限。
+
+**将 256,000 表示为每模型硬上限。** 不予采纳，因为配置值是所需请求预算，无法证明每个已配置端点都会拒绝更大的输出。显式调用方仍具有最终决定权。
+
+**由提供方默认值控制。** 对原生 DeepSeek 部署不予采纳，因为产品要求各兼容端点都采用稳定的 256,000 token 对话预算。
+
+## Consequences
+
+DeepSeek 对话默认发送 `max_tokens: 256000`，会话请求 header 中也会出现相同的值及其适配器来源。部署可以通过 `llm-deepseek.config.maxTokens` 更改适配器默认值；每个 agent 和每次请求的值都会覆盖它。更改路由会重新填入新的精确适配器默认值，而不是继续沿用 DeepSeek 派生出的值。其他适配器会保留现有行为，直至主动公布 `defaultMaxTokens`。
+
+对于预分配请求输出的端点，256,000 token 的输出预算会占用 1,000,000 token 上下文中的很大部分。如果部署使用的 gateway 或模型仅支持较小预算，则必须调低 `maxTokens`；显式配置优于未记录的提供方回退值。
@@ -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/2026-07-30-client-locale-full-rollout.md
+2026-07-30-client-locale-full-rollout.md: c080d9f240d4533ecd9694ceecfada8662c46425
+2026-07-30-client-locale-full-rollout.zh.md: 062d982e3d7ea62f3ca4c8fedb842e8336f0852c
@@ -0,0 +1,45 @@
+# Agent Note: Full client copy rollout onto the typed locale seat, and the non-translation boundary
+
+Status: implemented
+
+English | [中文](2026-07-30-client-locale-full-rollout.zh.md)
+
+## Problem
+
+After the typed locale standard seat landed (`locale:` on register → framework-injected typed `t`), only four early adopters rode it; every other client package still shipped hardcoded, mixed-language literals. Migrating the rest required mechanisms and boundary decisions the early adopters never touched: how registration-time text (nav rows, view-tab labels) refreshes on a language switch; how the zero-cordis ui-primitives atoms receive copy; and which strings deliberately stay untranslated — an unrecorded boundary invites a future agent to "complete" the localization.
+
+## Decision
+
+**Registration-time text rides a label thunk.** A list registration's `label` accepts `SlotLabel = string | (() => string)`; owners projecting ledger rows resolve through `resolveSlotLabel` (never reading `options.label` raw) and make the read point follow the locale revision (outlets subscribe to the revision themselves; off-ledger projections such as the ui-settings nav fold the revision into their cache key and subscribe to both sources). Thunks evaluate per read, so a language switch causes zero ledger churn — no re-registration, versions stay put, and every `locale/change` re-registration wiring is deleted.
+
+**Component copy rides the standard `t` seat; deep children take `t` as a plain prop** typed `XxxProps['t']`. The dictionary canon is unchanged: `zh satisfies Record<string, string>` is the key source and `en satisfies Record<XxxKey, string>` locks bilingual balance.
+
+**Zero-cordis atoms (ui-primitives) take copy as props**: `labels` on `TerminalBlock`/`JsonTree`, `copyLabel`/`copiedLabel` on `CodeBlock`, `codeLabels` on `MarkdownText`, `truncatedLabel` on `JsonBlock`, `label` on `ConnectionBanner`, `closeLabel` on `Modal` — defaults are the previous hardcoded strings, so a consumer passing nothing renders byte-identical output. Localized plugins pass dictionary-driven labels from their own `t` seat; call sites passing object props memoize them on the `t` identity (`MarkdownText` caches its component table on the `codeLabels` identity).
+
+**The non-translation boundary (deliberate decisions, not debt):**
+
+- **Error/failure strings stay English**: client-authored fallbacks (`command failed`, plan-toggle failures), RpcError messages, and wire `error.message (code)` pass-throughs render verbatim.
+- **Design literals stay out of the dictionaries**: tool-row variant titles (Think/Bash/…), SYSTEM/USER-style kind badges, the Plan chip wordmark, the whole StatsLine — identical in both languages.
+- **ui-trajectory is deferred wholesale** (a developer inspection surface, terminology-dense, ruled separately).
+- **Boot copy stays hardcoded** (AppRoot renders before the locale service exists).
+
+**Derivation layers stay pure; localization happens at render.** ui-workspace's `relativeTime` returns structured `{unit, n}` composed with dictionary templates by the renderer; blank sessions and the Ungrouped bucket keep their stored titles, with the renderer substituting localized copy off the `blank` flag / absent `workspaceId`; **blank rows are excluded from search entirely** (a bilingual display title cannot match a single-language query stably). Dates use no Intl: format templates live in the dictionaries (message clock `clock.md`/`clock.ymd`, workspace hover `date.ymd`) and the formatters take `t` as a parameter, staying pure.
+
+**Test and e2e doctrine**: `makeTranslate(...dicts)` (dsh-client-test-runtime) mirrors the service lookup chain (first-dict-wins, key fallback, `{name}` interpolation); component specs stub the `t` seat with it, typed against real props seats. Web e2e uniformly opens through `newEnglishPage` (pins `dsh.locale=en` before boot) and the built-boot snapshot pins the same — goldens are immune to localization migrations; the settings language-switch scenario deliberately bypasses the helper to cover the zh default.
+
+The "apply layer subscribes to `locale/change` and re-registers for fresh labels" mechanism in the [settings/locale/theme layering note](../../proposed/architecture/2026-07-25-client-settings-locale-theme.md) is superseded by this decision (thunk + revision lifecycle).
+
+## Alternatives considered
+
+- **Keep labels as strings and re-register on switch** (the early adopters' original shape): boot already registers once per package, and `locale/change` listeners re-registering amplifies into a storm; ledger version churn also busts every version-keyed projection cache. Thunks move the refresh cost to read points that already follow the revision.
+- **A locale context/injection channel for ui-primitives**: breaks the zero-cordis boundary (atoms would depend on the runtime) and drags unlocalized consumers (ui-trajectory) along. Props let each consumer decide independently.
+- **Error strings in the dictionaries**: the error surface is a debugging surface — verbatim English is what gets searched and compared in reports; wire pass-throughs are untranslatable anyway, and half-translation manufactures mixed-language text.
+- **`toLocaleString()`/Intl for dates**: follows the browser/OS language, not the app locale, guaranteeing mixed text after a switch; the dictionary templates are tiny and isomorphic to the message clock.
+- **Blank rows matching search (against localized or stored titles)**: either choice yields "visible but unfindable" in one language; placeholder rows carry no information, so whole-row exclusion is the stable semantic.
+
+## Consequences
+
+- A language switch refreshes the whole UI instantly with zero re-registration; adopting a new package is three steps (dictionary + declare-merge + `locale: NS`), no hand-written glue.
+- Cost: list-label consumers must know `resolveSlotLabel` (a raw `options.label` read can now hold a function); the `SlotLabel` type catches most misuse statically.
+- ui-primitives' Chinese defaults still render Chinese under the English locale **until a consumer passes labels** — the unmigrated JsonTree consumer (ui-trajectory) showing its English defaults happens to match that package's all-English status quo.
+- Pinning e2e to English means the zh default is covered mainly by package-level component specs and the settings language-switch scenario; browser e2e no longer asserts zh copy.
@@ -0,0 +1,45 @@
+# Agent Note: client 文案全量接入 typed locale 席位与不翻译边界
+
+Status: implemented
+
+[English](2026-07-30-client-locale-full-rollout.md) | 中文
+
+## Problem
+
+typed locale 标准席位（`locale:` 注册声明 → 框架注入强类型 `t`）落地后，只有四个先行包接入；其余 client 包的文案仍是硬编码的中英混杂字面量。全量迁移需要几个先行包没有触及的机制与边界决定：注册期文本（导航行、视图 tab 的 label）在语言切换时如何刷新；zero-cordis 的 ui-primitives 原子组件如何拿到文案；哪些字符串**刻意不**本地化——没有记录的边界会诱使后来者"补完"翻译。
+
+## Decision
+
+**注册期文本走 label thunk。** ui-slots 的 list 注册项 `label` 接受 `SlotLabel = string | (() => string)`；owner 投影 ledger 行时必须经 `resolveSlotLabel` 解析（不裸读 `options.label`），并让读取点跟随 locale revision（outlet 自身订阅 revision；ledger 外的投影如 ui-settings 导航把 revision 并进缓存键、订阅双源）。thunk 每次读取时求值，语言切换零 ledger churn——没有重注册、version 不动，`locale/change` 重注册接线全部删除。
+
+**组件文案走标准 `t` 席位；深层子组件用 prop 下传**，类型写 `XxxProps['t']`。字典规范形态不变：`zh satisfies Record<string, string>` 为 key 源、`en satisfies Record<XxxKey, string>` 锁双语平衡。
+
+**zero-cordis 原子组件（ui-primitives）文案 props 化**：`TerminalBlock`/`JsonTree` 的 `labels`、`CodeBlock` 的 `copyLabel`/`copiedLabel`、`MarkdownText` 的 `codeLabels`、`JsonBlock` 的 `truncatedLabel`、`ConnectionBanner` 的 `label`、`Modal` 的 `closeLabel`——默认值即原硬编码字符串，不传 props 的消费者渲染逐字节不变。已本地化的插件从自己的 `t` 席位传字典驱动的 label；传对象 props 的调用点按 `t` 身份 memo（`MarkdownText` 的组件表按 `codeLabels` 身份缓存）。
+
+**不翻译边界（刻意决定，不是欠账）：**
+
+- **错误/失败类字符串一律英文**：client 自产的兜底串（`command failed`、plan 切换失败）、RpcError message、wire 透出的 `error.message (code)` 原样呈现。
+- **设计字面量不进字典**：tool 行 variant 标题（Think/Bash/…）、SYSTEM/USER 类 kind 徽标、Plan chip 字标、StatsLine 全部指标——中英界面显示一致。
+- **ui-trajectory 整包缓做**（开发者检查面，术语密集，单独裁决）。
+- **boot 文案保持硬编码**（AppRoot 渲染早于 locale 服务可用）。
+
+**派生层保持纯函数，本地化只在渲染层**：ui-workspace 的 `relativeTime` 返回结构化 `{unit, n}` 由渲染组合字典模板；blank 会话/未分组桶的存储标题不变，渲染按 `blank` 标志/`workspaceId` 缺席替换本地化文案；**搜索态 blank 行一律排除**（双语标题无法与单语查询稳定匹配）。日期不引 Intl：格式模板进字典（消息时钟 `clock.md`/`clock.ymd`，workspace hover `date.ymd`），格式化函数吃 `t` 参数保持纯。
+
+**测试与 e2e 口径**：`makeTranslate(...dicts)`（dsh-client-test-runtime）镜像服务查找链（首个命中字典胜出、key 兜底、`{name}` 插值），组件测试的 `t` 桩统一用它并以真实 props 席位定型。web e2e 统一 `newEnglishPage`（boot 前钉 `dsh.locale=en`），built-boot snapshot 同样钉 en——golden 对语言迁移免疫；settings 语言切换用例刻意绕开该 helper 覆盖 zh 默认态。
+
+[settings/locale/theme 分层 Note](../../proposed/architecture/2026-07-25-client-settings-locale-theme.md) 中"apply 层订阅 `locale/change` 重注册刷新 label"的机制已被本决定取代（thunk + revision 生命周期）。
+
+## Alternatives considered
+
+- **label 保持 string、语言切换时重注册**（先行包的旧形态）：boot 每包一次注册已很重，`locale/change` 监听者重注册会放大成风暴；ledger version 抖动还会击穿一切按 version 缓存的投影。thunk 把刷新成本移到读取点，读取点本来就跟随 revision。
+- **给 ui-primitives 造 locale context/注入通道**：破坏 zero-cordis 边界（原子组件从此依赖运行时），且强迫未本地化消费者（ui-trajectory）陪跑。props 化让每个消费者独立决定。
+- **错误串进字典**：错误面是排障面，英文原样最利于搜索与上报比对；且 wire 透出串本就不可译，半译反而制造混合语言。
+- **日期用 `toLocaleString()`/Intl**：跟随浏览器/OS 语言而非应用语言，切换后必然产生混合文本；字典模板量小且与消息时钟同构。
+- **blank 行参与搜索（匹配本地化标题或存储标题）**：任一选择都在某个语言下"看得见搜不到"；占位行本无信息量，整体排除语义最稳。
+
+## Consequences
+
+- 语言切换全 UI 即时刷新且零重注册；新包接入 = 字典 + declare-merge + `locale: NS` 三步，无手写胶水。
+- 代价：list label 的消费方必须知道 `resolveSlotLabel`（裸读 `options.label` 拿到函数）；类型上 `SlotLabel` 已挡住多数误用。
+- ui-primitives 的中文默认值在英文语言下依旧是中文，**直到消费点传 label**——未迁移包（ui-trajectory 的 JsonTree）显示英文默认恰好符合其整包英文现状。
+- e2e 英文钉死意味着 zh 默认态主要靠包级组件测试与 settings 语言切换用例覆盖，浏览器 e2e 不再验证 zh 文案。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-30-settings-write-path-integrity.md
-2026-07-30-settings-write-path-integrity.md: 07bd095162879c8e7866846cf562f6a13307e5fc
-2026-07-30-settings-write-path-integrity.zh.md: 5d02177073d482b61750d7bdfbbd0866bc227a6a
+2026-07-30-settings-write-path-integrity.md: 7bd50adc8a812759c3ae3f80a50978d75baa712a
+2026-07-30-settings-write-path-integrity.zh.md: da07745ef1de1b694fc3fd1ee3d04322cdadc992
@@ -14,7 +14,7 @@ Review found the provider's write path could destroy state it never observed, an

 **One operation chain, and every write is a read-modify-write.** Watcher refreshes and persists from every namespace queue share a single settled chain, and `persistSection` begins by reconciling the on-disk text into the seam — publishing any unobserved difference first — before rendering against that fresh text. A write can no longer resurrect a stale document, and an on-disk document that turned invalid fails the write loud rather than being overwritten (the reload path keeps its warn-and-keep-last-good policy; the shared `reconcileFromDisk` throws and each caller picks its policy). The watcher's `ready` signal queues one extra reconcile, closing the startup gap between the initial load and the watcher becoming active.

-**Writes hold a `wx`-created `<file>.lock` sibling.** The read-render-rename cycle runs under a cross-process writer lock with exponential backoff, a 2 s acquisition deadline, and stale takeover after 5 s (a crashed holder, broken with a warning). Readers never lock — the rename commit is atomic — so contention is writer-only and resolves in milliseconds. The lock constants are protocol invariants, not config: a holder rewrites one small document, so the deadline and stale age derive from that bound, not from deployment taste.
+**Writes hold a `wx`-created `<file>.lock` sibling.** The read-render-rename cycle runs under a cross-process writer lock with exponential backoff and a 2 s acquisition deadline. A contender times out without removing the existing lock because age cannot distinguish a crashed owner from a paused live writer; orphan recovery is an operator action. Readers never lock — the rename commit is atomic — so contention is writer-only. The retry and deadline constants are protocol invariants, not deployment config.

 **Observer disposal is quiescent.** Watchers carry an `active` flag checked when a queued invocation would start, so a disposer that ran while the invocation waited prevents the start entirely; started invocations register in a service-level `pendingTails` set that the dispose drain awaits beside the write queues. The `settings/updated` fan-out contains a returned thenable's rejection through the same listener diagnostic as a sync throw, and the event contract now states that the `INVARIANT` rethrow serves synchronous listeners only — invariant companions must stay sync, which the shipped companion already is.

@@ -24,7 +24,7 @@ Review found the provider's write path could destroy state it never observed, an

 ## Alternatives considered

- **`proper-lockfile` instead of a hand-rolled lock** — the dependency-over-hand-rolling policy was weighed: the library is barely maintained, its stale/retry policy is broader than this one-file protocol needs, and the shipped lock is ~40 lines with deterministic tests (including injected `EEXIST`/`stat` races). The policy favors dependencies that delete owned code; this one would replace 40 explained lines with an opaque peer.
+- **`proper-lockfile` instead of a hand-rolled lock** — the dependency-over-hand-rolling policy was weighed: the library is barely maintained, its ownership and retry policy is broader than this one-file protocol needs, and the shipped lock is a small exclusive-create loop with deterministic contention tests. The policy favors dependencies that delete owned code; this one would replace a narrow protocol with an opaque peer.
 - **Revision/CAS instead of a lock** — rename cannot express compare-and-swap, so a CAS needs a version sidecar or content re-hash and a retry loop in every writer; the lock achieves the same serialization with one primitive and keeps readers free.
 - **Merging external edits into the in-flight write's own section** — the seam merges patches over the state visible at call time, so a same-namespace external edit racing a write still resolves last-write-wins; folding it in would need three-way merge semantics no consumer has asked for. The write publishes the external state first, so the loser is at least observed before being superseded.
 - **Declaring async `settings/updated` listeners unsupported** — the typed signature is `void` and lint flags misused promises, but an unlinted JS plugin can still register an async listener; a contract note cannot un-throw an unhandled rejection, so containment is the only defense that holds at runtime.
@@ -32,4 +32,4 @@ Review found the provider's write path could destroy state it never observed, an

 ## Consequences

-`update()` gained a documented failure mode (lock deadline, invalid on-disk document) and the rejection messages carry `$`-rooted paths. Remaining, documented in the provider README: same-namespace concurrent edits stay last-write-wins (no per-value merge or revision check), a watcher event the OS never delivers leaves the cache stale until the next signal or write, and comments inside replaced arrays or attached inline to changed scalar values go with the value they described. The [user-settings seam note](2026-07-28-user-settings-seam.md)'s deferred-lockfile alternative is superseded by this note. The same defect classes exist in `dsh-credentials-local` (two chains over one `.env`, cached whole-file write-back, post-persist emit) and in the `llm/adapters-updated` fan-out on the stacked branches; those fixes belong to the PRs that introduce the packages and follow this template on merge-up.
+`update()` has documented failure modes for the lock deadline and an invalid on-disk document, and rejection messages carry `$`-rooted paths. A crashed holder can leave a lock that requires verified operator removal; automatic age-based takeover would permit overlapping writers. Remaining, documented in the provider README: same-namespace concurrent edits stay last-write-wins (no per-value merge or revision check), a watcher event the OS never delivers leaves the cache stale until the next signal or write, and comments inside replaced arrays or attached inline to changed scalar values go with the value they described. The [user-settings seam note](2026-07-28-user-settings-seam.md)'s deferred-lockfile alternative is superseded by this note. The same defect classes exist in `dsh-credentials-local` (two chains over one `.env`, cached whole-file write-back, post-persist emit) and in the `llm/adapters-updated` fan-out on the stacked branches; those fixes belong to the PRs that introduce the packages and follow this template on merge-up.
@@ -18,7 +18,7 @@ YAML 写入则整体替换 namespace 节点，把分节内的每条注释都删

 **单一操作链，且每次写入都是读-改-写。**watcher 的刷新与来自各 namespace 队列的持久化共享同一条结算链；`persistSection` 会先把磁盘上的文本对账进 seam——任何未被观察到的差异都先发布出去——然后才对照这份新鲜文本渲染。写入不再可能复活一份陈旧文档；磁盘上已变非法的文档会让写入响亮失败，而不是被覆盖（重载路径保持其“告警并保留最后可用值”策略；共享的 `reconcileFromDisk` 抛错，各调用方自选策略）。watcher 的 `ready` 信号会额外排入一次对账，弥合初始加载与 watcher 生效之间的启动缺口。

-**写入持有以 `wx` 创建的同目录 `<file>.lock`。**读-渲染-rename 循环在一把跨进程写锁下运行：指数退避、2 s 获取截止时间、5 s 后陈旧接管（持有者已崩溃；打破旧锁时给出告警）。读方从不加锁——rename 提交是原子的——因此竞争只发生在写方之间，毫秒级即可化解。锁的各项常量是协议不变式，不是配置：持有者只是重写一份小文档，截止时间与陈旧时限都从这一上界推得，而非出自部署偏好。
+**写入持有以 `wx` 创建的同目录 `<file>.lock`。**读-渲染-rename 循环在一把跨进程写锁下运行，采用指数退避与 2 s 获取期限。竞争者会超时，但不会移除现有锁，因为锁龄无法区分已经崩溃的所有者与被暂停但仍存活的写入方；遗留锁恢复须由操作者执行。读方从不加锁——rename 提交是原子的——因此竞争只发生在写方之间。重试与期限常量是协议不变式，而非部署配置。

 **观察者 dispose 达到完全停稳。**watcher 携带一个 `active` 标志，排队的调用即将启动时先检查它，因此在调用等待期间已经运行过的释放器能让这次启动彻底不发生；已启动的调用会登记进服务级的 `pendingTails` 集合，dispose 排空除了等待各写队列，还会等待该集合。`settings/updated` 扇出会把监听器返回的 thenable 的 rejection 收容进与同步抛错相同的监听器诊断；事件契约现已写明 `INVARIANT` 重抛只服务同步监听器——不变式配套插件必须保持同步，而已交付的那个配套插件本就是同步的。

@@ -28,7 +28,7 @@ YAML 写入则整体替换 namespace 节点，把分节内的每条注释都删

 ## 曾考虑的替代方案

- **用 `proper-lockfile` 取代手写锁**——按“依赖优先于手写”政策做过权衡：该库几乎无人维护，其陈旧／重试策略比这个单文件协议所需的更宽泛，而已交付的锁约 40 行并带确定性测试（含注入的 `EEXIST`/`stat` 竞态）。该政策偏向能删除自有代码的依赖；这个依赖只会把 40 行带解释的代码换成一个不透明的等价物。
+- **用 `proper-lockfile` 取代手写锁**——按“依赖优先于手写”政策做过权衡：该库几乎无人维护，其所有权与重试策略比这个单文件协议所需的更宽泛，而已交付的锁只是一个小型独占创建循环，带确定性的竞争测试。该政策偏向能删除自有代码的依赖；这个依赖只会把一个窄协议换成不透明的等价物。
 - **用修订号/CAS 取代锁**——rename 表达不了 compare-and-swap，因此 CAS 需要一个版本伴随文件或内容重哈希，外加每个写方里的一个重试循环；锁用一个原语实现同样的串行化，还让读方完全免锁。
 - **把外部编辑合并进正在进行的写入自身的分节**——seam 是在调用时刻可见的状态之上合并 patch 的，因此与写入竞态的同 namespace 外部编辑仍按后写胜出解决；要把外部编辑并进来，需要三方合并语义，而没有任何消费方提出过这种需求。写入会先发布外部状态，落败一方至少在被取代之前被观察到。
 - **宣布不支持异步 `settings/updated` 监听器**——类型签名是 `void`，lint 也会标记误用的 promise，但未经 lint 的 JS 插件仍能注册异步监听器；契约里的一句说明无法收回已经抛出的 unhandled rejection，收容是唯一在运行时守得住的防线。
@@ -36,6 +36,6 @@ YAML 写入则整体替换 namespace 节点，把分节内的每条注释都删

 ## 后果

-`update()` 有了成文的失败模式（锁截止时间到期、磁盘文档非法），rejection 消息携带以 `$` 为根的路径。仍然存在、且已记录在提供方 README 中的有：同 namespace 并发编辑仍是后写胜出（没有逐值合并，也没有修订号检查）；OS 从未投递的 watcher 事件会让缓存保持陈旧，直到下一个信号或下一次写入；被替换数组内部的注释、以及行内附着在被改标量值上的注释，会随其描述的值一起消失。
+`update()` 对锁获取期限与磁盘文档非法都有成文的失败模式，rejection 消息携带以 `$` 为根的路径。持有者崩溃后可能留下锁，需要操作者核实后移除；若按锁龄自动接管，则会允许多个写入方重叠。仍然存在、且已记录在提供方 README 中的有：同 namespace 并发编辑仍是后写胜出（没有逐值合并，也没有修订号检查）；OS 从未投递的 watcher 事件会让缓存保持陈旧，直到下一个信号或下一次写入；被替换数组内部的注释、以及行内附着在被改标量值上的注释，会随其描述的值一起消失。

 [用户设置 seam note](2026-07-28-user-settings-seam.md)里“延后锁文件”那条替代方案已被本 note 取代。同类缺陷还存在于 `dsh-credentials-local`（两条链共用一个 `.env`、按缓存整文件写回、持久化之后才发事件）与堆叠分支上的 `llm/adapters-updated` 扇出；这些修复归引入相应包（package）的那些 PR（Pull Request）所有，向上合并时按本模板处理。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-27-web-session-search.md
+2026-07-27-web-session-search.md: 9a634c586a4793d1c6986a7e7c0b0c1157b5b687
+2026-07-27-web-session-search.zh.md: 5ec2baf7443aaaaa75abc348ee426df9c14fbaa2
@@ -0,0 +1,44 @@
+# Agent Note: Web past-session search
+
+Status: implemented
+
+English | [中文](2026-07-27-web-session-search.zh.md)
+
+## Problem
+
+The Web sidebar exposes session titles and Workspace membership but cannot retrieve a past conversation from words that appear only inside its messages. Scanning histories in the browser would require attaching or loading every session, duplicate the existing indexed-search service, and make cold persisted sessions both slow and easy to omit. The product also needs a predictable failure path: an unavailable derived index must not erase title matches that the client can compute locally.
+
+## Decision
+
+The shared Web/headless composition mounts [`@deepseek-ai/dsh-session-query-sqlite`](../../../../packages/session-query/session-query-sqlite/README.md) with `openAt: first-search` and an in-memory database. The service is ACTIVE at boot, while its `node:sqlite` module and connection-private handle open only on the first content query. This keeps Node 22 startup output free of SQLite's experimental warning before search is used without promising to suppress the warning when search first imports the module. Each service instance owns its index, preserving the SQLite backend's single-owner contract across parallel CLI or Web invocations without leaving process-scoped derived files behind. The database starts empty and lazily reconciles live and persisted sessions on that first query. It remains a disposable derived index, separate from canonical JSONL persistence.
+
+The host gateway exposes `session.search` through the existing typed RPC stack. It derives the authorization set from the same visible summaries as `session.list`, asks `ctx.sessionQuery.searchSessions` for globally ranked current-surface `user/message`, `assistant/message`, and `steering/message` matches, and consumes provider pages until it has 20 authorized sessions plus one lookahead or exhausts the stream. The first provider page requests 20 hits; a first-page `SESSION_QUERY_INVALID_LIMIT` halves that size through 10, 5, 2, and 1, retaining the learned size across continuations and stale-generation restarts. Every hit's session id, best-match session id, surface, and event type are revalidated before its snippet leaves the Host. Emitted snippets contain at most 240 Unicode code points; the Host and wire schema share the protocol bounds and code-point-safe truncation helper, while the wire schema independently enforces the snippet bound at client parse. Keeping the potentially large authorization set out of SQLite bindings avoids the portable variable ceiling while preserving global ranking. The response remains one bounded page; `hasMore` tells the UI to ask for a narrower query rather than exposing pagination. A stale continuation discards the current attempt's partial results, deduplication entries, and cursors, then restarts from the first page against the original visibility snapshot. Limit probes and stale retries share the limit of 100 provider calls (and therefore at most 2,000 inspected hits); a page larger than its requested limit, a repeated continuation cursor, or a still-unexhausted stream at that call budget fails closed as an `internal` business error. The carrier signal cancels superseded work, including persistence listing, bounded batches of cold-session metadata stats, and each provider call, and wins over a concurrent limit or stale rejection. A missing query service or an unrecovered indexing/query failure remains a business error and does not mutate the canonical session store.
+
+[`WorkspaceBrowser`](../../../../packages/client/ui-workspace/README.md) keeps metadata and content search deliberately separate. Its default copy is English, and its input plus defensive request path remove NUL and cap queries at the request schema's 500 UTF-16 code units without splitting a surrogate pair. A non-blank query immediately computes case-insensitive title and Workspace substring matches from the Session list, starts a 250 ms debounced content request, aborts the preceding request when the query changes, and ignores stale completions. It merges local matches first in recency order with backend-ranked content-only matches, deduplicates by session id, and renders a flat list regardless of the normal grouping mode. Each row shows the title, Workspace, and an available one-line snippet. Selecting a row opens the Session only and preserves the query; it does not navigate to an exact event.
+
+The result bound is one protocol constant, not per-connection state. `SESSION_SEARCH_RESULT_LIMIT` lives beside the response schema that enforces it in `dsh-host-apiproxy`, and `SessionsService.searchResultLimit` re-exposes that constant for presentation plugins. Reaching it from a feature is an explicit widening of the sessions domain: `ISessions` — the face injected as `ctx.sessions`, and therefore what the test runtime's sessions double must implement — declares the search verb next to that bound. The connection handle does not carry it: a per-connection field would imply a transport-varying or server-negotiated bound that the schema's fixed `max` forbids, and would leave the same fact with two homes in the same module.
+
+Content matching inherits the SQLite backend's normalized literal token/phrase semantics. The shared semantic projection excludes reasoning blocks, so UI search never returns a model's private reasoning as a hit or snippet; the derived-index schema version advances so existing persistent indexes rebuild without the former documents. FTS5 operators are inert data, and this surface adds no typo, fuzzy, prefix, or arbitrary-substring expansion. In particular, the `unicode61` tokenizer may treat an uninterrupted Chinese sequence as one token, so a shorter query such as `搜索` is not guaranteed to match inside `会话搜索功能`. Title and Workspace matching remains ordinary client-side substring matching.
+
+## Failure and visibility contract
+
+Search never widens session visibility: cold sessions without a servable cwd are absent for the same reason they are absent from `session.list`, and only provider hits whose ids occur in that baseline can leave the Host. Shadowed and log-only events, tool events outside message content, errors, todos, and other trace records do not produce UI hits.
+
+While the first or a later content request is pending, the UI keeps immediate metadata matches and shows a history-search status. If the backend fails, the same rows remain and a warning explains that content search is unavailable. Zero merged rows produce an explicit empty state. More than 20 candidate rows produce a refine-query hint.
+
+## Alternatives considered
+
+- **Scan every session history in the browser** — rejected because it attaches transport and fold cost to the UI, misses cold logs unless they are loaded, and duplicates the semantic extraction and source reconciliation already owned by `ctx.sessionQuery`.
+- **Make trigram or fuzzy search part of the first release** — rejected because it changes index size, ranking, short-query behavior, and product expectations. Trigrams also do not by themselves solve two-character queries. The first release uses the existing backend contract and leaves recall expansion as a separate measured decision.
+- **Return event addresses and jump to the exact match** — rejected for this release because conversation virtualization and stable event navigation need a separate UI contract. Session-level navigation is useful without coupling search to that work.
+- **Expose cursor pagination in the sidebar** — rejected in favor of a fixed top-20 surface and a narrow-query hint; this keeps the interaction and cancellation state bounded.
+
+## Consequences
+
+Past persisted conversations become discoverable without opening them first, while the host retains one visibility boundary and one semantic-index implementation. Immediate local results hide most request latency, cancellation prevents obsolete queries from repainting the list, and backend failure degrades to the behavior available before content search.
+
+The first content query can take longer because it imports and opens SQLite before paying lazy reconciliation. Search quality is token/phrase recall rather than fuzzy or arbitrary substring recall, including the documented continuous-Chinese limitation. Results are session-level, capped at 20, and have no paging or exact-message navigation. A valid but pathologically unselective or repeatedly stale provider attempt that does not complete within 100 calls takes the metadata-only failure path instead of consuming unbounded work.
+
+## Testing
+
+Host tests pin request and response validation, visible-session filtering, event/surface filters, result and snippet bounds, adaptive provider limits inside the shared call budget, learned-limit stale restarts, cursor and cross-page deduplication behavior, cancellation precedence, and failure mapping. SQLite lifecycle tests pin eager activation, first-search opening and failure, shared readiness, and unopened disposal; semantic extraction and SQLite/fixture search tests pin exclusion of reasoning-only text. The Node 22 compatibility gate builds the CLI and Web artifacts, boots the shipped `dsh web`/`AppCLIEntry` composition under plain Node with ambient warning suppression removed and an isolated temporary home/provider environment, waits for settled startup, and disposes it through the shipped signal path. Fixture, runtime, and UI tests pin match-centered bounded snippets, stateless delegation, the 500-code-unit query boundary, debounce/abort/stale-response behavior, local fallback, merge order, deduplication, English copy, ARIA tree membership, row rendering, and navigation semantics. A keyless assembled Web test preserves the lazy-open config while seeding an unopened persisted conversation, finds it by visible message content through the SQLite index, captures the sidebar result, opens it, and verifies that the query remains.
@@ -0,0 +1,44 @@
+# Agent Note: Web 历史会话搜索
+
+Status: implemented
+
+[English](2026-07-27-web-session-search.md) | 中文
+
+## 问题
+
+Web 侧边栏会展示会话标题及其 Workspace 归属，但无法根据只出现在消息中的词语检索历史对话。在浏览器中扫描历史记录，需要附加或加载每个会话，重复实现现有的索引搜索服务，也会让冷态持久化会话的检索既缓慢又容易遗漏。产品还需要一条可预测的故障路径：派生索引不可用时，不得抹去客户端能够在本地计算出的标题匹配结果。
+
+## 决策
+
+Web 与 headless 共用的组合会使用 `openAt: first-search` 和内存数据库挂载 [`@deepseek-ai/dsh-session-query-sqlite`](../../../../packages/session-query/session-query-sqlite/README.md)。服务启动时处于 ACTIVE 状态，而其 `node:sqlite` 模块与连接私有句柄分别要到首次内容查询才会导入和打开。这让 Node 22 的启动输出在使用搜索前不会出现 SQLite 实验性警告，但并不承诺在首次搜索导入该模块时抑制警告。每个服务实例都独占自己的索引，因此并行 CLI 或 Web 调用可维持 SQLite 后端的单一所有者契约，又不会留下进程级派生文件。数据库从空状态启动，并在该首次查询时惰性对齐实时会话与持久化会话。它仍是与规范 JSONL 持久化相互独立的可丢弃派生索引。
+
+宿主网关通过现有的类型化 RPC 栈公开 `session.search`。它根据 `session.list` 使用的同一组可见摘要推导授权集合，向 `ctx.sessionQuery.searchSessions` 请求全局排序后的当前 surface `user/message`、`assistant/message` 和 `steering/message` 匹配项，并持续消费提供方分页，直到获得 20 个已授权会话及一个前瞻项，或结果流耗尽。首个提供方页面请求 20 个命中；如果第一页返回 `SESSION_QUERY_INVALID_LIMIT`，页面大小会依次折半为 10、5、2、1，并在续传和陈旧世代重启中沿用探测所得的大小。每个命中的会话 id、最佳匹配会话 id、surface 和事件类型都会经过重新校验，其 snippet 才能离开宿主。发出的 snippet 最多包含 240 个 Unicode 码点；宿主与传输 schema 共用协议边界及码点安全的截断辅助函数，而传输 schema 会在客户端解析时独立强制执行 snippet 上限。将可能很大的授权集合排除在 SQLite 绑定之外，可避开可移植变量上限，同时保持全局排序。响应仍只有一个有界页面；`hasMore` 会指示 UI 提示用户缩小查询范围，而不是公开分页能力。陈旧的续传会丢弃当前尝试的部分结果、去重条目和游标，然后依据原始可见性快照从第一页重新开始。上限探测与陈旧重试共用 100 次提供方调用的限制（因此最多检查 2,000 个命中）；如果某页命中数超过其请求的上限、续传游标重复，或用尽该调用预算后结果流仍未耗尽，都会直接返回 `internal` 业务错误，不返回部分结果。载体信号会取消已被取代的工作，包括持久化列表枚举、分批受限执行的冷会话元数据 stat，以及每一次提供方调用；即使同时收到上限拒绝或陈旧拒绝，也以取消为准。查询服务缺失或索引／查询故障无法恢复时，仍作为业务错误处理，不会修改规范会话存储。
+
+[`WorkspaceBrowser`](../../../../packages/client/ui-workspace/README.md) 有意将元数据搜索与内容搜索保持独立。其默认界面文案为英文；输入框及防御性请求路径会移除 NUL，将查询限制在请求 schema 规定的 500 个 UTF-16 code unit 内且不会拆分 surrogate pair。非空白查询会立即从会话列表中计算不区分大小写的标题和 Workspace 子串匹配，在 250 ms 防抖后发起内容请求，在查询变化时中止前一请求，并忽略陈旧的完成结果。它先按新近程度排列本地匹配，再合并由后端排序且仅匹配内容的结果，按会话 id 去重；无论常规分组模式如何，最终都渲染为扁平列表。每一行显示标题、Workspace，并在存在时显示一行摘要片段。选择某一行只会打开对应会话，并保留查询条件；不会跳转至确切事件。
+
+结果上限是单一协议常量，而非逐连接状态。`SESSION_SEARCH_RESULT_LIMIT` 位于 `dsh-host-apiproxy` 中强制执行它的响应 schema 旁边，`SessionsService.searchResultLimit` 则把该常量重新公开给呈现插件。功能包要取用它，必须显式扩展 sessions 域的对外面：`ISessions`（即注入为 `ctx.sessions` 的那个面，也因此是测试运行时的 sessions 替身必须实现的面）在该上限旁声明了搜索动作。连接 handle 不携带它：逐连接字段会暗示该上限随传输层变化或由服务端协商，而 schema 固定的 `max` 恰恰禁止这一点，并且会让同一事实在同一模块内拥有两处归属。
+
+内容匹配沿用 SQLite 后端经过规范化的字面 token／短语语义。共享语义投影会排除推理（reasoning）块，因此 UI 搜索绝不会将模型的私有推理作为命中或 snippet 返回；派生索引的 schema 版本会随之前进，使现有持久化索引重建并移除先前的这些文档。FTS5 运算符只作为数据处理，此搜索界面不提供拼写错误纠正、模糊匹配、前缀匹配或任意子串扩展。特别是，`unicode61` 分词器可能将一段连续中文视作单个 token，因此不保证 `搜索` 之类的较短查询能匹配 `会话搜索功能` 的内部片段。标题与 Workspace 匹配仍采用普通的客户端子串匹配。
+
+## 故障与可见性契约
+
+搜索绝不会扩大会话可见范围：没有可供服务的 cwd 的冷会话会被排除，原因与它们不出现在 `session.list` 中相同；只有 id 位于这条基线中的提供方命中才能离开宿主。被遮蔽事件和纯日志事件、消息内容之外的工具事件、错误、待办事项及其他追踪记录都不会产生 UI 命中结果。
+
+首个或后续内容请求仍在处理期间，UI 会保留即时元数据匹配结果，并显示历史搜索状态。如果后端失败，这些行会保持不变，并显示警告说明内容搜索不可用。合并后没有任何行时，界面会显示明确的空状态。候选行超过 20 条时，界面会提示用户缩小查询范围。
+
+## 曾考虑的替代方案
+
+- **在浏览器中扫描每个会话的历史记录**：不予采纳，因为这会让 UI 承担传输与折叠开销；除非加载冷态日志，否则还会漏掉这些日志；并会重复实现已经由 `ctx.sessionQuery` 负责的语义提取与源对齐。
+- **首版即加入 trigram 或模糊搜索**：不予采纳，因为这会改变索引大小、排序、短查询行为与产品预期。trigram 本身也无法解决双字查询。首版沿用现有后端契约，将召回扩展留作另一项基于度量结果的决策。
+- **返回事件地址并跳转至确切匹配位置**：本版不予采纳，因为对话虚拟化与稳定的事件导航需要单独的 UI 契约。会话级导航本身已有价值，无需让搜索与这项工作耦合。
+- **在侧边栏公开游标分页**：不予采纳，改为固定显示前 20 条结果并提示缩小查询范围；这样可使交互与取消状态保持有界。
+
+## 后果
+
+无需预先打开，即可检索到历史持久化对话，同时宿主仍只保留一条可见性边界和一套语义索引实现。即时本地结果掩盖了大部分请求延迟，取消机制可防止已作废查询重新渲染列表，后端故障则会降级为内容搜索尚不可用时已有的行为。
+
+首次内容查询可能耗时更长，因为它要先导入并打开 SQLite，再承担惰性对齐的开销。搜索质量采用 token／短语召回，而不是模糊召回或任意子串召回，并受上述连续中文限制。结果粒度为会话，最多 20 条，不支持分页，也不能跳转到具体消息。如果有效但选择性极差或反复陈旧的提供方尝试未能在 100 次调用内完成，系统会进入仅保留元数据匹配的故障路径，而不是无限制地继续处理。
+
+## 测试
+
+宿主测试将请求与响应校验、可见会话过滤、事件和 surface 过滤、结果与 snippet 边界、共享调用预算内的自适应提供方上限、沿用探测所得上限的陈旧世代重启、游标与跨页去重行为、取消优先级及故障映射固定为契约。SQLite 生命周期测试将启动时激活、首次搜索时的打开与失败、共享就绪状态以及未打开状态下的处置固定为契约；语义提取测试与 SQLite／fixture 搜索测试将排除仅存在于推理中的文本固定为契约。Node 22 兼容性门禁会构建 CLI 与 Web 产物，在移除环境级警告抑制并采用隔离的临时 home／提供方环境后，以普通 Node 启动随产品交付的 `dsh web`／`AppCLIEntry` 组合，等待启动完成并稳定，再沿随产品交付的信号路径对其执行 dispose（资源释放）。fixture（测试前置数据）、运行时与 UI 测试将以匹配位置为中心的有界 snippet、无状态委托、500 个 code unit 的查询边界、防抖／中止／陈旧响应行为、本地回退、合并顺序、去重、英文文案、ARIA 树成员关系、行渲染与导航语义固定为契约。无密钥的组装层 Web 测试会在保留惰性打开配置的同时，播种一段尚未打开的持久化对话，通过 SQLite 索引按可见消息内容找到它，捕获侧边栏结果，打开该会话，并验证查询条件仍然保留。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.md
-2026-07-28-sdk-max-output-tokens.md: 5db48f21892d56addea7b72f73319f9dbfd1e71f
-2026-07-28-sdk-max-output-tokens.zh.md: 38b172718716d100726188163ff22be9ea0a7325
+2026-07-28-sdk-max-output-tokens.md: 3ba3e226d64b7d3d192d67bd88af463d2b0d9dc5
+2026-07-28-sdk-max-output-tokens.zh.md: aec566011d2d7a311b4de509c47ebba383c3b0d7
@@ -12,7 +12,7 @@ The Python and TypeScript SDKs could select a provider and model but could not b

 The high-level SDKs expose one optional process-wide output cap: Python names it `max_tokens`, TypeScript names it `maxTokens`, and the shared `initialize` wire payload carries `maxTokens`. The JSON-RPC server rejects values that are not positive safe integers and stores the accepted cap with its provider/model route.

-Each SDK-created root Agent receives the cap through `AgentOptions.maxTokens`. Agent Loop places that value in the initial `LlmCallConfig`, logs it in the request header, and reconstructs every dispatched conversation request from that durable header. Omitting the option leaves `maxTokens` absent so the selected provider retains its default.
+Each SDK-created root Agent receives the cap through `AgentOptions.maxTokens`. Agent Loop places that value in the initial `LlmCallConfig`; final call preparation preserves the explicit value or materializes an exact-model adapter default, logs the effective cap in the request header, and reconstructs every dispatched conversation request from that durable header. Omitting the SDK option therefore allows the selected adapter or provider route default to apply.

 In-process subagents inherit the parent's provider, model, and output cap. An explicit `SubagentStartRequest.agentOptions.maxTokens`, including one configured by `dsh-tool-subagent`, overrides the inherited value for that child and its descendants. Out-of-process providers own the configuration of their separate runtime; `subagent-dsh-sdk` therefore exposes its own optional `maxTokens` and forwards it through that child runtime's SDK handshake.

@@ -20,7 +20,7 @@ Compaction, session-title generation, web search, and other auxiliary calls keep

 ## Alternatives considered

-**Set an adapter environment variable.** This would be DeepSeek-adapter-specific, invisible in the session request header, ineffective for intercepted or alternate adapters, and easy to confuse with a provider default. The cap belongs in provider-neutral request configuration.
+**Set only an adapter environment variable.** A serializer-private fallback would be DeepSeek-adapter-specific, invisible in the session request header, ineffective for intercepted or alternate adapters, and easy to confuse with a provider default. Adapter-owned defaults may instead be exposed as exact-model metadata and materialized into provider-neutral request configuration before logging.

 **Add `maxTokens` to every `session/prompt`.** Per-turn mutation would enlarge the wire and introduce request-config transitions that callers do not need for the current evaluation use case. A runtime initialization option gives every session in one SDK process the same reproducible budget.

@@ -12,7 +12,7 @@ Python 与 TypeScript SDK 可以选择提供方和模型，却无法限制对话

 高层 SDK 公开一个可选的进程级输出上限：Python 命名为 `max_tokens`，TypeScript 命名为 `maxTokens`，共享的 `initialize` 线载荷使用 `maxTokens`。JSON-RPC 服务端拒绝非正安全整数，并将通过校验的上限与提供方／模型路由一同保存。

-每个由 SDK 创建的根 Agent 都通过 `AgentOptions.maxTokens` 获得该上限。Agent Loop 将它放入初始 `LlmCallConfig`、记录到请求 header，并从该持久化 header 重建每次分派的对话请求。省略该选项时，`maxTokens` 保持缺失，由所选提供方保留默认值。
+每个由 SDK 创建的根 Agent 都通过 `AgentOptions.maxTokens` 获得该上限。Agent Loop 将它放入初始 `LlmCallConfig`；最终调用准备会保留显式值，或填入确切模型的适配器默认值，再将生效上限记录到请求 header，并从该持久化 header 重建每次分派的对话请求。因此，省略 SDK 选项时会应用所选适配器或提供方路由的默认值。

 进程内 subagent 继承父级的提供方、模型和输出上限。显式的 `SubagentStartRequest.agentOptions.maxTokens`（包括通过 `dsh-tool-subagent` 配置的值）会覆盖该子级及其后代的继承值。进程外提供方自行持有其独立运行时的配置；因此 `subagent-dsh-sdk` 公开独立的可选 `maxTokens`，并通过该子运行时自己的 SDK 握手传入。

@@ -20,7 +20,7 @@ Python 与 TypeScript SDK 可以选择提供方和模型，却无法限制对话

 ## Alternatives considered

-**设置适配器环境变量。** 这种方式仅适用于 DeepSeek 适配器，不会出现在会话请求 header 中，对被拦截请求或其他适配器无效，也容易与提供方默认值混淆。该上限属于提供方无关的请求配置。
+**仅设置适配器环境变量。** 序列化器私有回退仅适用于 DeepSeek 适配器，不会出现在会话请求 header 中，对被拦截请求或其他适配器无效，也容易与提供方默认值混淆。适配器持有的默认值可以改为通过确切模型元数据公开，并在记录前填入提供方无关的请求配置。

 **在每个 `session/prompt` 上增加 `maxTokens`。** 按轮次修改会扩大线协议，并引入当前评测用例不需要的请求配置转换。运行时初始化选项可让一个 SDK 进程中的每个会话拥有相同、可重现的预算。

@@ -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-web-message-icon-actions-and-clock.md
-2026-07-29-web-message-icon-actions-and-clock.md: ccc9b127d2fcf276fa415ec0ede8b062e45f3df5
-2026-07-29-web-message-icon-actions-and-clock.zh.md: fb4b82a22478b2de38755368ec48a5dca420e79d
+2026-07-29-web-message-icon-actions-and-clock.md: f43f7f9c9687e4494993d7e225d11cf6446a9954
+2026-07-29-web-message-icon-actions-and-clock.zh.md: 866fae79f6ad3ea2cb80e5443d2cf5f763562d29
@@ -10,9 +10,9 @@ The web chat user bubble already had copy / branch / edit IconActions but no clo

 ## Decision

-**User bubbles prepend a date-aware local clock to the existing IconActions row; finalized assistant *content* nodes (non-empty text blocks) append a copy / branch / clock row with `margin-top: 16px`; both seats stay visible whenever mounted and re-format at the next local midnight.**
+**User bubbles prepend a date-aware local clock to the existing IconActions row; the last content-text assistant of each turn appends a copy / branch / clock row with `margin-top: 16px`; both seats stay visible whenever mounted and re-format at the next local midnight.**

-Both seats format `node.time` through `formatMessageClock`: same calendar day → `HH:mm`, earlier this year → `M月D日 HH:mm`, other years → `YYYY年M月D日 HH:mm`. `useCalendarDay` is a component-local day tick (timeout to the next local midnight) so memoized rows re-render when the calendar day changes without a new framework hook. `MessageItem` places the label before copy (figma `388:20051`). `AssistantMarkdown` places it after branch (figma `43:32997`) only when `streaming` is false, the event time is known, and the node has non-empty text content; Think-only nodes and the streaming tail omit the row. Copy writes joined text blocks. Both message rows pass their event's `seq` to the same fork callback; [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the real mutation contract. Clipboard write and the clock helpers live in `message-chrome.ts`. The assembled surface is pinned by `apps/web/tests/message-actions.e2e.ts` (cold-seeded history + aria golden); aria normalization collapses every clock shape to `{{clock}}`.
+Both seats format `node.time` through `formatMessageClock`: same calendar day → `HH:mm`, earlier this year → `M月D日 HH:mm`, other years → `YYYY年M月D日 HH:mm`. `useCalendarDay` is a component-local day tick (timeout to the next local midnight) so memoized rows re-render when the calendar day changes without a new framework hook. `MessageItem` places the label before copy (figma `388:20051`). `ChatView` derives turn-tail seqs via `assistantActionsSeqs` and withholds `time` for mid-turn content; `AssistantMarkdown` places the row after branch (figma `43:32997`) only when `streaming` is false, the event time is known, and the node has non-empty text content. Think-only nodes, mid-turn narration, and the streaming tail omit the row. Copy writes joined text blocks. Both message rows pass their event's `seq` to the same fork callback; [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the real mutation contract. Clipboard write and the clock helpers live in `message-chrome.ts`. The assembled surface is pinned by `apps/web/tests/message-actions.e2e.ts` (cold-seeded history + aria golden); aria normalization collapses every clock shape to `{{clock}}`.

 ## Alternatives considered

@@ -20,6 +20,8 @@ Both seats format `node.time` through `formatMessageClock`: same calendar day

 **Put IconActions under every finalized assistant node (including Think-only).** Rejected: copy has nothing useful to write without text content, and repeating the chrome under every step/Think row clutters the flow; only content output owns the seat.

+**Put IconActions under every content-text assistant in a multi-step turn.** Rejected: mid-turn narration (text before tools) is not the settled answer; repeating copy/branch/clock under each step clutters the flow. Only the last content assistant of the turn owns the seat.
+
 **Hover-reveal the action row on hover-capable pointers.** Rejected: once the row exists it should stay discoverable; opacity hiding made the chrome easy to miss and required parent hover selectors that duplicated the mount gate.

 **Let the IconActions decision also define session fork semantics.** Rejected: this note owns only message chrome, clocks, and mount gating; boundary selection, failure behavior, and switching semantics belong to the separate [Web session fork actions](2026-07-27-web-session-fork-actions.md), keeping presentation components from becoming a second home for session mutation.
@@ -28,4 +30,4 @@ Both seats format `node.time` through `formatMessageClock`: same calendar day

 ## Consequences

-Settled assistant content answers expose copy, branch, and the event clock as soon as the row mounts; Think-only nodes stay chrome-free. User and assistant clocks share the same day/year widening rules and refresh after midnight without a message mutation. Per-message paging remains a deferred footer seat in the package README. Package tests pin the three clock shapes, the midnight widen, the content-only assistant gate, and the respective event `seq` values passed by the user and assistant branch buttons; the web e2e scenario pins the assembled IconActions chrome.
+Each turn's last settled content answer exposes copy, branch, and the event clock as soon as the row mounts; mid-turn content and Think-only nodes stay chrome-free. User and assistant clocks share the same day/year widening rules and refresh after midnight without a message mutation. Per-message paging remains a deferred footer seat in the package README. Package tests pin the three clock shapes, the midnight widen, the content-only assistant gate, the turn-tail seq gate, and the respective event `seq` values passed by the user and assistant branch buttons; the web e2e scenario pins the assembled IconActions chrome.
@@ -10,9 +10,9 @@ Web 聊天的用户气泡已有复制／分支／编辑 IconActions，但没有

 ## 决策

-**用户气泡在既有 IconActions 行前追加感知日期的本地时钟；已定稿的 assistant *内容*节点（非空 text 块）在正文下追加带 `margin-top: 16px` 的复制／分支／时钟；两边只要挂载就保持可见，并在下一个本地午夜重新格式化。**
+**用户气泡在既有 IconActions 行前追加感知日期的本地时钟；每个轮次中最后一条带 text 内容的 assistant 在正文下追加带 `margin-top: 16px` 的复制／分支／时钟；两边只要挂载就保持可见，并在下一个本地午夜重新格式化。**

-两边都通过 `formatMessageClock` 格式化 `node.time`：同一日历日 → `HH:mm`，同年更早 → `M月D日 HH:mm`，跨年 → `YYYY年M月D日 HH:mm`。`useCalendarDay` 是组件本地的日刻度（定时到下一个本地午夜），因此 memo 行在日历日变化时会重渲染，且不新增框架 hook。`MessageItem` 把标签放在复制之前（figma `388:20051`）。`AssistantMarkdown` 把它放在分支之后（figma `43:32997`），且仅在 `streaming` 为 false、已知事件时间、且节点含非空 text 内容时渲染；纯 Think 节点与流式尾部省略该行。复制写入拼接后的 text 块。两种消息行都把自己的事件 `seq` 交给同一个 fork 回调；真实 mutation 契约由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。剪贴板写入与时钟辅助函数放在 `message-chrome.ts`。组装面由 `apps/web/tests/message-actions.e2e.ts`（冷 seed 历史 + aria golden）钉住；aria 归一化把每种时钟形态折叠为 `{{clock}}`。
+两边都通过 `formatMessageClock` 格式化 `node.time`：同一日历日 → `HH:mm`，同年更早 → `M月D日 HH:mm`，跨年 → `YYYY年M月D日 HH:mm`。`useCalendarDay` 是组件本地的日刻度（定时到下一个本地午夜），因此 memo 行在日历日变化时会重渲染，且不新增框架 hook。`MessageItem` 把标签放在复制之前（figma `388:20051`）。`ChatView` 通过 `assistantActionsSeqs` 推导轮次尾部的 seq，并不为轮次中间的内容传入 `time`；`AssistantMarkdown` 把该行放在分支之后（figma `43:32997`），且仅在 `streaming` 为 false、已知事件时间、且节点含非空 text 内容时渲染。纯 Think 节点、轮次中间的叙述与流式尾部省略该行。复制写入拼接后的 text 块。两种消息行都把自己的事件 `seq` 交给同一个 fork 回调；真实 mutation 契约由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。剪贴板写入与时钟辅助函数放在 `message-chrome.ts`。组装面由 `apps/web/tests/message-actions.e2e.ts`（冷 seed 历史 + aria golden）钉住；aria 归一化把每种时钟形态折叠为 `{{clock}}`。

 ## 曾考虑的方案

@@ -20,6 +20,8 @@ Web 聊天的用户气泡已有复制／分支／编辑 IconActions，但没有

 **给每个已定稿 assistant 节点（含纯 Think）都挂 IconActions。** 否决：没有 text 内容时复制没有可写内容，且在每一步／Think 下重复 chrome 会打乱流程；只有内容输出拥有该座位。

+**给多步骤轮次中的每一条带 text 内容的 assistant 都挂 IconActions。** 否决：轮次中间的叙述（工具调用前的 text）不是已定稿答案；在每一步下重复复制／分支／时钟会打乱流程。只有该轮次中最后一条内容 assistant 拥有该座位。
+
 **在具备 hover 能力的指针上用 hover 才揭示操作行。** 否决：行一旦存在就应保持可发现；用 opacity 隐藏容易漏看，且需要父级 hover 选择器重复挂载门控。

 **由 IconActions 决策同时定义 session fork 语义。** 否决：本笔记只拥有消息 chrome、时钟与挂载门控；边界选择、失败行为和切换语义属于独立的 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)，避免展示组件成为 session mutation 的第二正家。
@@ -28,4 +30,4 @@ Web 聊天的用户气泡已有复制／分支／编辑 IconActions，但没有

 ## 后果

-已定稿的 assistant 内容回答在行挂载后立刻暴露复制、分支与事件时钟；纯 Think 节点不带 chrome。用户与 assistant 时钟共用同一套跨天／跨年加宽规则，并在午夜后无需消息变更即可刷新。逐消息分页仍是包 README 中的暂缓 footer 座位。包级测试钉住三种时钟形态、午夜加宽、assistant 仅内容门控，以及 user/assistant 分支按钮各自传递的事件 `seq`；Web e2e 场景钉住组装后的 IconActions chrome。
+每个轮次中最后一条已定稿的内容回答在行挂载后立刻暴露复制、分支与事件时钟；轮次中间的内容与纯 Think 节点不带 chrome。用户与 assistant 时钟共用同一套跨天／跨年加宽规则，并在午夜后无需消息变更即可刷新。逐消息分页仍是包 README 中的暂缓 footer 座位。包级测试钉住三种时钟形态、午夜加宽、assistant 仅内容门控、轮次尾部 seq 门控，以及 user/assistant 分支按钮各自传递的事件 `seq`；Web e2e 场景钉住组装后的 IconActions chrome。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md
+2026-07-30-web-result-card-frontend.md: d6f4785e83335ca2dd5295516baf47c845ebf5bd
+2026-07-30-web-result-card-frontend.zh.md: ed95cbe39f4f0bf77ba5da64d664705a0841863f
@@ -0,0 +1,49 @@
+# Agent Note: Web result card frontend — rendering the web render intent in the browser
+
+Status: implemented
+
+English | [中文](2026-07-30-web-result-card-frontend.zh.md)
+
+## Problem
+
+The `web_search` and `web_fetch` tools declare a `card: 'web'` result view ([web result card](2026-07-30-web-result-card.md)): a `kind`-tagged union carrying either the structured cited sources plus an optional provider answer (`kind: 'search'`) or the fetched URL and its HTTP status (`kind: 'fetch'`). That view already reaches the browser — host, connection, and runtime deliver it onto `ConversationSnapshot` as `resultView` — but the Web client ignored it: a completed web call rendered only as its flattened model-facing text, the same lossy render the contract note explains the structured view exists to replace. A `web_search` reached the reader as one free-text markdown line per source rather than a citation list of clickable sources, and a `web_fetch` as its markdown body with no retrieval summary.
+
+## Decision
+
+`WebBlock` is a `ui-primitives` component that renders a completed web retrieval, and every Web render site for a web call consumes the `web` render intent through it: the keyed chat tool rows (`web_search`/`web_fetch`), the `GenericToolCard` render-site fallback, and the details panel's Output section. `ui-conversation/src/client/contract/web-card-model.ts` is the single place that turns the snapshot's `resultView` into the component's props, mirroring `terminal-card-model.ts`, so no two sites disagree about what a web call shows. It returns null — the generic path — for a running call (the web card is result-only, since the tools keep a generic pending view), for a settled call whose result view is not a web card including a `card` value this client version does not know (which arrives over the wire and so cannot be trusted to be a compiled variant), for a generic result view (a web tool's error path returns the generic card, whose text the generic path preserves), and for a web card whose `kind` this client version does not know (a newer host's value off the wire, which reading as a fetch would draw as an empty URL and `HTTP undefined`).
+
+One component draws both kinds, discriminated by `kind`. A `search` shows the answer as markdown above a citation list; each source is a safe external link labelled by its title, or its hostname when the provider gave none, with the snippet and publication date below it, and a `来源列表已截断` indicator when the tool capped the list. A `fetch` shows a compact summary: the linked final URL, its HTTP status, and a `内容已截断` indicator. One component rather than two because both are web retrieval rendered as one card family, which is exactly the reason the contract carries them under one `card` tag with a `kind` discriminant.
+
+**Links are safe by the http(s) subset of the allowlist MarkdownText applies to untrusted assistant-authored links** — MarkdownText also permits `mailto:`, deliberately excluded here since a retrieval URL is never a mail address. A source or fetch URL becomes a navigable anchor only when its protocol is `http:` or `https:`, with `target="_blank"` and `rel="noopener noreferrer"`; a `javascript:`/`data:`/`file:`/`mailto:` URL or an unparseable string renders as plain text with no href. The result content a web tool returns is model-authored and reaches this component unverified, so it is treated as untrusted exactly as assistant markdown is. The label falls back from title to hostname to the raw URL, so a source always reads as something even when both the title is absent and the URL does not parse.
+
+**Geometry mirrors CodeBlock/TerminalBlock** (12px radius, code-block surface, 16px vertical margin) so a web card reads as one family with them. A long source list caps at `maxSources` with a head/tail collapse using TerminalBlock's exact split arithmetic (`ceil(max/2)` head lines plus the remaining tail), so a long body's slices agree between the two cards. A source list is prose rather than column-aligned output, so it wraps normally instead of scrolling horizontally the way a terminal card's output does — that is the one deliberate divergence from TerminalBlock.
+
+The card is **resident** under the summary row in the chat rows, capped at `CHAT_WEB_MAX_SOURCES` (8) — half the primitive's own default of 16, which the details panel keeps — the same summary-surface-versus-reading-surface split `CHAT_TERMINAL_MAX_LINES` draws for the terminal card, and the same resident posture `BashRow` uses. The keyed rows register one `WebRow` component under both `web_search` and `web_fetch`; the row discriminates on the tool name only to pick its icon (search vs. browse) and its title (`Search`/`Fetch`). A web-declaring tool without its own keyed row lands on `GenericToolCard`, which grows the same resident card. The details panel renders the card at the primitive's full source allowance and, below it, the flattened model-visible result content: a `web_fetch` card carries only the URL and status, so its fetched body is readable only here.
+
+## Consequences
+
+`WebBlock` reads only the web view's fields, so it stays a pure function of what the render intent carries — no session lookups, replay-safe like the presenters that produce the view, and unlike the terminal card it needs no cwd resolution because a web view carries no path. A UI without the `web` capability (the TUI) still gets the contract's fallback `content`; nothing about the tools' result shape changed. `MarkdownText` is reused for the answer, so the answer's own untrusted-link handling and GFM rendering come for free.
+
+A separate later PR unifies the whole-row collapse/expand interaction and will flip every resident card (terminal, diff, web) to expand-gated at once; this card follows the current resident convention rather than pre-empting that change.
+
+## Alternatives considered
+
+**Two components, one per kind.** Rejected: the two shapes share their card chrome, their safe-link handling, and their truncation indicator, and the contract already expresses their difference as a `kind` discriminant under one `card` tag; two components would duplicate the shared surface and split the safe-link logic.
+
+**Reparse the model-facing render text instead of consuming the structured view.** Rejected for the same reason the contract note gives: `web_search`'s render collapses each source's fields into one free-text line labelled by title OR hostname, so reparsing cannot recover `{url, title?, snippet?, publishedAt?}`. The structured `resultView` is the only faithful source, which is why the backend PR added it.
+
+**Render plain anchors without the protocol allowlist.** Rejected: the URL is model-authored and unverified at this seam, so an unfiltered href would let a `javascript:` URL execute on click. The allowlist is the http(s) subset of MarkdownText's (which also permits `mailto:`), so untrusted retrieval links behave identically wherever they render.
+
+## Testing
+
+`packages/client/ui-primitives/tests/web-block.spec.tsx` pins the component per-file to the 100% gate: both kinds; the title-or-hostname-or-raw-URL label fallback; the safe-link attributes on both kinds (an http(s) URL becoming an external anchor with `target`/`rel`, a `javascript:`/`file:`/unparseable URL rendering as a plain span with no href); the snippet and date shown or omitted on present/empty/absent; the truncation indicator gated on the flag; and the source-list height cap with its head/tail slice and expand/collapse control including the default cap.
+
+`packages/client/ui-conversation/tests/web-card.spec.tsx` mirrors `terminal-card.spec.tsx` at every wiring seam: `webCardModel`'s derivation projecting every source field, its truncation and absent-answer arms, the fetch derivation, and each null arm (running, null result view, generic result view, unknown card tag, unknown web `kind`); the keyed `WebRow`'s resident card for both kinds capped tighter than the panel, its summary-row-alone running and failed arms; the `GenericToolCard` fallback growing the resident card for a web-declaring tool and keeping the plain row for a non-web call; the details panel's Output section for both kinds — including a `web_fetch`'s body flattened below its URL/status card — and its flattened fallback for a non-web result; and the keyed registration under both `web_search` and `web_fetch` with one component. That file sits on the coverage `exclude` list (`ui-conversation/src/*`), so a coverage run measures none of it.
+
+The fixture (`packages/client/connection/src/client/fixture.ts`) adds turns 66 (`web_search`) and 67 (`web_fetch`), authored inline because the client-side fixture cannot import the web tool: turn 66's result view carries an answer and three sources exercising the citation list (a titled source with a snippet and date, a source with no title so its hostname labels the link, and a source with a date but no snippet) with the capped indicator on; turn 67's carries the fetched URL and a 200 status. Both keep a generic pending call view and add the `web` card only at result time, matching the contract's result-only web shape, and are named after the real tools so they hit the keyed `WebRow`. They are ordered before the todo turn (renumbered to 68) for the same reason the terminal turn is: the standing plan retires at the next `turn/start`, so a turn appended after it would empty the dock's plan strip. This drives the built-boot snapshot and a live `?fixture` server.
+
+## Related
+
+- [Web result card](2026-07-30-web-result-card.md) — the backend PR that added the `card: 'web'` result arm and made the two tools emit it; this is its deferred frontend consumer.
+- [Web terminal card](2026-07-28-web-terminal-card.md) — the precedent this mirrors: a `ui-primitives` block, a single card-model derivation, keyed and fallback chat rows, and a details-panel arm, for the `terminal` render intent.
+- [Tagged render-intent union for tool-call presentation](../architecture/2026-07-02-tool-render-intent-union.md) — the `card`-tagged vocabulary; the Web client is now a full consumer of the `web` arm.
@@ -0,0 +1,49 @@
+# Agent Note: Web result 卡片前端 —— 在浏览器渲染 web 渲染意图
+
+Status: implemented
+
+[English](2026-07-30-web-result-card-frontend.md) | 中文
+
+## Problem
+
+`web_search` 和 `web_fetch` 工具声明了 `card: 'web'` result view（[web result card](2026-07-30-web-result-card.md)）：一个 `kind` 标签联合,携带结构化的被引用 sources 加可选的 provider answer（`kind: 'search'`),或抓取的 URL 及其 HTTP 状态（`kind: 'fetch'`）。该视图早已抵达浏览器 —— host、connection、runtime 将它作为 `resultView` 投递到 `ConversationSnapshot` —— 但 Web 客户端忽略了它:一次已完成的 web 调用只渲染为摊平的模型可见文本,正是契约笔记所解释的、结构化视图要替代的那种有损渲染。`web_search` 到达读者时是每个 source 一行自由文本 markdown,而非可点击 source 的引用列表;`web_fetch` 是它的 markdown 正文,没有检索摘要。
+
+## Decision
+
+`WebBlock` 是一个 `ui-primitives` 组件,渲染一次已完成的 web 检索,web 调用的每个 Web 渲染点都通过它消费 `web` 渲染意图:键控的 chat 工具行（`web_search`/`web_fetch`）、`GenericToolCard` 渲染点兜底,以及详情面板的 Output 区。`ui-conversation/src/client/contract/web-card-model.ts` 是唯一把快照的 `resultView` 转成组件 props 的地方,镜像 `terminal-card-model.ts`,因此没有两个渲染点会对一次 web 调用的显示产生分歧。它返回 null —— 走通用路径 —— 对运行中的调用（web 卡片是 result-only 的,因为工具保留 generic pending 视图）、对 result view 不是 web 卡片的已结算调用（包括本客户端版本不认识的 `card` 值,它经 wire 抵达因而不能被信任为已编译的变体）、对 generic result view（web 工具的错误路径返回 generic 卡片,其文本由通用路径保留）、以及对本客户端版本不认识 `kind` 的 web 卡片（更新的 host 经 wire 发来的值,读作 fetch 会画出空 URL 和 `HTTP undefined`）。
+
+一个组件绘制两种 kind,由 `kind` 判别。`search` 把 answer 作为 markdown 显示在引用列表上方;每个 source 是一个安全外链,以其标题为标签,provider 未给标题时以其主机名为标签,下方是 snippet 与发布日期,工具截断列表时显示 `来源列表已截断` 提示。`fetch` 显示一个紧凑摘要:带链接的最终 URL、其 HTTP 状态、以及 `内容已截断` 提示。用一个组件而非两个,因为两者都是渲染为同一卡片族的 web 检索 —— 这正是契约把它们放在一个 `card` 标签下、用 `kind` 判别的原因。
+
+**链接的安全性沿用 MarkdownText 对不受信任的 assistant 链接所用 allowlist 的 http(s) 子集。** MarkdownText 还允许 `mailto:`，此处刻意排除，因为检索 URL 绝不会是邮件地址。一个 source 或 fetch URL 仅当其协议为 `http:` 或 `https:` 时才成为可导航锚点，带 `target="_blank"` 和 `rel="noopener noreferrer"`；`javascript:`/`data:`/`file:`/`mailto:` URL 或无法解析的字符串渲染为纯文本、无 href。web 工具返回的 result content 是模型创作的,未经验证抵达本组件,因此像 assistant markdown 一样被当作不受信任处理。标签从标题回退到主机名再回退到原始 URL,因此即便标题缺失且 URL 无法解析,source 也总能读作某个东西。
+
+**几何镜像 CodeBlock/TerminalBlock**（12px 圆角、code-block 表面、16px 垂直外边距）,使 web 卡片与它们读作一家。长 source 列表在 `maxSources` 处折叠,用 TerminalBlock 完全相同的分割算术做头/尾折叠（`ceil(max/2)` 头部行加剩余尾部）,使长正文的切片在两张卡之间一致。source 列表是散文而非按列对齐的输出,所以它正常换行,而不像终端卡片的输出那样横向滚动 —— 这是与 TerminalBlock 唯一刻意的分歧。
+
+卡片在 chat 行中**常驻**于摘要行之下,上限 `CHAT_WEB_MAX_SOURCES`（8）—— 原语自身默认 16 的一半,面板保留 16 —— 与 `CHAT_TERMINAL_MAX_LINES` 为终端卡片所画的摘要面对阅读面的同一划分,以及 `BashRow` 所用的同一常驻姿态。键控行把一个 `WebRow` 组件注册在 `web_search` 与 `web_fetch` 两个键下;行仅根据工具名判别以选取其图标（search 对 browse）与标题（`Search`/`Fetch`）。没有自己键控行的 web 声明工具落到 `GenericToolCard`,它长出同一张常驻卡片。详情面板以原语的完整 source 额度渲染卡片,并在其下方渲染摊平的模型可见结果内容:`web_fetch` 卡片只携带 URL 与状态,因此其抓取正文只在此处可读。
+
+## Consequences
+
+`WebBlock` 只读 web view 的字段,因此它是渲染意图所携带内容的纯函数 —— 无会话查找,与产出该视图的 presenter 一样回放安全,且不同于终端卡片它不需要 cwd 解析,因为 web view 不携带路径。没有 `web` 能力的 UI（TUI）仍得到契约的回退 `content`;工具的 result 形状没有任何改变。answer 复用 `MarkdownText`,因此 answer 自身的不受信任链接处理与 GFM 渲染免费获得。
+
+一条独立的后续 PR 会统一整行折叠/展开交互,并把每张常驻卡片（terminal、diff、web）一次性翻成 expand-gated;本卡片遵循当前的常驻约定,而非抢先做那次改动。
+
+## Alternatives considered
+
+**两个组件,每种 kind 一个。** 拒绝:两种形状共享卡片外框、安全链接处理、截断提示,而契约已经把它们的差异表达为一个 `card` 标签下的 `kind` 判别;两个组件会重复共享表面并拆分安全链接逻辑。
+
+**重解析模型可见的渲染文本,而非消费结构化视图。** 因契约笔记给出的同一理由拒绝:`web_search` 的渲染把每个 source 的字段压缩成一行自由文本、以标题或主机名为标签,所以重解析无法恢复 `{url, title?, snippet?, publishedAt?}`。结构化的 `resultView` 是唯一忠实来源,这正是后端 PR 添加它的原因。
+
+**不加协议 allowlist 直接渲染裸锚点。** 拒绝:URL 在此接缝处是模型创作、未经验证的,所以未过滤的 href 会让 `javascript:` URL 在点击时执行。该 allowlist 是 MarkdownText allowlist（它还允许 `mailto:`）的 http(s) 子集,因此不受信任的检索链接无论在何处渲染都行为相同。
+
+## Testing
+
+`packages/client/ui-primitives/tests/web-block.spec.tsx` 把组件钉到 per-file 100% 门槛:两种 kind;标题-或-主机名-或-原始 URL 的标签回退;两种 kind 上的安全链接属性（http(s) URL 成为带 `target`/`rel` 的外链,`javascript:`/`file:`/无法解析的 URL 渲染为无 href 的纯 span）;snippet 与日期在存在/为空/缺失时的显示或省略;由标志位控制的截断提示;以及 source 列表高度上限及其头/尾切片与展开/收起控件,含默认上限。
+
+`packages/client/ui-conversation/tests/web-card.spec.tsx` 在每个接线接缝镜像 `terminal-card.spec.tsx`:`webCardModel` 的派生投影每个 source 字段、其截断与缺失 answer 的支路、fetch 派生、以及每个 null 支路（运行中、null result view、generic result view、未知 card 标签、未知 web `kind`）;键控 `WebRow` 对两种 kind 的常驻卡片、比面板收得更紧、其仅摘要行的运行中与失败支路;`GenericToolCard` 兜底为 web 声明工具长出常驻卡片、并为非 web 调用保持纯行;详情面板 Output 区对两种 kind —— 含 `web_fetch` 正文摊平在其 URL/状态卡片下方 —— 及其对非 web 结果的摊平回退;以及在 `web_search` 与 `web_fetch` 两键下用一个组件的键控注册。该文件位于覆盖率 `exclude` 列表（`ui-conversation/src/*`）,因此覆盖率运行不度量它。
+
+fixture（`packages/client/connection/src/client/fixture.ts`）添加 turn 66（`web_search`）与 67（`web_fetch`）,内联撰写,因为客户端 fixture 无法 import web 工具:turn 66 的 result view 携带一个 answer 与三个 source,演练引用列表（一个带 snippet 与日期的有标题 source、一个无标题因而以主机名标注链接的 source、一个有日期无 snippet 的 source）并开启截断提示;turn 67 携带抓取的 URL 与一个 200 状态。两者都保留 generic pending call view,仅在 result 时添加 `web` 卡片,匹配契约的 result-only web 形状,且以真实工具命名,使其命中键控 `WebRow`。它们被排在 todo turn（重编号为 68）之前,理由与终端 turn 相同:待定计划在下一个 `turn/start` 退休,所以排在其后的 turn 会清空 dock 的 plan strip。这驱动 built-boot snapshot 与一个实时 `?fixture` 服务。
+
+## Related
+
+- [Web result card](2026-07-30-web-result-card.md) —— 添加 `card: 'web'` result 支路并让两个工具发出它的后端 PR;本条是它推迟的前端消费者。
+- [Web terminal card](2026-07-28-web-terminal-card.md) —— 本条所镜像的先例:一个 `ui-primitives` block、一处 card-model 派生、键控与兜底 chat 行、以及一个详情面板支路,用于 `terminal` 渲染意图。
+- [工具调用呈现的标签化 render-intent union](../architecture/2026-07-02-tool-render-intent-union.md) —— `card` 标签词汇;Web 客户端现在是 `web` 支路的完整消费者。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-web-tool-row-unified-expand-and-inspect.md
+2026-07-30-web-tool-row-unified-expand-and-inspect.md: ba2f4ead8023772fad578ca0b647241ecc332905
+2026-07-30-web-tool-row-unified-expand-and-inspect.zh.md: ac4835c7429a3ff7d3042f73d26d267911533132
@@ -0,0 +1,34 @@
+# Agent Note: Web tool-row unified expand and trajectory Inspect
+
+Status: implemented
+
+English | [中文](2026-07-30-web-tool-row-unified-expand-and-inspect.zh.md)
+
+## Problem
+
+The chat view's tool rows had drifted into per-surface interaction dialects: ToolRow expanded through a leading-icon toggle and only for calls with an args body, the bash sample had its own expand affordance, todo/ask-question rows expanded raw args only, single-file tools were not expandable at all, and a call's OUTPUT was reachable only through the details panel. A failing bash command (exit≠0 settles `isError:false`) showed no collapsed-row failure signal. There was also no path from a chat row to its trajectory record, and switching chat → trajectory → chat lost the reader's scroll position because the tab ring unmounts inactive views.
+
+## Decision
+
+**Every expandable tool row shares one interaction — the whole row toggles (click / Enter / Space) with an icon→chevron hover preview — and one expanded body: an IN/OUT gutter-labeled card with per-section scroll caps; a hover-revealed Inspect pill jumps to the call's trajectory record through a one-shot store handoff; the chat view preserves its scroll offset across view switches through an in-memory per-session map.**
+
+- `toolRowModel` now derives result material alongside args: `output` (the `resultText` flatten, moved from DetailsPanel into the contract), and `errorSummary` (the failure's first line, shown as the collapsed summary in the error color). A row with body, output, or terminal material is expandable; the row itself is the toggle (`role="button"`, `aria-expanded`), and file-path summaries stay independent links via `stopPropagation`.
+- The expanded card (figma 1249:35657) is a column of IN/OUT sections: each section is its own scrollport (max-height 150px) with a sticky gutter label, and the l2 divider spans the full card width. Think prose and the run_code CodeBlock keep their non-card bodies; context injection reuses the row with a label-less `plainBody` card.
+- `terminalFailed` reads a settled terminal card's exit status so BashRow and GenericToolCard surface a failing command as the row's red state dot — the only failure signal the collapsed row has, since the call itself settles `isError:false`.
+- TerminalBlock's banner joins the same reading model: it shares the card surface (no banner token), an l2 hairline separates it from the body, the command column caps at 150px and scrolls with sticky copy/status controls top-aligned to the first prompt row.
+- Inspect: `ToolRowOwnerProps.inspect` (absent for rows without a call identity) renders a pill in real flow under the expanded body's bottom-left, revealed by hovering anywhere on the tool call. Clicking writes `{ callId }` to the chat store's one-shot `inspect` field and switches to the trajectory view; TrajectoryTable finds the record, opens its summary, and acknowledges by clearing the field.
+- Scroll preservation: the chat view saves its offset on every scroll (null when pinned to bottom) into an apply-scope `Map<SessionId, number>` exposed as `chatScroll` on the injected props; the open-jump branch restores it on remount. Deliberately not persisted — a fresh page load keeps the open-jump-to-bottom default.
+
+## Alternatives considered
+
+**Keeping the leading-icon toggle and per-registrant expand affordances.** Rejected: three surfaces had already diverged; the registrant posture (bash sample replicates CSS locally) makes drift permanent unless the interaction contract itself is uniform and small — whole-row toggle plus hover preview.
+
+**Routing Inspect through a URL or a trajectory-view prop.** Rejected: the view ring renders through the slot registry, so the two views share no parent that could carry a prop; the chat store already crosses that boundary and the one-shot field keeps the handoff replay-safe (persisted snapshots from before the field rehydrate with `?? null`).
+
+**Persisting the chat scroll offset.** Rejected: restoring a days-old offset into a conversation that has since grown reads as a bug; the in-memory map scopes the memory to exactly the view-switch case that loses it.
+
+**A per-row expanded OUTPUT fetched from the details panel's material.** Unnecessary: the settled result node already rides the snapshot's frozen call slice, so the contract-level `resultText` flatten serves both the row and the panel from one derivation.
+
+## Consequences
+
+Any registered toolview gets input AND output inspection in place, with the details panel and trajectory remaining the deep-dive surfaces. The unified interaction is contract-visible (`ToolRowProps.output/errorSummary/inspect`), so third-party rows opt in by passing model fields through. The bash sample intentionally re-replicates the new CSS (registrant posture), so future interaction changes still touch it by hand. `--dsw-font-markdown-code-block-small` (12/18) is a hand-added token pending a design-platform export. The web-cordis `distIndex` fix (plain concatenation, not URL.pathname) unblocks preview boots from a cwd with spaces.
@@ -0,0 +1,34 @@
+# Agent Note：Web 工具行统一展开交互与 trajectory Inspect
+
+状态：已实现
+
+[English](2026-07-30-web-tool-row-unified-expand-and-inspect.md) | 中文
+
+## 问题
+
+聊天视图的工具行交互已经分裂成多种方言：ToolRow 通过前导图标切换展开、且仅限有 args body 的调用，bash 示例有自己的一套展开方式，todo / ask-question 行只能展开原始 args，单文件工具完全不可展开，而调用的 OUTPUT 只能通过右侧详情面板查看。失败的 bash 命令（exit≠0 但结算为 `isError:false`）在折叠行上没有任何失败信号。此外聊天行没有跳转到 trajectory 记录的入口，且 chat → trajectory → chat 切换会丢失阅读位置（标签环会卸载非活跃视图）。
+
+## 决定
+
+**所有可展开工具行共享同一交互——整行即开关（点击 / Enter / 空格），图标 hover 时渐变为 chevron 预览——以及同一展开体：带 IN/OUT 侧栏标签的卡片，各分区独立滚动上限；hover 显示的 Inspect 胶囊通过 store 的一次性交接跳到该调用的 trajectory 记录；聊天视图用内存态的按会话 Map 在视图切换间保留滚动位置。**
+
+- `toolRowModel` 在 args 之外同时派生结果材料：`output`（`resultText` 拍平逻辑从 DetailsPanel 移入 contract）和 `errorSummary`（失败首行，以错误色作为折叠摘要）。有 body、output 或 terminal 材料的行即可展开；行本身是开关（`role="button"`、`aria-expanded`），文件路径摘要通过 `stopPropagation` 保持独立链接。
+- 展开卡片（figma 1249:35657）是 IN/OUT 分区列：每个分区是独立滚动区（max-height 150px），侧栏标签 sticky 固定，l2 分割线横贯整卡宽度。Think 的推理文本和 run_code 的 CodeBlock 保持非卡片体；上下文注入复用此行并以无标签的 `plainBody` 卡片展开。
+- `terminalFailed` 读取已结算 terminal 卡片的退出状态，让 BashRow 和 GenericToolCard 把失败命令显示为行的红色状态点——这是折叠行唯一的失败信号，因为调用本身结算为 `isError:false`。
+- TerminalBlock 的横幅并入同一阅读模型：与卡片共用同一表面（不再用 banner token），与正文之间是 l2 细线，命令列上限 150px 内部滚动，复制/状态控件 sticky 且顶对齐第一行提示符。
+- Inspect：`ToolRowOwnerProps.inspect`（无调用身份的行不提供）在展开体左下角以真实布局位置渲染胶囊，hover 整个 tool call 任意位置显示。点击将 `{ callId }` 写入 chat store 的一次性 `inspect` 字段并切换到 trajectory 视图；TrajectoryTable 找到记录、打开其摘要，并通过清空字段确认。
+- 滚动保留：聊天视图在每次滚动时保存偏移（贴底时为 null）到 apply 作用域的 `Map<SessionId, number>`，经注入 props 的 `chatScroll` 暴露；重挂载时 open-jump 分支恢复它。刻意不持久化——新页面加载保持打开即贴底的默认行为。
+
+## 曾考虑的替代方案
+
+**保留前导图标开关和各注册方自有的展开方式。** 否决：三个表面已经分化；注册方姿态（bash 示例本地复刻 CSS）意味着除非交互契约本身统一且足够小——整行开关加 hover 预览——否则漂移会永久存在。
+
+**通过 URL 或 trajectory 视图 prop 传递 Inspect。** 否决：视图环经由 slot 注册表渲染，两个视图没有可携带 prop 的共同父级；chat store 本就跨越该边界，一次性字段让交接可安全重放（字段出现之前的持久化快照以 `?? null` 复水）。
+
+**持久化聊天滚动偏移。** 否决：把几天前的偏移恢复到已经增长的会话里读起来像 bug；内存 Map 把记忆精确限定在会丢位置的视图切换场景。
+
+**从详情面板的材料为每行单独取展开 OUTPUT。** 不必要：已结算结果节点本就在快照的冻结调用切片上，contract 层的 `resultText` 拍平让行和面板共用一份派生。
+
+## 后果
+
+任何已注册 toolview 都能就地查看输入与输出，详情面板和 trajectory 仍是深查表面。统一交互契约可见（`ToolRowProps.output/errorSummary/inspect`），第三方行透传模型字段即可接入。bash 示例有意重新复刻新 CSS（注册方姿态），未来交互变更仍需手动同步它。`--dsw-font-markdown-code-block-small`（12/18）是手工补充的 token，待设计平台导出后替换。web-cordis 的 `distIndex` 修复（纯拼接而非 URL.pathname）解除了含空格 cwd 下预览无法启动的问题。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md
+2026-07-31-web-telemetry-default-mount.md: 6c1fdaa8719ee01726b51db9a469ff659cbac476
+2026-07-31-web-telemetry-default-mount.zh.md: b447832527ba9731097cd0776060db11ee4dfc30
@@ -0,0 +1,39 @@
+# Agent Note: Default session-telemetry mount (OTel reporting) in the dsh web composition
+
+Status: implemented
+
+English | [中文](2026-07-31-web-telemetry-default-mount.zh.md)
+
+## Problem
+
+The telemetry seam and OTel backend ([revival Note](2026-07-23-session-telemetry-otel-revival.md)) had never been wired into any deployment composition since completion: no roster row, no switch, no cadence ruling, and zero observability over user sessions for the internal deployment. A deployment decision was needed: which surfaces report, to where, on what cadence, how to opt out, and how CI stays isolated.
+
+## Decision
+
+The shared `dsh` core (`apps/cli/config/base.cordis.yml`) mounts the `telemetry-otel` row by default with a baked-in production endpoint, so every surface — TUI, web, and headless — reports; this is the **internal-testing deployment stance** — reporting is on when an endpoint exists, and users opt out through the environment. Each surface's exit path drains the queue: web/headless dispose on SIGINT/SIGTERM (headless gained those handlers in this change), and the TUI's normal exit runs `disposeRootAndExit` (root dispose, 5s bounded — above the ~1s drain ceiling configured here) while its `/resume` handoff disposes the root before `execve`.
+
+| Ruling | Value | Rationale |
+|---|---|---|
+| Mount surface | base.cordis.yml (TUI + web + headless) | One deployment stance for every surface; per-surface divergence would need a reason, and none exists |
+| Endpoint | `DSH_TELEMETRY_OTLP_URL`, default `https://harness-telemetry.deepseeksvc.com/v1/logs` | Internal collector; the env override serves local/dev runs |
+| Opt-out switch | any non-empty `DSH_TELEMETRY_DISABLED` (including `0`/`false`) disables | A privacy switch prefers off-by-mistake over on-by-mistake; a row can only be disabled at AppCLIEntry's patch layer (config has no disable semantic, and the switch must precede the load-time `exporter.url` validation) |
+| Cadence | `processor.scheduledDelayMillis: 10000` (10s/batch) | Streaming while the session runs, never exit-time-only; a crash loses at most the last unexported interval |
+| Exit-drain bound | `exporter.timeoutMillis: 1000` + `maxExportBatchSize: 2048` (== maxQueueSize) + `exportTimeoutMillis: 1500` | Dispose must release within ~1s against an unreachable collector: timeoutMillis doubles as the per-attempt socket timeout and the retry deadline (1s effectively disables the SDK's 5-try backoff), and aligning batch size with the queue cap makes the drain a single batch; SDK defaults can stall 40s+ |
+| Compression | `compression: gzip` | Event bodies carry full content; cross-datacenter bandwidth |
+| CI isolation | top-level `env: DSH_TELEMETRY_DISABLED: '1'` in all 8 GitHub workflows | Every CI channel that boots the web composition (e2e/snapshot/built smokes) must not stream test sessions to the production endpoint |
+
+The keyless integration test `apps/cli/tests/telemetry-web.e2e.ts` pins the deployment-level behavior: an in-test OTLP collector plus a mock LLM server, a real `dsh web` boot, asserting ledger coverage, seq monotonicity, the first-of-step chunk projection, and the ops `shutdown` marker arriving through the SIGINT drain.
+
+## Alternatives considered
+
+**No default mount; deployments add the row themselves (continuing the SDK stance).** Rejected for this stage: this repo's web/headless composition IS the internal deployment, and default-on reporting is that deployment's product requirement; the SDK stance survives in the seam packages (unmounted = nothing leaves).
+
+**A config field instead of an env patch for the switch.** Infeasible: cordis rows have no config-level disable semantic, and `exporter.url` validation fails loud at plugin construction, so the switch must take effect before the Loader — AppCLIEntry's patch layer is the only seat.
+
+**A `Promise.race` timeout backstop around exit.** Deferred: the parameter set already bounds the worst-case drain to ~1.5-3s (typically <100ms), measured SIGINT-to-exit 110ms-1.1s; the unbounded drip-feed-response risk stays under observation, and on real evidence the race lands inside the backend's `shutdown()` (never the coordinator — that would decide loss semantics for every backend).
+
+## Consequences
+
+- A developer running `dsh web` without a local collector POSTs to the production endpoint every 10s (silent failure when unreachable; no OTel diag logger is registered); local development sets `DSH_TELEMETRY_DISABLED=1` or points `DSH_TELEMETRY_OTLP_URL` locally.
+- **No redaction rule is mounted yet**: exports are the raw captured copy (full user/assistant message text, tool arguments and results, the system prompt, the local `session.cwd` path). Crossing a trust boundary requires `telemetry/record` rules first — the redaction rule, identity Resource attributes (hostname / anonymous user id / surface), and the usage-metrics track are the explicit follow-ups of this decision.
+- Test rigs reusing this tree (e.g. `apps/web/tests/scaffold.ts`) must explicitly disable the row, or fixture sessions stream to whatever collector the environment happens to name.
@@ -0,0 +1,39 @@
+# Agent Note: dsh web 组合默认挂载会话遥测（OTel 上报）
+
+Status: implemented
+
+[English](2026-07-31-web-telemetry-default-mount.md) | 中文
+
+## Problem
+
+遥测 seam 与 OTel backend（[revival Note](2026-07-23-session-telemetry-otel-revival.md)）自完成以来从未接入任何部署组合：没有 roster 行、没有开关、没有节奏口径，内部部署对用户会话零可观测。需要一个部署决策：哪些 surface 上报、报到哪、什么节奏、怎么关、CI 怎么隔离。
+
+## Decision
+
+`dsh` 共享核心（`apps/cli/config/base.cordis.yml`）默认挂载 `telemetry-otel` 行，内置生产 endpoint，因此所有 surface——TUI、web、headless——都上报；这是**内部测试期的部署立场**——有 endpoint 就报，用户可经环境变量退出。各 surface 的退出路径都会排空队列：web/headless 在 SIGINT/SIGTERM 上 dispose（headless 的信号处理是本次补上的），TUI 的正常退出走 `disposeRootAndExit`（根 dispose，5s 兜底——高于此处配置的 ~1s drain 上界），其 `/resume` 移交也在 `execve` 前 dispose 根。
+
+| 决策项 | 取值 | 理由 |
+|---|---|---|
+| 挂载面 | base.cordis.yml（TUI + web + headless） | 所有 surface 一个部署立场；按 surface 分化需要理由，而当前没有 |
+| endpoint | `DSH_TELEMETRY_OTLP_URL`，缺省 `https://harness-telemetry.deepseeksvc.com/v1/logs` | 内部 collector；env 覆盖供本地/联调 |
+| 退出开关 | `DSH_TELEMETRY_DISABLED` 非空（含 `0`/`false`）即关 | 隐私向开关取「宁关勿误开」；行级 disable 只能在 AppCLIEntry 的 patch 层做（config 无 disable 语义，且必须先于 `exporter.url` 的加载期校验生效） |
+| 上报节奏 | `processor.scheduledDelayMillis: 10000`（10s/批） | 流式回流，非退出才报；崩溃至多丢最后一个未导出间隔 |
+| 退出 drain 上界 | `exporter.timeoutMillis: 1000` + `maxExportBatchSize: 2048（== maxQueueSize）` + `exportTimeoutMillis: 1500` | collector 不可达时 dispose 必须 ~1s 内放行：timeoutMillis 同时是单次 socket 超时与重试 deadline（1s 等效关掉 SDK 5 次 backoff），批大小对齐队列上限使 drain 恒为单批；默认参数下最坏可卡 40s+ |
+| 压缩 | `compression: gzip` | 事件 body 含全文，跨机房带宽 |
+| CI 隔离 | 全部 8 个 GitHub workflow 顶层 `env: DSH_TELEMETRY_DISABLED: '1'` | CI 启动 web 组合的所有通道（e2e/snapshot/built smoke）不得向生产 endpoint 泄测试会话 |
+
+集成测试 `apps/cli/tests/telemetry-web.e2e.ts`（keyless）钉住部署级行为：测试内 OTLP collector + mock LLM，真启动 `dsh web`，断言 ledger 覆盖、seq 单调、chunk 首条投影、以及 SIGINT drain 后 ops `shutdown` 标记到达。
+
+## Alternatives considered
+
+**默认不挂载，部署方自行加行（SDK 立场的延续）。** 否决于当前阶段：本仓的 web/headless 组合就是内部部署本身，「上报默认开」是这个部署的产品要求；SDK 立场仍由 seam 包保持（不挂 = 零外发）。
+
+**开关做成 config 字段而非 env patch。** 不可行：cordis 行没有 config 层的 disable 语义，且 `exporter.url` 校验在插件构造期 fail-loud，开关必须在 Loader 之前生效——AppCLIEntry patch 层是唯一落点。
+
+**退出时 `Promise.race` 兜底超时。** 暂缓：参数组合已把最坏 drain 压到 ~1.5-3s（典型 <100ms），实测 SIGINT→退出 110ms-1.1s；drip-feed 慢滴响应的无界等待风险留观，出现实证再在 backend `shutdown()` 内加 race（不放 coordinator——那会替所有 backend 决定丢失语义）。
+
+## Consequences
+
+- 无本地 collector 的开发者跑 `dsh web` 会对生产 endpoint 每 10s 发一次 POST（联不通则静默失败，OTel diag logger 未注册）；本地开发设 `DSH_TELEMETRY_DISABLED=1` 或 `DSH_TELEMETRY_OTLP_URL` 指本地。
+- **当前零脱敏规则挂载**：导出即原始捕获副本（用户/助手消息全文、工具参数与结果、system prompt、`session.cwd` 本地路径）。跨信任边界前必须挂 `telemetry/record` 规则——脱敏规则、身份 Resource 维度（hostname/匿名 user id/surface）、使用数据 metrics 轨三件是本决策明确的后续工作。
+- 复用这棵树的测试载具（如 `apps/web/tests/scaffold.ts`）须显式关停该行，否则 fixture 会话会流向 env 里碰巧存在的 collector。
@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-2026-07-06-node-engine-floor.md: f1754ea7ca32452a04c6cd8a0599568f602e47dd
-2026-07-06-node-engine-floor.zh.md: 9d376a639378d3a0b9b645aa36c1a5d320d1d147
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-06-node-engine-floor.md
+2026-07-06-node-engine-floor.md: ef047d885a442106a35922f4716d2996d8a98ca7
+2026-07-06-node-engine-floor.zh.md: a0281addf7d4327d7f6ea30e3a3f0f40d6782bd0
@@ -10,7 +10,7 @@ The Node 22 branch of the root `engines.node` range is a contract for the instal

 ## Decision

-Set `engines.node` to `^22.19.0 || >=24.0.0` and test the keyless CI compatibility matrix on `['22.19', 24, 26]`. Every matrix leg runs the TypeScript typecheck plus a keyless source-mode worker smoke, so the floor is exercised through both a complete source typecheck and a real unbuilt runtime path. The real-API e2e workflow stays on Node 24 because it exercises API integration rather than the runtime floor.
+Set `engines.node` to `^22.19.0 || >=24.0.0` and test keyless CI on `['22.19', 24, 26]`. The primary Node 24 jobs own the complete typecheck and unit coverage inventory; every version runs focused source-worker, Zstandard, source-launch, and [jsdom storage](../testing/2026-07-30-vitest-jsdom-webstorage-ownership.md) smokes without repeating that inventory. The real-API e2e workflow stays on Node 24 because it exercises API integration rather than the runtime floor.

 Two Node features gate the source runtime:

@@ -24,7 +24,7 @@ Those source features clear on the 22.x line at **22.18**, but the installed Pi
 ## Consequences

 - The advertised LTS branch no longer undercuts the Pi adapter dependency floor.
- CI proves the Node 22 LTS floor directly with Node 22.19, keeps the Node 24 branch on `node: 24`, and keeps Node 26 for the next even line; each leg typechecks the source graph and launches the unbuilt workflow worker for real.
+- CI proves the Node 22 LTS floor directly with Node 22.19, keeps primary coverage on `node: 24`, and exercises Node 26 as the next even line; focused compatibility smokes run on all three versions.
 - The built-bin smoke needs no version-conditional flag: at 22.19 type-stripping is already the default, so the test stays the plain `node lib/bin.js` path it documents.
 - A future dependency or source API that raises the runtime floor must move `engines.node`, the compatibility matrix, and this Agent Note in the same change.

@@ -10,7 +10,7 @@ Status: implemented

 ## 决策

-将 `engines.node` 设为 `^22.19.0 || >=24.0.0`，并在 keyless CI 兼容性矩阵中测试 `['22.19', 24, 26]`。每条矩阵分支都运行 TypeScript 类型检查加一次 keyless 的源码模式 worker 冒烟测试，因此引擎下限通过完整的源码类型检查和真实的未构建运行时路径两条路径得到验证。真实 API 的 e2e 工作流保持在 Node 24 上，因为它验证的是 API 集成而非运行时下限。
+将 `engines.node` 设为 `^22.19.0 || >=24.0.0`，并在 `['22.19', 24, 26]` 上运行 keyless CI。主要的 Node 24 任务负责整套类型检查和单元测试覆盖率任务；三个版本均运行 source-worker、Zstandard、source-launch 和 [jsdom 存储](../testing/2026-07-30-vitest-jsdom-webstorage-ownership.md) 专项冒烟测试，不重复这套类型检查和覆盖率任务。真实 API 的 e2e 工作流保持在 Node 24 上，因为它验证的是 API 集成而非运行时下限。

 两个 Node 特性决定了源码运行时的门槛：

@@ -24,7 +24,7 @@ Status: implemented
 ## 后果

 - 宣传的 LTS 分支不再低于 Pi 适配器依赖的下限。
- CI 通过 Node 22.19 直接验证 Node 22 LTS 下限，Node 24 分支保持 `node: 24`，Node 26 用于下一个偶数线；每条分支都对源码图执行类型检查，并实际启动未构建的工作流 worker。
+- CI 通过 Node 22.19 直接验证 Node 22 LTS 下限，将主要覆盖率任务保留在 `node: 24`，并用 Node 26 验证下一个偶数线；三个版本均运行聚焦的兼容性冒烟测试。
 - built-bin 冒烟测试无需版本条件标志：在 22.19 上类型剥离已是默认行为，因此测试保持其文档所述的纯 `node lib/bin.js` 路径。
 - 未来若依赖或源码 API 提高运行时下限，必须在同一变更中同步调整 `engines.node`、兼容性矩阵和本 Agent Note（agent 决策记录）。

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-22-product-first-root-readme.md
+2026-07-22-product-first-root-readme.md: 32542a45019d64ed1826d4eb21e68c67c3c3d52e
+2026-07-22-product-first-root-readme.zh.md: 1c4d5fa53854bfcade9742da1fb74d9636909f84
@@ -0,0 +1,33 @@
+# Agent Note: Product-first root README
+
+Status: implemented
+
+English | [中文](2026-07-22-product-first-root-readme.zh.md)
+
+## Problem
+
+The root README is the repository's product front door. Its product-first structure and established voice remain useful, but concrete entry points and capability claims drift as the runtime grows. Rewriting sections whose facts remain correct increases the review surface and discards language that already works.
+
+## Decision
+
+The root README preserves its existing structure, order, and wording wherever the underlying fact remains correct. A refresh changes only stale claims and adds material needed to represent shipped surfaces; it does not use repository growth as a reason to reframe the whole page.
+
+A note before installation thanks internal testers, states that features and experience remain unfinished, and asks for direct reports of failures, confusion, and friction through the WeCom group. The existing development-stage statement identifies DeepSeek Harness as being in internal testing.
+
+The user-surface section adds the ACP automation server and Python/JSON-RPC SDK beside the existing Web, TUI, and headless entries. The installed TUI remains the single `dsh` command; the Web instructions build the active checkout before running `dsh web`, and custom or reused checkout paths stay explicit. These launch paths must remain executable through a real PTY and a production build/HTTP smoke, respectively. The capability paragraph keeps its compact inventory style while adding the shipped PTY, LSP, web, goal, planning, task, sandbox, approval, settings, credentials, session-query, and telemetry families and stating that compositions select subsets. One adjacent bullet records the authoritative-session-log rule because persistence, replay, queries, telemetry, and interfaces depend on it.
+
+Detailed package and service inventories remain at their owning documentation. The English and Chinese README sides share the same technical structure, while their community sections continue to point to the primary channel for each language audience. The documentation website keeps its separate user-guide landing page.
+
+## Alternatives considered
+
+**Rewrite the README around a new product narrative.** A complete rewrite can make every current surface prominent, but it replaces accurate, reviewed copy and creates unnecessary churn. Current facts fit the established product-first structure.
+
+**Present the repository as an SDK and package catalog.** This exposes implementation breadth immediately but makes a new reader reconstruct the product from package names. The package map and generated capability graph remain the authoritative inventories.
+
+**Use a long marketing page with screenshots, badges, and duplicated tutorials.** Rich media can demonstrate a stable product journey, but it ages separately from commands and source contracts. The root stays compact and links to runnable examples and owned guides.
+
+**Project the root README as the documentation website home page.** A single landing page avoids two narratives, but the website's user guide and the repository's product/developer front door have different navigation and maintenance needs.
+
+## Consequences
+
+Reviewers can distinguish factual refreshes from editorial rewrites, and future updates retain established wording unless its meaning becomes false or incomplete. The README must still change with affected commands, entry points, release-stage claims, or high-level capability families, while exhaustive detail remains linked rather than copied.
@@ -0,0 +1,33 @@
+# Agent Note: 产品优先的根 README
+
+Status: implemented
+
+[English](2026-07-22-product-first-root-readme.md) | 中文
+
+## 问题
+
+根 README 是仓库的产品入口。其产品优先的结构和既有语气仍然有效，但随着运行时不断扩展，具体入口和能力声明会逐渐陈旧。重写事实仍然正确的章节，会扩大评审范围，也会丢弃已经行之有效的措辞。
+
+## 决策
+
+只要背后的事实仍然正确，根 README 就保留既有结构、顺序和措辞。刷新时只修正陈旧声明，并补充呈现已交付内容所需的信息；不会因为仓库规模增长就重构整篇叙事。
+
+安装说明之前的一则文字感谢内测用户，说明功能和体验仍待完善，并邀请大家通过企业微信群直接反馈失败、困惑和不顺手之处。既有的开发阶段声明明确说明 DeepSeek Harness 处于内测阶段。
+
+用户入口章节在已有的 Web、TUI 和 Headless 入口旁补充 ACP（Agent Client Protocol）自动化服务器和 Python/JSON-RPC SDK。安装后的 TUI 仍只需执行一条 `dsh` 命令；Web 说明要求先构建当前检出，再运行 `dsh web`，并明确处理自定义或复用的检出路径。这两条启动路径必须分别能在真实 PTY 与生产构建／HTTP 冒烟中原样执行。能力段落沿用简洁清单的写法，补充已经交付的 PTY、LSP、Web、目标、规划、任务、沙箱、审批、设置、凭据、会话查询和遥测等能力类别，并说明不同组合只选用其中一部分。相邻的一条列表项说明权威会话日志规则，因为持久化、回放、查询、遥测和各类接口都依赖它。
+
+包（package）与服务的完整清单仍由各自的归属文档维护。中英文 README 采用相同的技术结构，但社区章节仍分别指向各自语言受众的主要交流渠道。文档网站继续使用独立的用户指南首页。
+
+## 考虑过的替代方案
+
+**围绕新的产品叙事重写 README。** 完整重写能够突出所有现有入口和能力，但也会替换准确且已经过评审的文案，造成不必要的变动。现有事实能够纳入既有的产品优先结构。
+
+**将仓库呈现为 SDK 和包清单。** 这样能立即展现实现广度，却会迫使新读者从包名反推出产品。包索引与生成的能力图仍是权威清单。
+
+**使用包含截图、徽章和重复教程的长篇营销页面。** 富媒体能够展示稳定的产品使用路径，但其内容会独立于命令和源码契约而逐渐陈旧。根 README 保持紧凑，并链接到可运行示例和各自维护的指南。
+
+**将根 README 投影为文档网站首页。** 使用同一个首页可以避免两套叙事，但文档网站的用户指南与仓库面向产品和开发者的入口在导航和维护需求上并不相同。
+
+## 结果
+
+评审者可以区分事实更新与编辑性重写；今后的更新会保留既有措辞，除非其含义已经不再正确或完整。受影响的命令、入口、发布阶段声明或高层能力类别发生变化时，README 仍须同步更新；完整细节则继续以链接方式提供，而不是复制到正文。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-31-coverage-exempt-heavy-suites.md
+2026-07-31-coverage-exempt-heavy-suites.md: 7235a5193554947ecf71f62d522d09f4e21cb1da
+2026-07-31-coverage-exempt-heavy-suites.zh.md: b739e4494ae8d240b0e35109920a49876ebd222d
@@ -0,0 +1,61 @@
+# Agent Note: Coverage-exempt heavy suites
+
+Status: implemented
+
+English | [中文](2026-07-31-coverage-exempt-heavy-suites.zh.md)
+
+## Problem
+
+The CI coverage lane (`check:ci:coverage`) had its wall clock pinned by a handful of heavy test files: in a local 6-worker full-suite profile, 555 test files aggregated 1595 seconds, with `packages/typert/generator/tests/type-model.spec.ts` alone at 885 seconds and the top 10 files holding 84% of the aggregate. These suites share one shape — every case performs whole-workspace compiler analysis or drives real subprocess fixtures — and v8 instrumentation multiplies exactly that kind of runtime.
+
+The decisive waste: the instrumentation tax these suites paid contributed **nothing** to the per-file 100% thresholds — the measured code they execute in-process is either outside the threshold scope already or independently fully covered by other suites. Running them instrumented traded lane time for zero information.
+
+## Decision
+
+The `ci-coverage` aggregate splits into two parallel gates; every test still runs, and only the heavy suites stop paying the instrumentation tax:
+
+- **Instrumented gate** (`test:coverage`): sets `DSH_COVERAGE_EXEMPT_HEAVY=1`, which makes `vitest.config.ts` drop the exempt suites from both projects' excludes; every remaining file runs instrumented and carries the entire threshold proof. The variable is injected through the gate's own env (the existing `Gate.env` mechanism), not the workflow-global environment, so the uninstrumented gate beside it and any local `vitest run` never see it and behave unchanged.
+- **Uninstrumented gate** (`test:coverage-exempt-heavy`): runs exactly the exempt suites through paired positional filters, keeping the correctness signal whole.
+
+`scripts/coverage-exempt.ts` is the single roster point, holding the membership contract and the filter/exclude pairs so the two sides cannot drift.
+
+### The roster, reconciled entry by entry
+
+A suite contributes to coverage exactly when it executes measured files in-process (`coverage.include` spans the package src trees). The current roster, audited:
+
+| Exempt suite | Measured code executed in-process | Who carries the coverage |
+| --- | --- | --- |
+| All 6 typert generator specs | The generator's own src | Generator src is threshold-excluded as a package (`vitest.config.ts`) — outside the threshold scope to begin with |
+| tools-catalog.spec additionally imports | `typert-registry` and `tool-cordis` src | Each package's own tests cover them fully (verified with focused coverage runs, zero threshold errors) |
+| `scripts/install-lefthook.spec.ts`, `scripts/oxlint-contract.spec.ts`, `scripts/change-scope.spec.ts` | None — they test `scripts/` sources (never in `coverage.include`) and work by spawning child processes | Nothing to carry |
+
+### Membership contract
+
+A new exemption must satisfy both: every measured file the suite executes in-process is already fully covered by other suites (or threshold-excluded), and the filter and exclude select exactly the same file set. The contract text lives beside the roster in the same file.
+
+### The gate polices the roster automatically
+
+The per-file 100% thresholds are themselves the roster's guard; a wrong roster cannot pass silently:
+
+- If a future exempt suite in fact solely covers some measured file, the instrumented gate goes red on the spot (that file drops below 100%).
+- The converse holds too: new code covered only by an exempt suite turns the gate red immediately.
+
+Coverage-result invariance therefore does not rest on humans maintaining the roster, in line with the misconfiguration-fails-loud convention. The only thing given up is that the exempt suites' own execution no longer produces coverage data — the table above shows that data was entirely redundant, so the final report is file-for-file identical in threshold terms.
+
+## Alternatives considered
+
+- **CLI `--exclude` to drop the exempt suites from the instrumented gate.** Proven ineffective: vitest 4's `cliExclude` does not participate in per-project include resolution, so under a multi-project config the exempt suites stayed selected; the env + config route replaced it.
+- **Lowering worker counts or raising gate concurrency.** Measured ineffective during the incident: the lane's wall clock was pinned by the longest tail files (aggregate/wall ≈ 4× effective parallelism), and the concurrency knobs moved nothing in either direction.
+- **Cross-runner sharding (`--shard` + blob merge).** Would compress the wall clock further but adds matrix, artifact-pipeline, and merge-job complexity; with the split landed the lane sits near 2 minutes, which does not justify the cost. Revisit if the suite grows substantially.
+- **Deleting or skipping the heavy suites.** Rejected: they are the sole correctness evidence for the typert generator and the scripts tooling; running them uninstrumented in parallel preserves the full signal.
+
+## Verification
+
+Measured on CI (16-core runner): the gate segment went from 424 seconds to the two gates in parallel — `test:coverage` 95.9 s + `test:coverage-exempt-heavy` 71.1 s — with the lane converging on the slower at about 96 seconds; the instrumented gate reported zero threshold errors both before and after the split. `vitest list` verifies the env toggle adds and removes exactly the exempt set; `run-gates.spec.ts` covers the aggregate graph construction.
+
+## Consequences
+
+- The coverage lane's gate segment drops from about 7 minutes to about 96 seconds with no change in threshold outcome or executed test set.
+- `DSH_GATE_CONCURRENCY` has two schedulable gates in this lane again, so the aggregate scheduler is no longer a pass-through.
+- Adding a heavy suite to the roster requires the membership audit above; a wrong entry fails the instrumented gate loudly rather than eroding coverage silently.
+- The exempt suites no longer appear in the coverage report's file list of contributors; their correctness signal lives solely in the uninstrumented gate's pass/fail.
@@ -0,0 +1,61 @@
+# Agent Note: 覆盖率豁免重型套件
+
+Status: implemented
+
+[English](2026-07-31-coverage-exempt-heavy-suites.md) | 中文
+
+## Problem
+
+CI 覆盖率 lane（`check:ci:coverage`）的墙钟被少数几个重型测试文件钉死：本地 6-worker 全量剖析中，555 个测试文件聚合 1595 秒，其中 `packages/typert/generator/tests/type-model.spec.ts` 一个文件占 885 秒，前 10 个文件占聚合时长的 84%。这类套件的共同点是每个用例都做全工作区编译器分析或真实子进程 fixture，v8 插桩把这类代码的运行时间放大数倍。
+
+关键的浪费在于：这些套件缴纳的插桩税对 per-file 100% 阈值**没有任何贡献**——它们进程内执行的被度量代码，要么本来就不在阈值口径内，要么已由其他套件独立满覆盖。继续在插桩下运行它们，纯粹是用 lane 时长换零信息。
+
+## Decision
+
+`ci-coverage` 聚合拆成两个并行 gate，全部测试仍然执行，只有重型套件不再交插桩税：
+
+- **插桩 gate**（`test:coverage`）：设 `DSH_COVERAGE_EXEMPT_HEAVY=1`，`vitest.config.ts` 据此从两个 project 的 exclude 中剔除豁免套件，其余全部文件照旧插桩并承担全部阈值证明。经 gate 自带 env 注入（既有 `Gate.env` 机制），不进 workflow 全局环境，因此并排的无插桩 gate 和本地直跑 `vitest run` 都看不到该变量、行为不变。
+- **无插桩 gate**（`test:coverage-exempt-heavy`）：用配对的 positional filter 恰好运行豁免套件，保证正确性信号不缩水。
+
+`scripts/coverage-exempt.ts` 是唯一名单点，集中持有成员资格契约与 filter/exclude 配对，防止两侧漂移。
+
+### 豁免名单与逐项对账
+
+一个套件对覆盖率有贡献，当且仅当它在进程内执行了被度量的文件（`coverage.include` = 包 src 树）。现行名单逐项核对：
+
+| 豁免套件 | 进程内执行的被度量代码 | 覆盖由谁接住 |
+| --- | --- | --- |
+| typert generator 全部 6 个 spec | generator 自身 src | generator src 已整包 threshold-excluded（`vitest.config.ts`），本不在阈值口径内 |
+| 其中 tools-catalog.spec 额外 import | `typert-registry`、`tool-cordis` 的 src | 两包各自的测试独立满覆盖（focused coverage 实测无阈值错误） |
+| `scripts/install-lefthook.spec.ts`、`scripts/oxlint-contract.spec.ts`、`scripts/change-scope.spec.ts` | 无——被测对象是 `scripts/` 源码（从不在 coverage.include），执行方式是 spawn 子进程 | 无需接 |
+
+### 成员资格契约
+
+新增豁免必须同时满足：套件进程内执行的每个被度量文件都已由其他套件满覆盖（或在阈值排除名单内）；filter 与 exclude 选中完全相同的文件集。契约文本随名单同文件维护。
+
+### 门禁自动守卫名单正确性
+
+per-file 100% 阈值本身就是豁免名单的守卫，名单错误无法静默通过：
+
+- 若未来某个豁免套件实际独家覆盖着某个被度量文件，插桩 gate 当场红（该文件跌破 100%）；
+- 反向同理：出现"只有豁免套件才覆盖"的新代码，同样立刻红。
+
+因此覆盖率结果的不变性不依赖人工维护名单，符合"misconfiguration fails loud"约定。唯一失去的是豁免套件自身的执行不再产出覆盖数据——由上表可知这些数据全部冗余，最终报告在阈值意义上逐文件相同。
+
+## Alternatives considered
+
+- **CLI `--exclude` 从插桩 gate 剔除豁免套件。** 实证无效：vitest 4 的 `cliExclude` 不参与 per-project include 解析，多 project 配置下豁免套件仍被选中，故改走 env + config。
+- **降低 worker 数或提高 gate 并发。** 事故期间实测无效：lane 墙钟被尾部最长文件钉死（聚合/墙钟 ≈ 4× 有效并行），并发旋钮两个方向都动不了尾巴。
+- **跨 runner 分片（`--shard` + blob 合并）。** 能进一步压墙钟但引入 matrix、artifact 管道与合并 job 的复杂度；拆分落地后 lane 已到约 2 分钟，不值得付。若未来套件规模再涨可重新评估。
+- **直接删除或跳过重型套件。** 拒绝：它们是 typert generator 与 scripts 工具的唯一正确性证据，无插桩并排执行保住全部信号。
+
+## Verification
+
+CI 实测（16 核 runner）：拆分前 gate 段 424 秒，拆分后两 gate 并行 `test:coverage` 95.9 秒 + `test:coverage-exempt-heavy` 71.1 秒，lane 收敛于较慢者约 96 秒；拆分前后插桩 gate 阈值错误均为零。`vitest list` 验证 env 开关两态恰好增删豁免集；`run-gates.spec.ts` 覆盖聚合图构造。
+
+## Consequences
+
+- 覆盖率 lane 的 gate 段从约 7 分钟降到约 96 秒，阈值结果与执行测试集均无变化。
+- `DSH_GATE_CONCURRENCY` 在本 lane 重新拥有两个可调度对象，聚合调度器不再是直通。
+- 向名单新增重型套件必须完成上述成员资格对账；错误条目会让插桩 gate 大声失败，而不是静默侵蚀覆盖率。
+- 豁免套件不再出现在覆盖率报告的贡献文件列表中；其正确性信号完全由无插桩 gate 的红绿承载。
@@ -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/testing/2026-07-30-vitest-jsdom-webstorage-ownership.md
+2026-07-30-vitest-jsdom-webstorage-ownership.md: 3956a7566fa1c79a767636bce9a19f16588126e2
+2026-07-30-vitest-jsdom-webstorage-ownership.zh.md: 9080ee2762b74bf2efdaccd7a5905672001bc0e8
@@ -0,0 +1,26 @@
+# Agent Note: Keep browser storage owned by jsdom in Vitest
+
+Status: implemented
+
+English | [中文](2026-07-30-vitest-jsdom-webstorage-ownership.zh.md)
+
+## Problem
+
+The supported Node range includes releases that reserve a process-wide `globalThis.localStorage`. Node 26 exposes that property as `undefined` without `--localstorage-file`; Vitest sees the reserved key and does not project jsdom's isolated `Storage` object over it. Component suites then fail before exercising product behavior, while the primary Node 24 coverage lane remains green because that runtime does not reserve the key by default.
+
+## Decision
+
+Vitest workers disable Node's process-wide Web Storage when the runtime advertises the `--webstorage` flag. The configuration passes `--no-webstorage` through each test project's `execArgv`; runtimes without that flag receive no argument. Node-environment suites therefore stay browser-free, and files selecting jsdom through `@vitest-environment jsdom` receive jsdom's isolated `localStorage`.
+
+The Node compatibility aggregate runs a dedicated jsdom smoke on every advertised compatibility line. It asserts both the conditional worker argument and usable storage, so a future Node or Vitest change cannot leave the primary Node 24 suite as the only signal.
+
+## Alternatives considered
+
+- **Set `NODE_OPTIONS=--no-webstorage` in package scripts or CI.** Rejected because it leaks test-runner policy into subprocesses and misses direct `pnpm exec vitest` invocations.
+- **Pass `--localstorage-file` to Node.** Rejected because one process-wide persistent store has different ownership and isolation semantics from browser storage created per jsdom environment.
+- **Patch `globalThis.localStorage` in setup code or guard every component test.** Rejected because setup would depend on Vitest's private jsdom projection details, while per-test guards hide a broken browser environment and duplicate policy across suites.
+- **Pin tests to Node 24.** Rejected because the package engine advertises newer even Node lines and the compatibility matrix exists to expose their runtime changes.
+
+## Consequences
+
+The same `pnpm test` command works on Node releases with and without built-in Web Storage. Test workers deliberately cannot exercise Node's process-wide Web Storage; a future product need for that API requires a separate explicit test configuration rather than weakening jsdom isolation. The compatibility lane adds one focused Vitest process instead of duplicating the complete unit inventory on every Node version.
@@ -0,0 +1,26 @@
+# Agent Note: 在 Vitest 中将浏览器存储交由 jsdom 管理
+
+Status: implemented
+
+[English](2026-07-30-vitest-jsdom-webstorage-ownership.md) | 中文
+
+## 问题
+
+受支持的 Node 版本范围包含会预留进程级 `globalThis.localStorage` 的版本。未设置 `--localstorage-file` 时，Node 26 将该属性暴露为 `undefined`；Vitest 检测到这个预留键后，不会用 jsdom 的隔离 `Storage` 对象覆盖该属性。因此，组件测试套件尚未验证产品行为便会失败，而主要的 Node 24 覆盖率分支仍能通过，因为该运行时默认不会预留此键。
+
+## 决策
+
+当运行时声明支持 `--webstorage` 标志时，Vitest worker 会禁用 Node 的进程级 Web Storage。配置通过每个测试项目的 `execArgv` 传入 `--no-webstorage`；未声明该标志的运行时则不传入此参数。因此，Node 环境测试套件不加载浏览器环境，而通过 `@vitest-environment jsdom` 选择 jsdom 的文件会获得 jsdom 隔离的 `localStorage`。
+
+Node 兼容性汇总任务会在每条声明支持的兼容版本线上运行专用的 jsdom 冒烟测试。该测试同时断言 worker 参数按条件传入且存储可用，因此未来 Node 或 Vitest 的变化不会让主要的 Node 24 测试套件成为唯一检测信号。
+
+## 曾考虑的替代方案
+
+- **在包脚本或 CI 中设置 `NODE_OPTIONS=--no-webstorage`。** 否决：这会将测试运行器策略传播到子进程，也无法覆盖直接调用 `pnpm exec vitest` 的情况。
+- **向 Node 传入 `--localstorage-file`。** 否决：单个进程级持久化存储与每个 jsdom 环境分别创建的浏览器存储具有不同的归属和隔离语义。
+- **在初始化代码中修改 `globalThis.localStorage`，或为每个组件测试增加保护逻辑。** 否决：初始化逻辑会依赖 Vitest 私有的 jsdom 映射细节，而逐测试添加的保护逻辑会掩盖浏览器环境损坏，并在多个测试套件中重复该策略。
+- **将测试固定在 Node 24。** 否决：包的引擎范围声明支持更新的偶数 Node 版本线，而兼容性矩阵正是为了暴露这些版本的运行时变化。
+
+## 后果
+
+同一条 `pnpm test` 命令在有无内置 Web Storage 的 Node 版本上均可运行。测试 worker 被有意禁止使用 Node 的进程级 Web Storage；未来若产品需要该 API，必须使用独立且显式的测试配置，而不能削弱 jsdom 隔离。兼容性分支只增加一个专项 Vitest 进程，无需在每个 Node 版本上重复整套单元测试。
@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-2026-07-25-client-settings-locale-theme.md: 87077b3fd3f0bd8a3375a71aebf947cbd9961799
-2026-07-25-client-settings-locale-theme.zh.md: a64a4afdf6565a527a25136694aa79305eeabb3c
+#   pnpm run verify-translation-pairing --write .agents/notes/proposed/architecture/2026-07-25-client-settings-locale-theme.md
+2026-07-25-client-settings-locale-theme.md: c86d6ac053f7bb87ce758613a5f3a0a34951e428
+2026-07-25-client-settings-locale-theme.zh.md: 05edbb3c550828832a390e3cf4fad3262b5be196
@@ -55,7 +55,7 @@ root
            └─ models (order 10)         ui-models 注册
 ```

-Section and item contributions both use declaration-aware deferral (ui-slots' `deferRegistration()`: ledger-judged presence, `refresh()` for localized labels, one-call disposal) and do not depend on the client manifest's apply order. The SlotMap types split homes: trigger/header/close/section have their canonical home in the ui-settings contract (the consumers, general and models, both depend on the shell — no cycle); `settings.general.item`'s canonical home is the locale package — it is the lowest common dependency of all item registrants (a settings row always carries copy), while the declarer general's contract is unreachable from locale/ui-theme (it would form a cycle); ui-theme consumes it through a re-export seam.
+Section and item contributions both use declaration-aware deferral (ui-slots' `deferRegistration()`: ledger-judged presence, one-call disposal; localized labels ride the label thunk from the [full-rollout note](../../implemented/architecture/2026-07-30-client-locale-full-rollout.md), not `refresh()`) and do not depend on the client manifest's apply order. The SlotMap types split homes: trigger/header/close/section have their canonical home in the ui-settings contract (the consumers, general and models, both depend on the shell — no cycle); `settings.general.item`'s canonical home is the locale package — it is the lowest common dependency of all item registrants (a settings row always carries copy), while the declarer general's contract is unreachable from locale/ui-theme (it would form a cycle); ui-theme consumes it through a re-export seam.

 ### Future work: promote slot declarations to first-class injectable waits

@@ -55,7 +55,7 @@ root
            └─ models (order 10)         ui-models 注册
 ```

-section/item contribution 均使用 declaration-aware deferral（ui-slots 的 `deferRegistration()`：ledger 判在位、`refresh()` 换本地化 label、一键 dispose），不依赖 client manifest 的 apply 顺序。SlotMap 类型分家：trigger/header/close/section 正家在 ui-settings contract（消费者 general/models 均依赖壳，无环）；`settings.general.item` 正家在 locale 包——它是全部 item 注册方的最低公共依赖（设置行必带文案），而声明方 general 的 contract 对 locale/ui-theme 不可达（会成环）；ui-theme 经 re-export seam 消费。
+section/item contribution 均使用 declaration-aware deferral（ui-slots 的 `deferRegistration()`：ledger 判在位、一键 dispose；本地化 label 走 [全量接入 Note](../../implemented/architecture/2026-07-30-client-locale-full-rollout.md) 的 label thunk，不再 `refresh()`），不依赖 client manifest 的 apply 顺序。SlotMap 类型分家：trigger/header/close/section 正家在 ui-settings contract（消费者 general/models 均依赖壳，无环）；`settings.general.item` 正家在 locale 包——它是全部 item 注册方的最低公共依赖（设置行必带文案），而声明方 general 的 contract 对 locale/ui-theme 不可达（会成环）；ui-theme 经 re-export seam 消费。

 ### Future work：坑位声明升格为可 inject 的一等等待物

@@ -28,6 +28,11 @@ concurrency:
 permissions:
  contents: read

+env:
+  # CI runs must never report to the production telemetry endpoint baked
+  # into apps/cli/cordis.yml (AppCLIEntry disables the row when set).
+  DSH_TELEMETRY_DISABLED: '1'
+
 jobs:
  # Job-level conditions cannot inspect `matrix`, so validate target names and
  # construct the matrix before the dependent jobs.
@@ -24,6 +24,9 @@ permissions:

 env:
  PRIMARY_NODE_VERSION: '24'
+  # CI runs must never report to the production telemetry endpoint baked
+  # into apps/cli/cordis.yml (AppCLIEntry disables the row when set).
+  DSH_TELEMETRY_DISABLED: '1'

 jobs:

@@ -23,6 +23,9 @@ permissions:

 env:
  PRIMARY_NODE_VERSION: '24'
+  # CI runs must never report to the production telemetry endpoint baked
+  # into apps/cli/cordis.yml (AppCLIEntry disables the row when set).
+  DSH_TELEMETRY_DISABLED: '1'

 jobs:
  build:
@@ -46,6 +46,11 @@ concurrency:
 permissions:
  contents: read

+env:
+  # CI runs must never report to the production telemetry endpoint baked
+  # into apps/cli/cordis.yml (AppCLIEntry disables the row when set).
+  DSH_TELEMETRY_DISABLED: '1'
+
 jobs:
  e2e:
    runs-on: ubuntu-latest
@@ -10,6 +10,11 @@ on:
 permissions:
  contents: read

+env:
+  # CI runs must never report to the production telemetry endpoint baked
+  # into apps/cli/cordis.yml (AppCLIEntry disables the row when set).
+  DSH_TELEMETRY_DISABLED: '1'
+
 jobs:
  expected-filenames:
    name: no golden filenames
@@ -19,6 +19,11 @@ concurrency:
 permissions:
  contents: read

+env:
+  # CI runs must never report to the production telemetry endpoint baked
+  # into apps/cli/cordis.yml (AppCLIEntry disables the row when set).
+  DSH_TELEMETRY_DISABLED: '1'
+
 defaults:
  run:
    working-directory: native/landlock-run
@@ -19,6 +19,11 @@ on:
 permissions:
  contents: read

+env:
+  # CI runs must never report to the production telemetry endpoint baked
+  # into apps/cli/cordis.yml (AppCLIEntry disables the row when set).
+  DSH_TELEMETRY_DISABLED: '1'
+
 jobs:
  e2e:
    runs-on: ubuntu-latest
@@ -19,6 +19,11 @@ concurrency:
 permissions:
  contents: read

+env:
+  # CI runs must never report to the production telemetry endpoint baked
+  # into apps/cli/cordis.yml (AppCLIEntry disables the row when set).
+  DSH_TELEMETRY_DISABLED: '1'
+
 jobs:
  # Keyless real-kernel sandbox proofs (sandbox Agent Note § Testing): each ladder
  # rung is only provable on a host where it enforces, so this job fans out
@@ -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: f9f7294b42e29132d5cd46c0ab6a5f5265a1d8f3
-README.zh.md: 88cbf8522d8f1a183a48dc7e80858d1a0ced8f0f
+README.md: baf5d79b157ae845cc837261452853afd48dbe46
+README.zh.md: 57d7bcf44cda36b37ae233754dbfba4ead2204fd
@@ -6,6 +6,16 @@ DeepSeek Harness (`dsh`) is an open-source coding agent built on the DeepSeek Ha

 It uses an architecture where **everything is a plugin**.

+## Internal testing notice
+
+Thank you for making time to try DeepSeek Harness.
+
+This version is still in internal testing. Some features remain unfinished, and parts of the experience may feel rough.
+
+“As one cuts and files, as one carves and polishes.” Products grow through repeated encounters with real use and candid feedback. The problems you uncover in practice may lead us to re-examine, or even discard, existing designs.
+
+We especially want to hear about moments of failure, confusion, or friction. If DeepSeek Harness does not help—or instead makes your work harder—please leave a message in our <a href="https://wj.qq.com/s2/27234598/03eb/">WeCom group</a> and tell us about your experience. Every report will help us refine it.
+
 ## Install

 Install `dsh` with one command:
@@ -22,20 +32,14 @@ The installer keeps every checkout under `~/.dsh/source`: the master clone at `~

 ### Web UI

-For the recommended local interface, build the frontend after installation and after each update, then start the Web UI. Resolve the running checkout from the `dsh` launcher so the command holds regardless of which staging worktree is current (the launcher resolves through the stable `current` symlink):
+For the recommended local interface, build the active checkout after installation and after each update, then start the Web UI:

 ```sh
-dsh_bin=$(cd "$(dirname "$(command -v dsh)")" && pwd -P)/$(basename "$(command -v dsh)")
-while [ -L "$dsh_bin" ]; do
-  link=$(readlink "$dsh_bin")
-  case $link in /*) dsh_bin=$link ;; *) dsh_bin=$(cd "$(dirname "$dsh_bin")" && cd "$(dirname "$link")" && pwd -P)/$(basename "$link") ;; esac
-done
-dsh_dir=$(cd "$(dirname "$dsh_bin")/.." && pwd -P)
-pnpm --dir "$dsh_dir" run build && pnpm --dir "$dsh_dir" run build:web
+(cd ~/.dsh/source/current && pnpm run build)
 dsh web
 ```

-The Web UI is served at `http://127.0.0.1:3080` by default.
+The full build produces the library and client bundles plus the frontend dist. 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.

 ### TUI

@@ -53,11 +57,22 @@ Run one task, print the final answer, and exit:
 dsh -p "summarize this workspace"
 ```

+### Automation and SDKs
+
+From a source checkout with `DEEPSEEK_API_KEY` in the environment or its root `.env`, start the ACP automation server:
+
+```sh
+pnpm run demo:acp
+```
+
+The [Python SDK](python/README.md) drives a bundled JSON-RPC runtime. The [examples](examples/README.md) cover the runnable headless, ACP, JSON-RPC, Code Mode, and self-referential compositions.
+
 ## Why DeepSeek Harness

-Built-in capabilities cover file reading, editing, and search; shell execution; reusable skills; task tracking; subagents and workflows; persistent sessions; and context compaction. The TUI also includes Plan Mode.
+Built-in capabilities cover file reading, editing, and search; shell and persistent PTY execution; reusable skills; task tracking, goals, plans, todos, and background tasks; subagents and workflows; sandboxing and approvals; settings and credentials; persistent, resumable, forkable, and queryable sessions; LSP and web access; context compaction; and telemetry. Each composition selects the subset appropriate to its surface. The TUI and Web UI both include Plan Mode.

 - **Everything is a plugin.** Models, tools, policies, storage, context management, and interfaces are composable [Cordis plugins](docs/user/develop/basic/index.md), so deployments can extend or replace behavior without forking the agent loop. See the [architecture](docs/architecture.md) for the underlying design.
+- **Runs are reconstructable.** Anything visible to the model is logged in the authoritative session stream; persistence, resume/fork/query, replay, telemetry, and UIs derive from the same events. See the [session-log architecture](docs/architecture.md#session-log).
 - **Code Mode (opt-in).** It exposes a `run_code` tool and a generated TypeScript SDK; only program output re-enters model context. See [Code Mode](packages/core/tools/README.md#code-mode).
 - **Self-referential Cordis tools are opt-in.** They let the agent inspect its live runtime and mount or unmount plugins while it runs. See the [Cordis tools](packages/cordis/tool-cordis/README.md).

@@ -76,7 +91,7 @@ Start with the [development guide](docs/development.md) and read the [architectu

 For agents, follow [AGENTS.md](AGENTS.md).

-DeepSeek Harness is currently pre-release.
+DeepSeek Harness is currently in internal testing.

 ## License

@@ -6,6 +6,16 @@ DeepSeek Harness（`dsh`）是一款基于 DeepSeek Harness SDK 构建的开源

 它采用了**一切皆插件**的架构。

+## 内测声明
+
+感谢您愿意拨冗试用 DeepSeek Harness。
+
+目前的版本仍处于内部测试阶段，有些功能仍待完善，有些体验难免粗粝。
+
+“如切如磋，如琢如磨。”产品的成长，离不开一次次真实的碰撞与坦诚的反馈。您在真实使用中暴露的问题，也可能促使我们重新审视，甚至推翻已有的设计。
+
+我们尤其希望听见那些失败、困惑与不顺手的时刻——如果它未能帮到您，甚至反而为工作平添了麻烦，请在企业微信群中留言，将使用感受告诉我们。每一条反馈，都会帮助我们把它打磨得更好。
+
 ## 安装

 使用一条命令安装 `dsh`：
@@ -22,20 +32,14 @@ curl -fsSL https://raw.githubusercontent.com/deepseek-harness/deepseek-harness/m

 ### Web UI

-推荐在本地使用 Web UI。安装完成后以及每次更新后，请先构建前端，再启动 Web UI。通过 `dsh` 启动器解析当前运行的检出，这样无论当前是哪个 staging worktree，命令都成立（启动器会经由稳定的 `current` 符号链接解析）：
+推荐在本地使用 Web UI。安装完成后以及每次更新后，请先构建当前生效的检出，再启动 Web UI：

 ```sh
-dsh_bin=$(cd "$(dirname "$(command -v dsh)")" && pwd -P)/$(basename "$(command -v dsh)")
-while [ -L "$dsh_bin" ]; do
-  link=$(readlink "$dsh_bin")
-  case $link in /*) dsh_bin=$link ;; *) dsh_bin=$(cd "$(dirname "$dsh_bin")" && cd "$(dirname "$link")" && pwd -P)/$(basename "$link") ;; esac
-done
-dsh_dir=$(cd "$(dirname "$dsh_bin")/.." && pwd -P)
-pnpm --dir "$dsh_dir" run build && pnpm --dir "$dsh_dir" run build:web
+(cd ~/.dsh/source/current && pnpm run build)
 dsh web
 ```

-Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。
+完整构建会生成库与客户端 bundle，以及前端 dist。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。

 ### TUI

@@ -53,11 +57,22 @@ dsh
 dsh -p "summarize this workspace"
 ```

+### 自动化与 SDK
+
+在源码检出中通过环境变量或根目录 `.env` 设置 `DEEPSEEK_API_KEY`，然后启动 ACP（Agent Client Protocol）自动化服务器：
+
+```sh
+pnpm run demo:acp
+```
+
+[Python SDK](python/README.md) 驱动随附的 JSON-RPC 运行时。[示例](examples/README.md)涵盖可运行的 headless、ACP、JSON-RPC、Code Mode 和自指组合。
+
 ## 为什么选择 DeepSeek Harness

-内置功能涵盖文件读取、编辑与搜索、shell 执行、可复用 skill（技能）、任务跟踪、subagent 与工作流、持久化会话，以及上下文压缩（context compaction）。TUI 还包含 Plan Mode。
+内置功能涵盖文件读取、编辑与搜索、shell 和持久 PTY 执行、可复用 skill（技能）、任务跟踪、目标、计划、待办事项与后台任务、subagent 与工作流、沙箱与审批、设置与凭据、可持久化、恢复、fork 与查询的会话、LSP 与 Web 访问、上下文压缩（context compaction），以及遥测。每个组合只选用适合其使用方式的能力子集。TUI 与 Web UI 均包含 Plan Mode。

 - **一切皆插件。** 模型、工具、策略、存储、上下文管理和界面均可组合为 [Cordis 插件](docs/user/develop/basic/index.md)，部署方无需 fork agent loop（智能体循环）即可扩展或替换行为。底层设计见[架构文档](docs/architecture.md)。
+- **运行可重建。** 凡是模型可见的内容，都会记录在权威会话流中；持久化、恢复／fork／查询、回放、遥测和 UI 均从同一组事件派生。参见[会话日志架构](docs/architecture.md#session-log)。
 - **Code Mode（需显式启用）。** 它会提供 `run_code` 工具和生成的 TypeScript SDK，只有程序输出会重新进入模型上下文。参见 [Code Mode](packages/core/tools/README.md#code-mode)。
 - **自指 Cordis 工具需显式启用。** 这些工具可让 agent 检查自身的实时运行时，并在运行中挂载或卸载插件。参见 [Cordis 工具](packages/cordis/tool-cordis/README.md)。

@@ -80,7 +95,7 @@ pnpm run test:coverage

 面向 agent：遵循 [AGENTS.md](AGENTS.md)。

-DeepSeek Harness 目前处于预发布阶段。
+DeepSeek Harness 目前处于内测阶段。

 ## 许可证

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write apps/cli/README.md
-README.md: d783d75cc9747d13887386fcf7609a6778e5dfb5
-README.zh.md: 3f5ce7e7a3a302fd9e255c1042ccb7b03deb59d9
+README.md: c36a75fc61fd7118f48c9b68be3144177df19534
+README.zh.md: e926fa99c4e483351f52ca4e76b668e26b34d02f
@@ -17,13 +17,14 @@ The TUI surface:

 `dsh upgrade` is a guided fresh-session entry over the default TUI surface: it mints a fresh session in the invoking directory and seeds its first turn with the bundled `dsh-upgrade` skill, exactly as if the user typed `/skill:<name>`. The launcher passes the skill name on the boot context ([`INITIAL_SKILL_KEY`](../../packages/ui/tui/README.md)), which the TUI auto-invokes once the chat is live. Both take no options — `--config`, `-p`, and `--resume` fail loud — and seed only on this first launch, so a later `dsh --resume <id>` of the session is an ordinary TUI session with no re-injection.

-
-The Web and headless surfaces boot `base.cordis.yml` plus `web.cordis.yml`, then apply `$DSH_HOME/config.yaml`; an explicit `--config <path>` replaces that personal overlay. Both surfaces otherwise share the same composition: both treat the invoking directory as the default project and Workspace root, create named Workspaces beneath that root unless `--workspace-root <path>` overrides it, load applicable `AGENTS.md`/`CLAUDE.md` instructions into each agent-loop request prefix with a 65,536-byte render budget, and opt into first-message model titles. Headless differs only in listening on an OS-assigned port (parallel `dsh -p` runs never collide; the stderr-printed URL opens the live session in a browser). Both need the frontend dist and client bundles built (`pnpm run build && pnpm run build:web`).
+The Web and headless surfaces boot `base.cordis.yml` plus `web.cordis.yml`, then apply `$DSH_HOME/config.yaml`; an explicit `--config <path>` replaces that personal overlay. Both surfaces otherwise share the same composition: both treat the invoking directory as the default project and Workspace root, create named Workspaces beneath that root unless `--workspace-root <path>` overrides it, load applicable `AGENTS.md`/`CLAUDE.md` instructions into each agent-loop request prefix with a 65,536-byte render budget, opt into first-message model titles, use the same bounded transient model-request retry policy as the TUI, and mount a disposable in-memory SQLite content-index service. That service is ACTIVE at boot, while its `node:sqlite` module and database handle open only on the first content search. This keeps Node 22 startup output free of SQLite's experimental warning before search is used; the first actual search may still emit the runtime warning. Each service instance owns its database, so parallel invocations neither share unsupported SQLite state nor leave derived index files behind, and the first search lazily reconciles live and persisted logs. Headless differs only in listening on an OS-assigned port (parallel `dsh -p` runs never collide; the stderr-printed URL opens the live session in a browser). Both need the frontend dist and client bundles built (`pnpm run build && pnpm run build:web`).

 The shipped TUI and Web compositions register the native DeepSeek adapter plus pi-ai OpenAI and Anthropic profiles. Credentials and endpoint overrides come from the provider-standard `DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL`, `OPENAI_API_KEY` / `OPENAI_BASE_URL`, and `ANTHROPIC_API_KEY` / `ANTHROPIC_BASE_URL` pairs in the boot's layered environment.

 `DSH_TOOLS_MODE` selects the tool presentation mode for the whole Web/headless process: `native` (the schema default when unset), `code` (the `run_code`-only Code Mode wire), or `both`; any other value fails loud at boot through the `dsh-tools` config schema. It is a TEMPORARY seam — process-wide because Loader composition is static — and is removed once the web UI owns per-session tool-mode selection; the TUI surface ignores it (its config tree pins its own mode).

+Every `dsh` surface — TUI, Web, and headless — reports session telemetry by default (the row lives in the shared `base.cordis.yml`): every session-log event streams as OTLP/HTTP log records to `https://harness-telemetry.deepseeksvc.com/v1/logs` on a 10-second batch cadence. `DSH_TELEMETRY_OTLP_URL` points the exporter at a different collector; setting `DSH_TELEMETRY_DISABLED` to ANY non-empty value — including `0` or `false` — disables the row before it loads (a privacy switch prefers off-by-mistake over on-by-mistake). No redaction rule is mounted in this composition yet: exported records are the raw captured copy, including message text, tool arguments and results, and the session's working-directory path. The deployment rulings live in the [web-telemetry-default-mount Agent Note](../../.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md).
+
 ## Install (developer machine)

 Symlink the source-running launcher onto your PATH; it resolves the checkout through its own real path, so code changes apply on the next launch with no build step:
@@ -17,13 +17,14 @@ TUI 界面：

 `dsh upgrade` 是默认 TUI 界面之上的引导式全新会话入口：它在调用目录中创建一个全新会话，并以内置 `dsh-upgrade` skill 播种其首轮，效果等同于用户手动键入 `/skill:<name>`。启动器将 skill 名称提供到启动上下文（[`INITIAL_SKILL_KEY`](../../packages/ui/tui/README.md)），TUI 在聊天就绪后自动调用它。两者都不接受任何选项——`--config`、`-p`、`--resume` 都会明确报错——且仅在首次启动时播种，因此之后 `dsh --resume <id>` 恢复该会话时是普通 TUI 会话，不会重复注入。

-
-Web 和无头界面启动 `base.cordis.yml` 与 `web.cordis.yml`，随后应用 `$DSH_HOME/config.yaml`；显式的 `--config <path>` 会替代该个人覆盖。除此之外，两者共享同一套组合：两者都将调用目录视为默认项目和 Workspace 根目录，除非通过 `--workspace-root <path>` 覆盖，否则会在该根目录下创建具名 Workspace；它们会把适用的 `AGENTS.md`/`CLAUDE.md` 指令加载到每个 agent-loop 请求前缀中，渲染预算为 65,536 字节，并选用首条消息模型标题。无头界面唯一的差异是监听操作系统分配的端口（并行 `dsh -p` 运行绝不冲突；stderr 打印的 URL 会在浏览器中打开实时会话）。两者都需要先构建前端 dist 和客户端 bundle（`pnpm run build && pnpm run build:web`）。
+Web 和无头界面启动 `base.cordis.yml` 与 `web.cordis.yml`，随后应用 `$DSH_HOME/config.yaml`；显式的 `--config <path>` 会替代该个人覆盖。除此之外，两者共享同一套组合：两者都将调用目录视为默认项目和 Workspace 根目录，除非通过 `--workspace-root <path>` 覆盖，否则会在该根目录下创建具名 Workspace；它们会把适用的 `AGENTS.md`/`CLAUDE.md` 指令加载到每个 agent-loop 请求前缀中，渲染预算为 65,536 字节，选用首条消息模型标题，采用与 TUI 相同的有界暂时性模型请求重试策略，并挂载一个可丢弃的内存 SQLite 内容索引服务。该服务在启动时处于 ACTIVE 状态，但其 `node:sqlite` 模块与数据库句柄分别要到首次内容搜索才会导入和打开。这样可使 Node 22 在尚未使用搜索时的启动输出不出现 SQLite 实验性警告；首次实际搜索仍可能发出运行时警告。每个服务实例独占自己的数据库，因此并行调用既不会共享不受支持的 SQLite 状态，也不会留下派生索引文件，首次搜索还会惰性对账实时日志与持久化日志。无头界面唯一的差异是监听操作系统分配的端口（并行 `dsh -p` 运行绝不冲突；stderr 打印的 URL 会在浏览器中打开实时会话）。两者都需要先构建前端 dist 和客户端 bundle（`pnpm run build && pnpm run build:web`）。

 已交付的 TUI 和 Web 组合会注册原生 DeepSeek 适配器，以及 pi-ai 的 OpenAI 和 Anthropic 提供方配置。凭据和端点覆盖来自启动分层环境中的提供方标准变量对：`DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL`、`OPENAI_API_KEY` / `OPENAI_BASE_URL` 和 `ANTHROPIC_API_KEY` / `ANTHROPIC_BASE_URL`。

 `DSH_TOOLS_MODE` 为整个 Web／无头进程选择工具呈现模式：可选值为 `native`（未设置时的 schema 默认值）、`code`（仅含 `run_code` 的 Code Mode 协议接口）或 `both`；任何其他值都会经由 `dsh-tools` 配置 schema 在启动时明确报错。它是一个临时 seam：Loader 组合是静态的，因此该设置作用于整个进程；待 Web UI 负责逐会话工具模式选择后便会移除。TUI 界面会忽略该变量（其配置树固定了自身模式）。

+每个 `dsh` 界面——TUI、Web 与无头——都默认上报会话遥测（该行位于共享的 `base.cordis.yml`）：每条会话日志事件以 OTLP/HTTP 日志记录的形式、按 10 秒批处理节奏流向 `https://harness-telemetry.deepseeksvc.com/v1/logs`。`DSH_TELEMETRY_OTLP_URL` 可将 exporter 指向其他 collector；将 `DSH_TELEMETRY_DISABLED` 设为**任意非空值**——包括 `0` 或 `false`——都会在该行加载前将其关停（隐私开关取「宁可误关、不可误开」）。该组合当前未挂载任何脱敏规则：导出记录即原始捕获副本，包含消息正文、工具参数与结果、以及会话工作目录路径。部署口径见 [web-telemetry-default-mount Agent Note](../../.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md)。
+
 ## 安装（开发机）

 将从源码运行的启动器符号链接到 PATH 上；它通过自身真实路径解析 checkout，因此代码更改会在下次启动时生效，无需构建：
@@ -38,6 +38,8 @@ flowchart LR
  cfg --> plugin_tui_session_persistence_jsonl
  plugin_tui_session_query_sqlite["session-query-sqlite<br/>@deepseek-ai/dsh-session-query-sqlite"]
  cfg --> plugin_tui_session_query_sqlite
+  plugin_tui_telemetry_otel["telemetry-otel<br/>@deepseek-ai/dsh-session-telemetry-otel"]
+  cfg --> plugin_tui_telemetry_otel
  plugin_tui_subprocess["subprocess<br/>@deepseek-ai/dsh-subprocess-local"]
  cfg --> plugin_tui_subprocess
  plugin_tui_bash_local["bash-local<br/>@deepseek-ai/dsh-bash-local"]
@@ -123,6 +125,7 @@ flowchart LR
 | `llm-pi-ai` | `@deepseek-ai/dsh-llm-pi-ai` |
 | `session-persistence-jsonl` | `@deepseek-ai/dsh-session-persistence-jsonl` |
 | `session-query-sqlite` | `@deepseek-ai/dsh-session-query-sqlite` |
+| `telemetry-otel` | `@deepseek-ai/dsh-session-telemetry-otel` |
 | `subprocess` | `@deepseek-ai/dsh-subprocess-local` |
 | `bash-local` | `@deepseek-ai/dsh-bash-local` |
 | `tool-bash` | `@deepseek-ai/dsh-tool-bash` |
@@ -88,12 +88,45 @@
      (() => { const path = process.getBuiltinModule('node:path'); const home = process.getBuiltinModule('node:os').homedir(); const configured = process.env.DSH_HOME; const selected = configured !== undefined && configured.trim().length > 0 ? configured : path.join(home, '.dsh'); const expanded = selected === '~' ? home : selected.startsWith('~/') || selected.startsWith('~\\') ? path.join(home, selected.slice(2)) : selected; return path.join(path.resolve(expanded), 'sessions') })()

 # TUI consumes this shared session capability. Its launcher supplies a unique
-# process-local path; non-TUI surfaces disable the row in their overlay.
+# process-local path; other surfaces repoint or disable the row in their
+# overlay (web patches it to an ephemeral in-memory index).
 - id: session-query-sqlite
  name: '@deepseek-ai/dsh-session-query-sqlite'
  config:
    path: !!js launcherSessionQueryPath ?? './.sessions/session-query.db'

+# Session telemetry, on for every dsh surface: mirrors every session-log
+# event (assistant/chunk projected to first-of-step) plus ops markers onto
+# OTLP/HTTP log records, streaming on the batch processor's cadence
+# (10s/batch here) — not at exit; a crash loses at most the last unexported
+# interval. No telemetry/record redaction rule is mounted yet, so exports
+# are the raw captured copy; the deployment stance, env seams, and
+# follow-ups are pinned in the web-telemetry-default-mount Agent Note.
+# DSH_TELEMETRY_OTLP_URL overrides the production endpoint, and a non-empty
+# DSH_TELEMETRY_DISABLED — any value, including '0'/'false' — opts the
+# process out (the launchers patch the row disabled; config cannot disable
+# a row). The exporter/processor values bound the shutdown drain to ~1s
+# against an unreachable collector: exporter.timeoutMillis is both the
+# per-attempt socket timeout and the retry deadline (1s effectively
+# disables the SDK's 5-try backoff), maxExportBatchSize == maxQueueSize
+# (both explicit) makes the drain a single batch, and exportTimeoutMillis
+# is the processor's own cap on that one export cycle — the second bound
+# when the exporter's clock alone does not fire. Every surface's exit path
+# drains it: web/headless dispose on SIGINT/SIGTERM, and the TUI's normal
+# exit and /resume handoff both dispose the root.
+- id: telemetry-otel
+  name: '@deepseek-ai/dsh-session-telemetry-otel'
+  config:
+    exporter:
+      url: !!js process.env.DSH_TELEMETRY_OTLP_URL ?? 'https://harness-telemetry.deepseeksvc.com/v1/logs'
+      compression: gzip
+      timeoutMillis: 1000
+    processor:
+      scheduledDelayMillis: 10000
+      maxQueueSize: 2048
+      maxExportBatchSize: 2048
+      exportTimeoutMillis: 1500
+
 - id: subprocess
  name: '@deepseek-ai/dsh-subprocess-local'

@@ -36,8 +36,8 @@
      Verify your work by running the code or tests. Keep answers brief and
      factual.

-# Shipped default: full thinking at max effort on every request (wire-only
-# defaults; they never enter the request header).
+# Shipped default: full thinking at max effort on every request. Exact-model
+# resolution materializes request defaults before the request header is logged.
 - id: llm-deepseek
  config:
    apiKey: !!js process.env.DEEPSEEK_API_KEY
@@ -14,9 +14,14 @@
 - id: hmr
  disabled: true

-# Session query is a TUI capability; Web owns its own session presentation.
+# Web content search runs on an ephemeral in-memory index. The service
+# activates at boot, while first-search defers the node:sqlite import and
+# in-memory handle so Node 22 startup stays quiet until content search
+# actually uses SQLite. That search then reconciles this boot's sources.
 - id: session-query-sqlite
-  disabled: true
+  config:
+    path: ':memory:'
+    openAt: first-search

 - id: tools
  config:
@@ -79,8 +79,10 @@
    "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
    "@deepseek-ai/dsh-session-projection": "workspace:^",
    "@deepseek-ai/dsh-session-projection-cache": "workspace:^",
+    "@deepseek-ai/dsh-session-query": "workspace:^",
    "@deepseek-ai/dsh-session-query-sqlite": "workspace:^",
    "@deepseek-ai/dsh-session-reference": "workspace:^",
+    "@deepseek-ai/dsh-session-telemetry-otel": "workspace:^",
    "@deepseek-ai/dsh-session-title": "workspace:^",
    "@deepseek-ai/dsh-session-title-first-message-llm": "workspace:^",
    "@deepseek-ai/dsh-settings-local": "workspace:^",
@@ -123,7 +125,9 @@
    "js-yaml": "^4.2.0"
  },
  "devDependencies": {
+    "@deepseek-ai/dsh-llm-mock-server": "workspace:^",
    "@types/js-yaml": "^4.0.9",
+    "execa": "^10.0.0",
    "node-pty": "1.1.0"
  }
 }
@@ -3,7 +3,7 @@
 * for the Web/headless surface.
 * Everything here is what must exist before the Loader runs: the patch
 * composition over the shipped base and surface overlay (profile json + CLI
- * flags + the resolved frontend dist), and the fail-loud triple after the tree
+ * flags + the resolved frontend dist), and the fail-loud activation audit after the tree
 * settles. The environment is what the bin already loaded (ambient plus the
 * invoking directory's `.env`); `$DSH_HOME/.env` belongs to the credential
 * provider and is never hoisted here.
@@ -24,6 +24,9 @@ import type {} from '@deepseek-ai/dsh-host-webserver'
 const PROFILE_DIR = '.dsh-tmp-profile'
 const PROFILE_FILE = 'config.json'

+/** The session-telemetry row id the DSH_TELEMETRY_DISABLED switch targets (mounted in web.cordis.yml). */
+const TELEMETRY_ROW_ID = 'telemetry-otel'
+
 /** The webserver schema's all-interfaces bind literal: gates LAN-authority derivation here and the printed LAN URL in web.ts. */
 const ALL_INTERFACES_HOST = '0.0.0.0'

@@ -59,6 +62,38 @@ export function resolveLanTrust(
  return { lanAddresses, trustedHosts: [...lanAddresses, ...extra] }
 }

+/**
+ * Resolve the telemetry opt-out switch into its boot patch. ANY non-empty
+ * value (including `'0'`/`'false'`) disables: a privacy switch prefers
+ * off-by-mistake over on-by-mistake. Throws when the switch is set but the
+ * row is absent — a silently no-op "disabled" privacy switch would keep
+ * exporting while the user believes it is off.
+ * @param disabledEnv - the raw `DSH_TELEMETRY_DISABLED` value (`undefined` when unset).
+ * @param hasRow - whether the composition carries the {@link TELEMETRY_ROW_ID} row.
+ * @returns the disable patch, or `undefined` when telemetry stays enabled.
+ */
+export function resolveTelemetryPatch(disabledEnv: string | undefined, hasRow: boolean): PatchOptions | undefined {
+  if ((disabledEnv ?? '') === '') return undefined
+  if (!hasRow) {
+    throw new Error(`dsh: DSH_TELEMETRY_DISABLED is set but row "${TELEMETRY_ROW_ID}" is not in this composition`)
+  }
+  return { id: TELEMETRY_ROW_ID, disabled: true }
+}
+
+/**
+ * Whether a config file carries the telemetry row, parsed under the same
+ * `!!js`-tolerant dialect the boot uses — the `hasRow` input for launchers
+ * that compose their patch lists outside {@link AppCLIEntry} (the TUI).
+ * @param file - absolute path of the config or overlay file.
+ * @returns true when a top-level (or inserted) row has the telemetry id.
+ */
+export function configHasTelemetryRow(file: string): boolean {
+  const doc = yaml.load(readFileSync(file, 'utf8'), { schema: includeYamlSchema })
+  if (!Array.isArray(doc)) throw new Error(`dsh: ${file} is not a top-level entry list`)
+  return (doc as { id?: string; insert?: { id?: string }[] }[]).some(row =>
+    row.id === TELEMETRY_ROW_ID || (row.insert ?? []).some(inserted => inserted.id === TELEMETRY_ROW_ID))
+}
+
 /** One profile-json key mapped onto a yml row's config field. */
 interface ProfileMapping {
  jsonPath: string
@@ -203,9 +238,15 @@ export class AppCLIEntry {
      if (yml === undefined) throw new Error(`dsh: patch target row "${id}" not found in ${this.options.configPath}`)
      return { id, config: { ...(yml.config ?? {}) as Record<string, unknown>, ...bag } }
    })
+
+    // Telemetry opt-out: a row can only be turned off at the patch layer
+    // (config cannot disable an entry), and the switch must hold BEFORE the
+    // plugin constructs — its exporter.url validation is load-time fail-loud.
+    const telemetryPatch = resolveTelemetryPatch(process.env.DSH_TELEMETRY_DISABLED, rows.has(TELEMETRY_ROW_ID))
+    if (telemetryPatch !== undefined) this.patches.push(telemetryPatch)
  }

-  /** Shared Loader boot; the dev HMR row mounts before await so the fail-loud sweep covers it. */
+  /** Shared Loader boot; the dev HMR row mounts before await so the activation audit covers it. */
  private async bootTree(): Promise<void> {
    // One include of the shared base with every overlay as a sibling patch
    // list: patches never cross an include boundary, so nesting them would
@@ -82,6 +82,17 @@ export async function runHeadless(task: string): Promise<void> {
  })
  const { ctx, port } = await entry.run()
  const dispose = async (): Promise<void> => { await ctx.fiber.dispose() }
+  // Signal exits must still dispose the tree: the composition mounts
+  // exit-drained plugins (telemetry's queued tail and shutdown marker would
+  // otherwise be lost), and Node's default signal exit skips disposal.
+  let signalled = false
+  const disposeAndExit = (code: number): void => {
+    if (signalled) return
+    signalled = true
+    void dispose().finally(() => { process.exit(code) })
+  }
+  process.on('SIGTERM', () => { disposeAndExit(143) })
+  process.on('SIGINT', () => { disposeAndExit(130) })
  // The headless session is web-observable while it runs (same composition).
  process.stderr.write(`dsh: observing at http://127.0.0.1:${String(port)}\n`)
  const api = new InProcessApiClient(toFetchHandler(ctx.apiProxy))
@@ -31,6 +31,7 @@ import {
  resolveConfigPath,
 } from '@deepseek-ai/dsh-app-boot'
 import { SessionId } from '@deepseek-ai/dsh-session'
+import { configHasTelemetryRow, resolveTelemetryPatch } from './app-cli-entry.ts'
 import { SESSION_QUERY_SQLITE_PATH_KEY } from '@deepseek-ai/dsh-session-query-sqlite'
 import { CONFIGURED_AGENT_IDENTITIES_KEY } from '@deepseek-ai/dsh-agent-loop'
 import type { Context } from 'cordis'
@@ -196,16 +197,26 @@ export async function runTui(
  // demo or test config would silently run on the user's provider and model.
  // `--config-replace` additionally discards the base and the surface overlay.
  const replaceTree = configReplace !== undefined
-  const patches = replaceTree ? [] : [
-    ...loadOverlayPatches(NAME, TUI_OVERLAY),
-    ...resolvedConfig === undefined
-      ? loadPersonalPatches(NAME) ?? []
-      : loadOverlayPatches(NAME, resolveConfigPath(resolvedConfig, undefined)),
+  const bootConfig = resolvedConfigReplace === undefined ? BASE_CONFIG : resolveConfigPath(resolvedConfigReplace, undefined)
+  // Same opt-out semantics as the web surface (resolveTelemetryPatch: any
+  // non-empty value disables; setting the switch against a tree without the
+  // row fails loud rather than silently no-opping a privacy switch). The row
+  // presence is checked against the tree actually booting, so a
+  // --config-replace tree is judged on its own rows, not the shipped base's.
+  const telemetryPatch = resolveTelemetryPatch(process.env.DSH_TELEMETRY_DISABLED, configHasTelemetryRow(bootConfig))
+  const patches = [
+    ...replaceTree ? [] : [
+      ...loadOverlayPatches(NAME, TUI_OVERLAY),
+      ...resolvedConfig === undefined
+        ? loadPersonalPatches(NAME) ?? []
+        : loadOverlayPatches(NAME, resolveConfigPath(resolvedConfig, undefined)),
+    ],
+    ...telemetryPatch === undefined ? [] : [telemetryPatch],
  ]
  const queryIndexPath = join(tmpdir(), SESSION_QUERY_DB)
  const ctx = await boot(
    NAME,
-    resolvedConfigReplace === undefined ? BASE_CONFIG : resolveConfigPath(resolvedConfigReplace, undefined),
+    bootConfig,
    patches,
    (hostCtx) => {
      // The launcher owns session identity and the exit line: a config-mounted
@@ -57,12 +57,14 @@ export async function runWeb(
    void Promise.resolve(ctx.fiber.dispose()).finally(() => { process.exit(code) })
  }

+  // Install shutdown handling before publishing readiness: supervisors may
+  // send a signal as soon as they observe the URL line.
+  process.on('SIGTERM', () => { shutdown(0) })
+  process.on('SIGINT', () => { shutdown(130) })
+
  // The entry's boot-time snapshot, not a fresh sample: the printed LAN URL
  // must name an address the /api trust fence was configured with.
  const lanCandidate = entry.lanAddresses[0]
  const localUrl = `http://${LOOPBACK_HOST}:${boundPort}`
  console.log(`dsh web: ${localUrl}${lanCandidate === undefined ? '' : ` (LAN: http://${lanCandidate}:${boundPort})`}`)
-
-  process.on('SIGTERM', () => { shutdown(0) })
-  process.on('SIGINT', () => { shutdown(130) })
 }
@@ -0,0 +1,112 @@
+/**
+ * Node 22 startup-output smoke for the shipped Web CLI composition.
+ *
+ * Only the dedicated Node compatibility gate opts this test in after building
+ * both artifacts; ordinary Vitest inventory deterministically skips it.
+ * The child runs built artifacts under plain Node with the real shipped
+ * config (base.cordis.yml + the web.cordis.yml overlay).
+ * Its URL line follows AppCLIEntry's settled boot; SIGTERM then exercises the
+ * shipped quiescent disposer.
+ */
+
+import { spawn } from 'node:child_process'
+import { existsSync } from 'node:fs'
+import { mkdtemp, readFile, rm } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join, resolve } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import yaml from 'js-yaml'
+import { describe, expect, it } from 'vitest'
+
+const repoRoot = fileURLToPath(new URL('../../../', import.meta.url))
+const builtBin = join(repoRoot, 'apps/cli/lib/bin.js')
+const webDist = join(repoRoot, 'apps/web/dist/index.html')
+// The web overlay owns the session-query-sqlite lazy-open patch row.
+const configPath = join(repoRoot, 'apps/cli/config/web.cordis.yml')
+const requireBuiltArtifacts = process.env.DSH_REQUIRE_BUILT_CLI_SMOKE === '1'
+
+interface ConfigRow {
+  id?: string
+  config?: { openAt?: unknown }
+}
+
+const jsExprType = new yaml.Type('tag:yaml.org,2002:js', {
+  kind: 'scalar',
+  construct: value => String(value),
+})
+const configSchema = yaml.JSON_SCHEMA.extend(jsExprType)
+
+/** Boot the built Web CLI, wait for its settled URL, then dispose through SIGTERM. */
+function runBuiltWeb(cwd: string): Promise<{ stdout: string; stderr: string; code: number }> {
+  return new Promise((resolveRun, rejectRun) => {
+    const env: NodeJS.ProcessEnv = {
+      ...process.env,
+      DEEPSEEK_API_KEY: 'dsh-cli-smoke-dummy-key',
+      DSH_HOME: join(cwd, '.dsh'),
+    }
+    delete env.DEEPSEEK_BASE_URL
+    delete env.NODE_OPTIONS
+    delete env.NODE_NO_WARNINGS
+    const child = spawn(process.execPath, [
+      builtBin,
+      'web',
+      '--host',
+      '127.0.0.1',
+      '--port',
+      '0',
+    ], {
+      cwd,
+      env,
+      stdio: ['ignore', 'pipe', 'pipe'],
+    })
+    let stdout = ''
+    let stderr = ''
+    let settled = false
+    child.stdout.setEncoding('utf8')
+    child.stderr.setEncoding('utf8')
+    child.stdout.on('data', (chunk: string) => {
+      stdout += chunk
+      if (!settled && /dsh web: http:\/\/127\.0\.0\.1:\d+/u.test(stdout)) {
+        settled = true
+        child.kill('SIGTERM')
+      }
+    })
+    child.stderr.on('data', (chunk: string) => { stderr += chunk })
+    const timer = setTimeout(() => {
+      child.kill('SIGKILL')
+      rejectRun(new Error(`built Web CLI did not settle and dispose within 60s\nstdout:\n${stdout}\nstderr:\n${stderr}`))
+    }, 60_000)
+    child.on('error', (error) => {
+      clearTimeout(timer)
+      rejectRun(error)
+    })
+    child.on('close', (code) => {
+      clearTimeout(timer)
+      if (!settled) {
+        rejectRun(new Error(`built Web CLI exited before settled startup (code ${String(code)})\nstdout:\n${stdout}\nstderr:\n${stderr}`))
+        return
+      }
+      resolveRun({ stdout, stderr, code: code ?? -1 })
+    })
+  })
+}
+
+describe.skipIf(!requireBuiltArtifacts)('built CLI lazy-search startup', () => {
+  it('boots and disposes the shipped composition without a SQLite startup warning', async () => {
+    expect(existsSync(builtBin), `missing built CLI ${resolve(builtBin)}; run pnpm build`).toBe(true)
+    expect(existsSync(webDist), `missing Web dist ${resolve(webDist)}; run pnpm run build:web`).toBe(true)
+    const rows = yaml.load(await readFile(configPath, 'utf8'), { schema: configSchema }) as ConfigRow[]
+    const searchRow = rows.find(row => row.id === 'session-query-sqlite')
+    expect(searchRow?.config?.openAt).toBe('first-search')
+
+    const cwd = await mkdtemp(join(tmpdir(), 'dsh-cli-lazy-search-'))
+    try {
+      const result = await runBuiltWeb(cwd)
+      expect(result.stdout).toMatch(/dsh web: http:\/\/127\.0\.0\.1:\d+/u)
+      expect(result.code).toBe(0)
+      expect(result.stderr).not.toMatch(/ExperimentalWarning: SQLite/u)
+    } finally {
+      await rm(cwd, { recursive: true, force: true })
+    }
+  }, 70_000)
+})
@@ -0,0 +1,23 @@
+import { describe, expect, it } from 'vitest'
+import { resolveTelemetryPatch } from '../src/app-cli-entry.ts'
+
+describe('resolveTelemetryPatch', () => {
+  it('keeps telemetry enabled when the switch is unset or empty', () => {
+    expect(resolveTelemetryPatch(undefined, true)).toBeUndefined()
+    expect(resolveTelemetryPatch('', true)).toBeUndefined()
+  })
+
+  it('disables on ANY non-empty value, including falsy-looking ones', () => {
+    for (const value of ['1', '0', 'false', 'no']) {
+      expect(resolveTelemetryPatch(value, true)).toEqual({ id: 'telemetry-otel', disabled: true })
+    }
+  })
+
+  it('fails loud when the switch is set but the row is absent', () => {
+    expect(() => resolveTelemetryPatch('1', false)).toThrow('DSH_TELEMETRY_DISABLED is set but row "telemetry-otel" is not in this composition')
+  })
+
+  it('ignores a missing row while the switch is unset', () => {
+    expect(resolveTelemetryPatch(undefined, false)).toBeUndefined()
+  })
+})
@@ -130,7 +130,9 @@ function smoke(overrides: Partial<TuiPtySmokeOptions> & { label: string }): Prom
    tempDirPrefix: 'dsh-tui-smoke-',
    binScript: dshBinScript,
    tsconfigPath,
-    env: { DEEPSEEK_API_KEY: 'keyless-tui-no-call' },
+    // Telemetry now mounts in the shared base: keep fixture sessions from
+    // POSTing to the production endpoint when run outside CI's workflow env.
+    env: { DEEPSEEK_API_KEY: 'keyless-tui-no-call', DSH_TELEMETRY_DISABLED: '1' },
    // Artifact CI builds and smokes concurrently on a contended runner.
    ...(process.env.DSH_EXAMPLE_MODE === 'lib' ? { timeoutMs: 60_000 } : {}),
    ...overrides,
@@ -3,6 +3,7 @@
  <head>
    <meta charset="utf-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1" />
+    <link rel="icon" type="image/svg+xml" href="/favicon.svg" />
    <title>DeepSeek Harness</title>
  </head>
  <body>
@@ -0,0 +1,3 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="50.000000" height="50.000000" viewBox="0 0 50 50" fill="none">
+	<path id="path" d="M48.8354 10.0479C48.3232 9.79199 48.1025 10.2798 47.8032 10.5278C47.7007 10.6079 47.6143 10.7119 47.5273 10.8076C46.7793 11.624 45.9048 12.1597 44.7622 12.0957C43.0923 12 41.666 12.5356 40.4058 13.8398C40.1377 12.2319 39.2476 11.272 37.8926 10.6558C37.1836 10.3359 36.4668 10.0156 35.9702 9.31982C35.6235 8.82373 35.5293 8.27197 35.356 7.72754C35.2456 7.3999 35.1353 7.06396 34.7651 7.00781C34.3633 6.94385 34.2056 7.2876 34.0479 7.57568C33.418 8.75195 33.1733 10.0479 33.1973 11.3599C33.2524 14.312 34.4736 16.6641 36.8999 18.3359C37.1758 18.5278 37.2466 18.7197 37.1597 19C36.9946 19.5757 36.7974 20.1357 36.624 20.7119C36.5137 21.0801 36.3486 21.1597 35.9624 21C34.6309 20.4321 33.481 19.5918 32.4644 18.5757C30.7393 16.8721 29.1792 14.9917 27.2334 13.52C26.7764 13.1758 26.3193 12.856 25.8467 12.5518C23.8618 10.584 26.1069 8.96777 26.627 8.77588C27.1704 8.57568 26.8159 7.8877 25.0591 7.896C23.3022 7.90381 21.6953 8.50391 19.647 9.30371C19.3477 9.42383 19.0322 9.51172 18.7095 9.58398C16.8501 9.22363 14.9199 9.14355 12.9033 9.37598C9.10596 9.80762 6.07275 11.6396 3.84326 14.7681C1.16455 18.5278 0.53418 22.7998 1.30664 27.2559C2.11768 31.9521 4.46582 35.8398 8.07373 38.8799C11.8159 42.0322 16.1255 43.5762 21.041 43.2803C24.0269 43.104 27.3516 42.6963 31.1016 39.4561C32.0469 39.936 33.0396 40.1279 34.686 40.272C35.9546 40.3921 37.1758 40.208 38.1211 40.0078C39.6021 39.688 39.4995 38.2881 38.9639 38.0322C34.623 35.9678 35.5762 36.8081 34.71 36.1279C36.9155 33.4639 40.2402 30.6958 41.54 21.728C41.6426 21.0161 41.5557 20.5679 41.54 19.9917C41.5322 19.6396 41.6108 19.5039 42.0049 19.4639C43.0923 19.3359 44.1479 19.0317 45.1167 18.4878C47.9292 16.9199 49.064 14.3438 49.3315 11.2559C49.3711 10.7837 49.3237 10.2959 48.8354 10.0479ZM24.3262 37.8398C20.1196 34.4639 18.0791 33.3521 17.2358 33.3999C16.4482 33.4482 16.5898 34.3682 16.7632 34.9678C16.9443 35.5601 17.1812 35.9683 17.5117 36.4878C17.7402 36.832 17.8979 37.3442 17.2832 37.728C15.9282 38.584 13.5728 37.4399 13.4624 37.3838C10.7207 35.7358 8.42822 33.5601 6.81348 30.584C5.25342 27.7197 4.34766 24.6479 4.19775 21.3677C4.1582 20.5757 4.38672 20.2959 5.15869 20.1519C6.17529 19.96 7.22314 19.9199 8.23926 20.0718C12.5327 20.7119 16.1885 22.6719 19.2529 25.7759C21.002 27.5439 22.3252 29.6558 23.6885 31.7202C25.1377 33.9121 26.6978 36 28.6831 37.7119C29.3843 38.312 29.9434 38.7681 30.479 39.104C28.8643 39.2881 26.1699 39.3281 24.3262 37.8398ZM26.3433 24.6001C26.3433 24.248 26.6191 23.9678 26.9658 23.9678C27.0444 23.9678 27.1152 23.9839 27.1782 24.0078C27.2651 24.04 27.3438 24.0879 27.4067 24.1602C27.5171 24.272 27.5801 24.4321 27.5801 24.6001C27.5801 24.9521 27.3042 25.2319 26.9575 25.2319C26.6108 25.2319 26.3433 24.9521 26.3433 24.6001ZM32.6064 27.8799C32.2046 28.0479 31.8027 28.1919 31.4165 28.208C30.8179 28.2397 30.1641 27.9922 29.8096 27.688C29.2583 27.2158 28.8643 26.9521 28.6987 26.1279C28.6279 25.7759 28.6675 25.2319 28.7305 24.9199C28.8721 24.248 28.7144 23.8159 28.2495 23.4238C27.8716 23.104 27.3911 23.0161 26.8633 23.0161C26.666 23.0161 26.4849 22.9277 26.3511 22.856C26.1304 22.7441 25.9492 22.4639 26.1226 22.1201C26.1777 22.0078 26.4458 21.7358 26.5088 21.688C27.2256 21.272 28.0527 21.4077 28.8169 21.7197C29.5259 22.0161 30.0615 22.5601 30.834 23.3281C31.6216 24.2559 31.7632 24.5117 32.2124 25.208C32.5669 25.752 32.8901 26.312 33.1104 26.9521C33.2446 27.3521 33.0713 27.6802 32.6064 27.8799Z" fill="#000" fill-opacity="1.000000" fill-rule="nonzero"/>
+</svg>
@@ -151,7 +151,7 @@ describe('web e2e: approval takeover keeps its actions reachable', () => {
      await page.setViewportSize(original)
    }

-    await panel.getByRole('button', { name: '允许一次' }).click()
+    await panel.getByRole('button', { name: 'Allow once' }).click()

    const sessionId = await settled
    if (MODE === 'record') {
@@ -60,6 +60,9 @@ let unmount: (() => void) | undefined

 beforeEach(() => {
  localStorage.clear()
+  // English pinned before boot: role/text locators stay deterministic across
+  // localized component migrations (the newEnglishPage e2e convention).
+  localStorage.setItem('dsh.locale', 'en')
  document.title = 'DeepSeek Harness'
  vi.stubGlobal('ResizeObserver', ResizeObserverStub)
  vi.stubGlobal('requestAnimationFrame', (callback: FrameRequestCallback) =>
@@ -108,6 +111,18 @@ it('boots the built plugin graph and renders a fixture session end to end', asyn
    expect(document.querySelector('[data-sample="bash-global"]')).not.toBeNull()
  }, { timeout: 10_000 })

+  // The web render intent reaches the assembled boot graph: the fixture's
+  // web_search / web_fetch turns render their keyed WebRow cards, proving the
+  // registration, wire projection, and card rendering survive the real bundle
+  // path (not just the per-package src benches). The selector pins the KEYED
+  // WebRow (its own `data-variant="web"` wrapper), not the `[data-web]` attribute
+  // WebBlock draws — the generic fallback renders the same WebBlock, so a silent
+  // keyed-registration failure would still satisfy a bare `[data-web]` check.
+  await waitFor(() => {
+    expect(document.querySelector('[data-variant="web"][data-tool="web_search"]')).not.toBeNull()
+    expect(document.querySelector('[data-variant="web"][data-tool="web_fetch"]')).not.toBeNull()
+  }, { timeout: 10_000 })
+
  // Every bundle injected its plugin-owned style tag (the loader's CSS path).
  const styleOwners = [...document.head.querySelectorAll('style[data-plugin]')]
    .map(style => style.getAttribute('data-plugin'))
@@ -107,7 +107,8 @@ describe('web e2e: Cordis tools use the generic row variants', () => {

    const mountRow = page.locator('[data-tool="cordis_mount"]').filter({ hasText: 'Mount temporary Plugin' }).first()
    await mountRow.waitFor({ timeout: 10_000 })
-    await mountRow.locator('button[aria-expanded]').click()
+    // The whole summary row is the expand toggle (unified tool-row interaction).
+    await mountRow.locator('[aria-expanded]').first().click()
    await expect.poll(() => mountRow.locator('pre.shiki').textContent(), { timeout: 10_000 })
      .toContain(MOUNT_CODE)

@@ -98,7 +98,7 @@ describe.skipIf(MODE === 'record')('web e2e: details panel follows the current S
    await page.getByText('LIGHTHOUSE', { exact: true }).waitFor({ timeout: 15_000 })

    await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0)
-    expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false)
+    expect(await page.getByText('Details', { exact: true }).isVisible()).toBe(false)
    await compareOrRefreshGolden(HANDLES_EXPECTED, await handleSnapshot(page), MODE)

    const sidebarBefore = await sidebarTrack(page)
@@ -118,18 +118,18 @@ describe.skipIf(MODE === 'record')('web e2e: details panel follows the current S
    await appFrame(page).waitFor({ timeout: 30_000 })
    await page.getByText('LIGHTHOUSE', { exact: true }).waitFor({ timeout: 15_000 })
    await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0)
-    expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false)
+    expect(await page.getByText('Details', { exact: true }).isVisible()).toBe(false)

    await page.getByRole('button', { name: /^(?:New session|新.*会话)$/ }).last().click()
    await page.getByText("Let's start building", { exact: false }).waitFor({ timeout: 15_000 })
    await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0)
-    expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false)
+    expect(await page.getByText('Details', { exact: true }).isVisible()).toBe(false)

    const original = page.locator('[role=treeitem]').filter({ hasText: 'Reply with the single word' }).first()
    await original.click()
    await page.getByText('LIGHTHOUSE', { exact: true }).waitFor({ timeout: 15_000 })
    await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0)
-    expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false)
+    expect(await page.getByText('Details', { exact: true }).isVisible()).toBe(false)

    const ungrouped = page.getByText('Ungrouped', { exact: true })
    const ungroupedRow = ungrouped.locator('..').locator('..')
@@ -25,6 +25,8 @@ import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './suppor
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/lifecycle-chrome', import.meta.url))
 const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
 const HERO_EXPECTED = join(SNAPSHOT_DIR, 'hero.expected.md')
+const COMMAND_MENU_EXPECTED = join(SNAPSHOT_DIR, 'command-menu.expected.md')
+const PLAN_ACTIVE_EXPECTED = join(SNAPSHOT_DIR, 'plan-active.expected.md')
 // Post-reload golden: the same settled conversation rebuilt purely from
 // persistence + history — byte-equal rendering is exactly the recovery claim.
 const RELOADED_EXPECTED = join(SNAPSHOT_DIR, 'reloaded.expected.md')
@@ -56,6 +58,88 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()
    await scaffold?.close()
  })

+  it.skipIf(MODE === 'record')('opens the shared slash menu from plus with only Command candidates', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-command-menu-launcher'))
+    const launcher = page.getByRole('button', { name: 'Commands' })
+    await launcher.click()
+    const menu = page.getByRole('listbox', { name: 'Trigger suggestions' })
+    await menu.waitFor({ timeout: 10_000 })
+    const snapshot = await captureStableAria(page, '[role="listbox"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(COMMAND_MENU_EXPECTED, snapshot, MODE)
+    expect(snapshot).toContain('text: Commands')
+    expect(snapshot).not.toContain('text: Skills')
+    expect(snapshot).not.toContain('text: Subagents')
+    const launchedBox = await menu.boundingBox()
+    await page.locator('textarea').first().press('Escape')
+    await expect.poll(() => menu.count()).toBe(0)
+    const input = page.locator('textarea').first()
+    await input.fill('/')
+    await menu.waitFor({ timeout: 10_000 })
+    const typedBox = await menu.boundingBox()
+    expect(launchedBox).not.toBeNull()
+    expect(typedBox).not.toBeNull()
+    expect(Math.abs(launchedBox!.x - typedBox!.x)).toBeLessThan(1)
+    expect(Math.abs(
+      launchedBox!.y + launchedBox!.height - typedBox!.y - typedBox!.height,
+    )).toBeLessThan(1)
+    await input.fill('')
+    await expect.poll(() => menu.count()).toBe(0)
+  })
+
+  it.skipIf(MODE === 'record')('shows active Plan as the warn-state status action', async () => {
+    const activeScaffold = await launchWebScaffold()
+    const activePage = await newEnglishPage(browser)
+    const activeTripwire = watchConsole(activePage)
+    try {
+      await activePage.goto(activeScaffold.baseUrl, { waitUntil: 'load' })
+      await activePage.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+      await connectFreshWorkspace(activePage)
+      const input = activePage.locator('textarea').first()
+      await activePage.getByRole('button', { name: 'Commands' }).click()
+      const menu = activePage.getByRole('listbox', { name: 'Trigger suggestions' })
+      await menu.waitFor({ timeout: 10_000 })
+      await menu.getByRole('option', { name: 'plan Enter or leave plan mode' }).click()
+      await expect.poll(() => input.inputValue()).toBe('/plan ')
+      await input.press('Enter')
+      const planButton = activePage.getByRole('button', { name: 'Plan mode on, press to turn off' })
+      await planButton.waitFor({ timeout: 10_000 })
+      const planSnapshot = await captureStableAria(activePage, '[class*="frame"]', activeScaffold.workspaceCwd)
+      await compareOrRefreshGolden(PLAN_ACTIVE_EXPECTED, planSnapshot, MODE)
+      const planStyle = await planButton.evaluate((element) => {
+        const probe = document.createElement('span')
+        probe.style.color = 'var(--dsw-alias-state-warn-label)'
+        probe.style.backgroundColor = 'var(--dsw-alias-state-warn-tertiary)'
+        document.body.append(probe)
+        const actual = getComputedStyle(element)
+        const reference = getComputedStyle(probe)
+        const result = {
+          color: actual.color,
+          backgroundColor: actual.backgroundColor,
+          borderRadius: actual.borderRadius,
+          fontSize: actual.fontSize,
+          referenceColor: reference.color,
+          referenceBackgroundColor: reference.backgroundColor,
+        }
+        probe.remove()
+        return result
+      })
+      expect(planStyle.color).toBe(planStyle.referenceColor)
+      expect(planStyle.backgroundColor).toBe(planStyle.referenceBackgroundColor)
+      expect(planStyle.borderRadius).toBe('999px')
+      expect(planStyle.fontSize).toBe('13px')
+      await planButton.click()
+      await expect.poll(() => planButton.count()).toBe(0)
+      expect(activeTripwire.pageErrors).toEqual([])
+      expect(activeTripwire.warnings).toEqual([])
+    } catch (error) {
+      await saveFailureShot(activePage, 'web-e2e-plan-active').catch(() => undefined)
+      throw error
+    } finally {
+      await activePage.close()
+      await activeScaffold.close()
+    }
+  })
+
  it('sends the first prompt from the empty-state hero (all modes)', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-lifecycle-send'))
    if (MODE !== 'record') {
@@ -152,6 +236,8 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()

  it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
    expect(tripwire.warnings).toEqual([])
-    await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'hero.expected.md', 'reloaded.expected.md'])
+    await assertFixtureInventory(SNAPSHOT_DIR, [
+      'session.jsonl', 'command-menu.expected.md', 'hero.expected.md', 'plan-active.expected.md', 'reloaded.expected.md',
+    ])
  })
 })
@@ -221,8 +221,8 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => {
    // only on change, so attempt count is invisible there).
    expect(sessionEvents.filter(e => e.type === 'llm/retry').length).toBeGreaterThanOrEqual(1)
    await expect.poll(() => page.getByText('event sourcing', { exact: false }).count(), { timeout: 10_000 }).toBeGreaterThan(0)
-    // Golden of the recovered end-state: indistinguishable from a clean
-    // completion — retries are deliberately invisible in the transcript.
+    // Golden of the recovered end-state: the discarded partial stays absent,
+    // while the settled retry row remains as durable recovery context.
    const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold!.workspaceCwd)
    await compareOrRefreshGolden(RETRY_EXPECTED, snapshot, MODE)
    expect(tripwire.pageErrors).toEqual([])
@@ -64,14 +64,14 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
    await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 15_000 }).toBe(1)

    // Focus-reveal the footers (hover:hover keeps them opacity-hidden until
-    // hover/focus-within). User has three actions; each finalized assistant
-    // text node has copy + branch.
-    const copyButtons = page.getByRole('button', { name: '复制' })
+    // hover/focus-within). User has three actions; each turn's last content
+    // assistant has copy + branch.
+    const copyButtons = page.getByRole('button', { name: 'Copy' })
    await expect.poll(() => copyButtons.count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(2)
    await copyButtons.first().focus()
-    await expect.poll(() => page.getByRole('button', { name: '在新对话中分支' }).count(), { timeout: 5_000 })
+    await expect.poll(() => page.getByRole('button', { name: 'Branch into a new conversation' }).count(), { timeout: 5_000 })
      .toBeGreaterThanOrEqual(2)
-    await expect.poll(() => page.getByRole('button', { name: '编辑' }).count(), { timeout: 5_000 }).toBe(1)
+    await expect.poll(() => page.getByRole('button', { name: 'Edit' }).count(), { timeout: 5_000 }).toBe(1)
  }, 60_000)

  it.skipIf(MODE === 'record')('matches the conversation aria golden with IconActions and clocks', async () => {
@@ -81,7 +81,7 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
    }).waitFor({ timeout: 10_000 })
    // Keep a footer focused so opacity-hidden actions stay in the a11y tree
    // as an active/focused control during the capture.
-    await page.getByRole('button', { name: '复制' }).first().focus()
+    await page.getByRole('button', { name: 'Copy' }).first().focus()
    const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd))
      .split(SEED_ID).join('{{seededId}}')
    await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
@@ -91,7 +91,7 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-message-fork'))
    // Exercise the assistant action specifically; package coverage pins the
    // user action separately at its own event seq.
-    await page.getByRole('button', { name: '在新对话中分支' }).last().click()
+    await page.getByRole('button', { name: 'Branch into a new conversation' }).last().click()
    await expect.poll(
      () => scaffold.ctx.agents.list().find(agent => agent.session.header.parentSession === SessionId(SEED_ID)),
      { timeout: 15_000 },
@@ -23,6 +23,7 @@ import { newEnglishPage, saveFailureShot } from './support.ts'
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/navigation-panes', import.meta.url))
 const SEED = join(SNAPSHOT_DIR, 'seed.jsonl')
 const TRAJECTORY_EXPECTED = join(SNAPSHOT_DIR, 'trajectory.expected.md')
+const SEARCH_EXPECTED = join(SNAPSHOT_DIR, 'search-results.expected.md')
 const TERMINAL_EXPECTED = join(SNAPSHOT_DIR, 'terminal-card.expected.md')
 const MODE = webSnapshotMode()
 const SEED_ID = 'navigation-panes-web-e2e'
@@ -95,39 +96,39 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
    expect(calls.map(e => e.data.name).sort()).toEqual(['bash', 'read', 'read'])
  }, 400_000)

-  it.skipIf(MODE === 'record')('opens the seeded session and renders both turns from the log', async () => {
-    onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-open'))
-    // Expand the collapsed group row, then open the revealed session row.
-    const groupRow = page.locator('[role="treeitem"]').first()
-    await groupRow.waitFor({ timeout: 15_000 })
-    await groupRow.click()
-    const sessionRow = page.locator('[role="treeitem"]').nth(1)
-    await sessionRow.waitFor({ timeout: 10_000 })
-    await sessionRow.click()
+  it.skipIf(MODE === 'record')('finds an unopened seeded session by message content and opens it', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-search'))
+    const search = page.getByPlaceholder('Search name, keywords', { exact: false })
+    // The cold row has not been opened, so only the persisted log can satisfy
+    // this query. First search lazily reconciles the SQLite content index.
+    await search.fill('zzzqx-no-such-session')
+    await page.getByText('No matching sessions').waitFor({ timeout: 30_000 })
+    await expect.poll(
+      () => page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem').count(),
+      { timeout: 10_000 },
+    ).toBe(0)
+
+    await search.fill('WATERFALL')
+    const resultTree = page.getByRole('tree', { name: 'Search results' })
+    const result = resultTree.getByRole('treeitem')
+    await expect.poll(() => result.count(), { timeout: 30_000 }).toBe(1)
+    await expect.poll(() => result.getByText('WATERFALL', { exact: false }).count(), {
+      timeout: 10_000,
+    }).toBeGreaterThanOrEqual(1)
+    const snapshot = (await captureStableAria(page, '[class*="listArea"]', scaffold.workspaceCwd))
+      .split(SEED_ID).join('{{seededId}}')
+    await compareOrRefreshGolden(SEARCH_EXPECTED, snapshot, MODE)
+
+    await result.click()
+    // Search navigation addresses the session, not a specific event, and the
+    // query remains until the user explicitly clears it.
+    await expect.poll(() => search.inputValue(), { timeout: 5_000 }).toBe('WATERFALL')
    await expect.poll(() => page.getByText('FIRST_DONE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
    await expect.poll(() => page.getByRole('heading', { name: 'Navigation Summary' }).count(), { timeout: 15_000 }).toBe(1)
-  }, 90_000)
-
-  it.skipIf(MODE === 'record')('filters the sidebar tree by title through the search box', async () => {
-    onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-search'))
-    // Runs after the session is open: a cold summary carries no title (the
-    // sidebar shows the cwd basename), and the durable title lands with the
-    // attach subscription's baseline — which is itself worth pinning: search
-    // matches the title the user sees, not a hidden cold field.
-    const search = page.getByPlaceholder('Search name, keywords', { exact: false })
-    await expect.poll(() => page.getByText('NavScenario', { exact: false }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
-    // Negative: a garbage query empties the tree (group rows hide too).
-    await search.fill('zzzqx-no-such-session')
-    await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBe(0)
-    // Positive: a title word narrows to the matched session + its group,
-    // force-expanded by search mode (case-insensitive client-side filter).
-    await search.fill('navscenario')
-    await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(2)
-    // Clear restores the unfiltered tree.
    await page.getByRole('button', { name: 'Clear search' }).click()
    await expect.poll(() => search.inputValue(), { timeout: 5_000 }).toBe('')
    await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1)
-  }, 60_000)
+  }, 90_000)

  it.skipIf(MODE === 'record')('renders the trajectory ledger and opens its local record inspector', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-trajectory'))
@@ -180,11 +181,13 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
    await bashRow.waitFor({ timeout: 15_000 })
    const frame = page.locator('[style*="grid-template-columns"]').first()
    expect(await frame.getAttribute('data-details-collapsed')).toBe('true')
+    // The row click is the card's expand toggle (unified tool-row
+    // interaction); it must not drive layout geometry either way.
    await bashRow.click()
    await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true')
    // The card's own controls are outside the summary row and must not open
-    // details either — the terminal card is read in place.
-    await page.locator('[data-sample="bash-global"] ~ [data-terminal] [class*="_copyButton_"]').first().click()
+    // details either — the expanded terminal card is read in place.
+    await page.locator('[data-sample="bash-global"] ~ div [data-terminal] [class*="_copyButton_"]').first().click()
    await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true')
    // Read summaries are host-open file links; they also must not open details.
    const fileLink = page.locator('[data-variant="read"] button').first()
@@ -196,10 +199,14 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
  it.skipIf(MODE === 'record')('renders the bash row as a terminal card in the real browser', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-terminal'))
    await page.getByRole('tab', { name: 'Chat' }).click()
-    // The card is resident in the keyed bash row (no expand gesture): the
-    // recorded command's own output sits in the message flow, derived from the
-    // logged call/result presentations alone.
-    const card = page.locator('[data-sample="bash-global"] ~ [data-terminal], [data-sample="bash-global"] [data-terminal]').first()
+    // The card is expand-gated behind the whole-row toggle (the unified
+    // tool-row interaction): open it if a previous case left it collapsed.
+    // Expanded, the recorded command's own output sits in the message flow,
+    // derived from the logged call/result presentations alone.
+    const bashRow = page.locator('[data-sample="bash-global"]').first()
+    await bashRow.waitFor({ timeout: 15_000 })
+    if (await bashRow.getAttribute('aria-expanded') !== 'true') await bashRow.click()
+    const card = page.locator('[data-sample="bash-global"] ~ div [data-terminal]').first()
    await card.waitFor({ timeout: 15_000 })
    // Real layout, not jsdom's stub (which computes no geometry at all):
    // squeeze the output pane below its content width and the line must keep
@@ -253,7 +260,7 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
      }
    })
    expect(dot.state).toBe('done')
-    expect(dot.label).toBe('已完成')
+    expect(dot.label).toBe('Done')
    expect(dot.beforePrompt).toBe(true)
    expect(dot.insideCard).toBe(true)
    expect(dot.leftOfPrompt).toBe(true)
@@ -270,7 +277,7 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
    await page.context().grantPermissions(['clipboard-read', 'clipboard-write'])
    await card.locator('[class*="_copyButton_"]').first().click()
    await expect.poll(() => card.locator('[class*="_copyButton_"]').first().textContent(), { timeout: 5_000 })
-      .toBe('复制成功')
+      .toBe('Copied')
    expect(await page.evaluate(() => navigator.clipboard.readText())).toContain('NAVIGATION_OK')
  }, 60_000)

@@ -279,7 +286,8 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
    expect(slotErrors).toEqual([])
    expect(tripwire.warnings).toEqual([])
    await assertFixtureInventory(SNAPSHOT_DIR, [
-      'seed.jsonl', 'trajectory.expected.md', 'terminal-card.expected.md',
+      'seed.jsonl', 'search-results.expected.md', 'trajectory.expected.md',
+      'terminal-card.expected.md',
    ])
  })
 })
@@ -81,7 +81,7 @@ describe('web e2e: queue row actions', () => {
      await input.fill(text)
      await input.press('Enter')
    }
-    const queueHeader = page.getByRole('button', { name: '2 条排队消息' })
+    const queueHeader = page.getByRole('button', { name: '2 queued messages' })
    await expect.poll(() => queueHeader.getAttribute('aria-expanded'), { timeout: 10_000 })
      .toBe('false')
    const collapsedSnapshot = await captureStableAria(
@@ -92,21 +92,21 @@ describe('web e2e: queue row actions', () => {
    await compareOrRefreshGolden(COLLAPSED_EXPECTED, collapsedSnapshot, MODE)
    await queueHeader.click()
    await expect.poll(
-      () => page.getByRole('button', { name: '删除排队消息' }).count(),
+      () => page.getByRole('button', { name: 'Remove queued message' }).count(),
      { timeout: 10_000 },
    ).toBe(2)

    const editRow = page.getByText(EDIT, { exact: true }).locator('..')
-    await editRow.getByRole('button', { name: '编辑排队消息' }).click()
-    const editor = page.getByRole('textbox', { name: '编辑排队消息' })
+    await editRow.getByRole('button', { name: 'Edit queued message' }).click()
+    const editor = page.getByRole('textbox', { name: 'Edit queued message' })
    await editor.fill(EDITED)
    const editingSnapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
    await compareOrRefreshGolden(EDITING_EXPECTED, editingSnapshot, MODE)
-    await page.getByRole('button', { name: '保存排队消息' }).click()
+    await page.getByRole('button', { name: 'Save queued message' }).click()
    await page.getByText(EDITED, { exact: true }).waitFor()

    const removeRow = page.getByText(REMOVE, { exact: true }).locator('..')
-    await removeRow.getByRole('button', { name: '删除排队消息' }).click()
+    await removeRow.getByRole('button', { name: 'Remove queued message' }).click()
    await expect.poll(() => page.getByText(REMOVE, { exact: true }).count()).toBe(0)

    const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
@@ -116,7 +116,7 @@ describe('web e2e: queue row actions', () => {
    expect(tripwire.warnings).toEqual([])

    const editedRow = page.getByText(EDITED, { exact: true }).locator('..')
-    await editedRow.getByRole('button', { name: '删除排队消息' }).click()
+    await editedRow.getByRole('button', { name: 'Remove queued message' }).click()
    await expect.poll(() => page.getByText(EDITED, { exact: true }).count()).toBe(0)
    await page.getByRole('button', { name: 'Stop generating' }).click()
    await settled
@@ -218,6 +218,7 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
  const patches: PatchOptions[] = [
    ...surfacePatches,
    { id: 'session-persistence-jsonl', config: { root: persistenceRoot } },
+    { id: 'session-query-sqlite', config: { path: ':memory:', openAt: 'first-search' } },
    // storage-json's './.storages' yml default is cwd-relative and resolves
    // per write; the scaffold restores the original cwd after boot, so the
    // row gets an absolute temp root (removed with the workspace at close).
@@ -240,6 +241,10 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
    // workspace, keeping the composition untouched.
    { id: 'workspace-context', disabled: true },
    { id: 'session-title-llm', disabled: true },
+    // Fixture sessions must never leave the process: the shipped row defaults
+    // to the production OTLP endpoint (or whatever DSH_TELEMETRY_OTLP_URL
+    // names in the ambient environment).
+    { id: 'telemetry-otel', disabled: true },
    { id: 'webserver', config: { host: '127.0.0.1', port: 0, distIndex: DIST_INDEX } },
    { id: 'settings', config: { dshHome: harnessHome } },
    { id: 'credentials', config: { dshHome: harnessHome } },
@@ -147,7 +147,7 @@ describe('web e2e: seeded history renders through cold resume', () => {
        }],
      },
    }))
-    await page.getByRole('button', { name: '上下文注入' }).waitFor({ timeout: 10_000 })
+    await page.getByRole('button', { name: 'Context injection' }).waitFor({ timeout: 10_000 })
  }, 60_000)

  it.skipIf(MODE === 'record')('matches the historical conversation aria golden', async () => {
@@ -165,7 +165,7 @@ describe('web e2e: seeded history renders through cold resume', () => {

  it.skipIf(MODE === 'record')('matches the Figma context disclosure geometry', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-context-injection'))
-    const disclosure = page.getByRole('button', { name: '上下文注入' })
+    const disclosure = page.getByRole('button', { name: 'Context injection' })
    expect(await disclosure.getAttribute('aria-expanded')).toBe('false')
    const collapsedIcon = disclosure.locator('svg').first()
    const collapsedIconBox = await collapsedIcon.boundingBox()
@@ -267,6 +267,98 @@ describe('dsh web keyless CLI smoke', () => {
    }
  })

+  it('retries a partial transport failure through the shipped Web composition', async () => {
+    requireDist()
+    const workspace = mkdtempSync(join(tmpdir(), 'dsh-web-retry-'))
+    const promptMarker = 'WEB_RETRY_REQUEST'
+    const recoveredMarker = 'WEB_RETRY_RECOVERED'
+    let mainAttempts = 0
+    const provider = createServer((request, response) => {
+      let body = ''
+      request.setEncoding('utf8')
+      request.on('data', (chunk: string) => { body += chunk })
+      request.on('end', () => {
+        const parsed = JSON.parse(body) as { max_tokens?: number; messages?: unknown[] }
+        const titleRequest = parsed.max_tokens === 64
+        const mainRequest = !titleRequest && body.includes(promptMarker)
+        response.writeHead(200, { 'content-type': 'text/event-stream' })
+        if (!mainRequest) {
+          response.end([
+            'data: {"choices":[{"delta":{"content":"Web retry title"}}]}',
+            'data: {"choices":[{"delta":{"content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":1,"completion_tokens":1}}',
+            'data: [DONE]',
+            '',
+          ].join('\n\n'))
+          return
+        }
+        mainAttempts++
+        if (mainAttempts === 1) {
+          response.write('data: {"choices":[{"delta":{"content":"WEB_RETRY_DISCARDED"}}]}\n\n')
+          setTimeout(() => { response.destroy() }, 20)
+          return
+        }
+        response.end([
+          `data: {"choices":[{"delta":{"content":"${recoveredMarker}"}}]}`,
+          'data: {"choices":[{"delta":{"content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}',
+          'data: [DONE]',
+          '',
+        ].join('\n\n'))
+      })
+    })
+    await new Promise<void>(resolve => provider.listen(0, '127.0.0.1', resolve))
+    const address = provider.address()
+    if (address === null || typeof address === 'string') throw new Error('mock provider did not bind a TCP port')
+    const tsxLoader = pathToFileURL(createRequire(join(REPO_ROOT, 'package.json')).resolve('tsx')).href
+    const child = spawn(
+      process.execPath,
+      ['--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', '0'],
+      {
+        cwd: workspace,
+        env: {
+          ...process.env,
+          DEEPSEEK_API_KEY: 'keyless-web-retry',
+          DEEPSEEK_BASE_URL: `http://127.0.0.1:${address.port}`,
+          DSH_HOME: join(workspace, '.dsh'),
+          TSX_TSCONFIG_PATH: join(REPO_ROOT, 'tsconfig.json'),
+        },
+        stdio: ['ignore', 'pipe', 'pipe'],
+      },
+    )
+    try {
+      const baseUrl = await waitForReadyLine(child)
+      const created = await rpc<{ sessionId: string }>(baseUrl, 'session.create', {})
+      await rpc<{ accepted: true }>(baseUrl, 'session.prompt', {
+        sessionId: created.sessionId,
+        mode: 'queue',
+        content: [{ type: 'text', text: promptMarker }],
+      })
+      let page: HistoryPage | undefined
+      await expect.poll(async () => {
+        page = await history(baseUrl, created.sessionId)
+        return hasAssistantMarker(page, recoveredMarker)
+      }, { timeout: 20_000 }).toBe(true)
+      if (page === undefined) throw new Error('retry history was not observed')
+      const retry = page.events.find(({ event }) => event.type === 'llm/retry')?.event
+      expect(mainAttempts).toBe(2)
+      expect(retry?.data).toMatchObject({
+        turn: 1,
+        step: 1,
+        retry: 1,
+        maxRetries: 2,
+        failure: { code: 'TRANSPORT' },
+      })
+      expect(JSON.stringify(page.events)).toContain('WEB_RETRY_DISCARDED')
+    } finally {
+      const closed = child.exitCode === null
+        ? new Promise<void>((resolveClose) => { child.once('close', () => { resolveClose() }) })
+        : Promise.resolve()
+      if (child.exitCode === null) child.kill('SIGTERM')
+      await closed
+      await new Promise<void>(resolveClose => provider.close(() => { resolveClose() }))
+      rmSync(workspace, { recursive: true, force: true })
+    }
+  }, 30_000)
+
  it('DSH_TOOLS_MODE=code collapses the provider wire tools to run_code with the SDK prompt section', async () => {
    requireDist()
    const workspace = mkdtempSync(join(tmpdir(), 'dsh-web-code-mode-'))
@@ -1,4 +1,4 @@
- text: 等待审批
- group "审批详情": "escalate sandbox to workspace-write: Need to write the notes.txt file as requested by the user. echo 'tok63z tokc7y tokibx tokofw tokujv tok10nu tok16rt tok1cvs tok1izr tok1p3q tok1v7p tok21bo tok2a4 tok8e3 tokei2 tokkm1 tokqq0 tokwtz tok12xy tok191x tok1f5w tok1l9v tok1rdu tok1xht tok23ls tok4k8 tokao7 tokgs6 tokmw5 tokt04 tokz43 tok1582 tok1bc1 tok1hg0 tok1njz tok1tny tok1zrx tokqd tok6uc tokcyb tokj2a tokp69 tokva8 tok11e7 tok17i6 tok1dm5 tok1jq4 tok1pu3 tok1vy2 tok2221 tok30h tok94g tokf8f toklce tokrgd tokxkc tok13ob tok19sa tok1fw9 tok1m08 tok1s47 tok1y86 tok24c5 tok5al tokbek tokhij toknmi toktqh tokzug tok15yf tok1c2e tok1i6d tok1oac tok1ueb tok20ia tok1gq tok7kp tokdoo tokjsn tokpwm tokw0l tok124k tok188j tok1eci tok1kgh tok1qkg tok1wof tok22se tok3qu tok9ut tokfys tokm2r toks6q tokyap tok14eo tok1ain tok1gmm tok1mql tok1suk tok1yyj tok252i tok60y tokc4x toki8w tokocv tokugu tok10kt tok16os tok1csr tok1iwq tok1p0p tok1v4o tok218n tok273 tok8b2 tokef1 tokkj0 tokqmz tokwqy tok12ux tok18yw tok1f2v tok1l6u tok1rat tok1xes tok23ir tok4h7 tokal6 tokgp5 tokmt4 toksx3 tokz12 tok1551 tok1b90 tok1hcz tok1ngy tok1tkx tok1zow toknc tok6rb tokcva tokiz9 tokp38 tokv77 tok11b6 tok17f5 tok1dj4 tok1jn3 tok1pr2 tok1vv1 tok21z0 tok2xg tok91f tokf5e tokl9d tokrdc tokxhb tok13la tok19p9 tok1ft8 tok1lx7 tok1s16 tok1y55 tok2494 tok57k tokbbj tokhfi toknjh tokktng tokzrf tok15ve tok1bzd tok1i3c tok1o7b tok1uba tok20f9 tok1dp tok7ho tokdln tokjpm tokptl tokvxk tok121j tok185i tok1e9h tok1kdg tok1qhf tok1wle tok22pd tok3nt tok9rs tokfvr toklzq toks3p toky7o tok14bn tok1afm tok1gjl tok1mnk tok1srj tok1yvi tok24zh tok5xx tokc1w toki5v toko9u tokudt tok10hs tok16lr tok1cpq tok1itp tok1oxo tok1v1n tok215m tok242 tok881 tokec0 tokfz tokqjy tokwnx' > notes.txt"
- button "拒绝"
- button "允许一次"
+- text: Waiting for approval
+- group "Approval details": "escalate sandbox to workspace-write: Need to write the notes.txt file as requested by the user. echo 'tok63z tokc7y tokibx tokofw tokujv tok10nu tok16rt tok1cvs tok1izr tok1p3q tok1v7p tok21bo tok2a4 tok8e3 tokei2 tokkm1 tokqq0 tokwtz tok12xy tok191x tok1f5w tok1l9v tok1rdu tok1xht tok23ls tok4k8 tokao7 tokgs6 tokmw5 tokt04 tokz43 tok1582 tok1bc1 tok1hg0 tok1njz tok1tny tok1zrx tokqd tok6uc tokcyb tokj2a tokp69 tokva8 tok11e7 tok17i6 tok1dm5 tok1jq4 tok1pu3 tok1vy2 tok2221 tok30h tok94g tokf8f toklce tokrgd tokxkc tok13ob tok19sa tok1fw9 tok1m08 tok1s47 tok1y86 tok24c5 tok5al tokbek tokhij toknmi toktqh tokzug tok15yf tok1c2e tok1i6d tok1oac tok1ueb tok20ia tok1gq tok7kp tokdoo tokjsn tokpwm tokw0l tok124k tok188j tok1eci tok1kgh tok1qkg tok1wof tok22se tok3qu tok9ut tokfys tokm2r toks6q tokyap tok14eo tok1ain tok1gmm tok1mql tok1suk tok1yyj tok252i tok60y tokc4x toki8w tokocv tokugu tok10kt tok16os tok1csr tok1iwq tok1p0p tok1v4o tok218n tok273 tok8b2 tokef1 tokkj0 tokqmz tokwqy tok12ux tok18yw tok1f2v tok1l6u tok1rat tok1xes tok23ir tok4h7 tokal6 tokgp5 tokmt4 toksx3 tokz12 tok1551 tok1b90 tok1hcz tok1ngy tok1tkx tok1zow toknc tok6rb tokcva tokiz9 tokp38 tokv77 tok11b6 tok17f5 tok1dj4 tok1jn3 tok1pr2 tok1vv1 tok21z0 tok2xg tok91f tokf5e tokl9d tokrdc tokxhb tok13la tok19p9 tok1ft8 tok1lx7 tok1s16 tok1y55 tok2494 tok57k tokbbj tokhfi toknjh tokktng tokzrf tok15ve tok1bzd tok1i3c tok1o7b tok1uba tok20f9 tok1dp tok7ho tokdln tokjpm tokptl tokvxk tok121j tok185i tok1e9h tok1kdg tok1qhf tok1wle tok22pd tok3nt tok9rs tokfvr toklzq toks3p toky7o tok14bn tok1afm tok1gjl tok1mnk tok1srj tok1yvi tok24zh tok5xx tokc1w toki5v toko9u tokudt tok10hs tok16lr tok1cpq tok1itp tok1oxo tok1v1n tok215m tok242 tok881 tokec0 tokfz tokqjy tokwnx' > notes.txt"
+- button "Reject"
+- button "Allow once"
@@ -5,38 +5,39 @@
    - tab "Chat" [selected]
    - tab "Trajectory"
 - text: "Using ONE run_code program: run bash `echo CODE_ROUND_OK`, then read the file missing.txt catching its error in the program. Return an object with both outcomes. Then reply DONE and stop. {{clock}}"
- button "复制":
+- button "Copy":
  - img
- button "在新对话中分支":
+- button "Branch into a new conversation":
  - img
- button "编辑":
+- button "Edit":
  - img
 - 'button "Think The user wants me to write a single `run_code` program that:"':
  - img
  - img
  - text: "Think The user wants me to write a single `run_code` program that:"
- button:
+- button "Code Run bash echo and catch missing file read":
  - img
  - img
- text: Code Run bash echo and catch missing file read
+  - text: Code Run bash echo and catch missing file read
 - img
- text: Bash Echo CODE_ROUND_OK Read
- button "missing.txt"
+- text: Bash Echo CODE_ROUND_OK
+- 'button "Read Error: cannot read \"{{cwd}}/workspace/missing.txt\": not found"':
+  - img
+  - text: "Read Error: cannot read \"{{cwd}}/workspace/missing.txt\": not found"
 - button "Think The program ran successfully. Let me now reply DONE as instructed.":
  - img
  - img
  - text: Think The program ran successfully. Let me now reply DONE as instructed.
 - paragraph: DONE
- button "复制":
+- button "Copy":
  - img
- button "在新对话中分支":
+- button "Branch into a new conversation":
  - img
 - text: {{clock}}
 - textbox "Message the agent"
- button "Add attachment":
+- button "Commands":
  - img
 - 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
@@ -5,52 +5,54 @@
    - tab "Chat" [selected]
    - tab "Trajectory"
 - text: "Use only Cordis tools. First call cordis_inspect with what \"temporary\". Then call cordis_mount with this exact code: \"return { name: \\\"snapshot-noop\\\", apply(ctx) {} }\". Read its returned id and call cordis_unmount with that exact id. After all three calls succeed, reply exactly CORDIS_UI_DONE and stop. {{clock}}"
- button "复制":
+- button "Copy":
  - img
- button "在新对话中分支":
+- button "Branch into a new conversation":
  - img
- button "编辑":
+- button "Edit":
  - img
 - button "Think The user wants me to:":
  - img
  - img
  - text: "Think The user wants me to:"
- button:
+- button "Inspect temporary":
  - img
  - img
- text: Inspect temporary
+  - text: Inspect temporary
 - 'button "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."':
  - img
  - img
  - text: "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."
- button [expanded]:
+- 'button "Mount temporary Plugin return { name: \"snapshot-noop\", apply(ctx) {} }" [expanded]':
  - img
- text: Mount temporary Plugin typescript
- button "复制"
+  - text: "Mount temporary Plugin return { name: \"snapshot-noop\", apply(ctx) {} }"
+- text: typescript
+- button "Copy"
 - code: "return { name: \"snapshot-noop\", apply(ctx) {} }"
+- text: OUT Temporary Plugin dyn-1 is running (plugin "snapshot-noop"; available until unmounted or DSH restarts).
+- button "Inspect"
 - 'button "Think The id is \"dyn-1\". Now step 3: call cordis_unmount with that id."':
  - img
  - img
  - text: "Think The id is \"dyn-1\". Now step 3: call cordis_unmount with that id."
- button:
+- button "Unmount temporary Plugin dyn-1":
  - img
  - img
- text: Unmount temporary Plugin dyn-1
+  - text: Unmount temporary Plugin dyn-1
 - button "Think All three calls succeeded. I should now reply exactly \"CORDIS_UI_DONE\" and stop.":
  - img
  - img
  - text: Think All three calls succeeded. I should now reply exactly "CORDIS_UI_DONE" and stop.
 - paragraph: CORDIS_UI_DONE
- button "复制":
+- button "Copy":
  - img
- button "在新对话中分支":
+- button "Branch into a new conversation":
  - img
 - text: {{clock}}
 - textbox "Message the agent"
- button "Add attachment":
+- button "Commands":
  - img
 - 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
@@ -5,35 +5,34 @@
    - tab "Chat" [selected]
    - tab "Trajectory"
 - text: "Use the bash tool to run exactly: echo WEB_E2E_OK. Then reply with the single word DONE and stop. {{clock}}"
- button "复制":
+- button "Copy":
  - img
- button "在新对话中分支":
+- button "Branch into a new conversation":
  - img
- button "编辑":
+- button "Edit":
  - img
 - button "Think The user wants me to run a simple bash command and reply with \"DONE\".":
  - img
  - img
  - text: Think The user wants me to run a simple bash command and reply with "DONE".
- img
- text: Bash Echo the test string 已完成 workspace echo WEB_E2E_OK
- button "复制"
- text: WEB_E2E_OK
+- button "Bash Echo the test string":
+  - img
+  - img
+  - text: Bash Echo the test string
 - button "Think The command executed successfully and output \"WEB_E2E_OK\". I just need to reply with \"DONE\".":
  - img
  - img
  - text: Think The command executed successfully and output "WEB_E2E_OK". I just need to reply with "DONE".
 - paragraph: DONE
- button "复制":
+- button "Copy":
  - img
- button "在新对话中分支":
+- button "Branch into a new conversation":
  - img
 - text: {{clock}}
 - textbox "Message the agent"
- button "Add attachment":
+- button "Commands":
  - img
 - 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
@@ -0,0 +1,6 @@
+- listbox "Trigger suggestions":
+  - text: Commands
+  - option "goal set or view the goal for a long-running task" [selected]
+  - option "permission Switch the permission preset (sandbox mode + approval policy)"
+  - option "plan Enter or leave plan mode"
+  - option "model Select the model for this conversation"
@@ -26,14 +26,13 @@
  - text: workspace
  - img
 - textbox "Describe what you want to build"
- button "Add attachment":
+- button "Commands":
  - img
 - 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
 - button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
 - button "Send message" [disabled]
- text: 详情
- button "关闭详情"
- text: 点击消息流中的工具行查看详情
+- text: Details
+- button "Close details"
+- text: Click a tool row in the message flow to view its details
--- a/Show More
+++ b/Show More