Merge master into fix/subagent-stack-end-result

.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.md
-2026-07-30-composer-context-stack-order.md: 9c269bcaf7fa360b6a5d0e16fd8cda48aa285d66
-2026-07-30-composer-context-stack-order.zh.md: 47288141ea4591b29adde0f85e810fc797740488
+2026-07-30-composer-context-stack-order.md: 150225ce27fa8459703170622cef754b7694e2fc
+2026-07-30-composer-context-stack-order.zh.md: f13ffc3c1136707a86ba5636a5b69304a132df01

.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.md

@@ -10,7 +10,7 @@ Goal, Todo, and Queue contribute independently to the same `conversation.input.d
 
 ## Decision
 
-The composer context stack has one canonical ascending order: Goal at `0`, Todo at `10`, and Queue at `20`, followed by the composer bar outside the list. The gaps leave room for future entries to declare their intended position without relying on plugin activation order.
+The [Todo-first alignment decision](2026-08-02-todo-first-composer-context-order.md) owns the current ascending order. This note retains the stack contract around that order: numeric gaps leave room for future entries to declare their intended position without relying on plugin activation order, and the composer bar follows the list.
 
 `ConversationRoot` owns the 6px space between independent context cards. Goal is a standalone 752×36px card and collapsed Todo is a standalone 752×44px card. Queue is the terminal dock entry: its 776px wrapper contains the same 752px panel column and subtracts the shared gap plus a named 5px layout overlap, so the later composer card paints over only the queue edge. Empty entries render null and consume no gap.
 
@@ -18,7 +18,7 @@ The order and overlap are separate contracts. Registration order establishes sem
 
 ## Verification
 
-Registration tests pin all three order values. Browser screenshots cover the full Goal/Todo/Queue matrix, Goal+Todo without Queue, and Queue alone; together they exercise every adjacency: Goal–Todo, Todo–Queue, and Queue–Composer.
+Registration tests pin all three order values. The keyless Queue browser scenario renders Todo, Goal, and Queue together, pins their accessibility order, and checks their visible card edges; focused Goal and Queue scenarios cover their independent states.
 
 ## Alternatives considered
 
@@ -30,4 +30,4 @@ Registration tests pin all three order values. Browser screenshots cover the ful
 
 ## Consequences
 
-The visual hierarchy is stable for every presence combination, and Queue is the only context surface joined to the composer. New input-dock plugins must choose an order relative to Goal `0`, Todo `10`, and Queue `20`; an entry after Queue also requires an explicit decision about which surface owns the composer boundary.
+The visual hierarchy is stable for every presence combination, and Queue is the only context surface joined to the composer. New input-dock plugins must choose an order relative to Todo `0`, Goal `10`, and Queue `20`; an entry after Queue also requires an explicit decision about which surface owns the composer boundary.

.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.zh.md

@@ -10,7 +10,7 @@ Goal、Todo 与 Queue 独立注册到同一个 `conversation.input.dock` 列表
 
 ## 决策
 
-composer 上下文堆栈采用唯一规范的升序排列：Goal 为 `0`，Todo 为 `10`，Queue 为 `20`，随后是位于列表外的 composer bar。顺序值之间的空档使未来条目可以声明预期位置，不必依赖插件激活顺序。
+[Todo 优先的对齐决策](2026-08-02-todo-first-composer-context-order.md)规定当前的升序排列。本记录保留围绕该顺序的堆栈契约：数值间隔使未来条目可以声明预期位置，不必依赖插件激活顺序；composer bar 位于列表之后。
 
 `ConversationRoot` 负责独立上下文卡片之间的 6px 间距。Goal 是一张独立的 752×36px 卡片，折叠后的 Todo 是一张独立的 752×44px 卡片。Queue 是末端 dock 条目：其 776px 包装层包含相同的 752px 面板列，并减去共享间距与具名的 5px 布局重叠量，因此后渲染的 composer 卡片只覆盖 Queue 边缘。空条目渲染为 null，不占用间距。
 
@@ -18,7 +18,7 @@ composer 上下文堆栈采用唯一规范的升序排列：Goal 为 `0`，Todo
 
 ## 验证
 
-注册测试固定了三个顺序值。浏览器截图覆盖完整的 Goal／Todo／Queue 组合矩阵、没有 Queue 的 Goal+Todo，以及仅有 Queue 的情况；这些场景共同覆盖全部相邻关系：Goal–Todo、Todo–Queue 与 Queue–Composer。
+注册测试固定了三个顺序值。无密钥 Queue 浏览器场景同时渲染 Todo、Goal 和 Queue，固定它们的无障碍顺序，并检查其可见卡片边缘；聚焦的 Goal 与 Queue 场景覆盖各自的独立状态。
 
 ## 考虑过的替代方案
 
@@ -30,4 +30,4 @@ composer 上下文堆栈采用唯一规范的升序排列：Goal 为 `0`，Todo
 
 ## 后果
 
-所有存在组合下的视觉层级都保持稳定，Queue 是唯一与 composer 相接的上下文界面。新的 input-dock 插件必须相对于 Goal `0`、Todo `10` 与 Queue `20` 选择顺序；若条目位于 Queue 之后，还必须明确决定由哪个界面负责 composer 边界。
+所有存在组合下的视觉层级都保持稳定，Queue 是唯一与 composer 相接的上下文界面。新的 input-dock 插件必须相对于 Todo `0`、Goal `10` 与 Queue `20` 选择顺序；若条目位于 Queue 之后，还必须明确决定由哪个界面负责 composer 边界。

.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.md
+2026-08-02-goal-round-wrapup-message.md: c6bc3d5912b0789efde55880c2be892e98e34a5b
+2026-08-02-goal-round-wrapup-message.zh.md: 0a504b4dcc61feb932775b3d9ffd8424f3b0597d

.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.md

@@ -0,0 +1,31 @@
+# Agent Note: Goal-round wrap-up message
+
+Status: implemented
+
+English | [中文](2026-08-02-goal-round-wrapup-message.zh.md)
+
+## Problem
+
+An autonomous goal round that reported `update_goal` `complete` or `blocked` concluded the physical turn at the tool result, so the model never spoke after the call. Sessions ended on a bare `update_goal` card, and internal testers read that as the agent stopping mid-sentence: the model's pre-call text routinely announces a report ("goal achieved, marking complete:") that never arrives, because the standard tool-use expectation is one more assistant message after a tool result and neither the goal-round prompt nor the tool description said the call was terminal. The hard stop came from the [goal-tool decision](../feature/2026-07-19-model-facing-goal-tools.md), whose turn-stop clause this note supersedes.
+
+## Decision
+
+A goal-round `complete` or `blocked` success no longer calls `concludeTurn()`. Instead the tool defers one wrap-up context onto its own result: a `{ kind: 'plugin', plugin: 'tool-goal' }`-sourced user message carrying a `<goal_complete>`/`<goal_blocked>` instruction to write a grounded closing message to the user and call no more tools. The turn then ends through the agent loop's ordinary no-tool-calls stop, so no new loop primitive exists and steering semantics are untouched. Direct-human mutations remain uninstructed exactly as before. The cost is one additional model request per goal lifecycle, not per round.
+
+The instruction wording was selected by A/B sampling on `deepseek-v4-pro` with a reconstructed goal-round transcript: a structured instruction (outcome, verification, artifacts, next steps) consistently beat a minimal "summarize" one on completeness; adding a session-grounding clause shifted unsupported detail from asserted fact to hedged suggestion; and the no-instruction control produced high-variance closings, including confidently fabricated file-level detail.
+
+Scripting the keyless proof required one snapshot-harness addition: `dsh-llm-replay` resolves `{{fromRequest:<regex>}}` placeholders in scripted entries against the live request, because a static sidecar cannot know the randomly minted goal id the model must echo into `update_goal`.
+
+## Verification
+
+`tool-goal` package tests pin the injected context (source, tag, objective, no-more-tools clause) and the absent `concludesTurn` for both terminal actions, plus the uninstructed direct-human pause and complete paths, at 100% file coverage. `llm-replay` unit tests pin the placeholder contract: last-match-wins capture, whole-match fallback, and loud failures for unmatched, invalid, and unterminated patterns. The new keyless ACP snapshot `goal-wrapup` drives the shipped application through create → round one → autonomous complete and asserts the plugin-sourced wrap-up injection, the same-turn closing assistant message, and the `completed` turn end in both the durable session log and the ACP stdout stream.
+
+## Alternatives considered
+
+- **Surface the completion text on the `update_goal` UI card** — rejected: `complete` carries no free text today, and adding a `summary` argument would route a user-facing report through tool arguments while still cutting off the model's natural post-result message.
+- **Keep `concludeTurn()` and add a "one more text-only step" loop primitive** — rejected: new `agent-loop` machinery for behavior the ordinary stop already provides once nothing concludes the turn.
+- **Instruct inside the tool result content** — rejected: the goal tools' canonical output is compact JSON consumed programmatically; a prose instruction block inside it would mix the model-facing contract with the tool's replayable value.
+
+## Consequences
+
+Every autonomous goal ends with a user-facing closing message instead of a bare tool card, at the cost of one model request per goal lifecycle. `concludeTurn()` keeps its loop semantics but loses its only first-party caller outside subagent structured output. Snapshot scenarios can now script values that only exist at run time via `{{fromRequest:...}}`, which unblocks keyless coverage of any echo-an-id tool flow, goal or otherwise.

.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.zh.md

@@ -0,0 +1,31 @@
+# Agent Note：Goal Round 收尾消息
+
+Status: implemented
+
+[English](2026-08-02-goal-round-wrapup-message.md) | 中文
+
+## 问题
+
+自主 Goal Round 报告 `update_goal` `complete` 或 `blocked` 时，物理轮次在工具结果处直接终结，模型在调用之后再无发言机会。会话终止在一张裸的 `update_goal` 卡片上，内测同学的观感是 agent 话说到一半戛然而止：模型调用前的文本通常预告了一份汇报（“目标达成，标记完成：”）却永远没有下文，因为标准 tool-use 预期是工具结果之后还有一条 assistant 消息，而 Goal Round 提示词与工具描述都没有说明这次调用是终点。硬停止来自 [goal 工具决策](../feature/2026-07-19-model-facing-goal-tools.md)，本 note 取代其中的轮次停止条款。
+
+## 决策
+
+Goal Round 的 `complete` 或 `blocked` 成功不再调用 `concludeTurn()`。工具改为在自己的结果上附带一条收尾上下文：以 `{ kind: 'plugin', plugin: 'tool-goal' }` 为 source 的 user 消息，携带 `<goal_complete>`/`<goal_blocked>` 指令，要求模型向用户写出有依据的收尾消息且不再调用工具。之后轮次经由 agent loop 常规的无工具调用停止路径结束，因此不存在新的 loop 原语，steering 语义不受影响。人类直接变更保持原样、不注入指令。代价是每个 goal 生命周期一次额外模型请求，而非每轮一次。
+
+指令措辞通过在 `deepseek-v4-pro` 上用重构的 Goal Round 转录做 A/B 采样选定：结构化指令（结果、验证、产物、后续）在完整度上稳定优于极简“总结一下”；补充“以会话内证据为准”的 grounding 条款让无依据细节从断言事实退为带保留的建议；而无指令对照组的收尾方差很大，包括言之凿凿的文件级细节编造。
+
+为让 keyless 证明可脚本化，快照设施补了一项能力：`dsh-llm-replay` 会针对实时请求解析脚本条目中的 `{{fromRequest:<regex>}}` 占位符，因为静态伴随文件不可能预知模型必须回填进 `update_goal` 的随机生成 goal id。
+
+## 验证
+
+`tool-goal` 包测试钉住两个终态 action 注入的上下文（source、标签、objective、禁止再调工具条款）与不存在的 `concludesTurn`，以及人类直接 pause 与 complete 的不注入路径，文件覆盖率 100%。`llm-replay` 单元测试钉住占位符契约：最后一次匹配取胜的捕获、无捕获组时整体匹配回退，以及未匹配、非法、未闭合模式的明确报错。新增 keyless ACP 快照 `goal-wrapup` 驱动成品应用走完 create → 第一轮 → 自主 complete，并在持久会话日志与 ACP stdout 流中同时断言 plugin 来源的收尾注入、同轮内的收尾 assistant 消息与 `completed` 轮次结束。
+
+## 曾考虑的替代方案
+
+- **在 `update_goal` 的 UI 卡片上展示完成文本** — 拒绝：`complete` 如今不携带任何自由文本；新增 `summary` 参数会让面向用户的汇报走工具参数通道，而且依然砍掉了模型在结果之后的自然发言。
+- **保留 `concludeTurn()` 并新增“再多一步纯文本”的 loop 原语** — 拒绝：为常规停止路径已经能提供的行为（只要没有结果终结轮次）增加新的 `agent-loop` 机制。
+- **把指令写进工具结果内容** — 拒绝：goal 工具的规范输出是被程序化消费的紧凑 JSON；在其中混入散文指令会把模型侧契约和工具的可回放值搅在一起。
+
+## Consequences
+
+每个自主 goal 都以一条面向用户的收尾消息结束，而非一张裸工具卡片，代价是每个 goal 生命周期一次模型请求。`concludeTurn()` 保留其 loop 语义，但在 subagent 结构化输出之外失去了唯一的一方调用者。快照场景现在可以通过 `{{fromRequest:...}}` 脚本化只在运行时才存在的值，为任何“回显 id”类工具流程（不限于 goal）解锁 keyless 覆盖。

.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.md
+2026-08-02-todo-first-composer-context-order.md: 26962426c763c6911fc61acab09cdb96725922b1
+2026-08-02-todo-first-composer-context-order.zh.md: a81401ffeb8df5855b584a5727e24067d9fb1e70

.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.md

@@ -0,0 +1,33 @@
+# Agent Note: Todo-first composer context order
+
+Status: implemented
+
+English | [中文](2026-08-02-todo-first-composer-context-order.zh.md)
+
+## Problem
+
+The composer context stack rendered Goal before Todo even though the Harness design orders the current task plan before its ongoing goal and pending Queue. Todo also used the Queue wrapper's 776px width as its visible card width, while Goal and the Queue panel rendered on the shared 752px card column. The result inverted the intended information hierarchy and left Todo wider than both adjacent panels.
+
+## Decision
+
+The `conversation.input.dock` list uses one ascending product order: Todo at `0`, Goal at `10`, and Queue at `20`, followed by the composer bar outside the list. Registration order remains the semantic source of truth; the renderer does not hardcode known component ids or repair their order with CSS.
+
+Todo, Goal, and the visible Queue panel share the 752px card column inside the 800px composer cap. Queue retains a 776px wrapper with 12px transparent inset on each side because that wrapper owns the composer overlap. Todo is a standalone card rather than a wrapper, so its responsive width and maximum width subtract both inset layers directly. Goal uses the same responsive column and caps its inner bar at 752px, preserving matching edges below the desktop cap.
+
+The [composer stack contract](2026-07-30-composer-context-stack-order.md) continues to own inter-card spacing and Queue's exclusive overlap with the composer. This decision supersedes only that note's Goal-first order.
+
+## Verification
+
+Todo and Goal registration tests pin orders `0` and `10`; Queue remains pinned at `20`. The keyless Queue browser scenario renders all three panels concurrently, records their Todo–Goal–Queue accessibility order, and compares their visible bounding boxes at the 1680px desktop baseline and a 640px sub-cap viewport before exercising Queue mutations.
+
+## Alternatives considered
+
+**Reorder the known panels inside `ConversationRoot`.** Rejected because `conversation.input.dock` is an extensible ordered list; a hardcoded component inventory would make plugin activation order and rendered order disagree.
+
+**Use CSS `order` to move Todo visually.** Rejected because accessibility and keyboard order must match the visual hierarchy, and the slot ledger already owns semantic order.
+
+**Keep Todo at the Queue wrapper width.** Rejected because the Queue wrapper's transparent inset is layout infrastructure for its composer overlap, not part of the visible panel column.
+
+## Consequences
+
+The standing task plan appears before the ongoing goal, pending Queue work remains closest to the composer, and all three visible cards share one horizontal edge. Future input-dock plugins choose an explicit position relative to Todo `0`, Goal `10`, and Queue `20`; only Queue owns the terminal wrapper overlap.

.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.zh.md

@@ -0,0 +1,33 @@
+# Agent Note: Todo 优先的 composer 上下文顺序
+
+Status: implemented
+
+[English](2026-08-02-todo-first-composer-context-order.md) | 中文
+
+## 问题
+
+composer 上下文堆栈将 Goal 渲染在 Todo 之前，但 Harness 设计稿把当前任务计划排在进行中的目标和待处理 Queue 之前。Todo 还把 Queue 包装层的 776px 宽度用作自身的可见卡片宽度，而 Goal 和 Queue 面板则渲染在共享的 752px 卡片列上。结果既颠倒了预期的信息层级，也让 Todo 比相邻两个面板更宽。
+
+## 决策
+
+`conversation.input.dock` 列表采用统一的产品顺序，升序依次为 Todo `0`、Goal `10`、Queue `20`，随后是位于列表外的 composer bar。注册顺序仍是语义真源；渲染器不会硬编码已知组件 id，也不会使用 CSS 修正它们的顺序。
+
+Todo、Goal 与可见的 Queue 面板共用 800px composer 宽度上限内的 752px 卡片列。Queue 保留 776px 包装层，并在两侧各留 12px 透明内缩，因为该包装层负责与 composer 重叠。Todo 是独立卡片，而非包装层，因此其响应式宽度和最大宽度都会直接扣除两层内缩。Goal 使用相同的响应式卡片列，并将内层横条的宽度上限设为 752px，从而在低于桌面宽度上限时也保持边缘对齐。
+
+[composer 堆栈契约](2026-07-30-composer-context-stack-order.md)继续规定卡片间距，以及仅限 Queue 与 composer 重叠。本决策只取代该记录中 Goal 优先的顺序。
+
+## 验证
+
+Todo 与 Goal 的注册测试分别固定顺序 `0` 和 `10`；Queue 仍固定为 `20`。无密钥 Queue 浏览器场景同时渲染三个面板，记录 Todo–Goal–Queue 的无障碍顺序，并在 1680px 桌面基线和低于宽度上限的 640px 视口下比较其可见边界框，随后再执行 Queue 变更。
+
+## 考虑过的替代方案
+
+**在 `ConversationRoot` 内重新排列已知面板。** 不予采纳，因为 `conversation.input.dock` 是可扩展的有序列表；硬编码的组件清单会使插件激活顺序与渲染顺序不一致。
+
+**使用 CSS `order` 移动 Todo 的视觉位置。** 不予采纳，因为无障碍顺序和键盘顺序必须与视觉层级一致，而 slot 账本已经负责语义顺序。
+
+**让 Todo 保持 Queue 包装层的宽度。** 不予采纳，因为 Queue 包装层的透明内缩是其与 composer 重叠所需的布局基础设施，不属于可见面板列。
+
+## 后果
+
+当前有效的任务计划显示在进行中的目标之前，待处理 Queue 工作仍最靠近 composer，三张可见卡片共用相同的横向边缘。未来的 input-dock 插件必须相对于 Todo `0`、Goal `10` 和 Queue `20` 选择明确位置；仅 Queue 负责末端包装层与 composer 的重叠。

.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml

@@ -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
-2026-07-19-model-facing-goal-tools.md: bc4305af80bb13ceeff1888d489dcd8a00132f94
-2026-07-19-model-facing-goal-tools.zh.md: b07f62aa526902c4b2e9c081777a76ca53783d31
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md
+2026-07-19-model-facing-goal-tools.md: 18235c484194f5daf10556ebfc13bdc2d672be2e
+2026-07-19-model-facing-goal-tools.zh.md: cc23a76e5faac2c203052d834ca0a87ca5dbed2a

.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md

@@ -22,7 +22,7 @@ The prompt tells the model that it may infer goal intent from a direct human req
 
 All three tools use exclusive execution so a model-ordered batch observes prior mutations and their new revisions. Results are compact JSON. UI presentation is a pure function of arguments and uses generic read or mutation cards; mutation cards select meaningful action values before the goal id, so accepted fillers cannot blank their input. Activation is reported only as live observation and is never written into replay state.
 
-An autonomous goal round that successfully reports completion or blocking marks its tool result as concluding the physical turn, preventing an unnecessary follow-up request. Direct-human mutations do not conclude the turn: the assistant can acknowledge the change, and concurrent human steering remains available to ordinary stopping checks.
+An autonomous goal round that successfully reports completion or blocking defers one wrap-up instruction onto its tool result so the model still addresses the user before the turn ends through the ordinary no-tool-calls stop; the original conclude-at-result stop is superseded by the [goal-round wrap-up decision](../bug-fix/2026-08-02-goal-round-wrapup-message.md). Direct-human mutations receive no instruction: the assistant can acknowledge the change, and concurrent human steering remains available to ordinary stopping checks.
 
 ### Execution authority
 

.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md

@@ -22,7 +22,7 @@ Status: implemented
 
 三个工具都采用独占执行，使模型排序的批次可以观察此前变更及其新修订号。结果为紧凑 JSON。UI 展示是参数的纯函数，使用通用读取或变更卡片；变更卡片选择输入时，先取有实际意义的操作值，再取目标 id，因此允许的占位值不会使卡片输入留空。激活态仅作为实时观察返回，绝不会写入回放状态。
 
-自主目标回合成功报告完成或阻塞后，其工具结果会被标记为结束该物理轮次，避免再发起一次不必要的模型请求。直接人类发起的变更不会结束轮次：agent 可以确认该变更，并且并发的人类 steering（中途引导）仍可参与普通的停止检查。
+自主目标回合成功报告完成或阻塞后，其工具结果会附带一条收尾指令，模型仍会在轮次经由常规无工具调用停止路径结束前向用户发言；原先在结果处终结轮次的做法已被[Goal Round 收尾决策](../bug-fix/2026-08-02-goal-round-wrapup-message.md)取代。直接人类发起的变更不会收到指令：agent 可以确认该变更，并且并发的人类 steering（中途引导）仍可参与普通的停止检查。
 
 ### 执行权限
 

.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.md
-2026-07-22-docked-web-goal-bar.md: 30f1d45e80cb2759175948f5683b499720ab50f0
-2026-07-22-docked-web-goal-bar.zh.md: 4c8481e64d9e5177a962f10ab1d043e761d07545
+2026-07-22-docked-web-goal-bar.md: 21f200f165acdf370a5896acb8f54afe33a4ee99
+2026-07-22-docked-web-goal-bar.zh.md: eb8e3edda54207b06e25812a38f969e74f342c34

.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.md

@@ -10,7 +10,7 @@ The web UI had no goal surface at all: the goal stack shipped with model tools,
 
 ## Decision
 
-`GoalBar` (`packages/client/ui-goal/src/client/GoalBar.tsx`) is a props-driven, self-contained component registered first in the composer's input-dock list. Its standalone 752px card follows the composer's horizontal geometry, and every visible state shares one fixed 36px height so switching phases never resizes it. Loading (`goal === undefined`), absent (`goal === null`), and `phase === 'complete'` render nothing — a completed goal is history, not chrome.
+`GoalBar` (`packages/client/ui-goal/src/client/GoalBar.tsx`) is a props-driven, self-contained component registered second in the composer's input-dock list, after Todo and before Queue. Its standalone 752px card follows the composer's horizontal geometry, and every visible state shares one fixed 36px height so switching phases never resizes it. Loading (`goal === undefined`), absent (`goal === null`), and `phase === 'complete'` render nothing — a completed goal is history, not chrome.
 
 Visibility drives the label and actions: active shows "Ongoing Goal" with pause/edit/clear; paused shows "Paused Goal" and swaps pause for a resume icon button; blocked shows "Blocked Goal" and carries `blockedReason.message` as the strip's `title` tooltip. Goal creation lives on the `/goal` command, not in the bar. The pencil swaps the strip for an inline edit form prefilled with the current objective: Enter or the check button saves through `GoalBarActions.onEdit(objective)`, Esc cancels, and an all-whitespace objective keeps save disabled. The form closes only when the edit succeeds; a failure preserves the draft and displays the error in the bar. Resume and clear failures are displayed there as well. Clear otherwise calls `onClear` directly with no confirmation — a clear keeps a durable tombstone, so nothing is unrecoverable. Every mutation first acquires a synchronous component-local single-flight latch because React's pending-state render cannot close the same-frame click window. A successful clear also suppresses that exact goal id immediately while the authoritative null projection catches up, so an acknowledged tombstone cannot leave a stale clear control that submits `GOAL_NOT_FOUND`; a failure releases the latch and remains retryable. An effect keyed on the goal's id resets this transient state and drops the edit form when the goal's identity changes, so neither a cleared marker nor a surviving draft can affect the replacement goal.
 

.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.zh.md

@@ -10,7 +10,7 @@ Web UI 此前没有任何目标相关的界面：目标栈已随模型工具、T
 
 ## 决策
 
-`GoalBar`（`packages/client/ui-goal/src/client/GoalBar.tsx`）是一个由 props 驱动的自包含组件，在 composer 的 input-dock 列表中注册为第一个条目。它采用独立的 752px 卡片，遵循 composer 的水平几何；所有可见状态均使用固定的 36px 高度，切换阶段不会改变尺寸。加载中（`goal === undefined`）、无目标（`goal === null`）和 `phase === 'complete'` 时不渲染任何内容：已完成的目标是历史记录，不是常驻界面元素。
+`GoalBar`（`packages/client/ui-goal/src/client/GoalBar.tsx`）是一个由 props 驱动的自包含组件，在 composer 的 input-dock 列表中注册为第二个条目，位于 Todo 之后、Queue 之前。它采用独立的 752px 卡片，遵循 composer 的水平几何；所有可见状态均使用固定的 36px 高度，切换阶段不会改变尺寸。加载中（`goal === undefined`）、无目标（`goal === null`）和 `phase === 'complete'` 时不渲染任何内容：已完成的目标是历史记录，不是常驻界面元素。
 
 可见性决定标签和操作：active 状态显示 "Ongoing Goal" 并提供暂停／编辑／清除；paused 状态显示 "Paused Goal"，把暂停换成一个恢复图标按钮；blocked 状态显示 "Blocked Goal"，并把 `blockedReason.message` 作为横条的 `title` 悬浮提示。创建目标的入口在 `/goal` 命令上，不在横条里。铅笔图标把横条切换为内联编辑表单，预填当前目标内容：Enter 或勾选按钮通过 `GoalBarActions.onEdit(objective)` 保存，Esc 取消，目标内容全为空白字符时保存按钮保持禁用。编辑成功后表单才会关闭；编辑失败时保留草稿，并在横条中显示错误。恢复和清除失败也显示在横条中。除此之外，清除直接调用 `onClear`，不做确认——清除会保留 durable 墓碑，没有不可恢复的损失。每次变更都会先取得一个同步的组件内 single-flight 锁，因为 React 的 pending 状态渲染无法关闭同一帧内的点击窗口。清除成功后还会立即抑制该 goal id，直到权威的 null 投影追上，因此已确认的墓碑不会留下陈旧的清除控件并再次提交 `GOAL_NOT_FOUND`；失败则释放锁，并且仍可重试。一个以目标 id 为键的 effect 会在目标身份变化时重置瞬态状态并丢弃编辑表单，因此无论已清除标记还是存留草稿，都不会影响替换目标。
 

.agents/notes/implemented/feature/2026-07-29-addressable-queue-operations.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-29-addressable-queue-operations.md
-2026-07-29-addressable-queue-operations.md: 02519f8fe8be60823ac773ac4cceecb9f12f88b2
-2026-07-29-addressable-queue-operations.zh.md: 998fc49ae7289b07c97312d4814d85b5cc84387b
+2026-07-29-addressable-queue-operations.md: 04bcaa26be2f4f70c4003f6cc2fce4798499d205
+2026-07-29-addressable-queue-operations.zh.md: a16bf8667294de8d08da54ddb0d317bf9938e4eb

.agents/notes/implemented/feature/2026-07-29-addressable-queue-operations.md

@@ -12,13 +12,13 @@ The Web queue rendered pending messages but could not edit or delete one row. `M
 
 **Each accepted FIFO occurrence has its own identity.** AgentLoop mints an opaque `InboxItemId` and publishes an `InboxItem` containing that id, the identified `UserMessage`, and its acceptance-time `queued | steering` placement. Reusing one `MessageId` creates distinct inbox identities. Injection bypasses the FIFOs and receives no inbox identity.
 
-**Mutation ends at driver claim.** `Agent.updateInbox(id, action)` synchronously searches the pending queued FIFO. Edit replaces frozen content while preserving `InboxItemId`, `MessageId`, source, wake policy, and position. Remove emits the occurrence’s terminal discard. Steering and driver-claimed occurrences return `not-found`, so queue operations never rewrite active-turn input or durable history.
+**Mutation ends at driver claim.** `Agent.updateInbox(id, action)` synchronously searches the pending queued FIFO. Edit replaces frozen content while preserving `InboxItemId`, `MessageId`, source, wake policy, and position. Remove emits the occurrence’s terminal discard. Strict steer transfers the message into an open next-step window as a new steering occurrence; a closed window returns `steer-unavailable` without changing the queued item. Pending steering and driver-claimed occurrences return `not-found`, so later mutations never rewrite active-turn input or durable history.
 
 **The live ledger is authoritative.** `agent/inbox/enqueue`, `update`, `dequeue`, and `discard` maintain a Host mirror of queued occurrences. A synchronously re-entrant update or terminal event may reach the mirror before its outer enqueue listener; the mirror retains that unseen outcome for the current dispatch and folds it into the enqueue, so listener registration order cannot publish stale content or a ghost row. The wire sends complete `session/queue` snapshots rather than incremental guesses. Reconnect sends the current baseline, and every queued mutation or terminal event replaces it. The client applies no optimistic edit and never retires a row from durable turn events or status changes.
 
 **Queue addresses require a live ordinary-session Agent.** `session.updateQueue` queries only the mounted Agent registry and never resumes a cold session: an `InboxItemId` is process-local and cannot name work after restart or disposal. A session-backed subagent returns `agent-busy` before inbox access and retains its continuation owner; for ordinary sessions, a missing Agent and a driver-claimed occurrence both return `queue-item-not-found`.
 
-**Web actions address Queue only.** The Host excludes pending steering from `session/queue`; steering retains its existing durable transcript path after consumption. QueueDock hides while empty, renders one pending occurrence directly, and defaults two or more occurrences to a collapsed `"<n> 条排队消息"` header that expands or collapses the complete list. The header exposes `aria-expanded` and `aria-controls`; the expanded list scrolls within a 180px height bound. An active edit or mutation keeps its rows visible, and emptying the queue restores the collapsed default for the next queue. Visible rows expose edit and delete, but no send-now control. The UI derives queue row and mutation types from the runtime `SessionFace` contract rather than importing the connection plugin, so plugin cooperation continues through services and snapshots. Edit is available only when all content blocks are text; the editor cannot silently drop non-text blocks. An editing row exposes only save and cancel, with Enter and Escape as their keyboard equivalents. Delete removes the exact occurrence. The Web stop action preserves pending Queue work; AgentLoop claims the next waking occurrence only after the interrupted turn reaches quiescence, and its dequeue event retires that row without a browser resend.
+**Web actions address Queue only.** The placement-aware `session/queue` snapshot carries both queued and pending-steering occurrences; QueueDock selects only queued items, while ChatView projects steering and retains the existing durable transcript path after consumption. QueueDock hides while empty, renders one pending occurrence directly, and defaults two or more occurrences to a collapsed `"<n> 条排队消息"` header that expands or collapses the complete list. The header exposes `aria-expanded` and `aria-controls`; the expanded list scrolls within a 180px height bound. An active edit or mutation keeps its rows visible, and emptying the queue restores the collapsed default for the next queue. Visible rows expose edit, delete, and a running-only strict-steer action. The UI derives queue row and mutation types from the runtime `SessionFace` contract rather than importing the connection plugin, so plugin cooperation continues through services and snapshots. Edit is available only when all content blocks are text; the editor cannot silently drop non-text blocks. An editing row exposes only save and cancel, with Enter and Escape as their keyboard equivalents. Delete removes the exact occurrence, while strict steer preserves every content block and retires the row only through the authoritative snapshot. The Web stop action preserves pending Queue work; AgentLoop claims the next waking occurrence only after the interrupted turn reaches quiescence, and its dequeue event retires that row without a browser resend. The [Web Queue steer action](2026-07-30-web-queue-steer-action.md) owns the strict transfer and pending-projection contract.
 
 ## Alternatives considered
 
@@ -26,7 +26,7 @@ The Web queue rendered pending messages but could not edit or delete one row. `M
 
 **Apply optimistic browser mutations.** Rejected because driver claim and another client can win before the Host action. Waiting for the authoritative snapshot makes the ownership boundary visible and lets `queue-item-not-found` report a real race.
 
-**Include pending steering in the queue mutation protocol.** Rejected because QueueDock has no steering interaction, and editing or deleting active-turn input would widen this feature beyond its current consumer. A dedicated steering interaction owns that delivery contract.
+**Allow editing or removal of pending steering.** Rejected because QueueDock only addresses independent queued turns. Once strict steer succeeds, the new steering occurrence belongs to the active turn and remains outside this mutation surface.
 
 **Expose a protocol-only promotion operation.** Rejected because no product interaction reorders Queue. A public operation without a current consumer would add ordering semantics and tests for speculative use.
 
@@ -34,10 +34,10 @@ The Web queue rendered pending messages but could not edit or delete one row. `M
 
 ## Verification
 
-AgentLoop contract tests hold prompt admission while editing and removing exact queued occurrences, reject mutations of steering occurrences, and verify the resulting independent turn and terminal lifecycle events. Host schema and proxy tests cover queued-only authoritative snapshots, synchronous re-entrant mutation order, reconnect, cold-Agent rejection, typed not-found errors, and the RPC transport. Client runtime and QueueDock tests cover non-optimistic projection, single-row presentation, default multi-row collapse, interaction-forced visibility, reset after emptying, expansion, text-only editing, save and cancel affordances, removal, retirement races, and disabled mixed-content editing. A keyless browser scenario captures the default collapsed header, drives edit and delete through the built Web composition and real HTTP/SSE wire, then stops consecutive active turns to prove the preserved FIFO advances without clearing its tail.
+AgentLoop contract tests hold prompt admission while editing, removing, and strictly steering exact queued occurrences; they reject mutations of steering occurrences and verify the resulting independent turn and terminal lifecycle events. Host schema and proxy tests cover queued-only authoritative snapshots, synchronous re-entrant mutation order, reconnect, cold-Agent rejection, typed race errors, and the RPC transport. Client runtime and QueueDock tests cover non-optimistic projection, single-row presentation, default multi-row collapse, interaction-forced visibility, reset after emptying, expansion, text-only editing, save and cancel affordances, removal, strict steer, retirement races, and disabled mixed-content editing. Keyless browser scenarios drive all three exposed actions through the built Web composition and real HTTP/SSE wire, then stop consecutive active turns to prove the preserved FIFO advances without clearing its tail.
 
 ## Consequences
 
-Queued work gains precise row operations without becoming durable session history. Occurrence identity is a live process-local capability and disappears at claim, broad cancellation, disposal, or restart; the Web stop action preserves it until a later claim, while reconnect recovers only queued items still held by the live Agent. Editing excludes mixed content until an editor can preserve every block, while pending steering remains outside this operation surface.
+Queued work gains precise row operations without becoming durable session history. Occurrence identity is a live process-local capability and disappears at claim, strict transfer, broad cancellation, disposal, or restart; the Web stop action preserves queued occurrences until a later claim, while reconnect recovers only queued items still held by the live Agent. Editing excludes mixed content until an editor can preserve every block, while pending steering remains outside the projection and operation surface.
 
 The protocol now carries full queue snapshots on each change. Queues are expected to remain short, so deterministic recovery and multi-client convergence are preferred over an incremental mutation protocol.

.agents/notes/implemented/feature/2026-07-29-addressable-queue-operations.zh.md

@@ -12,13 +12,13 @@ Web 队列能够渲染待处理消息，但无法编辑或删除其中某一行
 
 **每次获准进入 FIFO 的项都有独立标识。** AgentLoop 会铸造不透明的 `InboxItemId`，并发布一个 `InboxItem`，其中包含该 id、已有标识的 `UserMessage`，以及接受时确定的 `queued | steering` 放置方式。复用同一个 `MessageId` 会创建不同的 inbox 标识。注入绕过 FIFO，因此不会获得 inbox 标识。
 
-**变更边界止于驱动器认领。** `Agent.updateInbox(id, action)` 会同步搜索待处理的 queued FIFO。编辑会替换已冻结的内容，同时保留 `InboxItemId`、`MessageId`、来源、唤醒策略和位置。移除会发出该次入队项的终态 discard。steering（中途引导）项和已被驱动器认领的项会返回 `not-found`，因此队列操作绝不会改写活动轮次输入或持久历史。
+**变更边界止于驱动器认领。** `Agent.updateInbox(id, action)` 会同步搜索待处理的 queued FIFO。编辑会替换已冻结的内容，同时保留 `InboxItemId`、`MessageId`、来源、唤醒策略和位置。移除会发出该次入队项的终态 discard。严格 steering（中途引导）会把消息作为新的 steering 单次入队项转移到开放的 next-step 窗口；窗口关闭时返回 `steer-unavailable`，且不改变 queued 项。待处理 steering 和已被驱动器认领的项会返回 `not-found`，因此后续变更绝不会改写活动轮次输入或持久历史。
 
 **实时账本是权威状态。** `agent/inbox/enqueue`、`update`、`dequeue` 和 `discard` 共同维护 queued 入队项的 Host 镜像。同步可重入的 update 或终态事件可能先于外层 enqueue 监听器到达镜像；镜像会在当前分发期间保留这一尚不可见的结果，并在处理 enqueue 时把它合并进去，因此监听器注册顺序不会导致系统发布陈旧内容或不存在的行。协议发送完整的 `session/queue` 快照，而非增量猜测。重连会发送当前基线，每次 queued 变更或终态事件都会整体替换它。客户端不会进行乐观编辑，也绝不根据持久轮次事件或状态变化退役队列行。
 
 **Queue 寻址要求普通会话的 Agent 存活。** `session.updateQueue` 只查询已挂载的 Agent 注册表，绝不恢复冷会话：`InboxItemId` 属于进程本地标识，无法在重启或资源释放后继续指向工作。由会话支撑的 subagent 会在访问 inbox 前返回 `agent-busy`，并保留其继续执行 owner；对于普通会话，Agent 缺失和单次入队项已被驱动器认领这两种情况都返回 `queue-item-not-found`。
 
-**Web 操作只面向 Queue。** Host 从 `session/queue` 中排除待处理 steering；steering 消费后仍沿用既有的持久 transcript（文本记录）路径。QueueDock 在队列为空时隐藏，只有一个待处理项时直接渲染该行，存在两个或更多待处理项时则默认收起为可展开或收起完整列表的 `"<n> 条排队消息"` 表头。表头暴露 `aria-expanded` 和 `aria-controls`；展开后的列表以 180px 为高度上限，并可滚动。存在进行中的编辑或变更时，列表行会保持可见；队列清空后，下一次出现队列时会恢复默认收起状态。可见行暴露编辑和删除操作，不提供立即发送控件。UI 从运行时 `SessionFace` 契约派生队列行与变更类型，而不是导入连接插件，因此插件仍通过服务和快照协作。仅当所有内容块都是文本时才提供编辑功能；编辑器不能静默丢弃非文本块。编辑中的行只展示保存和取消操作，对应的键盘操作分别是 Enter 和 Escape。删除会移除对应的精确入队项。Web 停止操作会保留待处理 Queue 工作；只有在被中断轮次达到完全停稳后，AgentLoop 才认领下一个可唤醒入队项，其出队事件会退役该行，无需浏览器重发。
+**Web 操作只面向 Queue。** 带 placement 的 `session/queue` 会同时携带 queued 和待处理 steering；QueueDock 只选择 queued 项，ChatView 则投影 steering，并在消费后沿用既有的持久 transcript（文本记录）路径。QueueDock 在队列为空时隐藏，只有一个待处理项时直接渲染该行，存在两个或更多待处理项时则默认收起为可展开或收起完整列表的 `"<n> 条排队消息"` 表头。表头暴露 `aria-expanded` 和 `aria-controls`；展开后的列表以 180px 为高度上限，并可滚动。存在进行中的编辑或变更时，列表行会保持可见；队列清空后，下一次出现队列时会恢复默认收起状态。可见行暴露编辑、删除以及仅在运行期间可用的严格 steering 操作。UI 从运行时 `SessionFace` 契约派生队列行与变更类型，而不是导入连接插件，因此插件仍通过服务和快照协作。仅当所有内容块都是文本时才提供编辑功能；编辑器不能静默丢弃非文本块。编辑中的行只展示保存和取消操作，对应的键盘操作分别是 Enter 和 Escape。删除会移除对应的精确入队项；严格 steering 会保留每个内容块，并且只通过权威快照退役该行。Web 停止操作会保留待处理 Queue 工作；只有在被中断轮次达到完全停稳后，AgentLoop 才认领下一个可唤醒入队项，其出队事件会退役该行，无需浏览器重发。[Web Queue steering 操作](2026-07-30-web-queue-steer-action.md)负责定义严格转移与待处理投影契约。
 
 ## 考虑过的替代方案
 
@@ -26,7 +26,7 @@ Web 队列能够渲染待处理消息，但无法编辑或删除其中某一行
 
 **在浏览器中进行乐观变更。** 不予采纳，因为驱动器认领或另一个客户端可能先于 Host 操作完成。等待权威快照可以显式呈现所有权边界，并让 `queue-item-not-found` 报告真实竞态。
 
-**将待处理 steering 纳入队列变更协议。** 不予采纳，因为 QueueDock 没有 steering 交互，而编辑或删除活动轮次输入会把此功能扩展到当前消费方之外。应由专用 steering 交互负责该投递契约。
+**允许编辑或移除待处理 steering。** 不予采纳，因为 QueueDock 只寻址独立的 queued 轮次。严格 steering 一旦成功，新的 steering 单次入队项就属于活动轮次，并且不再位于此变更接口内。
 
 **暴露仅协议层的前移操作。** 不予采纳，因为当前没有产品交互会重新排序 Queue。公开一个没有当前消费方的操作，会为了推测性用途引入排序语义和测试。
 
@@ -34,10 +34,10 @@ Web 队列能够渲染待处理消息，但无法编辑或删除其中某一行
 
 ## 验证
 
-AgentLoop 契约测试会在编辑和移除精确 queued 入队项时阻塞提示词接纳，拒绝对 steering 入队项的变更，并验证所得独立轮次及终态生命周期事件。Host schema 与代理测试覆盖仅含 queued 项的权威快照、同步可重入变更顺序、重连、拒绝冷 Agent、类型化 not-found 错误和 RPC 传输。客户端运行时和 QueueDock 测试覆盖非乐观投影、单行呈现、多行默认收起、交互期间强制保持可见、清空后重置、展开、仅文本编辑、保存与取消入口、移除、退役竞态，以及禁用混合内容编辑。一个无密钥浏览器场景会捕获默认收起的表头，通过构建后的 Web 组合和真实 HTTP／SSE 协议执行编辑和删除，随后连续停止活动轮次，证明保留的 FIFO 会继续推进且不清空队尾。
+AgentLoop 契约测试会在编辑、移除和严格 steering 精确 queued 入队项时保持提示词接纳窗口打开，拒绝对 steering 入队项的变更，并验证所得独立轮次及终态生命周期事件。Host schema 与代理测试覆盖仅含 queued 项的权威快照、同步可重入变更顺序、重连、拒绝冷 Agent、类型化竞态错误和 RPC 传输。客户端运行时和 QueueDock 测试覆盖非乐观投影、单行呈现、多行默认收起、交互期间强制保持可见、清空后重置、展开、仅文本编辑、保存与取消入口、移除、严格 steering、退役竞态，以及禁用混合内容编辑。无密钥浏览器场景会通过构建后的 Web 组合和真实 HTTP／SSE 协议执行公开的全部三项操作，随后连续停止活动轮次，证明保留的 FIFO 会继续推进且不清空队尾。
 
 ## 后果
 
-queued 工作获得精确的行操作，但不会因此成为持久会话历史。单次入队标识是进程本地的实时寻址凭据，会在认领、广义取消、dispose 或重启时消失；Web 停止操作会将其保留到后续认领，而重连只能恢复仍由活跃 Agent 持有的 queued 项。编辑会排除混合内容，直至编辑器能够保留每个块；待处理 steering 则不属于此操作接口。
+queued 工作获得精确的行操作，但不会因此成为持久会话历史。单次入队标识是进程本地的实时寻址凭据，会在认领、严格转移、广义取消、dispose 或重启时消失；Web 停止操作会将 queued 入队项保留到后续认领，而重连只能恢复仍由活跃 Agent 持有的 queued 项。编辑会排除混合内容，直至编辑器能够保留每个块；待处理 steering 则不属于此投影和操作接口。
 
 现在，协议会在每次变更时携带完整队列快照。队列预期保持较短，因此系统优先选择确定性恢复和多客户端收敛，而非增量变更协议。

.agents/notes/implemented/feature/2026-07-30-web-queue-steer-action.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-web-queue-steer-action.md
+2026-07-30-web-queue-steer-action.md: b5bc3547e0f72ba8211f4338fb4c1f5223a3d0cc
+2026-07-30-web-queue-steer-action.zh.md: 6edde8e2cc2bee0a52a0b05df8f62f77b3d9ccfa

.agents/notes/implemented/feature/2026-07-30-web-queue-steer-action.md

@@ -0,0 +1,71 @@
+# Agent Note: Steer a queued Web message into the active turn
+
+Status: implemented
+
+English | [中文](2026-07-30-web-queue-steer-action.zh.md)
+
+## Problem
+
+The Web composer originally queued every Enter submission while an agent ran. QueueDock already gives each pending message an addressable row, and the durable transcript already renders consumed `steering/message` events as user-style bubbles, but Web had neither an action connecting those two surfaces nor a direct composer gesture for choosing current-turn steering.
+
+Implementing the row action as a client-side delete followed by `session.prompt(mode: 'steer')` would split one user intent across two RPCs. Driver claim could win between them, the steer could fail after deletion, or the existing best-effort `agent.steer()` fallback could silently append a new Queue item after the original occurrence was removed. A send-now action must therefore distinguish current-turn steering from Queue promotion and preserve the original row when steering is no longer possible.
+
+## Decision
+
+### Product contract
+
+Each non-editing ordinary-session QueueDock row exposes the upward-arrow action as “插话发送”. The action is enabled only while the session reports a running agent; mixed-content messages remain eligible because steering forwards the complete immutable `UserMessage` rather than the row's text projection. An addressed subagent keeps its Queue projection read-only because its continuation transport does not expose queue mutation.
+
+Activating the action requests strict current-turn steering for that exact `InboxItemId`. Success removes the Queue row through the authoritative Host snapshot and immediately projects the same pending steering after the `Deep diving...` running-status row; that bubble offers Copy but no Fork because the message has no durable event sequence yet. Once AgentLoop drains it, the existing durable `steering/message` event takes over the same user-style bubble and restores its clock, Copy, and Fork without a separate durable presentation path.
+
+The running bit is only an interaction hint. AgentLoop's `acceptsNextStep` value is authoritative at the synchronous mutation boundary. If that window has closed, the operation leaves the Queue occurrence unchanged and returns a typed `steer-unavailable` error, after which the original waking occurrence proceeds through Queue. If the driver already claimed the occurrence, it returns the existing `queue-item-not-found` error and independent-turn delivery is already underway. The UI treats both races as converged Queue delivery without a failure notice; transport and unknown errors still surface.
+
+The composer uses a separate best-effort contract for newly typed input. While the addressed session is idle, Enter and Cmd/Ctrl+Enter both perform an ordinary Queue send. While a primary session is running, a General Settings preference assigns plain Enter to Queue (the default) or Steer, and Cmd/Ctrl+Enter performs the other behavior; Shift+Enter inserts a newline. An addressed subagent keeps both gestures on its Queue-only continuation transport. The browser persists the preference, and it affects only the steer-capable busy-state gesture pair. If a direct composer Steer misses the current next-step window, AgentLoop automatically admits it as the next waking Queue turn and the Web does not report a failure.
+
+### Agent and lifecycle boundary
+
+`InboxAction` gains a consumer-backed `{ kind: 'steer' }` operation alongside edit and remove. `Agent.updateInbox()` handles it only after locating the queued occurrence and proving `acceptsNextStep`; it never delegates to the best-effort `agent.steer()` alias.
+
+An applied action ends the queued occurrence and accepts the same immutable `UserMessage` as a new steering occurrence. The steering occurrence receives a new `InboxItemId` and truthful `placement: 'steering'`, while the message retains its `MessageId`, content, source, and any pending `SteeringReceipt` delivery controller. AgentLoop installs the new outbox entry before publishing lifecycle events, then emits its enqueue before the old occurrence's discard so re-entrant cancellation cannot observe or retire an unannounced item. The existing inbox conservation invariant therefore continues to require one enqueue and one terminal dequeue or discard for each occurrence.
+
+The action does not run `agent/prompt-submit`: choosing steering intentionally changes delivery from an independently admitted turn to current-turn next-step input. It neither cancels current work nor reorders the remaining Queue.
+
+### Host and client boundary
+
+`session.updateQueue` carries the `steer` action and maps the two negative outcomes to typed RPC errors. The conversion is one synchronous Agent operation; the Host never reconstructs it by combining remove and prompt calls.
+
+The Host's existing `queuedMirror` remains the sole transient inbox authority. Its `session/queue` snapshot carries every live occurrence with `placement: 'queued' | 'steering'`: QueueDock renders only queued rows, while ChatView renders pending steering at the conversation tail after the `Deep diving...` running-status row, with Copy but without Fork, edit, or delete actions. Reconnect replays the same snapshot, so this visibility does not require client optimism or a second registry.
+
+When AgentLoop claims pending steering, it emits `agent/inbox/dequeue` immediately before synchronously appending `steering/message`. The Host retires that steering row on the following microtask, allowing the durable session event to enter the linear mux stream first. On the accepted live event, the client Session retires the first matching current steering occurrence before publishing its snapshot; history replay does not consume a later occurrence that reused the same `MessageId`. ChatView therefore renders one authority at a time without scanning durable history, and the durable projection restores the clock, Copy, and Fork against its logged event time and sequence. An append failure still retires the claimed row.
+
+The existing `session.prompt(mode: 'steer')` contract remains best-effort for new primary-session input: outside the next-step window it becomes a waking follow-up. The composer carries an explicit `queue | steer` mode through slash adjudication and reference serialization before calling that contract. A browser-local submission policy owns the persisted busy-Enter preference and resolves plain versus accelerated Enter as complementary gestures only for steer-capable sessions; the Settings row and InputBar share that policy without duplicating storage or delivery-window authority. Only the Queue row action is strict, because either negative result converges through the original Queue occurrence.
+
+### Verification
+
+AgentLoop contract coverage holds prompt admission open, converts one exact queued occurrence, and proves the replacement steering occurrence keeps the message value and delivery receipt, drains as `steering/message`, and never starts its former independent turn. It also pins unavailable-window retention, claimed-address rejection, and re-entrant cancellation lifecycle conservation.
+
+Host schema and proxy tests cover the new action, both typed errors, placement-aware snapshots and reconnect replay, plus durable-before-retirement ordering. Client tests cover silent convergence of both semantic races, genuine error reporting, read-only subagent rows and Queue-only subagent gestures. Runtime and ChatView tests cover occurrence-aware pending-to-durable handoff, including repeated `MessageId` values, while Web ARIA snapshots cover pending steering after the running-status row with Copy alone and the durable node with clock, Copy, and Fork.
+
+The keyless Web steering scenario queues a message through the real composer while the first response streams, activates the row arrow, then uses `ask_user_question` as a stable pending-steering barrier. It proves the Host-backed pending bubble appears before admission, hands off to one durable interjection after the answer, and affects the next model request. Assembled composer scenarios prove default-mode Cmd+Enter reaches the same pending and durable path without creating a Queue row, while Steer-mode Cmd+Enter creates a Queue row instead. Settings and submission-policy coverage pin the default, persistence, busy-only scope, and complementary gesture mapping; Queue edit/delete scenarios continue to prove those actions are unchanged.
+
+## Alternatives considered
+
+**Delete the row, then call `session.prompt(mode: 'steer')` from Web.** Rejected because two RPCs cannot make deletion and steering atomic; failure and driver-claim races can lose or duplicate the user's message.
+
+**Restore Queue promotion under the upward arrow.** Rejected because moving an item to the front still creates an independent admitted turn. The control promises current-turn steering, not priority within Queue.
+
+**Use the existing best-effort `agent.steer()` behavior for the Queue row.** Rejected for that action because a closed next-step window would create a new queued occurrence, possibly at a different position and identity. Strict refusal preserves the original occurrence so the UI can treat it as the same accepted Queue delivery. Newly typed composer input has no existing Queue occurrence to preserve, so it intentionally uses the best-effort behavior.
+
+**Change `agent.steer()` to be strict for every caller.** Rejected because TUI and plugin callers use its safe follow-up fallback for newly submitted input. A queued row has recoverable state that those callers do not.
+
+**Preserve the same `InboxItemId` while changing placement.** Rejected because `InboxItemId` identifies one FIFO acceptance and `placement` records that acceptance's resolved delivery. Ending one queued occurrence and accepting one steering occurrence keeps lifecycle facts truthful and leaves the conservation invariant unchanged.
+
+**Add a dedicated pending-steering projection and client store.** Rejected because queued and steering occurrences already share one Agent inbox lifecycle and one Host mirror. A second projection would duplicate reconnect state and ordering authority; a placement tag lets each client surface select its rows without widening Queue mutation semantics.
+
+**Cancel the active turn and run the selected Queue item.** Rejected because it destroys unrelated in-flight work and starts a new turn rather than steering the current one.
+
+## Consequences
+
+`session/queue` describes a placement-aware transient inbox snapshot rather than a Queue-only list, so every consumer must filter by placement. Pending steering survives reconnect and appears immediately, but remains non-durable until `steering/message` commits. The running bit can also remain true briefly after the strict next-step window closes, so an enabled action may internally return `steer-unavailable` while the product continues through Queue without reporting failure.
+
+The explicit action changes delivery from an independently admitted turn to current-turn steering, so prompt-admission plugins do not process the converted message. Enqueue-before-discard lifecycle publication remains required for re-entrant cancellation safety; focused regression coverage protects that ordering.

.agents/notes/implemented/feature/2026-07-30-web-queue-steer-action.zh.md

@@ -0,0 +1,71 @@
+# Agent Note（agent 决策记录）：将 Web 已排队消息转为活动轮次的 steering（中途引导）
+
+Status: implemented
+
+[English](2026-07-30-web-queue-steer-action.md) | 中文
+
+## 问题
+
+Web composer 原本会在 agent 运行期间把所有 Enter 提交作为 Queue 入队。QueueDock 已经为每条待处理消息提供可寻址的行，持久 transcript（文本记录）也已能把消费后的 `steering/message` 事件渲染为用户样式气泡，但 Web 既没有连接这两个界面的操作，也没有让用户从 composer 直接选择当前轮次 steering 的手势。
+
+如果 Web 先在客户端删除该行，再调用 `session.prompt(mode: 'steer')`，就会把用户的一次意图拆分到两个 RPC 中。驱动器可能在两次调用之间先认领该项，steering 投递也可能在删除后失败；现有尽力而为的 `agent.steer()` 回退还可能在原单次入队项被移除后，静默追加一个新的 Queue 项。因此，立即发送操作必须区分当前轮次 steering 与 Queue 前移，并在 steering 已不可用时保留原行。
+
+## 决策
+
+### 产品契约
+
+普通会话中每个非编辑态的 QueueDock 行都会提供名为“插话发送”的向上箭头操作。仅当会话报告 agent 正在运行时，该操作才会启用；包含混合内容的消息仍可使用，因为 steering 会转发完整且不可变的 `UserMessage`，而非该行的文本投影。已寻址 subagent 的 Queue 投影保持只读，因为其继续执行传输不提供 Queue 变更。
+
+触发该操作会针对对应的 `InboxItemId` 请求严格的当前轮次 steering。操作成功后，权威 Host 快照会移除 Queue 行，并在 `Deep diving...` 运行状态行之后立即投影同一条待处理 steering；该气泡提供复制，但消息尚无持久事件序号，因此不提供 fork。AgentLoop 排空该项后，现有持久 `steering/message` 事件会接管同一个用户样式气泡，并恢复时钟、复制和 fork，无需另建持久展示路径。
+
+running 标志位只用于提示交互状态。在同步变更边界上，AgentLoop 的 `acceptsNextStep` 值才是权威依据。如果该窗口已经关闭，操作会保持 Queue 单次入队项不变并返回类型化的 `steer-unavailable` 错误，随后原唤醒单次入队项会经 Queue 继续执行。如果驱动器已经认领该项，则返回现有的 `queue-item-not-found` 错误，且独立轮次投递已经开始。UI 会把两种竞态都视为已收敛的 Queue 投递，不显示失败通知；传输和未知错误仍会显示。
+
+Composer 对新输入采用另一套尽力而为契约。所寻址会话空闲时，Enter 和 Cmd/Ctrl+Enter 都执行普通 Queue 发送。主会话运行期间，General Settings 偏好会把普通 Enter 分配为 Queue（默认值）或 Steer，Cmd/Ctrl+Enter 则执行另一种行为；Shift+Enter 用于换行。已寻址 subagent 会让这两个手势都使用其仅支持 Queue 的继续执行传输。浏览器会持久化该偏好，并且它只影响支持 steering 的繁忙态手势对。如果 composer 直接发出的 Steer 错过当前 next-step 窗口，AgentLoop 会自动将其接纳为下一条唤醒 Queue 轮次，Web 不显示失败。
+
+### Agent 与生命周期边界
+
+`InboxAction` 会在编辑和移除之外，新增由实际消费方支撑的 `{ kind: 'steer' }` 操作。`Agent.updateInbox()` 只有在找到 queued 单次入队项并确认 `acceptsNextStep` 后才会处理该操作，绝不会委托给尽力而为的 `agent.steer()` 别名。
+
+操作成功应用后，系统会结束 queued 单次入队项，并把同一个不可变 `UserMessage` 接受为新的 steering 单次入队项。steering 单次入队项会获得新的 `InboxItemId` 和如实反映投递方式的 `placement: 'steering'`，消息则保留其 `MessageId`、内容、来源和任何待处理 `SteeringReceipt` 投递控制器。AgentLoop 会先安装新的 outbox 项，再发布生命周期事件；随后先发出新单次入队项的 enqueue，再发出旧单次入队项的 discard，确保可重入取消无法观察或退役一个尚未公布的项。因此，现有 inbox 守恒不变量仍然要求每个单次入队项恰好对应一个 enqueue，以及一个终态 dequeue 或 discard。
+
+该操作不会运行 `agent/prompt-submit`：选择 steering 会有意把投递方式从经独立接纳的轮次改为当前轮次的 next-step 输入。它既不会取消当前工作，也不会重新排序 Queue 中的剩余项。
+
+### Host 与客户端边界
+
+`session.updateQueue` 会携带 `steer` 操作，并把两种负面结果映射为类型化 RPC 错误。这项转换是一次同步 Agent 操作；Host 绝不会通过组合移除和提示词调用来重建它。
+
+Host 仍以现有 `queuedMirror` 作为唯一的瞬态 inbox 权威。`session/queue` 快照会携带所有存活单次入队项及其 `placement: 'queued' | 'steering'`：QueueDock 只渲染 queued 行，ChatView 则在会话流末尾、`Deep diving...` 运行状态行之后渲染待处理 steering，提供复制操作，但不提供 fork、编辑或删除操作。重连会重放同一份快照，因此这项可见性既不依赖客户端乐观展示，也不需要第二个 registry。
+
+AgentLoop 认领待处理 steering 时，会在同步追加 `steering/message` 之前立即发出 `agent/inbox/dequeue`。Host 会等到下一个微任务才退役该 steering 行，让持久 session 事件先进入线性 mux 流。客户端 Session 接纳该实时事件时，会在发布快照前退役第一个匹配的当前 steering 单次入队项；历史回放不会消费后来复用同一 `MessageId` 的单次入队项。因此，ChatView 无需扫描持久历史就能每次只渲染一份权威，持久投影则会根据已记录的事件时间与序号恢复时钟、复制与 fork 操作。追加失败时，已认领行仍会退役。
+
+现有 `session.prompt(mode: 'steer')` 对主会话新输入仍采用尽力而为的契约：在 next-step 窗口之外，它会变为唤醒 agent 的后续轮次。Composer 会让显式 `queue | steer` 模式经过 slash 裁决与引用序列化，再调用该契约。浏览器本地的提交策略拥有持久化的繁忙态 Enter 偏好，并且只为支持 steering 的会话把普通 Enter 与加速 Enter 解析为互补手势；Settings 行和 InputBar 共享该策略，不重复实现存储或投递窗口权威。只有 Queue 行操作采用严格语义，因为任一种负面结果都会经原 Queue 单次入队项收敛。
+
+### 验证
+
+AgentLoop 契约覆盖保持提示词接纳窗口打开，转换一个精确的 queued 单次入队项，并证明替代它的 steering 单次入队项保留消息值和投递回执、以 `steering/message` 的形式排空，且绝不启动原本的独立轮次。该覆盖还钉住窗口不可用时保留原项、拒绝已被认领的地址，以及可重入取消下的生命周期守恒。
+
+Host schema 和代理测试覆盖新操作、两种类型化错误、带 placement 的快照与重连重放，以及先持久化再退役的顺序。客户端测试覆盖两种语义竞态的静默收敛、真实错误报告、只读 subagent 行和仅支持 Queue 的 subagent 手势。运行时与 ChatView 测试覆盖按单次入队项完成的待处理到持久交接，包括重复的 `MessageId` 值；Web ARIA 快照则覆盖位于运行状态行之后且仅有复制的待处理 steering，以及带时钟、复制和 fork 的持久节点。
+
+无密钥 Web steering 场景在第一次响应流式输出期间，通过真实 composer 排队一条消息并触发行上的箭头，再用 `ask_user_question` 作为稳定的待处理 steering 屏障。该场景证明 Host 支撑的待处理气泡会在准入前出现，在回答后交接为唯一一条持久插话，并影响下一次模型请求。组装后的 composer 场景证明默认模式下的 Cmd+Enter 无需创建 Queue 行，也会进入同一条待处理与持久路径；Steer 模式下的 Cmd+Enter 则会创建 Queue 行。Settings 与提交策略覆盖会固定默认值、持久化、仅限繁忙态的作用域和互补手势映射；Queue 编辑／删除场景继续证明这些操作没有变化。
+
+## 考虑过的替代方案
+
+**在 Web 中删除该行，再调用 `session.prompt(mode: 'steer')`。** 不予采纳，因为两个 RPC 无法让删除和 steering 成为原子操作；失败和驱动器认领竞态可能丢失或重复用户消息。
+
+**恢复向上箭头对应的 Queue 前移操作。** 不予采纳，因为把某个项移到队首仍然会创建一个独立接纳的轮次。该控件承诺的是当前轮次 steering，而不是 Queue 内的优先级。
+
+**为 Queue 行使用现有尽力而为的 `agent.steer()` 行为。** 不予采纳，因为关闭的 next-step 窗口会创建新的 queued 单次入队项，而且位置和标识可能不同。严格拒绝会保留原单次入队项，让 UI 能将其视为同一次已接纳的 Queue 投递。新输入的 composer 消息没有需要保留的现有 Queue 单次入队项，因此有意采用尽力而为行为。
+
+**让每个调用方使用的 `agent.steer()` 都采用严格语义。** 不予采纳，因为 TUI 和插件调用方会针对新提交的输入使用其安全的后续轮次回退。queued 行具有这些调用方不具备的可恢复状态。
+
+**改变投递方式时保留同一个 `InboxItemId`。** 不予采纳，因为 `InboxItemId` 标识一次 FIFO 接受，而 `placement` 记录该次接受解析出的投递方式。结束一个 queued 单次入队项并接受一个 steering 单次入队项，能够使生命周期事实保持如实，并让守恒不变量保持不变。
+
+**增加专用的待处理 steering 投影和客户端 store。** 不予采纳，因为 queued 与 steering 单次入队项已经共享同一套 Agent inbox 生命周期和 Host mirror。第二份投影会重复保存重连状态与顺序权威；placement 标签能让各客户端界面选取自己的行，而不扩大 Queue 变更语义。
+
+**取消活动轮次并运行选中的 Queue 项。** 不予采纳，因为这会破坏无关的进行中工作，并且会启动新轮次，而不是 steering 当前轮次。
+
+## 后果
+
+`session/queue` 表示带 placement 的瞬态 inbox 快照，而不只是 Queue 列表，因此每个消费方都必须按 placement 过滤。待处理 steering 会在界面中立即出现并能在重连后恢复，但在 `steering/message` 提交前仍不持久。严格 next-step 窗口关闭后，running 标志位仍可能短暂保持为 true，因此已启用的操作可能会在内部返回 `steer-unavailable`，而产品仍经 Queue 继续执行且不显示失败。
+
+这项显式操作会把投递方式从经独立接纳的轮次改为当前轮次 steering，因此提示词接纳插件不会处理转换后的消息。为保证可重入取消安全，生命周期事件仍必须先发布 enqueue 再发布 discard；有针对性的回归覆盖会保护这一顺序。

.agents/notes/implemented/feature/2026-07-31-web-default-search.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-31-web-default-search.md
-2026-07-31-web-default-search.md: 121a1dff5fffd4223eefcc7475fff874276658aa
-2026-07-31-web-default-search.zh.md: ac98f4806413cb6050a08354a553942437866fe1
+2026-07-31-web-default-search.md: 8f2cc6f5d1a9ec9f33279ae8e5c992bdc660e7fa
+2026-07-31-web-default-search.zh.md: 7d528617143cb9756d0a4532bb1ed6a3a3e70ca8

.agents/notes/implemented/feature/2026-07-31-web-default-search.md

@@ -10,7 +10,7 @@ The harness had a complete Web capability family—provider registry, DeepSeek/E
 
 ## Decision
 
-`apps/cli/config/base.cordis.yml` explicitly mounts `dsh-web` with `searchProvider: deepseek-official`, `dsh-web-search-deepseek`, and `dsh-tool-web` with `fetch: false`. It does not mount `dsh-web-fetch-local` or select a fetch provider. The shared base makes only `web_search` a default for TUI, browser, and headless sessions. The explicit search provider id keeps selection independent of registration order and leaves personal or `--config` overlays able to replace or disable the rows.
+`apps/cli/config/base.cordis.yml` explicitly mounts `dsh-web` with `searchProvider: deepseek-official`, `dsh-web-search-deepseek`, and `dsh-tool-web` with `fetch: false` and `searchTimeoutMs: 60000`. It does not mount `dsh-web-fetch-local` or select a fetch provider. The shared base makes only `web_search` a default for TUI, browser, and headless sessions. The explicit search provider id keeps selection independent of registration order and leaves personal or `--config` overlays able to replace or disable the rows. The one-minute shipped budget covers an auxiliary DeepSeek Messages request plus server-side retrieval while leaving `dsh-tool-web`'s provider-neutral 30-second default unchanged for custom compositions.
 
 DeepSeek search uses the same `DEEPSEEK_API_KEY` credential reference as the official conversation adapter. The provider resolves that reference inside every search through the optional `ctx.credentials` service; only a composition without the seam falls back to the launching process environment, and a non-empty literal `apiKey` remains the programmatic last resort. A stored or rotated Web Models key therefore reaches the next search without restarting or retaining the value on the provider. Because `WebSearchProvider.available()` is synchronous, it treats an installed resolver as locally usable and missing dynamic credentials fail the operation with the provider-specific `WEB_PROVIDER_CREDENTIAL_MISSING` code while the stable tool schema stays registered.
 
@@ -28,8 +28,10 @@ The default mount does not create a Web-specific permission policy. `web_search`
 
 **Keep Web tools in `web.cordis.yml`.** Rejected because it preserves an unexplained tool-roster difference between TUI and Web/headless. The rows are not surface-specific, so `base.cordis.yml` is their one home; the [tool-roster decision](2026-07-31-even-out-shipped-tool-rosters.md) records the shared composition.
 
+**Raise `dsh-tool-web`'s provider-neutral timeout.** Rejected because custom providers and deployments own different latency expectations; the shipped DeepSeek composition owns this deployment budget.
+
 **Enable search and fetch together.** Rejected because default `web_fetch` would allow model-selected anonymous outbound HTTP(S) retrieval to arbitrary URLs. Search covers discovery; deployments that accept broader retrieval can opt into `dsh-web-fetch-local` and set `dsh-tool-web`'s `fetch` option to `true` in their overlay.
 
 ## Consequences
 
-Native model requests on every shipped surface carry only the `web_search` schema and search-only prompt guidance; Web/headless Code Mode exposes the same search capability beneath `run_code`. The prompt tells the model to use returned snippets and never advertises the disabled `web_fetch` tool. Search adds a complete auxiliary model call and may use the native server tool multiple times; its exact secret-free request remains reconstructable from the initiating session log. The default offers search-result snippets and source metadata but no arbitrary page retrieval; deployments that need full-page fetch must opt in. The Web snapshot lane boots the shipped tree, drives a replayed `web_search` call through the real DeepSeek provider against a local Messages fixture, asserts the durable auxiliary request and structured result, and pins the settled browser presentation. The TUI/Web composition smokes pin the shared `web_search` roster and absence of `web_fetch`; provider tests pin missing, stored, and rotated credential behavior plus literal and ambient compatibility.
+Native model requests on every shipped surface carry only the `web_search` schema and search-only prompt guidance; Web/headless Code Mode exposes the same search capability beneath `run_code`. The prompt tells the model to use returned snippets and never advertises the disabled `web_fetch` tool. Search adds a complete auxiliary model call and may use the native server tool multiple times; its exact secret-free request remains reconstructable from the initiating session log. The default offers search-result snippets and source metadata but no arbitrary page retrieval; deployments that need full-page fetch must opt in. The Web snapshot lane boots the shipped tree, drives a replayed `web_search` call through the real DeepSeek provider against a local Messages fixture, asserts the durable auxiliary request and structured result, and pins the settled browser presentation. The TUI/Web composition smokes pin the shared `web_search` roster and absence of `web_fetch`; the built composition dump pins the one-minute shipped search budget; provider tests pin missing, stored, and rotated credential behavior plus literal and ambient compatibility.

.agents/notes/implemented/feature/2026-07-31-web-default-search.zh.md

@@ -10,7 +10,7 @@ Status: implemented
 
 ## 决策
 
-`apps/cli/config/base.cordis.yml` 明确挂载 `dsh-web`，配置 `searchProvider: deepseek-official`，同时挂载 `dsh-web-search-deepseek`，并以 `fetch: false` 挂载 `dsh-tool-web`。它不挂载 `dsh-web-fetch-local`，也不选择抓取提供方。共享 base 只将 `web_search` 设为 TUI、浏览器与无头会话的默认工具。显式搜索提供方 id 使选择不受注册顺序影响，同时个人覆盖层或 `--config` 覆盖层仍可替换或禁用这些配置项。
+`apps/cli/config/base.cordis.yml` 明确挂载 `dsh-web`，配置 `searchProvider: deepseek-official`，同时挂载 `dsh-web-search-deepseek`，并以 `fetch: false` 和 `searchTimeoutMs: 60000` 挂载 `dsh-tool-web`。它不挂载 `dsh-web-fetch-local`，也不选择抓取提供方。共享 base 只将 `web_search` 设为 TUI、浏览器与无头会话的默认工具。显式搜索提供方 id 使选择不受注册顺序影响，同时个人覆盖层或 `--config` 覆盖层仍可替换或禁用这些配置项。已交付的一分钟预算用于覆盖一次辅助 DeepSeek Messages 请求及服务端检索，同时保持 `dsh-tool-web` 提供方无关的 30 秒默认值不变，以供自定义组合使用。
 
 DeepSeek 搜索使用与官方会话适配器相同的 `DEEPSEEK_API_KEY` 凭据引用。提供方在每次搜索内部通过可选的 `ctx.credentials` 服务解析该引用；只有未挂载该 seam 的组合才会回退到启动进程的环境变量，非空的 `apiKey` 字面值仍作为程序化配置的最后兜底。因此，由 Web 的 Models 页存储或轮换的密钥无需重启即可用于下一次搜索，提供方也无需保留该值。由于 `WebSearchProvider.available()` 是同步方法，它会将已安装解析器视为本地可用；若动态凭据缺失，操作会以提供方专属错误码 `WEB_PROVIDER_CREDENTIAL_MISSING` 失败，而稳定的工具 schema 仍保持注册。
 
@@ -28,8 +28,10 @@ DeepSeek 搜索使用与官方会话适配器相同的 `DEEPSEEK_API_KEY` 凭据
 
 **将 Web 工具保留在 `web.cordis.yml` 中。** 不予采纳：这会保留 TUI 与 Web／无头界面之间无法解释的工具清单差异。这些配置行并非界面特有，因此其唯一归属是 `base.cordis.yml`；[工具清单决策](2026-07-31-even-out-shipped-tool-rosters.md)记录了这一共享组合。
 
+**提高 `dsh-tool-web` 的提供方无关超时。** 不予采纳：自定义提供方和部署有各自不同的延迟预期；这一部署预算应归已交付的 DeepSeek 组合所有。
+
 **同时启用搜索和抓取。** 不予采纳：默认启用 `web_fetch` 会允许模型自行选择任意 URL，执行匿名出站 HTTP(S) 抓取。搜索负责发现信息；接受更广泛抓取范围的部署可以在覆盖层中选择启用 `dsh-web-fetch-local`，并将 `dsh-tool-web` 的 `fetch` 选项设为 `true`。
 
 ## 后果
 
-每个已交付界面的原生模型请求都只会携带 `web_search` schema，以及仅用于搜索的提示词指引；Web／无头 Code Mode 通过 `run_code` 公开相同的搜索能力。该提示词要求模型使用返回的 snippet，且绝不会向模型提及已禁用的 `web_fetch` 工具。搜索会增加一次完整的辅助模型调用，并可能多次使用原生服务器工具；发起会话的日志仍可精确重建其不含密钥的请求。默认配置会提供搜索结果 snippet 与来源元数据，但不支持任意页面抓取；需要抓取完整页面的部署必须自行选择启用抓取。Web 快照通道会启动已交付配置树，使用本地 Messages fixture（测试前置数据），经由真实 DeepSeek 提供方驱动一次回放的 `web_search` 调用，断言持久化的辅助请求与结构化结果，并固定最终浏览器呈现。TUI/Web 组合冒烟测试固定了共享的 `web_search` 清单及不提供 `web_fetch` 这一事实；提供方测试固定缺失、已存储及已轮换凭据的行为，以及字面值与环境变量的兼容性。
+每个已交付界面的原生模型请求都只会携带 `web_search` schema，以及仅用于搜索的提示词指引；Web／无头 Code Mode 通过 `run_code` 公开相同的搜索能力。该提示词要求模型使用返回的 snippet，且绝不会向模型提及已禁用的 `web_fetch` 工具。搜索会增加一次完整的辅助模型调用，并可能多次使用原生服务器工具；发起会话的日志仍可精确重建其不含密钥的请求。默认配置会提供搜索结果 snippet 与来源元数据，但不支持任意页面抓取；需要抓取完整页面的部署必须自行选择启用抓取。Web 快照通道会启动已交付配置树，使用本地 Messages fixture（测试前置数据），经由真实 DeepSeek 提供方驱动一次回放的 `web_search` 调用，断言持久化的辅助请求与结构化结果，并固定最终浏览器呈现。TUI/Web 组合冒烟测试固定了共享的 `web_search` 清单及不提供 `web_fetch` 这一事实；构建后组合配置的转储固定了已交付的一分钟搜索预算；提供方测试固定缺失、已存储及已轮换凭据的行为，以及字面值与环境变量的兼容性。

.agents/notes/implemented/feature/2026-08-02-web-thinking-tail-scroll.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-02-web-thinking-tail-scroll.md
+2026-08-02-web-thinking-tail-scroll.md: c45840731153627b4ce460ee140257ba33d2c007
+2026-08-02-web-thinking-tail-scroll.zh.md: b8d0444d62294e123bec1d26cb4c07538bbf966f

.agents/notes/implemented/feature/2026-08-02-web-thinking-tail-scroll.md

@@ -0,0 +1,31 @@
+# Agent Note: Web thinking tail scroll — collapsed reasoning follows live output
+
+Status: implemented
+
+English | [中文](2026-08-02-web-thinking-tail-scroll.zh.md)
+
+## Problem
+
+The Web Think row rendered the first reasoning line as its collapsed summary for both settled and streaming blocks. Once that first line existed, every later reasoning delta changed hidden body text only. A fast model therefore looked stationary while it was thinking, and the user had to expand the full chain of thought to verify that output was still moving. The product backlog already called for “thinking: scrolling chain-of-thought updates, expandable”; the current row satisfied only the second half.
+
+## Decision
+
+Only a collapsed Think row whose reasoning block is the active streaming tail follows live output. Its summary is the latest non-blank line instead of the settled first line, and the existing single-line summary element becomes a programmatic horizontal scrollport pinned to `scrollWidth - clientWidth` after each text update. Direct `scrollLeft` assignment deliberately follows real deltas without inventing an independent marquee speed: fast tokens move fast, a paused model stops, and short text stays still because the scroll range is zero.
+
+The behavior is owned by the existing presentation components. `AssistantMarkdown` chooses the latest line only while the Think row is running; `ToolRow` already owns collapsed/open state and therefore owns whether its summary should follow the inline end. No session, wire, durable event, or model-visible contract changes. Expanding removes the collapsed summary and renders the complete reasoning body in ordinary page flow. When the row settles, it restores the stable first line and resets the summary to the left edge. Other tool summaries and settled Think rows retain their existing ellipsis behavior.
+
+## Alternatives considered
+
+**Animate a CSS marquee independent of streaming.** Rejected: it would keep moving through provider stalls and make a slow model look fast, which breaks the throughput signal the interaction exists to expose.
+
+**Always show a fixed suffix of the complete reasoning string.** Rejected: character slicing can cut a word or grapheme, discards the current line’s beginning before overflow actually requires it, and jumps rather than moving with each delta.
+
+**Auto-scroll the expanded reasoning body or the conversation page.** Rejected: expanded content is a reading surface. Forcing it to follow would fight a user who scrolls back; the follower belongs only to the collapsed one-line summary.
+
+## Consequences
+
+The collapsed row now communicates provider cadence through content motion as well as the existing sweep, while the settled transcript remains byte-for-byte stable. The scroll update runs only on React renders the streaming accumulator already causes; it adds no timer, animation loop, subscription, durable state, or transport traffic. A long current reasoning line retains its full DOM text and programmatically clips the already-overflowing prefix, so expansion still reveals the complete block and assistive technology reads the same current summary text.
+
+## Testing
+
+`packages/client/ui-conversation/tests/chat-tool-row.spec.tsx` pins the latest-line selection, the calculated right-edge scroll position, and the settlement reset to the first line and `scrollLeft = 0`. The keyless assembled Chromium scenario in `apps/web/tests/lifecycle-chrome.e2e.ts` replays real recorded reasoning chunks at observable pacing, narrows the viewport until the summary overflows, and asserts that the live collapsed Think row reaches its actual browser scroll extent. Its settled replay golden remains unchanged, proving the historical summary contract stays stable.

.agents/notes/implemented/feature/2026-08-02-web-thinking-tail-scroll.zh.md

@@ -0,0 +1,31 @@
+# Agent Note：Web 思考尾部滚动 —— 折叠态 reasoning 跟随实时输出
+
+Status: implemented
+
+[English](2026-08-02-web-thinking-tail-scroll.md) | 中文
+
+## 问题
+
+Web Think 行在结算与流式 block 中都把 reasoning 首行渲染成折叠摘要。首行一旦出现，之后每个 reasoning delta 只会改变隐藏的正文。于是快速模型在思考时看起来静止，用户必须展开完整思维链才能确认输出仍在推进。产品事项表已经要求“thinking：滚动展示思维链更新、可展开”；当前行只满足了后半项。
+
+## 决策
+
+只有 reasoning block 是当前流式尾部、且仍处于折叠态的 Think 行会跟随实时输出。其摘要使用最新的非空行，而不是结算后的首行；已有单行摘要元素成为程序化横向滚动区，每次文本更新后钉到 `scrollWidth - clientWidth`。这里刻意直接赋值 `scrollLeft`，通过真实 delta 推进而不虚构独立的跑马灯速度：token 快则移动快，模型停顿则停止，短文本因滚动范围为零而保持静止。
+
+该行为由已有呈现组件拥有。`AssistantMarkdown` 只在 Think 行运行时选择最新行；`ToolRow` 已经拥有折叠／展开状态，因此由它决定摘要是否追随行内末端。不改变 session、wire、持久事件或模型可见契约。展开会移除折叠摘要，并让完整 reasoning 正文进入普通页面流。该行结算后恢复稳定首行，同时把摘要重置到左端。其他工具摘要与已结算 Think 行保留已有省略号行为。
+
+## 曾考虑的替代方案
+
+**播放与流式输出无关的 CSS 跑马灯。** 否决：它会在 provider 停顿时继续移动，让慢模型显得很快，破坏该交互本应暴露的吞吐信号。
+
+**始终显示完整 reasoning 字符串的固定后缀。** 否决：按字符切片可能截断单词或字素，在内容真正溢出前就丢掉当前行的开头，而且只会跳变，无法随每个 delta 移动。
+
+**自动滚动展开的 reasoning 正文或会话页面。** 否决：展开内容是阅读界面，强制跟随会与向上回看的用户争夺滚动；跟随器只属于折叠的单行摘要。
+
+## 后果
+
+折叠行现在会同时通过内容移动和已有扫光传达 provider 节奏，而结算后的 transcript 保持逐字节稳定。滚动更新只发生在流式累加器本就会触发的 React 渲染中；不会增加计时器、动画循环、订阅、持久状态或传输流量。较长的当前 reasoning 行仍会把完整文本留在 DOM 中，只以编程方式裁掉已经溢出的前缀，因此展开仍能显示完整 block，辅助技术读到的也仍是同一份当前摘要文本。
+
+## 测试
+
+`packages/client/ui-conversation/tests/chat-tool-row.spec.tsx` 固定最新行选择、算出的右端滚动位置，以及结算后恢复首行和 `scrollLeft = 0`。`apps/web/tests/lifecycle-chrome.e2e.ts` 中的 keyless 完整 Chromium 场景以可观察节奏回放真实录制的 reasoning chunks，把视口收窄到摘要溢出，并断言实时折叠 Think 行到达真实浏览器的滚动边界。其结算态 replay golden 保持不变，证明历史摘要契约仍然稳定。