Merge branch 'master' into worktree/persistent-bash-str-replace-editor

2026-07-30 15:19:27 +08:00
parent 4f17303265 007659b78f
commit 2550882875
1158 changed files with 47137 additions and 8419 deletions
@@ -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
+#   pnpm run verify-translation-pairing --write .agents/notes/README.md
 README.md: 3cfbb5154713046846a3bfcb2ccea62c0e4cb6c0
-README.zh.md: ddecac79519219c4a76cf9ba19edea312eea9d0d
+README.zh.md: a3369a94c6761e27567b1408d98a81665443f2ef
@@ -11,7 +11,7 @@
 - **生命周期**（顶层文件夹）是 Agent Note 的状态，Agent Note 随状态变化在文件夹之间移动：
  - **`proposed/`**：实施前评审的提案；尚未构建（或仅部分构建）。
  - **`implemented/`**：决策已交付。文件记录做了什么决定、否决了什么，并**与实际交付的内容保持同步**：当代码后续移动文件、重命名包（package）或更改键名/默认值时，Agent Note 在同一个变更中同步更新（仅限事实——路径、名称、结构——而非决策本身）。见 [implemented/AGENTS.md](implemented/AGENTS.md)。
-  - **`rejected/`**：提案经过讨论后被否决。仅当其决策依据仍能避免一种诱人且影响重大的错误时保留；否则删除完整的三个配对文件。
+  - **`rejected/`**：提案经过讨论后被否决。仅当其决策依据仍能避免一种诱人且影响重大的错误时保留；否则删除完整的英文、中文和伴随记录三文件组。
 - **类别**（嵌套文件夹）是决策的*种类*——见下方[分类](#classification)。

 文件名中的日期是该主题**首次提出**的时间（以 git 历史为准）。Agent Note 之间的交叉引用使用相对 Markdown 链接（`[topic](../../implemented/architecture/2026-…-….md)`），从不使用纯文字或编号，这样既可机械检查，也能在文件夹间移动时保持有效。
@@ -28,7 +28,7 @@
 |---|---|
 | `feature` | 面向用户或模型的新功能。 |
 | `bug-fix` | 修正缺陷或弥补事故复盘（postmortem）发现的缺口。 |
-| `simplification` | 在不增加功能的前提下移除代码、行为或对外表面积。 |
+| `simplification` | 在不增加功能的前提下移除代码、行为或对外范围。 |
 | `architecture` | 关于**交付源码**的结构性决策：包之间的关系、运行时词汇。 |
 | `process` | 代码**周边**的工具、策略或工作流——门禁、包管理器、vendor 化——不涉及运行时行为。 |
 | `testing` | 测试基础设施与策略。 |
@@ -39,13 +39,13 @@

 当一份 implemented Agent Note 记录的交付决策已经完整落地，且其决策依据不太可能再指导未来工作时，将其归档。如果其中的备选方案、归属边界、否定性保证、持久化语义或协议语义、安全规则，或者重新引入条件仍有价值，则继续作为活跃记录保留。绝不归档 proposed Agent Note：过时的提案应转为 rejected。仅当 rejected Agent Note 仍能避免一种可能发生的错误时保留；否则一并删除其英文、中文和伴随记录文件。请使用经过校准的 [`dsh-archive-agent-notes`](../skills/dsh-archive-agent-notes/SKILL.md) 工作流，不要根据字数、存续时间或目标配额来判断。

-归档路径编码为 `archived/{class}/yyyy-mm-dd-topic-title.md`；其中有意省略 `implemented`，因为只有 implemented Agent Note 可以进入归档。归档变更会移动完整的英文、中文和伴随记录三个文件，保留 `Status: implemented`，在两种语言的文件中紧接该状态行插入相同的 `Archived: YYYY-MM-DD` 行，重新记录伴随文件，并修复或删除入站链接。归档时只允许对内容做这些更改。
+归档路径编码为 `archived/{class}/yyyy-mm-dd-topic-title.md`；其中有意省略 `implemented`，因为只有 implemented Agent Note 可以进入归档。归档变更会移动完整的英文、中文和伴随记录三个文件，保留 `Status: implemented`，在两种语言的文件中紧接该状态行插入相同的 `Archived: YYYY-MM-DD` 行，重新记录伴随记录，并修复或删除入站链接。归档时只允许对内容做这些更改。

 封存后，每组归档文件都永久冻结。禁止编辑、翻译、重新格式化、更新、移动或删除，也不得将其视为当前行为的权威依据。文档门禁会跳过归档源文件，包括其中的出站链接；当活跃文档有意引用历史时，仍可链接到归档 Agent Note。[`verify-archived-agent-notes`](../../scripts/verify-archived-agent-notes.ts) 强制执行封闭的类别目录树、完整的三文件配对、归档元数据、伴随记录 hash，以及仅追加的冻结内容 manifest。[归档政策 Agent Note](implemented/process/2026-07-26-frozen-agent-note-archive.md) 记录了设计依据。

 ## 何时需要写一份

-每个非平凡变更都必须在同一 PR（Pull Request）中新增或更新至少一份 Agent Note。如果变更修改了行为、架构、跨文件或跨包契约、流程或工具、测试策略、磁盘、协议或配置格式，或者其他维护者可能合理重新审视的决策，就属于非平凡变更。对未来重大工作的提案从 `proposed/` 开始；已经做出的决策从 `implemented/` 开始。选择与决策匹配的类别文件夹（见[分类](#classification)）。
+每个非平凡变更都必须在同一 PR（Pull Request）中新增或更新至少一份 Agent Note。如果变更修改了行为、架构、跨文件或跨包契约、流程或工具、测试策略、磁盘存储格式、协议格式（wire format）或配置格式，或者其他维护者可能合理重新审视的决策，就属于非平凡变更。对未来重大工作的提案从 `proposed/` 开始；已经做出的决策从 `implemented/` 开始。选择与决策匹配的类别文件夹（见[分类](#classification)）。

 更新已经拥有该决策的 Agent Note 即可满足规则；不要创建重复记录。只有不涉及行为、契约、结构、流程或理由变化的纯机械性或局部编辑才可豁免。Agent Note 永远不会被编辑为一个*不同的决策*：用新 Agent Note 取代旧记录，并让两个记录保持互相链接，除非后续依据下方规则完全合并旧记录。编辑 `implemented/` Agent Note 以跟踪其现有决策的所在位置是必需的，而非禁止的；见 [implemented/AGENTS.md](implemented/AGENTS.md)。

@@ -112,7 +112,7 @@ Status: <status>

 ### 曾考虑的替代方案——必需

-每份 Agent Note 都必须包含 `## Alternatives considered` 章节：每个真实的替代方案及其落选原因，每个替代方案用一个加粗引导的段落，或对争议较大的替代方案用 `### Why not <X>?` 子节。记录决策时不记录它击败了什么，就是在邀请反复争论——正是这些 Agent Note 存在的意义所要防止的。
+每份 Agent Note 都必须包含 `## Alternatives considered` 章节：每个真实的替代方案及其落选原因，每个替代方案用一个加粗引导的段落，或对争议较大的替代方案用 `### Why not <X>?` 子节。记录决策时不记录它击败了什么，就是在邀请反复争论——这正是 Agent Note 旨在防止的问题。

 替代方案是记录下来的，不是凭空编造的。日期早于 2026-07-05 且替代方案无法从记录中重建的 Agent Note，在该章节位置放置以下精确注释，门禁仅对格式规范之前的文件接受此注释：

@@ -122,8 +122,8 @@ Status: <status>

 ### 在生命周期之间移动

-将文件在生命周期文件夹之间移动意味着在同一个变更中更新 `Status:` 行并满足目标文件夹的骨架要求——否则门禁会失败。具体而言，`proposed/` → `implemented/` 将 `## Proposal` 改写为现在时态的 `## Decision`，将 `## Acceptance criteria` 和 `## Risks` 折入 `## Consequences`（或折入一个现在时态的 `## Testing`/`## Verification` 章节，用于描述现在锁定该行为的内容），并用实际交付的内容替换计划——即 [implemented/AGENTS.md](implemented/AGENTS.md) 所要求的改写，使之机械化。`proposed/` → `rejected/` 仅在 `Status:` 行添加原因并冻结文件。
+将文件在生命周期文件夹之间移动意味着在同一个变更中更新 `Status:` 行并满足目标文件夹的骨架要求——否则门禁会失败。具体而言，`proposed/` → `implemented/` 将 `## Proposal` 改写为现在时态的 `## Decision`，将 `## Acceptance criteria` 和 `## Risks` 折入 `## Consequences`（或折入一个现在时态的 `## Testing`/`## Verification` 章节，用于描述现在锁定该行为的内容），并用实际交付的内容替换计划——也就是将 [implemented/AGENTS.md](implemented/AGENTS.md) 所要求的改写变成可机械检查的规则。`proposed/` → `rejected/` 仅在 `Status:` 行添加原因并冻结文件。

 ### 中文对侧文件

-`.zh.md` 对侧文件按 [i18n 契约](../../docs/i18n/README.md)逐章节镜像其英文兄弟文件的结构；机器检查的头部标记（`# Agent Note: ` 和 `Status:` 行）保持英文原样不翻译。格式门禁跳过 `.zh.md` 文件——配对门禁负责它们的一致性。
+`.zh.md` 对侧文件按 [i18n 契约](../../docs/i18n/README.md)逐章节镜像其英文对侧文件的结构；机器检查的头部标记（`# Agent Note: ` 和 `Status:` 行）保持英文原样不翻译。格式门禁跳过 `.zh.md` 文件——配对门禁负责它们的一致性。
@@ -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-gui-layering-and-rpc-protocol.md: 63db4786adcc007d09b7a58824a59f4d1e1e8be1
-2026-07-19-gui-layering-and-rpc-protocol.zh.md: b3037ceb8c172925581d2862ea675e53a7f8c54e
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md
+2026-07-19-gui-layering-and-rpc-protocol.md: b9718da4725316c64686adef24827e2984d8723d
+2026-07-19-gui-layering-and-rpc-protocol.zh.md: 2add148054e8f97c65600cd719fb4f8e0283f52d
@@ -165,7 +165,7 @@ One example row (the table structure is the reading key):
 |---|---|---|---|
 | `session.list` | `{ cursor?: string }` (cursor is a reserved seat, unimplemented) | `{ items: SessionSummary[] }` | persisted sessions, updatedAt descending; v1 builds no index |

-The remaining methods (`session.create`/`session.history`/`session.prompt`/`session.cancel`/`host.describe`) are not re-copied here — signatures are the source of truth; see `api/sessions.ts`, `api/host.ts`, and `RpcMethodMap`.
+The remaining methods (`session.create`/`session.history`/`session.rename`/`session.prompt`/`session.cancel`/`host.describe`) are not re-copied here — signatures are the source of truth; see `api/sessions.ts`, `api/host.ts`, and `RpcMethodMap`.

 ### Frames (server→client, named unions)

@@ -187,7 +187,7 @@ The remaining frame types are not re-copied here; the full unions are `MuxFrame`
 - **Cold sessions resume implicitly**: when `history`/`prompt` hits an unattached session the impl auto-resumes, deduplicating concurrent triggers with an in-flight table; attachment status is not exposed to clients (`running` already covers it).
 - **Approvals/questions**: the requested frame mints a stable rpcId on acceptance; first answer wins, and the host's in-memory pending table (keyed by rpcId) is the only referee; after a mux reopen, still-pending requested frames replay after the subscribed frame (rpcId reused verbatim — refresh recovery). The audit events `approval/asked`/`decided` continue through the durable log — frames = the live control plane, events = the durable audit. **Status**: the contract and frame types are shipped; the host-side pending table/wire answerer is unimplemented (`respond` in `api-proxy.ts` is a stub, always `not-pending`); PendingCard v1 is display-only.
 - **No protocol version**: client and host release bound together; `host.describe` has no protocolVersion field; introduce one when an independently released client appears.
- **Reserved-seam discipline**: the map holds only implemented methods; an unknown method fails loud at envelope parse (`bad-request`) — no not-implemented fallback code. The reservation list (implementing = copy the signature into the domain interface + add the map row + add the schema pair): `session.fork`, `prompt.mode` gaining `'inject'`, `task.list`, `host.listModels`, describe gaining `hostInstanceId`.
+- **Reserved-seam discipline**: the map holds only implemented methods; an unknown method fails loud at envelope parse (`bad-request`) — no not-implemented fallback code. The reservation list (implementing = copy the signature into the domain interface + add the map row + add the schema pair): `session.fork`, `prompt.mode` gaining `'inject'`, `task.list`, `host.listModels`, describe gaining `hostInstanceId`. (`session.rename` graduated from this list: it appends a user-source `session/title` event.)

 ## The client carrier: the AbstractApiClient class family (`fetch/client.ts`)

@@ -163,7 +163,7 @@ export type ResponseValue<K> =
 |---|---|---|---|
 | `session.list` | `{ cursor?: string }`（cursor 留座不实现） | `{ items: SessionSummary[] }` | 已持久化 session，updatedAt 倒序；v1 不建索引 |

-其余方法（`session.create`/`session.history`/`session.prompt`/`session.cancel`/`host.describe`）的参数与返回不在此复写——签名即事实源，见 `api/sessions.ts`、`api/host.ts` 与 `RpcMethodMap`。
+其余方法（`session.create`/`session.history`/`session.rename`/`session.prompt`/`session.cancel`/`host.describe`）的参数与返回不在此复写——签名即事实源，见 `api/sessions.ts`、`api/host.ts` 与 `RpcMethodMap`。

 ### 帧（server→client，具名 union）

@@ -185,7 +185,7 @@ export type ResponseValue<K> =
 - **冷 session 隐式 resume**：`history`/`prompt` 命中未 attach 的 session 时 impl 自动 resume，并发触发用在途表去重；attach 与否不对客暴露（`running` 已覆盖）。
 - **审批/问答**：requested 帧受理时 mint 稳定 rpcId；先到先赢，host 内存 pending 表（keyed by rpcId）是唯一裁判；mux 重开后在 subscribed 帧后重放仍 pending 的 requested 帧（rpcId 原样复用，刷新恢复）。审计事件 `approval/asked`/`decided` 照旧走 durable 日志——帧=live 控制面，事件=durable 审计。**现状**：契约与帧类型已 shipped，host 侧 pending 表/wire answerer 未实现（`api-proxy.ts` 的 `respond` 是 stub，恒回 `not-pending`）；PendingCard v1 只展示。
 - **不设协议版本**：client 与 host 绑定发布，`host.describe` 无 protocolVersion 字段；出现独立发布的 client 时再引入。
- **预留接缝纪律**：map 只含已实现方法，未知 method 在信封 parse 即 fail loud（`bad-request`），不设 not-implemented 兜底码。预留清单（实现时把签名抄进域接口+map 加行+schema 加对即升格）：`session.fork`、`prompt.mode` 加 `'inject'`、`task.list`、`host.listModels`、describe 加 `hostInstanceId`。
+- **预留接缝纪律**：map 只含已实现方法，未知 method 在信封 parse 即 fail loud（`bad-request`），不设 not-implemented 兜底码。预留清单（实现时把签名抄进域接口+map 加行+schema 加对即升格）：`session.fork`、`prompt.mode` 加 `'inject'`、`task.list`、`host.listModels`、describe 加 `hostInstanceId`。（`session.rename` 已从本清单毕业：追加 user 来源的 `session/title` 事件。）

 ## 客户端载体：AbstractApiClient 类体系（`fetch/client.ts`）

@@ -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/2026-07-22-unified-send-and-coalesced-user-messages.md
-2026-07-22-unified-send-and-coalesced-user-messages.md: ed171735cf483938c70291963a6e68dc02d7bde2
-2026-07-22-unified-send-and-coalesced-user-messages.zh.md: 8b2a3ebabb493954e653255e876255b9c0810c19
+2026-07-22-unified-send-and-coalesced-user-messages.md: 4d0cbeff0c8a07362caa1ec18493267a9f0d2823
+2026-07-22-unified-send-and-coalesced-user-messages.zh.md: 935a1a78a6bed451c1db646dec2ec5f4f5e87949
@@ -22,7 +22,7 @@ Separately, `context/message` and `user/message` had converged: the surface proj

 **`send` does not return identity.** Callers already own the complete message and its opaque `MessageId`; creation and freezing are owned by the [identified immutable message decision](2026-07-28-identified-immutable-message-values.md), not by routing.

-**Three inbox events replace agent/queued.** `agent/inbox/enqueue` (an item entered a FIFO), `agent/inbox/dequeue` (the driver claimed one), and `agent/inbox/discard` (`cancel()` dropped pending items) carry the accepted `UserMessage`. Enqueue and dequeue also carry the resolved `queued | steering` placement captured at acceptance, so observers and reconnect mirrors retire repeated message identities from the correct FIFO without reconstructing routing from later status or session history. Injection never touches a FIFO and emits none of these. Every FIFO entry publishes an enqueue, including steering submitted by an `agent/turn-stopping` listener, so the ledger stays balanced with its later dequeue or discard. The `dsh-agent` invariant companion asserts FIFO conservation: a per-agent outstanding count that dequeue and discard can never drive negative.
+**Inbox lifecycle events carry occurrence identities.** `agent/inbox/enqueue` (an item entered a FIFO), `agent/inbox/update` (a pending queued item was edited), `agent/inbox/dequeue` (the driver claimed one), and `agent/inbox/discard` (pending items were dropped) carry an `InboxItem`: an occurrence-local `InboxItemId`, the accepted `UserMessage`, and the resolved `queued | steering` placement captured at acceptance. The occurrence identity lets observers and reconnect mirrors distinguish repeated sends of the same `MessageId` without reconstructing routing from later status or session history. Injection never touches a FIFO and emits none of these. Every FIFO entry publishes one enqueue and exactly one terminal dequeue or discard; updates are non-terminal. The `dsh-agent` invariant companion asserts this FIFO conservation.

 **Admission accepts next-step input without becoming a turn.** The loop opens a private next-step acceptance window before `agent/prompt-submit`, keeps it open through the turn, and closes it before `turn/end`. Steering and injection received during admission therefore remain together in the outbox and join an allowed turn. If admission blocks or fails, a context-only caller batch takes idle injection's immediate append, while steering and context staged beside it remain available to retry; neither path writes the rejected prompt. When a later prompt is admitted, retained outbox input enters its turn before that prompt, while input accepted during the current admission remains after the prompt. Closing the window before `turn/end` preserves the rule that reentrant late steering becomes an independent queued turn. `Agent.acceptsNextStep` exposes whether a `next-step` send would currently join this window; `status` remains the broader activity signal rather than a routing predicate.

@@ -43,7 +43,7 @@ Separately, `context/message` and `user/message` had converged: the surface proj

 The delivery surface is now one primitive plus three self-documenting presets, and the (`target` × `wakeup`) matrix makes previously-unreachable combinations explicit. One durable message type serves prompts, injected context, and goal rounds, so the surface projection and every "human prompt?" check simplify to a `source` test. The `Agent` contract remains an interface, so alternate implementations and object-literal test fakes implement the same minimal structural surface. The goal fold's channel split moved from event type to `source.round`, and every consumer that filtered `context/message` now filters `user/message` by source. An idle injection appends `user/message` between turns without opening a turn or running the model.

-`wakeup` is the "should the model run" signal, so the inbox distinguishes waking queued work from anything available to dequeue: a lone `next-turn`/no-wakeup item stays parked at idle and rides along the next waking send, and `whenIdle`/`cancel` settle quiescence off the waking signal. Every FIFO exit publishes exactly one lifecycle event, while domain-specific durable facts travel in typed message sources rather than a parallel metadata channel. The direct pending-item representation keeps public lifecycle events correlated without maintaining a second steering wrapper or allowing its durable data to diverge.
+`wakeup` is the "should the model run" signal, so the inbox distinguishes waking queued work from anything available to dequeue: a lone `next-turn`/no-wakeup item stays parked at idle and rides along the next waking send, and `whenIdle`/`cancel` settle quiescence off the waking signal. Every FIFO exit publishes exactly one lifecycle event, while domain-specific durable facts travel in typed message sources rather than a parallel metadata channel. The direct pending-item representation keeps public lifecycle events correlated without maintaining a second steering wrapper or allowing its durable data to diverge. The later [addressable queue operations](../feature/2026-07-29-addressable-queue-operations.md) decision adds live mutations over that occurrence identity without changing the one-message-per-turn or durable-message contracts.

 ## Related

@@ -22,7 +22,7 @@ agent 的对外驱动接口逐渐长出三个近乎平行的动词——`send`

 **`send` 不返回标识。** 调用方已经持有完整消息及其不透明的 `MessageId`；消息的创建与冻结由[带标识的不可变消息值决策](2026-07-28-identified-immutable-message-values.md)负责，而不是由路由负责。

-**三个 inbox 事件取代 agent/queued。** `agent/inbox/enqueue`（一个队列项进入某个 FIFO）、`agent/inbox/dequeue`（驱动器认领了一个）和 `agent/inbox/discard`（`cancel()` 丢弃了待处理项）都会携带已接受的 `UserMessage`。enqueue 和 dequeue 还会携带生产方在接受消息时捕获的已解析 `queued | steering` 放置方式，因此观察方和重连镜像可以从正确的 FIFO 中结算重复出现的消息标识，无需根据后续状态或会话历史重建路由。注入从不触及 FIFO，也不发出这些事件中的任何一个。每一次 FIFO 入队都会发布一个 enqueue 事件，包括 `agent/turn-stopping` 监听器提交的 steering，因此账目会与其后的 dequeue 或 discard 保持平衡。`dsh-agent` 的不变量配套断言 FIFO 守恒：一个按 agent 计的未结算计数，dequeue 和 discard 永远无法把它压到负数。
+**Inbox 生命周期事件携带单次入队标识。** `agent/inbox/enqueue`（一个队列项进入某个 FIFO）、`agent/inbox/update`（待处理的 queued 项被编辑）、`agent/inbox/dequeue`（驱动器认领一个项）和 `agent/inbox/discard`（待处理项被丢弃）都会携带一个 `InboxItem`：仅属于本次入队的 `InboxItemId`、已接受的 `UserMessage`，以及生产方在接受消息时捕获的已解析 `queued | steering` 放置方式。单次入队标识让观察方和重连镜像能够区分同一 `MessageId` 的多次发送，无需根据后续状态或会话历史重建路由。注入从不触及 FIFO，也不发出这些事件中的任何一个。每次 FIFO 入队都会发布一个 enqueue，并且恰好发布一个终态 dequeue 或 discard；update 不是终态。`dsh-agent` 的不变量配套断言这种 FIFO 守恒。

 **准入接受 next-step 输入，但不会因此成为一个轮次。** 循环会在 `agent/prompt-submit` 前打开一个私有的 next-step 接受窗口，使其贯穿整个轮次，并在 `turn/end` 前关闭。因此，在准入期间收到的 steering 和注入会一起留在 outbox 中并加入获准轮次。如果准入被阻止或失败，仅含调用方上下文的批次会采用空闲注入的立即追加行为，而 steering 及与其一同暂存的上下文仍可重试；两种路径都不会写入被拒绝的提示词。后续提示词获准时，保留在 outbox 中的输入会先于该提示词进入其轮次，而当前准入期间接受的输入则留在提示词之后。在 `turn/end` 前关闭窗口，可以保留这样的规则：可重入的晚到 steering 会成为一个独立的排队轮次。`Agent.acceptsNextStep` 会公开一次 `next-step` 发送当前是否会加入该窗口；`status` 仍是更宽泛的活动信号，而非路由判据。

@@ -43,7 +43,7 @@ agent 的对外驱动接口逐渐长出三个近乎平行的动词——`send`

 投递接口现在是一个原语加三个自解释的预设，(`target` × `wakeup`) 矩阵把此前无法表达的组合显式化。一种持久消息类型同时服务提示词、注入的上下文和 goal 轮次，因此对外接口的投影和每一处“是否人类提示词？”检查都简化为一次 `source` 判断。`Agent` 契约仍是接口，因此其他实现和对象字面量形式的测试替身只需实现同一个最小结构接口。goal 折叠的通道区分从事件类型改到了 `source.round`；此前过滤 `context/message` 的每个消费方现在改为按来源过滤 `user/message`。空闲状态下的注入会在两个轮次之间追加 `user/message`，既不打开轮次，也不运行模型。

-`wakeup` 是“模型是否应当运行”的信号，因此 inbox 会区分能唤醒的排队工作与任何可 dequeue 的项：一个孤立的 `next-turn`/no-wakeup 队列项会停泊在空闲状态，并随下一次唤醒 send 一同带出，而 `whenIdle`/`cancel` 依据唤醒信号来结算静默。每一次 FIFO 退出都恰好发布一个生命周期事件，特定于领域的持久事实则通过类型化消息 source 传递，而非通过平行的元数据通道。直接使用待处理项的表示方式，使公开生命周期事件保持可关联，既无需维护第二个 steering 包装层，也避免其持久数据发生分歧。
+`wakeup` 是“模型是否应当运行”的信号，因此 inbox 会区分能唤醒的排队工作与任何可 dequeue 的项：一个孤立的 `next-turn`/no-wakeup 队列项会停泊在空闲状态，并随下一次唤醒 send 一同带出，而 `whenIdle`/`cancel` 依据唤醒信号来结算完全停稳。每一次 FIFO 退出都恰好发布一个生命周期事件，特定于领域的持久事实则通过类型化消息 source 传递，而非通过平行的元数据通道。直接使用待处理项的表示方式，使公开生命周期事件保持可关联，既无需维护第二个 steering 包装层，也避免其持久数据发生分歧。后续的[可寻址队列操作](../feature/2026-07-29-addressable-queue-operations.md)决策在该单次入队标识上增加了实时变更，但不改变单消息单轮次或持久消息契约。

 ## 相关

@@ -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: 8cf3be7b3b7579d0c37898a58fb0ab4990fd71bf
-2026-07-25-web-input-machine-and-slash-pipeline.zh.md: b1488893558d8b2bf9c104faca968435d46a9640
+2026-07-25-web-input-machine-and-slash-pipeline.md: f446f42c9e202afcb404c7a551a4f715228bb8e5
+2026-07-25-web-input-machine-and-slash-pipeline.zh.md: 8f5e449bb878811b70bc5bc29e4a09bbc1a33bfa
@@ -62,8 +62,8 @@ 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, candidates, onPick, matchSpace?, matchEnter?}`; (trigger,name) unique, registration order = group order = polling order) and `sessionOf(sctx)`. Implementing a match hook IS the declaration of participation in space/enter adjudication; the pipeline polls in registration 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); 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 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.
 - 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
@@ -62,8 +62,8 @@ 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, candidates, onPick, matchSpace?, matchEnter?}`；(trigger,name) 唯一、注册序 = 组序 = 轮询序）与 `sessionOf(sctx)`。实现 match 钩子即参与空格/回车裁决的声明；管线按注册序轮询，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）；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。
+- 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。
 - 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
@@ -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
-2026-07-26-subprocess-consumer-migration.md: b31f69f1251a7219e168ed7800ba16ff7d6b328c
-2026-07-26-subprocess-consumer-migration.zh.md: 47e7519a72f5482f255d15d87b483e9295f6cd2c
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-26-subprocess-consumer-migration.md
+2026-07-26-subprocess-consumer-migration.md: 477dffc2271db08b8986b34645067b247ad7ace7
+2026-07-26-subprocess-consumer-migration.zh.md: 5e1035872c6e2101e41d2801cccdfb5ef2c088fc
@@ -6,7 +6,7 @@ English | [中文](2026-07-26-subprocess-consumer-migration.zh.md)

 ## Problem

-The [subprocess seam](2026-07-26-subprocess-seam.md) shipped shaped for exactly one consumer family: batch-collected stdout/stderr, batch stdin, a single escalating `kill()`. That was deliberate scope control, and its own note records "migrate the other spawn sites" as rejected-for-now. Review on the introducing PR reversed that deferral: the stacked follow-up should reshape the interface toward Node's API and move the remaining process-running places onto the service. The remaining spawners each carried a private copy of some slice of the same mechanics — lsp-local had its own detached-tree signalling (POSIX group + Windows taskkill + liveness polling), subagent-subprocess had the dispose ladder and its own scrub, mcp-client and pty-local and the SDK helper each had a third/fourth/fifth copy of the credential scrub — and none of it was swappable or centrally testable.
+The [subprocess seam](2026-07-26-subprocess-seam.md) shipped shaped for exactly one consumer family: batch-collected stdout/stderr, batch stdin, a single escalating `kill()`. That was deliberate scope control, and its own note records "migrate the other spawn sites" as rejected-for-now. Review on the introducing PR reversed that deferral: the stacked follow-up should reshape the interface toward Node's API and move the remaining process-running places onto the service. The remaining spawners each carried a private copy of some slice of the same mechanics — lsp-local had its own detached-tree signalling (POSIX group + Windows taskkill + liveness polling), subagent-subprocess had the dispose ladder and its own scrub, and mcp-client, pty-local, the SDK helper, and the TUI Git probe each carried another credential scrub — and none of it was swappable or centrally testable.

 ## Decision

@@ -15,7 +15,7 @@ The seam's vocabulary is now Node-shaped, and every spawner that can ride the se
 - **Per-stream stdio dispositions** on `SubprocessSpawnSpec`: `'pipe'` (the raw `Readable`/`Writable`, for consumer-owned protocol framing), `'inherit'` (diagnostics to the parent's stream), and collect mode `{ maxBytes, spill? }` — the original bounded tail-keep shape, with the spill file now optional so a diagnostic tail (a language server's stderr) buffers without touching disk. stdin is `'ignore'`, `'pipe'`, or `{ data }` (write-and-close batch).
 - **`SubprocessOutcome` carries exit facts only** (Node's close-event vocabulary); collected output stays readable through `handle.collected` after settlement (spill fds seal at the settle boundary), so batch and streaming callers share one access path and nothing is copied into the outcome.
 - **Tree-scoped termination behind one verb**: `terminate()` owns the SIGTERM→grace→SIGKILL escalation (serves the spec's abort signal too, and is a no-op once the tree is gone) — the handle exposes no single-signal `kill(signal?)`, so a consumer cannot skip the grace window; `waitForExit()` polls tree liveness (POSIX group probe; direct-child boundary on Windows); Windows tree termination (`taskkill /T`, injectable) moved in from lsp-local, so tree semantics are platform-correct for every consumer. (The stdin-EOF-first dispose ladder initially absorbed from `subagent-subprocess` later moved back out to its one consumer — see the [ladder-ownership Agent Note](2026-07-27-dispose-ladder-to-consumer.md).)
- **One scrub definition**: `scrubbedParentEnv()`/`SENSITIVE_ENV_PATTERN` live on the seam. Spawners that cannot route the spawn itself through the service — pty-local (node-pty owns the fork) and mcp-client (the MCP SDK owns the transport spawn) — import the function, so environment policy is single-sourced even where process ownership is not; the SDK helper's `scrubEnvironment()` defaults through it as well.
+- **One scrub definition**: `scrubbedParentEnv()`/`SENSITIVE_ENV_PATTERN` live on the seam, and credential-shaped names contain `KEY`, `PASSWORD`, `SECRET`, or `TOKEN`, case-insensitively. Spawners that cannot route the spawn itself through the service — pty-local (node-pty owns the fork), mcp-client (the MCP SDK owns the transport spawn), and the TUI's synchronous Git branch probe — import the function, so environment policy is single-sourced even where process ownership is not. The SDK helper's `scrubEnvironment()` defaults through the function and applies the exported pattern when its caller supplies an explicit environment; the pattern remains public for this production consumer.

 Migrations landed with the reshape: **bash-local/bash-sandbox** (collect modes + batch stdin; the bash `kill()` maps to `terminate()` so `task_kill` keeps escalation semantics), **lsp-local** (piped protocol streams + a no-spill collected stderr tail; `LspConnection` takes the seam's spawn function; its private tree-op helpers deleted), **subagent-acp** (piped ndjson streams + inherited stderr; spawn failure surfaces through `done` rejection into the same startup race; disposal is the backend-owned `disposeAcpChild` ladder over the seam's verbs, with the plugin's configured graces). **`dsh-subagent-subprocess` is deleted** — the dispose ladder and scrub are the seam's; the unused isolated-config-dir helper died with it (no consumer existed).

@@ -23,16 +23,16 @@ Compositions mounting lsp-local or subagent-acp now load `dsh-subprocess-local`

 ## Alternatives considered

-**Keep the batch-only seam and let stream consumers stay bespoke.** The introducing note's position, rejected by review: it leaves three private copies of tree signalling and five of the scrub, and any future runner (containerized executor, remote process host) would have to pick which private copy to fork. The Node-shaped dispositions cover all three observed stream shapes without widening the outcome type or buffering piped streams.
+**Keep the batch-only seam and let stream consumers stay bespoke.** The introducing note's position, rejected by review: it leaves three private copies of tree signalling and six of the scrub, and any future runner (containerized executor, remote process host) would have to pick which private copy to fork. The Node-shaped dispositions cover all three observed stream shapes without widening the outcome type or buffering piped streams.

 **A single `stdio: 'pipe' | 'inherit' | 'collect'` mode for all three streams at once.** Rejected: real consumers mix modes per stream (lsp: pipe/pipe/collect; acp: pipe/pipe/inherit; bash: data/collect/collect). Per-stream dispositions are exactly Node's shape and avoid a second spawn call for the mixed cases.

 **Migrate pty-local and mcp-client spawns too.** Rejected on ownership grounds, not scope: node-pty's `fork()` allocates the terminal itself, and the MCP SDK's `StdioClientTransport` spawns internally — neither call site is ours to route. They adopt the shared scrub (the part that is policy), and their READMEs say why the spawn stays put.

-**Migrate the test-support launchers (acp-snapshot, loader-smoke) and the SDK package-manager runner.** Rejected: the support packages are deliberately dependency-light test infrastructure that must not depend on product seams, and the SDK wizard's `stdio: 'inherit'`-with-redirect semantics plus its out-of-composition lifecycle (no cordis context at all) make the service a poor fit; it shares the scrub instead.
+**Migrate the test-support launchers (acp-snapshot, loader-smoke), the SDK package-manager runner, and the TUI Git probe.** Rejected: the support packages are deliberately dependency-light test infrastructure that must not depend on product seams; the SDK wizard's `stdio: 'inherit'`-with-redirect semantics plus its out-of-composition lifecycle (no cordis context at all) make the service a poor fit; and the TUI probe is synchronous. The production callers share the scrub instead.

 ## Consequences

 Bought: one implementation of tree signalling, escalation, bounded collection, and the scrub, tested once in `dsh-subprocess-local`'s suites (including injected-platform Windows coverage that lsp-local's private copy never had); lsp-local and subagent-acp shed their process plumbing and their children now survive plugin reloads and die with composition teardown like bash's; a whole package (`dsh-subagent-subprocess`) is gone. The seam README's "one consumer family" limitation is retired.

-Cost: the seam is wider — three stdio modes and the terminate/waitForExit/dispose lifecycle surface instead of one mode and one verb — so a future backend implements more surface; the compositions for lsp-local/subagent-acp each carry the subprocess row now; and `SubprocessOutcome` no longer carries output, a breaking shape change inside the still-unreleased stack (the PR2 layer was updated in place rather than shimmed, per the pre-release stance). pty-local/mcp-client/SDK/test-support spawns remain outside the service by ownership, with the scrub as the shared floor.
+Cost: the seam is wider — three stdio modes and the terminate/waitForExit/dispose lifecycle surface instead of one mode and one verb — so a future backend implements more surface; the compositions for lsp-local/subagent-acp each carry the subprocess row now; and `SubprocessOutcome` no longer carries output, a breaking shape change inside the still-unreleased stack (the PR2 layer was updated in place rather than shimmed, per the pre-release stance). pty-local/mcp-client/SDK/TUI/test-support spawns remain outside the service by ownership or execution shape, with the scrub as the shared floor and its pattern intentionally exported for explicit-environment consumers.
@@ -6,7 +6,7 @@ Status: implemented

 ## 问题

-[进程 seam](2026-07-26-subprocess-seam.md) 交付时恰好只为一个消费方家族塑形：批量收集的 stdout/stderr、批量 stdin、单一的升级式 `kill()`。那是有意的范围控制，其自身的 Agent Note 也把「迁移其余 spawn 调用点」记为暂缓否决项。引入该 seam 的 PR（Pull Request）上的评审推翻了这一暂缓决定：堆叠其上的后续变更应当把接口向 Node 的 API 方向重塑，并把其余运行进程之处迁到该服务上。其余各 spawn 调用点此前各自持有同一套机制中某个切片的私有副本——lsp-local 自带 detached 进程树信号发送（POSIX 进程组 + Windows taskkill + 存活轮询），subagent-subprocess 自带 dispose（资源释放）阶梯和自己的凭据清除，mcp-client、pty-local 与 SDK helper 则各自持有凭据清除的第三、第四、第五份副本——而这一切既不可替换，也无法集中测试。
+[进程 seam](2026-07-26-subprocess-seam.md) 交付时恰好只为一个消费方家族塑形：批量收集的 stdout/stderr、批量 stdin、单一的升级式 `kill()`。那是有意的范围控制，其自身的 Agent Note 也把「迁移其余 spawn 调用点」记为暂缓否决项。引入该 seam 的 PR（Pull Request）上的评审推翻了这一暂缓决定：堆叠其上的后续变更应当把接口向 Node 的 API 方向重塑，并把其余运行进程之处迁到该服务上。其余各 spawn 调用点此前各自持有同一套机制中某个切片的私有副本——lsp-local 自带 detached 进程树信号发送（POSIX 进程组 + Windows taskkill + 存活轮询），subagent-subprocess 自带 dispose（资源释放）阶梯和自己的凭据清除，mcp-client、pty-local、SDK helper 与 TUI Git 探测则各自持有另一份凭据清除——而这一切既不可替换，也无法集中测试。

 ## 决策

@@ -15,7 +15,7 @@ Status: implemented
 - **按流划分的 stdio 处置方式（disposition）**，位于 `SubprocessSpawnSpec` 上：`'pipe'`（原始的 `Readable`/`Writable`，供消费方自有的协议分帧使用）、`'inherit'`（诊断输出直通父进程的流），以及收集模式（collect）`{ maxBytes, spill? }`——即最初的有界尾部保留形状，只是 spill 文件改为可选，使诊断尾部（例如语言服务器的 stderr）无需落盘即可缓冲。stdin 则为 `'ignore'`、`'pipe'` 或 `{ data }`（写完即关闭的批量形式）。
 - **`SubprocessOutcome` 只承载退出事实**（Node close 事件的词汇）；收集到的输出在结算后仍可经 `handle.collected` 读取（spill 文件描述符在结算边界封存），因此批量与流式调用方共用一条访问路径，也没有任何内容被复制进这份结果。
 - **以进程树为范围的终止，集中在一个动词后面**：`terminate()` 拥有 SIGTERM→宽限期→SIGKILL 升级（也承接 spec 的 abort 信号，进程树消亡后为空操作）——句柄不暴露单信号的 `kill(signal?)`，因此消费方无法跳过宽限窗口；`waitForExit()` 轮询进程树存活状态（POSIX 进程组探测；Windows 上以直接子进程为界）。Windows 进程树终止（`taskkill /T`，可注入）自 lsp-local 迁入，因此每个消费方拿到的进程树语义在各平台上都正确。（最初从 `subagent-subprocess` 吸收的以 stdin EOF 打头的 dispose 阶梯，后来又移回其唯一消费方——见[阶梯归属 Agent Note](2026-07-27-dispose-ladder-to-consumer.md)。）
- **凭据清除只有一份定义**：`scrubbedParentEnv()`/`SENSITIVE_ENV_PATTERN` 定义在 seam 上。无法把 spawn 本身路由到该服务的调用点——pty-local（node-pty 拥有 fork）与 mcp-client（MCP SDK 拥有传输层的 spawn）——改为导入该函数，因此即便进程所有权无法统一，环境策略仍是单一来源；SDK helper 的 `scrubEnvironment()` 默认同样委托给它。
+- **凭据清除只有一份定义**：`scrubbedParentEnv()`/`SENSITIVE_ENV_PATTERN` 定义在 seam 上，且凭据形状的名称不区分大小写地包含 `KEY`、`PASSWORD`、`SECRET` 或 `TOKEN`。无法把 spawn 本身路由到该服务的调用点——pty-local（node-pty 拥有 fork）、mcp-client（MCP SDK 拥有传输层的 spawn）与 TUI 的同步 Git 分支探测——改为导入该函数，因此即便进程所有权无法统一，环境策略仍是单一来源。SDK helper 的 `scrubEnvironment()` 默认委托给该函数，并在调用方显式传入环境时应用导出的正则；该正则因此生产消费方而保持公开。

 各项迁移随这次重塑一并落地：**bash-local/bash-sandbox**（收集模式 + 批量 stdin；bash 的 `kill()` 映射到 `terminate()`，因此 `task_kill` 保有升级语义），**lsp-local**（管道化的协议流 + 无 spill 的 stderr 收集尾部；`LspConnection` 改为接收 seam 的 spawn 函数；其私有的进程树操作辅助函数已删除），**subagent-acp**（管道化的 ndjson 流 + inherit 的 stderr；spawn 失败经 `done` 的 reject 汇入同一个启动竞态；dispose 是后端自有的 `disposeAcpChild` 阶梯，经由 seam 的动词运行，携带插件所配置的宽限期）。**`dsh-subagent-subprocess` 已删除**——dispose 阶梯与凭据清除归 seam 所有；无人使用的隔离配置目录辅助函数随之消亡（其消费方本就不存在）。

@@ -23,16 +23,16 @@ Status: implemented

 ## 曾考虑的替代方案

-**保持只支持批量的 seam，让流式消费方继续各自为政。**这正是引入该 seam 的 Agent Note 当初的立场，评审将其否决：这样会留下三份进程树信号发送的私有副本和五份凭据清除的私有副本，而未来任何运行器（容器化执行器、远程进程宿主）都得挑选去 fork 哪一份私有副本。Node 形状的处置方式覆盖已观察到的全部三种流形状，既不拓宽结果类型，也不缓冲管道化的流。
+**保持只支持批量的 seam，让流式消费方继续各自为政。**这正是引入该 seam 的 Agent Note 当初的立场，评审将其否决：这样会留下三份进程树信号发送的私有副本和六份凭据清除的私有副本，而未来任何运行器（容器化执行器、远程进程宿主）都得挑选去 fork 哪一份私有副本。Node 形状的处置方式覆盖已观察到的全部三种流形状，既不拓宽结果类型，也不缓冲管道化的流。

 **用单个 `stdio: 'pipe' | 'inherit' | 'collect'` 模式一次性统辖全部三条流。**否决：真实消费方按流混用模式（lsp：pipe/pipe/collect；acp：pipe/pipe/inherit；bash：data/collect/collect）。按流划分的处置方式恰好就是 Node 的形状，也免去了混用场景的第二个 spawn 调用。

 **把 pty-local 与 mcp-client 的 spawn 也一并迁移。**基于所有权而非范围否决：node-pty 的 `fork()` 自行分配终端，MCP SDK 的 `StdioClientTransport` 在内部完成 spawn——这两处调用点都不归我们路由。它们采纳共享的凭据清除（那正是属于策略的部分），并在各自的 README 中说明 spawn 为何留在原地。

-**迁移 test-support 启动器（acp-snapshot、loader-smoke）与 SDK package-manager 运行器。**否决：support 各包（package）是刻意保持轻依赖的测试基础设施，不得依赖产品 seam；而 SDK 向导那套附带重定向的 `stdio: 'inherit'` 语义，加上其完全脱离组合的生命周期（根本没有 cordis 上下文），使该服务并不合用；它改为共享凭据清除。
+**迁移 test-support 启动器（acp-snapshot、loader-smoke）、SDK package-manager 运行器与 TUI Git 探测。**否决：support 各包（package）是刻意保持轻依赖的测试基础设施，不得依赖产品 seam；SDK 向导那套附带重定向的 `stdio: 'inherit'` 语义，加上其完全脱离组合的生命周期（根本没有 cordis 上下文），使该服务并不合用；TUI 探测则是同步调用。这些生产调用点改为共享凭据清除。

 ## 后果

 换来的是：进程树信号发送、升级、有界收集与凭据清除各自只剩一份实现，且只在 `dsh-subprocess-local` 的测试套件中测试一次（其中包括 lsp-local 的私有副本从未有过的、以注入平台方式实现的 Windows 覆盖）；lsp-local 与 subagent-acp 卸下了自己的进程管道，其子进程如今像 bash 的一样，在插件重载后存活、随组合拆除而终止；一个完整的包（`dsh-subagent-subprocess`）就此消失。seam README 中「只有一个消费方家族」的限制说明也随之退役。

-代价是：这道 seam 变宽了（stdio 模式从一种变为三种、终止动词换成 terminate/waitForExit/dispose 这组生命周期表面），未来的后端因此要实现更宽的表面；lsp-local/subagent-acp 的各组合如今都多出 subprocess 这一行组合配置；`SubprocessOutcome` 也不再承载输出，这是仍未发布的堆叠变更内部的一次破坏性形状变更（依照预发布立场，PR2 那一层被就地更新，而非加 shim）。pty-local/mcp-client/SDK/test-support 的 spawn 因所有权归属留在该服务之外，以凭据清除作为共享底线。
+代价是：这道 seam 变宽了（stdio 模式从一种变为三种、终止动词换成 terminate/waitForExit/dispose 这组生命周期表面），未来的后端因此要实现更宽的表面；lsp-local/subagent-acp 的各组合如今都多出 subprocess 这一行组合配置；`SubprocessOutcome` 也不再承载输出，这是仍未发布的堆叠变更内部的一次破坏性形状变更（依照预发布立场，PR2 那一层被就地更新，而非加 shim）。pty-local/mcp-client/SDK/TUI/test-support 的 spawn 因所有权归属或执行形状留在该服务之外，以凭据清除作为共底线，且为显式环境的生产消费方有意保持该正则导出。
@@ -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
+2026-07-27-compiler-independent-typert-model.md: 338476924dfb5d9832d0b64bf01b8d3c297cd6d6
+2026-07-27-compiler-independent-typert-model.zh.md: a88f4dbba50696071552ea12a63b69ecac202418
@@ -0,0 +1,53 @@
+# Agent Note: Compiler-independent Typert type model
+
+Status: implemented
+
+English | [中文](2026-07-27-compiler-independent-typert-model.zh.md)
+
+## Problem
+
+Constructing Zod and reflection text directly from the TypeScript AST couples type analysis and business-semantic recognition to a single generation target. Such a generator can answer only “can this syntax be generated?” It cannot provide a canonical representation of packages, faces, public exports, services, events, objects, and their type relationships, nor can static checks and later generation targets reuse it.
+
+The host and client are independent TypeScript projects; placing both in one `ts.Program` merges conflicting Cordis `Context` and `Events` declarations. At the same time, client types still need to reference host types explicitly, so neither complete isolation nor duplicating types on both sides can express the actual dependencies.
+
+## Decision
+
+[`dsh-typert-generator`](../../../../packages/typert/generator/README.md) builds separate `ts.Program` instances from the host and client projects and uses compiler nodes, symbols, and checkers only as extraction tools. After analysis, every generator and scanner consumes only Typert's own `WorkspaceModel`, `FaceModel`, and `TypeGraph`; the model retains no AST or checker objects. The generator has no dependency on `@deepseek-ai/dsh-typert-registry`.
+
+TypeGraph preserves the developer-authored, pre-evaluation type structure, including generic parameters and applications, explicit inheritance, conditional and mapped types, recursive references, and JSDoc. A reachable type that cannot be represented losslessly causes analysis to fail. If an emitter cannot handle an already modeled node, that emitter fails instead of flattening the type or degrading it to `unknown`.
+
+Each face independently owns a PackageModel and TypeGraph. Direct project references from `tsconfig.host.json` and `tsconfig.client.json` determine a package's face membership, while `package.json#exports` defines its public boundary. Cross-face relationships come only from explicit imports or re-exports in source and remain separate links; external npm types are recorded as External without reading or copying their declarations.
+
+PackageModel recognizes Cordis services, events, `@typert object` reference objects, and `@typert schema` data roots. Services and objects expose only public instance members, excluding constructors and static, private, and protected members; inheritance edges remain in TypeGraph instead of being copied into flattened members. When a public property, parameter, or return type lacks an annotation, `check` mode reports an error, while `write` mode writes the checker-inferred result, rebuilds the project, and analyzes it again in strict mode.
+
+[`dsh-typert-registry`](../../../../packages/typert/registry/README.md) provides `ctx.typert` and handles runtime registration only: one contribution atomically carries package-face reflection and an optional Zod schema, and Cordis effect disposal revokes it. The registry neither analyzes TypeScript nor merges the two faces. JSON Schema is an on-demand projection of registered Zod schemas.
+
+Package artifact publication is explicit opt-in. When invoked, `WorkspaceTypertGenerator` validates that each requested host face exposes the user-facing subpath `package/typert` from the root artifact `package/lib/typert.host.{js,d.ts}`, or that each requested client face exposes `package/client/typert` from `package/lib/typert.client.{js,d.ts}`. It neither edits exports nor runs as part of the ordinary root build or typecheck, so those commands do not generate whole-workspace Typert artifacts. Generated declarations keep `TYPERT` typed as `unknown`, so business packages do not depend on the registry.
+
+At build time, `CordisCatalogProjector` consumes the analyzed `FaceModel` and `TypeGraph` once to generate `docs/cordis-catalog/events.md`, `docs/cordis-catalog/services.md`, and the static `SERVICE_API`, `EVENT_API`, and `TYPE_API` catalog committed for `tool-cordis`. `tool-cordis` reads that static catalog and has no runtime dependency on `ctx.typert`. [`dsh-typert-loader`](../../../../packages/typert/loader/README.md) and the registry remain an independent runtime path: the loader follows Cordis Loader entry lifecycle events, imports an explicitly published `./typert` host artifact, and registers it through `ctx.typert`; neither component supplies the current `cordis_inspect` catalog.
+
+## Verification contract
+
+A small two-face project in the repository snapshots the complete type model, including its source declaration index. Batched workspace analysis and direct focused analysis must produce model-equivalent `FaceModel` and `TypeGraph` results for the same faces. Compile-time exhaustive maps and runtime set comparisons ensure that every node, target, declaration, and member discriminant is exercised by source-authored TypeScript syntax; a field-semantics matrix covers every keyword, type operator, and literal value category, plus every state of generics, parameters, tuples, mapped modifiers, import attributes, abstract forms, predicates, and enum initializers.
+
+For every property in `SyntaxZoo`, the TypeScript printer normalizes the source type, which must exactly match the TypeGraph rendering; TypeScript then recompiles every rendered declaration. This layer checks that each node's internal information is preserved losslessly, including no-substitution template literals, type queries with type arguments, and constrained `infer`, without substituting discriminant coverage or code coverage for structural equivalence.
+
+Boundary cases pin explicit package imports within and across faces, cross-face named re-exports, exact export aliases, qualified `import()` links, and the External classification of global `@types` declarations; they reject TypeScript diagnostics originating in package-owned files, relative-path boundary crossings, references outside `package.json#exports`, and cross-face namespace re-exports without a model target. Interface declaration merging explicitly preserves every authored part; other merges that cannot be represented losslessly fail.
+
+For each supported node kind and literal category, Zod emitter tests run both successful and failing parses; for each unsupported kind, they assert an explicit `TypertEmitError`. Emitter fixtures snapshot generated Zod JavaScript and `.d.ts` text, execute the JavaScript, and typecheck the declarations. `dsh-typert-registry` tests pin atomic registration, queries, JSON Schema, and effect disposal; `dsh-typert-loader` tests also prove delayed mounting, unloading, and disposal while a dynamic import remains pending. A real `dsh-tools` vertical slice generates a contribution from the model, loads it through the runtime registry, and compares its service, event, and related-type records with the committed static `SERVICE_API`, `EVENT_API`, and `TYPE_API`. A full-workspace projector test regenerates the two Cordis catalog documents and the `tool-cordis` API catalog and requires all three texts to be byte-for-byte identical to the committed artifacts.
+
+## Alternatives considered
+
+**Retain the TypeScript AST directly.** The AST preserves source syntax, but it would make every consumer depend on the compiler lifecycle, node identity, and checker context, preventing a stable architectural boundary. It is therefore used only during extraction.
+
+**Generate final types from the checker.** A flattened `ts.Type` is easy to traverse directly, but it loses the developer's expression of generics, conditional and mapped types, and alias applications, so it cannot support reflection and later generation needs.
+
+**Merge the host/client projects or duplicate host types.** Merging would contaminate Cordis declaration merging; duplication would create a second source of truth for types. Independent faces with explicit cross-face links preserve project isolation and actual reference relationships.
+
+**Make `dsh-typert-registry` responsible for type resolution and cross-package composition.** That would recouple the TypeScript compiler, Cordis lifecycle, and a specific schema policy. The registry remains a lifecycle container for generated artifacts, while the build-time model retains complex analysis.
+
+## Consequences
+
+New generation targets and static checks can reuse the same TypeGraph, and business categories can extend PackageModel without parsing the AST again. Preserving pre-evaluation types and independent faces makes the model more complex than a flattened schema; emitters must explicitly declare their supported scope and fail on missing capabilities.
+
+Explicit opt-in keeps artifact publication and package exports under package ownership, while ordinary root builds and typechecks incur no whole-workspace Typert generation phase. The static Cordis catalogs remain reproducible from the canonical model without coupling `tool-cordis` to runtime registry state. `ctx.typert` reflects only artifacts mounted in the current runtime, and unloading does not control Zod instances that consumers retain after importing them directly.
@@ -0,0 +1,53 @@
+# Agent Note: 编译器无关的 Typert 类型模型
+
+Status: implemented
+
+[English](2026-07-27-compiler-independent-typert-model.md) | 中文
+
+## Problem
+
+直接从 TypeScript AST 拼接 Zod 和反射文本，会把类型分析、业务语义识别与单个生成目标绑在一起。这样的生成器只能回答“这段语法能否生成”，无法提供包、face、公开导出、service、event、对象及其类型关系的标准表示，也无法供静态检查和后续生成目标复用。
+
+host 与 client 属于独立 TypeScript project；把两者放进同一个 `ts.Program` 会合并冲突的 Cordis `Context` 与 `Events` 声明。与此同时，client 类型仍需显式引用 host 类型，因此完全隔离或在两边复制类型都不能表达真实依赖。
+
+## Decision
+
+[`dsh-typert-generator`](../../../../packages/typert/generator/README.md) 分别从 host 和 client project 建立 `ts.Program`，只把 compiler node、symbol 和 checker 当作提取工具。分析结束后，所有生成器和扫描器只消费 Typert 自有的 `WorkspaceModel`、`FaceModel` 与 `TypeGraph`，模型中不保留 AST 或 checker 对象。生成器不依赖 `@deepseek-ai/dsh-typert-registry`。
+
+TypeGraph 保存开发者写下的计算前类型结构，包括泛型参数与应用、显式继承、conditional、mapped、递归引用和 JSDoc。无法无损表示的可达类型使分析失败；某个 emitter 无法处理已经建模的节点时由该 emitter 失败，而不是把类型展平或降级为 `unknown`。
+
+每个 face 独立拥有 PackageModel 和 TypeGraph。`tsconfig.host.json` 与 `tsconfig.client.json` 的直接 project references 决定 package 的 face 归属，`package.json#exports` 决定公开边界。跨 face 关系只来自源码中的显式 import 或 re-export，并作为独立 link 保留；外部 npm 类型记录为 External，不读取或复制其声明。
+
+PackageModel 识别 Cordis service、event、`@typert object` 引用对象和 `@typert schema` 数据根。service 与 object 只暴露 public instance member，排除 constructor、static、private 和 protected；继承边保留在 TypeGraph 中，不复制为扁平成员。缺少 public property、parameter 或 return 类型标注时，`check` 模式报错，`write` 模式写入 checker 推断结果后重建 project 并再次以严格模式分析。
+
+[`dsh-typert-registry`](../../../../packages/typert/registry/README.md) 提供 `ctx.typert`，且只负责运行时注册：一个 contribution 原子携带 package-face reflection 与可选 Zod schema，并随 Cordis effect 撤销。注册表不分析 TypeScript，也不合并两个 face。JSON Schema 是对已注册 Zod schema 的按需投影。
+
+包产物发布采用显式 opt-in。`WorkspaceTypertGenerator` 仅在被调用时校验所请求 face 的根目录产物协议：host face 必须通过面向用户的 subpath `package/typert` 暴露 `package/lib/typert.host.{js,d.ts}`，client face 必须通过 `package/client/typert` 暴露 `package/lib/typert.client.{js,d.ts}`。它既不修改 exports，也不作为根目录普通 build 或 typecheck 的一部分运行，因此这些命令不会生成全仓 Typert 产物。生成的声明将 `TYPERT` 类型保持为 `unknown`，因此业务包不依赖注册表。
+
+构建期的 `CordisCatalogProjector` 一次消费分析后的 `FaceModel` 与 `TypeGraph`，生成 `docs/cordis-catalog/events.md`、`docs/cordis-catalog/services.md`，以及为 `tool-cordis` 提交的静态 `SERVICE_API`、`EVENT_API` 和 `TYPE_API` catalog。`tool-cordis` 读取该静态 catalog，运行时不依赖 `ctx.typert`。[`dsh-typert-loader`](../../../../packages/typert/loader/README.md) 与注册表仍是独立的运行时路径：loader 监听 Cordis Loader 配置项生命周期事件，导入显式发布的 `./typert` host 产物，并通过 `ctx.typert` 注册；两者都不是当前 `cordis_inspect` catalog 的数据源。
+
+## Verification contract
+
+提交内的小型双 face project 对完整类型模型及其源码声明索引做 snapshot。全仓分批分析与直接聚焦分析必须为相同 face 生成模型等价的 `FaceModel` 与 `TypeGraph`。类型级全集和运行时集合比较保证每种 node、target、declaration 与 member discriminant 都来自真实 TypeScript syntax；字段语义矩阵覆盖所有 keyword、type operator、literal value 类目，以及泛型、参数、tuple、mapped modifier、import attributes、abstract、predicate 和 enum initializer 的各个状态。
+
+`SyntaxZoo` 中每个 property 的源码类型经 TypeScript printer 标准化后，必须与 TypeGraph 渲染结果逐项相等，随后所有渲染 declaration 再交给 TypeScript 编译。这一层检查节点内部信息是否无损，包括无插值 template literal、带 type argument 的 type query 和受约束 `infer`，不以 discriminant 覆盖或代码覆盖率代替结构等价。
+
+边界用例固定同 face 与跨 face 的显式包导入、跨 face 命名 re-export、精确 export alias、qualified `import()` link 和全局 `@types` External 归属，并拒绝 package 自有 TypeScript 诊断、相对路径越界、`package.json#exports` 之外的引用，以及尚无模型 target 的跨 face namespace re-export。interface declaration merging 显式保留每个 authored part，无法无损表示的其他 merge 失败。
+
+Zod emitter 对支持的节点和各类 literal 逐类执行成功与失败 parse，对不支持的节点逐类断言明确的 `TypertEmitError`。Emitter fixture 对生成的 Zod JavaScript 与 `.d.ts` 文本做快照，执行 JavaScript，并对声明做类型检查。`dsh-typert-registry` 测试固定原子注册、查询、JSON Schema 和 effect 撤销，`dsh-typert-loader` 测试还证明延迟挂载、卸载及未完成 dynamic import 的释放行为。真实 `dsh-tools` 纵切从模型生成 contribution，经运行时注册表加载后，将其服务、事件与关联类型记录同已提交的静态 `SERVICE_API`、`EVENT_API` 和 `TYPE_API` 对照。全仓 projector 测试重新生成两份 Cordis catalog 文档与 `tool-cordis` API catalog，并要求三份文本同已提交产物逐字节一致。
+
+## Alternatives considered
+
+**直接保存 TypeScript AST。** AST 能保留源码写法，但会让每个消费者依赖 compiler 生命周期、node identity 和 checker 上下文，无法形成稳定的架构边界，因此只在提取阶段使用。
+
+**基于 checker 的最终类型生成。** 展平后的 `ts.Type` 便于直接遍历，却丢失泛型、conditional、mapped 和 alias application 的开发者表达，无法满足反射与后续生成需要。
+
+**合并 host/client project 或复制 host 类型。** 合并会污染 Cordis declaration merging；复制会产生第二份类型事实源。独立 face 加显式 cross-face link 保留了 project 隔离与真实引用关系。
+
+**让 `dsh-typert-registry` 承担类型解析和跨包合成。** 这会把 TypeScript compiler、Cordis 生命周期和具体 schema 策略重新耦合。注册表保持为生成 artifact 的生命周期容器，复杂分析留在构建期模型。
+
+## Consequences
+
+新增生成目标或静态检查可复用同一 TypeGraph，业务类目也可在 PackageModel 上扩展，而无需再次解析 AST。保留计算前类型和独立 face 的代价是模型比打平后的 schema 更复杂，emitter 必须显式声明支持范围并对缺失能力失败。
+
+显式 opt-in 使产物发布与 package exports 由各包自行管理，根目录普通 build 和 typecheck 不会引入全仓 Typert 生成阶段。静态 Cordis catalog 可从标准模型复现，同时不把 `tool-cordis` 与运行时注册表状态耦合。`ctx.typert` 只反映当前运行时中已挂载的产物；对于消费方直接导入后仍持有的 Zod 实例，卸载流程无法控制。
@@ -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/2026-07-28-dsh-native-typescript-source-launch.md
-2026-07-28-dsh-native-typescript-source-launch.md: 019389f3e5e9229f4359bbd58c95dbb2f14eb24b
-2026-07-28-dsh-native-typescript-source-launch.zh.md: 2cfff25d228e67ac85a9bc9087fa09ddb64213a0
+2026-07-28-dsh-native-typescript-source-launch.md: 1ba1dd2663038ad7c49af71f8b428245f7fa3e2b
+2026-07-28-dsh-native-typescript-source-launch.zh.md: 02f84f34820469ad9e810ae17d79d3fe12b0cd4c
@@ -4,6 +4,8 @@ Status: implemented

 English | [中文](2026-07-28-dsh-native-typescript-source-launch.zh.md)

+> The Node-native launch vector is superseded by [dsh source launch through the tsx ESM hook](2026-07-29-dsh-source-launch-tsx-esm.md): Node 26.0.0 removed `--experimental-transform-types`, and the paths loader described here is deleted. The Cordis-config declaration gate (`verify-cordis-config`), the app-boot fail-loud plugin diagnostic, and the vendored `import type` marks remain current.
+
 ## Problem

 The `dsh` source entry point originally used `tsx` to run `apps/cli/src/bin.ts`, with the same third-party loader implicitly handling both TypeScript transformation and the root tsconfig's `paths` resolution. With Node handling TypeScript natively, it does not apply tsconfig path mappings; resolving through package exports would instead mix potentially stale or nonexistent `lib/` artifacts into the source launch.
@@ -4,6 +4,8 @@ Status: implemented

 [English](2026-07-28-dsh-native-typescript-source-launch.md) | 中文

+> Node 原生启动向量已被 [dsh 通过 tsx ESM hook 源码启动](2026-07-29-dsh-source-launch-tsx-esm.md) 取代：Node 26.0.0 移除了 `--experimental-transform-types`，本文描述的 paths loader 已删除。Cordis 配置声明门禁（`verify-cordis-config`）、app-boot 的 fail-loud 插件诊断以及 vendor 中的 `import type` 标注仍然有效。
+
 ## 问题

 `dsh` 源码入口原本使用 `tsx` 运行 `apps/cli/src/bin.ts`，TypeScript 转换和根 tsconfig 的 `paths` 解析都由同一个第三方 loader 隐式处理。改由 Node 原生处理 TypeScript 后，Node 不会应用 tsconfig 路径映射；如果改为通过包导出解析，源码启动会混入可能陈旧或不存在的 `lib/` 产物。
@@ -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/2026-07-28-experimental-plugin-package-group.md
+2026-07-28-experimental-plugin-package-group.md: 1ebae5dbb16d4c966f94ffde69fb0cb9bc163d80
+2026-07-28-experimental-plugin-package-group.zh.md: f204ecd052de03d0cf347e2c770feb0ea33966c7
@@ -0,0 +1,33 @@
+# Agent Note: Experimental and internal package group
+
+Status: implemented
+
+English | [中文](2026-07-28-experimental-plugin-package-group.zh.md)
+
+## Problem
+
+The [package hierarchy](../../../../packages/README.md) groups plugins by product role, but it cannot distinguish release packages from prototypes or internal-only packages. The team needs an obvious shared place for useful work that is not part of the official release.
+
+## Decision
+
+The subtree rules in [`packages/experimental/AGENTS.md`](../../../../packages/experimental/AGENTS.md) make `packages/experimental/<pkg>/` the required home for Cordis plugin packages whose whole public contract is experimental or internal-only. Package names remain `@deepseek-ai/dsh-<pkg>`.
+
+The group is the team's in-repository place to share engineering and product-manager prototypes: members can discover, run, review, and extend one another's work against the real plugin graph without implying product support.
+
+Official releases exclude this directory. A package enters a release only after moving to its product-role group; release packages cannot take runtime dependencies on packages here. Examples may use them, while any other runtime dependent also belongs here. Tests may use them as development dependencies.
+
+Experimental packages carry no stability, compatibility, migration, or support promise: they may change APIs, configuration, or data, or disappear without deprecation or migration. Internal-only packages may define narrower internal contracts but make no public release promise. Neither status relaxes engineering, security, documentation, lifecycle, testing, or snapshot requirements.
+
+The pending `@deepseek-ai/dsh-tui-session-changes` `/diff` viewer and `/btw` plugin are examples governed by this rule. Promotion into an official release requires explicit review of the public contract, limitations, test evidence, and a named owner accepting stable-package obligations.
+
+## Alternatives considered
+
+**Keep experimental and internal-only packages in product-role groups with README labels.** Labels are easy to miss and cannot enforce dependency boundaries.
+
+**Treat every package as experimental until the first tagged release.** This provides no durable incubation boundary.
+
+**Develop prototypes and internal packages elsewhere.** This loses the real plugin graph, examples, snapshots, and lifecycle checks needed to evaluate them.
+
+## Consequences
+
+The path makes release exclusion and dependency blast radius visible while retaining the real plugin graph for team sharing. It gives up product-role colocation and creates path churn on promotion, while the npm name remains stable. The subtree rules, repository [current-owner/current-need rule](../../../../packages/AGENTS.md), and unchanged engineering gates limit junk-drawer growth. Because official release tooling does not yet exist, contributor policy enforces the exclusion; when such tooling is added, the directory is its required exclusion boundary.
@@ -0,0 +1,33 @@
+# Agent Note: 实验性与内部专用包（package）分组
+
+Status: implemented
+
+[English](2026-07-28-experimental-plugin-package-group.md) | 中文
+
+## 问题
+
+[包层级结构](../../../../packages/README.md)按产品角色对插件分组，但无法区分发布包、原型和内部专用包。团队需要一个明确的共享位置，存放不属于官方发布版本的有价值成果。
+
+## 决策
+
+[`packages/experimental/AGENTS.md`](../../../../packages/experimental/AGENTS.md) 中的子树规则要求所有公开契约整体处于实验状态或仅限内部使用的 Cordis 插件包位于 `packages/experimental/<pkg>/`。包名仍为 `@deepseek-ai/dsh-<pkg>`。
+
+该分组供团队在仓库内共享工程人员和产品经理制作的原型：成员可以基于真实插件图发现、运行、评审并扩展彼此的原型，但这不代表产品会提供支持。
+
+官方发布版本不包含此目录。包只有移入对应的产品角色分组后才会纳入发布版本；发布包不得在运行时依赖此处的包。示例可以使用这些包；其他任何运行时依赖方也必须位于此处。测试可以将它们用作开发依赖。
+
+实验性包不提供稳定性、兼容性、迁移或支持保证：其 API、配置或数据可以变更，包也可以移除，均不提供弃用期或迁移路径。内部专用包可以定义范围更窄的内部契约，但不作公开发布承诺。无论哪种状态，都不降低仓库对工程、安全、文档、生命周期、测试或快照的要求。
+
+尚待完成的 `@deepseek-ai/dsh-tui-session-changes` `/diff` 查看器和 `/btw` 插件都受这项规则约束。将包提升为稳定包并纳入官方发布版本，需要明确评审其公开契约、限制和测试证据，并指定一名愿意承担稳定包义务的负责人。
+
+## 考虑过的替代方案
+
+**将实验性和内部专用包留在产品角色分组中，并用 README 标注。** 标注容易被忽略，也无法强制执行依赖边界。
+
+**首个带标签的版本发布前，将所有包都视为实验性。** 这无法提供持久的孵化边界。
+
+**在其他位置开发原型和内部专用包。** 这会失去评估它们所需的真实插件图、示例、快照和生命周期检查。
+
+## 后果
+
+该路径明确标示不纳入发布版本的包及其依赖影响范围，同时保留供团队共享成果的真实插件图。代价是这些包无法与同产品角色的包共置，提升并纳入发布版本时还会产生路径变动，但 npm 包名保持稳定。子树规则、仓库已有的[「必须有当前负责人和实际需求」规则](../../../../packages/AGENTS.md)以及保持不变的工程门禁，可限制该分组无序膨胀。由于官方发布工具尚不存在，目前由贡献者政策执行这项排除规则；添加发布工具后，必须以该目录为排除边界。
@@ -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/2026-07-29-dsh-source-launch-tsx-esm.md
+2026-07-29-dsh-source-launch-tsx-esm.md: 93fbb248b45efde37d5fbdb1ec4b812ab3332088
+2026-07-29-dsh-source-launch-tsx-esm.zh.md: 48f410bd846e5808cc95180279348a0ac5ba1c95
@@ -0,0 +1,38 @@
+# Agent Note: dsh source launch through the tsx ESM hook
+
+Status: implemented
+
+English | [中文](2026-07-29-dsh-source-launch-tsx-esm.zh.md)
+
+> Supersedes [native TypeScript source launch](2026-07-28-dsh-native-typescript-source-launch.md): Node removed the capability that decision was built on.
+
+## Problem
+
+The [native source-launch decision](2026-07-28-dsh-native-typescript-source-launch.md) ran `apps/cli/src/bin.ts` under `node --experimental-transform-types` with a resolve-only paths loader, so Node owned TypeScript transformation. Node 26.0.0 removed `--experimental-transform-types` (the process rejects the flag with `bad option`), keeping only strip mode, and strip mode rejects syntax this source graph requires: vendored Cordis parameter properties (`constructor(private ctx: Context)`), the `@Inject` decorators in `vendor/hmr`, and runtime enums/namespaces throughout `vendor/` and `packages/workflow`. The repository's engines range (`^22.19.0 || >=24.0.0`) includes Node 26, so the native launch chain could not start at all there — and no CI job executed the real launch vector, so the incompatibility shipped silently.
+
+Startup latency also mattered: the off-thread `module.register()` hooks worker serialized every resolution across threads (~440ms of `makeSyncRequest` wait during TUI boot), and the full tsx default (`--import tsx`) pays ~0.4s in its CJS hook's resolution amplification.
+
+## Decision
+
+The `dsh` TUI, Web, and headless source launches run `node --import tsx/esm`: tsx's ESM-only hook owns both TypeScript transformation and tsconfig `paths` projection. `bin/dsh`, the root `dsh`/`demo:tui`/`demo:web` scripts, and the Code Mode TUI overlay use the same vector; `bin/dsh` references the hook and tsconfig by absolute checkout paths (bare `tsx/esm` does not resolve from an arbitrary cwd) and pins `TSX_TSCONFIG_PATH` to the root tsconfig. The CJS hook stays off because the CLI source graph is ESM-only; measured TUI time-to-banner is ~0.7s versus ~1.1s under the full tsx default and ~0.75s under the removed native chain.
+
+`scripts/tspath-loader.ts` and `apps/cli/src/tsconfig-paths-loader.ts` are deleted. With them went the loader's runtime rule of mapping a workspace import only for declared runtime dependencies — tsx applies the `paths` map unconditionally. Declaration completeness now rests on the static gates alone: `verify-cordis-config` for configured bare plugins, and workspace constraints for manifests. (That runtime rule found real bugs: `dsh-plan-mode` and `dsh-tool-tasks` imported `@deepseek-ai/dsh-llm` while declaring it only in devDependencies; fixed alongside this change.)
+
+The node-compat CI matrix (Node 22.19 and 26) gains `dsh-source-launch-smoke` (`apps/cli/tests/source-launch.compat.spec.ts`): a keyless piped-stdio launch of the exact production vector asserting the non-zero-exit TTY refusal. Any future Node change to module hooks or TypeScript handling turns this gate red instead of breaking developers' `pnpm dsh`.
+
+## Alternatives considered
+
+**Keep the native chain on Node ≤25 and branch by version.** Rejected: two transformation semantics (amaro versus esbuild) diverge on edge syntax, the launcher grows version probing, and the node-compat matrix must cover both paths — heavy maintenance for an experimental flag that already changed under us. amaro also rejects the `@Inject` decorators `vendor/hmr` uses, so the native path could not boot the shipped default TUI config anyway.
+
+**Make the source graph erasable-only so Node 26 strip mode accepts it.** Rejected: parameter properties and value namespaces pervade vendored Cordis/cosmokit/loader/schemastery; rewriting them is unbounded churn re-applied on every vendor sync.
+
+**A repo-owned in-thread loader (`module.registerHooks()` + esbuild or `@swc/core` transform).** Rejected for now: prototypes measured ~0.45s (esbuild path untested end-to-end; SWC breaks on `vendor/hmr`'s decorator + namespace merge in both decorator modes), but it means owning transform correctness and a resolve hook that tsx already provides. Revisit only if the ~0.3s gap becomes a real cost; the profiling evidence lives in the PR discussion.
+
+**Run built `lib/` for Node 26 and keep native for 24.** Rejected: loses the zero-build development loop on the newest Node line and mixes source and artifact planes.
+
+## Consequences
+
+- One launch vector across the whole engines range, including future Node lines that change native TypeScript support; the smoke gate enforces it per matrix line.
+- TypeScript transformation is delegated to tsx/esbuild again, reversing the prior note's goal of proving Node-native transformation; that goal is unreachable while vendored sources use non-erasable syntax and Node ships no transform mode.
+- The runtime declared-dependency enforcement in source launches is gone; undeclared workspace imports now surface only through static gates or built-mode resolution failures.
+- Startup improves ~0.4s over the full tsx default (`demo:headless` and ACP keep `--import tsx`; their graphs were not audited for CJS-hook dependence and their launch latency is not on the interactive path).
@@ -0,0 +1,38 @@
+# Agent Note: dsh 通过 tsx ESM hook 源码启动
+
+Status: implemented
+
+[English](2026-07-29-dsh-source-launch-tsx-esm.md) | 中文
+
+> 取代[原生 TypeScript 源码启动](2026-07-28-dsh-native-typescript-source-launch.md)：Node 移除了该决策所依赖的能力。
+
+## 问题
+
+[原生源码启动决策](2026-07-28-dsh-native-typescript-source-launch.md)让 `apps/cli/src/bin.ts` 在 `node --experimental-transform-types` 下运行，配合一个只做解析的 paths loader，由 Node 负责 TypeScript 转换。Node 26.0.0 移除了 `--experimental-transform-types`（进程以 `bad option` 拒绝该 flag），只保留 strip 模式，而 strip 模式无法接受这个源码图必需的语法：vendor Cordis 中的参数属性（`constructor(private ctx: Context)`）、`vendor/hmr` 中的 `@Inject` 装饰器，以及遍布 `vendor/` 与 `packages/workflow` 的运行时 enum/namespace。仓库的 engines 范围（`^22.19.0 || >=24.0.0`）包含 Node 26，因此原生启动链在其上完全无法启动——且没有任何 CI 任务执行过真实启动向量，这一不兼容悄然发布。
+
+启动延迟同样是问题：off-thread 的 `module.register()` hooks worker 把每次解析都跨线程序列化（TUI 启动期间约 440ms 的 `makeSyncRequest` 等待），而完整 tsx 默认形态（`--import tsx`）的 CJS hook 解析放大要多付约 0.4s。
+
+## 决策
+
+`dsh` 的 TUI、Web 与无头源码启动运行 `node --import tsx/esm`：由 tsx 的 ESM-only hook 同时负责 TypeScript 转换与 tsconfig `paths` 投影。`bin/dsh`、根目录的 `dsh`/`demo:tui`/`demo:web` 脚本以及 Code Mode TUI overlay 使用同一向量；`bin/dsh` 以 checkout 的绝对路径引用 hook 与 tsconfig（裸的 `tsx/esm` 无法从任意 cwd 解析），并将 `TSX_TSCONFIG_PATH` 固定到根 tsconfig。CJS hook 保持关闭，因为 CLI 源码图是纯 ESM；实测 TUI 到 banner 约 0.7s，对比完整 tsx 默认形态约 1.1s、已移除的原生链约 0.75s。
+
+`scripts/tspath-loader.ts` 与 `apps/cli/src/tsconfig-paths-loader.ts` 已删除。随之消失的还有该 loader "仅为已声明运行时依赖映射 workspace import" 的运行时规则——tsx 无条件应用 `paths` 映射。声明完整性现在仅由静态门禁保障：配置的裸插件走 `verify-cordis-config`，manifest 走 workspace constraints。（该运行时规则确实发现过真实缺陷：`dsh-plan-mode` 与 `dsh-tool-tasks` 导入 `@deepseek-ai/dsh-llm` 却只声明在 devDependencies；已随本变更修复。）
+
+node-compat CI 矩阵（Node 22.19 与 26）新增 `dsh-source-launch-smoke`（`apps/cli/tests/source-launch.compat.spec.ts`）：以精确的生产启动向量做 keyless 管道 stdio 启动，断言非零退出的 TTY 拒绝。未来 Node 对模块 hook 或 TypeScript 处理的任何改动都会让该门禁变红，而不是破坏开发者的 `pnpm dsh`。
+
+## 备选方案
+
+**在 Node ≤25 保留原生链并按版本分叉。** 拒绝：两套转换语义（amaro 与 esbuild）在边缘语法上会分歧，启动器要加版本探测，node-compat 矩阵要覆盖两条路径——为一个已经变动过的 experimental flag 付出沉重维护。而且 amaro 也不支持 `vendor/hmr` 使用的 `@Inject` 装饰器，原生路径本来就无法启动随附的默认 TUI 配置。
+
+**把源码图改成 erasable-only 以适配 Node 26 strip 模式。** 拒绝：参数属性与值 namespace 遍布 vendor 的 Cordis/cosmokit/loader/schemastery；改写是无界 churn，且每次 vendor sync 都要重做。
+
+**仓库自有的同线程 loader（`module.registerHooks()` + esbuild 或 `@swc/core` 转换）。** 暂拒：原型实测约 0.45s（esbuild 路径未端到端验证；SWC 在 `vendor/hmr` 的装饰器 + namespace 合并上两种装饰器模式都会崩），但意味着自行负责转换正确性和一个 tsx 已经提供的 resolve hook。仅当约 0.3s 的差距成为真实成本时再重启；profiling 证据在 PR 讨论中。
+
+**Node 26 运行构建产物 `lib/`，24 保留原生。** 拒绝：在最新 Node 版本线上失去零构建开发循环，且混淆源码面与产物面。
+
+## 结果
+
+- 整个 engines 范围（包括未来改变原生 TypeScript 支持的 Node 版本线）只有一个启动向量；冒烟门禁按矩阵行强制执行。
+- TypeScript 转换重新委托给 tsx/esbuild，逆转了前一篇 note "证明 Node 原生转换可用" 的目标；在 vendor 源码使用不可擦除语法且 Node 不再提供 transform 模式的情况下，该目标不可达。
+- 源码启动中的运行时依赖声明强制不复存在；未声明的 workspace import 现在只能通过静态门禁或构建模式的解析失败暴露。
+- 启动相比完整 tsx 默认形态快约 0.4s（`demo:headless` 与 ACP 保持 `--import tsx`：其依赖图未就 CJS hook 依赖性做审计，且其启动延迟不在交互路径上）。
@@ -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/2026-07-29-sticky-composer-conversation-scroll.md
+2026-07-29-sticky-composer-conversation-scroll.md: 7ceae95dafffdb756ef49bb5612cd4e711eb59ca
+2026-07-29-sticky-composer-conversation-scroll.zh.md: d925d82f94635b5fe67b0be119c041d003def393
@@ -0,0 +1,29 @@
+# Agent Note: Fixed header, sticky composer inside the transcript scrollport
+
+Status: implemented
+
+English | [中文](2026-07-29-sticky-composer-conversation-scroll.zh.md)
+
+## Problem
+
+The active conversation column split scrolling: the chat (and trajectory) view owned `overflow-y: auto`, while the composer stack sat as a sibling below that scrollport. A wheel gesture over the stats line or input therefore hit a non-scrolling region and did nothing — the transcript only moved when the pointer was over the message list. Long drafts made it worse: the textarea is itself a scrollport, so wheel over the composer could be trapped there. The session header must occupy the top of the column as ordinary chrome (not `position: sticky` inside the scrollport), while the composer must stick to the bottom of the same scrollport as the transcript so wheel over the footer moves the flow.
+
+## Decision
+
+While a session exists, `ConversationRoot` always supplies a `wrapActiveBody` owner callback that wraps the view ring in a `data-conversation-scroll` body and places a `data-composer-seat` around the whole `'conversation.composer'` chain output (fallback + elected overlay siblings from `overlay: true`). Active CSS sticks that seat with `position: sticky; bottom: 0` so Question/Approval takeovers stay visible when the user is not pinned to the floor; hero CSS centers the fallback stack inside the scroll body. `ConversationSession` keeps a chrome-hidden header + body shell while blank so that tree seat does not change on the first send. The session header remains `flex: none` column chrome above the scrollport when visible. ChatView and Trajectory/Waterfall keep a local scroller only when mounted outside that host (unit tests); under the host they set `overflow: visible` and resolve bottom-follow / prepend anchoring through `closest('[data-conversation-scroll]')`.
+
+Session stats live on `'conversation.composer.dock'` (above `'conversation.input.dock'`). The InputBar textarea, when inside the host, chains `wheel` with `{ passive: false }`: while the capped textarea can still scroll in that direction it keeps the native gesture; only at its own edge does it `preventDefault` and apply `deltaY` to the host.
+
+## Alternatives considered
+
+**Sticky header and sticky composer inside one column scrollport.** Rejected for the header: it must occupy the top as fixed layout chrome, not participate in the scrollport's sticky layer.
+
+**Fixed flex-none composer below the scrollport with wheel forwarding.** Rejected: the product requires the composer to stick inside the transcript scrollport so the footer is part of that scroll hit-testing surface, not a sibling that only forwards deltas.
+
+**Portal the composer into ChatView's scroller.** Rejected: the composer is shared across view tabs; the wrap target is the Session body owned by the resident shell.
+
+**Keep StatsLine inside ChatView below the message column.** Rejected: outside the sticky composer it would scroll away while the input stayed pinned.
+
+## Consequences
+
+Wheel over the footer scrolls the transcript; the visible layout is a fixed header, scrolling transcript, and sticky bottom composer. Stats appear on every active view tab. Nested view scrollers under the host are suppressed so sticky Turn headers in Trajectory stick to the column host. Hero → active keeps the same textarea DOM node (assembled slash-flow snapshot) and the InputHub draft.
@@ -0,0 +1,29 @@
+# Agent Note: 固定标题栏，sticky 编辑器位于 transcript 滚动容器内
+
+Status: implemented
+
+[English](2026-07-29-sticky-composer-conversation-scroll.md) | 中文
+
+## Problem
+
+活跃会话列把滚动拆成两段：聊天（以及 trajectory）视图自有 `overflow-y: auto`，编辑器栈则作为该滚动容器的兄弟节点坐在下方。指针落在统计行或输入区上时，滚轮打在不可滚动区域上因而毫无效果——只有指针在消息列表上时 transcript 才会移动。草稿变长时更糟：textarea 本身也是滚动容器，编辑器上的滚轮可能被截在那里。会话标题栏必须以普通 chrome 占据列顶（不能在滚动容器内 `position: sticky`），而编辑器必须与 transcript 贴在同一滚动容器底部，使页脚上的滚轮能带动内容流动。
+
+## Decision
+
+只要存在会话，`ConversationRoot` 就会始终提供 `wrapActiveBody` owner 回调，将视图环包进 `data-conversation-scroll` 主体，并用 `data-composer-seat` 包住整条 `'conversation.composer'` chain 输出（`overlay: true` 下的 fallback 与选举出的 overlay 兄弟节点）。活跃阶段 CSS 以 `position: sticky; bottom: 0` 钉住该 seat，使用户未贴底时 Question／Approval 接管仍可见；hero CSS 在滚动主体内居中 fallback 栈。`ConversationSession` 在 blank 时保留隐藏 chrome 的 header + body 壳，使首次发送时树座位不变。可见时会话标题栏仍是滚动容器之上的 `flex: none` 列 chrome。ChatView 与 Trajectory/Waterfall 仅在宿主之外挂载时（单元测试）保留本地 scroller；位于宿主下时设为 `overflow: visible`，并通过 `closest('[data-conversation-scroll]')` 解析贴底跟随与前置锚定。
+
+会话统计挂在 `'conversation.composer.dock'`（位于 `'conversation.input.dock'` 之上）。InputBar 的 textarea 在宿主内以 `{ passive: false }` 链式处理 `wheel`：在限高 textarea 仍能沿该方向滚动时保留原生手势；仅在自身边缘才 `preventDefault` 并将 `deltaY` 施加到宿主。
+
+## Alternatives considered
+
+**标题栏与编辑器都在同一列滚动容器内 sticky。** 标题栏否决：它必须作为固定布局 chrome 占据顶部，而不是参与滚动容器的 sticky 层。
+
+**滚动容器下方 flex-none 固定编辑器并转发滚轮。** 否决：产品要求编辑器 sticky 在 transcript 滚动容器内，使页脚成为该滚动命中面的一部分，而不是仅转发增量的兄弟节点。
+
+**把编辑器 portal 进 ChatView 的 scroller。** 否决：编辑器跨视图标签共享；包装目标是常驻壳拥有的 Session 主体。
+
+**把 StatsLine 留在 ChatView 消息列下方。** 否决：落在 sticky 编辑器之外会随内容滚走，而输入区仍钉在底部。
+
+## Consequences
+
+在页脚上滚轮会滚动 transcript；可见布局是固定标题栏、可滚动 transcript 与 sticky 底部编辑器。统计出现在每一个活跃视图标签上。宿主下的嵌套视图 scroller 被抑制，因而 Trajectory 的 sticky Turn 标题贴在列宿主上。hero → active 保持同一 textarea DOM 节点（assembled slash-flow 快照）以及 InputHub 草稿。
@@ -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/2026-07-29-web-details-session-lifecycle.md
+2026-07-29-web-details-session-lifecycle.md: d9e0255768f165bed0631b9324e971b57ec7dcae
+2026-07-29-web-details-session-lifecycle.zh.md: 09452ba80ff240ddca76df239b40ea661566f8e2
@@ -0,0 +1,29 @@
+# Agent Note: Web details follow the current Session lifecycle
+
+Status: implemented
+
+English | [中文](2026-07-29-web-details-session-lifecycle.zh.md)
+
+## Problem
+
+The details entry is Session-scoped, but its preferred grid width is root-scoped. Selecting a different Session replaced the details content without closing that root preference, so the new owner inherited stale viewing geometry. Hero and other unselected states render no Session-scoped details; they need a derived zero track without becoming false owners in the comparison.
+
+## Decision
+
+`AppFrame` reads the current Session id and its `blank` summary flag from the authoritative Session projection. It records the last non-blank selected id only when that Session can own details, so hero and other unselected states neither trigger closure nor replace the last Session owner; their rendered details track derives as zero without changing the stored preference. The first Session keeps the default details width; returning to the same Session restores its current width; selecting a different Session closes the root-scoped details preference through the layout store before paint. The per-Session chat selection remains owned by the session-scoped store described by the [slot system standard](../architecture/2026-07-22-slot-type-chain-implementation.md).
+
+The layout store is transient and starts details at its default width. It neither reads nor writes `localStorage`, so reload resets both panel widths and needs no Session-baseline exception. Manual close and reopen inside one unchanged Session retain their existing behavior. The lifecycle effect changes neither the [Workspace-owned New Session flow](../feature/2026-07-25-workspace-ui-product-flow.md), composer drafts, Session navigation, nor concession-chain resizing.
+
+## Alternatives considered
+
+**Close details in the New Session click handler.** Rejected because an unselected surface has no Session-scoped details and must not mutate geometry. Closure belongs to the later comparison between two defined Session owners.
+
+**Persist panel geometry per Session.** Rejected because the product contract needs stale context removed, not a new map of remembered widths. Per-Session geometry would also reopen details when users return, contrary to the chosen close-on-leave behavior.
+
+**Preserve persisted layout after the Session baseline is ready.** Rejected because it duplicates startup lifecycle in a presentation component solely to validate stale viewing state. Transient defaults make reload deterministic without a readiness flag.
+
+**Treat every current-projection change as a Session switch.** Rejected because startup materialization, hero, clearing selection, and invalidation are not transitions between two Session owners.
+
+## Consequences
+
+Details is open by default, including when the first Session materializes. Switching to a different Session forgets the dragged details width because close writes zero and reopen uses the contract default. Unselected states derive a zero rendered track while leaving the preferred geometry unchanged; returning to the same Session through one of those states restores its width. Reload forgets sidebar and details geometry. The layout behavior test covers initial defaults, first materialization, direct and hero-mediated Session switches, same-Session return, and the absence of layout storage; the keyless browser e2e drives the same owner transitions through the shipped composition while checking the full grid track and browser errors.
@@ -0,0 +1,29 @@
+# Agent Note: Web 详情栏遵循当前会话生命周期
+
+Status: implemented
+
+[English](2026-07-29-web-details-session-lifecycle.md) | 中文
+
+## 问题
+
+详情入口由会话作用域拥有，而其首选网格宽度由根作用域拥有。选择不同会话时，系统会替换详情内容，却不会关闭根作用域的该首选宽度，因此新 owner 会继承陈旧的查看几何信息。hero 和其他未选中状态不会渲染会话作用域的详情；其轨道需派生为零宽度，但不能因此在比较中成为伪 owner。
+
+## 决策
+
+`AppFrame` 从权威会话投影读取当前会话 id 及其摘要中的 `blank` 标志。它只在该会话能够拥有详情时记录最后一个选中的非 blank 会话 id，因此 hero 和其他未选中状态既不会触发关闭，也不会替换最后一个会话 owner；这些状态下，详情栏轨道的渲染宽度派生为零，但存储的首选宽度不变。首个会话保留详情栏的默认宽度；返回同一会话时恢复其当前宽度；选择不同会话时，系统会先通过布局 store 关闭根作用域存储的详情栏首选宽度，再进行绘制。逐会话的聊天选中项继续由 [slot 体系标准](../architecture/2026-07-22-slot-type-chain-implementation.md)所述的会话作用域 store 拥有。
+
+布局 store 是瞬时状态，详情栏以默认宽度启动。它既不读取也不写入 `localStorage`，因此重新加载会重置两个面板的宽度，无需会话基线例外。在同一个未变化的会话内手动关闭和重新打开详情栏，仍保持原有行为。该生命周期 effect 不改变 [Workspace 拥有的 New Session 动线](../feature/2026-07-25-workspace-ui-product-flow.md)、composer 草稿、会话导航或让步链缩放。
+
+## 考虑过的替代方案
+
+**在 New Session 点击处理器中关闭详情栏。** 之所以否决：未选中表面没有会话作用域的详情，不得修改几何信息。详情栏是否关闭，应由随后对两个已定义会话 owner 的比较决定。
+
+**按会话持久化面板几何信息。** 之所以否决：产品契约需要移除陈旧上下文，而不是新增一张保存各宽度的映射。按会话保存几何信息还会在用户返回时重新打开详情栏，与选定的离开即关闭行为相悖。
+
+**在会话基线就绪后保留持久化布局。** 之所以否决：这会仅为验证陈旧的查看状态，在呈现组件中重复实现启动生命周期。瞬时默认值无需就绪标志即可使重新加载具有确定性。
+
+**将当前投影的每次变化都视为会话切换。** 之所以否决：启动时的物化、hero、清除选中项和选中状态失效都不是两个会话 owner 之间的过渡。
+
+## 后果
+
+详情栏默认打开，首次会话物化时亦然。切换到不同会话会忘记拖动后的详情宽度，因为关闭操作会写入零值，重新打开时则使用契约默认值。未选中状态会将轨道的渲染宽度派生为零，同时保持首选几何信息不变；经由这些状态返回同一会话时，会恢复其宽度。重新加载会忘记侧边栏与详情栏的几何信息。布局行为测试覆盖初始默认值、首次物化、直接及经 hero 中转的会话切换、返回同一会话，以及不存在布局存储的情况；无密钥浏览器 e2e 则通过已交付的组合驱动相同的 owner 过渡，同时检查完整网格轨道和浏览器错误。
@@ -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
-2026-06-22-acp-subagent-backend.md: a45ce5e34873249969bbe4dabb87a89d10246b3d
-2026-06-22-acp-subagent-backend.zh.md: 3b6a11efc1ae0427eb5ce3b30029b77b00d6801a
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md
+2026-06-22-acp-subagent-backend.md: 5f12aa1c08d4f4cfaa35f2f7f4b09ad341c3eae8
+2026-06-22-acp-subagent-backend.zh.md: 61359246b0c552f6126cd82ae843d489de809a38
@@ -34,7 +34,7 @@ ACP `StopReason` → harness `SubagentStopReason`: `end_turn`→`completed`, `ma

 ### Security: scrubbed child environment

-The child is a separate process, so it inherits an environment. Credential-shaped ambient vars (`/KEY|SECRET|TOKEN/i`) are NOT forwarded by default — the parent harness's own secrets must not leak into a spawned process implicitly (the same policy the bash executor applies). The child's OWN credentials (it needs a model key) are supplied EXPLICITLY via `config.env`, layered AFTER the scrub, so an intended `DEEPSEEK_API_KEY` survives while an incidental `AWS_SECRET_ACCESS_KEY` does not. Child stderr is inherited to the parent's stderr (diagnostics surface naturally); a spawn-level `error` event (e.g. ENOENT for a bad command) is captured and raced against the ACP drive, so a bad command settles `error` instead of crashing the parent with an unhandled error.
+The child is a separate process, so it inherits an environment. Credential-shaped ambient vars (`/KEY|PASSWORD|SECRET|TOKEN/i`) are NOT forwarded by default — the parent harness's own secrets must not leak into a spawned process implicitly (the same policy the bash executor applies). The child's OWN credentials (it needs a model key) are supplied EXPLICITLY via `config.env`, layered AFTER the scrub, so an intended `DEEPSEEK_API_KEY` survives while an incidental `AWS_SECRET_ACCESS_KEY` does not. Child stderr is inherited to the parent's stderr (diagnostics surface naturally); a spawn-level `error` event (e.g. ENOENT for a bad command) is captured and raced against the ACP drive, so a bad command settles `error` instead of crashing the parent with an unhandled error.

 ## Testing

@@ -34,7 +34,7 @@ ACP `StopReason` → harness `SubagentStopReason`：`end_turn`→`completed`、`

 ### 安全：清洗子进程环境

-子 agent 是独立进程，因此会继承环境变量。形如凭证的环境变量（`/KEY|SECRET|TOKEN/i`）默认不转发——父 harness 自身的密钥不得隐式泄露到派生进程中（与 bash 执行器采用的策略相同）。子 agent 自己的凭证（它需要模型密钥）通过 `config.env` 显式提供，在清洗之后叠加，因此有意传入的 `DEEPSEEK_API_KEY` 得以保留，而偶然存在的 `AWS_SECRET_ACCESS_KEY` 则不会。子进程的 stderr 继承到父进程的 stderr（诊断信息自然浮现）；spawn 级别的 `error` 事件（如命令不存在时的 ENOENT）被捕获并与 ACP 驱动竞速，因此错误命令解析为 `error` 而非以未处理错误崩溃父进程。
+子 agent 是独立进程，因此会继承环境变量。形如凭证的环境变量（`/KEY|PASSWORD|SECRET|TOKEN/i`）默认不转发——父 harness 自身的密钥不得隐式泄露到派生进程中（与 bash 执行器采用的策略相同）。子 agent 自己的凭证（它需要模型密钥）通过 `config.env` 显式提供，在清洗之后叠加，因此有意传入的 `DEEPSEEK_API_KEY` 得以保留，而偶然存在的 `AWS_SECRET_ACCESS_KEY` 则不会。子进程的 stderr 继承到父进程的 stderr（诊断信息自然浮现）；spawn 级别的 `error` 事件（如命令不存在时的 ENOENT）被捕获并与 ACP 驱动竞速，因此错误命令解析为 `error` 而非以未处理错误崩溃父进程。

 ## 测试

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-24-workspace-context.md
-2026-06-24-workspace-context.md: f86e227be615c9b54e2a9013d3c7dca75d3975f0
-2026-06-24-workspace-context.zh.md: 154b5260955570e2de3c88d98286c5ea6afaa3b5
+2026-06-24-workspace-context.md: 8baced0143abb38ff34d16a072761ec016a53d6e
+2026-06-24-workspace-context.zh.md: 392d57f344b97c1816f691fef75440f815bccb50
@@ -34,7 +34,7 @@ The injection becomes a durable `user/message` with a typed `workspace-instructi

 A resumed agent creates a new loop instance and injects a baseline composed from current files before its first request. This permits current baseline content on resume without mutating an earlier history event. A resume and a hot plugin remount both face a log that may already hold a baseline; they are told apart by `agent/session-start`, which a startup or resume emits before the first step while a remount attaches to an already-live session and never sees it. A remount retains the existing baseline only when its typed event remains in the current visible surface, and still rebuilds scope and provider-version tracking from current files. If compaction has shadowed that event, the remount injects a current baseline. A resume always re-composes.

-The baseline is a user-role `<system-reminder>` with `Instructions from: <path>` sections and explicit authority and precedence language. This familiar model-facing frame avoids a harness-specific XML vocabulary. Project paths are root-relative and the user-global path is `~/.dsh/AGENTS.md` for the default home or `$DSH_HOME/AGENTS.md` for a configured home. A literal `</system-reminder>` inside file content is escaped. The package README owns the exact current [prompt shape](../../../../packages/context/workspace-context/README.md#prompt-shape).
+The baseline is a user-role `<system-reminder>` with `Instructions from: <path>` sections and explicit authority and precedence language. This familiar model-facing frame avoids a harness-specific XML vocabulary. Project paths are root-relative and the user-global path is `~/.dsh/AGENTS.md` for the default home or `$DSH_HOME/AGENTS.md` for a configured home. The final rendering boundary escapes a literal `</system-reminder>` anywhere in instruction content or model-visible path, scope, and budget metadata before byte accounting completes. The package README owns the exact current [prompt shape](../../../../packages/context/workspace-context/README.md#prompt-shape).

 ### Dynamic Discovery And Refresh

@@ -34,7 +34,7 @@ Status: implemented

 恢复 agent 会创建新的循环实例，并在其第一次请求前注入由当前文件组合的基线。这样，恢复时可以使用当前基线内容，而无需修改先前的历史事件。恢复与插件热重挂都会面对日志中可能已存在基线的情况；二者通过 `agent/session-start` 区分：启动或恢复会在第一步前发出该事件，而热重挂附着到一个已存活的会话、永远不会看到它。只有当基线的类型化事件仍在当前可见表层中时，热重挂才保留既有基线，同时仍会根据当前文件重建 scope 与提供方版本跟踪。如果压缩（compaction）已遮蔽该事件，热重挂会注入当前基线。恢复则始终重新组合。

-基线是一条 user 角色的 `<system-reminder>`，包含 `Instructions from: <path>` 章节，以及明确的权威性与优先级说明。这种熟悉的模型可见框架避免引入 harness 专用的 XML 词汇。项目路径相对于根目录；使用默认 home 时，用户全局路径为 `~/.dsh/AGENTS.md`，使用已配置 home 时则为 `$DSH_HOME/AGENTS.md`。文件内容中的字面量 `</system-reminder>` 会被转义。包 README 负责规定当前准确的[提示词形态](../../../../packages/context/workspace-context/README.md#prompt-shape)。
+基线是一条 user 角色的 `<system-reminder>`，包含 `Instructions from: <path>` 章节，以及明确的权威性与优先级说明。这种熟悉的模型可见框架避免引入 harness 专用的 XML 词汇。项目路径相对于根目录；使用默认 home 时，用户全局路径为 `~/.dsh/AGENTS.md`，使用已配置 home 时则为 `$DSH_HOME/AGENTS.md`。最终渲染边界会在完成字节核算前，转义指令内容或模型可见的路径、scope 与预算元数据中出现的字面量 `</system-reminder>`。包 README 负责规定当前准确的[提示词形态](../../../../packages/context/workspace-context/README.md#prompt-shape)。

 ### 动态发现与刷新

@@ -3,4 +3,4 @@
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-30-hook-bridges.md
 2026-06-30-hook-bridges.md: 99c6b1941a10e198ec3028f5fe505dabfff9abbe
-2026-06-30-hook-bridges.zh.md: 11ed3a5d177661271b30f1a58d034caa577b5348
+2026-06-30-hook-bridges.zh.md: 66855c3c4f36877aa627173de8e73250546e9621
@@ -15,7 +15,7 @@ harness 的扩展面是其类型化的拦截 seam（见[拦截 seam Agent Note](
 `packages/hooks/` 组下两个独立插件，各为 function/namespace 插件（`name`/`inject`/`Config`/`apply`，无 default export——见[事后复盘 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)），仅注入 `bash`：

 - **`dsh-hooks-claude`**——CC 方言。Claude Code 当前七个钩子点中的七个：`SessionStart`、`UserPromptSubmit`、`PreToolUse`、`PostToolUse`、`Stop`、`SubagentStart` 和 `SubagentStop`。拥有 CC 形态的每事件 stdin payload（基础字段 `session_id`/`transcript_path`/`cwd`/`hook_event_name` 加每事件字段）、`CLAUDE_PROJECT_DIR` 环境变量加 `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` 替换，以及字面量或正则的匹配模式。`transcript_path` 是持久化定位器结果或 `''`；stdin 带有**尾部换行**。
- **`dsh-hooks-codex`**——Codex 当前五个钩子点中的五个：`PreToolUse`、`PostToolUse`、`SessionStart`、`UserPromptSubmit` 和 `Stop`。使用始终为正则的匹配模式、Codex 形态的 snake_case payload（含 `turn_id`/`model`/`permission_mode` 额外字段），写入时不带尾部换行，不注入 Codex 插件环境变量，不做配置时占位符替换，也没有 pre-tool 审批或重写路径。`transcript_path` 是同一定位器结果或 `null`；工具 payload 在精简后的 `tool_input: { command }` 形态中携带真实的 `tool_name`。
+- **`dsh-hooks-codex`**——Codex 当前五个钩子点中的五个：`PreToolUse`、`PostToolUse`、`SessionStart`、`UserPromptSubmit` 和 `Stop`。它使用始终按正则解释的 matcher，输出 Codex 形态的 snake_case payload（含 `turn_id`/`model`/`permission_mode` 额外字段）且写入时不带尾部换行，不注入 Codex 插件环境变量，不做配置时占位符替换，也没有 pre-tool 审批或重写路径。`transcript_path` 是同一定位器结果或 `null`；工具 payload 在精简后的 `tool_input: { command }` 形态中携带真实的 `tool_name`。

 ### Outcome → Decision 映射

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.md
-2026-06-30-hook-protocol-lib.md: 33ec23dd4fa6aa8b4966bbe6c0ca5697ec83056c
-2026-06-30-hook-protocol-lib.zh.md: 8e8c89a4ecca3bea98fb26bc55974765f27f6a11
+2026-06-30-hook-protocol-lib.md: ce25f40e96ffd5c319d9845e36eab5130cec5857
+2026-06-30-hook-protocol-lib.zh.md: 062160931f52576e65557b6e0d385ccaac54aceb
@@ -15,7 +15,7 @@ This Agent Note introduces `@deepseek-ai/dsh-hook-protocol`, a **library** (not
 A new `packages/hooks/` group with `hook-protocol` as a pure library. It owns four primitive families and the `hook/*` session events; each bridge plugin (`dsh-hooks-claude`, `dsh-hooks-codex`) owns what genuinely differs.

 **Shared (here):**
- **Matcher** — `matchesMatcher(pattern, query, mode)`. The ONE axis the dialects differ on is collapsed to the `mode` parameter: `claude` treats a pure `[A-Za-z0-9_|]+` pattern as a literal (pipe = exact-match alternation) and anything else as a regex; `codex` is always an unanchored regex. Match-all on absent/`''`/`'*'`; an invalid regex matches nothing (never throws into the loop).
+- **Matcher** — `matcherDiagnostic(pattern, mode)` and `matchesMatcher(pattern, query, mode)`. The ONE axis the dialects differ on is collapsed to the `mode` parameter: `claude` treats a pure `[A-Za-z0-9_|]+` pattern as a literal (pipe = exact-match alternation) and anything else as a regex; `codex` is always an unanchored regex. Match-all on absent/`''`/`'*'`. Each bridge ignores unsupported events before group parsing, discards matcher fields on supported events without matcher subjects, validates the remaining runnable groups, and treats an invalid regex there as a whole-config load failure, with a stable dialect/pattern/event diagnostic; no hook listeners are registered. Runtime matching still contains an invalid regex as a non-match, so a direct library caller never throws into the loop.
 - **Execution** — `runHook(bash, hook, options)`. Runs a command hook through the `ctx.bash` seam rather than a bespoke `spawn`: the executor already provides the scrubbed-but-overridable env, process-group kills, and timeout the protocol needs, and `dsh-bash`'s `stdin`/`env` fields (added for exactly this) are the trusted-plugin surface an in-process bridge is allowed to use. It serializes the bridge-built payload to stdin (trailing newline iff CC), honors the hook's `timeoutSec` (else `DEFAULT_HOOK_TIMEOUT_MS`, the 10-minute reference default both dialects share), and never throws (an executor rejection becomes a non-blocking-error `HookOutput`).
 - **Decode** — `parseHookOutput(exit, stdout, stderr)`, the exit-code + structured-stdout codec, producing a dialect-neutral `HookOutput`. Exit `0` → lenient JSON parse of stdout; exit `2` → blocking error with `stderr` as the reason (surfaced as `decision: 'block'` so no caller needs a separate exit-code branch); other → non-blocking error. Parses the CC structured-stdout fields that have a consumer on some path (`continue`/`stopReason`/`decision`/`hookSpecificOutput.{permissionDecision,additionalContext,updatedInput}`/`systemMessage`); the bridge honors only the subset meaningful for its dialect. Fields with no consumer on any path are not parsed at all (CC's `suppressOutput` — hook stdout never enters a transcript here, so there is nothing to suppress; see [the tighten-hook-protocol-contract Agent Note](../simplification/2026-07-04-tighten-hook-protocol-contract.md)).
 - **Merge** — `mergeHookOutputs(outputs)`, folding multiple matched hooks into one most-restrictive `MergedHookOutcome`: permission precedence **deny > ask > allow**, halt sticky on the first `continue:false`, block reasons joined `\n\n`, context/system-messages accumulated in order.
@@ -29,4 +29,4 @@ A new `packages/hooks/` group with `hook-protocol` as a pure library. It owns fo

 ## Consequences

-Each bridge parses config, builds its dialect payload, invokes the shared runner and merge logic, maps the decision, and appends `hook/*`. Protocol tests cover every matcher mode, exit-code and codec field, runner plumbing, merge precedence, and audit helper at per-file 100%; bridge tests exercise the library's real load path. `updatedInput` is parsed but only logged and warned until the [input-rewrite proposal](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md) lands.
+Each bridge parses config atomically, builds its dialect payload, invokes the shared runner and merge logic, maps the decision, and appends `hook/*`. Protocol tests cover every matcher mode and diagnostic, exit-code and codec field, runner plumbing, merge precedence, and audit helper at per-file 100%; bridge tests exercise the library's load path and pin the exact warning. Keyless ACP snapshots boot both bridges through the real Loader/app path with a valid blocking group before an invalid matcher, then prove the request reaches the replay model and persists no `hook/*` rows, so partial registration cannot hide behind a hand-mounted context. `updatedInput` is parsed but only logged and warned until the [input-rewrite proposal](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md) lands.
@@ -15,7 +15,7 @@ Status: implemented
 在 `packages/hooks/` 分组下新建 `hook-protocol` 作为纯库。它拥有四个原语族和 `hook/*` 会话事件；每个桥接插件（`dsh-hooks-claude`、`dsh-hooks-codex`）拥有真正不同的部分。

 **共享（本库）：**
- **Matcher** — `matchesMatcher(pattern, query, mode)`。两种方言唯一不同的轴被收敛为 `mode` 参数：`claude` 将纯 `[A-Za-z0-9_|]+` 模式视为字面量（管道符 = 精确匹配的多选），其余视为正则；`codex` 始终是无锚定正则。缺省/`''`/`'*'` 匹配一切；无效正则匹配空集（绝不向 agent loop（智能体循环）抛异常）。
+- **Matcher** — `matcherDiagnostic(pattern, mode)` 与 `matchesMatcher(pattern, query, mode)`。两种方言的唯一差异收敛到 `mode` 参数：`claude` 将纯 `[A-Za-z0-9_|]+` pattern 视为字面量（管道符 = 精确匹配多选），其他 pattern 视为正则；`codex` 始终使用未锚定正则。缺省/`''`/`'*'` 匹配一切。每个桥接插件会在解析 group 前忽略不支持的事件，丢弃受支持但没有 matcher 匹配对象的事件所带字段，校验其余可运行 group；其中任何无效正则都会导致整份配置加载失败，并给出包含方言／pattern／事件的稳定诊断，不会注册任何钩子监听器。运行时匹配仍会将无效正则隔离为不匹配，因此直接调用本库绝不向 agent loop（智能体循环）抛异常。
 - **执行** — `runHook(bash, hook, options)`。通过 `ctx.bash` seam 而非自建 `spawn` 运行命令钩子：执行器已提供清洗但可覆盖的 env、进程组 kill 和超时，正是协议所需的能力；`dsh-bash` 的 `stdin`/`env` 字段（正是为此添加的）是进程内桥接插件被允许使用的受信插件接口。它将桥接插件构建的 payload 序列化到 stdin（CC 时追加尾部换行），遵守钩子的 `timeoutSec`（否则使用 `DEFAULT_HOOK_TIMEOUT_MS`，即两种方言共享的 10 分钟参考默认值），且从不抛异常（执行器拒绝变为 non-blocking-error 的 `HookOutput`）。
 - **解码** — `parseHookOutput(exit, stdout, stderr)`，exit-code + structured-stdout 编解码器，产出方言无关的 `HookOutput`。Exit `0` → 宽松 JSON 解析 stdout；exit `2` → blocking error，`stderr` 为原因（以 `decision: 'block'` 呈现，调用方无需单独处理 exit-code 分支）；其他 → non-blocking error。解析 CC structured-stdout 中在某条路径上有消费方的字段（`continue`/`stopReason`/`decision`/`hookSpecificOutput.{permissionDecision,additionalContext,updatedInput}`/`systemMessage`）；桥接插件只采纳对其方言有意义的子集。在任何路径上都没有消费方的字段不予解析（CC 的 `suppressOutput`——钩子 stdout 在此处从不进入 transcript（文本记录），因此无需抑制；见 [收紧钩子协议契约 Agent Note](../simplification/2026-07-04-tighten-hook-protocol-contract.md)）。
 - **合并** — `mergeHookOutputs(outputs)`，将多个匹配钩子的输出折叠为一个最严格的 `MergedHookOutcome`：权限优先级 **deny > ask > allow**，halt 在首个 `continue:false` 时粘滞，阻止原因以 `\n\n` 拼接，context/system-messages 按序累积。
@@ -29,4 +29,4 @@ Status: implemented

 ## 后果

-每个桥接插件解析配置、构建方言 payload、调用共享的 runner 与合并逻辑、映射 decision、追加 `hook/*`。协议测试覆盖每种 matcher 模式、exit-code 与编解码器字段、runner 管道、合并优先级和审计辅助函数，逐文件 100% 覆盖率；桥接插件测试验证库的真实加载路径。`updatedInput` 已解析但仅记录日志并发出警告，直到 [input-rewrite 提案](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)落地。
+每个桥接插件以原子方式解析配置、构建方言 payload、调用共享的 runner 与合并逻辑、映射 decision、追加 `hook/*`。协议测试覆盖每种 matcher 模式与诊断、exit-code 与编解码器字段、runner 管道、合并优先级和审计辅助函数，逐文件 100% 覆盖率；桥接插件测试验证库的加载路径并锁定精确警告。无密钥 ACP 快照通过真实 Loader/app 路径启动两个桥接插件，在非法 matcher 之前放置一个合法的拦截 group，然后证明请求仍到达 replay 模型且没有持久化任何 `hook/*` 行，从而避免手工挂载 Context 掩盖部分注册。`updatedInput` 已解析但仅记录日志并发出警告，直到 [input-rewrite 提案](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)落地。
@@ -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/2026-07-05-skill-system.md
-2026-07-05-skill-system.md: 4fc621a9fdfa8042ebf3eb1975f0930cb1bf116c
-2026-07-05-skill-system.zh.md: 0dbebd211a1fa9e434d3f0a189c936f2b1c76574
+2026-07-05-skill-system.md: 242650ec8ba64fd0801a958711d5790fae07b259
+2026-07-05-skill-system.zh.md: da5f4af4b2f8bc0144be0a7ed608de7edd9a9947
@@ -18,13 +18,13 @@ Provider plugins register synchronously during `apply()`. Provider membership is

 The local provider scans cwd-sensitive project roots, custom roots, and user roots in first-wins rank order: project `.dsh`, project `.agents`, `customSkillDirs`, user `.dsh`, then user `.agents`. The user `.dsh/skills` scan skips `.system` so a system-owned directory is not treated as normal user content. DeepSeek Harness does not ship built-in system skills; embedded or remote providers supply additional skills when configured.

-Each skill is either `<name>/SKILL.md` or `<name>.md` with YAML frontmatter. `name` and `description` are required; `whenToUse`, `disableModelInvocation`, and `metadata` are optional. Names are kebab-case. YAML frontmatter is parsed with the `yaml` package instead of `js-yaml` or a hand-written parser: `yaml` is the already-declared modern parser for this package's limited frontmatter needs, and a narrow parser would either reject valid YAML users expect to work or grow into an unreviewed YAML subset.
+Each skill is either `<name>/SKILL.md` or `<name>.md` with YAML frontmatter. `name` and `description` are required; `whenToUse`, `metadata`, `disable-model-invocation`, and `user-invocable` are optional. Names are kebab-case. The invocation fields project into a typed nested policy as defined by the [independent model and user invocation decision](2026-07-28-skill-invocation-policy.md); the parser rejects the old camel-case spellings. YAML frontmatter is parsed with the `yaml` package instead of `js-yaml` or a hand-written parser: `yaml` is the already-declared modern parser for this package's limited frontmatter needs, and a narrow parser would either reject valid YAML users expect to work or grow into an unreviewed YAML subset.

 Local skill filesystem I/O goes through `ctx.fs` when a filesystem service is loaded: project-root lookup probes `.git` with `resolve` and `stat`, root discovery uses `listDir`, and skill reads use `readText`. The Node filesystem remains a fallback for minimal contexts that mount `dsh-skill-local` without the fs seam. Missing roots, unreadable or malformed skill files, and transient provider `list()` failures degrade to warn-and-skip so one bad source does not make every agent request fail; malformed candidates still fail fast because they are provider contract violations.

 `dsh-tool-skill` injects one durable user-role `<system-reminder>` catalog as a sourced `user/message` at the session's first `agent/step`, and only when that agent's tool view resolves this plugin's exact `skill` registration. The catalog contains sorted skill name and description only; it excludes bodies, paths, sources, providers, and routing hints. Descriptions are whitespace-normalized, XML-escaped, and capped by `catalogDescriptionMaxLength`, whose default is `500` and minimum is `3`. Full skill bodies are never included in the catalog. (The catalog originally rode the request-only [session-prefix seam](../../archived/feature/2026-07-07-session-prefix.md), archived; the [unified sourced-message decision](../architecture/2026-07-22-unified-send-and-coalesced-user-messages.md) moved it into durable history.)

-The `skill({ name })` tool loads one full skill for the current agent cwd and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` supplies a directory, URL, or opaque provider-managed base for explicitly referenced scripts, references, and assets; resources load only as needed, without directory enumeration. An unresolved name reports that the skill is unknown or no longer available; invalid names and skills marked `disableModelInvocation` retain distinct tool errors. The tool result is the model-visible disclosure path.
+The registry's `list()` returns every winning summary, while model and user consumers apply the invocation predicates owned by the [independent invocation-policy decision](2026-07-28-skill-invocation-policy.md). The `skill({ name })` tool loads one model-invocable skill for the current agent cwd and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` supplies a directory, URL, or opaque provider-managed base for explicitly referenced scripts, references, and assets; resources load only as needed, without directory enumeration. An unresolved name reports that the skill is unknown or no longer available; invalid names and skills with `invocation.modelInvocable: false` retain distinct tool errors. The tool result is the model-visible disclosure path.

 The data structures and catalog/tool contract are documented in [skills.md](../../../../docs/core-data-structures/skills.md), with service signatures in the generated [services catalog](../../../../docs/cordis-catalog/services.md).

@@ -52,4 +52,4 @@ The catalog is deterministic for a fixed root set and runtime registration revis

 ## Deferred

-Forked skill contexts (`context: fork`), parameter declarations and hints (`arguments` and `argument-hint`), and per-skill tool constraints (`allowed-tools` and `disallowed-tools`) are outside the shipped contract. The registry, local provider, and model-facing tool do not parse, advertise, or enforce these fields, and the `user-invocable` frontmatter field is likewise unparsed. Direct user invocation itself ships as a consumer-side affordance instead: the TUI front door offers a manual `/skill:<name>` command over the registry's existing `list()` and `get()` methods, without a registry, provider, or tool contract change — see [the TUI skill slash command](2026-07-21-tui-skill-slash-command.md).
+Forked skill contexts (`context: fork`), parameter declarations and hints (`arguments` and `argument-hint`), and per-skill tool constraints (`allowed-tools` and `disallowed-tools`) are outside the shipped contract. The registry, local provider, and model-facing tool do not parse, advertise, or enforce these fields. Direct user invocation ships as a TUI affordance over the shared invocation policy and trusted `get()` primitive; see [the TUI skill slash command](2026-07-21-tui-skill-slash-command.md).
@@ -18,13 +18,13 @@ DeepSeek Harness 使用同一原语，使项目特定的评审、插件编写和

 本地提供方按先到先得的排名顺序扫描 cwd 敏感的项目根目录、自定义根目录和用户根目录：项目 `.dsh`、项目 `.agents`、`customSkillDirs`、用户 `.dsh`，然后是用户 `.agents`。用户 `.dsh/skills` 扫描跳过 `.system`，以免系统拥有的目录被当作普通用户内容处理。DeepSeek Harness 不随附内置系统 skill；嵌入式或远程提供方在配置后提供额外 skill。

-每个 skill 是 `<name>/SKILL.md` 或带 YAML frontmatter 的 `<name>.md`。`name` 和 `description` 为必填；`whenToUse`、`disableModelInvocation` 和 `metadata` 为可选。名称采用 kebab-case。YAML frontmatter 使用 `yaml` 包（package）解析，而非 `js-yaml` 或手写解析器：`yaml` 是本包有限 frontmatter 需求已声明的现代解析器，窄解析器要么拒绝用户预期可用的合法 YAML，要么膨胀为一个未经评审的 YAML 子集。
+每个 skill 是 `<name>/SKILL.md` 或带 YAML frontmatter 的 `<name>.md`。`name` 和 `description` 为必填；`whenToUse`、`metadata`、`disable-model-invocation` 和 `user-invocable` 为可选。名称采用 kebab-case。调用字段会投影到类型化的嵌套策略中，具体由[模型与用户独立调用决策](2026-07-28-skill-invocation-policy.md)定义；解析器会拒绝旧的驼峰拼写。YAML frontmatter 使用 `yaml` 包（package）解析，而非 `js-yaml` 或手写解析器：`yaml` 是本包有限 frontmatter 需求已声明的现代解析器，窄解析器要么拒绝用户预期可用的合法 YAML，要么膨胀为一个未经评审的 YAML 子集。

 本地 skill 的文件系统 I/O 在加载了文件系统服务时通过 `ctx.fs` 进行：项目根目录查找使用 `resolve` 和 `stat` 探测 `.git`，根目录发现使用 `listDir`，skill 读取使用 `readText`。Node 文件系统作为后备，供在不挂载 fs seam 的最小上下文中加载 `dsh-skill-local` 时使用。缺失的根目录、不可读或格式错误的 skill 文件、以及提供方 `list()` 的瞬态失败均降级为警告并跳过，使一个坏源不会导致所有 agent 请求失败；格式错误的候选项仍然快速失败，因为它们违反了提供方契约。

 `dsh-tool-skill` 在会话的第一个 `agent/step` 注入一个持久化的 user-role `<system-reminder>` 目录，作为带来源的 `user/message`，且仅当该 agent 的工具视图解析到本插件精确的 `skill` 注册时才注入。该目录仅包含排序后的 skill 名称与描述；不包含正文、路径、来源、提供方和路由提示。描述经过空白规范化、XML 转义，并受 `catalogDescriptionMaxLength` 上限约束，其默认值为 `500`，最小值为 `3`。完整的 skill 正文从不包含在目录中。（目录最初通过仅请求的[会话前缀 seam](../../archived/feature/2026-07-07-session-prefix.md)（已归档）传递；[统一带来源消息的决策](../architecture/2026-07-22-unified-send-and-coalesced-user-messages.md)将其移入持久化历史。）

-`skill({ name })` 工具为当前 agent cwd 加载一个完整 skill，返回包含 `<skill_content name="...">`、`<skill_resources>` 和 `<skill_instructions>` 的工具结果。`resourceBase` 提供一个目录、URL 或不透明的提供方管理的基路径，用于显式引用的脚本、参考资料和资产；资源仅按需加载，不进行目录枚举。无法解析的名称报告该 skill 未知或不再可用；无效名称和标记了 `disableModelInvocation` 的 skill 保留不同的工具错误。工具结果是面向模型的可见披露路径。
+注册表的 `list()` 返回全部胜出摘要，而模型与用户消费方应用[独立调用策略决策](2026-07-28-skill-invocation-policy.md)定义的调用判定。`skill({ name })` 工具为当前 agent cwd 加载一个模型可调用的 skill，返回包含 `<skill_content name="...">`、`<skill_resources>` 和 `<skill_instructions>` 的工具结果。`resourceBase` 提供一个目录、URL 或不透明的提供方管理的基路径，用于显式引用的脚本、参考资料和资产；资源仅按需加载，不进行目录枚举。无法解析的名称报告该 skill 未知或不再可用；无效名称和 `invocation.modelInvocable` 为 `false` 的 skill 保留不同的工具错误。工具结果是面向模型的可见披露路径。

 数据结构与目录/工具契约记录在 [skills.md](../../../../docs/core-data-structures/skills.md) 中，服务签名见生成的[服务目录](../../../../docs/cordis-catalog/services.md)。

@@ -52,4 +52,4 @@ agent-core 主干包含一个目录贡献者、一个本地提供方和一个面

 ## 延后

-Fork 的 skill 上下文（`context: fork`）、参数声明与提示（`arguments` 和 `argument-hint`）、以及逐 skill 的工具约束（`allowed-tools` 和 `disallowed-tools`）不在已交付的契约范围内。注册表、本地提供方和面向模型的工具不解析、不广播、也不执行这些字段，`user-invocable` frontmatter 字段同样不会被解析。直接用户调用本身则作为消费方层面的能力交付：TUI 前门基于注册表现有的 `list()` 与 `get()` 方法提供手动 `/skill:<name>` 命令，无需变更注册表、提供方或工具契约——见 [TUI skill 斜杠命令](2026-07-21-tui-skill-slash-command.md)。
+Fork 的 skill 上下文（`context: fork`）、参数声明与提示（`arguments` 和 `argument-hint`）、以及逐 skill 的工具约束（`allowed-tools` 和 `disallowed-tools`）不在已交付的契约范围内。注册表、本地提供方和面向模型的工具不解析、不广播、也不执行这些字段。直接用户调用作为 TUI 功能交付，基于共享调用策略和受信的 `get()` 原语；见 [TUI skill 斜杠命令](2026-07-21-tui-skill-slash-command.md)。
@@ -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
-2026-07-07-mcp-client-plugin.md: 2a8ad62e3bad1f2ae47100294f5dba25ceb47d12
-2026-07-07-mcp-client-plugin.zh.md: 9860d5ec805b394eb0c5f59f54349264593a5599
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md
+2026-07-07-mcp-client-plugin.md: 756a5c4dc9f1152ecb1955d93b8dc47fcf07c661
+2026-07-07-mcp-client-plugin.zh.md: d2ff04d68033402fbb2718f8624e44d35d860db3
@@ -149,7 +149,7 @@ A unified `execute` handler for all tools from one MCP server:

 ### Subprocess environment (stdio transport)

-Replicate the `buildChildEnv` + `SENSITIVE_ENV_PATTERN` scrub from `dsh-subagent-acp`: filter ambient env (strip credential-shaped vars matching `/KEY|SECRET|TOKEN/i`), then merge `config.env` on top. Explicit env overrides survive the scrub.
+Build the child environment from the subprocess seam's shared `scrubbedParentEnv()` base, which removes ambient names matching `/KEY|PASSWORD|SECRET|TOKEN/i` and ambient `DSH_*` names, then merge `config.env` on top. Explicit env overrides survive the scrub.

 ### Disconnection / crash

@@ -149,7 +149,7 @@ MCP 仅保证工具名在[单个服务器内](https://modelcontextprotocol.io/sp

 ### 子进程环境（stdio 传输）

-复用 `dsh-subagent-acp` 的 `buildChildEnv` + `SENSITIVE_ENV_PATTERN` 清洗逻辑：过滤环境变量（剥离匹配 `/KEY|SECRET|TOKEN/i` 的凭证形变量），然后将 `config.env` 覆盖合并到顶层。显式配置的 env 不受清洗影响。
+以子进程服务边界共享的 `scrubbedParentEnv()` 为基础构建子进程环境；该基础环境会移除环境中匹配 `/KEY|PASSWORD|SECRET|TOKEN/i` 的名称以及 `DSH_*` 名称，然后在其上合并 `config.env`。显式配置的 env 覆盖在清洗后仍会保留。

 ### 断连 / 崩溃

@@ -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
-2026-07-10-parallel-tool-call-execution.md: c67ae61939a3e7974f9bf729058a57f5576308a1
-2026-07-10-parallel-tool-call-execution.zh.md: a80317aa951cbf3a9cae0651348c99712a4193d5
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md
+2026-07-10-parallel-tool-call-execution.md: 19f5dc189821433052edfa72613980a2e94e2cae
+2026-07-10-parallel-tool-call-execution.zh.md: e90e357180ae3684500adf7cba41c5fc1dac5743
@@ -10,7 +10,7 @@ An assistant message may contain several sibling `tool-call` blocks. Running the

 Concurrency is a host scheduling concern, not model-facing tool metadata. The loop needs to decide which calls may overlap without hardcoding tool names or exposing scheduler policy in the JSON schema.

-The session log remains authoritative: every started call has an audit event, every started call receives a result, and model history observes results in the original call order regardless of completion order.
+The session log remains authoritative: every started call has an audit event, ordinary completion and cancellation pair calls with results, and model history observes committed results in the original call order regardless of completion order.

 ## Decision

@@ -46,7 +46,7 @@ Only dispatch and the tool body overlap. `tools/pre-execute` and `tools/post-exe

 Each started call appends `tool/call` immediately before its pre-execute gate. Completed dispatches occupy model-order slots, and a commit cursor appends `tool/result` and collects `additionalContexts` only when the next slot is ready. Live surfaces may show several pending calls, but results and post-tool context remain model-ordered.

-An abort before a group starts records no calls from that group. An abort during a group stops replenishment, waits for already-started calls, commits their results in order, drains accepted batch context after those results, and then ends the step through the existing abort path. Calls that never start have no audit event.
+An abort before a group starts records no calls from that group. An abort during a group stops replenishment, waits for already-started calls, commits their results in order, drains accepted batch context after those results, and then ends the step through the existing abort path. Calls that never start have no audit event. An unexpected scheduler failure stops new dispatches, waits for every already-started dispatch to settle, and rethrows the first failure. Because that failure is terminal internal state rather than a tool outcome, the loop does not invent tool results for rejected or uncommitted calls.

 Code Mode remains outside this scheduler because the model emits one native `run_code` call. `run_code` and its internal dispatch queue remain serial; native sibling calls in `mode: 'both'` use the normal scheduler.

@@ -66,7 +66,7 @@ Filesystem read relies on a narrow recorder exception: its synchronous observati

 ## Verification

-Unit coverage pins fail-closed classification, typed argument validation, grouping, barriers, live reclassification after registry replacement, the rolling cap, distinct execution objects, middleware order, ordered results and context, and abort draining. First-party tests pin each parallel declaration.
+Unit coverage pins fail-closed classification, typed argument validation, grouping, barriers, live reclassification after registry replacement, the rolling cap, distinct execution objects, middleware order, ordered results and context, abort draining, and scheduler-failure quiescence. First-party tests pin each parallel declaration.

 Snapshot coverage pins the visible multi-call transcript: pending calls may overlap while completed results remain model-ordered. Code Mode coverage pins its serial boundary. No provider-backed e2e is required because scheduling is deterministic loop behavior.

@@ -84,6 +84,8 @@ Snapshot coverage pins the visible multi-call transcript: pending calls may over

 **Expose staged methods or a scheduling waterfall.** Public `prepare` / `dispatch` / `finalize` methods or a `tools/execution-mode` event add extension surface before another consumer needs it. The loop uses an internal scheduler view, while `executionMode(exec)` leaves an insertion point for a policy seam.

+**Convert scheduler failures into tool results.** AgentLoop cannot determine whether a rejected dispatch invoked the tool body; ToolRegistry owns body-invocation state and typed tool outcomes. Internal scheduler failures therefore remain terminal instead of being reclassified as `ABORTED` results.
+
 **Start calls while the model streams.** This may reduce latency further but changes assistant-message authority, replay, and call/result pairing. The scheduler starts only after the assistant message is complete.

 **Use fixed-size windows.** Waiting for every call in one window before starting the next leaves capacity idle behind a slow call. The rolling pool preserves the cap without that delay.
@@ -101,3 +103,5 @@ Ordered commits may hold a fast result behind a slow earlier sibling. This prese
 Concurrent external calls can compete for quota or process capacity. Providers own their capacity controls; the loop cap only limits calls from one agent step.

 Tool registration is a scheduling boundary. Registry mutations affect not-yet-started calls because the scheduler reclassifies after each barrier and before every pool replenishment. Already-started calls retain the scheduling decision under which they entered the pool.
+
+A terminal scheduler failure may leave recorded calls without results before the failed step closes. Waiting for live dispatches preserves quiescence without misreporting those internal failures as tool outcomes.
@@ -10,7 +10,7 @@ Status: implemented

 并发属于宿主调度范畴，不是面向模型的工具元数据。循环需要在不硬编码工具名称、不向 JSON Schema 暴露调度策略的前提下，判断哪些调用可以重叠执行。

-会话日志仍是权威记录：每个已启动的调用都有审计事件，都会获得结果；无论完成顺序如何，模型历史都按原始调用顺序观察结果。
+会话日志仍是权威记录：每个已启动的调用都有审计事件，正常完成和取消都会使调用与结果配对；无论完成顺序如何，模型历史都按原始调用顺序观察已提交的结果。

 ## 决策

@@ -46,7 +46,7 @@ Status: implemented

 每个已启动的调用都会在进入 pre-execute 门禁之前立即追加 `tool/call`。已完成的派发占据模型顺序的槽位；提交游标只有在下一个槽位就绪时，才会追加 `tool/result` 并收集 `additionalContexts`。实时界面可以显示多个待处理调用，但结果和工具执行后的上下文仍按模型顺序排列。

-如果在一组启动前中止，系统不会记录该组的任何调用。如果在一组执行期间中止，系统会停止补充池，等待已启动的调用，按顺序提交其结果，在这些结果之后排空已接受的批次上下文，然后通过现有中止路径结束该步骤。从未启动的调用没有审计事件。
+如果在一组启动前中止，系统不会记录该组的任何调用。如果在一组执行期间中止，系统会停止补充池，等待已启动的调用，按顺序提交其结果，在这些结果之后排空已接受的批次上下文，然后通过现有中止路径结束该步骤。从未启动的调用没有审计事件。调度器发生意外故障时，会停止新的派发，等待每项已启动的派发结算，并重新抛出第一个故障。由于该故障是内部终态，而非工具结果，循环不会为被拒绝或未提交的调用虚构工具结果。

 Code Mode 仍不使用此调度器，因为模型只会发出一个原生 `run_code` 调用。`run_code` 及其内部派发队列仍按串行方式执行；`mode: 'both'` 中的原生并列调用使用常规调度器。

@@ -66,7 +66,7 @@ Code Mode 仍不使用此调度器，因为模型只会发出一个原生 `run_c

 ## 验证

-单元测试覆盖固定了安全退化的分类、类型化参数验证、分组、屏障、替换注册表后的实时重新分类、滚动上限、独立执行对象、中间件顺序、有序结果与上下文，以及中止排空。第一方测试固定每项并行声明。
+单元测试覆盖固定了安全退化的分类、类型化参数验证、分组、屏障、替换注册表后的实时重新分类、滚动上限、独立执行对象、中间件顺序、有序结果与上下文、中止排空，以及调度器故障后的完全停稳。第一方测试固定每项并行声明。

 快照覆盖固定了可见的多调用 transcript（文本记录）：待处理调用可以重叠执行，已完成结果仍按模型顺序排列。Code Mode 覆盖固定其串行边界。此调度属于确定性循环行为，因此无需依赖提供方的 e2e 测试。

@@ -84,6 +84,8 @@ Code Mode 仍不使用此调度器，因为模型只会发出一个原生 `run_c

 **公开分阶段方法或调度 waterfall。** 公开的 `prepare` / `dispatch` / `finalize` 方法或 `tools/execution-mode` 事件，会在出现另一个消费方之前扩大扩展接口。循环使用内部调度器视图，而 `executionMode(exec)` 为策略 seam 保留了插入点。

+**将调度器故障转换为工具结果。** AgentLoop 无法判断被拒绝的派发是否已调用工具主体；ToolRegistry 负责工具主体调用状态和类型化工具结果。因此，内部调度器故障保持为终态，而不会被重新分类为 `ABORTED` 结果。
+
 **在模型流式输出时启动调用。** 这可能进一步降低延迟，但会改变 assistant 消息的权威性、回放以及调用/结果配对。调度器只在 assistant 消息完成后才启动。

 **使用固定大小的窗口。** 如果在启动下一个窗口前等待当前窗口的每个调用，一个缓慢调用就会使容量闲置。滚动池在保持上限的同时避免了这项延迟。
@@ -101,3 +103,5 @@ Code Mode 仍不使用此调度器，因为模型只会发出一个原生 `run_c
 并发外部调用可能会争用配额或进程容量。提供方负责自身容量控制；循环上限只限制一个 agent 步骤中的调用数量。

 工具注册是调度边界。调度器会在每个屏障之后以及每次补充池之前重新分类，因此注册表变更会影响尚未启动的调用。已启动的调用保留它们进入池时所依据的调度决策。
+
+终态调度器故障可能会在故障步骤关闭前留下已记录但没有结果的调用。等待仍在运行的派发可确保完全停稳，而不会将这些内部故障误报为工具结果。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-16-persistent-pty-sessions.md
-2026-07-16-persistent-pty-sessions.md: 691ccd4341837d63bb48d27c2a3fb007657fe7ba
-2026-07-16-persistent-pty-sessions.zh.md: 86d57f79ee74429542730ebcad60bc9f3c9f15ca
+2026-07-16-persistent-pty-sessions.md: d7d06dc8517780a37889e4f94dd0b99475dc5432
+2026-07-16-persistent-pty-sessions.zh.md: 7783fa4b4f3056ab3b3088a4e9618f45d030ccbf
@@ -40,7 +40,7 @@ Agent-scope disposal closes registrations first, then awaits quiescent teardown

 A registered `shell` backend constrains how a terminal starts; it does not constrain commands typed after startup. `dsh-pty-local` therefore applies two protections before spawning:

- It builds a scrubbed child environment using the same credential-shaped-name policy as `bash-local`, removing ambient `*KEY*`, `*SECRET*`, `*TOKEN*`, and harness-managed variables unless an explicit trusted mapping supplies them.
+- It builds a scrubbed child environment using the same credential-shaped-name policy as `bash-local`, removing ambient `*KEY*`, `*PASSWORD*`, `*SECRET*`, `*TOKEN*`, and harness-managed variables unless an explicit trusted mapping supplies them.
 - It requires `ctx.sandbox` and the shared `ctx.sandboxPolicy`. At spawn, the backend resolves the owner's effective session mode over the deployment default and wraps the shell argv once; that mode and workspace root remain the process boundary for the PTY lifetime. A write that would change the effective `sandbox/mode` is rejected before commit while the owner has any open PTY or unpublished spawn, with an instruction to wait for creation to settle and close those sessions first; same-effective-mode writes remain valid. The pending reservation spans backend setup through publication, so there is no race in which a wider terminal appears after a downgrade. `danger-full-access` is the existing explicit unconfined choice rather than a PTY-specific bypass.

 Sandboxing confines local process effects but does not make arbitrary shell input safe: network calls and other external side effects remain governed by deployment policy. Tool descriptions state that PTY sessions are less auditable than one-shot tools and should be used only when persistence or interactive stdin is necessary.
@@ -40,7 +40,7 @@ agent scope dispose 时先关闭注册，再等待全部所属 PTY 静默退出

 注册的 `shell` 后端只约束终端如何启动，不约束启动后输入的命令。因此 `dsh-pty-local` 在 spawn 前应用两层保护：

- 它使用与 `bash-local` 相同的凭证形态名称策略构建清洗后的子进程环境，移除环境中的 `*KEY*`、`*SECRET*`、`*TOKEN*` 和 harness 管理的变量，除非显式的可信映射提供这些值。
+- 它使用与 `bash-local` 相同的凭证形态名称策略构建清洗后的子进程环境，移除环境中的 `*KEY*`、`*PASSWORD*`、`*SECRET*`、`*TOKEN*` 和 harness 管理的变量，除非显式的可信映射提供这些值。
 - 它要求 `ctx.sandbox` 和共享的 `ctx.sandboxPolicy`。后端在 spawn 时，以部署默认值为底折叠 owner 的有效 session mode，并只包装一次 shell argv；该 mode 与 workspace root 在 PTY 的整个生命周期中充当进程边界。只要 owner 有任何已打开的 PTY 或尚未发布的 spawn，任何会改变生效 `sandbox/mode` 的写入都会在提交前被拒绝，并提示先等待创建操作结算，再关闭这些会话；不会改变生效模式的写入仍然有效。这项进行中的预留从后端 setup 持续到发布完成，因此不存在降级后又出现权限更宽的终端这一竞态。`danger-full-access` 是现有的显式无约束选择，不另设 PTY 私有 bypass。

 沙箱限制本地进程副作用，但不会让任意 shell 输入自动安全：网络调用和其他外部副作用仍由部署策略治理。工具描述会说明 PTY 会话比一次性工具更难审计，只应在确实需要持久状态或交互式 stdin 时使用。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md
-2026-07-21-log-backed-session-titles.md: 1bd58e35ec625fb0b04c0c119ce425ff30a64881
-2026-07-21-log-backed-session-titles.zh.md: 37ec95efbca334f71d19d2bc3e18c22d50d9b5fb
+2026-07-21-log-backed-session-titles.md: 81ac687c6f55dd0ca1eaeb9d84c811edcfe17b5c
+2026-07-21-log-backed-session-titles.zh.md: b0c7e9d76a1b9365fa16dcb223b390b5aec3e174
@@ -36,9 +36,13 @@ Model providers require explicit word, CJK-character, input-byte, output-token,

 Automatic provider failures are nonfatal warnings and retain the latest title. Explicit refresh failures reject to the caller. Output must be non-empty text with unique ordered seqs drawn from the fixed request; the service normalizes and byte-limits it before log acceptance.

+### Explicit rename
+
+`rename(session, title)` accepts a user title synchronously: it normalizes the text under the accepted-title byte limit, supersedes in-flight automatic work, and appends a `session/title` event with the third source kind, `user`. A user-sourced latest title pins the session: `onUserMessage` schedules no automatic revision while it stands, under either cadence. An explicit `refresh()` remains the deliberate unpin — it appends a provider or fallback event over the pinned one whenever a replacement title is derivable (an underivable fallback, e.g. under a tiny byte cap, leaves the pin standing). The Web host exposes this as the `session.rename` unary method (resuming cold sessions first) and returns the normalized title plus its event seq so the client settles its `title` projection cell before the push frame arrives.
+
 ### Forks and consumers

-A fork inherits seed title events unchanged, like the rest of its source log. The first-message provider does not automatically retitle a fork. The all-messages provider may append a child-owned revision after a later child prompt, using inherited and new eligible messages.
+A fork inherits seed title events unchanged, like the rest of its source log — a pinned (user-sourced) title stays pinned in the child until an explicit refresh. The first-message provider does not automatically retitle a fork. The all-messages provider may append a child-owned revision after a later child prompt, using inherited and new eligible messages.

 `ctx.sessionQuery.readTitle()` folds one live-preferred or persisted log without loading titles during `listSessions()`. The TUI uses the latest title as its header subtitle and sets the terminal window title to `<session title> — <configured product title>` after terminal-safe rendering. The Web host folds the same log state into a validated mux control frame after each attached-session subscription baseline and immediately after forwarding a live raw title event. The browser retains only newer title event seqs even when the control frame precedes list or session-instance creation; sidebar labels, search, breadcrumbs, and the browser title then react to the projected revision. `session.list` remains metadata-only, so a cold persisted session uses the cwd basename or id until opening or resuming it attaches the log. The browser title uses `<session title> — <existing HTML title>` only for a selected titled session and otherwise preserves the product title. Consumers reporting agent completion use the core `findLastMessageTurnEnd()` fold, so a later between-turn title record cannot replace the preceding message-triggered outcome.

@@ -59,4 +63,4 @@ A fork inherits seed title events unchanged, like the rest of its source log. Th
 - A fallback appears immediately. Each fresh Web session adds one first-message auxiliary call; other compositions choose whether better titles justify model cost and whether later prompts should retitle a session.
 - Auxiliary request records and late accepted titles consume event seqs without consuming turn numbers, so persistence exposes both attempted dispatches and accepted updates even though model history and KV-cache identity do not change.
 - One provider and monotonic per-session revisions make disposal, supersession, and stale-result rejection explicit, at the cost of leaving multi-strategy precedence to a composite provider.
- Manual rename, deletion, generated-versus-user precedence, search, and list indexing remain outside the capability.
+- Deletion (unpinning without an explicit refresh), search, and list indexing remain outside the capability.
@@ -36,9 +36,13 @@ Status: implemented

 自动提供方故障只会发出非致命警告，并保留最新标题。显式刷新失败则会向调用方返回拒绝。输出必须是非空文本，并包含来自固定请求、唯一且有序的 seq；服务会在日志接受前对其进行规范化并施加字节限制。

+### 显式重命名
+
+`rename(session, title)` 同步接受用户标题：按已接受标题的字节上限规范化文本、取代在途自动工作，并追加一条第三种来源 `user` 的 `session/title` 事件。最新标题来源为 user 即钉住该会话：只要它还在，`onUserMessage` 在任一节奏下都不再安排自动修订。显式 `refresh()` 仍是有意的解钉手段——只要能推导出替代标题，它就在被钉住的标题之上追加提供方或回退事件（推导不出回退标题时，例如字节上限过小，钉住状态保持不变）。Web host 将其暴露为 `session.rename` unary 方法（冷会话先恢复），并返回规范化后的标题及其事件 seq，使 client 在推送帧到达前就结算自己的 `title` 投影格。
+
 ### Fork 与消费方

-与源日志的其他部分相同，fork 会原样继承作为种子的标题事件。首消息提供方不会自动为 fork 重新生成标题。全部消息提供方可以在子会话出现后续提示词后追加一项归子会话所有的修订，并使用继承的合格消息和新增的合格消息。
+与源日志的其他部分相同，fork 会原样继承作为种子的标题事件——被钉住（user 来源）的标题在子会话中保持钉住，直到显式 refresh。首消息提供方不会自动为 fork 重新生成标题。全部消息提供方可以在子会话出现后续提示词后追加一项归子会话所有的修订，并使用继承的合格消息和新增的合格消息。

 `ctx.sessionQuery.readTitle()` 会折叠一份实时优先或已持久化的日志，而不会在 `listSessions()` 期间加载标题。TUI 使用最新标题作为其标题栏副标题，并在完成终端安全渲染后，将终端窗口标题设置为 `<session title> — <configured product title>`。Web host 会在每个已附加会话的订阅基线之后，以及转发实时原始标题事件后立即，将同一份日志状态折叠为经过校验的 mux 控制帧。即使控制帧先于列表或会话实例创建抵达，浏览器也只保留标题事件 seq 较新的版本；侧边栏标签、搜索、面包屑和浏览器标题会随投影后的修订更新。`session.list` 仍只包含元数据，因此尚未打开的持久化会话会继续以 cwd 基名或 id 作为回退，直至打开或恢复会话时附加其日志。浏览器仅在选中已有标题的会话时将标题设置为 `<session title> — <existing HTML title>`，否则保留产品标题。报告 agent 完成情况的消费方使用核心的 `findLastMessageTurnEnd()` 折叠逻辑，因此后续的轮次间标题记录无法取代此前由消息触发的结果。

@@ -59,4 +63,4 @@ Status: implemented
 - 回退标题会立即出现。每个新建的 Web 会话都会增加一次针对首消息的辅助调用；其他组合可以自行决定更优标题是否值得模型成本，以及后续提示词是否需要重新生成会话标题。
 - 辅助请求记录和延迟接受的标题会占用事件 seq，但不会占用轮次编号，因此持久化会同时呈现尝试发起的调用与已接受的更新，尽管模型历史和 KV 缓存标识保持不变。
 - 单个提供方和每会话单调递增的修订号让释放、取代和陈旧结果拒绝行为明确可见，但多策略优先级必须由复合提供方负责。
- 手动重命名、删除、生成标题与用户标题的优先级、搜索和列表索引不在此功能范围内。
+- 删除（不经显式 refresh 的解钉）、搜索和列表索引不在此功能范围内。
@@ -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
-2026-07-21-tui-skill-slash-command.md: 8370ab61f552a6a60177b6da0b598dd142d21960
-2026-07-21-tui-skill-slash-command.zh.md: 66edec6ecd5c2a974b56e08bd9e924729302cc4a
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.md
+2026-07-21-tui-skill-slash-command.md: 872e1f109728731e0d55e81a538c81e794724856
+2026-07-21-tui-skill-slash-command.zh.md: 772e25745ea7ab25f715208a9c6b1d10cf0c6e65
@@ -10,17 +10,17 @@ The [skill system](2026-07-05-skill-system.md) shipped with model-initiated load

 ## Decision

-The [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) front door owns a `/skill:<name> [instructions]` command. On submit it loads the named skill and delivers one text block as a user turn — sent with `agent.send()` while idle and `agent.steer()` while running, the same rule as ordinary editor input. The block is `renderSkillInvocation(skill, instructions)`: a `<skill name="…">` element wrapping the skill body, preceded by one resource-base line when the provider exposes one, with the user's trailing text appended after a blank line. The command is a TUI-only affordance; it adds no model-facing tool and changes no skill-system package contract.
+The [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) front door owns a `/skill:<name> [instructions]` command. On submit it loads the named skill and delivers one text block as a user turn — sent with `agent.send()` while idle and `agent.steer()` while running, the same rule as ordinary editor input. The block is `renderSkillInvocation(skill, instructions)`: a `<skill name="…">` element wrapping the skill body, preceded by one resource-base line when the provider exposes one, with the user's trailing text appended after a blank line. The command is a TUI-only affordance; it adds no model-facing tool. Its visibility and loading policy comes from the shared [independent model and user skill invocation policy](2026-07-28-skill-invocation-policy.md).

 The TUI reads the skill service through `ctx.get('skills')`, not a declared injection, because skills mount conditionally: a deployment without the registry keeps a working front door, and `/skill:` there reports that skills are unavailable rather than failing to mount. `createTuiChat` is synchronous while `ctx.skills.list()` is async, so autocomplete seeds the static slash commands immediately and rebuilds the provider with `skill:<name>` entries once the catalog resolves; a resolution that arrives after disposal is dropped, and a rejected lookup keeps the base commands.

-Autocomplete lists only model-invocable skills — it is built from `list()`, which omits `disableModelInvocation` skills — while manual submission resolves through `get()`, which the skill registry documents as the trusted-caller path that returns disabled skills too. So a person can load any skill by typing its exact name, but the completion menu never advertises a skill the model is meant not to see. Each completion entry is labeled with its winning source's scope — `(project)` for the `project-` sources, `(user)` for every other source — in the slash-command argument-hint slot, which the menu shows but selection never inserts, so trailing instructions still follow the completed name. An unknown name, an empty name after the prefix, and a lookup failure each surface as a transcript notice without sending anything.
+Autocomplete filters the invocation-neutral `list()` result with `isUserInvocable`, and manual submission applies the same predicate after trusted `get()` resolves the definition. A user-only skill can therefore appear and load even when model invocation is disabled, while a user-disabled skill is neither advertised nor loadable by exact name. Each completion entry is labeled with its winning source's scope — `(project)` for the `project-` sources, `(user)` for every other source — in the slash-command argument-hint slot, which the menu shows but selection never inserts, so trailing instructions still follow the completed name. An unknown name, an empty name after the prefix, a user-disabled name, and a lookup failure each surface as a transcript notice without sending anything.

 `renderSkillInvocation` and the resource-base line are the TUI's own, deliberately not reused from `dsh-tool-skill`'s `skill` tool result. The tool wraps a body in `<skill_content>`/`<skill_resources>`/`<skill_instructions>` for a *tool result*; a manual invocation is a *user turn*, and coupling the two renderers would force one model-facing shape to serve both surfaces. The cost is two renderers that both format a skill body; the benefit is that each surface's model-facing text evolves independently, and each is pinned where it is produced.

 ## Alternatives considered

-**Add a `user-invocable` frontmatter field and enforce it in the registry.** Rejected for this change. The skill-system note defers that field, and manual invocation does not need it: the TUI is a trusted local caller, so `get()` already authorizes loading any skill, and autocomplete visibility keys off the existing `disableModelInvocation`. A new per-skill field would add a contract to the registry, local provider, and tool with no current consumer beyond visibility, which `disableModelInvocation` already covers.
+**Add a `user-invocable` frontmatter field only inside the original TUI change.** Rejected there because a TUI-only field would have changed the registry, provider, and tool contract without a shared invocation model. The later [independent invocation-policy decision](2026-07-28-skill-invocation-policy.md) adds it across every relevant consumer and preserves `get()` as a trusted primitive.

 **Declare `skills` as a TUI injection.** Rejected because skills mount conditionally; a declared injection would make the front door require the registry and refuse to mount without it, contradicting the package's optional-service stance. `ctx.get('skills')` reads the global store and tolerates absence.

@@ -10,17 +10,17 @@ Status: implemented

 ## Decision

-[`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) 前门拥有一条 `/skill:<name> [instructions]` 命令。提交时它加载指定的 skill，并投递一个文本块作为用户轮次——空闲时用 `agent.send()` 发送、运行中用 `agent.steer()` 中途引导，与普通编辑器输入遵循同一规则。该文本块由 `renderSkillInvocation(skill, instructions)` 生成：一个包裹 skill 正文的 `<skill name="…">` 元素，当提供方暴露资源基址时在其前加一行资源基址行，用户尾随的文本在空行之后追加。该命令是 TUI 独有的能力；它不新增任何面向模型的工具，也不改动任何 skill 系统包的契约。
+[`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) 前门拥有一条 `/skill:<name> [instructions]` 命令。提交时它加载指定的 skill，并投递一个文本块作为用户轮次——空闲时用 `agent.send()` 发送、运行中用 `agent.steer()` 中途引导，与普通编辑器输入遵循同一规则。该文本块由 `renderSkillInvocation(skill, instructions)` 生成：一个包裹 skill 正文的 `<skill name="…">` 元素，当提供方暴露资源基址时在其前加一行资源基址行，用户尾随的文本在空行之后追加。该命令是 TUI 独有的功能；它不新增任何面向模型的工具。其可见性和加载策略来自共享的[模型与用户独立 skill 调用策略](2026-07-28-skill-invocation-policy.md)。

 TUI 通过 `ctx.get('skills')` 读取 skill 服务，而非声明式注入，因为 skill 是条件挂载的：没有注册表的部署仍保有可用的前门，此时 `/skill:` 会报告 skill 不可用，而不是挂载失败。`createTuiChat` 是同步的，而 `ctx.skills.list()` 是异步的，所以自动补全先立即种入静态斜杠命令，待目录解析完成后再用 `skill:<name>` 条目重建 provider（提供方）；在 dispose（资源释放）之后才到达的解析结果会被丢弃，而被拒绝的查找会保留基础命令。

-自动补全只列出模型可调用的 skill——它基于 `list()` 构建，而 `list()` 会略去 `disableModelInvocation` 的 skill——手动提交则通过 `get()` 解析，skill 注册表将其记录为返回被禁用 skill 的可信调用方路径。因此用户可以通过键入 skill 的确切名称加载任意 skill，但补全菜单绝不会宣传一个本不该让模型看见的 skill。每个补全条目都以其胜出来源的作用域为标签——`project-` 来源标为 `(project)`，其他一切来源标为 `(user)`——标签置于斜杠命令的参数提示位，菜单会显示它，但选中时绝不会插入，因此尾随指令仍然跟在补全后的名称之后。未知名称、前缀之后为空的名称、以及查找失败，都会各自呈现为 transcript（文本记录）中的一条通知，且不发送任何内容。
+自动补全使用 `isUserInvocable` 过滤与调用策略无关的 `list()` 结果；手动提交则在受信的 `get()` 解析定义后应用相同判定。因此，即使模型调用已禁用，仅供用户调用的 skill 仍会显示并可加载；用户禁用的 skill 既不会展示，也无法按精确名称加载。每个补全条目都以其胜出来源的作用域为标签——`project-` 来源标为 `(project)`，其他一切来源标为 `(user)`——标签置于斜杠命令的参数提示位，菜单会显示它，但选中时绝不会插入，因此尾随指令仍然跟在补全后的名称之后。未知名称、前缀之后为空的名称、用户禁用的名称以及查找失败，都会各自呈现为 transcript（文本记录）中的一条通知，且不发送任何内容。

 `renderSkillInvocation` 及资源基址行是 TUI 自有的，刻意不复用 `dsh-tool-skill` 的 `skill` 工具结果。该工具把正文包进 `<skill_content>`/`<skill_resources>`/`<skill_instructions>` 是为了一个*工具结果*；而手动调用是一个*用户轮次*，把两个渲染器耦合起来会迫使一种面向模型的形态同时服务两个界面。代价是两个都在格式化 skill 正文的渲染器；收益是各界面面向模型的文本可以独立演进，且各自在其产出处被固定。

 ## Alternatives considered

-**新增 `user-invocable` frontmatter 字段并在注册表中强制执行。** 本次改动否决。skill 系统 note 把该字段列为待办，而手动调用并不需要它：TUI 是可信的本地调用方，`get()` 已经授权加载任意 skill，自动补全的可见性以既有的 `disableModelInvocation` 为准。新增一个逐 skill 字段会给注册表、本地提供方和工具都加上一条契约，而除了可见性之外没有任何现有消费方，可见性又已由 `disableModelInvocation` 覆盖。
+**仅在最初的 TUI 变更内新增 `user-invocable` frontmatter 字段。** 当时未采纳，因为 TUI 独有的字段会在没有共享调用模型的情况下改变注册表、提供方和工具契约。后续的[独立调用策略决策](2026-07-28-skill-invocation-policy.md)将其扩展到每个相关消费方，并保留 `get()` 作为受信原语。

 **把 `skills` 声明为 TUI 注入。** 否决，因为 skill 是条件挂载的；声明式注入会使前门必须依赖注册表，缺少它就拒绝挂载，与本包可选服务的立场相悖。`ctx.get('skills')` 读取全局存储并容忍其缺失。

@@ -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: 52a7d223ce3522c5ba977b1126dcd63bd2f6366f
-2026-07-22-docked-web-goal-bar.zh.md: e4842a03ccb8a29b35c7af0c03c51b1324b6ab36
+2026-07-22-docked-web-goal-bar.md: 110aea299a260896b0098f10b337734e0c0aebcf
+2026-07-22-docked-web-goal-bar.zh.md: cc0a5eda6815e6c02e97fd02197659764d4f2d69
@@ -12,9 +12,9 @@ The web UI had no goal surface at all: the goal stack shipped with model tools,

 `GoalBar` (`packages/client/ui-goal/src/client/GoalBar.tsx`) is a new props-driven, self-contained component; `ConversationRoot` mounts it immediately before the composer `InputBar`. The strip's CSS mirrors the composer's horizontal geometry (32px side padding, 776px centered cap) plus the mock's 12px inset, and a -10px bottom margin eats InputBar's 8px top padding and tucks its square bottom edge 2px under the composer card's top edge. All strip states share one fixed 38px height so switching between them 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 edit/clear; paused shows "Paused Goal" and adds 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. An effect keyed on the goal's id drops the edit form when the goal's identity changes, so a surviving draft can never be written over the goal that replaced it.
+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. An effect keyed on the goal's id drops the edit form when the goal's identity changes, so a surviving draft can never be written over the goal that replaced it.

-`GoalBarActions` lives in the contract layer (`contract/slots.ts`, next to the `ConversationInjected.goalActions` slot it feeds) and carries exactly the rendered verbs: `onEdit`/`onResume`/`onClear`. Each callback asynchronously returns an explicit success/failure result so `GoalBar` owns its transitions and error display. `apply.ts` wires them to the runtime session methods; the runtime session resolves the current goal's compare-and-set ref internally, so the UI passes no ref.
+`GoalBarActions` lives in ui-goal's slot contract (`packages/client/ui-goal/src/client/slots.ts`) and carries exactly the rendered verbs: `onEdit`/`onPause`/`onResume`/`onClear`. Each callback asynchronously returns an explicit success/failure result so `GoalBar` owns its transitions and error display. `apply.ts` wires them to the runtime session methods; the runtime session resolves the current goal's compare-and-set ref internally, so the UI passes no ref.

 The runtime session gains the goal surface the strip (and future UI) needs: `fetchGoal` populates the snapshot on open, and a live `context/message` carrying `goal/change` meta triggers a coalesced refetch — concurrent triggers share the in-flight `goal.get`, while a trigger received during that read schedules one coalesced trailing read so independently ordered notifications and GET responses cannot leave stale state. Window replays never refetch, and matching the meta kind (rather than a goal key) also catches clear tombstones written by other clients. The six mutation verbs fold transport failures into `{ ok: false }` results like every sibling session method, and a get result older than a mutation response that landed mid-flight is dropped.

@@ -22,18 +22,18 @@ The strip's background is `--dsw-alias-interactive-bg-hover` rather than the moc

 ## Testing

-`packages/client/ui-goal/tests/goalbar.spec.tsx` pins the behavior through props alone: loading/absent/complete render nothing, the active strip renders label/objective and fires clear, the edit form prefills, rejects empty, saves on Enter, cancels on Esc, and resets when the goal's identity changes, the paused strip fires resume, and the blocked strip exposes the reason tooltip. Component failure-path cases prove that a failed edit preserves its draft and that edit/resume/clear errors remain visible in the bar. The skeleton specs mount `ConversationRoot` with and without `goalActions`; the undefined case is seeded with an active goal, so the missing gate — not the missing goal — is what hides the strip. Runtime session specs pin the folded-error results, the live-only in-flight-plus-trailing refetch, and the stale-read guard. A keyless real-browser smoke boots the assembled application through `boot → RPC → runtime → GoalBar` and records an inline snapshot of the rendered label, objective, and actions.
+`packages/client/ui-goal/tests/goalbar.spec.tsx` pins the behavior through props alone: loading/absent/complete render nothing, the active strip renders label/objective and fires clear, the edit form prefills, rejects empty, saves on Enter, cancels on Esc, and resets when the goal's identity changes, the active strip fires pause, the paused strip fires resume, and the blocked strip exposes the reason tooltip. Component failure-path cases prove that a failed edit preserves its draft and that edit/resume/clear errors remain visible in the bar. The skeleton specs mount `ConversationRoot` with and without `goalActions`; the undefined case is seeded with an active goal, so the missing gate — not the missing goal — is what hides the strip. Runtime session specs pin the folded-error results, the live-only in-flight-plus-trailing refetch, and the stale-read guard. A keyless real-browser smoke boots the assembled application through `boot → RPC → runtime → GoalBar` and records an inline snapshot of the rendered label, objective, and actions.

 ## Alternatives considered

 - **Put the strip in the session header** — rejected because the redesign's premise is that goal presence belongs to the composer's context; a header strip cannot dock into the composer card.
 - **Render a "Loading goal…" placeholder for `undefined`** — rejected: the strip would flash and collapse on every session open, chrome noise for a sub-second state.
 - **Include an inline create affordance when no goal is set** — rejected after implementation review: goal creation lives on the `/goal` command, matching the pattern where the model creates goals on request; the bar is a status indicator, not a creation surface.
- **Carry the full verb set (`onPause`/`onComplete`) in `GoalBarActions`** — rejected as speculative generality: no consumer calls them, so the interface carries only the rendered verbs.
+- **Carry the full verb set (`onComplete` included) in `GoalBarActions`** — rejected as speculative generality: the interface carries only the rendered verbs (`onPause` joined it when the active strip gained its pause action).

 ## Consequences

- Goal presence in the web UI is a composer-docked strip: sparkle, phase label, truncated objective, and edit/clear (plus resume when paused) — the browser client's first goal surface.
+- Goal presence in the web UI is a composer-docked strip: sparkle, phase label, truncated objective, and pause/edit/clear (resume replacing pause when paused) — the browser client's first goal surface.
 - The runtime session exposes the goal verbs over RPC with folded transport errors, and refreshes the snapshot's goal on open and on live goal-change meta (coalesced, guarded against stale reads).
- Objective editing is reachable from the UI for the first time, through `goal.edit` with the runtime-owned ref; pause/complete remain available to other surfaces (`/goal`, model tools).
+- Objective editing is reachable from the UI for the first time, through `goal.edit` with the runtime-owned ref; complete remains available to other surfaces (`/goal`, model tools).
 - `goal === null` renders nothing; the composer carries no persistent create affordance — creation is the `/goal` command's job.
@@ -12,9 +12,9 @@ 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

 `GoalBar`（`packages/client/ui-goal/src/client/GoalBar.tsx`）是一个新的、由 props 驱动的自包含组件；`ConversationRoot` 将它挂载在输入框 `InputBar` 紧上方。横条的 CSS 对齐输入框的水平几何（两侧 32px 内边距、776px 居中上限），再加上设计稿的 12px 内缩，并用 -10px 的下外边距吃掉 InputBar 的 8px 上内边距，使它方形的底边收进输入框卡片顶边之下 2px。横条的所有状态共享固定的 38px 高度，状态切换不会引起尺寸变化。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" 并提供编辑／清除；paused 状态显示 "Paused Goal"，并增加一个恢复图标按钮；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。一个以目标 id 为键的 effect 会在目标身份变化时丢弃编辑表单，因此存留的草稿绝不可能覆盖掉替换它的新目标。
+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。一个以目标 id 为键的 effect 会在目标身份变化时丢弃编辑表单，因此存留的草稿绝不可能覆盖掉替换它的新目标。

-`GoalBarActions` 位于 contract 层（`contract/slots.ts`，紧挨它所喂给的 `ConversationInjected.goalActions` 槽位），只携带实际渲染的动词：`onEdit`/`onResume`/`onClear`。每个回调都会异步返回显式成功／失败结果，因此 `GoalBar` 自行负责界面转换和错误显示。`apply.ts` 把它们接到运行时会话方法上；运行时会话在内部解析当前目标的 compare-and-set ref，因此 UI 不传 ref。
+`GoalBarActions` 位于 ui-goal 的槽位契约（`packages/client/ui-goal/src/client/slots.ts`），只携带实际渲染的动词：`onEdit`/`onPause`/`onResume`/`onClear`。每个回调都会异步返回显式成功／失败结果，因此 `GoalBar` 自行负责界面转换和错误显示。`apply.ts` 把它们接到运行时会话方法上；运行时会话在内部解析当前目标的 compare-and-set ref，因此 UI 不传 ref。

 运行时会话获得了横条（以及未来 UI）所需的目标表面：`fetchGoal` 在打开时填充快照；携带 `goal/change` 元数据的 live `context/message` 触发合并重新拉取——并发触发器共享正在执行的 `goal.get`，读取期间收到的触发器会安排一次合并后的尾随读取，避免彼此独立排序的通知和 GET 响应留下陈旧状态。窗口重放绝不触发重新拉取，且匹配元数据 kind（而不是 goal 键）还能捕获其他客户端写入的清除墓碑。六个变更动词与所有同类会话方法一样，把传输层失败折叠为 `{ ok: false }` 结果；比在拉取途中落地的变更响应更旧的 get 结果会被丢弃。

@@ -22,18 +22,18 @@ 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

 ## 测试

-`packages/client/ui-goal/tests/goalbar.spec.tsx` 仅通过 props 固定这些行为：加载中／无目标／已完成时不渲染；active 横条渲染标签和目标内容并触发清除；编辑表单预填内容、拒绝空值、按 Enter 保存、按 Esc 取消，并在目标身份变化时重置；paused 横条触发恢复；blocked 横条暴露原因悬浮提示。组件失败路径用例证明编辑失败时保留草稿，并且编辑／恢复／清除错误持续显示在横条中。skeleton 规格测试分别挂载带与不带 `goalActions` 的 `ConversationRoot`；未定义的情形预置了一个 active 目标，因此隐藏横条的是缺失的挂载门，而不是缺失的目标。运行时会话规格测试固定了折叠错误结果、仅 live 的执行中读取加尾随读取，以及陈旧读取守卫。一个无密钥真实浏览器冒烟测试通过 `boot → RPC → runtime → GoalBar` 启动组装后的应用，并以内联快照记录渲染出的标签、目标内容和操作。
+`packages/client/ui-goal/tests/goalbar.spec.tsx` 仅通过 props 固定这些行为：加载中／无目标／已完成时不渲染；active 横条渲染标签和目标内容并触发清除；编辑表单预填内容、拒绝空值、按 Enter 保存、按 Esc 取消，并在目标身份变化时重置；active 横条触发暂停；paused 横条触发恢复；blocked 横条暴露原因悬浮提示。组件失败路径用例证明编辑失败时保留草稿，并且编辑／恢复／清除错误持续显示在横条中。skeleton 规格测试分别挂载带与不带 `goalActions` 的 `ConversationRoot`；未定义的情形预置了一个 active 目标，因此隐藏横条的是缺失的挂载门，而不是缺失的目标。运行时会话规格测试固定了折叠错误结果、仅 live 的执行中读取加尾随读取，以及陈旧读取守卫。一个无密钥真实浏览器冒烟测试通过 `boot → RPC → runtime → GoalBar` 启动组装后的应用，并以内联快照记录渲染出的标签、目标内容和操作。

 ## 考虑过的替代方案

 - **把横条放在会话头部**：不予采纳，因为重新设计的前提是目标的存在感属于输入框的上下文；放在头部的横条无法停靠进输入框卡片。
 - **为 `undefined` 渲染 "Loading goal…" 占位**：不予采纳，每次打开会话横条都会闪现再坍缩，对一个不到一秒的状态来说只是界面噪音。
 - **未设置目标时在横条内提供内联创建入口**：实现评审后不予采纳，创建目标的职责在 `/goal` 命令上，与模型按请求创建目标的模式一致；横条是状态指示器，不是创建入口。
- **在 `GoalBarActions` 中携带完整动词集合（`onPause`/`onComplete`）**：作为投机性泛化不予采纳，没有消费方调用它们，接口只携带实际渲染的动词。
+- **在 `GoalBarActions` 中携带完整动词集合（含 `onComplete`）**：作为投机性泛化不予采纳，接口只携带实际渲染的动词（active 横条获得暂停操作后，`onPause` 随之加入）。

 ## 后果

- Web UI 中目标的存在形式是停靠在输入框上方的横条：闪光图标、阶段标签、截断的目标内容，以及编辑／清除（暂停时另有恢复）——这是浏览器客户端的第一个目标界面。
+- Web UI 中目标的存在形式是停靠在输入框上方的横条：闪光图标、阶段标签、截断的目标内容，以及暂停／编辑／清除（暂停时恢复取代暂停）——这是浏览器客户端的第一个目标界面。
 - 运行时会话通过 RPC 暴露目标动词并折叠传输层错误，且在打开时和 live 目标变更元数据到达时刷新快照中的目标（合并拉取，带陈旧读取守卫）。
- 目标内容首次可以从 UI 编辑，经由 `goal.edit`，ref 由运行时持有；暂停／完成对其他界面（`/goal`、模型工具）照常可用。
+- 目标内容首次可以从 UI 编辑，经由 `goal.edit`，ref 由运行时持有；完成对其他界面（`/goal`、模型工具）照常可用。
 - `goal === null` 时不渲染任何内容；输入框不提供常驻的创建入口，创建是 `/goal` 命令的职责。
@@ -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-skill-catalog-hot-refresh.md
+2026-07-27-skill-catalog-hot-refresh.md: 8e70fb10e7da4292325b72f3a0392bef2271738c
+2026-07-27-skill-catalog-hot-refresh.zh.md: 9a6b6d944baa4a9cc4dddb5158fdcbac2b05f5db
@@ -0,0 +1,48 @@
+# Agent Note: Skill catalog hot refresh
+
+Status: implemented
+
+English | [中文](2026-07-27-skill-catalog-hot-refresh.zh.md)
+
+## Problem
+
+Skill summaries are model routing input, but local skills can appear, disappear, or be renamed after a session starts. IDEs, Git operations, shell commands, and other processes can all mutate `.agents/skills` without going through the harness filesystem tools. A startup-only catalog leaves the model unaware of new skills and able to call deleted names. Treating every instruction-body edit as a catalog revision would instead couple progressive loading to unnecessary prompt churn.
+
+Filesystem updates are also non-atomic from the observer's perspective. An editor or Git operation may briefly remove a file, a watched root may not exist at startup, and discovery may fail transiently. Publishing those intermediate observations as authoritative empty catalogs would be worse than retaining the last complete view.
+
+## Decision
+
+The skill capability separates catalog membership from instruction-body loading. `ctx.skills.snapshot()` returns summaries plus a completeness bit. `ctx.skills.registerProvider(factory)` gives the synchronous factory one registration-scoped `{ signal, invalidate }` control: `invalidate()` dirties only that exact active registration and discards completed catalog caches, while the signal aborts when registration fails or is disposed. Provider arrays are complete-discovery shorthand; an explicit incomplete observation can retain readable candidates for direct loads without becoming cacheable or authoritative for model-facing consumers. A provider or runtime generation change during discovery retries once; if the retry is also superseded, the latest candidates return as an incomplete, uncached observation. A late invalidation after disposal or replacement is a no-op because the capability has been revoked.
+
+`@deepseek-ai/dsh-skill-local` directly depends on Chokidar and observes catalog-relevant host paths. Existing roots watch direct skill bundle directories, flat Markdown entries, and direct `SKILL.md` entry files. Additions, removals, and directory changes invalidate membership; file changes support frontmatter `name` and `description` refresh. Resource files below a bundle are ignored. Events in one microtask batch coalesce to one invalidation. Project watchers use a bounded least-recently-observed set.
+
+A missing root is followed from its nearest existing ancestor one absent segment at a time with `fs.watchFile`, then handed to Chokidar once the real root exists. Before scanning, each discovery re-probes the retained root/ancestor mode. That independent probe re-establishes ancestor observation after deletion even when child removals invalidate and publish an authoritative empty catalog before, or without, a root `unlinkDir` event. Chokidar configuration exposes native-versus-polling mode, write stability, polling interval, symlink following, and project watcher capacity. First-party `write` and `edit` tool observations synchronously invalidate a relevant provider, so the next model step sees its own mutation without waiting for host delivery. Watch startup/runtime failures are logged and retried; discovery still returns readable candidates for direct loads but reports an incomplete observation. Teardown closes watchers and ignores late callbacks.
+
+`@deepseek-ai/dsh-tool-skill` injects the first non-empty complete catalog as a durable sourced `user/message` on the first complete `agent/step` that observes one. At every `agent/step` it applies exact `skill` tool visibility, hashes the exact rendered text between the `<available_skills>` tags, and scans the read-only session events backwards without copying them for the newest recognizable visible catalog from this plugin. A changed digest appends a durable, complete replacement through `agent.inject()`, including an explicit empty catalog when all skills disappear. If no catalog remains visible but a recognizable one exists in historical events, compaction hid it and the next complete observation re-establishes the current catalog, including an empty tombstone. A current empty catalog with no historical publication emits nothing, while an incomplete snapshot preserves the last-good model view. The backward scan normally stops at the newest visible catalog; when compaction hides every catalog it pays an O(session-events) scan to recover that fact.
+
+The TUI consumes the same invalidation as presentation state, not session history. `skills/change` carries no diff; the TUI refetches `snapshot()` for the active session cwd, applies only the latest complete result, and retains the previous commands across incomplete observations. A complete empty result clears stale completions. Because pi-tui closes autocomplete when its provider is replaced, a catalog that arrives while the user is typing a slash-command name also triggers a suggestion-only re-query of the current draft.
+
+Instruction bodies keep progressive disclosure. Every `skill(name)` call asks the provider to reread and parse the current file; there is no body cache, hash, revision, or proactive notification. Previously logged tool results remain unchanged. If the loaded frontmatter name no longer matches the selected candidate, the registry rejects the stale name and invalidates that provider so a later catalog observation can publish the new name.
+
+## Verification
+
+Registry tests pin registration-scoped invalidation, revocation, signal abort, contained observer failures, incomplete candidates, bounded generation retries, and stale-name rejection. Local-provider tests cover bundle and flat-file creation, removal, rename, root creation/deletion/recreation including an unobserved root `unlinkDir`, description changes, body-only edits, first-party observation, symlinks, polling options, persistent watcher failures with loadable candidates, event coalescing, bounded projects, teardown, and transient reads. Tool tests pin full replacement messages, empty tombstones, digest stability for body-only edits, incomplete-state retention, visibility, and resume metadata. TUI tests pin last-complete retention, authoritative empty removal, latest-wins refresh, teardown, and the already-open slash-draft race; a real Loader/PTY smoke adds a local skill after startup and observes its completion without restarting. A keyless assembled agent-spine snapshot creates a project skill through model-facing filesystem tools, observes its replacement catalog on the next request, and loads its current body with the real `skill` tool.
+
+## Alternatives considered
+
+- **Put the live catalog in World State** — rejected because catalog replacements are model-visible session inputs and must be reconstructable from the event log. Durable injected history already provides replay, resume, fork, and compaction semantics without another mutable state plane.
+- **Rely only on `fs/observed`** — rejected because IDEs, Git, shell commands, and external processes do not cross that seam. The event remains a latency fast path for first-party tools, while host watching supplies coverage.
+- **Hash or version every `SKILL.md` body** — rejected because the model initially sees only names and descriptions, and the provider already rereads the body on each tool call. Body revisions would create catalog traffic without changing routing and would not justify rewriting historical tool results.
+- **Watch every bundle resource** — rejected because references, scripts, and assets are loaded on demand and do not affect the category list. Broad recursive watching would add invalidations, descriptor pressure, and platform variability without improving routing.
+- **Publish partial or failed discovery as the new catalog** — rejected because a transient read failure is not evidence of deletion. The completeness bit lets the model-facing consumer preserve its last-good catalog until a full observation succeeds.
+- **Keep `invalidateProvider(provider)` public** — rejected because it exposes a registry mutation method and makes callers resupply an identity the registry already owns. The factory-issued closure binds invalidation to one registration and becomes inert on disposal, so observers need neither registry access nor provider identity.
+- **Extract a generic Cordis file-watching service now** — deferred until another consumer establishes the reusable service contract. The local provider marks its Chokidar and missing-root observation boundary for that extraction; skill-path filtering and the call to the provider's invalidation closure remain skill-specific.
+
+## Consequences
+
+- New, deleted, and renamed local skills become visible at model-step boundaries without restarting the agent, including when the skills root did not exist at startup.
+- The TUI's `/skill:` completions converge on the same complete catalog without blocking each keystroke on discovery; an open slash-name draft refreshes when the catalog arrives.
+- Catalog messages are append-only, logged, whole-list snapshots. They preserve earlier reusable tokens; replacements retire stale names explicitly, at token cost proportional to the current catalog on each actual digest change.
+- Body-only edits produce no catalog message. A subsequent tool call sees current content, while prior tool results remain an accurate record of what the model previously loaded.
+- Missing-root polling and Chokidar add one maintained runtime dependency, host watcher resources, bounded detection latency, and deployment tunables. The bounded project set and teardown contract contain those costs.
+- Remote or future mutable providers retain their own registration-scoped invalidation closure and call it from their observation mechanism; the registry does not impose a universal watcher or TTL.
@@ -0,0 +1,48 @@
+# Agent Note: Skill 目录热刷新
+
+Status: implemented
+
+[English](2026-07-27-skill-catalog-hot-refresh.md) | 中文
+
+## 问题
+
+skill（技能）摘要是模型的路由输入，但本地 skill 可在会话启动后新增、消失或重命名。IDE、Git 操作、shell 命令和其他进程都可以修改 `.agents/skills`，而不经过 harness 文件系统工具。仅在启动时构建目录，会让模型无法获知新 skill，并且仍能调用已删除的名称。反之，如果把每次指令正文编辑都视为目录修订，就会让渐进式加载与不必要的提示词频繁变化耦合。
+
+从观察方来看，文件系统更新也不是原子完成的。编辑器或 Git 操作可能会短暂移除文件，受监视的根目录在启动时可能不存在，发现也可能暂时失败。把这些中间观察结果发布为权威空目录，比保留最后一个完整视图更糟。
+
+## 决策
+
+skill 服务将目录成员关系与指令正文加载分离。`ctx.skills.snapshot()` 返回摘要及一个完整性位。`ctx.skills.registerProvider(factory)` 会向同步工厂提供一项注册作用域内的 `{ signal, invalidate }` 控制能力：`invalidate()` 只会将该精确活动注册标记为脏，并丢弃已完成目录缓存；注册失败或释放时，信号会中止。提供方返回的数组是完整发现的简写形式；显式的不完整观测可以保留可读候选项供直接加载，但不能缓存，也不能作为面向模型消费方的权威结果。在发现期间，如果提供方或运行时 generation 发生变化，系统会重试一次；如果这次重试也被后续修订取代，则最新候选项会作为不完整且不缓存的观测返回。资源释放或替换后的延迟失效操作不会执行任何操作，因为该能力已被撤销。
+
+`@deepseek-ai/dsh-skill-local` 直接依赖 Chokidar，并观察与目录相关的宿主路径。已有根目录会监视其直属 skill bundle 目录、平铺的 Markdown 条目和直属 `SKILL.md` 条目文件。新增、移除和目录变更会使成员关系失效；文件变更还支持刷新 frontmatter 中的 `name` 和 `description`。bundle 内更深层的资源文件会被忽略。同一微任务批次中的事件会合并为一次失效。项目 watcher 使用有界集合，并按最久未观察顺序淘汰。
+
+系统从缺失根目录最近的现有祖先开始，使用 `fs.watchFile` 每次跟进一层缺失路径片段；真实根目录出现后，再交给 Chokidar。每次发现操作都会在扫描前重新探测所保留的根目录／祖先模式。即使子项移除在根目录 `unlinkDir` 事件之前就触发失效并发布权威空目录，或者该事件根本没有到达，这项独立探测也会在删除后重新建立祖先观察。Chokidar 配置公开原生事件或轮询模式、写入稳定性、轮询间隔、符号链接跟随选项和项目 watcher 容量。第一方 `write` 和 `edit` 工具观察会同步使相关提供方失效，因此下一个模型步骤无需等待宿主事件投递，就能看到自身改动。watcher 启动或运行失败会被记录并触发重试；发现过程仍会返回可读候选项供直接加载，但会报告不完整观测。资源销毁会关闭 watcher，并忽略延迟回调。
+
+`@deepseek-ai/dsh-tool-skill` 在 `agent/step` 首次观察到非空完整目录时，将该目录注入为一条持久且带来源的 `user/message`。每次 `agent/step`，它都会应用 `skill` 工具的精确可见性，对 `<available_skills>` 标签之间精确渲染的文本计算哈希，并从后向前扫描只读会话事件且不复制，以查找该插件发布的最新一条可识别且仍可见的目录。digest 变化时，插件通过 `agent.inject()` 追加一份持久的完整替换目录；所有 skill 消失时，也会追加显式空目录。如果没有目录仍然可见，但历史事件中存在可识别目录，则说明压缩（compaction）已将其遮蔽，下一次完整观察会重新建立当前目录，包括空 tombstone。如果当前目录为空且历史上从未发布目录，则不发送任何内容；不完整快照则保留最后一次完整的模型视图。反向扫描通常在最新且仍可见的目录处停止；当压缩遮蔽所有目录时，它会以一次 O(session-events) 扫描的成本确认这一事实。
+
+TUI 将同一失效通知作为界面状态而非会话历史来消费。`skills/change` 不携带 diff；TUI 会为活动会话的 cwd 重新获取 `snapshot()`，仅应用最新的完整结果，并在观测不完整时保留先前命令。完整的空结果会清除陈旧补全项。pi-tui 在其提供方被替换时会关闭自动补全，因此如果目录在用户输入斜杠命令名称期间到达，还会触发一次仅用于更新建议的当前草稿重查。
+
+指令正文继续采用渐进式披露。每次调用 `skill(name)` 时，系统都会要求提供方重新读取并解析当前文件；不存在正文缓存、哈希、修订或主动通知。先前记录的工具结果保持不变。如果加载后的 frontmatter 名称不再匹配所选候选项，注册表会拒绝这个陈旧名称，并使该提供方失效，以便后续目录观察发布新名称。
+
+## 验证
+
+注册表测试固定了注册作用域内的失效、能力撤销、信号中止、监听器失败隔离、不完整候选项、有界 generation 重试和陈旧名称拒绝。local-provider 测试覆盖 bundle 与平铺文件的创建、移除和重命名，以及根目录创建／删除／重建（包括未观测到根目录 `unlinkDir` 事件的情形）、描述变更、仅正文编辑、第一方观察、符号链接、轮询选项、候选项仍可加载的持续 watcher 失败、事件合并、项目 watcher 容量上限、资源销毁和暂时读取。工具测试固定了完整替换消息、空 tombstone、仅修改正文时 digest 稳定、不完整状态保留、可见性和恢复元数据。TUI 测试固定了上一份完整结果保留、权威空结果清除、刷新时以最新结果为准、资源销毁和已打开斜杠草稿的竞态；一项使用真实 Loader/PTY 的 smoke 测试会在启动后添加本地 skill，并观察其补全项出现，而无需重启。一个无密钥、装配完成的 agent-spine 快照测试通过面向模型的文件系统工具创建项目 skill，观察下一次请求中的替换目录，并使用真实 `skill` 工具加载当前正文。
+
+## 考虑过的替代方案
+
+- **将实时目录放入 World State**：不予采纳，因为目录替换是模型可见的会话输入，必须能够从事件日志重建。持久注入历史已经提供回放、恢复、fork 和压缩语义，无需再引入一套可变状态层。
+- **只依赖 `fs/observed`**：不予采纳，因为 IDE、Git、shell 命令和外部进程都不会经过该 seam。该事件仍作为第一方工具的低延迟快速路径，宿主监视则补齐覆盖。
+- **为每个 `SKILL.md` 正文计算哈希或版本**：不予采纳，因为模型最初只看到名称和描述，提供方已经在每次工具调用时重新读取正文。正文修订会产生目录流量，却不会改变路由，也不足以成为改写历史工具结果的理由。
+- **监视每个 bundle 资源**：不予采纳，因为参考资料、脚本和产物都是按需加载的，不影响类别列表。宽泛的递归监视会增加失效、描述符压力和平台差异，却不能改善路由。
+- **将部分发现或失败发现发布为新目录**：不予采纳，因为暂时读取失败不能证明文件已删除。完整性位让面向模型的消费方保留最后一次完整目录，直到完整观察成功。
+- **保留公开的 `invalidateProvider(provider)`**：不予采纳，因为这会公开一项注册表变更方法，并要求调用方重复提供注册表已经持有的身份。发给工厂的闭包会将失效绑定到单个注册，并在释放后失去作用，因此观察方既不需要访问注册表，也不需要提供方身份。
+- **现在提取通用 Cordis 文件监视服务**：暂缓，直到另一个消费方确立可复用的服务契约。本地提供方标出了其 Chokidar 和缺失根目录观测边界，以便后续提取；skill 路径过滤以及对提供方失效闭包的调用仍属于 skill 专用逻辑。
+
+## 影响
+
+- 新增、删除和重命名的本地 skill 会在模型步骤边界变得可见，无需重启 agent（智能体），即使 skill 根目录在启动时不存在也一样。
+- TUI 的 `/skill:` 补全会收敛到同一份完整目录，而不会让每次按键都阻塞于发现；打开的斜杠命令名称草稿会在目录到达时刷新。
+- 目录消息采用仅追加、日志记录和全量列表快照。它们会保留较早的可重用 token；替换目录会显式停用陈旧名称，每次 digest 实际变化时，token 成本与当前目录大小成正比。
+- 仅修改正文不会产生目录消息。后续工具调用会看到当前内容，而先前工具结果仍准确记录模型之前加载的内容。
+- 缺失根目录轮询和 Chokidar 引入一个有人维护的运行时依赖、宿主 watcher 资源、有界检测延迟和部署可调参数。有界项目集合与资源销毁契约会限制这些成本。
+- 远程或未来的可变提供方会保留各自注册作用域内的失效闭包，并通过自身观察机制调用它；注册表不会强制采用通用 watcher 或 TTL。
@@ -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-tmux-location-context.md
+2026-07-27-tmux-location-context.md: bac5861f7f55c259de04d153115f164d90c415ad
+2026-07-27-tmux-location-context.zh.md: 03cd722381c45604f7aae8f3d0a9f9fbb8b12bb5
@@ -0,0 +1,61 @@
+# Agent Note: tmux-location context
+
+Status: implemented
+
+English | [中文](2026-07-27-tmux-location-context.zh.md)
+
+## Problem
+
+An agent running inside tmux has no way to tell the model where it is: which session, window, and pane the process occupies, and how the window is laid out. A user directing several panes wants the model to orient itself to its own location so instructions like "the pane below" or "this window" resolve. The location must reach the model as durable, reconstructable context, not a system-prompt value rewritten in place, and must cost nothing when the location has not changed.
+
+tmux exposes this without a daemon: `$TMUX_PANE` names the process's pane, and `tmux display-message -t "$TMUX_PANE" -p '<format>'` prints any pane/window/session field. The open question was how to observe it — pull on each preparation, or push from a tmux hook — and how to avoid a per-step token cost and hidden process-local state.
+
+## Decision
+
+`@deepseek-ai/dsh-tmux-context` is an opt-in function plugin in `packages/context/tmux-context/`, alongside the other bounded request-context enrichments that define neither a tool nor a service. Shipped examples do not mount it because tmux-location disclosure and its token cost are deployment policy.
+
+**Pull on the first step of each turn, not a tmux push.** The plugin prepends an `agent/step` listener and acts only when `step === 1`. A pull model needs no background process, no hook installation in the user's tmux, and no teardown; it re-reads current state each turn so a moved, renamed, or re-laid-out pane is picked up naturally. Gating on the first step makes the reading per-turn: a location is stable within a turn, and re-querying every step would add cost without new information. A pane moved mid-turn is reflected on the next turn, which is the accepted tradeoff for the simpler design.
+
+**Read through the `ctx.bash` seam, never raw `child_process`.** The listener runs the tmux/`ps` read commands through `ctx.bash`, so the deployment's sandbox and policy apply and the plugin owns no subprocess code. Absent `ctx.bash`, absent tmux env, a wrong field count, or an empty pane id each make the attempt a no-op, matching how `workspace-context` no-ops without an `fs` provider.
+
+**Detect a real pane by tty, not by `$TMUX_PANE` alone.** `$TMUX_PANE` is inherited: a terminal launched from a tmux shell (a VS Code integrated terminal, a desktop launcher) carries `$TMUX`/`$TMUX_PANE` from that ancestor even though the process does not live in that pane, which otherwise injects a stale, wrong location. The command resolves this process's controlling terminal with `ps -o tty= -p <pid>` (the agent's own pid, passed in-process) and compares it to the pane's `#{pane_tty}`; fields are emitted only on a match. A genuine pane owns this process's tty; an inherited environment names some other pane's tty and reads as "not in tmux". Checking `$TMUX` instead does not help — it is inherited identically. This is the definitive discriminator and needs no allowlist of terminal emulators.
+
+**Own location and layout only.** The queried fields are session name, window index/name, pane index/id, window/pane active flags, and `window_layout`. Pane and window pixel sizes are excluded (layout tree conveys structure; sizes are noisy and change on every terminal resize). Sibling-pane contents are never captured (`capture-pane`), keeping the reading small and avoiding scraping unrelated, possibly sensitive, output.
+
+**Inject only on change, with optional interval floor.** When due, the plugin calls `agent.inject()` for one `user/message` with source `{ kind: 'plugin', plugin: 'tmux-context' }`. Change suppression compares the rendered state block (everything after the turn preamble line) against the latest injection of this source, found by scanning raw durable session events — so the schedule survives compaction and process resume without a process-local cache. The optional `refreshIntervalMs` (manually validated as a non-negative safe integer at plugin load) additionally suppresses injections within that window of the latest one.
+
+### Text
+
+```text
+tmux location (turn <turn>):
+session <session>, window <index> "<name>", pane <index> <pane-id>
+window active=<0|1>, pane active=<0|1>, layout <window-layout>
+```
+
+The turn preamble is the volatile first line; the two-line state block below it is the unit compared for change suppression, so re-injection is driven by tmux state, not loop position.
+
+### Durability and request reconstruction
+
+Each reading is a normal surface node until compaction shadows it; the plugin contributes nothing to system-prompt assembly and `request/header` carries no tmux-context text. The reading records a preparation attempt, not a committed step: because the prepended listener runs first, its append may remain when a later `agent/step` listener cancels or fails the attempt, and the append-only log performs no rollback.
+
+The published `./invariant` companion registers no runtime check: a reading is a per-turn snapshot of external tmux state, so the session holds no cross-event relation to validate, and scheduling and format stay pinned by the package's pipeline tests.
+
+## Consequences
+
+An agent booted inside tmux now receives its own session/window/pane location and window layout as durable, source-attributed context, updated per turn when the location changes. Deployments opt in through cordis.yml; the default spine and shipped examples stay silent. Outside a real tmux pane — including a terminal that merely inherited `$TMUX`/`$TMUX_PANE` — or without a `ctx.bash` executor, the plugin is inert with no error, so composing it is safe everywhere. Because the reading is one durable `user/message`, it survives compaction as ordinary history, contributes nothing to system-prompt assembly or request headers, and costs at most one two-line message per changed turn. The pull model adds one `tmux display-message` subprocess (through the sandboxed bash seam) on the first step of each turn that is due. The optional interval floor is checked before the query and so suppresses both; an unchanged location is detected only by comparing the returned state, so it suppresses the injection while still paying for the query.
+
+## Testing
+
+Unit tests pin: first-step injection and source/surface metadata; the `$TMUX_PANE`-keyed command including its `#{pane_tty}`-vs-`ps -o tty=` guard; step-gating; change suppression across turns and re-injection on a moved pane; positive-interval suppression and threshold; every no-op path (no bash, nonzero exit, wrong field count, empty pane id, aborted signal, and a contained executor rejection from either `resolve()` or `run()` that warns instead of failing the turn); prepended ordering before ordinary `agent/step` listeners; resilience to a corrupt prior reading (non-text block, single-line text); and config rejection of negative and non-integer intervals. Per-file coverage is 100%.
+
+## Alternatives considered
+
+- **Push from a tmux hook / background watcher** — rejected: requires installing hooks in the user's tmux and a background process with teardown, to gain mid-step freshness that per-turn context does not need.
+- **Run every step** — rejected: location is stable within a turn; re-querying adds token cost without new information. Gating on `step === 1` yields per-turn readings.
+- **Raw `child_process`** — rejected: bypasses the sandbox/policy seam and hand-rolls subprocess code the `ctx.bash` executor already owns.
+- **Include pane/window pixel sizes** — rejected: sizes churn on every resize and add noise; the layout tree already conveys structure.
+- **Scrape sibling panes with `capture-pane`** — rejected: large, noisy, and privacy-sensitive; out of scope for "own location".
+- **Dynamic system-prompt section** — rejected: replacing a value erases the earlier readings behind prior reasoning and is not reconstructable; one durable attributed message records each location where it became visible.
+- **Trust `$TMUX_PANE` (or `$TMUX`) presence** — rejected: both are inherited by terminals launched from a tmux shell (VS Code integrated terminal), so a non-pane process injects a stale location. The pane `#{pane_tty}` vs. this process's controlling tty is the definitive check.
+- **Denylist known terminal emulators (e.g. `TERM_PROGRAM=vscode`)** — rejected: a partial, ever-growing list that still misses other launchers; the tty match is exact and launcher-agnostic.
+- **A runtime invariant validating each reading's turn, position, and format** — shipped initially, then removed: it re-derived the producer's own scheduling from the log and asserted a regex over text the same package had just rendered, so it restated `apply()` rather than checking an independent relation. Every failure it could report required an edit to this package, which its pipeline tests already catch. Reintroduce a companion check only for a relation the plugin does not itself compute — for example if readings gain cross-turn ordering or enclosure obligations that another package can violate.
@@ -0,0 +1,61 @@
+# Agent Note：tmux 位置上下文
+
+Status: implemented
+
+[English](2026-07-27-tmux-location-context.md) | 中文
+
+## 问题
+
+运行在 tmux 内的 agent 无法告诉模型自己身在何处：进程占据哪个 session、window、pane，以及 window 如何布局。当用户操作多个 pane 时，希望模型能对自身位置有所定位，从而让"下方的 pane""这个 window"之类的指令得以解析。位置必须以持久、可重建的上下文形式送达模型，而非在原地被改写的系统提示值，并且当位置未变化时不产生任何成本。
+
+tmux 无需守护进程即可暴露这些信息：`$TMUX_PANE` 标识进程所在 pane，`tmux display-message -t "$TMUX_PANE" -p '<format>'` 可打印任意 pane/window/session 字段。待决问题在于如何观测——在每次准备时拉取，还是由 tmux hook 推送——以及如何避免逐步骤 token 成本与隐藏的进程内状态。
+
+## 决策
+
+`@deepseek-ai/dsh-tmux-context` 是位于 `packages/context/tmux-context/` 的可选启用型函数插件，与其他既不定义工具也不定义服务的有界请求上下文增强并列。随附示例不挂载它，因为 tmux 位置披露及其 token 成本属于部署策略。
+
+**在每轮的第一个 step 拉取，而非 tmux 推送。** 插件前置注册一个 `agent/step` 监听器，仅在 `step === 1` 时动作。拉取模型无需后台进程、无需在用户的 tmux 中安装 hook、也无需清理；它每轮重新读取当前状态，因此被移动、改名或重新布局的 pane 都会被自然感知。以第一个 step 为门槛使读数按轮次生成：位置在一轮内是稳定的，逐步骤重复查询只会增加成本而不带来新信息。轮次中途移动的 pane 会在下一轮反映，这是换取更简单设计所接受的取舍。
+
+**通过 `ctx.bash` seam 读取，绝不用裸 `child_process`。** 监听器通过 `ctx.bash` 运行 tmux／`ps` 只读命令，从而应用部署方的沙箱与策略，插件不拥有任何子进程代码。`ctx.bash` 缺失、tmux 环境缺失、字段数不符或 pane id 为空，都会使本次尝试成为空操作，与 `workspace-context` 在无 `fs` provider 时的空操作一致。
+
+**以 tty 判定真实 pane，而非仅凭 `$TMUX_PANE`。** `$TMUX_PANE` 会被继承：从 tmux shell 启动的终端（VS Code 集成终端、桌面启动器）会从该祖先进程带上 `$TMUX`／`$TMUX_PANE`，即使进程并不位于那个 pane 中，否则就会注入一个陈旧且错误的位置。命令用 `ps -o tty= -p <pid>`（在进程内传入 agent 自身的 pid）解析本进程的控制终端，并与 pane 的 `#{pane_tty}` 比较；只有匹配时才输出字段。真正的 pane 拥有本进程的 tty；继承而来的环境指向的是另一个 pane 的 tty，因而被读作"不在 tmux 中"。改为检查 `$TMUX` 也无济于事——它同样会被继承。这是决定性的判别依据，且无需维护终端模拟器名单。
+
+**仅自身位置与布局。** 查询字段为 session name、window index/name、pane index/id、window/pane 活动标志以及 `window_layout`。省略 pane 与 window 像素尺寸（布局树已传达结构；尺寸嘈杂且每次终端缩放都会变化）。从不采集相邻 pane 内容（`capture-pane`），使读数保持小巧，并避免抓取无关、可能敏感的输出。
+
+**仅在变化时注入，并可选间隔下限。** 需要时，插件调用 `agent.inject()` 注入一条来源为 `{ kind: 'plugin', plugin: 'tmux-context' }` 的 `user/message`。变化抑制将渲染出的状态块（轮次前缀行之后的全部内容）与该来源的最近一次注入比较，后者通过扫描原始持久会话事件获得——因此调度可跨压缩与进程恢复存续，无需进程内缓存。可选的 `refreshIntervalMs`（在插件加载时手动校验为非负安全整数）会额外抑制距最近一次注入不足该窗口的注入。
+
+### 文本
+
+```text
+tmux location (turn <turn>):
+session <session>, window <index> "<name>", pane <index> <pane-id>
+window active=<0|1>, pane active=<0|1>, layout <window-layout>
+```
+
+轮次前缀是易变的首行；其下的两行状态块才是变化抑制所比较的单元，因此重新注入由 tmux 状态驱动，而非循环位置。
+
+### 持久性与请求重建
+
+每条读数在被压缩遮蔽前都是普通表层节点；插件对系统提示装配毫无贡献，`request/header` 也不携带任何 tmux-context 文本。读数记录的是一次准备尝试，而非已提交的 step：由于前置监听器最先运行，当后续 `agent/step` 监听器取消或失败时其追加可能仍会保留，只追加的日志不做回滚。
+
+发布的 `./invariant` 伴生插件不注册任何运行时检查：读数是外部 tmux 状态的按轮快照，会话中不存在需要校验的跨事件关系，调度与格式由本包的管线测试固定。
+
+## 后果
+
+启动于 tmux 内的 agent 现在会以持久、带来源标记的上下文收到自身的 session/window/pane 位置及 window 布局，并在位置变化时按轮次更新。部署方通过 cordis.yml 选择启用；默认 spine 与随附示例保持沉默。在真实 tmux pane 之外——包括仅继承了 `$TMUX`／`$TMUX_PANE` 的终端——或没有 `ctx.bash` 执行器时，插件保持惰性且不报错，因此在任何地方组合它都安全。由于读数是一条持久的 `user/message`，它作为普通历史经受压缩，对系统提示装配与请求头毫无贡献，且每个发生变化的轮次至多花费一条两行消息。拉取模型在每个到期轮次的第一个 step 增加一次 `tmux display-message` 子进程（经沙箱化的 bash seam）。可选的间隔下限在查询之前检查，因此同时抑制查询与注入；而位置未变化只能通过比较查询返回的状态得知，因此它只抑制注入，查询开销仍会付出。
+
+## 测试
+
+单元测试固定了：首个 step 的注入及来源/表层元数据；以 `$TMUX_PANE` 为键的命令（含其 `#{pane_tty}` 与 `ps -o tty=` 的比对守卫）；step 门槛；跨轮次的变化抑制与 pane 移动时的重新注入；正间隔抑制与阈值；每条空操作路径（无 bash、非零退出、字段数不符、pane id 为空、信号已取消，以及 `resolve()` 或 `run()` 抛出的执行器拒绝被兜住并记录警告而非使该轮失败）；前置排序先于普通 `agent/step` 监听器；对损坏的历史读数（非文本块、单行文本）的容错；以及配置对负值与非整数间隔的拒绝。逐文件覆盖率为 100%。
+
+## 考虑过的替代方案
+
+- **由 tmux hook / 后台监视器推送**——否决：需要在用户的 tmux 中安装 hook，并引入带清理的后台进程，只为换取按轮次上下文并不需要的步内新鲜度。
+- **每个 step 都运行**——否决：位置在一轮内稳定；重复查询只增加 token 成本而无新信息。以 `step === 1` 为门槛得到按轮次读数。
+- **裸 `child_process`**——否决：绕过沙箱/策略 seam，并手写 `ctx.bash` 执行器已拥有的子进程代码。
+- **包含 pane/window 像素尺寸**——否决：尺寸每次缩放都变动、徒增噪声；布局树已传达结构。
+- **用 `capture-pane` 抓取相邻 pane**——否决：庞大、嘈杂且涉及隐私；超出"自身位置"范围。
+- **动态系统提示区块**——否决：替换某个值会抹去支撑先前推理的历史读数且不可重建；单条持久且带来源的消息在每个位置变得可见时予以记录。
+- **信任 `$TMUX_PANE`（或 `$TMUX`）存在即可**——否决：两者都会被从 tmux shell 启动的终端（VS Code 集成终端）继承，于是非 pane 进程会注入陈旧位置。pane 的 `#{pane_tty}` 与本进程控制终端的比对才是决定性检查。
+- **对已知终端模拟器设黑名单（如 `TERM_PROGRAM=vscode`）**——否决：名单不完整且会不断增长，仍会漏掉其他启动器；tty 比对精确且与启动器无关。
+- **用运行时 invariant 校验每条读数的轮次、位置与格式**——最初随包发布，随后移除：它从日志中重新推导生产者自身的调度，并对同一个包刚刚渲染出的文本断言正则，因此只是重述 `apply()`，而非检查一条独立关系。它能报出的每种失败都必须先修改本包，而这些本包的管线测试已经覆盖。仅当出现插件自身并不计算的关系时才重新引入伴生检查——例如读数将来具备可被其他包破坏的跨轮次顺序或包裹义务。
@@ -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-trajectory-inspection-ledger.md
+2026-07-27-trajectory-inspection-ledger.md: 8c2a7c42b7898776de5d42459b09c0fb1737ec0b
+2026-07-27-trajectory-inspection-ledger.zh.md: 6c5733046dc2cfd3fd2bd005f4cf5c2d2bd110af
@@ -0,0 +1,43 @@
+# Agent Note: Trajectory inspection ledger
+
+Status: implemented
+
+English | [中文](2026-07-27-trajectory-inspection-ledger.zh.md)
+
+## Problem
+
+Trajectory has to make prose, machine payloads, token usage, timing, and nested tool activity readable in the same viewport. The earlier stacked Turn and Step cards preserved hierarchy but spent too much vertical space on repeated chrome, while a completely flat table would erase the causal structure that makes a trajectory useful. Role colors also risked borrowing success and warning semantics, which made visual decoration indistinguishable from runtime state.
+
+## Decision
+
+**Render a compact, turn-aware event ledger with a local record inspector, using the existing DeepSeek design system.**
+
+- The ledger keeps session events in sequence within rewind-delimited branches. Turn boundaries use a slightly heavier rule, the raw Turn id, and a continuous left rail; Request boundaries appear as small points integrated into that structure and use one chronological numbering space across ordinary and compaction requests.
+- Event kind and content form the two stable columns. Role tags align toward the content, nested subtools receive a small indentation, and CSS truncation preserves the available preview width. Token usage and duration stay in the inspector.
+- Product prose uses the existing sans stack. Turn ids, token counts, durations, tool calls, raw payloads, and other machine data use the existing code stack.
+- Existing theme tokens own both light and dark rendering. Neutral borders and surfaces form the structure; distinct low-emphasis role hues support scanning without carrying success or failure meaning, while business blue identifies selection, links, and focus.
+- The client runtime exposes a read-only history source independent from Session and SessionManager. Each activated source owns its raw entries, paging, live gap repair, and reconnect rebuild; the ordinary conversation snapshot remains the folded Chat projection. Trajectory subscribes to that source, exhausts its paging only while mounted, and lazily derives its event order, context lineage, schema index, and Requests instead of imposing those structures on every conversation consumer.
+- Ordinary generation and compaction calls form one chronological Request projection, distinguished by purpose rather than separate collections. Effective prompt state and its change ride the Request that introduced them; compaction and prompt changes are not independent inspection entities. Complete history makes global Request numbering and cumulative usage session-wide rather than tail-window-relative.
+- Call schemas come from the active recorded Request header. Keyless snapshot fixtures deliberately replace that catalog with the non-array `{{tools}}` token, which the durable inspection boundary treats as unavailable instead of attempting to project or fabricate schemas.
+- Selecting a record or Request opens an inspector inside Trajectory. Tabs and Summary sections follow the selected entity: Markdown messages expose rendered, source, provenance, and hierarchy views; tools add JSON payload/result and schema views; Requests add options, usage, timing, and result navigation. Images render as media rather than serialized data.
+- Turn folding removes all rows after its first record and replaces them with a compact step/tool-call count; Assistant folding applies the same interaction to its tool-call descendants. Global controls fold or expand both levels.
+- The separate Waterfall tab is removed. A fixed Overview above the ledger projects every record with known `startedAt` onto three semantic timing lanes using its own duration. Dragging left or right commits an inclusive interval filter: any record whose active interval overlaps either boundary remains visible, records without known timing leave the focused ledger, and clearing the selection restores the full branch. The Overview keeps the full time domain while focused so the selection can be resized or cleared without losing orientation.
+- This local inspector remains independent from the conversation-wide Chat details column. At narrow widths it overlays the ledger and remains dismissible by keyboard or pointer.
+
+## Alternatives considered
+
+**Copy Vite DevTools fonts, colors, glass surfaces, or component shapes.** Rejected: those choices express a different product identity. The implementation only adopts the transferable method: neutral structure, semantic accents, machine-data typography, dense scanning, and shadows reserved for floating layers.
+
+**Keep one card per Turn and Step.** Rejected: repeated card chrome reduced the number of visible records and made cross-step comparison slower.
+
+**Flatten every record without Turn or Request boundaries.** Rejected: a trajectory is not merely a log stream; those boundaries preserve the causal structure without consuming dedicated rows.
+
+**Reuse the global Chat details column.** Rejected: it would couple local inspection to conversation navigation and make a row click unexpectedly change another view's state.
+
+**Keep timing in a separate Waterfall tab.** Rejected: the placeholder summarized node counts rather than record timing and forced users to switch away from the rows they wanted to focus. A full-domain Overview keeps timing and filtered records in one visual context.
+
+**Change global theme tokens to match the reference.** Rejected: the existing theme already provides paired light and dark semantic layers, and a local redesign does not justify changing unrelated surfaces.
+
+## Consequences
+
+Trajectory shows more useful records per viewport while retaining Turn and Request orientation. Context rewrites and compactions remain inline with their surrounding history, while a rewind begins a successor branch that inherits only the retained prefix. The main ledger omits token usage and duration so content receives the available width; the local inspector exposes those facts together with full payloads, provenance, schemas, and request timing. The Overview uses recorded start/duration facts without fabricating live elapsed time, and its inclusive focus behavior matches the interaction users already know from Chrome DevTools Network. Focused component tests pin projection, folding, record and interval selection, entity-specific tabs, and running/error semantics; the assembled Web snapshot pins the ledger, Overview, and inspector through the real client composition.
@@ -0,0 +1,43 @@
+# Agent Note：轨迹检查记录表
+
+Status: implemented
+
+[English](2026-07-27-trajectory-inspection-ledger.md) | 中文
+
+## 问题
+
+轨迹视图需要在同一视口内清晰呈现正文、机器载荷、token 用量、计时数据和嵌套工具活动。此前堆叠式的轮次与步骤卡片虽然保留了层级，却在重复界面框架上耗费了太多垂直空间；完全扁平化的表格又会抹去因果结构，而这种结构正是轨迹视图的价值所在。角色配色还可能借用成功与警告语义，使视觉装饰与运行时状态无法区分。
+
+## 决策
+
+**使用现有 DeepSeek 设计系统，渲染保留轮次结构的紧凑事件记录表，并提供局部记录检查器。**
+
+- 记录表在以 `rewind` 划分的分支内按会话事件顺序展示。轮次边界由稍粗的分割线、原始轮次 id 和连续的左侧竖线表示；请求边界以融入该结构的小圆点表示，普通请求与压缩（compaction）请求在整个时间序列中共用一套编号。
+- 事件类型与内容构成两个稳定列。角色标签朝内容侧对齐，嵌套子工具略微缩进，内容预览使用 CSS 截断以适应可用宽度。token 用量和耗时留在检查器中。
+- 产品正文使用现有无衬线字体栈。轮次 id、token 数、耗时、工具调用、原始载荷和其他机器数据使用现有代码字体栈。
+- 现有主题 token 同时负责亮色和暗色渲染。中性边框与表面构成整体结构；区分度较低的角色色帮助扫读而不表达成功或失败语义，业务蓝色则标识选择状态、链接和焦点。
+- 客户端 runtime 提供独立于 Session 和 SessionManager 的只读历史数据源。每个已激活的数据源自行拥有原始条目、分页、实时缺口修复和重连重建；普通会话快照仍然只是 Chat 所需的折叠投影。Trajectory 订阅该数据源，仅在挂载期间补齐全部历史，并按需派生事件顺序、上下文谱系、schema 索引和请求，避免让所有会话消费者承担这些结构。
+- 普通生成调用与压缩调用形成一条按时间排序的请求投影，以 purpose 区分而不是放入不同集合。生效的提示词状态及其变化附着在引入它们的请求上；压缩和提示词变化都不是独立检查实体。完整历史使全局请求编号和累计用量以整个会话为范围，而不是相对于末尾窗口。
+- 调用 schema 来自当前生效且已记录的请求头。无密钥快照 fixture（测试前置数据）有意将该目录替换为非数组 token `{{tools}}`，持久化检查边界会将其视为不可用，而不是尝试投影或虚构 schema。
+- 选择记录或请求后，轨迹视图内部会打开检查器，其标签页和概览区域随实体类型变化：Markdown 消息提供渲染、源码、来源和层级视图；工具提供 JSON 载荷／结果和 schema 视图；请求提供选项、用量、计时和结果跳转。图片以媒体形式渲染，而不是显示为序列化数据。
+- 折叠轮次时保留其第一条记录，将后续行替换为紧凑的步骤和工具调用数量；折叠助手时对其工具调用后代应用相同交互。全局控件可以分别折叠或展开这两个层级。
+- 移除独立的 waterfall（瀑布式事件）标签页。固定在记录表上方的 Overview 区域将所有 `startedAt` 已知的记录按各自耗时投影到三条语义计时轨道。向左或向右拖动会提交包含边界的区间筛选：任何活动区间与所选区间相交的记录都会保留，计时未知的记录会从聚焦后的记录表中移除，清除选择则恢复完整分支。聚焦后，Overview 区域仍保留完整时间范围，以便在不失去方位的情况下调整或清除选择。
+- 此局部检查器与会话级 Chat 详情栏相互独立。在窄屏下，检查器会覆盖记录表，并且仍可通过键盘或指针关闭。
+
+## 曾考虑的替代方案
+
+**照搬 Vite DevTools 的字体、颜色、玻璃表面或组件形状。** 不予采纳：这些选择表达的是另一种产品身份。实现仅吸收可迁移的方法，即中性结构、语义强调色、机器数据排版、紧凑扫读，以及只为浮层保留阴影。
+
+**每个轮次和步骤保留一张卡片。** 不予采纳：重复的卡片框架减少了可见记录数量，并降低了跨步骤比较的速度。
+
+**不使用轮次或请求边界，将所有记录完全扁平化。** 不予采纳：轨迹并非普通日志流；这些边界无需占用独立行，也能保留因果结构。
+
+**复用全局 Chat 详情栏。** 不予采纳：这会让局部检查与会话导航耦合，还会使行点击意外改变另一个视图的状态。
+
+**将计时保留在独立的 waterfall 标签页中。** 不予采纳：占位实现汇总的是节点数而非记录计时，并迫使用户离开想要聚焦的记录。保留完整时间范围的 Overview 区域让计时和筛选后的记录处于同一视觉上下文中。
+
+**修改全局主题 token 以匹配参考设计。** 不予采纳：现有主题已经提供配对的亮色与暗色语义层，局部重新设计不足以成为修改无关表面的理由。
+
+## 后果
+
+轨迹视图在保留轮次与请求定位的同时，每个视口可以显示更多有效记录。上下文 `rewrite` 与压缩保持在周边历史中的原始位置，`rewind` 则建立仅继承保留前缀的后继分支。主记录表省略 token 用量和耗时，让内容获得可用宽度；局部检查器展示这些数据以及完整载荷、来源、schema 和请求计时。Overview 区域使用记录的开始时间与耗时数据，而不虚构实时流逝时间，其包含边界的聚焦行为与用户熟悉的 Chrome DevTools Network 交互一致。针对性组件测试锁定投影、折叠、记录与区间选择、实体特定标签页和运行／错误语义；组装后的 Web 快照则通过真实客户端组合锁定记录表、Overview 区域与检查器。
@@ -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/2026-07-28-skill-invocation-policy.md
+2026-07-28-skill-invocation-policy.md: f74b0bcfddb1699c48279b4d8b153cabf764b140
+2026-07-28-skill-invocation-policy.zh.md: 1a7117a382be224c5371964dd4ad3e916d4e0917
@@ -0,0 +1,50 @@
+# Agent Note: Independent model and user skill invocation policy
+
+Status: implemented
+
+English | [中文](2026-07-28-skill-invocation-policy.zh.md)
+
+## Problem
+
+The skill registry originally treated discovery as a model catalog: `ctx.skills.list()` removed model-disabled skills, while `ctx.skills.get()` remained an unfiltered trusted loader. That was enough for model-initiated loading, but it could not represent Claude-compatible skills that are advertised only to a person, only to a model, to both, or to neither. The TUI compounded the mismatch by deriving user autocomplete from the model-filtered list and allowing every exact name through `get()`.
+
+The local parser also exposed an internal camel-case spelling as frontmatter. Supporting the established negative `disable-model-invocation` and positive `user-invocable` fields requires a durable, symmetric domain representation without turning every possible YAML key into an untyped cross-package contract.
+
+## Decision
+
+`SkillSummary` carries a required typed `invocation: SkillInvocationPolicy` object whose `modelInvocable: boolean` and `userInvocable: boolean` fields are positive and symmetric. Omission exists only at explicit input seams: a runtime `SkillRegistration` without a policy and local frontmatter without either invocation key resolve to `{ modelInvocable: true, userInvocable: true }` before producing candidates or definitions. Future frontmatter keys remain outside the domain model until a consumer and enforcement contract exist; the local provider still parses frontmatter as an open `Record<string, unknown>`, then projects only recognized fields and their defaults into the normalized typed policy.
+
+`ctx.skills.list()` returns every winning summary and no longer chooses an invocation surface. `isModelInvocable(skill)` and `isUserInvocable(skill)` read the matching positive field directly. `ctx.skills.get()` remains policy-neutral because trusted internal callers may need any definition, while a public consumer must enforce its own predicate before advertising or loading a skill. The model tool and TUI check the invocation-neutral summary before calling `get()`, then recheck the loaded definition so a denied name never reaches definition loading and a policy change between discovery and load cannot expose its body.
+
+The local provider accepts the exact kebab-case frontmatter keys `disable-model-invocation` and `user-invocable`. It accepts YAML booleans plus case-insensitive `true`/`false`, `yes`/`no`, `on`/`off`, and `1`/`0`, matching the practical boolean forms accepted by Claude skills. It maps `disable-model-invocation` to the inverse positive field and fills both positive fields from their defaults even when neither key is present. A camel-case external spelling or non-boolean invocation value drops the entire skill from discovery with a targeted warning; this pre-release repository does not keep an on-disk compatibility alias. Invocation data fails closed because ignoring it would default to permission and could expose the skill on a disabled surface, while wrong-typed optional `whenToUse` and `metadata` values are omitted because they do not decide invocation.
+
+The model-facing `dsh-tool-skill` catalog and loader enforce `isModelInvocable`. The TUI `/skill:` autocomplete and exact loader enforce the user field locally, so a user-only skill is visible and loadable there even when it is absent from model discovery, without turning the optional skill peer into a runtime import. The launcher-seeded initial skill used by guided `dsh migrate` and `dsh upgrade` sessions follows this same TUI path and must remain user-invocable. The browser `skill.list` RPC serves a user-selected reference that still asks the model to load the skill, so it exposes the intersection of model- and user-invocable skills; no direct browser skill-loading RPC is added.
+
+These rules permit all four combinations:
+
+| Policy | Model surface | User surface |
+|---|---|---|
+| `{ modelInvocable: true, userInvocable: true }` | included | included |
+| `{ modelInvocable: true, userInvocable: false }` | included | excluded |
+| `{ modelInvocable: false, userInvocable: true }` | excluded | included |
+| `{ modelInvocable: false, userInvocable: false }` | excluded | excluded |
+
+This decision extends the [skill system](2026-07-05-skill-system.md) and supersedes the invocation-policy limitation recorded by the [TUI skill slash command](2026-07-21-tui-skill-slash-command.md).
+
+## Alternatives considered
+
+**Store all frontmatter in a generic `Map` and read string keys in `isModelInvocable` / `isUserInvocable`.** Rejected because misspelled keys, non-boolean values, and consumer-specific coercion would cross package seams without type checking. The parser boundary remains open; the domain model is deliberately typed and narrow.
+
+**Keep `ctx.skills.list()` model-filtered and add a second user list.** Rejected because discovery, duplicate resolution, caching, and ordering are surface-neutral work. One complete catalog plus explicit predicates prevents those mechanisms from drifting while making each consumer's policy visible at its boundary.
+
+**Enforce invocation policy inside `ctx.skills.get()`.** Rejected because `get()` cannot know whether its caller is a model tool, a human command, or trusted orchestration. Filtering there would also make the both-disabled quadrant impossible to inspect or administer.
+
+**Treat camel-case frontmatter as an alias.** Rejected because the external format is the kebab-case Claude skills contract and the repository has no released compatibility obligation. Failing loud avoids silently preserving a nonstandard spelling.
+
+**Add a browser-side direct skill invocation RPC.** Rejected for this change because the existing browser flow inserts a model reference rather than a loaded instruction body. Its correct policy is therefore the intersection; a direct user-loading surface needs its own wire and logging design.
+
+## Consequences
+
+Providers and runtime registrations expose a small typed invocation contract, while local YAML remains extensible. Every new discovery consumer must consciously choose the model predicate, the user predicate, their intersection, or trusted unfiltered access; forgetting that choice is now review-visible rather than hidden in registry behavior.
+
+The changed model catalog is pinned by the keyless ACP snapshot, which includes a model-only skill and excludes a user-only skill. The assembled keyless TUI snapshot discovers and loads a user-only skill by exact name, then rejects a model-only skill before loading its body; the real Loader/PTY smoke proves the same user-only path through the shipped terminal process. The real-host Chromium snapshot pins the browser intersection across all four policy quadrants. TUI unit coverage exercises those quadrants plus disposal races, while registry, local-parser, model-tool, and API-proxy tests cover defaults, supported boolean forms, malformed values, legacy-key rejection, exact-load enforcement, and the browser intersection.
@@ -0,0 +1,50 @@
+# Agent Note: 模型与用户彼此独立的 skill（技能）调用策略
+
+Status: implemented
+
+[English](2026-07-28-skill-invocation-policy.md) | 中文
+
+## 问题
+
+skill 注册表最初将发现操作视为模型目录：`ctx.skills.list()` 会移除禁止模型调用的 skill，而 `ctx.skills.get()` 仍是不过滤内容的可信 loader。该设计足以支持由模型发起的加载，却无法表示与 Claude 兼容的四类 skill：仅向用户公开、仅向模型公开、同时向两者公开，或者两者均不公开。TUI 从面向模型过滤后的列表中生成用户自动补全，并允许通过 `get()` 加载任意精确名称，这进一步放大了两类调用策略不匹配的问题。
+
+本地解析器还将一种内部驼峰式拼写暴露为 frontmatter。若要支持既有的负向字段 `disable-model-invocation` 和正向字段 `user-invocable`，需要建立持久且对称的领域表示，同时避免把所有可能出现的 YAML 键都变成跨包的无类型契约。
+
+## 决策
+
+`SkillSummary` 包含一个必填且类型明确的 `invocation: SkillInvocationPolicy` 对象，其 `modelInvocable: boolean` 和 `userInvocable: boolean` 字段为正向且对称。只有显式输入 seam 可以省略它：未提供策略的运行时 `SkillRegistration`，以及两个调用键均未提供的本地 frontmatter，都会在生成候选项或定义前解析为 `{ modelInvocable: true, userInvocable: true }`。未来的 frontmatter 键只有在具备消费方和执行契约后，才会进入领域模型；本地提供方仍将 frontmatter 解析为开放的 `Record<string, unknown>`，然后只把已识别字段及其默认值投影到规范化的类型化策略中。
+
+`ctx.skills.list()` 返回所有胜出的摘要，不再替任何调用接口选择策略。`isModelInvocable(skill)` 和 `isUserInvocable(skill)` 分别直接读取对应的正向字段。`ctx.skills.get()` 保持策略无关，因为可信内部调用方可能需要任意定义；对外消费方则必须在展示或加载 skill 之前执行自身对应的判定函数。模型工具和 TUI 会在调用 `get()` 前检查与调用策略无关的摘要，随后再次检查已加载的定义：被拒绝的名称绝不会进入定义加载流程，发现与加载之间发生策略变更也无法暴露该 skill 的正文。
+
+本地提供方只接受拼写完全一致的 kebab-case frontmatter 键 `disable-model-invocation` 和 `user-invocable`。它接受 YAML 布尔值，以及不区分大小写的 `true`/`false`、`yes`/`no`、`on`/`off` 和 `1`/`0`，与 Claude skills 实际支持的布尔写法一致。它将 `disable-model-invocation` 映射为相反的正向字段，即使两个键都不存在，也会根据默认值填充两个正向字段。若使用外部驼峰式拼写或提供非布尔调用值，发现流程会丢弃整个 skill，并给出有针对性的警告；本仓库尚处于发布前阶段，因此不为磁盘格式保留兼容别名。调用数据校验遵循失败时默认拒绝原则，因为忽略这类数据会默认授予权限，可能使 skill 暴露在已禁用的接口上；与之不同，类型错误的可选 `whenToUse` 和 `metadata` 值会被省略，因为它们不参与调用判定。
+
+面向模型的 `dsh-tool-skill` 目录和 loader 执行 `isModelInvocable`。TUI 的 `/skill:` 自动补全与精确名称 loader 在本地执行用户字段，因此仅允许用户调用的 skill 即使不出现在模型发现结果中，仍会在此处显示并可加载，同时不会将可选的 skill peer 变成运行时导入。由 launcher 预置、供引导式 `dsh migrate` 和 `dsh upgrade` 会话使用的初始 skill 沿用同一条 TUI 路径，因此必须保持允许用户调用。浏览器的 `skill.list` RPC 提供的是由用户选择、但仍要求模型加载的引用，因此只公开同时允许模型和用户调用的 skill；本次改动不新增让浏览器直接加载 skill 的 RPC。
+
+这些规则允许以下四种组合：
+
+| 策略 | 模型侧接口 | 用户侧接口 |
+|---|---|---|
+| `{ modelInvocable: true, userInvocable: true }` | 包含 | 包含 |
+| `{ modelInvocable: true, userInvocable: false }` | 包含 | 排除 |
+| `{ modelInvocable: false, userInvocable: true }` | 排除 | 包含 |
+| `{ modelInvocable: false, userInvocable: false }` | 排除 | 排除 |
+
+该决策扩展了 [skill 系统](2026-07-05-skill-system.md)，并取代 [TUI skill 斜杠命令](2026-07-21-tui-skill-slash-command.md)中记录的调用策略限制。
+
+## 曾考虑的替代方案
+
+**将所有 frontmatter 存入通用 `Map`，并在 `isModelInvocable` / `isUserInvocable` 中读取字符串键。** 不予采纳，因为拼写错误的键、非布尔值以及各消费方自行采用的类型转换都会越过包边界，且无法获得类型检查。解析器边界仍保持开放；领域模型则有意采用类型明确的窄接口。
+
+**保持 `ctx.skills.list()` 仅返回允许模型调用的 skill，并另增一份用户列表。** 不予采纳，因为发现、重复项解析、缓存和排序都是与调用接口无关的工作。采用一份完整目录和显式判定函数，可以避免这些机制逐渐分化，并在各消费方边界清楚呈现其策略。
+
+**在 `ctx.skills.get()` 内执行调用策略。** 不予采纳，因为 `get()` 无法判断调用方是模型工具、人类命令还是可信编排逻辑。在此处过滤还会使两个接口均禁止调用的组合无法被检查或管理。
+
+**将驼峰式 frontmatter 作为别名处理。** 不予采纳，因为外部格式遵循采用 kebab-case 的 Claude skills 契约，而本仓库尚未发布，无需承担兼容义务。快速失败可以避免暗中保留不符合标准的拼写。
+
+**增加由浏览器端直接调用 skill 的 RPC。** 本次改动不予采纳，因为现有浏览器流程插入的是模型引用，而非已经加载的指令正文。因此，该流程应当取模型与用户调用策略的交集；直接由用户加载的接口需要单独设计协议与日志记录方式。
+
+## 后果
+
+提供方与运行时注册对外提供小而类型明确的调用契约，同时本地 YAML 仍可扩展。每个新的发现消费方都必须明确选择模型判定函数、用户判定函数、两者的交集，或可信且不过滤的访问方式；如果遗漏这项选择，评审时可以直接看出问题，而不会再被注册表行为掩盖。
+
+无密钥 ACP（Agent Client Protocol）快照固定了模型目录的变更：其中包含仅允许模型调用的 skill，并排除仅允许用户调用的 skill。组装后的无密钥 TUI 快照按精确名称发现并加载一个仅允许用户调用的 skill，随后在加载正文前拒绝一个仅允许模型调用的 skill；真实 Loader/PTY 冒烟测试通过随产品交付的终端进程证明了同一条仅允许用户调用的路径。真实宿主上的 Chromium 快照固定了浏览器在全部四种策略组合下的交集行为。TUI 单元测试覆盖这些组合以及资源释放竞态；注册表、本地解析器、模型工具和 API 代理测试则覆盖默认值、支持的布尔写法、格式错误的值、旧键拒绝、精确名称加载时的策略执行，以及浏览器侧的策略交集。
@@ -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/2026-07-28-web-terminal-card.md
+2026-07-28-web-terminal-card.md: 14896b1d88e5cfd2e4c58830c7a1bca1e54ed823
+2026-07-28-web-terminal-card.zh.md: 16c9004f8f80b720b25b76ba5c04f308b0fccbaf
@@ -0,0 +1,70 @@
+# Agent Note: Web terminal card — the bash render intent reaches the browser
+
+Status: implemented
+
+English | [中文](2026-07-28-web-terminal-card.zh.md)
+
+## Problem
+
+The bash tool declares `card: 'terminal'` for both its call and its result ([render-intent union](../architecture/2026-07-02-tool-render-intent-union.md)): the call view carries the command, an optional model-authored description, and the working directory; the result view carries the output, exit code, and terminating signal. That view already reaches the browser — host, connection, and runtime deliver it onto `ConversationSnapshot` as `callView`/`resultView` — and the TUI already renders it as a `$`-prompt card with an exit line and a head/tail height cap.
+
+The Web client ignored it. `packages/client/ui-conversation/src/client/contract/tool-call-model.ts` derived every row from raw tool args, and `skeleton/DetailsPanel.tsx` flattened every tool's content blocks into one `<pre>` with `white-space: pre-wrap; word-break: break-word`. Two defects followed from soft-wrapping and from having no height bound: multi-column output (`ls`, a table, box drawing) folded into a paragraph and lost the column alignment that is the whole point of that output, and a long single-column listing stretched the details panel to the length of the listing.
+
+## Decision
+
+`TerminalBlock` is a `ui-primitives` component that renders a shell command as a terminal surface, and both Web render sites for a bash call consume the terminal render intent through it: the chat tool row's expanded body and the details panel's Output section. `ui-conversation/src/client/contract/terminal-card-model.ts` is the single place that turns the snapshot's `callView`/`resultView` pair into the component's props, so the two sites cannot disagree about a command, its cwd, or its exit status. It returns null — the generic path — whenever neither side declares `card: 'terminal'`, including a `card` value this client version does not know, and whenever a settled call's result view is generic, which is how the bash tool's execution errors and background starts keep their existing rendering. Two duties the render-intent contract assigns to the UI bridge land here rather than in the tool: a settled result's `title` REPLACES the pending one, and the working directory resolves against the session workspace — an absolute view cwd is used as-is, a relative one joins under the workspace, and an omitted one IS the workspace, which is the common case for a bash call with no `workdir`. A pure presenter cannot see the session cwd, which is why the resolution belongs at this seam; each render site supplies the cwd off the session list row. Only a PRESENT call view can mean "omitted, so use the workspace": when the paging window drops the call head there is no cwd anywhere — the result view carries none — and the original call may have used an explicit workdir, so the prompt draws a bare `$` rather than naming a directory it cannot know. The resolved path also normalizes its `.`/`..` segments, because the bash executor resolves the workdir before running: a `..` against `/w/app` runs in `/w`, so the prompt label has to read `w` rather than `..`. A UNC path's `server` and `share` are part of its root rather than poppable segments, since Windows cannot climb above a share. The call view's `description` rides the same derivation, since the contract renders it above the card and it must outrank the row's args-derived summary. All three render sites draw it: both chat-row shapes and the details panel. An expanded row draws it itself, because the collapsed summary is hidden while a row is open — without that the description would only ever be visible collapsed, which is the opposite of what "above the card" means.
+
+The component's contract:
+
+- **Prompt lines, one per command line.** Each line of the command gets its own row: label, then that line verbatim. A `command` carrying two shell commands on two lines therefore reads as the two commands it is, instead of collapsing into one ellipsized row. The label is the cwd's last path segment, or `~` when the cwd equals the `home` prop — a browser has no `$HOME`, so the caller supplies the absolute home directory and the collapse simply does not apply without it. A view with no cwd renders a plain `$`. A trailing newline is a terminator, not an empty final command. Only the FIRST row carries the label: the view knows one working directory — where the call started — and a later line may run somewhere else entirely, since a `cd` in the command is enough to move it. Repeating the label down the rows would state a directory per line that nothing here knows, which is the same reason the run-state dot appears once. Later rows keep a bare `$` so they still read as prompts.
+- **One run-state dot for the call, on the first row.** `StateDot` in three of its four states: the chase while running, red for the exit status that also renders the pill, green for a clean settle — the same indicator a tool row's leading icon uses, so a row and its own card cannot disagree about one command. The dot exists because the first question a reader has about a shell command is whether it is still running, and without it that had to be inferred from the absence of output — which a settled command producing no output also looks like. It sits out of flow in a gutter the card reserves as its OWN left padding, so it neither indents its command nor depends on the command's text metrics to line up. The reservation is padding rather than margin because every render site rewrites `margin` wholesale to set its own indent, which silently cancelled a margin-based gutter and let a container clip the dot. Exactly one dot, whatever the line count: the exit status the view carries is the whole call's, and bash reports no per-command status, so a dot per line would assert of a line that succeeded inside a failing call that the line itself failed. The single visually hidden text label carries the same scope, since `StateDot` is `aria-hidden` and one label per row would read to assistive technology as several distinct outcomes.
+- **No soft wrapping.** Output lines are `white-space: pre` inside a horizontally scrolling box. Column alignment survives; a long line scrolls instead of folding.
+- **Height cap with an expand control.** Output longer than `DEFAULT_TERMINAL_MAX_LINES` (16) lines shows `ceil(max/2)` head lines plus the remaining tail lines, with a button in between that reports the hidden count and expands. The count is of parsed lines after the trailing output terminator is dropped, so an N-line output ending in a newline is N lines. The split arithmetic is the same as the TUI transcript's collapsed tool card (`packages/ui/tui/src/components/transcript.ts`), so one command's head and tail slices agree between the two front ends.
+- **ANSI color.** `anser` splits the SGR runs; `ui-primitives/src/ansi.ts` resolves each run into an inline style rendered as React spans. A foreground-only run maps the basic 16 colors onto `--dsw-*` theme tokens so authored color stays legible under both themes; a run that paints its own background keeps anser's literal rgb for both so its intended contrast survives, as do 256-palette, truecolor, and the two basic colors this design system has no token for. Sequences that carry no color (OSC strings, non-CSI escapes, inert C0 controls) are stripped before parsing so they never reach the DOM as literal characters. Cursor movements resolve before that strip, into a per-line column buffer rather than by string surgery, because carriage return and backspace only MOVE the cursor — neither erases anything, so what a reader sees is whatever each column last had written to it. `100%` then a carriage return and `OK` shows `OK0%`, since the redraw is shorter than the frame beneath it; a trailing `abc` plus a backspace still shows `abc`, since nothing overwrote the `c`; `abc` plus two backspaces and `XY` shows `aXY`. Each of these was checked against a real terminal, because the earlier truncate-and-delete approximations looked right and were not. SGR state is stamped per column as a terminal stores it per cell, so a partial overwrite keeps each surviving character's own color: red `bad`, three backspaces, then `ok` shows `okd` with the `d` still red. A CSI sequence occupies no column and changes only the state later writes are stamped with, which is also why a carriage return does not reset color, and why SGR state threads from one line to the next rather than closing at each newline. Erase-in-line is part of the same replay, because `\r\x1b[K` is the single idiom every spinner and progress bar writes — modelling the `\r` alone left the previous frame's tail standing, which is text the terminal never showed. Only `m` accumulates into a cell's style; a cursor or erase sequence must not, or the state string grows per redraw and emits boundaries anser has to discard. SGR is held per cell as a NORMALIZED record (foreground, background, attribute set), not as the sequence history: accumulating raw sequences made every state boundary re-emit the whole chain, so output that switches color without a full reset emitted O(n^2) characters — 3200 such cells produced 25 MB and a `RangeError` well under bash's own output cap. The record also lets the attribute closers every chalk-based tool writes (`39`, `49`, `22`, `24`, …) actually close their attribute, and each boundary emits one canonical sequence for the state it opens. A run also has to CLOSE: the replay converges to the state the scan ended in, not the last written cell's, because a reset after the final write changes no cell yet ends the run — without that a line finishing in `\x1b[0m` leaked its color onto every later line. The cursor advances by terminal columns, so a tab reaches the next 8-column stop, a wide character takes two (its spacer blanking rather than closing the gap once the lead cell is overwritten), and a combining mark takes none. Width follows emoji PRESENTATION rather than the U+2600-U+27BF block: `\u2713`, the check every progress line writes, is one column, so treating the block as wide misaligned exactly the output this card exists for. Writing over either half of a wide pair blanks the other, since a terminal cannot leave one cell of a two-cell glyph standing: `a\tb` then a redraw of `XY` shows `XY      b`, since a two-character redraw cannot reach column 8.
+- **Exit status and copy.** A non-zero exit code or a signal renders a status pill, matching the exit-status distinction the bash tool's own renderer draws; a clean exit renders none, and settled empty output renders a dimmed placeholder — judged on the parsed lines the card renders, not on the raw text, since output that is only escapes or control bytes survives a `trim()` yet parses to nothing visible and would otherwise draw blank rows plus a copy control for invisible bytes. The copy control copies the raw output text, not the rendered tree, so the prompt line and the pill stay out of the clipboard.
+
+Geometry, radius, and fonts mirror `CodeBlock`, so a terminal card and a fenced code block match visually; `white-space: pre` plus horizontal scroll is the deliberate divergence. The clipboard write both components need moved out of `CodeBlock` into a package-internal `src/clipboard.ts`, unexported so it stays an implementation detail of the two blocks.
+
+### Inline output in the chat row reverses a stated convention
+
+`chat/ToolRow.tsx` and `contract/tool-call-model.ts` asserted "no inline output ever — full results live in the details panel". Showing the terminal block in the row reverses that, on the owner's explicit decision.
+
+The reason the reversal holds: for a shell command the output *is* the result the user is reading, so routing it exclusively to a panel makes the common case a two-step interaction. A bounded, height-capped, non-wrapping terminal block in the row is what makes a bash-heavy transcript readable in one pass. The old rule's actual concern was a row whose height was unbounded by the length of the output, and the height cap plus expand control is what keeps that from returning.
+
+The remaining bound: the row caps at `CHAT_TERMINAL_MAX_LINES` (8), half the primitive's default, which the panel keeps — the message flow is a summary surface read across many calls, the panel is the single-call reading surface. Only the terminal intent renders inline; a generic tool's content is still panel-only.
+
+One premise of that split has since weakened: [tool rows stopped being details-panel click targets](2026-07-28-tool-call-file-open-in-os.md) and nothing replaced the gesture, so the panel is currently unreachable in the assembled application. The in-row cap is therefore the only surface a reader actually has for a long output, which the expand control covers. Restoring a panel entry point is that change's follow-up, not this one's — but until it lands, "the panel stays the place for the full output" is not true, and the row's expand control carries that load alone.
+
+## Alternatives considered
+
+**Render the terminal block only in the details panel.** This keeps the stated no-inline-output convention and needs no reversal to record. Rejected by the owner's explicit decision: a shell command's output is what the user came to read, and putting it one click away costs more than the convention buys. Recorded here as the owner's call, not as a conclusion derived from the codebase.
+
+**Reuse `CodeBlock` with a `console` language instead of a new primitive.** Rejected: `CodeBlock` soft-wraps, which is the defect being fixed, and it has no exit status, no cwd prompt line, no height cap, and no ANSI handling. Adding four terminal-specific concerns to the shared code-fence component would impose them on every markdown fence. The two components share their geometry and font tokens instead, which is the only part where one implementation is correct for both.
+
+**Hand-roll the SGR parser.** Rejected: an SGR parser is exactly the surface [prefer maintained dependencies over hand-rolling](../process/2026-07-26-dependencies-over-hand-rolling.md) says not to own — its edge cases (256-palette and truecolor forms, `reverse`, multi-parameter runs, unterminated sequences) each fail on output nobody produces in a test, so a hand-rolled version stays subtly wrong for a long time. Stated honestly against that policy's bar: `anser` does **not** delete existing owned code. It is a capability addition, which that note distinguishes from a net-deletion simplification; the health and boundary-fit halves of the bar are what it clears. What stays hand-rolled is the part `anser` does not cover: the theme-token color mapping, the non-CSI sanitizing, the carriage-return redraw, and the per-line span folding the height cap slices.
+
+## Consequences
+
+`anser` is a new runtime dependency of `packages/client/ui-primitives`, so every consumer of that package pays for it once. A bash row in the Web chat carries output, which is a deliberate density increase over a summary-only row; the cap is what keeps it bounded, and a tighter cap is a props change, not a redesign.
+
+`TerminalBlock` reads only the terminal 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. A UI without the terminal capability still gets the bridge's fenced fallback; nothing about the tool's result shape changed.
+
+A `run_code` sub-dispatch does not reach a terminal card on the shipped wire: `session.ts` folds `tool/code-dispatch(-start)` with `callView: null`/`resultView: null`, and the host's `viewFor` presents only top-level `tool/call`/`tool/result`, so a nested bash call keeps the generic flattened form. Both arms are pinned — the resolution path with views injected, and the no-view shape the wire actually delivers — so the gap is recorded rather than implied. Carrying presenter views through the code-dispatch wire is that seam's own change.
+
+Inline rendering is licensed for the terminal intent alone. A future intent that wants it needs its own bound and its own decision, argued against the reason recorded here rather than against the panel-only convention on its own.
+
+## Testing
+
+`packages/client/ui-primitives/tests/ansi.spec.ts` pins the parse layer: token mapping for the basic colors, literal rgb for the values with no token, the background-run pair, every decoration and the `textDecoration` collision between two of them, the sanitizing of OSC strings and non-CSI escapes and inert controls, the cursor replay (redraws leaving a longer frame's tail standing, a trailing backspace erasing nothing, erase-in-line in all three parameter forms, tab stops, wide characters, SGR threading across lines, and a cursor/erase sequence never entering a cell style), and CRLF preservation. Each replay case was checked against a real terminal first. `packages/client/ui-primitives/tests/terminal-block.spec.tsx` pins the component: cwd shortening, the running/empty/settled arms, signal outranking exit code, the trailing-newline terminator rule, the head/tail cap with its `aria-expanded` toggle, the run-state dot across all three reachable states plus its position ahead of the prompt label, the one-row-per-command-line prompt and its single dot on the first row, and the copy control asserting raw output on both the accepted and refused clipboard paths, plus `writeClipboard` directly.
+
+`packages/client/ui-conversation/tests/terminal-card.spec.tsx` pins the wiring at every render site: `terminalCardModel`'s derivation and each of its null arms, the result title replacing the pending one, the cwd resolving against the session workspace across all four of its cases, the panel resetting the card's expand state when the selection changes, the chat row's expand-gated body against the panel's full-height one, `BashRow`'s resident card and its agreement with its own summary row's state dot, and the panel's Output section including the run_code sub-dispatch and the out-of-window head. That file is written against no gate pressure — `packages/client/ui-conversation/src/*` sits on the coverage `exclude` list in `vitest.config.ts`, so a coverage run over this package measures none of these files.
+
+`apps/web/tests/terminal-card.snapshot.ts` pins the assembled application over the built client bundles: the same render intent at both conversation render sites and in both chat-row shapes, because a bash call reaches a resident card only through the keyed `BashRow` registration and every other terminal-declaring tool name lands on the render-site fallback row, whose body is expand-gated. Fixture turn 65 was named `bash` and turn 60 left as `fx-bash` so one fixture covers both shapes, and turn 60's command was made two lines so the built-bundle snapshot pins the per-line prompt and its single dot (`dotsPerPromptRow: [1, 0]`). That terminal turn is ordered BEFORE the todo turn on purpose: the standing plan retires at the next `turn/start`, so appending it after would have emptied the dock's plan strip and taken the todo surfaces' own coverage with it; that turn also carries what turn 60's two prompt rows cannot — SGR runs resolved to `--dsw-*` tokens, output past the chat cap, a nested cwd, and a non-zero exit authored beside the sample. The sample's body deliberately carries NO `[exit code: N]` line: the real bash presenter consumes that marker out of the body precisely because the card shows the exit as its own pill, so leaving it in would pin a frame showing the exit twice — one the product path cannot produce.
+
+`apps/web/tests/navigation-panes.e2e.ts` adds the real-browser scenario over its existing `echo NAVIGATION_OK` bash call, asserting what jsdom cannot compute: squeezing the output pane below its content width leaves the line at one row and gives the pane horizontal overflow, the run-state dot resolves to the green success token rather than to a literal color (a `--dsw-*` var has no computed value at all without the real theme stylesheet) and sits inside the card box yet left of the prompt label, which is the invariant the gutter padding owns, and the copy control reaches the page's own async Clipboard API rather than the `execCommand` fallback. Its `terminal-card.expected.md` golden records the resolved workspace in the prompt row, which is what a bash call with no `workdir` must show instead of a bare `$`.
+
+## Related
+
+- [Tagged render-intent union for tool-call presentation](../architecture/2026-07-02-tool-render-intent-union.md) — the `card`-tagged vocabulary this consumes; the Web client is now a full consumer of the `terminal` arm rather than of args alone.
+- [Web client syntax highlighting](../process/2026-07-26-web-syntax-highlighting-shiki.md) — owns `CodeBlock` and its shiki arm, and records why tool output deliberately stays unhighlighted; ANSI color here is authored color, not guessed grammar.
+- [Web client architecture](../architecture/2026-07-19-gui-web-client-architecture.md) — the slot and snapshot layering the two render sites sit in.
@@ -0,0 +1,70 @@
+# Agent Note: Web terminal card — the bash render intent reaches the browser
+
+Status: implemented
+
+[English](2026-07-28-web-terminal-card.md) | 中文
+
+## Problem
+
+bash 工具的调用与结果都声明 `card: 'terminal'`（[渲染意图联合类型](../architecture/2026-07-02-tool-render-intent-union.md)）：调用视图携带命令、一段可选的模型撰写描述以及工作目录，结果视图携带输出、退出码与终止信号。该视图早已抵达浏览器——host、connection 与 runtime 把它投递到 `ConversationSnapshot` 的 `callView`/`resultView` 上——TUI 也早已把它渲染为带 `$` 提示符的卡片，附退出行与首尾高度上限。
+
+Web client 却对它视而不见。`packages/client/ui-conversation/src/client/contract/tool-call-model.ts` 仅从原始工具参数推导每一行，`skeleton/DetailsPanel.tsx` 则把所有工具的内容块压平进一个 `<pre>`，样式为 `white-space: pre-wrap; word-break: break-word`。软换行加上没有高度约束，带来两个缺陷：多列输出（`ls`、表格、制表符绘图）被折成一段文字，丢掉了这类输出赖以存在的列对齐；而单列的长列表会把详情面板拉长到与列表等长。
+
+## Decision
+
+`TerminalBlock` 是 `ui-primitives` 中把 shell 命令渲染为终端表面的组件，bash 调用在 Web 侧的两个渲染点都经由它消费 terminal 渲染意图：聊天工具行展开后的正文，以及详情面板的 Output 区。`ui-conversation/src/client/contract/terminal-card-model.ts` 是把快照上的 `callView`/`resultView` 这一对转换为该组件 props 的唯一位置，因此两个渲染点不可能在命令、cwd 或退出状态上产生分歧。当两侧都不声明 `card: 'terminal'` 时它返回 null，即走 generic 路径——包括本 client 版本不认识的 `card` 取值；当一个已落定调用的结果视图是 generic 时同样返回 null，这正是 bash 工具的执行错误与后台启动得以保持既有渲染的方式。渲染意图契约交给 UI 桥接层的两项职责也落在这里，而不在工具侧：已落定结果的 `title` **替换**待定标题；工作目录针对会话 workspace 解析——视图给出的绝对路径原样使用，相对路径在 workspace 之下拼接，省略则**就是** workspace，而这正是不带 `workdir` 的 bash 调用的常见情形。纯 presenter 看不到会话 cwd，因此该解析属于这道接缝；两个渲染点各自从会话列表行取出 cwd 传入。只有**存在**的调用视图才能表示「省略了 cwd，因此取 workspace」：当分页窗口丢掉调用头时，任何地方都不再有 cwd——结果视图并不携带它——而原调用完全可能使用过一个显式 workdir，因此提示行绘制一个裸 `$`，而不是命名一个它无法知晓的目录。解析后的路径还会归一化其 `.`／`..` 段，因为 bash 执行器在运行前就已解析 workdir：相对 `/w/app` 的 `..` 实际运行在 `/w`，因此提示标签必须读作 `w` 而不是 `..`。UNC 路径的 `server` 与 `share` 属于其根，而非可弹出的路径段，因为 Windows 无法越过一个共享向上。调用视图的 `description` 走同一处推导，因为契约把它渲染在卡片上方，且它必须优先于该行由参数推导出的摘要。三个渲染点都会绘制它：两种聊天行形态与详情面板。展开后的行自行绘制它，因为一行处于展开态时其折叠摘要是隐藏的——否则该描述将只在折叠时可见，这与「位于卡片上方」的含义正好相反。
+
+该组件的契约：
+
+- **提示符行，每条命令行一行。** 命令的每一行各占一行：标签，其后原样跟随该行。因此一个在两行上承载两条 shell 命令的 `command` 就读作它本身的两条命令，而不是被压成一行并省略号截断。标签取 cwd 的最后一段路径，当 cwd 等于 `home` prop 时取 `~`——浏览器没有 `$HOME`，因此由调用方提供绝对家目录，不提供时该折叠不生效。视图不带 cwd 时渲染一个纯 `$`。末尾换行是终止符，不是一条空的末命令。只有**第一行**携带该标签：视图只知道一个工作目录——调用开始处的那个——而后面的行完全可能在别处运行，命令里一个 `cd` 就足以改变它。把标签在各行重复，等于陈述一个此处无人知晓的逐行目录，这与运行状态点只出现一次是同一个理由。其余行保留一个裸 `$`，因此它们仍读作提示符。
+- **整次调用一枚运行状态点，位于第一行。** 它是 `StateDot` 四种状态中的三种：运行期间为追逐动画，与渲染状态徽章相同的退出状态为红色，干净落定为绿色——与工具行行首图标使用同一个指示器，因此一行与其自身的卡片不可能对同一条命令产生分歧。该状态点存在的理由是：读者对一条 shell 命令的第一个问题就是它是否仍在运行；没有它时，这一点只能从「没有输出」推断，而一条落定后无输出的命令看起来也一样。它以脱离文档流的方式落在卡片以**自身左内边距**预留的落区里，因此既不会缩进其命令，也不依赖命令自身的文本度量来与之对齐。该预留用 padding 而非 margin，是因为每个渲染点都会整条重写 `margin` 来设定自己的缩进——那会静默取消基于 margin 的落区，并让容器把状态点裁掉。无论有多少行，都只有一枚：视图携带的退出状态属于整次调用，而 bash 不报告逐条命令的状态，因此每行一枚状态点就等于在断言——一条在失败调用中其实成功了的命令行自身失败了。那一处视觉隐藏的文本标签具有相同的作用域，因为 `StateDot` 是 `aria-hidden`，而每行一个标签会被辅助技术读成好几个各自独立的结果。
+- **不软换行。** 输出行使用 `white-space: pre`，置于横向滚动的容器内。列对齐得以保留；长行滚动，而非折行。
+- **高度上限与展开控件。** 输出超过 `DEFAULT_TERMINAL_MAX_LINES`（16）行时，显示 `ceil(max/2)` 行首部加余下的尾部行数，中间是一个按钮，报告被隐藏的行数并可展开。计数针对的是剥除输出末尾终止符之后解析出的行，因此以换行结尾的 N 行输出就是 N 行。切分算法与 TUI transcript 折叠态工具卡片（`packages/ui/tui/src/components/transcript.ts`）完全一致，因此同一条命令的首尾切片在两个前端之间吻合。
+- **ANSI 颜色。** `anser` 切分 SGR 分段；`ui-primitives/src/ansi.ts` 把每段解析为内联样式，渲染成 React span。只设前景色的分段把基本 16 色映射到 `--dsw-*` 主题 token，使作者指定的颜色在两种主题下都可读；自行绘制背景的分段则前后景都保留 anser 给出的字面 rgb，以保住它意图中的对比度，256 色板、truecolor 以及本设计系统没有对应 token 的两种基本色同样如此。不承载颜色的转义序列（OSC 串、非 CSI 转义、无显示意义的 C0 控制符）在解析前被剥除，因此绝不会以字面字符抵达 DOM。光标移动在该剥除之前先行结算，且落在逐行的列缓冲里而不是靠字符串手术，因为回车与退格**只移动**光标——两者都不擦除任何东西，所以读者看到的就是每一列最后被写入的内容。`100%` 后接回车再接 `OK` 显示为 `OK0%`，因为这次重绘比它下面的帧更短；末尾 `abc` 加一个退格仍显示 `abc`，因为没有任何东西覆盖过那个 `c`；`abc` 加两个退格再接 `XY` 显示 `aXY`。这些用例都对照真实终端核实过，因为先前「截断加删除」的近似看起来是对的，实际并不对。SGR 状态按列打戳，与终端按单元格存储颜色的方式一致，因此部分覆盖会保留每个存活字符自身的颜色：红色 `bad`、三个退格、再写 `ok`，显示为 `okd` 且那个 `d` 仍是红的。CSI 序列不占列，只改变后续写入被打上的状态——这也正是回车不会重置颜色的原因，以及 SGR 状态会从一行延续到下一行、而不是在每个换行处关闭的原因。行内擦除属于同一次重放，因为 `\r\x1b[K` 是每个 spinner 与进度条都会写的同一个惯用法——只建模 `\r` 会让上一帧的尾巴留在原处，那是终端从未显示过的文本。只有 `m` 会累加进单元格样式；光标或擦除序列不能累加，否则状态串会随每次重绘线性增长，并发出 anser 只能丢弃的边界。SGR 按单元格以**归一化记录**保存（前景、背景、属性集合），而不是序列历史：累积原始序列会让每个状态边界重新发射整条链，因此不做完整 reset 的换色输出会发射 O(n^2) 个字符——3200 个这样的单元格产生 25 MB 并最终 `RangeError`，远低于 bash 自身的输出上限。该记录也让所有 chalk 系工具写出的属性闭合码（`39`、`49`、`22`、`24` 等）真正闭合其属性，且每个边界只为它开启的状态发射一条规范序列。一个分段也必须**收束**：重放收敛到扫描结束时的状态，而不是最后一个被写入单元格的状态——因为最后一次写入之后的 reset 不改变任何单元格，却结束了该分段；没有这一步，以 `\x1b[0m` 结尾的行会把颜色泄漏到其后所有行。光标按终端列推进，因此制表符前进到下一个 8 列制表位、宽字符占两列（其续列在首列被覆盖后变为空白而非合拢），组合标记不占列。宽度依据 emoji **presentation** 而非 U+2600–U+27BF 整个区块：`\u2713`——每条进度行都会写的对勾——只占一列，把该区块整体当作双宽恰好会错位这张卡片赖以存在的那类输出。写入宽字符对的任一半都会把另一半清成空白，因为终端无法让一个双格字形只留下一格：`a\tb` 之后用 `XY` 重绘显示为 `XY      b`，因为两个字符的重绘到不了第 8 列。
+- **退出状态与复制。** 非零退出码或信号渲染一枚状态徽章，与 bash 工具自身渲染器所作的退出状态区分一致；干净退出不渲染徽章，落定后的空输出渲染一处变暗的占位文字——该判定读的是卡片实际渲染的解析行，而非原始文本，因为只含转义或控制字节的输出能通过 `trim()` 却解析不出任何可见内容，否则就会画出一片空行外加一个把不可见字节写进剪贴板的复制控件。复制控件复制的是原始输出文本而非渲染后的树，因此提示符行与徽章不会进入剪贴板。
+
+几何尺寸、圆角与字体沿用 `CodeBlock`，因此终端卡片与围栏代码块在视觉上一致；`white-space: pre` 加横向滚动是有意的分歧。两个组件都需要的剪贴板写入从 `CodeBlock` 中提取到包内部的 `src/clipboard.ts`，不对外导出，因此它仍是这两个块的实现细节。
+
+### 聊天行内嵌输出推翻了一条既有约定
+
+`chat/ToolRow.tsx` 与 `contract/tool-call-model.ts` 都断言过「绝不内嵌输出——完整结果在详情面板」。在行内显示终端块推翻了这一点，依据是 owner 的明确决定。
+
+这次推翻成立的理由：对 shell 命令而言，输出**就是**用户要读的结果，把它专门收进面板会让最常见的情形变成两步交互。行内一个有界、限高、不换行的终端块，正是让 bash 密集的 transcript 一遍读完的条件。旧规则真正担心的是行高不受输出长度约束，而高度上限加展开控件正是防止其复现的机制。
+
+余下的约束：行内上限为 `CHAT_TERMINAL_MAX_LINES`（8），是组件默认值的一半，而面板沿用默认值——消息流是跨多次调用阅读的摘要表面，面板才是单次调用的阅读表面。只有 terminal 意图内嵌渲染；generic 工具的内容依旧只在面板中。
+
+这一划分的一个前提此后被削弱了：[工具行已不再是详情面板的点击目标](2026-07-28-tool-call-file-open-in-os.md)，且没有任何手势接替它，因此该面板在组装后的应用中当前不可达。于是行内上限成为读者实际拥有的唯一长输出表面，由展开控件承担。恢复面板入口属于那次改动的后续，而非本次改动——但在它落地之前，「面板仍是查看完整输出的地方」并不成立，行内的展开控件独自承担了这一职责。
+
+## Alternatives considered
+
+**只在详情面板渲染终端块。** 这样保留既有的「不内嵌输出」约定，也不需要记录任何推翻。已被 owner 的明确决定否决：shell 命令的输出正是用户来读的东西，把它挪到一次点击之外，代价高于该约定带来的收益。此处记录的是 owner 的裁决，而非从代码库推导出的结论。
+
+**复用 `CodeBlock` 并传入 `console` 语言，而不新建组件。** 已否决：`CodeBlock` 会软换行，而软换行正是本次要修的缺陷，且它没有退出状态、没有 cwd 提示符行、没有高度上限、也不处理 ANSI。把四项终端专属关注点加进共享的代码围栏组件，等于把它们强加给每一个 markdown 围栏。两个组件改为共享几何与字体 token，那是唯一一处「一套实现对两者都正确」的部分。
+
+**手写 SGR 解析器。** 已否决：SGR 解析器恰是[优先采用维护良好的依赖而非手写](../process/2026-07-26-dependencies-over-hand-rolling.md)所指明不该自持的那类实现——它的边界情形（256 色板与 truecolor 形式、`reverse`、多参数分段、未终止的序列）各自只在没人会写进测试的输出上失效，因此手写版本会在很长时间内一直微妙地出错。对照那条策略的门槛如实陈述：`anser` **并未**删除任何既有自持代码。它是一次能力增补，而那条 Agent Note 把这与净删除式的简化区分开来；它清过的是健康度与边界契合这两半门槛。`anser` 未覆盖而仍由我们手写的部分是：主题 token 的颜色映射、非 CSI 序列的剥除、回车重绘，以及供高度上限切片的逐行 span 折叠。
+
+## Consequences
+
+`anser` 成为 `packages/client/ui-primitives` 的一项新运行时依赖，因此该包的每个消费方都为它支付一次。Web 聊天中的 bash 行现在承载输出，相比只有摘要的行，这是有意提高的信息密度；上限是维持其有界的机制，而调紧上限是改一个 prop，不是重新设计。
+
+`TerminalBlock` 只读取 terminal 视图携带的字段，因此它始终是渲染意图内容的纯函数——不查会话状态，与产出该视图的 presenter 一样可安全回放。不具备终端能力的 UI 仍从桥接层拿到围栏式回退；工具的结果形态未作任何改动。
+
+在当前已交付的 wire 上，`run_code` 子派发不会得到终端卡片：`session.ts` 把 `tool/code-dispatch(-start)` 折叠为 `callView: null`／`resultView: null`，而 host 的 `viewFor` 只呈现顶层的 `tool/call`／`tool/result`，因此嵌套的 bash 调用保持通用的压平形式。两条分支都已钉住——注入视图后的解析路径，以及 wire 实际投递的无视图形态——因此这个缺口是被记录下来的，而非暗含的。把 presenter 视图贯穿 code-dispatch wire 属于那道接缝自身的改动。
+
+内嵌渲染的许可仅授予 terminal 意图。将来想要内嵌的意图需要有自己的边界与自己的决定，且需针对此处记录的理由来论证，而不是仅针对「只在面板」这条约定本身。
+
+## Testing
+
+`packages/client/ui-primitives/tests/ansi.spec.ts` 固定解析层：基本色的 token 映射、无对应 token 取值的字面 rgb、带背景分段的前后景配对、每一项装饰以及其中两项之间的 `textDecoration` 冲突、OSC 串与非 CSI 转义及无显示意义控制符的剥除、光标重放（较短重绘让上一帧尾巴留存、末尾退格不擦除任何东西、行内擦除的全部三种参数形式、制表位、宽字符、SGR 跨行延续，以及光标／擦除序列绝不进入单元格样式），以及 CRLF 的保留。每一条重放用例都先对照真实终端核实过。`packages/client/ui-primitives/tests/terminal-block.spec.tsx` 固定组件：cwd 缩短、运行中／空／已落定三条分支、信号优先于退出码、末尾终止符规则、首尾高度上限及其 `aria-expanded` 开关、运行状态点全部三种可达状态及其位于提示符标签之前的位置、每条命令行一行的提示区及其位于第一行的单枚状态点，以及复制控件在剪贴板接受与拒绝两条路径上都断言原始输出，另有对 `writeClipboard` 的直接固定。
+
+`packages/client/ui-conversation/tests/terminal-card.spec.tsx` 固定每个渲染点上的接线：`terminalCardModel` 的推导及其每一处 null 分支、结果标题替换待定标题、cwd 针对会话 workspace 解析的全部四种情形、切换选中调用时面板重置卡片展开态、对话行受展开控制的输出体与面板的全高输出体的对比、`BashRow` 的常驻卡片及其与自身摘要行状态点的一致性，以及面板 Output 区段（含 run_code 子派发与超出窗口的调用头）。该文件在没有门禁压力的情况下写成——`packages/client/ui-conversation/src/*` 位于 `vitest.config.ts` 的覆盖率 `exclude` 列表中，因此覆盖率运行不会统计其中任何文件。
+
+`apps/web/tests/terminal-card.snapshot.ts` 在构建后的客户端产物上固定组装完整的应用：同一渲染意图在两个对话渲染点、以及两种对话行形态下的表现——因为 bash 调用只有经由带键的 `BashRow` 注册才得到常驻卡片，而其他任何声明 terminal 的工具名都落到渲染点兜底行上，其输出体受展开控制。fixture 第 65 轮改名为 `bash`、第 60 轮保留 `fx-bash`，于是一份 fixture 覆盖两种形态，并把第 60 轮的命令改为两行，使构建产物快照钉住逐行提示区及其单枚状态点（`dotsPerPromptRow: [1, 0]`）。该终端轮有意排在 todo 轮**之前**：站立计划会在下一次 `turn/start` 时退役，若追加在其后就会让 dock 的计划条变空，并连带毁掉 todo 表面自身的覆盖；该轮还承载第 60 轮两个提示行无法覆盖的部分——解析到 `--dsw-*` token 的 SGR 分段、超出对话上限的输出、嵌套 cwd，以及在样本旁另行标注的非零退出码。样本正文有意**不含** `[exit code: N]` 行：真实的 bash presenter 正是因为卡片以徽章单独呈现退出状态，才把该标记从正文中消费掉；若保留它，钉住的将是一帧把退出状态显示两次的画面——而产品路径产不出这一帧。
+
+`apps/web/tests/navigation-panes.e2e.ts` 在其既有的 `echo NAVIGATION_OK` bash 调用上新增真实浏览器场景，断言 jsdom 无法计算的部分：把输出面板挤压到窄于内容宽度后，行仍保持单行且面板产生横向溢出；运行状态点解析为绿色的 success token，而不是字面颜色（没有真实主题样式表时，`--dsw-*` 变量根本不产生计算值），且它位于卡片盒之内、提示标签之左——这正是那道 gutter 内边距所拥有的不变量；复制控件走的是页面自身的异步 Clipboard API，而非 `execCommand` 兜底路径。其 `terminal-card.expected.md` 基准记录了提示行中已解析的 workspace——这正是不带 `workdir` 的 bash 调用应当显示的内容，而非一个裸 `$`。
+
+## Related
+
+- [Tagged render-intent union for tool-call presentation](../architecture/2026-07-02-tool-render-intent-union.md)——本次消费的 `card` 标签词汇；Web client 现在是 `terminal` 分支的完整消费方，而不再只消费参数。
+- [Web client syntax highlighting](../process/2026-07-26-web-syntax-highlighting-shiki.md)——它拥有 `CodeBlock` 及其 shiki 分支，并记录了工具输出为何有意不做语法高亮；这里的 ANSI 颜色是作者指定的颜色，不是猜出来的语法。
+- [Web client architecture](../architecture/2026-07-19-gui-web-client-architecture.md)——两个渲染点所处的 slot 与快照分层。
@@ -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/2026-07-29-addressable-queue-operations.md
+2026-07-29-addressable-queue-operations.md: 78a7d346163bb7e5e76c989c6e93576b4a6cee64
+2026-07-29-addressable-queue-operations.zh.md: 050b9755ad4ebe70e2bdcafb711ef279331e27af
@@ -0,0 +1,43 @@
+# Agent Note: Address pending queue occurrences for edit and removal
+
+Status: implemented
+
+English | [中文](2026-07-29-addressable-queue-operations.zh.md)
+
+## Problem
+
+The Web queue rendered pending messages but could not edit or delete one row. `MessageId` was insufficient as an address because callers may enqueue the same immutable message more than once. The browser also inferred queue retirement from turn and status events, so a row operation racing with driver claim had no authoritative outcome.
+
+## Decision
+
+**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.
+
+**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 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 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 exposes 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.
+
+## Alternatives considered
+
+**Address rows by `MessageId`.** Rejected because one immutable message may be sent repeatedly; editing or deleting by message identity would affect an ambiguous occurrence.
+
+**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.
+
+**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.
+
+**Resume a cold Agent for a queue operation.** Rejected because durable session identity does not preserve the process-local inbox capability. Resuming can only produce `not-found` after creating unrelated live state.
+
+## 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, text-only editing, save and cancel affordances, removal, retirement races, and disabled mixed-content editing. Keyless browser scenarios drive the exposed edit and delete actions through the built Web composition and real HTTP/SSE wire.
+
+## Consequences
+
+Queued work gains precise row operations without becoming durable session history. Occurrence identity is a live process-local capability and disappears at claim, cancellation, disposal, or restart; 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.
+
+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.
@@ -0,0 +1,43 @@
+# Agent Note（agent 决策记录）：为待处理队列项提供编辑与移除操作
+
+Status: implemented
+
+[English](2026-07-29-addressable-queue-operations.md) | 中文
+
+## 问题
+
+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。`MessageId` 不足以充当寻址标识，因为调用方可以多次将同一条不可变消息加入队列。浏览器还会根据轮次和状态事件推断队列项已退役，因此当行操作与驱动器认领发生竞态时，系统无法给出权威结果。
+
+## 决策
+
+**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。
+
+**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 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。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 暴露编辑和删除，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。
+
+## 考虑过的替代方案
+
+**通过 `MessageId` 寻址行。** 不予采纳，因为同一条不可变消息可以重复发送；按消息标识编辑或删除会无法确定应操作哪一次入队。
+
+**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。
+
+**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。
+
+**为队列操作恢复冷 Agent。** 不予采纳，因为持久会话标识不会保留进程本地的 inbox 寻址凭据。恢复只能在创建无关的实时状态后得到 `not-found`。
+
+## 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、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。无密钥浏览器场景会通过构建后的 Web 组合和真实 HTTP／SSE 协议操作公开的编辑和删除。
+
+## 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、取消、dispose 或重启时消失；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。
+
+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。
@@ -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/2026-07-29-web-message-icon-actions-and-clock.md
+2026-07-29-web-message-icon-actions-and-clock.md: e79662056792c3ab413468ad038dec40455be767
+2026-07-29-web-message-icon-actions-and-clock.zh.md: 72d3b4e0cda19438f2f46fd402b3b76de3726ae5
@@ -0,0 +1,31 @@
+# Agent Note: Web message IconActions and clocks
+
+Status: implemented
+
+English | [中文](2026-07-29-web-message-icon-actions-and-clock.zh.md)
+
+## Problem
+
+The web chat user bubble already had copy / branch / edit IconActions but no clock. Finalized assistant narration had no under-body action chrome at all, even though the Harness design shows a copy / branch / clock row after the answer settles. Streaming replies must not flash that chrome mid-token. Memoized rows also keep stable props across midnight, so a one-shot `Date.now()` would leave yesterday's messages stuck on `HH:mm`.
+
+## 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.**
+
+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. Branch stays a chrome stub. 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
+
+**Show assistant IconActions during streaming.** Rejected: the request is to reveal the row only after output completes; mid-stream chrome would flicker and invite copying a partial answer.
+
+**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.
+
+**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.
+
+**Wire branch to a real session fork.** Rejected for this change: same rationale as the archived [user IconActions note](../../archived/feature/2026-07-27-user-message-icon-actions.md) — the mutation path is unspecified; the button reserves the design seat.
+
+**Publish the calendar day through a chat store or inject hook.** Rejected: the day tick is presentation-only local state with no cross-entry consumers; a component-local timeout matches the client rule that behavioral hooks may own state that does not subscribe to an external source.
+
+## Consequences
+
+Settled assistant content answers expose copy and the event clock as soon as the row mounts; Think-only nodes stay chrome-free; branch stays a stub. 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, and the content-only assistant gate; the web e2e scenario pins the assembled IconActions chrome.
@@ -0,0 +1,31 @@
+# Agent Note: Web 消息 IconActions 与时钟
+
+Status: implemented
+
+[English](2026-07-29-web-message-icon-actions-and-clock.md) | 中文
+
+## 问题
+
+Web 聊天的用户气泡已有复制／分支／编辑 IconActions，但没有时钟。已定稿的 assistant 叙述下方完全没有操作栏，尽管 Harness 设计稿在回答结束后展示复制／分支／时钟。流式回复不得在 token 中途闪出该栏。经 memo 的行在跨午夜时仍保持稳定 props，因此一次性的 `Date.now()` 会让昨日消息一直卡在 `HH:mm`。
+
+## 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。**
+
+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。分支仍是 chrome stub。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
+
+**在流式过程中展示 assistant IconActions。** 否决：需求是输出完成后才展示该行；中途 chrome 会闪烁，并诱使复制半截回答。
+
+**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。
+
+**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。
+
+**把分支接到真实的会话 fork。** 本次否决：与已归档的[用户 IconActions 笔记](../../archived/feature/2026-07-27-user-message-icon-actions.md)同一理由——变更路径尚未规定；按钮只预留设计座位。
+
+**通过 chat store 或 inject hook 发布日历日。** 否决：日刻度只是展示层本地状态，没有跨入口消费者；组件本地 timeout 符合「行为 hook 可拥有不订阅外部源的状态」这一客户端规则。
+
+## 后果
+
+已定稿的 assistant 内容回答在行挂载后立刻暴露复制与事件时钟；纯 Think 节点不带 chrome；分支仍为 stub。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、午夜加宽与 assistant 仅内容门控；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-composer-stats-and-input-polish.md
+2026-07-30-web-composer-stats-and-input-polish.md: 0d90b8c1d2e283f2bcca7d9e82ac461d9fa4eb7e
+2026-07-30-web-composer-stats-and-input-polish.zh.md: db47250852724e62337948aa516effb42f19066c
@@ -0,0 +1,33 @@
+# Agent Note: Web composer stats detail and input-zone polish
+
+Status: implemented
+
+English | [中文](2026-07-30-web-composer-stats-and-input-polish.zh.md)
+
+## Problem
+
+The web composer footer showed a single joined stats string (cache/tokens/turns/steps) in its own stack row, visually detached from the input card and missing the design's duration and token-split details. The input zone itself had accumulated per-entry spacing hacks: dock strips carried their own margins, the sticky seat sat on a solid fill that clipped the transcript hard, the back-to-bottom control cleared the composer by a hardcoded offset that broke as the draft grew, and the goal and todo strips disagreed on surface color and column width.
+
+## Decision
+
+**The stats line renders inside the InputBar's width column through a new `footer` owner prop and expands to the design's grouped detail row; the composer stack owns one 8px rhythm; the seat fades the transcript through a fixed 36px token-bound gradient; the back-to-bottom control follows a live `--dsh-composer-height`; goal and todo share one 752px tip-fill column.**
+
+- `'conversation.composer.dock'` entries reach the page as the `ComposerBarOwnerProps.footer` slot, rendered under the card inside the bar's `.root`, so the stats line and the card share one width constraint. `StatsLine` derives everything client-side from the snapshot: turns/steps, LLM wall time from assistant `timing` (`completedTime - stepStartTime`), tool wall time from tool-result `time - callTime` pairs, prompt/output token split with cache-read folded into input, and cache-hit percentage. Groups render pipe-separated and drop out whole when empty; `formatTokens` (517 / 12.2K / 1.2M) and `formatDuration` (45.2s / 2m42s) are exported for tests. Durations cover only in-window nodes — the README owns that limitation.
+- `.composerStack` carries `gap: 8px` and entries carry no outer margins (QueueDock's margin removed), so a dock entry that renders null costs nothing. GoalBar is the one deliberate exception: `margin: 0 auto -10px` cancels the gap and tucks its square bottom edge 2px under the card.
+- The sticky seat's background is a `linear-gradient` from `color-mix(bg-base 0%, transparent)` at 0px to solid `bg-base` at 36px — pixel stops, not the figma export's percentage, so a growing draft widens only the solid region; `color-mix` keeps both themes fading from their own base.
+- A `useCallback` ref on the seat attaches a ResizeObserver that publishes `--dsh-composer-height` on the scroll body; ChatView's back-to-bottom slot computes `bottom` from it (152px first-paint fallback) instead of the prior hardcoded 168px.
+- The textarea's 52px two-line floor applies to the hero variant only; the docked composer collapses to content height. Goal and todo strips both use the 44px-gutter / 752px-cap column with the todo `tip` fill and l1 border; the todo header is compacted (13/20 type, 8+8 padding) so its collapsed height equals the goal strip's 38px.
+
+## Alternatives considered
+
+**Percentage gradient stops (the figma export's 24%).** Rejected: the stop scales with seat height, so a tall draft stretches the fade band over most of the transcript; the fixed 36px band equals the design's 24% at the resting ~150px composer and stays constant as the composer grows.
+
+**A skeleton-owned dock column with a generic "bottommost entry tucks" contract.** Built and backed out in review: a `.inputDock` wrapper owning width/rhythm plus `--dsh-dock-tuck-*` vars on `:last-child` would retarget the tuck automatically on reorder, but it rewrote every entry and the GoalBar DOM ahead of a pending merge. Per-entry CSS with GoalBar owning its own tuck was chosen; the generic column remains available if dock entries multiply.
+
+**Backend-supplied duration fields for the stats line.** Unnecessary: assistant `timing` and tool call/result pairs already reach the snapshot, so wall times fold client-side with no new session event or host projection.
+
+**Keeping the stats line as a composer-stack sibling.** Rejected: as a stack row it carried its own width constraint that drifted from the card's; as the bar's `footer` both share one column and the stats participate in the seat's sticky/gradient region by construction.
+
+## Consequences
+
+The stats row now reads turns/steps, LLM and tool durations, cache hit, and input/output tokens at a glance, at the cost that durations cover only the loaded event window (README Known Limitation). The one-gap stack rhythm makes dock spacing composition-independent, but GoalBar's tuck is positional: it must stay the bottommost dock entry (`order: 1`) or its negative margin tucks it under the wrong neighbor. The fade band is a constant 36px, so any future design retune is one stop value. `chat-stats-bash-sample.spec.tsx` pins the derivation (timing/tool folds, token split), both formatters, the grouped render, and the zero-renders-during-streaming acceptance.
@@ -0,0 +1,33 @@
+# Agent Note: Web composer stats detail and input-zone polish
+
+Status: implemented
+
+[English](2026-07-30-web-composer-stats-and-input-polish.md) | 中文
+
+## Problem
+
+Web 编辑器页脚原本以独立 stack 行显示一条拼接的统计字符串（cache／tokens／turns／steps），视觉上与输入卡脱节，且缺少设计稿中的耗时与 token 拆分细节。输入区自身也积累了逐条目的间距补丁：dock 条各带自己的 margin，sticky 座位下是硬切消息流的纯色填充，「回到底部」控件用硬编码偏移躲避编辑器、草稿一长高就失效，goal 与 todo 条的底色和列宽也互不一致。
+
+## Decision
+
+**统计行经由新的 `footer` owner prop 渲染进 InputBar 的宽度列内，并扩展为设计稿的分组细节行；composer stack 拥有唯一的 8px 节奏；座位以固定 36px 的 token 绑定渐变淡出消息流；「回到底部」控件跟随实时的 `--dsh-composer-height`；goal 与 todo 共用一条 752px 的 tip 填充列。**
+
+- `'conversation.composer.dock'` 条目以 `ComposerBarOwnerProps.footer` 席位到达页面，渲染在卡片下方、bar 的 `.root` 之内，统计行与卡片因此共享同一宽度约束。`StatsLine` 全部在客户端从快照推导：turns／steps、由 assistant `timing`（`completedTime - stepStartTime`）折算的 LLM 墙钟时间、由 tool-result 的 `time - callTime` 配对折算的工具墙钟时间、把 cache-read 并入输入侧的提示／输出 token 拆分，以及缓存命中率。各组以竖线分隔、无数据时整组消失；`formatTokens`（517 / 12.2K / 1.2M）与 `formatDuration`（45.2s / 2m42s）导出供测试。耗时只覆盖窗口内节点——该限制由 README 记录。
+- `.composerStack` 携带 `gap: 8px`，条目不带外边距（QueueDock 的 margin 已删除），渲染为 null 的 dock 条目零成本。GoalBar 是唯一的刻意例外：`margin: 0 auto -10px` 抵消 gap，把方形下缘塞进卡片下方 2px。
+- sticky 座位的背景是从 0px 处的 `color-mix(bg-base 0%, transparent)` 到 36px 处纯色 `bg-base` 的 `linear-gradient`——像素节点而非 figma 导出的百分比，草稿长高只扩大纯色区域；`color-mix` 让两个主题都从各自的底色淡出。
+- 座位上的 `useCallback` ref 挂 ResizeObserver，把 `--dsh-composer-height` 发布到滚动体上；ChatView 的回到底部席位据此计算 `bottom`（首帧回退 152px），替换先前硬编码的 168px。
+- textarea 的 52px 两行下限只保留在 hero 变体；停靠态编辑器折叠到内容高度。goal 与 todo 条统一使用 44px 边距／752px 上限的列、todo 的 `tip` 填充与 l1 边框；todo 表头紧凑化（13/20 字号、8+8 内边距），折叠高度与 goal 条的 38px 对齐。
+
+## Alternatives considered
+
+**百分比渐变节点（figma 导出的 24%）。** 否决：节点随座位高度缩放，长草稿会把过渡带拉伸到消息流的大半；固定 36px 过渡带等于设计稿在静息 ~150px 编辑器下的 24%，且随编辑器长高保持恒定。
+
+**骨架拥有的 dock 列加通用「最底条目贴卡」契约。** 实现后在评审中撤回：由 `.inputDock` 包装层拥有宽度／节奏、在 `:last-child` 上发布 `--dsh-dock-tuck-*` 变量，重排时贴卡会自动换人，但它在一次待合并前重写了每个条目和 GoalBar 的 DOM。最终选择逐条目 CSS、GoalBar 自持贴卡；dock 条目增多时通用列方案仍然可用。
+
+**由后端为统计行提供耗时字段。** 不必要：assistant `timing` 与工具 call/result 配对已经到达快照，墙钟时间可在客户端折算，无需新的会话事件或 host 投影。
+
+**统计行保持为 composer stack 的兄弟节点。** 否决：作为 stack 行它携带独立的宽度约束、与卡片漂移；作为 bar 的 `footer`，两者共享一列，统计行也天然落在座位的 sticky／渐变区域内。
+
+## Consequences
+
+统计行现在一眼可读 turns／steps、LLM 与工具耗时、缓存命中和输入／输出 token，代价是耗时只覆盖已加载事件窗口（README 已知限制）。单 gap 的 stack 节奏使 dock 间距与组合无关，但 GoalBar 的贴卡是位置性的：它必须保持为最底的 dock 条目（`order: 1`），否则其负边距会塞到错误的邻居下面。过渡带恒为 36px，未来设计调整只改一个节点值。`chat-stats-bash-sample.spec.tsx` 钉住推导（timing／工具折算、token 拆分）、两个格式化器、分组渲染，以及流式期间零重渲染的验收。
@@ -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
-2026-06-11-quality-gates.md: e1af110387936d644208dc1829fde4a4fdf8a3f9
-2026-06-11-quality-gates.zh.md: a4e57b7a08ecf20babb33b55d8c94414df1b10b1
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-06-11-quality-gates.md
+2026-06-11-quality-gates.md: 60db7ba5cfa8184c0fcce764aa027f32a9b721ab
+2026-06-11-quality-gates.zh.md: a5ac7cd831255d479f7a1d75586785e546877fba
@@ -15,11 +15,11 @@ This codebase is developed primarily by coding agents. Agents follow enforced ga
 Every mechanically checkable AGENTS.md promise gets a command that exits non-zero. CI invokes the exhaustive set, while Git hooks reserve their latency budget for cheap local defects:

 - Max-strict TypeScript (`noUncheckedIndexedAccess`, `exactOptionalPropertyTypes`, …); examples, tests, and scripts typecheck in CI via the root no-emit `tsconfig.json` while package/vendor code stays behind its own project-reference boundary.
- ESLint strict-type-checked + @stylistic (the house style, enforced), including file-local duplicated logic checks; vendored code excluded.
+- [Oxlint](2026-07-29-oxlint-linter.md) with type-aware TypeScript rules plus the @stylistic and SonarJS compatibility plugins, enforcing the house style and file-local duplicated-logic checks; vendored code excluded.
 - jscpd detects cross-file clones in package production TypeScript and repository scripts; narrow source-range exceptions document deliberately parallel implementations.
 - Per-file 100% coverage on `packages/*/*/src` (v8); unreachable defensive guards carry `/* v8 ignore */ ` with stated reasons instead of deletion.
 - knip (dead code/deps), publint (package correctness), workspace constraints (workspace rules: private, cordis peer+dev, uniform version, ESM), and a NodeNext consumer typecheck for built package declarations.
- lefthook pre-commit fixes staged lint, rejects staged whitespace, and checks the vendor manifest; pre-push runs incremental typecheck. CI runs the full matrix on node 22.19/24/26 plus built application smokes for the Headless, TUI, ACP, JSON-RPC, workflow, and code-runtime entry paths.
+- lefthook pre-commit applies formatting-only ESLint fixes before Oxlint validation and native fixes, rejects staged whitespace, and checks the vendor manifest; pre-push runs incremental typecheck. CI runs the full matrix on node 22.19/24/26 plus built application smokes for the Headless, TUI, ACP, JSON-RPC, workflow, and code-runtime entry paths.

 ## Consequences

@@ -15,11 +15,11 @@ Status: implemented
 每条可机械检查的 AGENTS.md 承诺都有一个以非零状态退出的命令。CI 执行完整集合，而 Git 钩子将延迟预算留给可低成本发现的本地缺陷：

 - 最严格的 TypeScript 配置（`noUncheckedIndexedAccess`、`exactOptionalPropertyTypes` 等）；示例、测试和脚本通过根目录的 no-emit `tsconfig.json` 在 CI 中进行类型检查，而包（package）/vendor 代码保持在各自 project-reference 边界之后。
- ESLint strict-type-checked + @stylistic（作为强制执行的统一代码风格），包括文件内重复逻辑检查；vendor 代码排除在外。
+- [Oxlint](2026-07-29-oxlint-linter.md) 配合类型感知的 TypeScript 规则以及 @stylistic 和 SonarJS 兼容插件，强制执行统一代码风格和文件内重复逻辑检查；vendor 代码排除在外。
 - jscpd 检测包的生产 TypeScript 代码与仓库脚本中的跨文件克隆；窄范围的源码区间例外用于记录有意为之的并行实现。
 - `packages/*/*/src` 下按文件 100% 覆盖率（v8）；不可达的防御性守卫使用 `/* v8 ignore */ ` 并注明理由，而非删除。
 - knip（死代码/依赖）、publint（包的正确性）、workspace 约束（workspace 规则：private、cordis peer+dev、统一版本、ESM），以及对构建出的包声明文件进行 NodeNext 消费方类型检查。
- lefthook pre-commit 修复已暂存文件的 lint 问题、拒绝已暂存的空白问题并检查 vendor manifest；pre-push 运行增量类型检查。CI 在 Node 22.19/24/26 上运行完整矩阵，并对 Headless、TUI、ACP（Agent Client Protocol）、JSON-RPC、工作流和代码运行时入口路径执行已构建应用的冒烟测试。
+- lefthook pre-commit 先应用仅用于格式化的 ESLint 修复，再执行 Oxlint 验证和原生修复，拒绝已暂存的空白问题并检查 vendor manifest；pre-push 运行增量类型检查。CI 在 Node 22.19/24/26 上运行完整矩阵，并对 Headless、TUI、ACP（Agent Client Protocol）、JSON-RPC、工作流和代码运行时入口路径执行已构建应用的冒烟测试。

 ## 后果

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.md
-2026-07-06-parallel-pre-push-gates.md: d86642b7feb82908ec792db0c6a3da403cfc79fd
-2026-07-06-parallel-pre-push-gates.zh.md: 0425cf1a01b56604a07be366dd46d3920c5fb487
+2026-07-06-parallel-pre-push-gates.md: 538e52c5318fb6d4eab2e8786513a08c1ff0ec55
+2026-07-06-parallel-pre-push-gates.zh.md: e93eec8757c20c8154703d9bdfd2f0c805e6a26c
@@ -14,7 +14,7 @@ Aggregate jobs such as documentation synchronization hide long sequential chains

 [scripts/run-gates.ts](../../../../scripts/run-gates.ts) owns the bounded scheduler used by CI, `doc-sync`, and the opt-in `check:all` command. It expands named modes into leaf gates, rejects empty or ambiguous dependency graphs before starting a child, respects artifact dependencies, buffers attributable output, reports exit and signal outcomes independently, and accepts `DSH_GATE_CONCURRENCY` when a caller needs a different worker bound.

-The Node 24 consumer job is one seven-gate mode rather than a shell-owned process pool. Its default worker count equals its gate count while dependencies control readiness: `publint` precedes built-package invariant validation, and snapshot replay, NodeNext type checks, built-bin smokes, and lint wait for that validation. Lint waits because the invariant verifier temporarily stages package views that ESLint must not traverse; source compatibility checks can overlap the validation chain.
+The Node 24 consumer job is one seven-gate mode rather than a shell-owned process pool. Its default worker count equals its gate count while dependencies control readiness: `publint` precedes built-package invariant validation, and snapshot replay, NodeNext type checks, built-bin smokes, and lint wait for that validation. Lint waits because the invariant verifier temporarily stages package views that the linter must not traverse; source compatibility checks can overlap the validation chain.

 [scripts/publint-all.ts](../../../../scripts/publint-all.ts) discovers packages from `packages/<group>/<pkg>` and runs `publint` with a worker pool sized from `availableParallelism()`. `DSH_PUBLINT_CONCURRENCY` can cap or raise the worker count for local machines and CI runners with different resource profiles. Results are buffered per package and printed in deterministic package order, so parallel execution does not scramble each package's log block.

@@ -14,7 +14,7 @@ Status: implemented

 [scripts/run-gates.ts](../../../../scripts/run-gates.ts) 拥有 CI、`doc-sync` 和选择启用的 `check:all` 命令所使用的有界调度器。它将具名模式展开为叶子门禁，在启动子进程前拒绝空的或有歧义的依赖图，遵守产物依赖，缓冲可归因的输出，分别报告退出结果与信号结果，并在调用方需要不同 worker 上限时接受 `DSH_GATE_CONCURRENCY`。

-Node 24 消费方 job 采用单个包含七道门禁的模式，而非由 shell 管理的进程池。其默认 worker 数等于门禁数，但门禁是否就绪由依赖关系控制：`publint` 先于已构建包不变式验证运行，快照回放、NodeNext 类型检查、built-bin 冒烟测试和 lint 则等待该验证完成。lint 之所以等待，是因为不变式验证器会临时暂存包视图，而 ESLint 不得遍历这些视图；源码兼容性检查可以与这条验证链重叠运行。
+Node 24 消费方 job 采用单个包含七道门禁的模式，而非由 shell 管理的进程池。其默认 worker 数等于门禁数，但门禁是否就绪由依赖关系控制：`publint` 先于已构建包不变式验证运行，快照回放、NodeNext 类型检查、built-bin 冒烟测试和 lint 则等待该验证完成。lint 之所以等待，是因为不变式验证器会临时暂存包视图，而 linter 不得遍历这些视图；源码兼容性检查可以与这条验证链重叠运行。

 [scripts/publint-all.ts](../../../../scripts/publint-all.ts) 从 `packages/<group>/<pkg>` 发现包，并以根据 `availableParallelism()` 确定大小的 worker 池运行 `publint`。`DSH_PUBLINT_CONCURRENCY` 可以针对资源配置不同的本地机器和 CI runner 限制或提高 worker 数量。结果按包缓冲，并按确定性的包顺序打印，因此并行执行不会打乱各包的日志块。

@@ -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
-2026-07-20-gui-testing-system.md: 546f65f065c0c2266773acc3c28b2833a094ba9b
-2026-07-20-gui-testing-system.zh.md: 6601ae0a1c2bd1671af6f02961fbda81d30ab971
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-20-gui-testing-system.md
+2026-07-20-gui-testing-system.md: 8c6dafb18fc207fc4eac780ba18e108267bc28b1
+2026-07-20-gui-testing-system.zh.md: 9a0de4bfa8fa2f8de55beef53bedde51649c5d9c
@@ -20,7 +20,7 @@ Cut along the architecture's natural test seams into three tiers, bottom-up:
 |---|---|---|---|
 | 1 Protocol isomorphism | `AbstractApiClient` + `toFetchHandler` (bidirectional data / rpcId / zod types / SSE streams / batching / timeouts) | **The full chain at the isomorphic point**: `InProcessApiClient(toFetchHandler(脚本化 impl))` skips the network but genuinely runs the wire serialization — zero browser, pure node env | `packages/host/apiproxy/tests/client-handler.spec.ts` |
 | 2 Object-layer orchestration | `Session`/`SessionManager`/`ConnectionController` (state machines and timing: stitching / dedup / paging / optimistic draft clearing / pendingBuffers / reconnect / backoff) | **The "event sequence in → snapshot out" golden path**: programmable fakes + deferreds controlling timing + fake timers controlling backoff | `packages/client/{runtime,connection}/tests/` |
-| 3 Assembled presentation | Built artifacts × the real client loader and plugin composition | App-owned semantic snapshots boot all eight built client plugins under jsdom for deterministic cross-plugin state changes; bare Playwright smoke separately proves the real browser/carrier boundary, with real-host cases self-skipping without a key; the keyless browser e2e lane disables the shipped model-adapter row and replays recorded session fixtures through `dsh-llm-replay` in the real in-process web assembly against conversation aria goldens ([web e2e lane](../testing/2026-07-24-web-gui-browser-e2e-lane.md)) | `apps/web/tests/*.snapshot.ts`, `apps/web/tests/smoke-{fixture,real}.e2e.ts`, `apps/web/tests/{replay-round-trip,seeded-history}.e2e.ts` |
+| 3 Assembled presentation | Built artifacts × the real client loader and plugin composition | App-owned semantic snapshots boot all eight built client plugins under jsdom for deterministic cross-plugin state changes; bare Playwright smoke separately proves the real browser/carrier boundary, with real-host cases self-skipping without a key; the keyless browser e2e lane disables the shipped model-adapter row and replays recorded session fixtures through `dsh-llm-replay` in the real in-process web assembly against conversation aria goldens ([web e2e lane](../testing/2026-07-24-web-gui-browser-e2e-lane.md), [required CI gate](../testing/2026-07-30-web-browser-snapshot-ci-gate.md)) | `apps/web/tests/*.snapshot.ts`, `apps/web/tests/smoke-{fixture,real}.e2e.ts`, `apps/web/tests/{replay-round-trip,seeded-history}.e2e.ts` |

 Inter-tier discipline: **each tier tests its own layer, upper tiers never re-test lower ones** — an app semantic snapshot pins only user-visible projection across the assembled plugin boundary, while Playwright smoke proves browser and carrier liveness; wire semantics belong to tier 1 and data semantics to tier 2. Pure-function layers (lineage/partial/notifier/fold-adapter) are tested directly with zero fakes in the same package's tests/ alongside tier 2.

@@ -34,6 +34,7 @@ Inter-tier discipline: **each tier tests its own layer, upper tiers never re-tes
 | Baseline | `pnpm run test:gui` | Tier 1+2 vitest (`packages/client packages/host`), seconds-fast, no browser, no server | Casually, after touching any GUI source |
 | Semantic snapshot | `DSH_EXAMPLE_MODE=lib pnpm run test:snapshot` | Keyless assembled-application semantics plus the repo's transport-specific expected outputs | After a human-visible GUI change; before delivery |
 | Browser end-to-end | `pnpm run test:web` | Rebuilds the front-end dist first, then runs the tier-3 browser set: the two-level smoke (fixture level + real-host level self-skip) plus the keyless replayed e2e scenarios (`DSH_SNAPSHOT=record`/`refresh` re-record fixtures / rewrite goldens) | After touching the build surface/boot/carriage; before delivery |
+| Browser expected-output gate | `DSH_SNAPSHOT=replay pnpm run test:web:built` | Reuses CI-built artifacts and compares every committed browser golden without writing | Every Linux pull request |
 | Gate | `pnpm run test:coverage` | The repo-wide gate (host and client GUI packages included, except annotated browser-grade exclusions) | The PR window |

 **Division of labor between the browser scripts and vitest**: Playwright owns browser/carrier black-box regression and long sequential user journeys; ordinary vitest owns data-layer semantics such as reference stability, timing, and wire shapes; snapshot vitest owns stable app-level semantic output through the built composition. These lanes complement each other rather than duplicating assertions.
@@ -46,7 +47,7 @@ Inter-tier discipline: **each tier tests its own layer, upper tiers never re-tes

 ## Consequences

-Each lane tests its own tier: touching any GUI source gets seconds-fast `test:gui` feedback, wire/object-layer semantics assert in milliseconds in Node, built-composition snapshots pin deterministic user-visible projection, and the browser carries wiring and carrier acceptance. The accepted cost is that inter-tier discipline is upheld by review rather than a machine gate and every new app snapshot must avoid unstable layout or clock output.
+Each lane tests its own tier: touching any GUI source gets seconds-fast `test:gui` feedback, wire/object-layer semantics assert in milliseconds in Node, built-composition snapshots pin deterministic user-visible projection, and the browser carries wiring and carrier acceptance. Inter-tier discipline remains review-owned, while Linux CI mechanically enforces browser-golden freshness. Every new app snapshot must avoid unstable layout or clock output.

 ## Alternatives considered

@@ -56,4 +57,4 @@ Each lane tests its own tier: touching any GUI source gets seconds-fast `test:gu
 | Migrating the verify scripts to vitest | An ordered script shares one browser session; splitting the cases either formalizes it (sequential + shared page) or re-runs the preamble × N; streaming PASS/FAIL output is exactly the agent's locating interface |
 | Reusing FixtureApiClient in tests | The demo script runs on a real clock, tests need deferred hand-controlled timing — orthogonal purposes; forced reuse chains the tests to the demo's rhythm |
 | A standalone vitest config for GUI packages (once designed as vitest.gui.config.ts) | Package-level tests/ are already scanned by the root include; `vitest run packages/client packages/host` path filtering is the tight loop — zero new config |
-| Deferring hooks/component-layer unit tests (the original ruling) | Once deferred as "components are consumables, revisit after the redo"; overturned by the user on 2026-07-20 — **the jsdom mainline enters coverage** (no browser infrastructure in CI is the decisive reason, playwright demoted to a local enhancement), the RTL dependencies entered devDependencies, the first spec landed |
+| Deferring hooks/component-layer unit tests | jsdom remains the coverage mainline because it gives fast per-file component behavior; the required browser replay gate complements it at the assembled tier rather than replacing it ([CI gate decision](../testing/2026-07-30-web-browser-snapshot-ci-gate.md)) |
@@ -20,7 +20,7 @@ GUI 栈需要考虑多种应用形态，同应用形态内的不同运行环境
 |---|---|---|---|
 | 1 协议同构层 | `AbstractApiClient` + `toFetchHandler`（双向数据/rpcId/ZOD类型/SSE 流/合批/超时） | **同构点全链**：`InProcessApiClient(toFetchHandler(脚本化 impl))` 不过网络但真跑 wire 序列化——零浏览器、纯 node env | `packages/host/apiproxy/tests/client-handler.spec.ts` |
 | 2 对象层编排 | `Session`/`SessionManager`/`ConnectionController`（状态机与时序：缝合/去重/翻页/乐观清稿/pendingBuffers/重连/退避） | **「事件序列进→快照出」黄金路径**：可编程假体 + deferred 控时序 + fake timers 控退避 | `packages/client/{runtime,connection}/tests/` |
-| 3 组装呈现层 | 构建产物 × 真实 client loader 与插件组合 | 归应用所有的语义快照会在 jsdom 下启动全部 8 个已构建的 client 插件，以固定确定性的跨插件状态变化；独立使用 Playwright 裸库的冒烟测试负责验证真实浏览器/承载层边界，真 host 用例在无密钥时自行跳过；无密钥浏览器 e2e 车道会禁用交付配置中的模型适配器行，并通过 `dsh-llm-replay` 在真实进程内 web 组装中回放录制的会话 fixture，与会话区 aria 期望输出比对（[web e2e 车道](../testing/2026-07-24-web-gui-browser-e2e-lane.md)） | `apps/web/tests/*.snapshot.ts`、`apps/web/tests/smoke-{fixture,real}.e2e.ts`、`apps/web/tests/{replay-round-trip,seeded-history}.e2e.ts` |
+| 3 组装呈现层 | 构建产物 × 真实 client loader 与插件组合 | 归应用所有的语义快照会在 jsdom 下启动全部 8 个已构建的 client 插件，以固定确定性的跨插件状态变化；独立使用 Playwright 裸库的冒烟测试负责验证真实浏览器/承载层边界，真 host 用例在无密钥时自行跳过；无密钥浏览器 e2e 车道会禁用交付配置中的模型适配器行，并通过 `dsh-llm-replay` 在真实进程内 web 组装中回放录制的会话 fixture，与会话区 aria 期望输出比对（[web e2e 车道](../testing/2026-07-24-web-gui-browser-e2e-lane.md)、[必需 CI 门禁](../testing/2026-07-30-web-browser-snapshot-ci-gate.md)） | `apps/web/tests/*.snapshot.ts`、`apps/web/tests/smoke-{fixture,real}.e2e.ts`、`apps/web/tests/{replay-round-trip,seeded-history}.e2e.ts` |

 层间纪律：**下层各测各的，上层不重测下层**：应用语义快照只固定组装后插件边界上的用户可见投影，Playwright 冒烟测试负责验证浏览器与承载层是否存活；wire 语义归 1 层，数据语义归 2 层。纯函数层（lineage/partial/notifier/fold-adapter）随 2 层同包 tests/ 零假体直测。

@@ -34,6 +34,7 @@ GUI 栈需要考虑多种应用形态，同应用形态内的不同运行环境
 | 基础 | `pnpm run test:gui` | 1+2 层 vitest（`packages/client packages/host`），秒级、无浏览器无 server | 改 GUI 任意源码后随手跑 |
 | 语义快照 | `DSH_EXAMPLE_MODE=lib pnpm run test:snapshot` | 无需密钥的组装应用语义，以及仓库按传输形态划分的预期输出 | 用户可见的 GUI 变更后；交付前 |
 | 浏览器端到端 | `pnpm run test:web` | 先重建前端 dist，再跑 3 层浏览器全集：双级 smoke（fixture 级 + 真 host 级 self-skip）加上无密钥回放 e2e 场景（`DSH_SNAPSHOT=record`/`refresh` 重录 fixture / 重写期望输出） | 改构建面/boot/承载后；交付前 |
+| 浏览器预期输出门禁 | `DSH_SNAPSHOT=replay pnpm run test:web:built` | 复用 CI 构建的产物，并在不写入的情况下比较每份已提交的浏览器预期输出 | 每个 Linux 拉取请求 |
 | 门禁 | `pnpm run test:coverage` | 全仓 gate（host 与 client GUI 包均纳入，仅排除带注释的浏览器级例外） | PR 窗口 |

 **浏览器脚本与 vitest 的分工**：Playwright 负责浏览器/承载层黑盒回归和较长的连续用户操作流程；普通 vitest 负责引用稳定性、时序和 wire 结构等数据层语义；快照 vitest 通过构建后的组合负责稳定的应用层语义输出。这些车道彼此互补，而不重复断言。
@@ -46,7 +47,7 @@ GUI 栈需要考虑多种应用形态，同应用形态内的不同运行环境

 ## Consequences

-各车道各测各层：改动任意 GUI 源码后都能获得秒级 `test:gui` 反馈，wire/对象层语义在 Node 环境中进行毫秒级断言，基于构建后组合的快照固定确定性的用户可见投影，浏览器负责接线与承载层验收。接受的代价是层间纪律由评审而非机器门禁维持，而且每个新的应用快照都必须避开不稳定的布局或时钟输出。
+各车道各测各层：改动任意 GUI 源码后都能获得秒级 `test:gui` 反馈，wire/对象层语义在 Node 环境中进行毫秒级断言，基于构建后组合的快照固定确定性的用户可见投影，浏览器负责接线与承载层验收。层间纪律仍由评审负责，而 Linux CI 通过机器门禁确保浏览器预期输出的新鲜度。每个新的应用快照都必须避开不稳定的布局或时钟输出。

 ## Alternatives considered

@@ -56,4 +57,4 @@ GUI 栈需要考虑多种应用形态，同应用形态内的不同运行环境
 | verify 脚本迁 vitest | 有序剧本共享浏览器会话，拆 case 要么形式化（sequential+共享 page）要么重走前置×N；PASS/FAIL 流式输出正是 agent 定位接口 |
 | 测试复用 FixtureApiClient | 演示脚本走真实时钟，测试需要 deferred 手控时序——用途正交，硬复用把测试绑死在演示节奏上 |
 | GUI 包独立 vitest config（曾设计 vitest.gui.config.ts） | 包级 tests/ 本就被根 include 扫到，`vitest run packages/client packages/host` 路径过滤即窄循环——零新 config |
-| hooks/组件层暂缓单测（原裁决） | 曾以「组件是耗材、等重做后再议」暂缓；2026-07-20 用户改判——**jsdom 主线进覆盖率**（CI 无浏览器基建是决定性理由，playwright 降级为本地增强），RTL 依赖入 devDeps、首个 spec 已落 |
+| hooks/组件层暂缓单测 | jsdom 仍是覆盖率主线，因为它能快速验证逐文件组件行为；必需的浏览器回放门禁在组装层与之互补，而非取代它（[CI 门禁决策](../testing/2026-07-30-web-browser-snapshot-ci-gate.md)） |
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md
-2026-07-22-evidence-based-larger-hosted-runners.md: 67fc7ded5cffc6a219665f135a4c9e1cc4752691
-2026-07-22-evidence-based-larger-hosted-runners.zh.md: 71c5c067361b57fab5aae9e9ffa3850a30609db3
+2026-07-22-evidence-based-larger-hosted-runners.md: 983d5520bd73fc3cf82c37bf0d4a9ff1c6e6f51c
+2026-07-22-evidence-based-larger-hosted-runners.zh.md: a86dcf2c60d7b950e7557e84ef6993e712a2ce09
@@ -18,7 +18,7 @@ The required primary path depends on those enterprise pools. Standard GitHub-hos

 The former gate-level and coarse primary shard jobs are absent from the workflow. Their static, lint, coverage, snapshot, and scenario shard selectors are also absent from the repository, so an unused diagnostic path cannot preserve a second CI architecture.

-Linux primary work uses three independent 32-core jobs. Coverage runs alone with its own worker bound, and the static scheduler runs alone so its result has no post-build consumer tail. After static gates finish, that job publishes its emitted `apps/*/lib`, `packages/*/*/lib`, and `vendor/*/lib` tree as a run-scoped artifact. The third job restores that exact tree, then starts lint, Node 24 runtime compatibility, build-backed snapshots, and all artifact consumers without repeating the build. Generated NodeNext consumer directories are excluded from ESLint discovery because the artifact check removes them while these processes overlap. The pnpm store and ESLint cache are restored without putting cache uploads on the pull-request critical path. Performance reports use each job's `startedAt` to `completedAt` interval; runner queue delay is capacity evidence, not repository execution time.
+Linux primary work uses three independent 32-core jobs. Coverage runs alone with its own worker bound, and the static scheduler runs alone so its result has no post-build consumer tail. After static gates finish, that job publishes its emitted `apps/*/lib`, `packages/*/*/lib`, and `vendor/*/lib` tree as a run-scoped artifact. The third job restores that exact tree, then starts lint, Node 24 runtime compatibility, build-backed snapshots, and all artifact consumers without repeating the build. Generated NodeNext consumer directories are excluded from Oxlint discovery because the artifact check removes them while these processes overlap. The pnpm store is restored without putting cache uploads on the pull-request critical path; Oxlint has no repository-managed result cache. Performance reports use each job's `startedAt` to `completedAt` interval; runner queue delay is capacity evidence, not repository execution time.

 The gate dependencies remain explicit. Coverage consumes source and does not wait for build. Documentation typechecking builds its complete project-reference graph once. Snapshot replay and publication consumers wait for emitted output, while Node-version compatibility jobs exercise runtime-sensitive source loading without repeating the primary source-graph typecheck. PTY and subprocess suites keep their bounded inner concurrency rather than inheriting the runner's core count.

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

 原有的门禁级和粗粒度主流程分片作业已从工作流中移除。相应的静态、lint、覆盖率、快照和场景分片选择器也已从仓库中移除，因此未使用的诊断路径无法继续维系第二套 CI 架构。

-Linux 主流程使用 3 个相互独立的 32 核作业。覆盖率单独运行，并设有自己的工作线程上限；静态调度器也单独运行，因此构建后的消费方不会拖延其结果。静态门禁完成后，该作业将其生成的 `apps/*/lib`、`packages/*/*/lib` 和 `vendor/*/lib` 目录树作为仅供本次运行使用的产物发布。第三个作业恢复完全相同的目录树，再让 lint、Node 24 运行时兼容性、依赖构建产物的快照和所有产物消费方基于构建完成后的工作树启动，而不重复构建。生成的 NodeNext 消费方目录不会纳入 ESLint 的文件发现范围，因为这些进程重叠执行时，产物检查会删除这些目录。pnpm store 和 ESLint 缓存会得到恢复，但缓存上传不会进入拉取请求关键路径。性能报告采用每个作业从 `startedAt` 到 `completedAt` 的区间；运行器排队延迟是容量证据，而非仓库执行时间。
+Linux 主流程使用 3 个相互独立的 32 核作业。覆盖率单独运行，并设有自己的工作线程上限；静态调度器也单独运行，因此构建后的消费方不会拖延其结果。静态门禁完成后，该作业将其生成的 `apps/*/lib`、`packages/*/*/lib` 和 `vendor/*/lib` 目录树作为仅供本次运行使用的产物发布。第三个作业恢复完全相同的目录树，再让 lint、Node 24 运行时兼容性、依赖构建产物的快照和所有产物消费方基于构建完成后的工作树启动，而不重复构建。生成的 NodeNext 消费方目录不会纳入 Oxlint 的文件发现范围，因为这些进程重叠执行时，产物检查会删除这些目录。pnpm store 会得到恢复，但缓存上传不会进入拉取请求关键路径；Oxlint 没有由仓库管理的结果缓存。性能报告采用每个作业从 `startedAt` 到 `completedAt` 的区间；运行器排队延迟是容量证据，而非仓库执行时间。

 门禁依赖关系保持显式。覆盖率消费源码，不等待构建。文档类型检查只构建一次完整的 project-reference 图。快照回放和发布消费方等待生成的输出，而 Node 版本兼容性作业会验证对运行时敏感的源码加载，且不重复主源码项目图的类型检查。PTY 和子进程套件继续使用自身有界的内部并发，不继承运行器的核心数。

--- a/Show More
+++ b/Show More