Merge master into subagent usage branch

# Conflicts:
#	.agents/notes/implemented/feature/2026-07-27-web-subagent-conversations.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-27-web-subagent-conversations.md
#	.agents/notes/implemented/feature/2026-07-27-web-subagent-conversations.zh.md
#	apps/web/tests/snapshots/subagent-conversation/tree.expected.md
#	apps/web/tests/subagent-conversation.e2e.ts
#	packages/client/ui-subagent/src/client/SubagentCatalogAction.tsx

.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-2026-07-08-agent-scope-contexts.md: e4c076189a8e8a438b561232d3779ad1f6ab0d08
-2026-07-08-agent-scope-contexts.zh.md: 35e725e43d402b048daf12c3b4be384b3fd2d2ce
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md
+2026-07-08-agent-scope-contexts.md: 5e09bdbcae1e57e6b65eb7d1720a6e7a7f758a9f
+2026-07-08-agent-scope-contexts.zh.md: 4714045f28e0386a3a53b53437d063462e75a9f1

.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md

@@ -108,11 +108,11 @@ A listener registered with `{ global: true }` deliberately bypasses contextual a
 
 ### Creation publishes last and disposal revokes last
 
-`ctx.agents.create()` and `resume()` build an unpublished session, scope, agent, and driver. They await `setup`, admit the final session and agent entries, announce them in order, start the loop, and only then return a handle.
+`ctx.agents.create()` and `resume()` build an unpublished session, scope, agent, and driver. They await `setup`, synchronously invoke its optional `AgentSetupCommit`, admit the final session and agent entries, announce them in order, start the loop, and only then return a handle. The commit lets mutable provisioning revalidate at the exact publication boundary after every setup await; a throw rolls the private transaction back before either identity is announced, while revocation after a successful commit is ordinary live teardown.
 
 An optional creation signal cancels work only while create or resume is pending. After the promise resolves, the returned `AgentHandle` owns explicit disposal.
 
-If loading, setup, admission, or publication fails, the private transaction rolls back everything it prepared. Concurrent operations using the same caller-supplied live ID may both reach setup, but final registry entry admits only one; every loser rejects and cleans its private resources. Sequential reuse after awaited disposal remains valid.
+If loading, setup, the optional setup commit, admission, or publication fails, the private transaction rolls back everything it prepared. Concurrent operations using the same caller-supplied live ID may both reach setup, but final registry entry admits only one; every loser rejects and cleans its private resources. Sequential reuse after awaited disposal remains valid.
 
 `AgentHandle.dispose()` reverses the boundary. It deactivates creation or driving, waits for synchronous publication to unwind, stops and drains the driver and final session flushes, detaches the agent and session, and finally disposes the scope. Repeated or racing disposal requests join one completion promise.
 
@@ -122,12 +122,14 @@ The calling Cordis context and the concrete AgentLoop factory are structural co-
 flowchart TB
   request["Create or resume"] --> privateWorld["Build private session, scope, agent, and driver"]
   privateWorld --> setup["Await composition through agent.ctx"]
-  setup --> admission["Admit final session and agent entries"]
+  setup --> setupCommit["Commit optional mutable provisioning"]
+  setupCommit --> admission["Admit final session and agent entries"]
   admission --> publish["Announce lifecycle and start the driver"]
   publish --> live["Return AgentHandle"]
 
   privateWorld -->|"failure, cancellation, or owner loss"| rollback["Rollback private work"]
   setup -->|"failure, cancellation, or owner loss"| rollback
+  setupCommit -->|"revalidation failure or owner loss"| rollback
   admission -->|"duplicate or owner loss"| rollback
   publish -->|"listener failure or owner loss"| rollback
   live -->|"handle or owner disposal"| quiesce["Stop and drain work"]
@@ -166,6 +168,6 @@ Parentage describes lifetime and conversation lineage, not a universal merge pol
 
 ## Consequences
 
-Contributors use one familiar pattern: register shared behavior through a plugin context, register local behavior through `agent.ctx`, select the real agent on operations, and dispose the returned handle. Setup is atomic from an observer's perspective, and teardown preserves local behavior until work stops.
+Contributors use one familiar pattern: register shared behavior through a plugin context, register local behavior through `agent.ctx`, select the real agent on operations, and dispose the returned handle. Setup and its optional publication commit are atomic from an observer's perspective, and teardown preserves local behavior until work stops.
 
 The cost is explicit subject selection, asynchronous programmatic creation, and service-specific scope adoption. Flat registration scope is intentionally not authority, and subagent composition controls remain a separate feature rather than hidden scope semantics.

.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md

@@ -108,11 +108,11 @@ setup 接收一个完整的受信 Cordis 上下文，因此可以组合普通插
 
 ### 创建最后发布，dispose 最后撤销
 
-`ctx.agents.create()` 和 `resume()` 构建未发布的会话、作用域、agent 和驱动器。它们等待 `setup`，准入最终的会话和 agent 条目，按序公告，启动循环，然后才返回 handle。
+`ctx.agents.create()` 和 `resume()` 构建未发布的会话、作用域、agent 和驱动器。它们等待 `setup`，同步调用其可选的 `AgentSetupCommit`，准入最终的会话和 agent 条目，按序公告，启动循环，然后才返回 handle。该提交操作让可变的配置状态在所有 setup 的 await 均结算后，于确切的发布边界重新校验；若其抛出异常，则会在公告任何一个身份前回滚私有事务，而成功提交后的撤销属于普通的实时拆卸。
 
 可选的创建信号仅在创建或恢复挂起期间取消工作。promise resolve 后，返回的 `AgentHandle` 拥有显式 dispose 权。
 
-如果加载、setup、准入或发布失败，私有事务回滚其准备的一切。使用同一个调用方提供的存活 ID 的并发操作可能都到达 setup，但最终注册表条目只准入一个；每个失败者拒绝并清理其私有资源。在等待 dispose 完成后的顺序复用仍然有效。
+如果加载、setup、可选的 setup 提交、准入或发布失败，私有事务回滚其准备的一切。使用同一个调用方提供的存活 ID 的并发操作可能都到达 setup，但最终注册表条目只准入一个；每个失败者拒绝并清理其私有资源。在等待 dispose 完成后的顺序复用仍然有效。
 
 `AgentHandle.dispose()` 反转边界。它停用创建或驱动，等待同步发布解除，停止并排空驱动器和最终会话刷写，分离 agent 和会话，最后 dispose 作用域。重复或竞争的 dispose 请求合并为一个完成 promise。
 
@@ -122,12 +122,14 @@ setup 接收一个完整的受信 Cordis 上下文，因此可以组合普通插
 flowchart TB
   request["Create or resume"] --> privateWorld["Build private session, scope, agent, and driver"]
   privateWorld --> setup["Await composition through agent.ctx"]
-  setup --> admission["Admit final session and agent entries"]
+  setup --> setupCommit["Commit optional mutable provisioning"]
+  setupCommit --> admission["Admit final session and agent entries"]
   admission --> publish["Announce lifecycle and start the driver"]
   publish --> live["Return AgentHandle"]
 
   privateWorld -->|"failure, cancellation, or owner loss"| rollback["Rollback private work"]
   setup -->|"failure, cancellation, or owner loss"| rollback
+  setupCommit -->|"revalidation failure or owner loss"| rollback
   admission -->|"duplicate or owner loss"| rollback
   publish -->|"listener failure or owner loss"| rollback
   live -->|"handle or owner disposal"| quiesce["Stop and drain work"]
@@ -166,6 +168,6 @@ agent 作用域组合的是受信的同进程注册。它不沙箱化插件、
 
 ## 后果
 
-贡献者使用一种熟悉的模式：通过插件上下文注册共享行为，通过 `agent.ctx` 注册本地行为，在操作中选择真实 agent，dispose 返回的 handle。从观察者角度看 setup 是原子的，拆除则保留本地行为直到工作停止。
+贡献者使用一种熟悉的模式：通过插件上下文注册共享行为，通过 `agent.ctx` 注册本地行为，在操作中选择真实 agent，dispose 返回的 handle。从观察者角度看，setup 及其可选的发布提交是原子的，拆除则保留本地行为直到工作停止。
 
 代价是显式的主体选择、异步的编程式创建，以及服务需要逐个采纳作用域。扁平注册作用域有意不等同于权限，subagent 组合控制作为独立功能存在，而非隐藏的作用域语义。

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

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

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

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

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

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

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

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-2026-07-19-model-facing-goal-tools.md: bc4305af80bb13ceeff1888d489dcd8a00132f94
-2026-07-19-model-facing-goal-tools.zh.md: b07f62aa526902c4b2e9c081777a76ca53783d31
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md
+2026-07-19-model-facing-goal-tools.md: 18235c484194f5daf10556ebfc13bdc2d672be2e
+2026-07-19-model-facing-goal-tools.zh.md: cc23a76e5faac2c203052d834ca0a87ca5dbed2a

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

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

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

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

.agents/notes/implemented/feature/2026-07-27-web-subagent-conversations.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-27-web-subagent-conversations.md
-2026-07-27-web-subagent-conversations.md: 6658bcc960ec691f3646f4ff08d8a065d3a8d70a
-2026-07-27-web-subagent-conversations.zh.md: 5e89c9a7a420687c53be961245de7adb99bf3c44
+2026-07-27-web-subagent-conversations.md: f4d2035dfc7224cd7a11575449ff79cdae3fce48
+2026-07-27-web-subagent-conversations.zh.md: 79ce2711af32fb67685f29d48fc53d29376907f4

.agents/notes/implemented/feature/2026-07-27-web-subagent-conversations.md

@@ -37,7 +37,7 @@ The Figma [subagent list](https://www.figma.com/design/jRBBK7zBgcszdVWQ0Fh5J8/Ha
 
 ## Product contract
 
-The header action is absent only after a complete empty direct-catalog response. Its trigger counts every known session-summary descendant reached through an uninterrupted `origin: 'subagent'` lineage, stops at ordinary forks, and shows ongoing activity when any counted descendant is running. Every healthy direct-catalog row carries a read-time `hasChildren` hint derived only from direct lineage headers with durable `origin: 'subagent'`; normal healthy and diagnostic subagent candidates carry that marker, while ordinary forks do not. This lookahead reads no descendant event log, and the descriptor-backed catalog loaded after disclosure remains authoritative. The UI omits disclosure for a known leaf before interaction; the hint does not promise that the child will remain a leaf. While an expanded direct catalog is loading, known lineage reserves one disabled loading row per direct descendant without recursively fetching descendant catalogs. The tree then presents continuable and one-shot rows, falling back to the session id when an optional one-shot label is absent. Corrupt, unsupported, and unavailable candidates remain visible as disabled diagnostic rows.
+The header action is absent only when a complete empty direct-catalog response agrees with the session-summary projection that no subagent descendants are known. Its trigger counts every known session-summary descendant reached through an uninterrupted `origin: 'subagent'` lineage, stops at ordinary forks, and shows ongoing activity when any counted descendant is running. Every healthy direct-catalog row carries a read-time `hasChildren` hint derived only from direct lineage headers with durable `origin: 'subagent'`; normal healthy and diagnostic subagent candidates carry that marker, while ordinary forks do not. This lookahead reads no descendant event log, and the descriptor-backed catalog loaded after disclosure remains authoritative. When summaries establish descendants before that catalog exists or after a stale empty response, the action stays visible and exposes only disabled loading rows until opening it refreshes the catalog; summary-only rows never grant navigation. The UI omits disclosure for a known leaf before interaction; the hint does not promise that the child will remain a leaf. While an expanded direct catalog is loading, known lineage reserves one disabled loading row per direct descendant without recursively fetching descendant catalogs. The tree then presents continuable and one-shot rows, falling back to the session id when an optional one-shot label is absent. Corrupt, unsupported, and unavailable candidates remain visible as disabled diagnostic rows.
 
 `running` means the exact child Agent driver is draining work at the Host sampling boundary; `inactive` means that driver is idle or absent. The UI does not translate either value into success, failure, cancellation, completeness, or resumability. `subagent.list` supplies the current driver-status baseline, `host/session-status` updates known activity in place, request-local replay prevents an older in-flight list response from overwriting a newer transition, and `host/session-removed` returns a known row to `inactive`; reconnect reads a fresh baseline. A `host/session-added` frame for a direct subagent immediately flips any loaded parent row to `hasChildren: true`, and that positive hint survives an older in-flight catalog response; membership, labels, mode, diagnostics, and the authoritative snapshot still require a debounced `subagent.list` refresh while the affected branch is open. A prompt response remains delivery-time authority.
 
@@ -104,8 +104,8 @@ The shipped Web composition mounts SQLite session query beside JSONL persistence
 - Host protocol tests pin schemas including required boolean expandability, id echoing, mode verification, non-activating history, exact-parent enforcement, FIFO admission receipts, cancellation, and sanitized failure mapping.
 - Generic Host tests pin attached and cold history and forks without Agent publication, cold projection folding, descriptor/origin/runtime-owner denial, explicit-id adoption denial, and the direct queue-control fence.
 - Client object tests pin retained and restored addresses, one-shot read-only rejection, history routing, continuable prompt routing, no addressed cancellation, suppression of Agent-bound model controls, live activity flips including in-flight response replay and detach fallback, subagent-parent expandability flips, and membership refresh.
-- jsdom tests pin the aggregate descendant count and activity, token totals, second-precision running and frozen inactive durations, known loading-row shape, mixed-mode rows, pre-click leaf disclosure, diagnostics, lazy descendant disclosure, direct-parent addresses, keyboard behavior, and both read-only reasons.
-- The keyless assembled Web snapshot contains an inactive continuable child with durable usage, an inactive one-shot sibling, and a persisted grandchild; it pins the three-descendant trigger, usage and timing rows, and aggregate running transition, expands without activation, opens persisted history, admits a human FIFO follow-up, reconciles child mux events, and proves one-shot history remains read-only.
+- jsdom tests pin the aggregate descendant count and activity, token totals, second-precision running and frozen inactive durations, the summary-backed root action across absent and stale-empty catalogs, known loading-row shape, mixed-mode rows, pre-click leaf disclosure, diagnostics, lazy descendant disclosure, direct-parent addresses, keyboard behavior, and both read-only reasons.
+- The keyless assembled Web snapshot contains an inactive continuable child with durable usage, an inactive one-shot sibling, and a persisted grandchild; it pins the three-descendant trigger across a stale empty catalog response, usage and timing rows, and aggregate running transition, expands without activation, opens persisted history, admits a human FIFO follow-up, reconciles child mux events, and proves one-shot history remains read-only.
 - Navigation tests pin subagent-only breadcrumbs, workspace placement for forks created from subagents, and `origin: 'subagent'` sidebar filtering without hiding ordinary forks.
 
 ## Consequences

.agents/notes/implemented/feature/2026-07-27-web-subagent-conversations.zh.md

@@ -37,7 +37,7 @@ Figma 中的 [subagent 列表](https://www.figma.com/design/jRBBK7zBgcszdVWQ0Fh5
 
 ## 产品契约
 
-只有在完整的直接目录响应为空后，才不显示页头操作。其触发器会统计经不间断的 `origin: 'subagent'` 谱系可达的每个已知会话摘要后代，在普通 fork 处停止，并在任一计入统计的后代处于 `running` 时显示活动仍在进行。每个健康的直接目录行都携带读取时的 `hasChildren` 提示，该值只根据持久化 `origin: 'subagent'` 的直接谱系 header 派生；正常的健康与 diagnostic subagent 候选都会携带该标记，而普通 fork 不会。该预查不读取任何后代事件日志，展开后仍以描述符支撑的目录为权威依据。UI 会在交互前就省略已知叶子节点的展开控件；该提示不承诺 child 会一直是叶子。已展开的直接目录加载期间，已知谱系会为每个直接后代预留一行禁用的加载行，而不会递归获取后代目录。随后树会呈现可继续与 one-shot 行；one-shot 的可选 label 缺失时，回退到其会话 id。损坏、不受支持或不可用的候选仍以禁用的 diagnostic 行显示。
+只有当完整的直接目录空响应与会话摘要投影相符，二者均表明没有已知的 subagent 后代时，才不显示页头操作。其触发器会统计经不间断的 `origin: 'subagent'` 谱系可达的每个已知会话摘要后代，在普通 fork 处停止，并在任一计入统计的后代处于 `running` 时显示活动仍在进行。每个健康的直接目录行都携带读取时的 `hasChildren` 提示，该值只根据持久化 `origin: 'subagent'` 的直接谱系 header 派生；正常的健康与 diagnostic subagent 候选都会携带该标记，而普通 fork 不会。该预查不读取任何后代事件日志，展开后仍以描述符支撑的目录为权威依据。当摘要在该目录尚不存在时或在一次陈旧的空响应后确认已有后代时，该操作会保持可见，并且在打开它以刷新目录之前仅显示禁用的加载行；仅由摘要支撑的行绝不会提供导航能力。UI 会在交互前就省略已知叶子节点的展开控件；该提示不承诺 child 会一直是叶子。已展开的直接目录加载期间，已知谱系会为每个直接后代预留一行禁用的加载行，而不会递归获取后代目录。随后树会呈现可继续与 one-shot 行；one-shot 的可选 label 缺失时，回退到其会话 id。损坏、不受支持或不可用的候选仍以禁用的 diagnostic 行显示。
 
 `running` 表示在 Host 采样边界，确切 child Agent driver 正在处理工作；`inactive` 表示该 driver 空闲或不存在。UI 不会把任一值解释为成功、失败、取消、完成状态或可恢复性。`subagent.list` 提供当前 driver 状态基线，`host/session-status` 会就地更新已知活动状态，请求内回放会阻止更早发起但尚未完成的列表响应覆盖较新的状态转换，`host/session-removed` 则会使已知行恢复为 `inactive`；重连时会读取新的基线。直接 subagent 的 `host/session-added` 帧会立即把任何已加载的 parent 行翻转为 `hasChildren: true`，并使这项正向提示不被更早发起但尚未完成的目录响应覆盖；受影响分支打开期间，成员、label、mode、diagnostic 与权威快照仍需要通过去抖动的 `subagent.list` 刷新来更新。消息投递时仍以提示词响应为权威依据。
 
@@ -104,8 +104,8 @@ one-shot 行始终会用文案替代输入框，说明执行记录为只读。
 - 宿主协议测试固定 schema（包括必需的布尔可展开性）、id 回显、mode 校验、非激活式历史、确切 parent 强制要求、FIFO 准入回执、取消与脱敏后的失败映射。
 - 通用 Host 测试固定在不发布 Agent 的情况下读取已附加与冷态历史及执行 fork、冷态投影归并、按描述符／origin／运行时 owner 拒绝、拒绝显式 id 接纳，以及直接队列控制栅栏。
 - 客户端对象测试固定已保留与已恢复的地址、one-shot 只读拒绝、历史路由、可继续提示词路由、已寻址对话不提供取消、屏蔽绑定到 agent 的模型控件、实时活动状态翻转（包括在途响应回放与 detach 回退）、subagent parent 可展开性翻转与成员刷新。
-- jsdom 测试固定后代聚合计数与活动状态、token 总量、精确到秒的运行中耗时与冻结后 inactive 耗时、已知加载行的形态、混合 mode 行、点击前的叶子展开控件、diagnostic、后代懒加载展开、直接 parent 地址、键盘行为与两种只读原因。
-- 无密钥的组装 Web 快照包含一个具有持久化用量的 inactive 可继续 child、一个 inactive 的 one-shot sibling 和一个持久化 grandchild；它会固定触发器显示三个后代、用量与计时行，以及聚合 `running` 状态转换，在不激活的情况下展开、打开持久化历史、准入一条用户 FIFO 后续消息、归并 child mux 事件，并证明 one-shot 历史仍然只读。
+- jsdom 测试固定后代聚合计数与活动状态、token 总量、精确到秒的运行中耗时与冻结后 inactive 耗时、目录缺失或为陈旧空目录时由摘要支撑的根操作、已知加载行的形态、混合 mode 行、点击前的叶子展开控件、diagnostic、后代懒加载展开、直接 parent 地址、键盘行为与两种只读原因。
+- 无密钥的组装 Web 快照包含一个具有持久化用量的 inactive 可继续 child、一个 inactive 的 one-shot sibling 和一个持久化 grandchild；它会固定触发器在一次陈旧的空目录响应后仍显示三个后代，并固定用量与计时行以及聚合 `running` 状态转换，在不激活的情况下展开、打开持久化历史、准入一条用户 FIFO 后续消息、归并 child mux 事件，并证明 one-shot 历史仍然只读。
 - 导航测试固定仅含 subagent 的面包屑导航、从 subagent 创建 fork 时的 Workspace 归属，以及 `origin: 'subagent'` 侧边栏过滤，同时不隐藏普通 fork。
 
 ## 后果

.agents/notes/implemented/feature/2026-07-30-continuable-subagent-report-tool.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-continuable-subagent-report-tool.md
-2026-07-30-continuable-subagent-report-tool.md: 24922cfe88084bb0f9fea8c9363980a224b875da
-2026-07-30-continuable-subagent-report-tool.zh.md: bb0b1847f157dba6116526851194cf1228e52e49
+2026-07-30-continuable-subagent-report-tool.md: 8324f1fa08f7dace6153712575e7e70a07ee9344
+2026-07-30-continuable-subagent-report-tool.zh.md: e7599c1d85328e83c7773718101b59e763a1e37f

.agents/notes/implemented/feature/2026-07-30-continuable-subagent-report-tool.md

@@ -54,7 +54,7 @@ The first version provides no durable mailbox, idempotency key, delivery receipt
 
 The subagent seam adds `registerContinuableSetup(contribution): () => void`, backed by `SubagentActivationSetupRegistry`. Each synchronous contribution receives the unpublished child context and returns the disposer for its installation. The continuation manager first applies base child composition, then current contributions in registration order through the same setup closure used for fresh creation and cold resume.
 
-The registry owns registration, per-child installation records, setup rollback, child-scope cleanup, and immediate revocation. A throwing or concurrently revoked contribution rejects before Activation publication and rolls back the batch. New registrations affect a resident child only on its next Activation; removing a registration first closes it to new setup and then revokes every provisioning or resident installation immediately. Registration disposal and child-context disposal are idempotent and attempt every release before aggregating failures.
+The registry owns registration, per-child installation records, setup rollback, child-scope cleanup, and immediate revocation. Applying a batch returns the Agent setup commit that revalidates provisioning after every setup await and immediately before Agent publication. A throwing or concurrently revoked contribution therefore rejects before either Agent or Session publication and rolls back the batch. New registrations affect a resident child only on its next Activation; removing a registration first closes it to new setup and then revokes every provisioning or resident installation immediately. Registration disposal and child-context disposal are idempotent and attempt every release before aggregating failures.
 
 This seam keeps the continuation manager unaware of tool names. The report package installs only `report`; `@deepseek-ai/dsh-tool-subagent-control` independently installs parent-side `send_message` and `list_agents`. A deployment can install either direction, both, or neither. Providers remain data-only, durable descriptors do not snapshot report availability or delivery mode, and cold resume uses the deployment's current contributions and policy.
 
@@ -94,6 +94,10 @@ Mutating or cold-resuming an absent parent requires a new durable addressing, au
 
 A result-bearing wrapper makes one report or one turn appear terminal and recreates the lifetime mismatch that continuable Activations removed. Explicit repeatable sends need no intermediate execution object.
 
+### Validate setup after Agent creation
+
+A post-creation revocation check can reject the Activation only after the Agent and Session have been published. Disposing the returned handle removes the live objects but cannot delete persistence through the current seam, leaving a resumable child that the continuation manager said was never established. Returning an `AgentSetupCommit` instead lets the Agent factory perform the same mutable-state check synchronously at its publication boundary.
+
 ## Consequences
 
 - A continuable in-process child exposes exactly one scope-local `report` schema only while the report package's contribution is installed; unrelated Agents never expose it.
@@ -112,5 +116,3 @@ The acceptance boundary is weaker than durable end-to-end delivery. A crash can
 Wakeup mode can amplify model work when nested children report frequently. Deployment ownership and a quiet default limit but do not remove that risk.
 
 Registry presence is the parent liveness signal. A host-owned parent whose `AgentHandle.dispose()` has started but has not yet unwound its scope can still accept and append a report that it will not act on in this process. Closing that gap requires an Agent-level disposal-start signal rather than subagent-layer inference.
-
-The final setup-revocation check runs after `ctx.agents.create()` or `ctx.agents.resume()` returns, after lower-level Agent and Session publication. Revocation in this window rolls back the handle and prevents the subagent Activation start edge but may leave a persisted Session. Moving the cutoff before lower-level publication requires a future Agent-creation setup transaction seam.

.agents/notes/implemented/feature/2026-07-30-continuable-subagent-report-tool.zh.md

@@ -54,7 +54,7 @@ root、one-shot child、伪造对象、陈旧 Agent 和同 id 替换对象都以
 
 subagent seam 新增 `registerContinuableSetup(contribution): () => void`，由 `SubagentActivationSetupRegistry` 支撑。每个同步贡献都会接收尚未发布的 child 上下文，并返回其安装的 disposer。继续执行管理器首先应用基础 child 组合，然后通过同一个用于首次创建与冷恢复的设置闭包，按注册顺序应用当前贡献。
 
-注册表负责注册、每个 child 的安装记录、设置回滚、child 作用域清理和立即撤销。某项贡献抛出异常或被并发撤销时，会在 Activation 发布前拒绝操作并回滚该批次。新注册项只会在驻留 child 的下一个 Activation 生效；移除注册项时，会先将它对新设置关闭，再立即撤销为正在配置或驻留的每个 child 安装的实例。注册 dispose 与 child 上下文 dispose 都是幂等的，两者都会先尝试每项释放，再聚合失败。
+注册表负责注册、每个 child 的安装记录、设置回滚、child 作用域清理和立即撤销。应用一个批次会返回 Agent setup 提交对象，用于在所有 setup 的 await 均结算后、紧邻 Agent 发布前重新校验配置状态。因此，某项贡献抛出异常或被并发撤销时，会在 Agent 与 Session 发布前拒绝操作并回滚该批次。新注册项只会在驻留 child 的下一个 Activation 生效；移除注册项时，会先将它对新设置关闭，再立即撤销为正在配置或驻留的每个 child 安装的实例。注册 dispose 与 child 上下文 dispose 都是幂等的，两者都会先尝试每项释放，再聚合失败。
 
 该 seam 使继续执行管理器无需知道工具名。report 包只安装 `report`；`@deepseek-ai/dsh-tool-subagent-control` 则独立安装 parent 侧的 `send_message` 和 `list_agents`。部署时可安装任一方向、同时安装两者或两者均不安装。提供方仍只负责数据，持久化描述符不会对 report 可用性或投递模式建立快照，冷恢复则使用部署当前的贡献与策略。
 
@@ -94,6 +94,10 @@ ACP（Agent Client Protocol）快照 harness 新增 `waitForSubagentTurnEnd`，
 
 承载结果的包装层会让一次报告或一个轮次看似具有终止性，并重新引入可继续 Activation 已经移除的生命周期不匹配。显式、可重复的发送无需中间执行对象。
 
+### 在 Agent 创建后校验 setup
+
+创建完成后的撤销检查只能在 Agent 与 Session 均已发布后拒绝 Activation。对返回的 handle 执行 dispose 会移除实时对象，但当前 seam 无法删除持久化内容，因此会留下一个仍可恢复的 child，而继续执行管理器却判定它从未建立。改为返回 `AgentSetupCommit`，Agent 工厂便可在自身的发布边界同步执行同一项可变状态检查。
+
 ## 影响
 
 - 只有安装 report 包贡献时，可继续进程内 child 才会恰好暴露一个作用域局部 `report` schema；无关 Agent 永远不会暴露该 schema。
@@ -112,5 +116,3 @@ ACP（Agent Client Protocol）快照 harness 新增 `waitForSubagentTurnEnd`，
 wakeup 模式可能在嵌套 child 频繁报告时放大模型工作量。由部署所有者控制并默认静默，可以限制该风险，但无法完全消除。
 
 注册表中的存在性就是 parent 在线信号。宿主拥有的 parent 如果已开始 `AgentHandle.dispose()` 但尚未展开其作用域，仍可能接受并追加一条本进程不会再处理的报告。要弥合这个缺口，需要 Agent 层面的 dispose 开始信号，不能由 subagent 层推断。
-
-最终 setup 撤销检查发生在 `ctx.agents.create()` 或 `ctx.agents.resume()` 返回之后，此时底层 Agent 和 Session 已经发布。在该窗口内撤销会回滚 handle，并阻止 subagent Activation 的 start 边，但可能留下持久化 Session。若要把截止点移到底层发布之前，需要未来提供 Agent 创建 setup 事务 seam。

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

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

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

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

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

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

.agents/notes/implemented/simplification/2026-07-27-intent-named-subagent-continuation-operations.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-07-27-intent-named-subagent-continuation-operations.md
-2026-07-27-intent-named-subagent-continuation-operations.md: 5029d8335f699e99e67c6027b7d1666880db4724
-2026-07-27-intent-named-subagent-continuation-operations.zh.md: 0785730c1934a192380af41f3ad88f95a2747cf7
+2026-07-27-intent-named-subagent-continuation-operations.md: e74d62b7582e92f8e5ce68327a677259c8453d24
+2026-07-27-intent-named-subagent-continuation-operations.zh.md: dae4dd37fa9950f0b8d1ba6ec5c46b99977a7201

.agents/notes/implemented/simplification/2026-07-27-intent-named-subagent-continuation-operations.md

@@ -4,7 +4,7 @@ Status: implemented
 
 English | [中文](2026-07-27-intent-named-subagent-continuation-operations.zh.md)
 
-The `followup` operation this record names is retained by [Continuable subagents](../feature/2026-07-28-continuable-subagent-conversations.md), which replaces its Task-backed return value with the accepted `MessageId`, retains its bare `Agent` parameter as exact live-direct-parent authority, and replaces provider `resume` dispatch with `prepareContinuable`.
+The current activation-based realization is owned by [Continuable subagents](../feature/2026-07-28-continuable-subagent-conversations.md). It retains the `followup` operation this record names, returns the accepted `MessageId`, uses the bare `Agent` parameter as exact live-direct-parent authority, and limits provider participation in continuable children to `prepareContinuable`.
 
 ## Problem
 
@@ -14,25 +14,25 @@ The durability boundary also exposed both `SessionStore.flush()` and `flushRequi
 
 ## Decision
 
-`SubagentService` exposes three execution intents: `start(name, request)` for an ordinary holder-owned run, `startContinuable(spec)` for a durable Task-backed child, and `followup(parent, childId, content, { source, signal })` for later content. The last verb matches `Agent.followup()`, while `SubagentRun.steer()` remains the narrower confirmed live-activation capability. The model-facing tool keeps its stable `send_message` name and delegates routing to `followup()`.
+`SubagentService` separates four execution intents: `start(name, request)` returns an ordinary holder-owned one-shot run; `startContinuable(spec)` establishes a durable child and returns its id plus the accepted initial `MessageId`; `followup(parent, childId, content, { source, signal })` sends later parent content; and `reportFrom(child, content, { delivery, signal })` sends selected child content to its direct parent. `followup` matches `Agent.followup()`, while `SubagentRun.steer()` remains the narrower confirmed live-run capability. The model-facing tools keep their stable `send_message` and `report` names and delegate routing to the corresponding intent methods.
 
-Caller and provider requests are distinct. `SubagentStartRequest` contains only caller-supplied start data; `SubagentProviderStartRequest` adds service-resolved continuation state. Ordinary `start()` clears that state before provider dispatch. `SubagentProviderResumeRequest` remains part of the provider seam, but `SubagentService.resume()` is absent: the continuation manager loads the descriptor, authorizes the parent, and invokes private provider start/resume closures owned by the service. Provider dispatch still receives the same capability checks and run lifecycle observation without becoming a caller operation.
+Caller and provider requests are distinct. `SubagentStartRequest` contains caller-supplied one-shot data; `ResolvedSubagentStartRequest` adds the service-resolved descriptor before `SubagentProvider.start()`. For continuable creation, the manager passes a `ContinuableCreateRequest` to optional `SubagentProvider.prepareContinuable()` and receives detached creation data only. `SubagentService.resume()` and provider resume dispatch are absent: the continuation manager loads the descriptor, authorizes the parent, and owns Agent materialization, prompt delivery, cold resume, and teardown.
 
-`SessionStore.flush(session)` returns `Promise<boolean>`. It resolves `true` after at least one scoped durability listener participates successfully, resolves `false` for an empty listener snapshot, and rejects with the first registered listener failure after all listeners settle. Ordinary checkpoints may ignore the boolean. A continuable provider requires `true` at its final result boundary and maps `false` or rejection to `DURABILITY_FAILED`.
+`SessionStore.flush(session)` is the single durability barrier and returns `Promise<boolean>`. It resolves `true` after at least one scoped listener participates successfully, resolves `false` for an empty listener snapshot, and rejects with the first registered listener failure after all listeners settle. Participation cannot identify whether a selected persistence backend stored the state. Ordinary checkpoints may ignore the boolean; the continuation manager also treats its final flush as a best-effort barrier, deliberately ignores participation, logs rejection, and still disposes the child and releases ownership.
 
 ## Alternatives considered
 
-**Keep public provider resume dispatch.** No production caller outside the continuation manager owns the descriptor lookup, direct-parent authorization, Task cancellation, and activation association needed to call it safely. A public method would expose resolved implementation data without a valid independent intent.
+**Keep public provider resume dispatch.** No production caller outside the continuation manager owns descriptor lookup, direct-parent authorization, Agent materialization, Activation ownership, and child-first teardown. A public method would expose resolved implementation data without a valid independent intent; providers instead contribute detached first-creation data through `prepareContinuable` and never participate in cold resume.
 
 **Keep `sendMessage` on the service.** The model tool sends a message, but the service operation represents a follow-up that may steer or cold-resume. `followup` aligns with the structural `Agent` interface and does not promise a particular route.
 
 **Keep `flushRequired()`.** A second method hides only an empty-listener check. Returning participation from the existing barrier keeps dispatch in one implementation and lets each caller state whether absence is acceptable.
 
-**Fold ordinary and continuable starts together.** A flag would make one method return either an awaited holder-owned run or immediate child/Task identities. Separate intent methods preserve the ownership and timing distinction without a return union.
+**Fold ordinary and continuable starts together.** A flag would make one method return either an awaited holder-owned one-shot run or immediate durable child and message identities. Separate intent methods preserve the ownership and timing distinction without a return union.
 
 ## Consequences
 
-- The Cordis service catalog contains only caller operations; provider reconstruction remains extensible through `SubagentProvider.resume?()` without exposing its resolved request as a service method.
+- The Cordis service catalog contains only caller operations; a provider can opt into continuable first creation through `SubagentProvider.prepareContinuable?()` without receiving Agent lifecycle authority or a public resume operation.
 - Follow-up source and cancellation travel in one options object, matching the intent-helper shape on `Agent` while retaining the existing live-delivery and cold-resume semantics.
-- Session durability has one barrier operation. Callers that require a backend must inspect its participation result rather than selecting a second dispatch method.
-- The `send_message` schema, route results, Task ownership, durable event vocabulary, and model-visible transcript remain unchanged.
+- Session durability has one barrier operation. Its participation result remains observable, but no continuable-child path treats arbitrary listener participation as proof that a persistence backend stored the state.
+- The `send_message` and `report` schemas, accepted message identities, `AgentHandle` ownership, durable event vocabulary, and model-visible transcript follow the activation-based realization linked above.

.agents/notes/implemented/simplification/2026-07-27-intent-named-subagent-continuation-operations.zh.md

@@ -4,7 +4,7 @@ Status: implemented
 
 [English](2026-07-27-intent-named-subagent-continuation-operations.md) | 中文
 
-本记录命名的 `followup` 操作由[可继续的 subagent](../feature/2026-07-28-continuable-subagent-conversations.md)保留，但后者以已接受的 `MessageId` 替换其基于 Task 的返回值，保留裸 `Agent` 参数作为准确的实时直属父级权限，并以 `prepareContinuable` 替换提供方 `resume` 派发。
+当前基于 Activation 的实现由[可继续的 subagent](../feature/2026-07-28-continuable-subagent-conversations.md)负责。它保留本记录命名的 `followup` 操作，返回已接受的 `MessageId`，使用裸 `Agent` 参数作为确切的在线直属父级权限，并将提供方对可继续 child 的参与限制为 `prepareContinuable`。
 
 ## 问题
 
@@ -14,25 +14,25 @@ Status: implemented
 
 ## 决策
 
-`SubagentService` 公开三种执行意图：`start(name, request)` 用于普通的、由持有方负责的 run；`startContinuable(spec)` 用于具备持久性且由 Task 支撑的 child；`followup(parent, childId, content, { source, signal })` 用于投递后续内容。最后一个动词与 `Agent.followup()` 一致，而 `SubagentRun.steer()` 仍是范围更窄的能力，仅向已确认仍在运行的激活提供 steering（中途引导）。面向模型的工具保留稳定的 `send_message` 名称，并将路由委托给 `followup()`。
+`SubagentService` 分离四种执行意图：`start(name, request)` 返回普通的、由持有方负责的 one-shot run；`startContinuable(spec)` 建立持久化 child，并返回其 id 与已接受的初始 `MessageId`；`followup(parent, childId, content, { source, signal })` 发送后续 parent 内容；`reportFrom(child, content, { delivery, signal })` 将选定的 child 内容发送给其直接 parent。`followup` 与 `Agent.followup()` 一致，而 `SubagentRun.steer()` 仍是范围更窄的能力，仅向已确认仍在运行的 run 提供 steering。面向模型的工具保留稳定的 `send_message` 与 `report` 名称，并将路由委托给对应的意图方法。
 
-调用方请求与提供方请求相互分离。`SubagentStartRequest` 只包含调用方提供的启动数据；`SubagentProviderStartRequest` 则加入由服务解析的继续执行状态。普通 `start()` 在分发给提供方之前会清除该状态。`SubagentProviderResumeRequest` 仍属于提供方 seam，但 `SubagentService.resume()` 不对外公开：继续执行管理器加载描述符、对 parent 进行鉴权，并调用由服务持有的私有提供方启动与恢复闭包。提供方分发仍会经过相同的功能检查和 run 生命周期观测，而无需将其变成调用方操作。
+调用方请求与提供方请求相互分离。`SubagentStartRequest` 包含调用方提供的 one-shot 数据；`ResolvedSubagentStartRequest` 会在调用 `SubagentProvider.start()` 前加入由服务解析的描述符。创建可继续 child 时，管理器将 `ContinuableCreateRequest` 传给可选的 `SubagentProvider.prepareContinuable()`，且只接收分离的创建数据。`SubagentService.resume()` 与提供方恢复分发均不存在：继续执行管理器加载描述符、对 parent 进行鉴权，并负责 Agent 实体化、提示词投递、冷恢复与 teardown。
 
-`SessionStore.flush(session)` 返回 `Promise<boolean>`。至少一个作用域内的持久性监听器成功参与后，它解析为 `true`；监听器快照为空时解析为 `false`；所有监听器结算后，如有失败，则以注册顺序最靠前的监听器错误拒绝。普通检查点可以忽略该布尔值。可继续提供方在最终结果边界要求该值为 `true`，并将 `false` 或拒绝映射为 `DURABILITY_FAILED`。
+`SessionStore.flush(session)` 是唯一的持久性屏障，并返回 `Promise<boolean>`。至少一个作用域内监听器成功参与后，它解析为 `true`；监听器快照为空时解析为 `false`；所有监听器结算后，如有失败，则以注册顺序最靠前的监听器错误拒绝。参与结果无法表明所选的持久化后端是否已经存储状态。普通检查点可以忽略该布尔值；继续执行管理器同样将最终 flush 视为 best-effort 屏障，有意忽略参与结果，记录拒绝日志，并仍会对 child 执行 dispose（资源释放）并释放所有权。
 
 ## 已考虑的替代方案
 
-**保留公开的提供方恢复分发。** 继续执行管理器之外没有任何生产调用方负责安全调用所需的描述符查找、直接 parent 鉴权、Task 取消与激活关联。公开方法会暴露已解析的实现数据，但并不存在与之对应的合理独立调用意图。
+**保留公开的提供方恢复分发。** 继续执行管理器之外，没有任何生产调用方同时负责安全调用所需的描述符查找、直接 parent 鉴权、Agent 实体化、Activation 所有权与 child-first teardown。公开方法会暴露已解析的实现数据，却没有合理的独立调用意图；提供方改为通过 `prepareContinuable` 贡献分离的首次创建数据，且从不参与冷恢复。
 
 **在服务上保留 `sendMessage`。** 面向模型的工具发送消息，但服务操作表达的是后续操作，既可能对运行中的激活执行 steering，也可能从持久化存储恢复。`followup` 与结构化 `Agent` 接口保持一致，也不承诺特定路由。
 
 **保留 `flushRequired()`。** 第二个方法只封装了空监听器检查。由现有屏障返回是否有监听器参与，可以让分发只保留一套实现，并让每个调用方自行判定缺少监听器是否可接受。
 
-**合并普通启动与可继续启动。** 一个标志会让同一方法要么等待由持有方负责的 run 就绪后返回，要么立即返回 child 和 Task 标识。按意图拆分的方法无需返回值联合类型即可保留所有权与时序差异。
+**合并普通启动与可继续启动。** 一个标志会让同一方法要么等待由持有方负责的 one-shot run 就绪后返回，要么立即返回持久化 child 与消息标识。按意图拆分的方法无需返回值联合类型即可保留所有权与时序差异。
 
 ## 影响
 
-- Cordis 服务目录只包含调用方操作；提供方的重建能力仍可通过 `SubagentProvider.resume?()` 扩展，同时不会将已解析的请求暴露为服务方法。
+- Cordis 服务目录只包含调用方操作；提供方可以通过 `SubagentProvider.prepareContinuable?()` 选择参与可继续 child 的首次创建，但不会获得 Agent 生命周期权限或公开恢复操作。
 - 后续操作的来源与取消信号通过同一个选项对象传递，与 `Agent` 上按意图命名的辅助方法形态一致，同时保留在线投递与从持久化存储恢复的语义。
-- 会话持久性只保留一个屏障操作。需要后端参与的调用方必须检查参与结果，而不是选择第二种分发方法。
-- `send_message` schema、路由结果、Task 所有权、持久化事件词汇与模型可见的 transcript（文本记录）保持不变。
+- 会话持久性只有一个屏障操作。参与结果仍可观测，但任何可继续 child 路径都不会将任意监听器参与视为持久化后端已存储状态的证明。
+- `send_message` 与 `report` schema、已接受的消息标识、`AgentHandle` 所有权、持久化事件词汇与模型可见的 transcript（文本记录）遵循上文链接的基于 Activation 的实现。