fix(subagents): 子会话与普通会话一样长期保存,修复后台任务面板打开子会话 404

CLAUDE.md

@@ -162,11 +162,11 @@ Core tools are registered for both TUI and daemon paths: `bash`, `file_read`, `f
 
 `spawn_subagent` / `wait_subagent` are registered in both daemon (`worker.cpp`) and TUI (via `src/apps/tui/subagent_host.{hpp,cpp}` — SessionRegistry/LocalSessionClient have no web dependency, so the TUI process instantiates them directly; the TUI main session lives outside the registry, so its permission mode reaches children through `SubagentToolDeps::fallback_permissions`, and `on_spawn` lets the host register tasks + subscribe child events): a sub-agent is a normal SessionRegistry session (isolated context) created with the parent's cwd and permission mode. `spawn_subagent(prompt, wait=true)` blocks until the child turn finishes and returns its final assistant reply into the parent context; `wait=false` is fire-and-forget for pipeline handoff, joined later via `wait_subagent(session_id)`. Prompts starting with `/` go through the same skill-command expansion as Web input. Sub-agents cannot spawn further sub-agents (`SessionEntry::subagent_depth`). Implementation: [src/host/session_host/tools/spawn_subagent_tool.cpp](src/host/session_host/tools/spawn_subagent_tool.cpp); deps are late-bound via shared_ptr because ToolExecutor is constructed before SessionRegistry in worker.cpp.
 
-**TUI surface**: the right sidebar's "Background Tasks" section lists running sub-agents only (● title + elapsed; removed the moment the child turn ends — user decision); `/tasks [list|abort <id>|clear]` is the operation entry (clear = same permanent-purge semantics as Web, via `SessionStorage::purge_session_files`). A child's `permission_request` is queued (`TuiState::remote_confirm_queue`) and pumped into the confirm overlay when free (origin-labelled; the answer routes back via `SubagentHost::respond_permission`). AskUserQuestion needs no bridging — children share the TUI ToolExecutor, so the TUI ask tool runs directly; it now queues on `TuiState::overlay_cv` until the confirm/ask overlay is free and sets `ask_origin_label` when the caller is a sub-agent. `on_tool_confirm` in tui/app/tui_agent_bridge.cpp queues on the same cv, so concurrent overlay claims (main confirm / child ask / remote pump) serialize instead of clobbering each other.
+**TUI surface**: the right sidebar's "Background Tasks" section lists running sub-agents only (● title + elapsed; removed the moment the child turn ends — user decision); `/tasks [list|abort <id>|clear]` is the operation entry (clear = archive, same as the Web panel: unload + `meta.archived`, records kept). TUI exit cleanup (`cleanup_old_sessions`) counts only main sessions against `max_sessions` and deletes children together with their main session; orphans whose parent is gone count as main sessions. A child's `permission_request` is queued (`TuiState::remote_confirm_queue`) and pumped into the confirm overlay when free (origin-labelled; the answer routes back via `SubagentHost::respond_permission`). AskUserQuestion needs no bridging — children share the TUI ToolExecutor, so the TUI ask tool runs directly; it now queues on `TuiState::overlay_cv` until the confirm/ask overlay is free and sets `ask_origin_label` when the caller is a sub-agent. `on_tool_confirm` in tui/app/tui_agent_bridge.cpp queues on the same cv, so concurrent overlay claims (main confirm / child ask / remote pump) serialize instead of clobbering each other.
 
 Full subagent reference (design, wire protocol, Web panel, TUI bridging, test map): [docs/subagents.md](docs/subagents.md).
 
-Sub-agent sessions are **hidden from normal session lists** and surfaced only in the parent session's Web「后台任务」panel: the child meta persists `parent_session_id` (survives daemon restart; resume restores `subagent_depth=1` so the depth limit keeps holding), `GET /api/sessions` excludes them by default, `?parent=<id>` queries them, and `DELETE /api/sessions/:id?purge=1` is the panel's「清除」(destroy + delete disk data; sub-agent sessions only, busy → 409). Frontend: `web/src/lib/subagentTasks.js` (pure state, Node tests) + `lib/useSubagentTasks.js` (REST list + WS increments + retainSession for running children so their permission/question requests reach App-level listeners even with the panel closed) + `components/SubagentPanel.jsx` (overlay inside ChatView's message area: running/settled card groups, per-card stop, read-only transcript that shares the main conversation's `projectCollapsedTranscriptItems` projection and `TranscriptItems` renderer, with AskUserQuestion rows filtered out through the projection seam). A running child's `permission_request` pops the global PermissionModal and its `question_request` renders in the parent's QuestionPicker (payloads carry the child `session_id`, so answers route back automatically); both show a「来自后台任务:<title>」origin label.
+Sub-agent sessions are **hidden from normal session lists** and surfaced only in the parent session's Web「后台任务」panel: the child meta persists `parent_session_id` (survives daemon restart; resume restores `subagent_depth=1` so the depth limit keeps holding), `GET /api/sessions` excludes them by default, `?parent=<id>` queries them. **Children are kept like ordinary sessions (user decision):** the panel's「归档」archives settled children (`PUT /api/workspaces/:hash/sessions/:id/archive`; hidden from `?parent=` and from the `?archived=1` list, records kept), and permanently deleting an archived main session (`purge_session_data`) cascades to all its children — any running child → 409, children go first so a failure keeps the parent retryable. A mesh agent archived from the panel is unarchived when addressed again (`MeshAgentService::ensure_loaded`). The panel's read-only transcript passes the parent's `workspaceHash`: the Desktop daemon serves many workspaces and an unloaded child (after a Desktop restart or a mesh eviction) is otherwise 404 SESSION_NOT_FOUND. Frontend: `web/src/lib/subagentTasks.js` (pure state, Node tests) + `lib/useSubagentTasks.js` (REST list + WS increments + retainSession for running children so their permission/question requests reach App-level listeners even with the panel closed) + `components/SubagentPanel.jsx` (overlay inside ChatView's message area: running/settled card groups, per-card stop, read-only transcript that shares the main conversation's `projectCollapsedTranscriptItems` projection and `TranscriptItems` renderer, with AskUserQuestion rows filtered out through the projection seam). A running child's `permission_request` pops the global PermissionModal and its `question_request` renders in the parent's QuestionPicker (payloads carry the child `session_id`, so answers route back automatically); both show a「来自后台任务:<title>」origin label.
 
 **蜂群模式（网状）(openspec add-mesh-swarm-mode,复刻 Codex Multi-Agent V2,全文见 [docs/subagents.md](docs/subagents.md) §9)。** 蜂群模式是会话级三态 `off | star | mesh`(`SessionMeta.swarm_mode`,入口:消息体 `swarm_mode`、`/swarm`、headless `--swarm`),AgentLoop 每回合从 SessionManager 读,切换只影响下一回合。两套协作工具互斥:`swarm_mode_hidden_tools` → `ToolCapabilityPolicy::hidden_builtin_tools`(schema 与执行同一谓词),mesh 隐藏 `spawn_subagent` / `wait_subagent` / thread 工具,off / star 隐藏六个 `agent_*`。网状子 agent 的 `parent_session_id` 恒为**根** id(扁平,面板 / 权限冒泡 / purge 全复用星型通道),真实层级是 `SessionMeta.agent_path`(`/root/a/b`),树目录落在根会话目录的 `mesh_agents.json`。服务 `host/session_host/mesh/MeshAgentService` 在 worker / TUI(`SubagentHost`,TUI 主会话是外部根)/ headless 各一份,工具只捕获 `weak_ptr`。几条别改回去的语义:(1) 邮件一律进 AgentLoop 邮箱(`engine/agent/mailbox`),每次模型请求前并入;**子 agent 完成回报不唤醒空闲的父 agent**(Codex 原样),只有 `agent_followup_task` / NEW_TASK 唤醒;interrupted 回合不回报。(2) 信封落盘为 **user 角色** + `metadata.inter_agent`(有意偏离 Codex 的 assistant 角色:连续 assistant 在 Anthropic / DeepSeek 上会被拒),NEW_TASK 算真实用户消息、其余是内部上下文,TUI / Web 都转成系统提示行,别让它变成用户气泡(会开出假回合、触发「重发末尾用户消息」)。(3) 驻留上限 `swarm.mesh.max_concurrent_agents` 默认 4 **含根**,满了按 LRU 换出已结束的子 agent(`registry.destroy`,发消息时 `resume` 恢复),都在跑就报 `agent thread limit reached`。(4) Web 输入框芯片 = 服务端模式 + 未提交的本地选择,**只有二者不同才随消息提交 `swarm_mode`**(`web/src/lib/swarmMode.js`):每条消息都带会把 `/swarm` 刚切的模式改回去,网状树里有 agent 在跑时还会直接 409。回归:`tests/session_host/mesh_agent_service_test.cpp`(真实 SessionRegistry + 脚本化 provider 跑整棵树)、`tests/agent/agent_loop_mesh_mailbox_test.cpp`、`swarmMode.test.js` / `interAgentMessage.test.js`。
 

docs/daemon-api.md

@@ -812,13 +812,22 @@ the user-message search index, then removes `<id>.jsonl`, the per-session
 `<id>/` persisted-data directory, and `<id>.meta.json` last. Returns `204` only
 after cleanup succeeds.
 
+Sub-agent sessions (`spawn_subagent` tasks and every mesh agent of the tree)
+are kept like ordinary sessions and live and die with their main session:
+purging a main session first applies the same cleanup to each of its child
+sessions (archived or not, including children that exist only in memory), then
+to the main session itself. A failure stops before the main session is removed,
+so the operation stays retryable.
+
 Guard rails and errors:
 
 - `400` when `purge=1` is missing or the session id is invalid
 - `404` when the workspace or session does not exist
 - `409 {"error":"session must be archived before permanent deletion"}` when
   the target is not archived
 - `409` when the target is unexpectedly busy
+- `409 {"error":"subagent session <id> is busy; abort it first"}` when one of
+  the main session's child sessions is running a turn; nothing is deleted
 - `500` when search-index or file cleanup fails; metadata is retained until
   the other known session data has been removed so the operation remains
   retryable
@@ -1079,9 +1088,13 @@ thread, and removes it from the registry. It does not delete disk history.
 Returns `204`; returns `503` when the session client is unavailable.
 
 `DELETE /api/sessions/:id?purge=1` performs the same durable cleanup for either
-an archived main session or a sub-agent session. It remains the background-task
-"clear" action for sub-agents and is also the compatibility fallback used by
-the archived-session settings page. Guard rails:
+an archived main session (cascading to its child sessions as above) or a single
+sub-agent session. It is the compatibility fallback used by the
+archived-session settings page. The background-task panel no longer purges:
+its "archive" action uses `PUT /api/workspaces/:hash/sessions/:id/archive`
+(or `PUT /api/sessions/:id/archive` without a workspace), which unloads the
+child, hides it from `?parent=` listings and keeps its records. Archived child
+sessions never appear in the `?archived=1` list. Guard rails:
 
 - `400 {"error":"only subagent sessions can be purged"}` for a non-archived
   main session

docs/help-source/group5.py

@@ -24,7 +24,7 @@
         '''<p>子代理拥有独立上下文，并继承父任务的工作目录与权限模式。主任务通常收到子代理最终答复，而非自动把所有中间工具输出复制进自身上下文。共享工作目录意味着文件变化会相互可见；独立上下文不等于独立 Git 工作树。</p><p>网状模式下，子 Agent 默认继承派生者的对话上下文（只保留用户消息与最终回答），也可以只继承最近几轮或完全不继承。下级完成或出错时，结果以「某某已完成」「某某执行出错」提示行送到上级，不会打断上级正在进行的工作，上级下一次回复时会看到它。同一棵协作树同时最多保留 4 个 Agent（含主任务，可在配置文件的 <code>swarm.mesh.max_concurrent_agents</code> 调整）；满了会暂时卸载最久没有活动、已经结束的 Agent，再次给它发消息时自动恢复。仍有子 Agent 在运行时不能退出网状模式，先等待它们完成或停止它们。</p>''',
         figure("AD-03", "开启蜂群模式并提交分工", "展示添加能力菜单中的蜂群模式、开启后的标签，以及说明任务边界的输入内容。")),
     section("progress", "查看进度与处理操作确认",
-        '''<p>产生子任务后，在主会话的<strong>后台任务</strong>面板查看运行中和已完成的任务，打开任务可阅读其会话与工具结果。子任务归属于父会话，不会作为普通任务充满主侧边栏和全局搜索结果。</p><p>来自子任务的权限请求与问题会在主界面出现，并标注来源。检查任务名称、工具参数与目标路径后处理；不要仅因为主任务尚有输出，就忽略另一个子任务正在等待回答。</p><p>可以在面板中停止运行中的子任务。停止父任务也会向其子任务传播中断；已经产生的文件和记录会保留，不自动回滚。清除已结束任务会删除这些子会话记录，确认不再需要查看后再清理。</p>''',
+        '''<p>产生子任务后，在主会话的<strong>后台任务</strong>面板查看运行中和已完成的任务，打开任务可阅读其会话与工具结果。子任务归属于父会话，不会作为普通任务充满主侧边栏和全局搜索结果。</p><p>来自子任务的权限请求与问题会在主界面出现，并标注来源。检查任务名称、工具参数与目标路径后处理；不要仅因为主任务尚有输出，就忽略另一个子任务正在等待回答。</p><p>可以在面板中停止运行中的子任务。停止父任务也会向其子任务传播中断；已经产生的文件和记录会保留，不自动回滚。</p><p>子任务的会话记录与普通会话一样长期保留。面板中的<strong>归档</strong>和 TUI 的 <code>/tasks clear</code> 只把已结束任务从列表中收起，不删除记录；网状模式下被收起的 Agent 再次收到消息时会自动恢复并重新出现在面板中。只有把主会话归档后再永久删除，它的全部子任务记录才会随之删除。</p>''',
         code("/tasks\n/tasks list\n/tasks abort 子任务ID\n/tasks clear", "TUI · 管理后台任务"),
         figure("AD-04", "后台任务与来自子任务的请求", "展示运行中与已完成分组、查看会话和停止入口，以及带来源名称的权限确认。"),
         '''<p>全部子任务完成后，让主任务检查它们之间的冲突、统一差异并运行必要验证。各自报告“完成”不能代替整合后的构建或测试。</p>''')