tianshu-mcp 0.3.0 → 0.3.2

package/CHANGELOG.en.md

@@ -16,6 +16,99 @@ Chinese version: [CHANGELOG.md](CHANGELOG.md)
 - TraeWork executable discovery and native-dialog driving on macOS (currently fail-closed).
 - Optional project-level skill seeding (by default nothing is written into target repos).
 - macOS hardware verification for the Codex GUI adapter (built-in status remains `research`).
+- Best-effort stop of a GUI-side pending session (via a temporary CDP connection) when cancelling
+  a task in the `needs_user` state.
+
+---
+
+## [0.3.2] — 2026-09-12
+
+Fixes for issues #5 / #6: **the MCP task model was disconnected from the state of the turn inside
+the Codex GUI**. The former is the completion-detection deadlock that kept reporting `running`
+while Codex waited for user confirmation; the latter is `cancel_task` only aborting the MCP-side
+wait loop, never stopping the in-GUI run, with a misleading description. Both share the same root
+cause and are resolved together.
+
+### Fixed
+
+- **Waiting-for-user detection (issue #5)**:
+  - `judgeCodexPoll` gains a stall fallback: while the stop button stays visible and the
+    conversation hash is unchanged for `gui.stallTimeoutMs` (default 5 minutes), the task
+    transitions to `needs_user` (`needsUserKind=user_confirmation`) instead of deadlocking in
+    `running` until the overall timeout; the stall timer resets as soon as content changes again.
+  - New configurable UI detection `gui.selectors.userGate` (e.g. the embedded-checkout page or
+    approval cards): when configured and matched, transitions to `needs_user` immediately.
+    Unset by default (disabled) — no unverified selectors are built in.
+  - Tightened the `stopButton` selector: removed the `aria-label*="取消"` over-match (the Cancel
+    button on waiting-for-user screens used to be mistaken for a running signal).
+- **Recovery path (issue #5 fallout)**: `continue_task` now supports codex —
+  - `user_confirmation`: after the user completes the action in the Codex window, resume by
+    re-attaching as an observer of the in-GUI run (no message is sent); if the turn already
+    finished before resuming, the task is still judged `succeeded` correctly;
+  - `login_required`: after login, re-checks the environment and re-dispatches the task brief
+    (fresh session + project binding + full initial prompt);
+  - zcode recovery behaviour is unchanged; other agents are rejected explicitly.
+- **Cancel actually stops the GUI (issue #6)**:
+  - `cancel_task` no longer succeeds on request alone for GUI agents: it first best-effort clicks
+    the in-app stop button over CDP, then waits (bounded by `gui.cancelWaitMs`, default 15s) for
+    the GUI to become idle before settling `cancelled`; if the stop could not be confirmed the
+    terminal message states "GUI 内运行未确认停止…" (the in-GUI run may still be going);
+  - process-tree termination for CLI agents is unchanged;
+  - cancelling from `needs_user` now notes that a pending session may remain in the GUI
+    (no CDP connection exists at that point — documented limitation).
+- **Re-dispatch anti-overlap guard (issue #6 chain risk)**: when dispatching, if the managed
+  instance still has an unstopped run, MCP first tries to stop it; if it cannot, the dispatch
+  fails hard with `instance_busy`, preventing old and new turns from overlapping inside the same
+  app (observed in the wild when re-dispatching right after a cancel).
+- The startup log no longer hardcodes the tool count as `8`; it reports the actual registry size
+  (`TOOL_DEFS.length`, currently 9).
+
+### Changed
+
+- Tool descriptions match actual semantics: `cancel_task` distinguishes CLI (kill process tree)
+  from GUI (best-effort stop click + bounded wait); `continue_task` no longer claims to be
+  ZCode-only.
+- `GuiProfile` gains two configurable options, `stallTimeoutMs` (default 300000) and
+  `cancelWaitMs` (default 15000), both overridable via agent-profiles.json.
+- Skill docs (SKILL.md §4/§5, usage-examples.md §7) document the codex `user_confirmation` /
+  `login_required` recovery flows, GUI cancel semantics and the new options.
+
+---
+
+## [0.3.1] — 2026-09-12
+
+Post-v0.3.0 housekeeping for docs and release automation: **no source-level behavior changes**.
+The focus is a full rewrite of the self-installed skill docs plus GitHub/Gitee release-body
+composition and link fixes.
+
+### Changed
+
+- **Skill docs (`skills/tianshu-mcp/`) fully rewritten to match the actual v0.3.0 tool surface**:
+  - Corrected the `codex` description from "headless CLI" to the ChatGPT desktop GUI adapter
+    (MSIX + COM activation + CDP); documents the required `model`, optional `reasoningLevel` /
+    `planDoc` / `designSystem`, and that `mode` is not supported;
+  - Documented the `run_task` `context` parameter and the send-time validation of path references
+    inside task/context; corrected the `autoFixRounds` default precedence
+    (call argument > codex 5 / zcode 2 > server default 0);
+  - Added usage for `list_tasks`, `query_task(tailLines)`, `get_task_report(round)` and
+    `verify_task` (`extraChecks` / `checksMode` / `baselineRef`) plus the four-level acceptance
+    command precedence;
+  - Documented the four `needs_user` kinds and meta fields such as `needsUserKind` /
+    `pendingQuestion` / `errorType` / `reportRound` / `verificationSource`;
+  - Added `continue_task` to the approval list; replaced emoji status markers with plain text
+    (PASS / warning) in the usage examples.
+- **Release automation fixes (exposed by the v0.3.0 tag)**:
+  - The release body is now composed bilingually from `docs/release-v<version>.md` and `.en.md`,
+    with in-document relative links rewritten to tag-absolute links; a missing doc fails the
+    workflow loudly instead of producing a shell-only body;
+  - `Full Changelog` resolves the previous tag via `git describe` into a `compare/<prev>...<tag>`
+    link instead of degrading to a commits link;
+  - The body's `CI` link resolves the CI run for the same SHA instead of pointing at the Release run;
+  - Gitee releases are automated in `release.yml`: `scripts/gitee-release.mjs` idempotently
+    creates/updates the mirrored release (requires the `GITEE_TOKEN` secret; skipped loudly when unset).
+- `.gitignore` now ignores npm pack artifacts and local temporary verification directories.
+- Added the missing `[0.1.10]` / `[0.2.0]` / `[0.3.0]` / `[0.3.1]` compare links at the bottom of
+  this file and its Chinese counterpart.
 
 ---
 
@@ -401,7 +494,12 @@ project → pick model and reasoning level → send instructions → run detecti
 
 ---
 
-[Unreleased]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.9...HEAD
+[Unreleased]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.2...HEAD
+[0.3.2]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.1...v0.3.2
+[0.3.1]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.0...v0.3.1
+[0.3.0]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.2.0...v0.3.0
+[0.2.0]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.10...v0.2.0
+[0.1.10]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.9...v0.1.10
 [0.1.9]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.8...v0.1.9
 [0.1.8]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.7...v0.1.8
 [0.1.7]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.6...v0.1.7

package/CHANGELOG.md

@@ -15,6 +15,81 @@
 - TraeWork 在 macOS 下的可执行探测与原生对话框驱动（当前 macOS 分支 fail-closed）。
 - 可选的项目级技能播种（默认不写入目标项目仓库）。
 - Codex GUI 的 macOS 真机验证（当前内置状态为 `research`）。
+- needs_user 状态下取消任务时经临时 CDP 连接尽力停止 GUI 内等待中的会话。
+
+---
+
+## [0.3.2] — 2026-09-12
+
+修复 issue #5 / #6：**MCP 任务模型与 Codex GUI 内 turn 的状态脱节**。
+前者是"等用户确认时恒报 running"的完成判定死锁，后者是 `cancel_task` 只停 MCP 侧等待、
+不停 GUI 内运行且描述失实。同根问题一并收敛。
+
+### 修复
+
+- **等待用户检测（issue #5）**：
+  - `judgeCodexPoll` 新增 stall 兜底：停止按钮持续可见且对话哈希 `gui.stallTimeoutMs`
+    （默认 5 分钟）不变 → 判定等待用户，任务转 `needs_user`（`needsUserKind=user_confirmation`），
+    不再死锁在 `running` 直到总超时；对话内容恢复变化会重置 stall 计时。
+  - 新增可配置界面检测 `gui.selectors.userGate`（如结账页 `embedded-checkout`、确认卡）：
+    命中即快速转 `needs_user`；默认未配置 = 禁用，不内置未真机验证的选择器。
+  - 收紧 `stopButton` 选择器：移除 `aria-label*="取消"` 过匹配（等待用户界面的"取消"
+    按钮曾被误判为运行信号）。
+- **恢复通道（issue #5 牵连）**：`continue_task` 扩展支持 codex——
+  - `user_confirmation`：用户在 Codex 窗口处理完后恢复，MCP 仅重新接入观察 GUI 内运行
+    （不发送消息）；恢复前 turn 已完成也能正确判 `succeeded`；
+  - `login_required`：复检环境后重新派发任务书（新会话 + 项目绑定 + 完整初始指令）；
+  - zcode 原有恢复行为不变；其他 agent 明确拒绝。
+- **取消真停 GUI（issue #6）**：
+  - `cancel_task` 对 GUI agent 不再"请求即成功"：先经 CDP 尽力点击界面停止按钮，
+    并在 `gui.cancelWaitMs`（默认 15 秒）内有界等待 GUI 真正空闲后落 `cancelled`；
+    未确认停止时终态文案明示"GUI 内运行未确认停止，Codex 窗口中的任务可能仍在继续"；
+  - CLI agent 的进程树终止语义不变；
+  - `needs_user` 状态取消的文案提示"GUI 内可能仍有等待中的会话"（此时 MCP 侧无 CDP 连接，
+    列为已知边界）。
+- **重派防交叠护栏（issue #6 连锁）**：派发前发现受管实例上仍有未停止的运行时，
+  先尽力停止；仍不空闲则以 `instance_busy` 硬失败拒绝派发，杜绝新旧 turn 在同一
+  应用内交叠（取消后立刻重派曾实测踩中）。
+- 启动日志的工具数由硬编码 `8` 改为按注册表实际数量（`TOOL_DEFS.length`，当前为 9）输出。
+
+### 变更
+
+- 工具描述对齐实际语义：`cancel_task` 区分 CLI（kill 进程树）与 GUI（尽力点击停止 +
+  有界等待）；`continue_task` 去掉"只用于 ZCode"限定。
+- `GuiProfile` 新增 `stallTimeoutMs`（默认 300000）与 `cancelWaitMs`（默认 15000）配置项，
+  均可由 agent-profiles.json 覆盖。
+- 技能文档（SKILL.md §4/§5、usage-examples.md §7）补齐 codex `user_confirmation` /
+  `login_required` 恢复方式、GUI 取消语义与相关配置示例。
+
+---
+
+## [0.3.1] — 2026-09-12
+
+v0.3.0 发布后的文档与发布自动化收口：**无源码行为变更**，重点是技能自检安装文档全面重写、
+GitHub/Gitee 发行版正文合成与链接修复。
+
+### 变更
+
+- **技能文档（`skills/tianshu-mcp/`）全面重写并对齐 v0.3.0 实际工具面**：
+  - 修正 `codex` 描述：由「无头 CLI」更正为 ChatGPT 桌面端 GUI adapter（MSIX + COM 激活 + CDP），
+    标注 `model` 必填、`reasoningLevel` / `planDoc` / `designSystem` 用法、不支持 `mode`；
+  - 补齐 `run_task` 的 `context` 参数语义与 task/context 路径引用发送前校验说明；
+    修正 `autoFixRounds` 默认值优先级（调用参数 > codex 5 / zcode 2 > server 默认 0）；
+  - 补齐 `list_tasks`、`query_task(tailLines)`、`get_task_report(round)` 与
+    `verify_task`（`extraChecks` / `checksMode` / `baselineRef`）的用法与验收命令四级优先级；
+  - 补充 `needs_user` 四种等待类型与 meta 块 `needsUserKind` / `pendingQuestion` / `errorType` /
+    `reportRound` / `verificationSource` 等字段解读；
+  - 审批清单补上 `continue_task`；使用示例中的 emoji 状态标记改为文字（PASS / 告警）。
+- **发布自动化修复（v0.3.0 tag 实测暴露）**：
+  - Release 正文改为由 `docs/release-v<版本>.md` 与 `.en.md` 双语合成，文档内相对链接改写为
+    该 tag 的绝对链接，缺文档时工作流明确报错（不再产出空壳正文）；
+  - `Full Changelog` 经 `git describe` 解析上一 tag，生成 `compare/<prev>...<tag>` 比较链接，
+    不再退化为 commits 链接；
+  - 正文 `CI` 链接解析同 SHA 的 CI 运行，避免误指 Release 自身运行；
+  - Gitee 发行版纳入 `release.yml` 自动化：`scripts/gitee-release.mjs` 幂等创建/更新
+    （需仓库 Secret `GITEE_TOKEN`，未配置时明确提示并跳过）。
+- `.gitignore` 忽略 npm pack 产物与本地临时校验目录。
+- 补齐本文件与英文版底部缺失的 `[0.1.10]` / `[0.2.0]` / `[0.3.0]` / `[0.3.1]` 比较链接。
 
 ---
 
@@ -356,7 +431,12 @@ Codex 桌面端改为 **GUI 驱动**：新增 `codex-gui` adapter，通过 MSIX
 
 ---
 
-[未发布]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.9...HEAD
+[未发布]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.2...HEAD
+[0.3.2]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.1...v0.3.2
+[0.3.1]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.0...v0.3.1
+[0.3.0]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.2.0...v0.3.0
+[0.2.0]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.10...v0.2.0
+[0.1.10]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.9...v0.1.10
 [0.1.9]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.8...v0.1.9
 [0.1.8]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.7...v0.1.8
 [0.1.7]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.6...v0.1.7

package/README.en.md

@@ -182,6 +182,7 @@ Use `server.log` when troubleshooting connections; do not treat stderr output it
 | [docs/zcode-windows-smoke.en.md](docs/zcode-windows-smoke.en.md) | ZCode Windows hardware record for development, same-session repair, and question continuation |
 | [docs/codex-gui-cdp.en.md](docs/codex-gui-cdp.en.md) | Codex desktop GUI driver: MSIX COM activation, CDP attach, selectors, run detection, verify/repair |
 | [docs/codex-windows-smoke.en.md](docs/codex-windows-smoke.en.md) | Codex Windows hardware record (incl. verify-fail → auto plan → repair-pass loop) |
+| [docs/release-v0.3.1.en.md](docs/release-v0.3.1.en.md) | v0.3.1 release notes (skill docs rewrite + release automation fixes) |
 | [docs/release-v0.3.0.en.md](docs/release-v0.3.0.en.md) | v0.3.0 release notes (Codex desktop GUI adapter, incl. BREAKING) |
 | [docs/release-v0.2.0.en.md](docs/release-v0.2.0.en.md) | v0.2.0 release notes (unified ZCode GUI loop) |
 | [docs/acceptance-config.en.md](docs/acceptance-config.en.md) | Project-level `.tianshu-mcp/acceptance.json` acceptance config spec |
@@ -254,6 +255,9 @@ Use `server.log` when troubleshooting connections; do not treat stderr output it
   - Hardware-verified: full loop for a registered project, full loop for an unregistered project after automatic registration, and the verify-fail → generated plan → repair-pass loop
   - Real business acceptance: drove Codex to build a "Fruit Ninja" mini-game, passed acceptance, verified playable in a headless browser; [acceptance record](docs/codex-windows-smoke.en.md)
   - macOS unverified; built-in status `research`
+- **M13 — Skill docs alignment + release automation fixes + v0.3.1** (2026-09-12, see [release-v0.3.1.en.md](docs/release-v0.3.1.en.md))
+  - Self-installed skill docs (SKILL.md / usage-examples.md) rewritten item by item against the v0.3.0 tool surface (codex GUI params, needs_user handling, verify/list usage)
+  - Bilingual release bodies, Full Changelog & CI link fixes, and automated Gitee releases
 
 ## Agent support status
 
@@ -276,7 +280,7 @@ Use `server.log` when troubleshooting connections; do not treat stderr output it
 
 | Document | Content |
 |---|---|
-| [CHANGELOG.en.md](CHANGELOG.en.md) | Version history (v0.1.0 → v0.3.0) |
+| [CHANGELOG.en.md](CHANGELOG.en.md) | Version history (v0.1.0 → v0.3.1) |
 | [CONTRIBUTING.en.md](CONTRIBUTING.en.md) | Dev setup, conventions, commit/release flow, adding an agent |
 | [SECURITY.en.md](SECURITY.en.md) | Security model (zero credentials / command whitelist / process & desktop-automation boundaries) and private reporting |
 | [CODE_OF_CONDUCT.en.md](CODE_OF_CONDUCT.en.md) | Contributor Code of Conduct |

package/README.md

@@ -180,6 +180,7 @@ ZCode 提问或需要用户处理登录、旧实例、系统权限时进入 `nee
 | [docs/zcode-windows-smoke.md](docs/zcode-windows-smoke.md) | ZCode Windows 真机开发、同会话返修与提问续跑验收记录 |
 | [docs/codex-gui-cdp.md](docs/codex-gui-cdp.md) | Codex 桌面端 GUI 驱动：MSIX COM 激活、CDP 接管、选择器、运行检测、验收返修 |
 | [docs/codex-windows-smoke.md](docs/codex-windows-smoke.md) | Codex Windows 真机验收记录（含验收失败→自动生成计划→返修通过闭环） |
+| [docs/release-v0.3.1.md](docs/release-v0.3.1.md) | v0.3.1 发布说明（技能文档重写 + 发布自动化修复） |
 | [docs/release-v0.3.0.md](docs/release-v0.3.0.md) | v0.3.0 发布说明（Codex 桌面端 GUI 适配，含 BREAKING） |
 | [docs/release-v0.2.0.md](docs/release-v0.2.0.md) | v0.2.0 发布说明（ZCode GUI 统一闭环） |
 | [docs/acceptance-config.md](docs/acceptance-config.md) | 项目级 `.tianshu-mcp/acceptance.json` 验收配置规范 |
@@ -254,6 +255,9 @@ ZCode 提问或需要用户处理登录、旧实例、系统权限时进入 `nee
   - 真机通过：已登记项目全链路、未登记项目自动登记全链路、验收失败→自动生成计划→返修通过闭环
   - 真实业务验收：驱动 Codex 开发「切水果小游戏」并通过验收，无头浏览器实测可玩；[验收记录](docs/codex-windows-smoke.md)
   - macOS 未验证，内置状态 `research`
+- **M13 — 技能文档对齐 + 发布自动化修复 + v0.3.1**（2026-09-12，见 [release-v0.3.1.md](docs/release-v0.3.1.md)）
+  - 技能自检安装文档（SKILL.md / usage-examples.md）对照 v0.3.0 工具面逐项重写（codex GUI 参数、needs_user 处理、verify/list 用法）
+  - Release 正文双语合成、Full Changelog 与 CI 链接修复、Gitee 发行版纳入自动化
 
 ## Agent 适配现状
 
@@ -277,7 +281,7 @@ ZCode 提问或需要用户处理登录、旧实例、系统权限时进入 `nee
 | 文档 | 内容 |
 |---|---|
 | [HANDOFF.md](HANDOFF.md) | 项目交接文档：当前状态快照、架构导览、硬性红线、已知限制、接手建议 |
-| [CHANGELOG.md](CHANGELOG.md) | 版本变更日志（v0.1.0 → v0.3.0） |
+| [CHANGELOG.md](CHANGELOG.md) | 版本变更日志（v0.1.0 → v0.3.1） |
 | [CONTRIBUTING.md](CONTRIBUTING.md) | 开发环境、工程规范、提交与发布流程、如何新增 agent |
 | [SECURITY.md](SECURITY.md) | 安全模型（凭证零管理/命令白名单/进程与桌面自动化边界）与私密报告渠道 |
 | [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md) | 贡献者行为准则 |

package/dist/agents/adapter.d.ts

@@ -47,6 +47,11 @@ export interface TaskContext {
         kind: "continue" | "rework";
         message?: string;
         sendMessage: boolean;
+        /**
+         * 重新接入观察（不发送任何消息）：codex user_confirmation 恢复专用。
+         * 用户在 GUI 处理完等待项后 turn 自行继续，MCP 只需重连 CDP 观察到终态。
+         */
+        reobserve?: boolean;
         sessionId?: string;
         sessionTitle?: string;
         boundProjectPath?: string;
@@ -75,8 +80,17 @@ export interface AgentRunResult {
     endReason?: string;
     /** GUI 实例是否因任务未真正完成而被保留 */
     keptInstance?: boolean;
-    needsUserKind?: "agent_question" | "close_existing_instance" | "login_required" | "system_permission";
+    needsUserKind?: "agent_question" | "close_existing_instance" | "login_required" | "system_permission" | "user_confirmation";
     pendingQuestion?: string;
+    /**
+     * 取消路径的 GUI 侧停止结果（GUI agent 专用）：
+     * clicked=是否点击了界面停止按钮；idle=等待窗口内 GUI 是否真正空闲。
+     * idle=false 时编排方必须在终态文案中明示「GUI 内运行未停止」。
+     */
+    guiStop?: {
+        clicked: boolean;
+        idle: boolean;
+    };
     session?: {
         id?: string;
         title?: string;

package/dist/agents/builtin.js

@@ -37,6 +37,8 @@ export const BUILTIN_PROFILES = {
             pollIntervalMs: 3_000,
             stableRounds: 4,
             idleTimeoutMs: 10 * 60_000,
+            stallTimeoutMs: 5 * 60_000,
+            cancelWaitMs: 15_000,
             cdpSendTimeoutMs: 15_000,
             progressIntervalMs: 30_000,
             modelSwitch: true,
@@ -94,6 +96,8 @@ export const BUILTIN_PROFILES = {
             pollIntervalMs: 3_000,
             stableRounds: 4,
             idleTimeoutMs: 10 * 60_000,
+            stallTimeoutMs: 5 * 60_000,
+            cancelWaitMs: 15_000,
             cdpSendTimeoutMs: 15_000,
             progressIntervalMs: 30_000,
             modelSwitch: true,
@@ -150,6 +154,8 @@ export const BUILTIN_PROFILES = {
             pollIntervalMs: 3_000,
             stableRounds: 12,
             idleTimeoutMs: 10 * 60_000,
+            stallTimeoutMs: 5 * 60_000,
+            cancelWaitMs: 15_000,
             cdpSendTimeoutMs: 15_000,
             progressIntervalMs: 30_000,
             modelSwitch: true,

package/dist/agents/codex/cdp.d.ts

@@ -26,6 +26,8 @@ export interface CodexPoll {
     conversationText: string;
     /** 登录/引导页可见 */
     loginVisible: boolean;
+    /** 「等待用户」界面检测命中（gui.selectors.userGate 配置后启用） */
+    userGateVisible: boolean;
 }
 export declare class CodexCdpClient {
     private readonly selectors;

package/dist/agents/codex/cdp.js

@@ -258,11 +258,16 @@ export class CodexCdpClient {
          const els=__codexResolve(${specArgs("modelMenuItem", this.selectors)}).filter(vis);
          const available=els.map((e)=>(e.innerText||'').replace(/\\s+/g,' ').trim()).filter(Boolean);
          const hits=els.filter((e)=>norm(e.innerText)===target);
-         if(hits.length===1){const e=hits[0];const r=e.getBoundingClientRect();return {count:1,available,point:{x:Math.round(r.left+r.width/2),y:Math.round(r.top+r.height/2)}}}
+         if(hits.length===1){
+           // 真机实测（26.903.9818.0）：模型 radio 对 trusted 鼠标点击只收起菜单、不切换选中态，
+           // DOM .click() 才会真正生效（aria-checked 翻转）且菜单保持打开（后续调滑块依赖它）。
+           // 与「项目选择触发器需要 trusted 才能展开」相反——菜单项选择用 DOM click。
+           hits[0].click();
+           return {count:1,available,clicked:true};
+         }
          return {count:hits.length,available};`));
-        if (!found.point)
+        if (!found.clicked)
             return { clicked: false, count: found.count, available: found.available };
-        await this.clickAt(found.point.x, found.point.y);
         return { clicked: true, count: found.count, available: found.available };
     }
     /** 读取当前模型/思考等级触发器文本（限定输入框作用域，排除菜单栏与模式切换器） */
@@ -336,6 +341,7 @@ export class CodexCdpClient {
             sendButton: specArgs("sendButton", this.selectors),
             chatInput: specArgs("chatInput", this.selectors),
             loginIndicator: specArgs("loginIndicator", this.selectors),
+            userGate: specArgs("userGate", this.selectors),
             messageArea: specArgs("messageArea", this.selectors),
         })};${this.visibleFilter}
         const resolve=(k)=>__codexResolve(JSON.parse(sels[k]));
@@ -346,7 +352,8 @@ export class CodexCdpClient {
           sendVisible:visAny('sendButton'),
           composerText:(textOf('chatInput')||'').trim(),
           conversationText:(textOf('messageArea')||'').trim().slice(0,20000),
-          loginVisible:visAny('loginIndicator')
+          loginVisible:visAny('loginIndicator'),
+          userGateVisible:visAny('userGate')
         };`));
     }
 }

package/dist/agents/codex/liveness.d.ts

@@ -9,6 +9,8 @@ export interface CodexPoll {
     loginVisible: boolean;
     /** 发送按钮当前是否可见（输入非空时） */
     sendVisible?: boolean;
+    /** 「等待用户」界面检测命中（gui.selectors.userGate 配置后启用） */
+    userGateVisible?: boolean;
 }
 export interface CodexPollState {
     hash: string;
@@ -16,12 +18,16 @@ export interface CodexPollState {
     idleSince: number;
     /** 本轮是否曾观测到权威运行信号 */
     sawRunning: boolean;
+    /** 停止按钮可见且对话哈希不变的起始时刻（0 = 未在计时） */
+    stallSince: number;
 }
 export type CodexVerdict = {
-    kind: "running" | "pending" | "finished" | "needs_login" | "idle_timeout";
+    kind: "running" | "pending" | "finished" | "needs_login" | "needs_user" | "idle_timeout";
     state: CodexPollState;
     evidence: string;
 };
+/** 与 GuiProfileSchema.stallTimeoutMs 默认一致；仅供直调兜底，生产路径由 codexGuiOf 传入 */
+export declare const DEFAULT_STALL_TIMEOUT_MS = 300000;
 export declare function hashText(text: string): string;
 export declare const initialCodexState: () => CodexPollState;
-export declare function judgeCodexPoll(poll: CodexPoll, previous: CodexPollState, stableRounds: number, idleTimeoutMs: number, now?: number): CodexVerdict;
+export declare function judgeCodexPoll(poll: CodexPoll, previous: CodexPollState, stableRounds: number, idleTimeoutMs: number, now?: number, stallTimeoutMs?: number): CodexVerdict;

package/dist/agents/codex/liveness.js

@@ -1,5 +1,5 @@
 /**
- * Codex 任务运行判定（开发计划决策 7/8）。
+ * Codex 任务运行判定（开发计划决策 7/8；issue #5 修复后含 stall 判定）。
  *
  * 设计（吸取 TraeWork 误判完成的教训）：
  * 1. 停止按钮为**权威运行信号**：出现即 running，绝不在此时判完成。
@@ -7,8 +7,17 @@
  *    把「其实还在生成、只是 DOM 恰好静止」误判为完成。
  * 3. 若始终未观测到运行信号（选择器未命中）→ 不判完成，转入空闲计时，最终 idle_timeout：
  *    结束本轮但**不终止实例**（失败开放，不比现状更糟）。
+ * 4. 等待用户判定（issue #5）：「方案确认卡/订阅结账页」等场景下 turn 是暂停而非结束，
+ *    停止按钮恒可见 → 上面的规则会死锁。两条出路：
+ *    - userGateVisible：profile.gui.selectors.userGate 配置的界面检测（快速路径）；
+ *    - stall 兜底：停止按钮持续可见且对话哈希 stallTimeoutMs 不变 → needs_user。
+ *      它无法区分「等用户确认」与「长时间静默的合法长命令」，误判后果是转
+ *      needs_user（非终态、可 continue 恢复），远好于死等总超时；长命令任务
+ *      应调大 gui.stallTimeoutMs。
  */
 import { createHash } from "node:crypto";
+/** 与 GuiProfileSchema.stallTimeoutMs 默认一致；仅供直调兜底，生产路径由 codexGuiOf 传入 */
+export const DEFAULT_STALL_TIMEOUT_MS = 300_000;
 export function hashText(text) {
     return createHash("sha256").update(text).digest("hex").slice(0, 12);
 }
@@ -17,29 +26,55 @@ export const initialCodexState = () => ({
     stable: 0,
     idleSince: 0,
     sawRunning: false,
+    stallSince: 0,
 });
-export function judgeCodexPoll(poll, previous, stableRounds, idleTimeoutMs, now = Date.now()) {
+export function judgeCodexPoll(poll, previous, stableRounds, idleTimeoutMs, now = Date.now(), stallTimeoutMs = DEFAULT_STALL_TIMEOUT_MS) {
     const hash = hashText(poll.conversationText);
     if (poll.loginVisible)
         return {
             kind: "needs_login",
-            state: { hash, stable: 0, idleSince: 0, sawRunning: previous.sawRunning },
+            state: { hash, stable: 0, idleSince: 0, sawRunning: previous.sawRunning, stallSince: 0 },
             evidence: "login_indicator",
         };
-    if (poll.stopVisible)
+    // 等待用户快速路径：界面检测命中（如结账页/确认卡，选择器可配置）
+    if (poll.userGateVisible)
+        return {
+            kind: "needs_user",
+            state: { hash, stable: 0, idleSince: 0, sawRunning: previous.sawRunning, stallSince: 0 },
+            evidence: "user_gate",
+        };
+    if (poll.stopVisible) {
+        // stall 兜底（issue #5）：停止按钮恒可见时对话哈希长时间不变 → 判定等待用户。
+        const hashUnchanged = hash === previous.hash;
+        const stallSince = hashUnchanged ? previous.stallSince || now : now;
+        if (hashUnchanged && previous.stallSince && now - previous.stallSince >= stallTimeoutMs)
+            return {
+                kind: "needs_user",
+                state: { hash, stable: 0, idleSince: 0, sawRunning: true, stallSince },
+                evidence: "stop_button+stall",
+            };
         return {
             kind: "running",
-            state: { hash, stable: 0, idleSince: 0, sawRunning: true },
+            state: { hash, stable: 0, idleSince: 0, sawRunning: true, stallSince },
             evidence: "stop_button",
         };
+    }
     const sawRunning = previous.sawRunning;
     const stable = hash === previous.hash && poll.conversationText.trim() ? previous.stable + 1 : 0;
     const idleSince = stable >= stableRounds ? previous.idleSince || now : 0;
     // 权威完成：曾运行 → 停止钮消失 → 文本稳定
     if (sawRunning && stable >= stableRounds && poll.conversationText.trim())
-        return { kind: "finished", state: { hash, stable, idleSince, sawRunning }, evidence: "stop_button_gone+text_stable" };
+        return {
+            kind: "finished",
+            state: { hash, stable, idleSince, sawRunning, stallSince: 0 },
+            evidence: "stop_button_gone+text_stable",
+        };
     // 失败开放：始终无运行信号 → 空闲超时（结束本轮、保留实例）
     if (idleSince && now - idleSince >= idleTimeoutMs)
-        return { kind: "idle_timeout", state: { hash, stable, idleSince, sawRunning }, evidence: "no_running_signal+idle" };
-    return { kind: "pending", state: { hash, stable, idleSince, sawRunning }, evidence: "none" };
+        return {
+            kind: "idle_timeout",
+            state: { hash, stable, idleSince, sawRunning, stallSince: 0 },
+            evidence: "no_running_signal+idle",
+        };
+    return { kind: "pending", state: { hash, stable, idleSince, sawRunning, stallSince: 0 }, evidence: "none" };
 }