tianshu-mcp 0.3.3 → 0.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (53) hide show
  1. package/CHANGELOG.en.md +588 -509
  2. package/CHANGELOG.md +506 -446
  3. package/README.en.md +415 -337
  4. package/README.md +415 -338
  5. package/dist/agents/adapter.d.ts +1 -1
  6. package/dist/agents/builtin.js +10 -3
  7. package/dist/agents/codex/discovery.js +15 -17
  8. package/dist/agents/codex/instance.js +99 -33
  9. package/dist/agents/codex/launcher.js +7 -0
  10. package/dist/agents/codex/registry.js +47 -18
  11. package/dist/agents/codex/run.js +61 -11
  12. package/dist/agents/registry.js +17 -15
  13. package/dist/agents/traework/cdp/client.js +28 -1
  14. package/dist/agents/traework/launcher.js +11 -10
  15. package/dist/agents/traework/run.js +14 -11
  16. package/dist/agents/traework/ui/composer.js +2 -1
  17. package/dist/agents/traework/ui/model.js +3 -1
  18. package/dist/agents/traework/ui/session.js +11 -8
  19. package/dist/agents/zcode/cdp.d.ts +2 -1
  20. package/dist/agents/zcode/cdp.js +21 -17
  21. package/dist/agents/zcode/dialog.d.ts +8 -2
  22. package/dist/agents/zcode/dialog.js +153 -66
  23. package/dist/agents/zcode/discovery.js +37 -55
  24. package/dist/agents/zcode/dom.d.ts +7 -0
  25. package/dist/agents/zcode/dom.js +76 -0
  26. package/dist/agents/zcode/instance.d.ts +6 -1
  27. package/dist/agents/zcode/instance.js +104 -44
  28. package/dist/agents/zcode/model.d.ts +5 -0
  29. package/dist/agents/zcode/model.js +27 -2
  30. package/dist/agents/zcode/project.js +10 -1
  31. package/dist/agents/zcode/recovery.d.ts +31 -0
  32. package/dist/agents/zcode/recovery.js +107 -0
  33. package/dist/agents/zcode/run.d.ts +2 -2
  34. package/dist/agents/zcode/run.js +321 -102
  35. package/dist/agents/zcode/selectors.js +14 -14
  36. package/dist/config/schema.d.ts +66 -0
  37. package/dist/config/schema.js +37 -0
  38. package/dist/loop/fix-loop.js +1 -0
  39. package/dist/mcp/handlers.js +56 -14
  40. package/dist/tasks/task-store.js +4 -18
  41. package/dist/tasks/task.d.ts +1 -1
  42. package/dist/util/path.js +85 -3
  43. package/dist/util/ttl-cache.js +35 -0
  44. package/dist/verify/acceptance.js +135 -32
  45. package/dist/verify/code-analysis.js +99 -72
  46. package/dist/verify/exec.js +6 -1
  47. package/dist/verify/git-baseline.js +41 -16
  48. package/dist/verify/report.js +5 -1
  49. package/dist/verify/runner.js +46 -25
  50. package/dist/version.generated.d.ts +1 -1
  51. package/dist/version.generated.js +1 -1
  52. package/package.json +2 -1
  53. package/scripts/release-body.mjs +2 -1
package/CHANGELOG.en.md CHANGED
@@ -1,26 +1,103 @@
1
- # Changelog
2
-
3
- All notable changes to `tianshu-mcp` are documented here. The format follows
4
- [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and the project adheres to
5
- [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
6
-
7
- Chinese version: [CHANGELOG.md](CHANGELOG.md)
8
-
9
- ---
10
-
11
- ## [Unreleased]
12
-
13
- ### Planned
14
-
15
- - More external AI-Agent adapters (a new agent = one profile + an optional adapter file).
16
- - TraeWork executable discovery and native-dialog driving on macOS (currently fail-closed).
17
- - Optional project-level skill seeding (by default nothing is written into target repos).
18
- - macOS hardware verification for the Codex GUI adapter (built-in status remains `research`).
19
- - Best-effort stop of a GUI-side pending session (via a temporary CDP connection) when cancelling
20
- a task in the `needs_user` state.
21
-
1
+ # Changelog
2
+
3
+ All notable changes to `tianshu-mcp` are documented here. The format follows
4
+ [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and the project adheres to
5
+ [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
6
+
7
+ Chinese version: [CHANGELOG.md](CHANGELOG.md)
8
+
22
9
  ---
23
10
 
11
+ ## [Unreleased]
12
+
13
+ ### Planned
14
+
15
+ - More external AI-Agent adapters (a new agent = one profile + an optional adapter file).
16
+ - TraeWork executable discovery and native-dialog driving on macOS (currently fail-closed).
17
+ - Optional project-level skill seeding (by default nothing is written into target repos).
18
+ - Cancel/rework/new-project matrices for the Codex and ZCode GUI drivers on macOS (both remain `research` on darwin).
19
+ - Best-effort stop of a GUI-side pending session (via a temporary CDP connection) when cancelling
20
+ a task in the `needs_user` state.
21
+
22
+ ---
23
+
24
+ ## [0.4.0] — 2026-09-13
25
+
26
+ ### Added
27
+
28
+ - `projectPath` safety gate: `run_task`/`verify_task` validate at submission (absolute path +
29
+ existing directory + realpath symlink resolution), reject the home directory itself and
30
+ system/root directories (including macOS `/private/*` realpath forms); the submission receipt
31
+ notes symlink resolution; dirty git repos get an uncommitted-changes coexistence warning.
32
+ - ZCode GUI driver supports macOS: adapts to the main process rewriting its title (relaxed port
33
+ attribution + bounded scan of the configured port range when argv hides the debug port) and
34
+ detached+unref instance persistence; the folder-panel driver is rewritten for the macOS window
35
+ form (NSOpenPanel as a standalone window + AX value write into the go-to field, immune to IME
36
+ interception). Machine-verified closed loop on 2026-09-13 (macOS arm64, ZCode 3.11.2: bind →
37
+ readback → send → run evidence → acceptance PASS → succeeded); macOS stays `research` until
38
+ the cancel/rework/new-project matrix is covered.
39
+ - Codex GUI driver supports macOS: spawns the ChatGPT.app bundle executable directly
40
+ (per-platform `activation` default spawn/msix-com) with detached+unref instance persistence;
41
+ POSIX process enumeration and SIGTERM stop; default discovery dirs on darwin; project
42
+ registration writes the shared state file (`~/.codex/.codex-global-state.json`) on darwin too;
43
+ the observation loop reconnects CDP across transient renderer hangs / target replacement
44
+ (only 5 consecutive failures count as disconnected). Machine-verified closed loop on
45
+ 2026-09-13 (macOS arm64: discover → register → bind → send → run evidence → acceptance PASS
46
+ → succeeded); macOS stays `research` until the cancel/rework matrix is covered.
47
+
48
+ ### Fixed
49
+
50
+ - zcode macOS new-task inert-button fallback: `conversation-new-task` can hit an inert home-screen
51
+ icon (click does nothing); when the project trigger misses, the flow now falls back to the
52
+ sidebar `[data-testid=task-new-button]` and retries.
53
+ - `normalizeProjectPath` resolves symlinks: macOS `/tmp`→`/private/tmp` used to fail project
54
+ path matching and degrade into a name match, falsely reporting `project_ambiguous`;
55
+ falls back to lexical normalization when realpath fails.
56
+ - zcode macOS panel failures no longer misreport `needsPermission`: the execFile message embeds
57
+ the full script text (containing the `ACCESSIBILITY_PERMISSION_REQUIRED` literal), so every
58
+ failure looked like a permission problem — the check now reads the stderr execution-error line.
59
+ - `get_profiles` now lists user-defined profiles from the data-directory `agent-profiles.json`
60
+ (previously hidden until first resolve, even though `run_task` could already use them — inconsistent discovery feedback).
61
+ - zcode-flow test stubs now cover `listDialogs`, removing a flake where real osascript/PowerShell
62
+ calls blew the `taskTimeoutMs` wall-clock budget under full-suite load.
63
+ - CDP `connect()` failure paths now dispose of the WebSocket themselves (no longer relying on
64
+ callers to disconnect); the `send()` timeout timer is unref'd.
65
+
66
+ ### Performance
67
+
68
+ - All `execFileSync`/`spawnSync` calls across GUI instance probing, discovery and registration
69
+ are now async; ready-wait loops reuse a per-tick process snapshot with a 1.5s TTL cache —
70
+ eliminating event-loop freezes during Windows polling (up to 30s per call).
71
+ - Acceptance command checks run with bounded parallelism: new `verifyConcurrency` (**⚠ default
72
+ changed from serial to 2**, range 1–4; project-level `.tianshu-mcp/acceptance.json` overrides,
73
+ 1 = fully serial — set 1 explicitly for checks that write build outputs, run with `--fix`, or
74
+ share cache directories); logs are concatenated in declaration order with unchanged format;
75
+ cancellation interrupts both in-flight and pending checks.
76
+ - Git baseline hashing is single-pass with bounded async concurrency (untracked cap 5000);
77
+ code analysis reads each file at most once, sniffing only a prefix of large files.
78
+ - `get_profiles` and task snapshot reads now use `Promise.all`.
79
+ - Test suite 267s → 51s: traework UI-layer sleeps are injectable (production defaults unchanged);
80
+ vitest split into parallel unit / serial integration projects.
81
+ - `tsconfig.build.json` no longer emits declarations — 70 `.d.ts` files dropped (140 → 71 files).
82
+
83
+ ### Documentation
84
+
85
+ - README (both languages) gains "macOS headless path: codex-cli (user profile)" — including the
86
+ revoked-certificate warning for ≤0.130.0 and a complete profile example.
87
+
88
+ ---
89
+
90
+ ## [0.3.4] — 2026-09-13
91
+
92
+ - Fix #8/#10 project-selector ambiguity, full-path binding false negatives and contaminated model readback.
93
+ - Fix #9 environment recovery without a session: send full task/context/references once and locate the session through its marker or unique delta.
94
+ - Add initialization recovery with shared deadlines, configurable budgets and a resumable `setup_recovery` state. Reconcile native side effects after timeouts and terminate helper processes on cancellation.
95
+ - Handle split model labels, hidden outgoing animation text, residual project menus trapping focus and send buttons that are not yet ready.
96
+ - Add real DOM and recovery/cancellation regressions. Windows hardware verifies cold first import, imported-project reuse and same-task recovery with actual artifacts and 2/2 acceptance checks.
97
+ - Published as a GitHub Release/tarball and to npm (`latest`). macOS has no real-device verification for this patch and the ZCode profile remains `research`.
98
+
99
+ See [release notes](docs/release-v0.3.4.en.md) and [validation evidence](docs/zcode-issue-8-10-validation.en.md).
100
+
24
101
  ## [0.3.3] — 2026-09-12
25
102
 
26
103
  Fixes issues #4 / #7 by adapting the ZCode GUI driver to the 3.11.2 model-menu and project-binding semantics, while making acceptance fail closed for zero-test and zero-change outcomes.
@@ -42,492 +119,494 @@ Fixes issues #4 / #7 by adapting the ZCode GUI driver to the 3.11.2 model-menu a
42
119
  ---
43
120
 
44
121
  ## [0.3.2] — 2026-09-12
45
-
46
- Fixes for issues #5 / #6: **the MCP task model was disconnected from the state of the turn inside
47
- the Codex GUI**. The former is the completion-detection deadlock that kept reporting `running`
48
- while Codex waited for user confirmation; the latter is `cancel_task` only aborting the MCP-side
49
- wait loop, never stopping the in-GUI run, with a misleading description. Both share the same root
50
- cause and are resolved together.
51
-
52
- ### Fixed
53
-
54
- - **Waiting-for-user detection (issue #5)**:
55
- - `judgeCodexPoll` gains a stall fallback: while the stop button stays visible and the
56
- conversation hash is unchanged for `gui.stallTimeoutMs` (default 5 minutes), the task
57
- transitions to `needs_user` (`needsUserKind=user_confirmation`) instead of deadlocking in
58
- `running` until the overall timeout; the stall timer resets as soon as content changes again.
59
- - New configurable UI detection `gui.selectors.userGate` (e.g. the embedded-checkout page or
60
- approval cards): when configured and matched, transitions to `needs_user` immediately.
61
- Unset by default (disabled) — no unverified selectors are built in.
62
- - Tightened the `stopButton` selector: removed the `aria-label*="取消"` over-match (the Cancel
63
- button on waiting-for-user screens used to be mistaken for a running signal).
64
- - **Recovery path (issue #5 fallout)**: `continue_task` now supports codex —
65
- - `user_confirmation`: after the user completes the action in the Codex window, resume by
66
- re-attaching as an observer of the in-GUI run (no message is sent); if the turn already
67
- finished before resuming, the task is still judged `succeeded` correctly;
68
- - `login_required`: after login, re-checks the environment and re-dispatches the task brief
69
- (fresh session + project binding + full initial prompt);
70
- - zcode recovery behaviour is unchanged; other agents are rejected explicitly.
71
- - **Cancel actually stops the GUI (issue #6)**:
72
- - `cancel_task` no longer succeeds on request alone for GUI agents: it first best-effort clicks
73
- the in-app stop button over CDP, then waits (bounded by `gui.cancelWaitMs`, default 15s) for
74
- the GUI to become idle before settling `cancelled`; if the stop could not be confirmed the
75
- terminal message states "GUI 内运行未确认停止…" (the in-GUI run may still be going);
76
- - process-tree termination for CLI agents is unchanged;
77
- - cancelling from `needs_user` now notes that a pending session may remain in the GUI
78
- (no CDP connection exists at that point — documented limitation).
79
- - **Re-dispatch anti-overlap guard (issue #6 chain risk)**: when dispatching, if the managed
80
- instance still has an unstopped run, MCP first tries to stop it; if it cannot, the dispatch
81
- fails hard with `instance_busy`, preventing old and new turns from overlapping inside the same
82
- app (observed in the wild when re-dispatching right after a cancel).
83
- - The startup log no longer hardcodes the tool count as `8`; it reports the actual registry size
84
- (`TOOL_DEFS.length`, currently 9).
85
-
86
- ### Changed
87
-
88
- - Tool descriptions match actual semantics: `cancel_task` distinguishes CLI (kill process tree)
89
- from GUI (best-effort stop click + bounded wait); `continue_task` no longer claims to be
90
- ZCode-only.
91
- - `GuiProfile` gains two configurable options, `stallTimeoutMs` (default 300000) and
92
- `cancelWaitMs` (default 15000), both overridable via agent-profiles.json.
93
- - Skill docs (SKILL.md §4/§5, usage-examples.md §7) document the codex `user_confirmation` /
94
- `login_required` recovery flows, GUI cancel semantics and the new options.
95
-
96
- ---
97
-
98
- ## [0.3.1] — 2026-09-12
99
-
100
- Post-v0.3.0 housekeeping for docs and release automation: **no source-level behavior changes**.
101
- The focus is a full rewrite of the self-installed skill docs plus GitHub/Gitee release-body
102
- composition and link fixes.
103
-
104
- ### Changed
105
-
106
- - **Skill docs (`skills/tianshu-mcp/`) fully rewritten to match the actual v0.3.0 tool surface**:
107
- - Corrected the `codex` description from "headless CLI" to the ChatGPT desktop GUI adapter
108
- (MSIX + COM activation + CDP); documents the required `model`, optional `reasoningLevel` /
109
- `planDoc` / `designSystem`, and that `mode` is not supported;
110
- - Documented the `run_task` `context` parameter and the send-time validation of path references
111
- inside task/context; corrected the `autoFixRounds` default precedence
112
- (call argument > codex 5 / zcode 2 > server default 0);
113
- - Added usage for `list_tasks`, `query_task(tailLines)`, `get_task_report(round)` and
114
- `verify_task` (`extraChecks` / `checksMode` / `baselineRef`) plus the four-level acceptance
115
- command precedence;
116
- - Documented the four `needs_user` kinds and meta fields such as `needsUserKind` /
117
- `pendingQuestion` / `errorType` / `reportRound` / `verificationSource`;
118
- - Added `continue_task` to the approval list; replaced emoji status markers with plain text
119
- (PASS / warning) in the usage examples.
120
- - **Release automation fixes (exposed by the v0.3.0 tag)**:
121
- - The release body is now composed bilingually from `docs/release-v<version>.md` and `.en.md`,
122
- with in-document relative links rewritten to tag-absolute links; a missing doc fails the
123
- workflow loudly instead of producing a shell-only body;
124
- - `Full Changelog` resolves the previous tag via `git describe` into a `compare/<prev>...<tag>`
125
- link instead of degrading to a commits link;
126
- - The body's `CI` link resolves the CI run for the same SHA instead of pointing at the Release run;
127
- - Gitee releases are automated in `release.yml`: `scripts/gitee-release.mjs` idempotently
128
- creates/updates the mirrored release (requires the `GITEE_TOKEN` secret; skipped loudly when unset).
129
- - `.gitignore` now ignores npm pack artifacts and local temporary verification directories.
130
- - Added the missing `[0.1.10]` / `[0.2.0]` / `[0.3.0]` / `[0.3.1]` compare links at the bottom of
131
- this file and its Chinese counterpart.
132
-
133
- ---
134
-
135
- ## [0.3.0] — 2026-09-12
136
-
137
- The Codex desktop app now runs through a **GUI driver**: a new `codex-gui` adapter uses MSIX COM activation
138
- plus CDP to drive the ChatGPT desktop app through the full loop (locate install → launch GUI → bind/create
139
- project → pick model and reasoning level → send instructions → run detection → verify → auto-repair).
140
-
141
- ### BREAKING CHANGES
142
-
143
- - **`agentId=codex` now executes via the desktop GUI instead of the headless CLI**: a new `driver=gui` +
144
- `adapter=codex-gui` + `activation=msix-com`, with the previous **`codex exec` headless path removed**.
145
- After upgrading, `run_task(agentId="codex")` launches and drives the Codex desktop window rather than a
146
- headless child process. To keep headless execution, add a separate `driver=spawn` profile
147
- (`argsTemplate: ["exec", "<prompt:arg>", "--skip-git-repo-check", "--sandbox", "workspace-write"]`) as
148
- documented in `docs/agent-profiles.en.md`.
149
- - This path requires the Codex desktop app (MSIX store package) to be installed; CLI-only environments are
150
- no longer directly supported.
151
-
152
- ### Added
153
-
154
- - `codex-gui` adapter (`src/agents/codex/**`): Appx-first install discovery (scan fallback taking the newest
155
- version), MSIX COM activation with a dedicated `user-data-dir` and dynamic debug port, plus CDP attach and
156
- target convergence (excluding the overlay secondary window).
157
- - Task parameters: `reasoningLevel` (low/medium/high, bilingual), `planDoc`, `designSystem`.
158
- - Model and reasoning level: models are `menuitemradio` candidates while **reasoning strength is a slider**
159
- (0–4: 轻度/中/高/极高/极高), set precisely with arrow keys and read back for verification; level
160
- comparison is exact to avoid matching "高" against "极高".
161
- - **Automatic project registration**: a target directory not yet registered on the Codex side is written
162
- directly into Codex project state (idempotent, backup-before-write, atomic write, only while the
163
- MCP-managed instance is stopped), so it takes the stable bound-project path instead of the brittle native
164
- folder dialog; on failure it falls back to UI creation.
165
- - Verification and repair: reuses the existing AcceptanceEngine (defaults derived from `package.json`, with
166
- weak-verification labelling); on failure the MCP generates an in-project
167
- `.zcode/plans/codex-fix-r<N>.md` (one per round, never overwritten) and cites it in the repair instruction,
168
- up to 5 rounds by default (`defaultAutoFixRounds`).
169
- - Run detection: the stop button is the authoritative running signal, and text stability counts as completion
170
- evidence only after it; without a running signal it fails open to `idle_timeout` while keeping the instance
171
- (never a false completion).
172
- - `scripts/probe-codex.mjs` hardware diagnostic script; 67 Codex unit tests plus integration coverage of the
173
- verify-fail → generated plan → repair-pass loop.
174
- - Docs: `docs/codex-gui-cdp.en.md`, `docs/codex-windows-smoke.en.md` (including the round-2 real business task
175
- acceptance) and their Chinese counterparts.
176
-
177
- ### Changed
178
-
179
- - `GuiProfile` gains `activation` / `userDataDir` / `appxPackageName` / `permissionMode` / `fixPlanDir`;
180
- existing `spawn` profiles are unaffected.
181
- - `ExecutableDiscovery` gains `appxPackageName` / `installRelativeExe` / `scanRoots` / `scanPattern`.
182
-
183
- ### Fixed (exposed by hardware testing)
184
-
185
- - The model trigger mis-matched the sibling permission chip (4 chips share `aria-haspopup`; only the model chip
186
- lacks `aria-label`).
187
- - Reasoning strength was clicked like a menu item and could never be set (it is actually a slider).
188
- - Menus/popovers only open on **trusted** mouse events (DOM `.click()` is ignored).
189
- - A transient empty model read during toolbar re-render after binding was treated as a "model mismatch".
190
- - Model/reasoning trigger selectors now exclude the top menu bar and the mode switcher.
191
- - Cold-start readiness budget widened to 150s (registration stops the instance first; cold start measured ~85s).
192
- - CI: fixed a `normalizeDir` assertion that depended on the host platform, which failed on ubuntu/macos.
193
- - Fixed integration tests polluting real Codex project state by not injecting `ensureRegistered`.
194
-
195
- ### Verification
196
-
197
- - Windows 10 x64 hardware: full loop for a registered project, and the verify-fail → generated plan →
198
- repair-pass loop; an unregistered project completed the full loop after automatic registration.
199
- - Real business task: drove Codex to build a "Fruit Ninja" mini-game in HTML+CSS+JS (`GPT-5.6 Sol` with
200
- reasoning strength "高"); the artifacts passed acceptance and were verified playable in a headless browser
201
- (score rises, lives decrement, Game Over and restart work, no JS exceptions).
202
- - macOS unverified: the built-in Codex GUI status is `research` and is excluded from readiness.
203
-
204
- ---
205
-
206
- ## [0.2.0] — 2026-09-11
207
-
208
- ### Added
209
-
210
- - Dedicated `zcode-gui` Electron CDP adapter with data-driven Windows/macOS discovery, dynamic ports, product/process checks, and a global serial lock.
211
- - Exact ZCode project binding, guarded native folder pickers, `provider/model`, Full Access read-back, and idempotent sending.
212
- - Paused `needs_user` state and approval-gated `continue_task` for original-session answers and environment rechecks after instance, login, or permission handling.
213
- - Multi-signal liveness, progress events, UI preservation, default auto-verification, and two same-session repair rounds. Repair plans stay in MCP task storage.
214
- - `scripts/probe-zcode.mjs`, fake-CDP/state/path/model tests, and bilingual documentation.
215
-
216
- ### Safety and compatibility
217
-
218
- - GUI profiles support an explicit `adapter`; legacy `driver="gui"` profiles retain TraeWork behavior.
219
- - The built-in ZCode profile remains `research` until both real platform loops pass.
220
- - No private `app-server`, credential access, automatic user-instance termination, or fixed screen coordinates.
221
-
222
- ### Fixed and verified
223
-
224
- - Fixed ZCode read-back for dynamic model labels, transient renderer load/reload, delayed new-session registration, and stale session-ID contamination.
225
- - `AskUserQuestion` continuation now selects and submits an exact accessible option in the original session; zero or ambiguous matches fail closed.
226
- - Windows 10 x64 passed three hardware loops: real file development, same-session repair after a controlled failure, and `continue_task` after a model question. macOS hardware evidence remains pending.
227
-
228
- ---
229
-
230
- ## [0.1.10] — 2026-09-10
231
-
232
- ### Fixed
233
-
234
- - **Fixed stdio log pollution (issue #1)**: the unified logger previously sent only ERROR to
235
- `console.error` while INFO/WARN/DEBUG went to `console.log`, sharing stdout with MCP JSON-RPC
236
- messages and breaking handshakes or tool calls in strict stdio clients. All levels passing the
237
- threshold now go to stderr, leaving stdout for valid MCP messages only.
238
- - Log file appending, timestamps, level tags and the `<data dir>/logs/server.log` path are unchanged;
239
- a startup failure is still reported on stderr.
240
-
241
- ### Added
242
-
243
- - New `scripts/check-stdio.mjs` strict stdio smoke: a real child process validates the complete
244
- stdout/stderr byte stream, allowing only newline-delimited, schema-valid MCP JSON-RPC messages on
245
- stdout; empty lines, non-JSON lines, parser errors, or trailing fragments at exit fail the run.
246
- It covers six scenarios: first start, second start with matching skills, `--no-skill-install`,
247
- a corrupt `config.json`, logs during a stub task, and clean EOF shutdown.
248
- - New `npm run check:stdio` and `npm run check:stdio:src` scripts.
249
-
250
- ### Tests
251
-
252
- - New `test/unit/log.test.ts`: real-child-process checks for the four log levels' channels, default
253
- INFO filtering, threshold-filtered file logging, and UTF-8 content (4/6 failed before the fix; see
254
- `docs/m2-evidence/issue1-old-impl-log-test-failure.txt`).
255
- - CI's three-platform matrix now includes Node 24; the build step runs the strict stdio check instead
256
- of an EOF-exit-only smoke.
257
- - CI `pack-check` and Release install the freshly built tarball into a clean consumer directory, read
258
- the installed bin dynamically, and reuse the same strict stdio check; Release adds `lint` and the
259
- installed-package protocol gate, failing before a draft is created.
260
- - ESLint enables `no-console` (allowing `error` only) for `src/**/*.ts` to prevent new direct stdout writes.
261
-
262
- ---
263
-
264
- ## [0.1.9] — 2026-09-09
265
-
266
- ### Fixed
267
-
268
- - Fixed premature TraeWork completion while the model was still thinking but the DOM stayed unchanged for about 36 seconds.
269
- The stop button and loading task tail are now authoritative running signals and override completion marks; stable rounds now
270
- start an idle timer, which defaults to ten minutes before returning `idle`.
271
- - Fixed permanently pending `Runtime.evaluate` calls after a CDP WebSocket disconnect. Close/error rejects all pending requests,
272
- each CDP command has a 15-second default timeout, and task cancellation is observed within about one second.
273
- - Only `completion_mark` / `ask_user` release an instance launched by this module. Idle, timeout, cancellation, and CDP loss retain
274
- it, with `agentEndReason` / `keptInstance` exposed in task metadata.
275
- - Fixed a shutdown race where an orchestrator still collecting its baseline could remain `queued` and be mislabeled as a user
276
- cancellation. User cancellation is now determined only from structured cancellation intent.
277
-
278
- ### Added
279
-
280
- - Polling emits a progress event visible through `query_task` every 30 seconds by default.
281
- - Added `gui.idleTimeoutMs`, `gui.cdpSendTimeoutMs`, `gui.progressIntervalMs`, and five overrideable liveness selectors.
282
-
283
- ### Testing
284
-
285
- - Added liveness truth-table, CDP timeout/disconnect convergence, selector-expression, and fake-CDP instance-retention regressions.
286
- - Windows/macOS/Linux × Node 20/22 and tarball gates remain covered.
287
-
288
- ---
289
-
290
- ## [0.1.8] — 2026-09-08
291
-
292
- ### Fixed
293
-
294
- - **Atomic-write concurrency defect** (the real cause of intermittent CI failures): the temp filename in
295
- `writeJsonAtomic`/`writeTextAtomic` was `<target>.<pid>.tmp`, so concurrent writes to the same target in one
296
- process shared one temp file - the first to finish renames it away and the next throws `ENOENT`; on Windows a
297
- concurrent rename can also throw `EPERM`. Symptom: `rework_task` intermittently returned an `undefined` meta
298
- (hit on CI windows/Node 20). Fixed by a random temp suffix plus backoff-retry on transient rename errors.
299
-
300
- ### Testing
301
-
302
- - New `test/unit/atomic-write.test.ts` (3 cases: concurrent JSON/text writes all succeed, no leftover temp files).
303
-
304
- ---
305
-
306
- ## [0.1.7] — 2026-09-08
307
-
308
- ### Fixed
309
-
310
- - **Project-folder binding still failed** (v0.1.6 did not fully resolve it; field report: the native dialog
311
- appeared but the edit box was empty and confirm was clicked anyway):
312
- - **Root cause**: the MCP passes a `normPath()`-normalized path (lowercase drive + forward slashes, e.g.
313
- `d:/Trae项目/AI游戏/象棋`), which the **native Windows picker rejects** — measured: read-back matched, yet the dialog
314
- stayed open after confirm. Fix: convert via the new `toNativeWindowsPath()` to `D:\a\b`.
315
- - `WM_GETTEXT` **read-back verification** after writing; on mismatch re-locate and retry (up to 3 times);
316
- if it still mismatches, **never click confirm** and fail loudly.
317
- - The hwnd detected after the footer click is **passed into the write script**; after clicking, success
318
- requires that hwnd to be gone.
319
- - **Auto-close stale dialogs** (left over from a previous failure) before binding.
320
- - Confirm button now also requires its rect to be in the lower half of the dialog.
321
- - The dialog script's full trace (HWND/READBACK) is written to the task log.
322
-
323
- ### Testing
324
-
325
- - Total tests **172 → 181** (unit incl. path normalization and atomic-write concurrency; integration incl. stale-dialog cleanup).
326
- - Machine-verified: a new Chinese project `D:\Trae项目\AI游戏\象棋` (absent from the dropdown)
327
- passed end-to-end through the native dialog; `五子棋` and the ASCII project `ts-bind-test` regressed green.
328
-
329
- ---
330
-
331
- ## [0.1.6] — 2026-09-08
332
-
333
- ### Fixed
334
-
335
- - **Project-folder binding got stuck / reported "waiting for native dialog timed out"** (field report; the adapter was not broken):
336
- - `clickDropdownFooter` used to trust `element.click()`'s return value, but the native popup may never
337
- appear → it now **confirms the dialog actually appeared**, otherwise it logs a dropdown DOM snapshot and fails loudly.
338
- - Dialog detection polled from Node every 800 ms while PowerShell cold start is ~4.5–6 s, so a 15 s budget
339
- allowed only ~2 probes → now it polls **inside a single PowerShell call** (400 ms interval) with a 30 s budget.
340
- - **CJK paths were corrupted** (measured: `D:\Trae项目\ts-bind-test` became `D:Traes-bind-test`):
341
- SendKeys/clipboard are mangled by the console code page → the path is now written via Win32
342
- **`WM_SETTEXT`**, which is fully reliable for CJK.
343
- - **The confirm click hit a file-list row**: `AutomationId="1"` is not unique (rows also use 0/1/2…) →
344
- now located by **AutomationId=1 AND ControlType=Pane**, then clicked by bounding rect.
345
- - PowerShell output was garbled for Chinese → the script now emits **ASCII-only** and Node maps it back
346
- via `localizeDialogMessage()`.
347
-
348
- ### Added
349
-
350
- - **Non-Work binding fallback**: when binding fails in Code/Design, the driver **falls back to Work once**,
351
- switches back to the target mode, and re-verifies the project is still bound; only if both attempts fail
352
- does it report an error including the reason from each mode.
353
- - Machine-verified: for a project **absent from the dropdown** (`D:\Trae项目\ts-bind-test`),
354
- `run_task(agentId=traework, mode=Code)` passed end-to-end — native dialog wrote the path → confirm clicked →
355
- project entered TraeWork's list (`solo-lite.local-project-folders` 22→23) → task sent → auto-verification `succeeded`.
356
-
357
- ### Changed
358
-
359
- - `docs/traework-cdp.md` / `.en.md`: 7 new pitfall entries; added the "dropdown entries ≠ project map" fact and the fallback note.
360
-
361
- ### Testing
362
-
363
- - Total tests **167 → 172** (new dialog message-mapping/platform-branch unit tests + Code→Work fallback integration test).
364
-
365
- ---
366
-
367
- ## [0.1.5] — 2026-09-08
368
-
369
- ### Added
370
-
371
- - **TraeWork panel mode switching**: `run_task` gained a `mode` parameter supporting `Work` / `Code` / `Design`.
372
- - Resolution order: explicit `mode` parameter > task-text detection > keep `Work`.
373
- - Text detection handles mixed Chinese/English phrasing ("switch to Code mode", "use design mode", "工作模式", "代码模式", "设计模式", …).
374
- - New `gui.modeSwitch` profile switch (default `true`).
375
- - New pure functions `detectModeFromText` / `resolveMode` (unit-tested).
376
- - **Dedicated SVG assets**: `assets/tianshu-mcp-icon.svg` (app icon), `assets/tianshu-mcp-banner.svg` (wide banner).
377
- - New `scripts/probe-traework.mjs mode <Work|Code|Design>` subcommand (real-machine diagnostics/verification).
378
- - New bilingual release notes `docs/release-v0.1.5.md` / `.en.md`.
379
-
380
- ### Changed
381
-
382
- - **TraeWork execution order**: measurement showed the three modes **each keep an independent project binding** —
383
- switching modes replaces the input bar's project with whatever that mode last used.
384
- Order is now: ensure instance → wait for UI → new session → switch to target mode → bind project inside that mode → switch model → send.
385
- - After binding, both mode and project are re-verified; any mismatch **fails loudly** (never silently develops in the wrong mode).
386
- - meta block now exposes `model` / `mode` for Tianshu to read back.
387
- - `package.json`: `license` changed from `MIT` to `Apache-2.0` (matching the repository `LICENSE` file);
388
- added `repository` / `homepage` / `bugs`; `files` now includes `assets`.
389
- - README.md / README.en.md fully rewritten: stack badges, SVG banner (above the icon), language isolation
390
- (the Chinese README references Chinese docs only; the English README references English docs only).
391
-
392
- ### Fixed
393
-
394
- - **Rework feedback race** (pre-existing; intermittent under load): the terminal snapshot is written first, so a caller's
395
- immediate `rework_task(feedback)` could be erased by the previous run's `delete meta.reworkFeedback`, leaving the rework
396
- round without feedback. Now the feedback is consumed and cleared atomically when `startTask` begins.
397
- Added regression test `test/integration/rework-feedback-race.test.ts`.
398
- - **`projectBasename` cross-platform**: it used `path.basename` (which does not split backslashes on POSIX), failing
399
- Linux/macOS CI; now it splits explicitly on both `\` and `/`.
400
-
401
- ### Testing
402
-
403
- - Total tests **153 → 167** (14 new mode-related cases).
404
- - Real-machine end-to-end: `mode=Work` / `mode=Code` / `mode=Design` all completed
405
- "switch mode → bind project → send → create file → auto-verification passed".
406
-
407
- ---
408
-
409
- ## [0.1.4] — 2026-09-08
410
-
411
- ### Added
412
-
413
- - TraeWork GUI driver over CDP: `traework` moved from `unsupported` to `driver=gui` / `status=ready`.
414
- - Capabilities: launch/reuse instance → new session → bind project folder (dropdown first, restricted computer-use
415
- native dialog as fallback) → optional model selection → read-back-verified send → poll to completion →
416
- auto-verify → repair-plan file + same-session rework on failure.
417
- - Safety: reuse the user's instance by default, never kill a process tree, verify the command line before terminating;
418
- computer-use is limited to TraeWork's folder picker.
419
- - `AgentAdapter` gained an optional `run()` execution surface; the orchestrator branches on `adapter.run`
420
- (CLI agents still use spawn).
421
- - Profile gained `driver` (`spawn` / `gui`) and a `gui` section; `run_task` gained a `model` parameter.
422
- - New `src/agents/traework/**` (CDP client, selector table, launcher, session/input/model/reply modules, restricted computer-use).
423
- - On verification failure a repair-plan file `rework-<taskId>-r<N>.md` is generated (task dir + project `.tianshu-mcp`)
424
- and its filename is referenced in the rework message.
425
-
426
- ### Changed
427
-
428
- - `docs/adapter-matrix.md` T1 conclusion corrected from `unsupported` to "integrated (driver=gui)".
429
- - formatter now passes cancel-source fields (`abortSource`, …) through to `query_task`'s meta block.
430
-
431
- ### Fixed
432
-
433
- - Unified timeout terminal state: normal timeouts now also land `failed(timeout)` plus exactly one `timeout_killed` event, in fixed order.
434
- - Stabilized the `shutdown` test polling.
435
-
436
- ### Testing
437
-
438
- - Total tests **72 → 153** (new TraeWork unit/integration cases).
439
- - Real-machine end-to-end: `run_task(agentId=traework, model=GLM-5.3, autoVerify=true)` drove TraeWork to create a file and passed acceptance.
440
-
441
- ---
442
-
443
- ## [0.1.3] — 2026-09-08
444
-
445
- ### Fixed
446
-
447
- - **S1** No-reason cancel was mis-recorded as `interrupted`: added independent `cancelRequestedAt` / `abortSource` fields;
448
- cancel intent no longer depends on the optional `reason` (5 regression tests).
449
- - **S2** Unified timeout terminal state (shared with 0.1.4).
450
- - **S3** Tracked pre-dirty net-diff attribution: pre-existing dirty files are excluded by content hash when unchanged;
451
- unchanged staged/unstaged files are no longer reported as agent changes (4 regressions).
452
- - **S4** `verify_task(taskId)` persists real-task metadata (`reportRound` / `verificationSource` /
453
- `latestVerificationVerdict`, keeping `agentId`); single-source MCP version (`sync-version` injection).
454
- - **S5** `projects.json` official Zod schema + last-known-good for `config`/`profiles`/`projects` + content-sha256
455
- hot-reload invalidation (fixed corrupt JSON being treated as missing and reset).
456
-
457
- ### Changed
458
-
459
- - **S6** CI/Release `npm ci` retry corrected (stop on success / 3 attempts / attempt counter);
460
- Vitest v3 upgrade (0 audit vulnerabilities); plain-text status markers (emoji scan test).
461
-
462
- ### Testing
463
-
464
- - Total tests **53 → 72**.
465
-
466
- ---
467
-
468
- ## [0.1.2] — 2026-09-08
469
-
470
- ### Changed
471
-
472
- - Build no longer ships source maps (no `.map`, tarball ≈ 69.9 KB).
473
-
474
- ### Testing
475
-
476
- - Total tests **53**.
477
-
478
- ---
479
-
480
- ## [0.1.1] — 2026-09-07
481
-
482
- ### Added
483
-
484
- - **Release after the R1–R5 fixes**:
485
- - **R1** Cancel/interrupt state persistence (`cancel_requested → cancelled`, `cancelReason`/`finishedAt`/`errorType`
486
- persisted, restart-recoverable, idempotent, bounded shutdown).
487
- - **R2** Call-level `taskTimeoutMs` precedence fix + cross-platform process-tree termination
488
- (POSIX process-group SIGTERM→SIGKILL, Windows `taskkill /T /F`).
489
- - **R3** Git baseline participates in diff (boundary at `baseline.head`; agent commits do not lose changes;
490
- dirty-worktree hash attribution).
491
- - **R4** Verification tool parameters and report-round semantics (`round=0` valid, manual verify does not overwrite
492
- reports, `extraChecks` append + `checksMode=replace`, `optional` does not affect verdict, `baselineRef` validated).
493
- - **R5** Removed hardcoded agent paths (`{LOCALAPPDATA}` placeholders + platform-standard candidates);
494
- mtime hot reload for `config`/`profile`/`projects`.
495
- - **R6** Cross-platform CI matrix (Windows/macOS/Linux × Node 20/22) and Release version consistency
496
- (tag/input = `package.json` = tarball), plus tarball content checks.
497
- - **R7** npm published `tianshu-mcp@0.1.1` + `npx -y` raise with 8 tools connected.
498
- - **R8** Bilingual docs synced (including 4 English topic docs).
499
-
500
- ---
501
-
502
- ## [0.1.0] — 2026-09-07
503
-
504
- ### Added
505
-
506
- - First usable release: **M1 core engine + stub-agent end-to-end**.
507
- - 8 MCP tools: `run_task` / `query_task` / `list_tasks` / `get_task_report` / `cancel_task` / `verify_task` /
508
- `rework_task` / `get_profiles`.
509
- - `TaskManager` state machine / per-project serial queue / global concurrency gate / cancel (kill tree) / event-stream persistence.
510
- - Acceptance engine: git baseline & diff, default check-set derivation, command runner, code analysis,
511
- `report.md` / `report.json`.
512
- - fix-loop auto rework + `needs_attention`; skill self-install.
513
- - Stub-agent 3 playbooks (good / fix-on-first / never) integration tests + protocol tests — **53/53 green**.
514
-
515
- ---
516
-
517
- [Unreleased]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.3...HEAD
122
+
123
+ Fixes for issues #5 / #6: **the MCP task model was disconnected from the state of the turn inside
124
+ the Codex GUI**. The former is the completion-detection deadlock that kept reporting `running`
125
+ while Codex waited for user confirmation; the latter is `cancel_task` only aborting the MCP-side
126
+ wait loop, never stopping the in-GUI run, with a misleading description. Both share the same root
127
+ cause and are resolved together.
128
+
129
+ ### Fixed
130
+
131
+ - **Waiting-for-user detection (issue #5)**:
132
+ - `judgeCodexPoll` gains a stall fallback: while the stop button stays visible and the
133
+ conversation hash is unchanged for `gui.stallTimeoutMs` (default 5 minutes), the task
134
+ transitions to `needs_user` (`needsUserKind=user_confirmation`) instead of deadlocking in
135
+ `running` until the overall timeout; the stall timer resets as soon as content changes again.
136
+ - New configurable UI detection `gui.selectors.userGate` (e.g. the embedded-checkout page or
137
+ approval cards): when configured and matched, transitions to `needs_user` immediately.
138
+ Unset by default (disabled) — no unverified selectors are built in.
139
+ - Tightened the `stopButton` selector: removed the `aria-label*="取消"` over-match (the Cancel
140
+ button on waiting-for-user screens used to be mistaken for a running signal).
141
+ - **Recovery path (issue #5 fallout)**: `continue_task` now supports codex —
142
+ - `user_confirmation`: after the user completes the action in the Codex window, resume by
143
+ re-attaching as an observer of the in-GUI run (no message is sent); if the turn already
144
+ finished before resuming, the task is still judged `succeeded` correctly;
145
+ - `login_required`: after login, re-checks the environment and re-dispatches the task brief
146
+ (fresh session + project binding + full initial prompt);
147
+ - zcode recovery behaviour is unchanged; other agents are rejected explicitly.
148
+ - **Cancel actually stops the GUI (issue #6)**:
149
+ - `cancel_task` no longer succeeds on request alone for GUI agents: it first best-effort clicks
150
+ the in-app stop button over CDP, then waits (bounded by `gui.cancelWaitMs`, default 15s) for
151
+ the GUI to become idle before settling `cancelled`; if the stop could not be confirmed the
152
+ terminal message states "GUI 内运行未确认停止…" (the in-GUI run may still be going);
153
+ - process-tree termination for CLI agents is unchanged;
154
+ - cancelling from `needs_user` now notes that a pending session may remain in the GUI
155
+ (no CDP connection exists at that point — documented limitation).
156
+ - **Re-dispatch anti-overlap guard (issue #6 chain risk)**: when dispatching, if the managed
157
+ instance still has an unstopped run, MCP first tries to stop it; if it cannot, the dispatch
158
+ fails hard with `instance_busy`, preventing old and new turns from overlapping inside the same
159
+ app (observed in the wild when re-dispatching right after a cancel).
160
+ - The startup log no longer hardcodes the tool count as `8`; it reports the actual registry size
161
+ (`TOOL_DEFS.length`, currently 9).
162
+
163
+ ### Changed
164
+
165
+ - Tool descriptions match actual semantics: `cancel_task` distinguishes CLI (kill process tree)
166
+ from GUI (best-effort stop click + bounded wait); `continue_task` no longer claims to be
167
+ ZCode-only.
168
+ - `GuiProfile` gains two configurable options, `stallTimeoutMs` (default 300000) and
169
+ `cancelWaitMs` (default 15000), both overridable via agent-profiles.json.
170
+ - Skill docs (SKILL.md §4/§5, usage-examples.md §7) document the codex `user_confirmation` /
171
+ `login_required` recovery flows, GUI cancel semantics and the new options.
172
+
173
+ ---
174
+
175
+ ## [0.3.1] — 2026-09-12
176
+
177
+ Post-v0.3.0 housekeeping for docs and release automation: **no source-level behavior changes**.
178
+ The focus is a full rewrite of the self-installed skill docs plus GitHub/Gitee release-body
179
+ composition and link fixes.
180
+
181
+ ### Changed
182
+
183
+ - **Skill docs (`skills/tianshu-mcp/`) fully rewritten to match the actual v0.3.0 tool surface**:
184
+ - Corrected the `codex` description from "headless CLI" to the ChatGPT desktop GUI adapter
185
+ (MSIX + COM activation + CDP); documents the required `model`, optional `reasoningLevel` /
186
+ `planDoc` / `designSystem`, and that `mode` is not supported;
187
+ - Documented the `run_task` `context` parameter and the send-time validation of path references
188
+ inside task/context; corrected the `autoFixRounds` default precedence
189
+ (call argument > codex 5 / zcode 2 > server default 0);
190
+ - Added usage for `list_tasks`, `query_task(tailLines)`, `get_task_report(round)` and
191
+ `verify_task` (`extraChecks` / `checksMode` / `baselineRef`) plus the four-level acceptance
192
+ command precedence;
193
+ - Documented the four `needs_user` kinds and meta fields such as `needsUserKind` /
194
+ `pendingQuestion` / `errorType` / `reportRound` / `verificationSource`;
195
+ - Added `continue_task` to the approval list; replaced emoji status markers with plain text
196
+ (PASS / warning) in the usage examples.
197
+ - **Release automation fixes (exposed by the v0.3.0 tag)**:
198
+ - The release body is now composed bilingually from `docs/release-v<version>.md` and `.en.md`,
199
+ with in-document relative links rewritten to tag-absolute links; a missing doc fails the
200
+ workflow loudly instead of producing a shell-only body;
201
+ - `Full Changelog` resolves the previous tag via `git describe` into a `compare/<prev>...<tag>`
202
+ link instead of degrading to a commits link;
203
+ - The body's `CI` link resolves the CI run for the same SHA instead of pointing at the Release run;
204
+ - Gitee releases are automated in `release.yml`: `scripts/gitee-release.mjs` idempotently
205
+ creates/updates the mirrored release (requires the `GITEE_TOKEN` secret; skipped loudly when unset).
206
+ - `.gitignore` now ignores npm pack artifacts and local temporary verification directories.
207
+ - Added the missing `[0.1.10]` / `[0.2.0]` / `[0.3.0]` / `[0.3.1]` compare links at the bottom of
208
+ this file and its Chinese counterpart.
209
+
210
+ ---
211
+
212
+ ## [0.3.0] — 2026-09-12
213
+
214
+ The Codex desktop app now runs through a **GUI driver**: a new `codex-gui` adapter uses MSIX COM activation
215
+ plus CDP to drive the ChatGPT desktop app through the full loop (locate install → launch GUI → bind/create
216
+ project → pick model and reasoning level → send instructions → run detection → verify → auto-repair).
217
+
218
+ ### BREAKING CHANGES
219
+
220
+ - **`agentId=codex` now executes via the desktop GUI instead of the headless CLI**: a new `driver=gui` +
221
+ `adapter=codex-gui` + `activation=msix-com`, with the previous **`codex exec` headless path removed**.
222
+ After upgrading, `run_task(agentId="codex")` launches and drives the Codex desktop window rather than a
223
+ headless child process. To keep headless execution, add a separate `driver=spawn` profile
224
+ (`argsTemplate: ["exec", "<prompt:arg>", "--skip-git-repo-check", "--sandbox", "workspace-write"]`) as
225
+ documented in `docs/agent-profiles.en.md`.
226
+ - This path requires the Codex desktop app (MSIX store package) to be installed; CLI-only environments are
227
+ no longer directly supported.
228
+
229
+ ### Added
230
+
231
+ - `codex-gui` adapter (`src/agents/codex/**`): Appx-first install discovery (scan fallback taking the newest
232
+ version), MSIX COM activation with a dedicated `user-data-dir` and dynamic debug port, plus CDP attach and
233
+ target convergence (excluding the overlay secondary window).
234
+ - Task parameters: `reasoningLevel` (low/medium/high, bilingual), `planDoc`, `designSystem`.
235
+ - Model and reasoning level: models are `menuitemradio` candidates while **reasoning strength is a slider**
236
+ (0–4: 轻度/中/高/极高/极高), set precisely with arrow keys and read back for verification; level
237
+ comparison is exact to avoid matching "高" against "极高".
238
+ - **Automatic project registration**: a target directory not yet registered on the Codex side is written
239
+ directly into Codex project state (idempotent, backup-before-write, atomic write, only while the
240
+ MCP-managed instance is stopped), so it takes the stable bound-project path instead of the brittle native
241
+ folder dialog; on failure it falls back to UI creation.
242
+ - Verification and repair: reuses the existing AcceptanceEngine (defaults derived from `package.json`, with
243
+ weak-verification labelling); on failure the MCP generates an in-project
244
+ `.zcode/plans/codex-fix-r<N>.md` (one per round, never overwritten) and cites it in the repair instruction,
245
+ up to 5 rounds by default (`defaultAutoFixRounds`).
246
+ - Run detection: the stop button is the authoritative running signal, and text stability counts as completion
247
+ evidence only after it; without a running signal it fails open to `idle_timeout` while keeping the instance
248
+ (never a false completion).
249
+ - `scripts/probe-codex.mjs` hardware diagnostic script; 67 Codex unit tests plus integration coverage of the
250
+ verify-fail → generated plan → repair-pass loop.
251
+ - Docs: `docs/codex-gui-cdp.en.md`, `docs/codex-windows-smoke.en.md` (including the round-2 real business task
252
+ acceptance) and their Chinese counterparts.
253
+
254
+ ### Changed
255
+
256
+ - `GuiProfile` gains `activation` / `userDataDir` / `appxPackageName` / `permissionMode` / `fixPlanDir`;
257
+ existing `spawn` profiles are unaffected.
258
+ - `ExecutableDiscovery` gains `appxPackageName` / `installRelativeExe` / `scanRoots` / `scanPattern`.
259
+
260
+ ### Fixed (exposed by hardware testing)
261
+
262
+ - The model trigger mis-matched the sibling permission chip (4 chips share `aria-haspopup`; only the model chip
263
+ lacks `aria-label`).
264
+ - Reasoning strength was clicked like a menu item and could never be set (it is actually a slider).
265
+ - Menus/popovers only open on **trusted** mouse events (DOM `.click()` is ignored).
266
+ - A transient empty model read during toolbar re-render after binding was treated as a "model mismatch".
267
+ - Model/reasoning trigger selectors now exclude the top menu bar and the mode switcher.
268
+ - Cold-start readiness budget widened to 150s (registration stops the instance first; cold start measured ~85s).
269
+ - CI: fixed a `normalizeDir` assertion that depended on the host platform, which failed on ubuntu/macos.
270
+ - Fixed integration tests polluting real Codex project state by not injecting `ensureRegistered`.
271
+
272
+ ### Verification
273
+
274
+ - Windows 10 x64 hardware: full loop for a registered project, and the verify-fail → generated plan →
275
+ repair-pass loop; an unregistered project completed the full loop after automatic registration.
276
+ - Real business task: drove Codex to build a "Fruit Ninja" mini-game in HTML+CSS+JS (`GPT-5.6 Sol` with
277
+ reasoning strength "高"); the artifacts passed acceptance and were verified playable in a headless browser
278
+ (score rises, lives decrement, Game Over and restart work, no JS exceptions).
279
+ - macOS unverified: the built-in Codex GUI status is `research` and is excluded from readiness.
280
+
281
+ ---
282
+
283
+ ## [0.2.0] — 2026-09-11
284
+
285
+ ### Added
286
+
287
+ - Dedicated `zcode-gui` Electron CDP adapter with data-driven Windows/macOS discovery, dynamic ports, product/process checks, and a global serial lock.
288
+ - Exact ZCode project binding, guarded native folder pickers, `provider/model`, Full Access read-back, and idempotent sending.
289
+ - Paused `needs_user` state and approval-gated `continue_task` for original-session answers and environment rechecks after instance, login, or permission handling.
290
+ - Multi-signal liveness, progress events, UI preservation, default auto-verification, and two same-session repair rounds. Repair plans stay in MCP task storage.
291
+ - `scripts/probe-zcode.mjs`, fake-CDP/state/path/model tests, and bilingual documentation.
292
+
293
+ ### Safety and compatibility
294
+
295
+ - GUI profiles support an explicit `adapter`; legacy `driver="gui"` profiles retain TraeWork behavior.
296
+ - The built-in ZCode profile remains `research` until both real platform loops pass.
297
+ - No private `app-server`, credential access, automatic user-instance termination, or fixed screen coordinates.
298
+
299
+ ### Fixed and verified
300
+
301
+ - Fixed ZCode read-back for dynamic model labels, transient renderer load/reload, delayed new-session registration, and stale session-ID contamination.
302
+ - `AskUserQuestion` continuation now selects and submits an exact accessible option in the original session; zero or ambiguous matches fail closed.
303
+ - Windows 10 x64 passed three hardware loops: real file development, same-session repair after a controlled failure, and `continue_task` after a model question. macOS hardware evidence remains pending.
304
+
305
+ ---
306
+
307
+ ## [0.1.10] — 2026-09-10
308
+
309
+ ### Fixed
310
+
311
+ - **Fixed stdio log pollution (issue #1)**: the unified logger previously sent only ERROR to
312
+ `console.error` while INFO/WARN/DEBUG went to `console.log`, sharing stdout with MCP JSON-RPC
313
+ messages and breaking handshakes or tool calls in strict stdio clients. All levels passing the
314
+ threshold now go to stderr, leaving stdout for valid MCP messages only.
315
+ - Log file appending, timestamps, level tags and the `<data dir>/logs/server.log` path are unchanged;
316
+ a startup failure is still reported on stderr.
317
+
318
+ ### Added
319
+
320
+ - New `scripts/check-stdio.mjs` strict stdio smoke: a real child process validates the complete
321
+ stdout/stderr byte stream, allowing only newline-delimited, schema-valid MCP JSON-RPC messages on
322
+ stdout; empty lines, non-JSON lines, parser errors, or trailing fragments at exit fail the run.
323
+ It covers six scenarios: first start, second start with matching skills, `--no-skill-install`,
324
+ a corrupt `config.json`, logs during a stub task, and clean EOF shutdown.
325
+ - New `npm run check:stdio` and `npm run check:stdio:src` scripts.
326
+
327
+ ### Tests
328
+
329
+ - New `test/unit/log.test.ts`: real-child-process checks for the four log levels' channels, default
330
+ INFO filtering, threshold-filtered file logging, and UTF-8 content (4/6 failed before the fix; see
331
+ `docs/m2-evidence/issue1-old-impl-log-test-failure.txt`).
332
+ - CI's three-platform matrix now includes Node 24; the build step runs the strict stdio check instead
333
+ of an EOF-exit-only smoke.
334
+ - CI `pack-check` and Release install the freshly built tarball into a clean consumer directory, read
335
+ the installed bin dynamically, and reuse the same strict stdio check; Release adds `lint` and the
336
+ installed-package protocol gate, failing before a draft is created.
337
+ - ESLint enables `no-console` (allowing `error` only) for `src/**/*.ts` to prevent new direct stdout writes.
338
+
339
+ ---
340
+
341
+ ## [0.1.9] — 2026-09-09
342
+
343
+ ### Fixed
344
+
345
+ - Fixed premature TraeWork completion while the model was still thinking but the DOM stayed unchanged for about 36 seconds.
346
+ The stop button and loading task tail are now authoritative running signals and override completion marks; stable rounds now
347
+ start an idle timer, which defaults to ten minutes before returning `idle`.
348
+ - Fixed permanently pending `Runtime.evaluate` calls after a CDP WebSocket disconnect. Close/error rejects all pending requests,
349
+ each CDP command has a 15-second default timeout, and task cancellation is observed within about one second.
350
+ - Only `completion_mark` / `ask_user` release an instance launched by this module. Idle, timeout, cancellation, and CDP loss retain
351
+ it, with `agentEndReason` / `keptInstance` exposed in task metadata.
352
+ - Fixed a shutdown race where an orchestrator still collecting its baseline could remain `queued` and be mislabeled as a user
353
+ cancellation. User cancellation is now determined only from structured cancellation intent.
354
+
355
+ ### Added
356
+
357
+ - Polling emits a progress event visible through `query_task` every 30 seconds by default.
358
+ - Added `gui.idleTimeoutMs`, `gui.cdpSendTimeoutMs`, `gui.progressIntervalMs`, and five overrideable liveness selectors.
359
+
360
+ ### Testing
361
+
362
+ - Added liveness truth-table, CDP timeout/disconnect convergence, selector-expression, and fake-CDP instance-retention regressions.
363
+ - Windows/macOS/Linux × Node 20/22 and tarball gates remain covered.
364
+
365
+ ---
366
+
367
+ ## [0.1.8] — 2026-09-08
368
+
369
+ ### Fixed
370
+
371
+ - **Atomic-write concurrency defect** (the real cause of intermittent CI failures): the temp filename in
372
+ `writeJsonAtomic`/`writeTextAtomic` was `<target>.<pid>.tmp`, so concurrent writes to the same target in one
373
+ process shared one temp file - the first to finish renames it away and the next throws `ENOENT`; on Windows a
374
+ concurrent rename can also throw `EPERM`. Symptom: `rework_task` intermittently returned an `undefined` meta
375
+ (hit on CI windows/Node 20). Fixed by a random temp suffix plus backoff-retry on transient rename errors.
376
+
377
+ ### Testing
378
+
379
+ - New `test/unit/atomic-write.test.ts` (3 cases: concurrent JSON/text writes all succeed, no leftover temp files).
380
+
381
+ ---
382
+
383
+ ## [0.1.7] — 2026-09-08
384
+
385
+ ### Fixed
386
+
387
+ - **Project-folder binding still failed** (v0.1.6 did not fully resolve it; field report: the native dialog
388
+ appeared but the edit box was empty and confirm was clicked anyway):
389
+ - **Root cause**: the MCP passes a `normPath()`-normalized path (lowercase drive + forward slashes, e.g.
390
+ `d:/Trae项目/AI游戏/象棋`), which the **native Windows picker rejects** — measured: read-back matched, yet the dialog
391
+ stayed open after confirm. Fix: convert via the new `toNativeWindowsPath()` to `D:\a\b`.
392
+ - `WM_GETTEXT` **read-back verification** after writing; on mismatch re-locate and retry (up to 3 times);
393
+ if it still mismatches, **never click confirm** and fail loudly.
394
+ - The hwnd detected after the footer click is **passed into the write script**; after clicking, success
395
+ requires that hwnd to be gone.
396
+ - **Auto-close stale dialogs** (left over from a previous failure) before binding.
397
+ - Confirm button now also requires its rect to be in the lower half of the dialog.
398
+ - The dialog script's full trace (HWND/READBACK) is written to the task log.
399
+
400
+ ### Testing
401
+
402
+ - Total tests **172 → 181** (unit incl. path normalization and atomic-write concurrency; integration incl. stale-dialog cleanup).
403
+ - Machine-verified: a new Chinese project `D:\Trae项目\AI游戏\象棋` (absent from the dropdown)
404
+ passed end-to-end through the native dialog; `五子棋` and the ASCII project `ts-bind-test` regressed green.
405
+
406
+ ---
407
+
408
+ ## [0.1.6] — 2026-09-08
409
+
410
+ ### Fixed
411
+
412
+ - **Project-folder binding got stuck / reported "waiting for native dialog timed out"** (field report; the adapter was not broken):
413
+ - `clickDropdownFooter` used to trust `element.click()`'s return value, but the native popup may never
414
+ appear → it now **confirms the dialog actually appeared**, otherwise it logs a dropdown DOM snapshot and fails loudly.
415
+ - Dialog detection polled from Node every 800 ms while PowerShell cold start is ~4.5–6 s, so a 15 s budget
416
+ allowed only ~2 probes → now it polls **inside a single PowerShell call** (400 ms interval) with a 30 s budget.
417
+ - **CJK paths were corrupted** (measured: `D:\Trae项目\ts-bind-test` became `D:Traes-bind-test`):
418
+ SendKeys/clipboard are mangled by the console code page → the path is now written via Win32
419
+ **`WM_SETTEXT`**, which is fully reliable for CJK.
420
+ - **The confirm click hit a file-list row**: `AutomationId="1"` is not unique (rows also use 0/1/2…) →
421
+ now located by **AutomationId=1 AND ControlType=Pane**, then clicked by bounding rect.
422
+ - PowerShell output was garbled for Chinese → the script now emits **ASCII-only** and Node maps it back
423
+ via `localizeDialogMessage()`.
424
+
425
+ ### Added
426
+
427
+ - **Non-Work binding fallback**: when binding fails in Code/Design, the driver **falls back to Work once**,
428
+ switches back to the target mode, and re-verifies the project is still bound; only if both attempts fail
429
+ does it report an error including the reason from each mode.
430
+ - Machine-verified: for a project **absent from the dropdown** (`D:\Trae项目\ts-bind-test`),
431
+ `run_task(agentId=traework, mode=Code)` passed end-to-end — native dialog wrote the path → confirm clicked →
432
+ project entered TraeWork's list (`solo-lite.local-project-folders` 22→23) → task sent → auto-verification `succeeded`.
433
+
434
+ ### Changed
435
+
436
+ - `docs/traework-cdp.md` / `.en.md`: 7 new pitfall entries; added the "dropdown entries ≠ project map" fact and the fallback note.
437
+
438
+ ### Testing
439
+
440
+ - Total tests **167 → 172** (new dialog message-mapping/platform-branch unit tests + Code→Work fallback integration test).
441
+
442
+ ---
443
+
444
+ ## [0.1.5] — 2026-09-08
445
+
446
+ ### Added
447
+
448
+ - **TraeWork panel mode switching**: `run_task` gained a `mode` parameter supporting `Work` / `Code` / `Design`.
449
+ - Resolution order: explicit `mode` parameter > task-text detection > keep `Work`.
450
+ - Text detection handles mixed Chinese/English phrasing ("switch to Code mode", "use design mode", "工作模式", "代码模式", "设计模式", …).
451
+ - New `gui.modeSwitch` profile switch (default `true`).
452
+ - New pure functions `detectModeFromText` / `resolveMode` (unit-tested).
453
+ - **Dedicated SVG assets**: `assets/tianshu-mcp-icon.svg` (app icon), `assets/tianshu-mcp-banner.svg` (wide banner).
454
+ - New `scripts/probe-traework.mjs mode <Work|Code|Design>` subcommand (real-machine diagnostics/verification).
455
+ - New bilingual release notes `docs/release-v0.1.5.md` / `.en.md`.
456
+
457
+ ### Changed
458
+
459
+ - **TraeWork execution order**: measurement showed the three modes **each keep an independent project binding** —
460
+ switching modes replaces the input bar's project with whatever that mode last used.
461
+ Order is now: ensure instance → wait for UI → new session → switch to target mode → bind project inside that mode → switch model → send.
462
+ - After binding, both mode and project are re-verified; any mismatch **fails loudly** (never silently develops in the wrong mode).
463
+ - meta block now exposes `model` / `mode` for Tianshu to read back.
464
+ - `package.json`: `license` changed from `MIT` to `Apache-2.0` (matching the repository `LICENSE` file);
465
+ added `repository` / `homepage` / `bugs`; `files` now includes `assets`.
466
+ - README.md / README.en.md fully rewritten: stack badges, SVG banner (above the icon), language isolation
467
+ (the Chinese README references Chinese docs only; the English README references English docs only).
468
+
469
+ ### Fixed
470
+
471
+ - **Rework feedback race** (pre-existing; intermittent under load): the terminal snapshot is written first, so a caller's
472
+ immediate `rework_task(feedback)` could be erased by the previous run's `delete meta.reworkFeedback`, leaving the rework
473
+ round without feedback. Now the feedback is consumed and cleared atomically when `startTask` begins.
474
+ Added regression test `test/integration/rework-feedback-race.test.ts`.
475
+ - **`projectBasename` cross-platform**: it used `path.basename` (which does not split backslashes on POSIX), failing
476
+ Linux/macOS CI; now it splits explicitly on both `\` and `/`.
477
+
478
+ ### Testing
479
+
480
+ - Total tests **153 → 167** (14 new mode-related cases).
481
+ - Real-machine end-to-end: `mode=Work` / `mode=Code` / `mode=Design` all completed
482
+ "switch mode → bind project → send → create file → auto-verification passed".
483
+
484
+ ---
485
+
486
+ ## [0.1.4] — 2026-09-08
487
+
488
+ ### Added
489
+
490
+ - TraeWork GUI driver over CDP: `traework` moved from `unsupported` to `driver=gui` / `status=ready`.
491
+ - Capabilities: launch/reuse instance → new session → bind project folder (dropdown first, restricted computer-use
492
+ native dialog as fallback) → optional model selection → read-back-verified send → poll to completion →
493
+ auto-verify → repair-plan file + same-session rework on failure.
494
+ - Safety: reuse the user's instance by default, never kill a process tree, verify the command line before terminating;
495
+ computer-use is limited to TraeWork's folder picker.
496
+ - `AgentAdapter` gained an optional `run()` execution surface; the orchestrator branches on `adapter.run`
497
+ (CLI agents still use spawn).
498
+ - Profile gained `driver` (`spawn` / `gui`) and a `gui` section; `run_task` gained a `model` parameter.
499
+ - New `src/agents/traework/**` (CDP client, selector table, launcher, session/input/model/reply modules, restricted computer-use).
500
+ - On verification failure a repair-plan file `rework-<taskId>-r<N>.md` is generated (task dir + project `.tianshu-mcp`)
501
+ and its filename is referenced in the rework message.
502
+
503
+ ### Changed
504
+
505
+ - `docs/adapter-matrix.md` T1 conclusion corrected from `unsupported` to "integrated (driver=gui)".
506
+ - formatter now passes cancel-source fields (`abortSource`, …) through to `query_task`'s meta block.
507
+
508
+ ### Fixed
509
+
510
+ - Unified timeout terminal state: normal timeouts now also land `failed(timeout)` plus exactly one `timeout_killed` event, in fixed order.
511
+ - Stabilized the `shutdown` test polling.
512
+
513
+ ### Testing
514
+
515
+ - Total tests **72 → 153** (new TraeWork unit/integration cases).
516
+ - Real-machine end-to-end: `run_task(agentId=traework, model=GLM-5.3, autoVerify=true)` drove TraeWork to create a file and passed acceptance.
517
+
518
+ ---
519
+
520
+ ## [0.1.3] — 2026-09-08
521
+
522
+ ### Fixed
523
+
524
+ - **S1** No-reason cancel was mis-recorded as `interrupted`: added independent `cancelRequestedAt` / `abortSource` fields;
525
+ cancel intent no longer depends on the optional `reason` (5 regression tests).
526
+ - **S2** Unified timeout terminal state (shared with 0.1.4).
527
+ - **S3** Tracked pre-dirty net-diff attribution: pre-existing dirty files are excluded by content hash when unchanged;
528
+ unchanged staged/unstaged files are no longer reported as agent changes (4 regressions).
529
+ - **S4** `verify_task(taskId)` persists real-task metadata (`reportRound` / `verificationSource` /
530
+ `latestVerificationVerdict`, keeping `agentId`); single-source MCP version (`sync-version` injection).
531
+ - **S5** `projects.json` official Zod schema + last-known-good for `config`/`profiles`/`projects` + content-sha256
532
+ hot-reload invalidation (fixed corrupt JSON being treated as missing and reset).
533
+
534
+ ### Changed
535
+
536
+ - **S6** CI/Release `npm ci` retry corrected (stop on success / 3 attempts / attempt counter);
537
+ Vitest v3 upgrade (0 audit vulnerabilities); plain-text status markers (emoji scan test).
538
+
539
+ ### Testing
540
+
541
+ - Total tests **53 → 72**.
542
+
543
+ ---
544
+
545
+ ## [0.1.2] — 2026-09-08
546
+
547
+ ### Changed
548
+
549
+ - Build no longer ships source maps (no `.map`, tarball ≈ 69.9 KB).
550
+
551
+ ### Testing
552
+
553
+ - Total tests **53**.
554
+
555
+ ---
556
+
557
+ ## [0.1.1] — 2026-09-07
558
+
559
+ ### Added
560
+
561
+ - **Release after the R1–R5 fixes**:
562
+ - **R1** Cancel/interrupt state persistence (`cancel_requested → cancelled`, `cancelReason`/`finishedAt`/`errorType`
563
+ persisted, restart-recoverable, idempotent, bounded shutdown).
564
+ - **R2** Call-level `taskTimeoutMs` precedence fix + cross-platform process-tree termination
565
+ (POSIX process-group SIGTERM→SIGKILL, Windows `taskkill /T /F`).
566
+ - **R3** Git baseline participates in diff (boundary at `baseline.head`; agent commits do not lose changes;
567
+ dirty-worktree hash attribution).
568
+ - **R4** Verification tool parameters and report-round semantics (`round=0` valid, manual verify does not overwrite
569
+ reports, `extraChecks` append + `checksMode=replace`, `optional` does not affect verdict, `baselineRef` validated).
570
+ - **R5** Removed hardcoded agent paths (`{LOCALAPPDATA}` placeholders + platform-standard candidates);
571
+ mtime hot reload for `config`/`profile`/`projects`.
572
+ - **R6** Cross-platform CI matrix (Windows/macOS/Linux × Node 20/22) and Release version consistency
573
+ (tag/input = `package.json` = tarball), plus tarball content checks.
574
+ - **R7** npm published `tianshu-mcp@0.1.1` + `npx -y` raise with 8 tools connected.
575
+ - **R8** Bilingual docs synced (including 4 English topic docs).
576
+
577
+ ---
578
+
579
+ ## [0.1.0] — 2026-09-07
580
+
581
+ ### Added
582
+
583
+ - First usable release: **M1 core engine + stub-agent end-to-end**.
584
+ - 8 MCP tools: `run_task` / `query_task` / `list_tasks` / `get_task_report` / `cancel_task` / `verify_task` /
585
+ `rework_task` / `get_profiles`.
586
+ - `TaskManager` state machine / per-project serial queue / global concurrency gate / cancel (kill tree) / event-stream persistence.
587
+ - Acceptance engine: git baseline & diff, default check-set derivation, command runner, code analysis,
588
+ `report.md` / `report.json`.
589
+ - fix-loop auto rework + `needs_attention`; skill self-install.
590
+ - Stub-agent 3 playbooks (good / fix-on-first / never) integration tests + protocol tests — **53/53 green**.
591
+
592
+ ---
593
+
594
+ [Unreleased]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.4.0...HEAD
595
+ [0.4.0]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.4...v0.4.0
596
+ [0.3.4]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.3...v0.3.4
518
597
  [0.3.3]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.2...v0.3.3
519
- [0.3.2]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.1...v0.3.2
520
- [0.3.1]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.0...v0.3.1
521
- [0.3.0]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.2.0...v0.3.0
522
- [0.2.0]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.10...v0.2.0
523
- [0.1.10]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.9...v0.1.10
524
- [0.1.9]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.8...v0.1.9
525
- [0.1.8]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.7...v0.1.8
526
- [0.1.7]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.6...v0.1.7
527
- [0.1.6]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.5...v0.1.6
528
- [0.1.5]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.4...v0.1.5
529
- [0.1.4]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.3...v0.1.4
530
- [0.1.3]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.2...v0.1.3
531
- [0.1.2]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.1...v0.1.2
532
- [0.1.1]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.0...v0.1.1
533
- [0.1.0]: https://github.com/lanlan0811/tianshu-mcp/releases/tag/v0.1.0
598
+ [0.3.2]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.1...v0.3.2
599
+ [0.3.1]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.3.0...v0.3.1
600
+ [0.3.0]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.2.0...v0.3.0
601
+ [0.2.0]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.10...v0.2.0
602
+ [0.1.10]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.9...v0.1.10
603
+ [0.1.9]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.8...v0.1.9
604
+ [0.1.8]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.7...v0.1.8
605
+ [0.1.7]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.6...v0.1.7
606
+ [0.1.6]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.5...v0.1.6
607
+ [0.1.5]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.4...v0.1.5
608
+ [0.1.4]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.3...v0.1.4
609
+ [0.1.3]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.2...v0.1.3
610
+ [0.1.2]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.1...v0.1.2
611
+ [0.1.1]: https://github.com/lanlan0811/tianshu-mcp/compare/v0.1.0...v0.1.1
612
+ [0.1.0]: https://github.com/lanlan0811/tianshu-mcp/releases/tag/v0.1.0