@tea-agent/loop-agent 0.13.0 → 0.14.0

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 (270) hide show
  1. package/AGENTS.md +157 -157
  2. package/CHANGELOG.md +73 -301
  3. package/README.md +338 -334
  4. package/bin/agent-worker.js +22 -22
  5. package/bin/loop-agent.js +21 -21
  6. package/dist/commands/cursor-prompt.js +6 -6
  7. package/dist/commands/init.js +505 -505
  8. package/dist/commands/loop-benchmark.js +11 -11
  9. package/dist/commands/pi-reuse-benchmark.js +16 -16
  10. package/dist/executors/pi-event-serializer.js +33 -11
  11. package/dist/sidecars/cursor-prompt/executor.js +1 -1
  12. package/dist/task/runtime.js +27 -27
  13. package/dist/worker/observe/spec-evidence.js +19 -10
  14. package/dist/worker/observe/static/api.js +46 -46
  15. package/dist/worker/observe/static/app.js +151 -150
  16. package/dist/worker/observe/static/constants.js +156 -148
  17. package/dist/worker/observe/static/copy.js +67 -67
  18. package/dist/worker/observe/static/dag-helpers.js +201 -172
  19. package/dist/worker/observe/static/dag-layout.d.ts +31 -31
  20. package/dist/worker/observe/static/dag-layout.js +83 -83
  21. package/dist/worker/observe/static/dag-model.js +72 -72
  22. package/dist/worker/observe/static/dom.js +122 -122
  23. package/dist/worker/observe/static/format-pool.d.ts +71 -0
  24. package/dist/worker/observe/static/format-pool.js +134 -67
  25. package/dist/worker/observe/static/format.js +317 -292
  26. package/dist/worker/observe/static/index.html +350 -308
  27. package/dist/worker/observe/static/kpi.js +100 -94
  28. package/dist/worker/observe/static/markdown-render.js +124 -0
  29. package/dist/worker/observe/static/relations.js +133 -133
  30. package/dist/worker/observe/static/router.js +93 -93
  31. package/dist/worker/observe/static/run-processing.js +148 -148
  32. package/dist/worker/observe/static/shell-chrome.js +74 -68
  33. package/dist/worker/observe/static/state.js +273 -267
  34. package/dist/worker/observe/static/styles.css +2504 -1902
  35. package/dist/worker/observe/static/views/batch.js +227 -227
  36. package/dist/worker/observe/static/views/dag-graph.js +172 -172
  37. package/dist/worker/observe/static/views/dag-inspector.js +530 -627
  38. package/dist/worker/observe/static/views/dag.js +371 -371
  39. package/dist/worker/observe/static/views/dashboard.js +86 -100
  40. package/dist/worker/observe/static/views/failures.js +143 -143
  41. package/dist/worker/observe/static/views/feature.js +492 -492
  42. package/dist/worker/observe/static/views/pool.js +708 -350
  43. package/dist/worker/observe/static/views/run.js +453 -453
  44. package/dist/worker/observe/static/views/session-timeline.js +771 -219
  45. package/dist/worker/observe/static/views/shell.js +7 -7
  46. package/dist/worker/observe/static/views/task.js +314 -314
  47. package/dist/worker/observe/static/views/timeline.js +163 -163
  48. package/dist/workflows/dag/canvas-observer.js +275 -275
  49. package/docs/README.md +105 -104
  50. package/docs/agent-dag-recovery-playbook.md +195 -195
  51. package/docs/agent-dag-runner.md +67 -67
  52. package/docs/architecture/README.md +26 -26
  53. package/docs/architecture/dag-execution.md +140 -140
  54. package/docs/architecture/evolution.md +54 -54
  55. package/docs/architecture/facts-and-state.md +71 -71
  56. package/docs/architecture/runtime-boundaries.md +191 -191
  57. package/docs/architecture/system-overview.md +93 -93
  58. package/docs/architecture/worker-and-feature.md +85 -85
  59. package/docs/cursor-prompt-sidecar.md +36 -36
  60. package/docs/decisions/README.md +18 -18
  61. package/docs/design/README.md +167 -167
  62. package/docs/development-principles.md +73 -73
  63. package/docs/exec-plans/README.md +6 -6
  64. package/docs/exec-plans/active/README.md +2 -1
  65. package/docs/exec-plans/completed/README.md +105 -104
  66. package/docs/feature-workflow.md +414 -414
  67. package/docs/harness-methodology-debugging.md +153 -153
  68. package/docs/harness-methodology-tdd.md +130 -130
  69. package/docs/harness-methodology-verification.md +27 -27
  70. package/docs/init-surface.manifest.json +307 -307
  71. package/docs/loop-agent-harness.md +142 -142
  72. package/docs/production-readiness.md +96 -96
  73. package/docs/progress/README.md +59 -58
  74. package/docs/reports/README.md +123 -119
  75. package/docs/skills/README.md +7 -7
  76. package/docs/skills/vetted-skill-registry.md +29 -29
  77. package/docs/templates/adr.md +60 -60
  78. package/docs/templates/agent-dag-authority-surface-audit.prompt.md +94 -94
  79. package/docs/templates/agent-dag-decision-envelope.schema.json +213 -213
  80. package/docs/templates/agent-dag-decision-gate-dogfood-report.md +117 -117
  81. package/docs/templates/agent-dag-decision-gate.prompt.md +246 -246
  82. package/docs/templates/agent-dag-process-supervisor.prompt.md +98 -98
  83. package/docs/templates/agent-dag-report.schema.json +473 -473
  84. package/docs/templates/agent-dag-review-verdict.prompt.md +68 -68
  85. package/docs/templates/agent-dag.base.json +190 -190
  86. package/docs/templates/agent-dag.final-verification.json +185 -185
  87. package/docs/templates/agent-dag.schema.json +411 -411
  88. package/docs/templates/agent-dag.supervised-implementation.json +620 -620
  89. package/docs/templates/backend-test-analysis.schema.json +44 -44
  90. package/docs/templates/backend-test-case-manifest.schema.json +190 -190
  91. package/docs/templates/backend-test-dag.classify.prompt.md +75 -75
  92. package/docs/templates/backend-test-dag.generate-pytest.prompt.md +204 -204
  93. package/docs/templates/backend-test-dag.json +559 -559
  94. package/docs/templates/backend-test-dag.retrospect.prompt.md +139 -139
  95. package/docs/templates/backend-test-dag.review-cases.prompt.md +83 -83
  96. package/docs/templates/backend-test-execution.schema.json +133 -133
  97. package/docs/templates/backend-test-result.schema.json +99 -99
  98. package/docs/templates/exec-plan.md +64 -64
  99. package/docs/templates/feature-spec.md +53 -53
  100. package/docs/templates/frontend-design-contract.md +42 -42
  101. package/docs/templates/frontend-eval/fixtures/failures/01-type-build-error.md +17 -17
  102. package/docs/templates/frontend-eval/fixtures/failures/02-unit-component-test-fail.md +16 -16
  103. package/docs/templates/frontend-eval/fixtures/failures/03-fixture-schema-drift.md +16 -16
  104. package/docs/templates/frontend-eval/fixtures/failures/04-missing-loading-empty-error-state.md +16 -16
  105. package/docs/templates/frontend-eval/fixtures/failures/05-forbidden-write-writeset-expansion.md +16 -16
  106. package/docs/templates/frontend-eval/fixtures/failures/06-unapproved-dependency-add.md +16 -16
  107. package/docs/templates/frontend-eval/fixtures/failures/07-mock-production-on.md +21 -21
  108. package/docs/templates/frontend-eval/fixtures/functional/01-simple-component-style.md +29 -29
  109. package/docs/templates/frontend-eval/fixtures/functional/02-form-validation.md +28 -28
  110. package/docs/templates/frontend-eval/fixtures/functional/03-list-detail-page.md +28 -28
  111. package/docs/templates/frontend-eval/fixtures/functional/04-api-mock.md +29 -29
  112. package/docs/templates/frontend-eval/fixtures/functional/05-permission-auth-gated-ui.md +27 -27
  113. package/docs/templates/frontend-eval/fixtures/functional/06-ssr-server-client-boundary.md +28 -28
  114. package/docs/templates/frontend-eval/fixtures/functional/07-shared-public-component-api.md +28 -28
  115. package/docs/templates/frontend-eval/fixtures/functional/08-pure-local-no-remote.md +27 -27
  116. package/docs/templates/frontend-eval/metrics.md +138 -138
  117. package/docs/templates/frontend-eval/smoke-targets.md +53 -53
  118. package/docs/templates/frontend-implementation-contract.schema.json +27 -27
  119. package/docs/templates/frontend-task-constraints.md +35 -35
  120. package/docs/templates/frontend-task-requirement.md +70 -70
  121. package/docs/templates/frontend-test-dag.generate-cases.prompt.md +5 -5
  122. package/docs/templates/frontend-test-dag.json +23 -23
  123. package/docs/templates/frontend-test-dag.retrieve-context.prompt.md +3 -3
  124. package/docs/templates/frontend-test-dag.retrospect.prompt.md +3 -3
  125. package/docs/templates/frontend-test-dag.review-cases.prompt.md +3 -3
  126. package/docs/templates/frontend-test-dag.review-execution.prompt.md +3 -3
  127. package/docs/templates/harness.schema.json +221 -221
  128. package/docs/templates/hybrid-dag.json +188 -188
  129. package/docs/templates/init-evolution-review.md +35 -35
  130. package/docs/templates/interactive-ui-round2-experiment.md +66 -66
  131. package/docs/templates/knowledge-graph-bootstrap-dag.json +118 -118
  132. package/docs/templates/knowledge-sync-dag.json +178 -178
  133. package/docs/templates/knowledge-sync-draft.schema.json +71 -71
  134. package/docs/templates/product-line/AGENTS.md +8 -8
  135. package/docs/templates/product-line/README.md +9 -9
  136. package/docs/templates/product-line/acceptance.yaml +14 -14
  137. package/docs/templates/product-line/closeout.yaml +9 -9
  138. package/docs/templates/product-line/design.md +13 -13
  139. package/docs/templates/product-line/links.md +10 -10
  140. package/docs/templates/product-line/requirement.md +17 -17
  141. package/docs/templates/product-line/task-graph.yaml +15 -15
  142. package/docs/templates/product-line/task.yaml +64 -64
  143. package/docs/templates/product-line/test-plan.md +7 -7
  144. package/docs/templates/production-readiness-checklist.md +57 -57
  145. package/docs/templates/progress-log.md +17 -17
  146. package/docs/templates/project-start-checklist.md +9 -9
  147. package/docs/templates/qa-report.md +48 -48
  148. package/docs/templates/sprint-contract.md +29 -29
  149. package/docs/templates/worker-dogfood-evidence.md +80 -80
  150. package/docs/templates/worker-dogfood-setup.md +68 -68
  151. package/docs/verification-matrix.md +70 -70
  152. package/examples/decision-gate-agent-dag.json +173 -173
  153. package/examples/example-dag.json +46 -46
  154. package/examples/hybrid-loop-agent-dag.json +188 -188
  155. package/harness.json +66 -66
  156. package/package.json +88 -52
  157. package/scripts/check-product-line-docs.sh +29 -29
  158. package/scripts/check-task-pool-root.sh +32 -32
  159. package/scripts/kb-bootstrap-init-skeleton.sh +240 -240
  160. package/scripts/kb-graph-incremental-prepare.mjs +386 -386
  161. package/scripts/kb-graph-incremental-prepare.sh +5 -5
  162. package/scripts/kb-graph-materialize.mjs +105 -105
  163. package/scripts/kb-graph-materialize.sh +4 -4
  164. package/scripts/kb-graph-promote.mjs +164 -164
  165. package/scripts/kb-graph-promote.sh +4 -4
  166. package/scripts/kb-query.mjs +554 -554
  167. package/scripts/kb-query.sh +5 -5
  168. package/skills/agent-worker/SKILL.md +39 -39
  169. package/skills/agent-worker/references/agent-worker-operator.md +60 -60
  170. package/skills/ai-engineering-context/SKILL.md +48 -48
  171. package/skills/analyze-product-dependencies/SKILL.md +67 -67
  172. package/skills/analyze-product-dependencies/agents/openai.yaml +4 -4
  173. package/skills/analyze-product-dependencies/references/api-documentation-schema.md +30 -30
  174. package/skills/analyze-product-dependencies/references/dependency-analysis-schema.md +28 -28
  175. package/skills/analyze-product-dependencies/references/example.md +76 -76
  176. package/skills/analyze-product-dependencies/references/forward-test-cases.md +35 -35
  177. package/skills/analyze-product-dependencies/references/input-contract.md +11 -11
  178. package/skills/analyze-product-dependencies/references/scouting-rules.md +61 -61
  179. package/skills/analyze-product-dependencies/scripts/test-validators.mjs +267 -267
  180. package/skills/analyze-product-dependencies/scripts/validate-api-documentation.mjs +101 -101
  181. package/skills/analyze-product-dependencies/scripts/validate-dependency-analysis.mjs +142 -142
  182. package/skills/analyze-product-dependencies/scripts/validate-product-requirement-input.mjs +76 -76
  183. package/skills/analyze-product-dependencies/scripts/validation-helpers.mjs +146 -146
  184. package/skills/analyze-product-requirements/SKILL.md +90 -90
  185. package/skills/analyze-product-requirements/agents/openai.yaml +4 -4
  186. package/skills/analyze-product-requirements/references/acceptance-criteria.md +91 -91
  187. package/skills/analyze-product-requirements/references/clarification-and-knowledge.md +56 -56
  188. package/skills/analyze-product-requirements/references/example.md +86 -86
  189. package/skills/analyze-product-requirements/references/forward-test-cases.md +66 -66
  190. package/skills/analyze-product-requirements/references/product-analysis-schema.md +32 -32
  191. package/skills/analyze-product-requirements/references/product-requirement-schema.md +33 -33
  192. package/skills/analyze-product-requirements/references/requirement-clarification-schema.md +35 -35
  193. package/skills/analyze-product-requirements/scripts/test-validators.mjs +193 -193
  194. package/skills/analyze-product-requirements/scripts/validate-product-analysis.mjs +69 -69
  195. package/skills/analyze-product-requirements/scripts/validate-product-requirement.mjs +97 -97
  196. package/skills/analyze-product-requirements/scripts/validate-requirement-clarification.mjs +98 -98
  197. package/skills/analyze-product-requirements/scripts/validation-helpers.mjs +156 -156
  198. package/skills/browser-tools/SKILL.md +196 -196
  199. package/skills/browser-tools/browser-content.js +103 -103
  200. package/skills/browser-tools/browser-cookies.js +35 -35
  201. package/skills/browser-tools/browser-eval.js +53 -53
  202. package/skills/browser-tools/browser-hn-scraper.js +108 -108
  203. package/skills/browser-tools/browser-nav.js +44 -44
  204. package/skills/browser-tools/browser-pick.js +162 -162
  205. package/skills/browser-tools/browser-screenshot.js +34 -34
  206. package/skills/browser-tools/browser-start.js +86 -86
  207. package/skills/browser-tools/package-lock.json +2556 -2556
  208. package/skills/browser-tools/package.json +19 -19
  209. package/skills/code-review-core/SKILL.md +20 -20
  210. package/skills/codebase-scout/SKILL.md +19 -19
  211. package/skills/frontend-design-review/SKILL.md +66 -66
  212. package/skills/frontend-design-review/references/review-checklist.md +58 -58
  213. package/skills/frontend-implementation/SKILL.md +49 -49
  214. package/skills/frontend-implementation/references/code-standards.md +32 -32
  215. package/skills/frontend-implementation/references/design-spec.md +46 -46
  216. package/skills/frontend-implementation/references/node-contracts.md +27 -27
  217. package/skills/frontend-review/SKILL.md +59 -59
  218. package/skills/frontend-review/references/review-findings.md +47 -47
  219. package/skills/frontend-verification/SKILL.md +53 -53
  220. package/skills/frontend-verification/references/verification-checklist.md +68 -68
  221. package/skills/grill-me/SKILL.md +10 -10
  222. package/skills/grill-with-docs/SKILL.md +88 -88
  223. package/skills/grill-with-docs/adr-format.md +47 -47
  224. package/skills/grill-with-docs/context-format.md +60 -60
  225. package/skills/init-capability-evolution/SKILL.md +70 -70
  226. package/skills/loop-agent/SKILL.md +151 -151
  227. package/skills/loop-agent/references/README.md +67 -67
  228. package/skills/loop-agent/references/command-reference.md +527 -527
  229. package/skills/loop-agent/references/docs-converge.md +126 -126
  230. package/skills/loop-agent/references/harness-policy.md +263 -263
  231. package/skills/loop-agent/references/hybrid-dag.md +243 -243
  232. package/skills/loop-agent/references/learned/README.md +21 -21
  233. package/skills/loop-agent/references/long-running-loop.md +57 -57
  234. package/skills/loop-agent/references/model-routing.md +36 -36
  235. package/skills/loop-agent/references/multi-worktree.md +54 -54
  236. package/skills/loop-agent/references/one-shot-runs.md +85 -85
  237. package/skills/loop-agent/references/orchestrator-and-interventions.md +169 -169
  238. package/skills/loop-agent/references/pi-prompt.md +23 -23
  239. package/skills/loop-agent/references/pi-subagent-assisted-mode.md +84 -84
  240. package/skills/loop-agent/references/post-implementation-and-patterns.md +44 -44
  241. package/skills/loop-agent/references/task-workflow.md +89 -89
  242. package/skills/loop-agent/references/verification-and-failure-handling.md +141 -141
  243. package/skills/playwright-cli/SKILL.md +420 -420
  244. package/skills/playwright-cli/references/element-attributes.md +23 -23
  245. package/skills/playwright-cli/references/playwright-tests.md +39 -39
  246. package/skills/playwright-cli/references/request-mocking.md +87 -87
  247. package/skills/playwright-cli/references/running-code.md +241 -241
  248. package/skills/playwright-cli/references/session-management.md +225 -225
  249. package/skills/playwright-cli/references/storage-state.md +275 -275
  250. package/skills/playwright-cli/references/test-generation.md +433 -433
  251. package/skills/playwright-cli/references/tracing.md +139 -139
  252. package/skills/playwright-cli/references/video-recording.md +143 -143
  253. package/skills/playwright-cli-case-generator/SKILL.md +74 -74
  254. package/skills/requesting-code-review/SKILL.md +101 -101
  255. package/skills/requesting-code-review/code-reviewer.md +168 -168
  256. package/skills/systematic-debugging/CREATION-LOG.md +119 -119
  257. package/skills/systematic-debugging/SKILL.md +296 -296
  258. package/skills/systematic-debugging/condition-based-waiting-example.ts +158 -158
  259. package/skills/systematic-debugging/condition-based-waiting.md +115 -115
  260. package/skills/systematic-debugging/defense-in-depth.md +122 -122
  261. package/skills/systematic-debugging/find-polluter.sh +63 -63
  262. package/skills/systematic-debugging/root-cause-tracing.md +169 -169
  263. package/skills/systematic-debugging/test-academic.md +14 -14
  264. package/skills/systematic-debugging/test-pressure-1.md +58 -58
  265. package/skills/systematic-debugging/test-pressure-2.md +68 -68
  266. package/skills/systematic-debugging/test-pressure-3.md +69 -69
  267. package/skills/test-driven-development/SKILL.md +20 -20
  268. package/skills/using-git-worktrees/SKILL.md +215 -215
  269. package/skills/verification-before-completion/SKILL.md +154 -154
  270. package/skills/webapp-testing/SKILL.md +19 -19
@@ -1,122 +1,122 @@
1
- # Defense-in-Depth Validation
2
-
3
- ## Overview
4
-
5
- Bug 由 invalid data 引起时,在一处加 validation 感觉足够。但 single check 可被不同 code paths、refactoring 或 mocks 绕过。
6
-
7
- **Core principle:** 在 data 经过的 EVERY layer 验证。使 bug structurally impossible。
8
-
9
- ## Why Multiple Layers
10
-
11
- Single validation:"We fixed the bug"
12
- Multiple layers:"We made the bug impossible"
13
-
14
- 不同 layers 捕获不同 cases:
15
- - Entry validation 捕获 most bugs
16
- - Business logic 捕获 edge cases
17
- - Environment guards 防止 context-specific dangers
18
- - Debug logging 在其他 layers fail 时帮助 forensics
19
-
20
- ## The Four Layers
21
-
22
- ### Layer 1: Entry Point Validation
23
- **Purpose:** 在 API boundary 拒绝 obviously invalid input
24
-
25
- ```typescript
26
- function createProject(name: string, workingDirectory: string) {
27
- if (!workingDirectory || workingDirectory.trim() === '') {
28
- throw new Error('workingDirectory cannot be empty');
29
- }
30
- if (!existsSync(workingDirectory)) {
31
- throw new Error(`workingDirectory does not exist: ${workingDirectory}`);
32
- }
33
- if (!statSync(workingDirectory).isDirectory()) {
34
- throw new Error(`workingDirectory is not a directory: ${workingDirectory}`);
35
- }
36
- // ... proceed
37
- }
38
- ```
39
-
40
- ### Layer 2: Business Logic Validation
41
- **Purpose:** 确保 data 对此 operation 有意义
42
-
43
- ```typescript
44
- function initializeWorkspace(projectDir: string, sessionId: string) {
45
- if (!projectDir) {
46
- throw new Error('projectDir required for workspace initialization');
47
- }
48
- // ... proceed
49
- }
50
- ```
51
-
52
- ### Layer 3: Environment Guards
53
- **Purpose:** 在特定 contexts 阻止 dangerous operations
54
-
55
- ```typescript
56
- async function gitInit(directory: string) {
57
- // In tests, refuse git init outside temp directories
58
- if (process.env.NODE_ENV === 'test') {
59
- const normalized = normalize(resolve(directory));
60
- const tmpDir = normalize(resolve(tmpdir()));
61
-
62
- if (!normalized.startsWith(tmpDir)) {
63
- throw new Error(
64
- `Refusing git init outside temp dir during tests: ${directory}`
65
- );
66
- }
67
- }
68
- // ... proceed
69
- }
70
- ```
71
-
72
- ### Layer 4: Debug Instrumentation
73
- **Purpose:** 捕获 forensics context
74
-
75
- ```typescript
76
- async function gitInit(directory: string) {
77
- const stack = new Error().stack;
78
- logger.debug('About to git init', {
79
- directory,
80
- cwd: process.cwd(),
81
- stack,
82
- });
83
- // ... proceed
84
- }
85
- ```
86
-
87
- ## Applying the Pattern
88
-
89
- 找到 bug 时:
90
-
91
- 1. **Trace the data flow** — Bad value 从哪 originate?在哪使用?
92
- 2. **Map all checkpoints** — 列出 data 经过的 every point
93
- 3. **Add validation at each layer** — Entry、business、environment、debug
94
- 4. **Test each layer** — 尝试 bypass layer 1,verify layer 2 捕获
95
-
96
- ## Example from Session
97
-
98
- Bug:Empty `projectDir` 导致 `git init` 在 source code
99
-
100
- **Data flow:**
101
- 1. Test setup → empty string
102
- 2. `Project.create(name, '')`
103
- 3. `WorkspaceManager.createWorkspace('')`
104
- 4. `git init` 在 `process.cwd()` 运行
105
-
106
- **Four layers added:**
107
- - Layer 1: `Project.create()` validates not empty/exists/writable
108
- - Layer 2: `WorkspaceManager` validates projectDir not empty
109
- - Layer 3: `WorktreeManager` refuses git init outside tmpdir in tests
110
- - Layer 4: Stack trace logging before git init
111
-
112
- **Result:** All 1847 tests passed,bug impossible to reproduce
113
-
114
- ## Key Insight
115
-
116
- 四层都必要。Testing 中每层捕获 others 遗漏的 bugs:
117
- - 不同 code paths 绕过 entry validation
118
- - Mocks 绕过 business logic checks
119
- - 不同 platforms 的 edge cases 需要 environment guards
120
- - Debug logging 识别 structural misuse
121
-
122
- **Don't stop at one validation point.** 在 every layer 加 checks。
1
+ # Defense-in-Depth Validation
2
+
3
+ ## Overview
4
+
5
+ Bug 由 invalid data 引起时,在一处加 validation 感觉足够。但 single check 可被不同 code paths、refactoring 或 mocks 绕过。
6
+
7
+ **Core principle:** 在 data 经过的 EVERY layer 验证。使 bug structurally impossible。
8
+
9
+ ## Why Multiple Layers
10
+
11
+ Single validation:"We fixed the bug"
12
+ Multiple layers:"We made the bug impossible"
13
+
14
+ 不同 layers 捕获不同 cases:
15
+ - Entry validation 捕获 most bugs
16
+ - Business logic 捕获 edge cases
17
+ - Environment guards 防止 context-specific dangers
18
+ - Debug logging 在其他 layers fail 时帮助 forensics
19
+
20
+ ## The Four Layers
21
+
22
+ ### Layer 1: Entry Point Validation
23
+ **Purpose:** 在 API boundary 拒绝 obviously invalid input
24
+
25
+ ```typescript
26
+ function createProject(name: string, workingDirectory: string) {
27
+ if (!workingDirectory || workingDirectory.trim() === '') {
28
+ throw new Error('workingDirectory cannot be empty');
29
+ }
30
+ if (!existsSync(workingDirectory)) {
31
+ throw new Error(`workingDirectory does not exist: ${workingDirectory}`);
32
+ }
33
+ if (!statSync(workingDirectory).isDirectory()) {
34
+ throw new Error(`workingDirectory is not a directory: ${workingDirectory}`);
35
+ }
36
+ // ... proceed
37
+ }
38
+ ```
39
+
40
+ ### Layer 2: Business Logic Validation
41
+ **Purpose:** 确保 data 对此 operation 有意义
42
+
43
+ ```typescript
44
+ function initializeWorkspace(projectDir: string, sessionId: string) {
45
+ if (!projectDir) {
46
+ throw new Error('projectDir required for workspace initialization');
47
+ }
48
+ // ... proceed
49
+ }
50
+ ```
51
+
52
+ ### Layer 3: Environment Guards
53
+ **Purpose:** 在特定 contexts 阻止 dangerous operations
54
+
55
+ ```typescript
56
+ async function gitInit(directory: string) {
57
+ // In tests, refuse git init outside temp directories
58
+ if (process.env.NODE_ENV === 'test') {
59
+ const normalized = normalize(resolve(directory));
60
+ const tmpDir = normalize(resolve(tmpdir()));
61
+
62
+ if (!normalized.startsWith(tmpDir)) {
63
+ throw new Error(
64
+ `Refusing git init outside temp dir during tests: ${directory}`
65
+ );
66
+ }
67
+ }
68
+ // ... proceed
69
+ }
70
+ ```
71
+
72
+ ### Layer 4: Debug Instrumentation
73
+ **Purpose:** 捕获 forensics context
74
+
75
+ ```typescript
76
+ async function gitInit(directory: string) {
77
+ const stack = new Error().stack;
78
+ logger.debug('About to git init', {
79
+ directory,
80
+ cwd: process.cwd(),
81
+ stack,
82
+ });
83
+ // ... proceed
84
+ }
85
+ ```
86
+
87
+ ## Applying the Pattern
88
+
89
+ 找到 bug 时:
90
+
91
+ 1. **Trace the data flow** — Bad value 从哪 originate?在哪使用?
92
+ 2. **Map all checkpoints** — 列出 data 经过的 every point
93
+ 3. **Add validation at each layer** — Entry、business、environment、debug
94
+ 4. **Test each layer** — 尝试 bypass layer 1,verify layer 2 捕获
95
+
96
+ ## Example from Session
97
+
98
+ Bug:Empty `projectDir` 导致 `git init` 在 source code
99
+
100
+ **Data flow:**
101
+ 1. Test setup → empty string
102
+ 2. `Project.create(name, '')`
103
+ 3. `WorkspaceManager.createWorkspace('')`
104
+ 4. `git init` 在 `process.cwd()` 运行
105
+
106
+ **Four layers added:**
107
+ - Layer 1: `Project.create()` validates not empty/exists/writable
108
+ - Layer 2: `WorkspaceManager` validates projectDir not empty
109
+ - Layer 3: `WorktreeManager` refuses git init outside tmpdir in tests
110
+ - Layer 4: Stack trace logging before git init
111
+
112
+ **Result:** All 1847 tests passed,bug impossible to reproduce
113
+
114
+ ## Key Insight
115
+
116
+ 四层都必要。Testing 中每层捕获 others 遗漏的 bugs:
117
+ - 不同 code paths 绕过 entry validation
118
+ - Mocks 绕过 business logic checks
119
+ - 不同 platforms 的 edge cases 需要 environment guards
120
+ - Debug logging 识别 structural misuse
121
+
122
+ **Don't stop at one validation point.** 在 every layer 加 checks。
@@ -1,63 +1,63 @@
1
- #!/usr/bin/env bash
2
- # Bisection script to find which test creates unwanted files/state
3
- # Usage: ./find-polluter.sh <file_or_dir_to_check> <test_pattern>
4
- # Example: ./find-polluter.sh '.git' 'src/**/*.test.ts'
5
-
6
- set -e
7
-
8
- if [ $# -ne 2 ]; then
9
- echo "Usage: $0 <file_to_check> <test_pattern>"
10
- echo "Example: $0 '.git' 'src/**/*.test.ts'"
11
- exit 1
12
- fi
13
-
14
- POLLUTION_CHECK="$1"
15
- TEST_PATTERN="$2"
16
-
17
- echo "🔍 Searching for test that creates: $POLLUTION_CHECK"
18
- echo "Test pattern: $TEST_PATTERN"
19
- echo ""
20
-
21
- # Get list of test files
22
- TEST_FILES=$(find . -path "$TEST_PATTERN" | sort)
23
- TOTAL=$(echo "$TEST_FILES" | wc -l | tr -d ' ')
24
-
25
- echo "Found $TOTAL test files"
26
- echo ""
27
-
28
- COUNT=0
29
- for TEST_FILE in $TEST_FILES; do
30
- COUNT=$((COUNT + 1))
31
-
32
- # Skip if pollution already exists
33
- if [ -e "$POLLUTION_CHECK" ]; then
34
- echo "⚠️ Pollution already exists before test $COUNT/$TOTAL"
35
- echo " Skipping: $TEST_FILE"
36
- continue
37
- fi
38
-
39
- echo "[$COUNT/$TOTAL] Testing: $TEST_FILE"
40
-
41
- # Run the test
42
- npm test "$TEST_FILE" > /dev/null 2>&1 || true
43
-
44
- # Check if pollution appeared
45
- if [ -e "$POLLUTION_CHECK" ]; then
46
- echo ""
47
- echo "🎯 FOUND POLLUTER!"
48
- echo " Test: $TEST_FILE"
49
- echo " Created: $POLLUTION_CHECK"
50
- echo ""
51
- echo "Pollution details:"
52
- ls -la "$POLLUTION_CHECK"
53
- echo ""
54
- echo "To investigate:"
55
- echo " npm test $TEST_FILE # Run just this test"
56
- echo " cat $TEST_FILE # Review test code"
57
- exit 1
58
- fi
59
- done
60
-
61
- echo ""
62
- echo "✅ No polluter found - all tests clean!"
63
- exit 0
1
+ #!/usr/bin/env bash
2
+ # Bisection script to find which test creates unwanted files/state
3
+ # Usage: ./find-polluter.sh <file_or_dir_to_check> <test_pattern>
4
+ # Example: ./find-polluter.sh '.git' 'src/**/*.test.ts'
5
+
6
+ set -e
7
+
8
+ if [ $# -ne 2 ]; then
9
+ echo "Usage: $0 <file_to_check> <test_pattern>"
10
+ echo "Example: $0 '.git' 'src/**/*.test.ts'"
11
+ exit 1
12
+ fi
13
+
14
+ POLLUTION_CHECK="$1"
15
+ TEST_PATTERN="$2"
16
+
17
+ echo "🔍 Searching for test that creates: $POLLUTION_CHECK"
18
+ echo "Test pattern: $TEST_PATTERN"
19
+ echo ""
20
+
21
+ # Get list of test files
22
+ TEST_FILES=$(find . -path "$TEST_PATTERN" | sort)
23
+ TOTAL=$(echo "$TEST_FILES" | wc -l | tr -d ' ')
24
+
25
+ echo "Found $TOTAL test files"
26
+ echo ""
27
+
28
+ COUNT=0
29
+ for TEST_FILE in $TEST_FILES; do
30
+ COUNT=$((COUNT + 1))
31
+
32
+ # Skip if pollution already exists
33
+ if [ -e "$POLLUTION_CHECK" ]; then
34
+ echo "⚠️ Pollution already exists before test $COUNT/$TOTAL"
35
+ echo " Skipping: $TEST_FILE"
36
+ continue
37
+ fi
38
+
39
+ echo "[$COUNT/$TOTAL] Testing: $TEST_FILE"
40
+
41
+ # Run the test
42
+ npm test "$TEST_FILE" > /dev/null 2>&1 || true
43
+
44
+ # Check if pollution appeared
45
+ if [ -e "$POLLUTION_CHECK" ]; then
46
+ echo ""
47
+ echo "🎯 FOUND POLLUTER!"
48
+ echo " Test: $TEST_FILE"
49
+ echo " Created: $POLLUTION_CHECK"
50
+ echo ""
51
+ echo "Pollution details:"
52
+ ls -la "$POLLUTION_CHECK"
53
+ echo ""
54
+ echo "To investigate:"
55
+ echo " npm test $TEST_FILE # Run just this test"
56
+ echo " cat $TEST_FILE # Review test code"
57
+ exit 1
58
+ fi
59
+ done
60
+
61
+ echo ""
62
+ echo "✅ No polluter found - all tests clean!"
63
+ exit 0