principles-disciple 1.72.0 → 1.73.0

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 (309) hide show
  1. package/openclaw.plugin.json +10 -5
  2. package/package.json +17 -19
  3. package/scripts/acceptance-test.mjs +16 -73
  4. package/scripts/sync-plugin.mjs +382 -77
  5. package/src/commands/archive-impl.ts +2 -1
  6. package/src/commands/capabilities.ts +2 -2
  7. package/src/commands/context.ts +2 -2
  8. package/src/commands/disable-impl.ts +2 -1
  9. package/src/commands/evolution-status.ts +16 -16
  10. package/src/commands/export.ts +12 -67
  11. package/src/commands/pain.ts +91 -1
  12. package/src/commands/principle-rollback.ts +2 -1
  13. package/src/commands/promote-impl.ts +7 -43
  14. package/src/commands/rollback-impl.ts +2 -1
  15. package/src/commands/rollback.ts +2 -1
  16. package/src/commands/samples.ts +2 -1
  17. package/src/commands/thinking-os.ts +2 -1
  18. package/src/config/errors.ts +18 -2
  19. package/src/constants/diagnostician.ts +2 -2
  20. package/src/constants/tools.ts +2 -1
  21. package/src/core/__tests__/focus-history.test.ts +210 -0
  22. package/src/core/config.ts +1 -1
  23. package/src/core/confirm-first-gate.ts +255 -0
  24. package/src/core/correction-cue-learner.ts +2 -136
  25. package/src/core/correction-types.ts +16 -88
  26. package/src/core/dictionary.ts +19 -20
  27. package/src/core/empathy-keyword-matcher.ts +17 -289
  28. package/src/core/empathy-types.ts +18 -229
  29. package/src/core/event-log.ts +38 -132
  30. package/src/core/evolution-reducer.ts +21 -2
  31. package/src/core/evolution-types.ts +76 -464
  32. package/src/core/file-store.ts +80 -0
  33. package/src/core/focus-history.ts +228 -955
  34. package/src/core/local-worker-routing.ts +34 -314
  35. package/src/core/merge-gate-audit.ts +0 -195
  36. package/src/core/pain-diagnostic-gate.ts +154 -0
  37. package/src/core/pain-signal.ts +21 -138
  38. package/src/core/pain.ts +15 -88
  39. package/src/core/pd-task-reconciler.ts +26 -115
  40. package/src/core/pd-task-service.ts +9 -9
  41. package/src/core/pd-task-types.ts +23 -127
  42. package/src/core/principle-compiler/__tests__/compiler-replay-gate.test.ts +174 -0
  43. package/src/core/principle-compiler/code-validator.ts +15 -42
  44. package/src/core/principle-compiler/compiler.ts +100 -15
  45. package/src/core/principle-compiler/index.ts +5 -2
  46. package/src/core/principle-compiler/template-generator.ts +4 -104
  47. package/src/core/principle-injection.ts +10 -202
  48. package/src/core/principle-internalization/filesystem-lifecycle-datasource.ts +42 -0
  49. package/src/core/principle-internalization/lifecycle-read-model.ts +39 -242
  50. package/src/core/principle-internalization/principle-lifecycle-service.ts +12 -10
  51. package/src/core/principle-tree-ledger-adapter.ts +145 -0
  52. package/src/core/principle-tree-ledger.ts +8 -6
  53. package/src/core/reflection/reflection-context.ts +14 -109
  54. package/src/core/replay-engine.ts +8 -500
  55. package/src/core/rule-host-helpers.ts +5 -35
  56. package/src/core/rule-host-types.ts +10 -82
  57. package/src/core/rule-host.ts +6 -63
  58. package/src/core/runtime-v2-prompt-activation-reader.ts +231 -0
  59. package/src/core/session-tracker.ts +87 -101
  60. package/src/core/shadow-observation-registry.ts +19 -48
  61. package/src/core/trajectory.ts +3 -1
  62. package/src/core/workflow-funnel-loader.ts +62 -68
  63. package/src/core/workspace-context.ts +46 -0
  64. package/src/core/workspace-dir-service.ts +1 -1
  65. package/src/core/workspace-dir-validation.ts +18 -9
  66. package/src/hooks/AGENTS.md +1 -1
  67. package/src/hooks/gate-block-helper.ts +46 -44
  68. package/src/hooks/gate.ts +207 -7
  69. package/src/hooks/lifecycle.ts +30 -32
  70. package/src/hooks/llm.ts +60 -32
  71. package/src/hooks/pain.ts +297 -103
  72. package/src/hooks/prompt.ts +459 -439
  73. package/src/hooks/subagent.ts +2 -29
  74. package/src/i18n/commands.ts +2 -10
  75. package/src/index.ts +95 -85
  76. package/src/openclaw-sdk.ts +311 -0
  77. package/src/service/central-database.ts +8 -4
  78. package/src/service/evolution-queue-migration.ts +2 -1
  79. package/src/service/evolution-worker.ts +163 -1786
  80. package/src/service/internalization-trigger-adapter.ts +302 -0
  81. package/src/service/keyword-optimization-service.ts +4 -4
  82. package/src/service/monitoring-query-service.ts +1 -215
  83. package/src/service/queue-io.ts +60 -331
  84. package/src/service/runtime-summary-service.ts +59 -16
  85. package/src/service/subagent-workflow/index.ts +0 -41
  86. package/src/service/subagent-workflow/types.ts +9 -120
  87. package/src/service/subagent-workflow/workflow-store.ts +2 -119
  88. package/src/service/workflow-watchdog.ts +0 -43
  89. package/src/types/event-payload.ts +16 -74
  90. package/src/types/event-types.ts +39 -547
  91. package/src/types/hygiene-types.ts +7 -30
  92. package/src/types/principle-tree-schema.ts +20 -222
  93. package/src/types/queue.ts +15 -70
  94. package/src/types/runtime-summary.ts +5 -49
  95. package/src/utils/io.ts +10 -0
  96. package/src/utils/retry.ts +1 -1
  97. package/src/utils/shadow-fingerprint.ts +2 -2
  98. package/src/utils/workspace-resolver.ts +50 -0
  99. package/templates/langs/en/core/AGENTS.md +2 -2
  100. package/templates/langs/en/core/BOOT.md +1 -1
  101. package/templates/langs/en/core/HEARTBEAT.md +2 -2
  102. package/templates/langs/en/skills/ai-sprint-orchestration/references/agent-registry.json +1 -72
  103. package/templates/langs/en/skills/ai-sprint-orchestration/references/specs/bugfix-complex-template.json +6 -6
  104. package/templates/langs/en/skills/ai-sprint-orchestration/references/specs/feature-complex-template.json +6 -6
  105. package/templates/langs/en/skills/ai-sprint-orchestration/references/specs/workflow-validation-minimal-verify.json +2 -12
  106. package/templates/langs/en/skills/ai-sprint-orchestration/references/specs/workflow-validation-minimal.json +2 -12
  107. package/templates/langs/en/skills/ai-sprint-orchestration/runtime/.gitignore +2 -2
  108. package/templates/langs/en/skills/ai-sprint-orchestration/scripts/run.mjs +51 -15
  109. package/templates/langs/en/skills/evolve-task/SKILL.md +1 -1
  110. package/templates/langs/en/skills/pd-cli-operator/SKILL.md +67 -0
  111. package/templates/langs/en/skills/pd-diagnostician/SKILL.md +1 -1
  112. package/templates/langs/en/skills/pd-mentor/SKILL.md +1 -1
  113. package/templates/langs/en/skills/pd-pain-signal/SKILL.md +17 -39
  114. package/templates/langs/en/skills/pd-runtime-v2/SKILL.md +61 -0
  115. package/templates/langs/zh/core/AGENTS.md +2 -2
  116. package/templates/langs/zh/core/BOOT.md +1 -1
  117. package/templates/langs/zh/core/HEARTBEAT.md +2 -2
  118. package/templates/langs/zh/skills/ai-sprint-orchestration/references/agent-registry.json +1 -72
  119. package/templates/langs/zh/skills/ai-sprint-orchestration/references/specs/bugfix-complex-template.json +6 -6
  120. package/templates/langs/zh/skills/ai-sprint-orchestration/references/specs/feature-complex-template.json +6 -6
  121. package/templates/langs/zh/skills/ai-sprint-orchestration/references/specs/nocturnal-trinity-quality-enhancement.json +8 -8
  122. package/templates/langs/zh/skills/ai-sprint-orchestration/references/specs/workflow-validation-minimal-verify.json +2 -12
  123. package/templates/langs/zh/skills/ai-sprint-orchestration/references/specs/workflow-validation-minimal.json +2 -12
  124. package/templates/langs/zh/skills/ai-sprint-orchestration/runtime/.gitignore +2 -2
  125. package/templates/langs/zh/skills/ai-sprint-orchestration/scripts/run.mjs +51 -15
  126. package/templates/langs/zh/skills/ai-sprint-orchestration/test/run.test.mjs +21 -5
  127. package/templates/langs/zh/skills/evolve-task/SKILL.md +2 -2
  128. package/templates/langs/zh/skills/pd-cli-operator/SKILL.md +67 -0
  129. package/templates/langs/zh/skills/pd-diagnostician/SKILL.md +1 -1
  130. package/templates/langs/zh/skills/pd-mentor/SKILL.md +1 -1
  131. package/templates/langs/zh/skills/pd-pain-signal/SKILL.md +17 -38
  132. package/templates/langs/zh/skills/pd-runtime-v2/SKILL.md +61 -0
  133. package/tests/build-artifacts.test.ts +1 -3
  134. package/tests/commands/evolution-status.test.ts +0 -118
  135. package/tests/core/bootstrap-rules.test.ts +1 -1
  136. package/tests/core/config.test.ts +1 -1
  137. package/tests/core/event-log.test.ts +35 -0
  138. package/tests/core/evolution-engine.test.ts +610 -0
  139. package/tests/core/file-store.test.ts +102 -0
  140. package/tests/core/focus-history.test.ts +203 -11
  141. package/tests/core/merge-gate-audit.test.ts +2 -169
  142. package/tests/core/model-deployment-registry.test.ts +7 -1
  143. package/tests/core/model-training-registry.test.ts +19 -0
  144. package/tests/core/observability.test.ts +0 -1
  145. package/tests/core/pain-diagnostic-gate.test.ts +498 -0
  146. package/tests/core/pain.test.ts +0 -1
  147. package/tests/core/principle-internalization/deprecated-readiness.test.ts +2 -2
  148. package/tests/core/principle-internalization/lifecycle-metrics.test.ts +2 -2
  149. package/tests/core/principle-internalization/{internalization-routing-policy.test.ts → lifecycle-routing-policy.test.ts} +6 -6
  150. package/tests/core/principle-internalization/lineage-source-retired.test.ts +56 -0
  151. package/tests/core/principle-internalization/principle-lifecycle-service.test.ts +1 -23
  152. package/tests/core/principle-tree-ledger-adapter.test.ts +253 -0
  153. package/tests/core/reflection-context.test.ts +0 -14
  154. package/tests/core/replay-engine.test.ts +127 -215
  155. package/tests/core/rule-host-helpers.test.ts +2 -2
  156. package/tests/core/rule-implementation-runtime.test.ts +0 -27
  157. package/tests/core/workflow-funnel-loader.test.ts +162 -0
  158. package/tests/core/workspace-dir-validation.test.ts +8 -1
  159. package/tests/core-anti-growth.test.ts +192 -0
  160. package/tests/hook-workspace-nextaction-contract.test.ts +42 -0
  161. package/tests/hooks/confirm-first-gate.test.ts +333 -0
  162. package/tests/hooks/gate-auto-correct-shadow.test.ts +310 -0
  163. package/tests/hooks/gate-auto-correct.test.ts +665 -0
  164. package/tests/hooks/gate-rule-host-pipeline.test.ts +2 -1
  165. package/tests/hooks/pain.test.ts +269 -12
  166. package/tests/hooks/prompt-characterization.test.ts +500 -0
  167. package/tests/hooks/prompt-size-guard.test.ts +32 -17
  168. package/tests/hooks/runtime-v2-prompt-activation.test.ts +869 -0
  169. package/tests/index.test.ts +94 -1
  170. package/tests/integration/auto-entry-gate.test.ts +248 -0
  171. package/tests/integration/internalization-trigger-guard.test.ts +69 -0
  172. package/tests/integration/m8-legacy-paths.test.ts +63 -0
  173. package/tests/integration/runtime-v2-pain-guard.test.ts +125 -0
  174. package/tests/plugin-config-resolution-cutover.test.ts +359 -0
  175. package/tests/runtime-v2-discovery-guard.test.ts +154 -0
  176. package/tests/service/central-database.test.ts +457 -0
  177. package/tests/service/evolution-worker.correction-observer.test.ts +173 -0
  178. package/tests/service/evolution-worker.timeout.test.ts +11 -129
  179. package/tests/service/internalization-trigger-adapter.test.ts +251 -0
  180. package/tests/service/monitoring-query-service.test.ts +1 -47
  181. package/tests/service/queue-io.test.ts +1 -62
  182. package/tests/service/runtime-summary-service.test.ts +3 -1
  183. package/tests/service/workflow-watchdog.test.ts +0 -91
  184. package/tests/utils/file-lock.test.ts +5 -3
  185. package/tests/utils/session-key.test.ts +52 -0
  186. package/tests/utils/subagent-probe.test.ts +48 -1
  187. package/vitest.config.ts +4 -11
  188. package/.planning/codebase/ARCHITECTURE.md +0 -157
  189. package/.planning/codebase/CONCERNS.md +0 -145
  190. package/.planning/codebase/CONVENTIONS.md +0 -148
  191. package/.planning/codebase/INTEGRATIONS.md +0 -81
  192. package/.planning/codebase/STACK.md +0 -87
  193. package/.planning/codebase/STRUCTURE.md +0 -193
  194. package/.planning/codebase/TESTING.md +0 -243
  195. package/.planning/phases/01-basic-visualization/01-GAP-CLOSURE-VERIFICATION.md +0 -113
  196. package/docs/COMMAND_REFERENCE.md +0 -76
  197. package/docs/COMMAND_REFERENCE_EN.md +0 -79
  198. package/scripts/build-web.mjs +0 -46
  199. package/scripts/diagnose-nocturnal.mjs +0 -537
  200. package/scripts/seed-nocturnal-scenarios.mjs +0 -384
  201. package/src/commands/nocturnal-review.ts +0 -322
  202. package/src/commands/nocturnal-rollout.ts +0 -790
  203. package/src/commands/nocturnal-train.ts +0 -986
  204. package/src/commands/pd-reflect.ts +0 -88
  205. package/src/core/adaptive-thresholds.ts +0 -478
  206. package/src/core/diagnostician-task-store.ts +0 -192
  207. package/src/core/nocturnal-arbiter.ts +0 -715
  208. package/src/core/nocturnal-artifact-lineage.ts +0 -116
  209. package/src/core/nocturnal-artificer.ts +0 -257
  210. package/src/core/nocturnal-candidate-scoring.ts +0 -530
  211. package/src/core/nocturnal-compliance.ts +0 -1146
  212. package/src/core/nocturnal-dataset.ts +0 -763
  213. package/src/core/nocturnal-executability.ts +0 -428
  214. package/src/core/nocturnal-export.ts +0 -499
  215. package/src/core/nocturnal-paths.ts +0 -240
  216. package/src/core/nocturnal-reasoning-deriver.ts +0 -343
  217. package/src/core/nocturnal-rule-implementation-validator.ts +0 -246
  218. package/src/core/nocturnal-snapshot-contract.ts +0 -99
  219. package/src/core/nocturnal-trajectory-extractor.ts +0 -512
  220. package/src/core/nocturnal-trinity-types.ts +0 -218
  221. package/src/core/nocturnal-trinity.ts +0 -2680
  222. package/src/core/principle-internalization/deprecated-readiness.ts +0 -93
  223. package/src/core/principle-internalization/internalization-routing-policy.ts +0 -208
  224. package/src/core/principle-internalization/lifecycle-metrics.ts +0 -152
  225. package/src/http/principles-console-route.ts +0 -709
  226. package/src/service/central-health-service.ts +0 -49
  227. package/src/service/central-overview-service.ts +0 -138
  228. package/src/service/control-ui-query-service.ts +0 -900
  229. package/src/service/cooldown-strategy.ts +0 -97
  230. package/src/service/evolution-pain-context.ts +0 -79
  231. package/src/service/evolution-query-service.ts +0 -407
  232. package/src/service/health-query-service.ts +0 -1038
  233. package/src/service/nocturnal-config.ts +0 -214
  234. package/src/service/nocturnal-runtime.ts +0 -734
  235. package/src/service/nocturnal-service.ts +0 -1605
  236. package/src/service/nocturnal-target-selector.ts +0 -545
  237. package/src/service/sleep-cycle.ts +0 -157
  238. package/src/service/startup-reconciler.ts +0 -112
  239. package/src/service/subagent-workflow/correction-observer-types.ts +0 -82
  240. package/src/service/subagent-workflow/correction-observer-workflow-manager.ts +0 -250
  241. package/src/service/subagent-workflow/deep-reflect-workflow-manager.ts +0 -1
  242. package/src/service/subagent-workflow/dynamic-timeout.ts +0 -30
  243. package/src/service/subagent-workflow/empathy-observer-workflow-manager.ts +0 -268
  244. package/src/service/subagent-workflow/nocturnal-workflow-manager.ts +0 -795
  245. package/src/service/subagent-workflow/runtime-direct-driver.ts +0 -268
  246. package/src/service/subagent-workflow/workflow-manager-base.ts +0 -580
  247. package/src/tools/write-pain-flag.ts +0 -215
  248. package/tests/commands/nocturnal-review.test.ts +0 -448
  249. package/tests/commands/nocturnal-train.test.ts +0 -97
  250. package/tests/commands/pd-reflect.test.ts +0 -49
  251. package/tests/core/adaptive-thresholds.test.ts +0 -261
  252. package/tests/core/nocturnal-arbiter.test.ts +0 -559
  253. package/tests/core/nocturnal-artifact-lineage.test.ts +0 -53
  254. package/tests/core/nocturnal-artificer.test.ts +0 -241
  255. package/tests/core/nocturnal-candidate-scoring.test.ts +0 -532
  256. package/tests/core/nocturnal-compliance-p-principles.test.ts +0 -133
  257. package/tests/core/nocturnal-compliance.test.ts +0 -646
  258. package/tests/core/nocturnal-dataset.test.ts +0 -892
  259. package/tests/core/nocturnal-e2e.test.ts +0 -234
  260. package/tests/core/nocturnal-executability.test.ts +0 -357
  261. package/tests/core/nocturnal-export.test.ts +0 -517
  262. package/tests/core/nocturnal-reasoning-deriver.test.ts +0 -372
  263. package/tests/core/nocturnal-reviewed-subset-comparison.test.ts +0 -428
  264. package/tests/core/nocturnal-rule-implementation-validator.test.ts +0 -127
  265. package/tests/core/nocturnal-snapshot-contract.test.ts +0 -121
  266. package/tests/core/nocturnal-trajectory-extractor.test.ts +0 -634
  267. package/tests/core/nocturnal-trinity.test.ts +0 -2053
  268. package/tests/core/pain-auto-repair.test.ts +0 -96
  269. package/tests/core/pain-integration.test.ts +0 -510
  270. package/tests/fixtures/nocturnal-reviewed-subset.json +0 -183
  271. package/tests/http/principles-console-route.test.ts +0 -162
  272. package/tests/integration/chaos-resilience.test.ts +0 -348
  273. package/tests/integration/empathy-workflow-integration.test.ts +0 -626
  274. package/tests/integration/pain-diagnostician-loop.e2e.test.ts +0 -380
  275. package/tests/service/control-ui-query-service.test.ts +0 -121
  276. package/tests/service/cooldown-strategy.test.ts +0 -164
  277. package/tests/service/data-endpoints-regression.test.ts +0 -834
  278. package/tests/service/empathy-observer-workflow-manager.test.ts +0 -175
  279. package/tests/service/evolution-worker.nocturnal.test.ts +0 -601
  280. package/tests/service/nocturnal-runtime-hardening.test.ts +0 -118
  281. package/tests/service/nocturnal-runtime.test.ts +0 -473
  282. package/tests/service/nocturnal-service-code-candidate.test.ts +0 -330
  283. package/tests/service/nocturnal-target-selector.test.ts +0 -615
  284. package/tests/service/startup-reconciler.test.ts +0 -148
  285. package/tests/tools/write-pain-flag.test.ts +0 -358
  286. package/ui/src/App.tsx +0 -45
  287. package/ui/src/api.ts +0 -220
  288. package/ui/src/charts.tsx +0 -955
  289. package/ui/src/components/ErrorState.tsx +0 -6
  290. package/ui/src/components/Loading.tsx +0 -13
  291. package/ui/src/components/ProtectedRoute.tsx +0 -12
  292. package/ui/src/components/Shell.tsx +0 -91
  293. package/ui/src/components/WorkspaceConfig.tsx +0 -178
  294. package/ui/src/components/index.ts +0 -5
  295. package/ui/src/context/auth.tsx +0 -80
  296. package/ui/src/context/theme.tsx +0 -66
  297. package/ui/src/hooks/useAutoRefresh.ts +0 -39
  298. package/ui/src/i18n/ui.ts +0 -473
  299. package/ui/src/main.tsx +0 -16
  300. package/ui/src/pages/EvolutionPage.tsx +0 -333
  301. package/ui/src/pages/FeedbackPage.tsx +0 -138
  302. package/ui/src/pages/GateMonitorPage.tsx +0 -136
  303. package/ui/src/pages/LoginPage.tsx +0 -89
  304. package/ui/src/pages/OverviewPage.tsx +0 -599
  305. package/ui/src/pages/SamplesPage.tsx +0 -174
  306. package/ui/src/pages/ThinkingModelsPage.tsx +0 -702
  307. package/ui/src/styles.css +0 -2020
  308. package/ui/src/types.ts +0 -384
  309. package/ui/src/utils/format.ts +0 -15
@@ -0,0 +1,610 @@
1
+ import { describe, test, expect, vi, beforeEach } from 'vitest';
2
+ import type { EvolutionConfig, ToolCallContext } from '../../src/core/evolution-types.js';
3
+ import { EvolutionTier } from '../../src/core/evolution-types.js';
4
+
5
+ // ── Mocks ──────────────────────────────────────────────────────────────────
6
+
7
+ vi.mock('../../src/core/paths.js', () => ({
8
+ resolvePdPath: vi.fn().mockReturnValue('/tmp/test-ws/.principles/state'),
9
+ }));
10
+
11
+ vi.mock('../../src/utils/file-lock.js', () => ({
12
+ withLock: vi.fn((_path: string, fn: () => unknown) => fn()),
13
+ }));
14
+
15
+ vi.mock('fs', async () => {
16
+ const actual = await vi.importActual<typeof import('fs')>('fs');
17
+ return {
18
+ ...actual,
19
+ existsSync: vi.fn().mockReturnValue(false),
20
+ readFileSync: vi.fn(),
21
+ writeFileSync: vi.fn(),
22
+ mkdirSync: vi.fn(),
23
+ renameSync: vi.fn(),
24
+ openSync: vi.fn().mockReturnValue(42),
25
+ fsyncSync: vi.fn(),
26
+ closeSync: vi.fn(),
27
+ unlinkSync: vi.fn(),
28
+ };
29
+ });
30
+
31
+ // ── Imports (after mocks) ──────────────────────────────────────────────────
32
+
33
+ import * as fs from 'fs';
34
+ import {
35
+ EvolutionEngine,
36
+ getEvolutionEngine,
37
+ disposeEvolutionEngine,
38
+ disposeAllEvolutionEngines,
39
+ recordEvolutionSuccess,
40
+ recordEvolutionFailure,
41
+ checkEvolutionGate,
42
+ } from '../../src/core/evolution-engine.js';
43
+ import { resolvePdPath } from '../../src/core/paths.js';
44
+ import { withLock } from '../../src/utils/file-lock.js';
45
+
46
+ // ── Helpers ────────────────────────────────────────────────────────────────
47
+
48
+ const WORKSPACE = '/tmp/test-ws';
49
+
50
+ function createEngine(config?: Partial<EvolutionConfig>): EvolutionEngine {
51
+ return new EvolutionEngine(WORKSPACE, config);
52
+ }
53
+
54
+ /** Build a scorecard JSON string as it would be stored on disk */
55
+ function buildStoredScorecard(overrides?: Record<string, unknown>) {
56
+ const base = {
57
+ version: '2.0',
58
+ agentId: 'default',
59
+ totalPoints: 0,
60
+ availablePoints: 0,
61
+ currentTier: EvolutionTier.Seed,
62
+ recentFailureHashes: [],
63
+ stats: {
64
+ totalSuccesses: 0,
65
+ totalFailures: 0,
66
+ consecutiveSuccesses: 0,
67
+ consecutiveFailures: 0,
68
+ doubleRewardsEarned: 0,
69
+ tierPromotions: 0,
70
+ pointsByDifficulty: { trivial: 0, normal: 0, hard: 0 },
71
+ },
72
+ recentEvents: [],
73
+ lastUpdated: new Date().toISOString(),
74
+ };
75
+ return JSON.stringify({ ...base, ...overrides });
76
+ }
77
+
78
+ // ── Tests ──────────────────────────────────────────────────────────────────
79
+
80
+ describe('EvolutionEngine', () => {
81
+ beforeEach(() => {
82
+ vi.clearAllMocks();
83
+ // Default: no stored scorecard on disk
84
+ vi.mocked(fs.existsSync).mockReturnValue(false);
85
+ });
86
+
87
+ // ── Constructor & Loading ─────────────────────────────────────────────────
88
+
89
+ describe('constructor', () => {
90
+ test('creates new scorecard when no file exists', () => {
91
+ const engine = createEngine();
92
+ expect(engine.getPoints()).toBe(0);
93
+ expect(engine.getTier()).toBe(EvolutionTier.Seed);
94
+ });
95
+
96
+ test('loads existing v2.0 scorecard from disk', () => {
97
+ vi.mocked(fs.existsSync).mockReturnValue(true);
98
+ vi.mocked(fs.readFileSync).mockReturnValue(
99
+ buildStoredScorecard({
100
+ totalPoints: 100,
101
+ availablePoints: 80,
102
+ currentTier: EvolutionTier.Sprout,
103
+ recentFailureHashes: [['edit:foo.ts', '2026-01-01T00:00:00Z']],
104
+ })
105
+ );
106
+
107
+ const engine = createEngine();
108
+ expect(engine.getPoints()).toBe(100);
109
+ expect(engine.getAvailablePoints()).toBe(80);
110
+ expect(engine.getTier()).toBe(EvolutionTier.Sprout);
111
+ });
112
+
113
+ test('creates new scorecard when stored version is not 2.0', () => {
114
+ vi.mocked(fs.existsSync).mockReturnValue(true);
115
+ vi.mocked(fs.readFileSync).mockReturnValue(JSON.stringify({ version: '1.0' }));
116
+
117
+ const engine = createEngine();
118
+ expect(engine.getPoints()).toBe(0);
119
+ expect(engine.getTier()).toBe(EvolutionTier.Seed);
120
+ });
121
+
122
+ test('creates new scorecard when JSON parse fails', () => {
123
+ vi.mocked(fs.existsSync).mockReturnValue(true);
124
+ vi.mocked(fs.readFileSync).mockReturnValue('not-json');
125
+
126
+ const engine = createEngine();
127
+ expect(engine.getPoints()).toBe(0);
128
+ });
129
+
130
+ test('applies custom config overrides', () => {
131
+ const engine = createEngine({ maxRecentEvents: 10 });
132
+ // Record 15 events to verify the limit
133
+ for (let i = 0; i < 15; i++) {
134
+ engine.recordSuccess('write_file', { filePath: `f${i}.ts` });
135
+ }
136
+ const scorecard = engine.getScorecard();
137
+ expect(scorecard.recentEvents).toHaveLength(10);
138
+ });
139
+ });
140
+
141
+ // ── Getters ───────────────────────────────────────────────────────────────
142
+
143
+ describe('getters', () => {
144
+ test('getScorecard returns a copy', () => {
145
+ const engine = createEngine();
146
+ const sc1 = engine.getScorecard();
147
+ const sc2 = engine.getScorecard();
148
+ expect(sc1).not.toBe(sc2);
149
+ expect(sc1).toEqual(sc2);
150
+ });
151
+
152
+ test('getStats returns a copy', () => {
153
+ const engine = createEngine();
154
+ const s1 = engine.getStats();
155
+ const s2 = engine.getStats();
156
+ expect(s1).not.toBe(s2);
157
+ expect(s1).toEqual(s2);
158
+ });
159
+
160
+ test('getTierDefinition returns current tier info', () => {
161
+ const engine = createEngine();
162
+ const def = engine.getTierDefinition();
163
+ expect(def.tier).toBe(EvolutionTier.Seed);
164
+ expect(def.name).toBe('Seed');
165
+ });
166
+
167
+ test('getStatusSummary returns complete status', () => {
168
+ const engine = createEngine();
169
+ const summary = engine.getStatusSummary();
170
+ expect(summary.tier).toBe(EvolutionTier.Seed);
171
+ expect(summary.tierName).toBe('Seed');
172
+ expect(summary.totalPoints).toBe(0);
173
+ expect(summary.availablePoints).toBe(0);
174
+ expect(summary.permissions).toBeDefined();
175
+ expect(summary.stats).toBeDefined();
176
+ });
177
+ });
178
+
179
+ // ── recordSuccess ─────────────────────────────────────────────────────────
180
+
181
+ describe('recordSuccess', () => {
182
+ test('awards points for constructive tool', () => {
183
+ const engine = createEngine();
184
+ const result = engine.recordSuccess('write_file', { filePath: 'test.ts' });
185
+ expect(result.pointsAwarded).toBeGreaterThan(0);
186
+ expect(engine.getPoints()).toBe(result.pointsAwarded);
187
+ });
188
+
189
+ test('awards 0 points for exploratory tool but clears failure hash', () => {
190
+ const engine = createEngine();
191
+ // First record a failure to create a hash
192
+ engine.recordFailure('read_file', { filePath: 'test.ts' });
193
+ const result = engine.recordSuccess('read_file', { filePath: 'test.ts' });
194
+ expect(result.pointsAwarded).toBe(0);
195
+ expect(result.isDoubleReward).toBe(false);
196
+ });
197
+
198
+ test('updates consecutive success count', () => {
199
+ const engine = createEngine();
200
+ engine.recordSuccess('write_file');
201
+ engine.recordSuccess('write_file');
202
+ const stats = engine.getStats();
203
+ expect(stats.consecutiveSuccesses).toBe(2);
204
+ expect(stats.consecutiveFailures).toBe(0);
205
+ });
206
+
207
+ test('resets consecutive failures on success', () => {
208
+ const engine = createEngine();
209
+ engine.recordFailure('write_file');
210
+ engine.recordSuccess('write_file');
211
+ const stats = engine.getStats();
212
+ expect(stats.consecutiveFailures).toBe(0);
213
+ expect(stats.consecutiveSuccesses).toBe(1);
214
+ });
215
+
216
+ test('returns double reward when recovering from failure', () => {
217
+ const engine = createEngine({ doubleRewardCooldownMs: 0 });
218
+ engine.recordFailure('write_file', { filePath: 'test.ts' });
219
+ const result = engine.recordSuccess('write_file', { filePath: 'test.ts' });
220
+ expect(result.isDoubleReward).toBe(true);
221
+ expect(result.pointsAwarded).toBeGreaterThan(3); // normal base is 3, doubled = 6
222
+ });
223
+
224
+ test('infers hard difficulty for high-risk tools', () => {
225
+ const engine = createEngine();
226
+ const result = engine.recordSuccess('bash');
227
+ // hard base = 8
228
+ expect(result.pointsAwarded).toBe(8);
229
+ });
230
+
231
+ test('infers normal difficulty for constructive tools', () => {
232
+ const engine = createEngine();
233
+ const result = engine.recordSuccess('write_file');
234
+ // normal base = 3
235
+ expect(result.pointsAwarded).toBe(3);
236
+ });
237
+
238
+ test('infers trivial difficulty for unknown tools', () => {
239
+ const engine = createEngine();
240
+ const result = engine.recordSuccess('some_unknown_tool');
241
+ // trivial base = 1
242
+ expect(result.pointsAwarded).toBe(1);
243
+ });
244
+
245
+ test('allows explicit difficulty override', () => {
246
+ const engine = createEngine();
247
+ const result = engine.recordSuccess('write_file', { difficulty: 'hard' });
248
+ expect(result.pointsAwarded).toBe(8);
249
+ });
250
+ });
251
+
252
+ // ── recordFailure ─────────────────────────────────────────────────────────
253
+
254
+ describe('recordFailure', () => {
255
+ test('does not deduct points', () => {
256
+ const engine = createEngine();
257
+ engine.recordSuccess('write_file');
258
+ const pointsBefore = engine.getPoints();
259
+ engine.recordFailure('write_file');
260
+ expect(engine.getPoints()).toBe(pointsBefore);
261
+ });
262
+
263
+ test('records lesson (failure hash)', () => {
264
+ const engine = createEngine();
265
+ const result = engine.recordFailure('write_file', { filePath: 'test.ts' });
266
+ expect(result.lessonRecorded).toBe(true);
267
+ expect(result.pointsAwarded).toBe(0);
268
+ });
269
+
270
+ test('updates failure stats', () => {
271
+ const engine = createEngine();
272
+ engine.recordFailure('write_file');
273
+ engine.recordFailure('write_file');
274
+ const stats = engine.getStats();
275
+ expect(stats.totalFailures).toBe(2);
276
+ expect(stats.consecutiveFailures).toBe(2);
277
+ expect(stats.consecutiveSuccesses).toBe(0);
278
+ });
279
+
280
+ test('resets consecutive successes on failure', () => {
281
+ const engine = createEngine();
282
+ engine.recordSuccess('write_file');
283
+ engine.recordFailure('write_file');
284
+ const stats = engine.getStats();
285
+ expect(stats.consecutiveSuccesses).toBe(0);
286
+ });
287
+
288
+ test('exploratory tool failure records event but no stats impact', () => {
289
+ const engine = createEngine();
290
+ const result = engine.recordFailure('read_file', { filePath: 'test.ts' });
291
+ expect(result.pointsAwarded).toBe(0);
292
+ expect(result.lessonRecorded).toBe(true);
293
+ // exploratory failures do NOT increment totalFailures (only event recorded)
294
+ const stats = engine.getStats();
295
+ expect(stats.totalFailures).toBe(0);
296
+ });
297
+ });
298
+
299
+ // ── Tier Promotion ────────────────────────────────────────────────────────
300
+
301
+ describe('tier promotion', () => {
302
+ test('promotes from Seed to Sprout at 50 points', () => {
303
+ const engine = createEngine();
304
+ // 50 / 3 (normal) = ~17 successes
305
+ let promoted = false;
306
+ for (let i = 0; i < 20; i++) {
307
+ const r = engine.recordSuccess('write_file');
308
+ if (r.newTier !== undefined) {
309
+ promoted = true;
310
+ expect(r.newTier).toBe(EvolutionTier.Sprout);
311
+ break;
312
+ }
313
+ }
314
+ expect(promoted).toBe(true);
315
+ expect(engine.getTier()).toBe(EvolutionTier.Sprout);
316
+ });
317
+
318
+ test('promotes through multiple tiers with enough points', () => {
319
+ // Load a scorecard with 490 points (just below Tree at 500)
320
+ vi.mocked(fs.existsSync).mockReturnValue(true);
321
+ vi.mocked(fs.readFileSync).mockReturnValue(
322
+ buildStoredScorecard({
323
+ totalPoints: 490,
324
+ availablePoints: 490,
325
+ currentTier: EvolutionTier.Sapling,
326
+ })
327
+ );
328
+ const engine = createEngine();
329
+ // hard = 8 points, need 10 more → 2 successes
330
+ const r = engine.recordSuccess('bash');
331
+ if (r.newTier !== undefined) {
332
+ expect(r.newTier).toBe(EvolutionTier.Tree);
333
+ }
334
+ });
335
+
336
+ test('getStatusSummary shows next tier info', () => {
337
+ const engine = createEngine();
338
+ const summary = engine.getStatusSummary();
339
+ expect(summary.nextTier).not.toBeNull();
340
+ expect(summary.nextTier!.tier).toBe(EvolutionTier.Sprout);
341
+ expect(summary.nextTier!.pointsNeeded).toBe(50);
342
+ });
343
+ });
344
+
345
+ // ── Difficulty Penalty ────────────────────────────────────────────────────
346
+
347
+ describe('difficulty penalty (high-tier trivial)', () => {
348
+ test('Tree tier gets reduced points for trivial tasks', () => {
349
+ vi.mocked(fs.existsSync).mockReturnValue(true);
350
+ vi.mocked(fs.readFileSync).mockReturnValue(
351
+ buildStoredScorecard({
352
+ totalPoints: 500,
353
+ availablePoints: 500,
354
+ currentTier: EvolutionTier.Tree,
355
+ })
356
+ );
357
+ const engine = createEngine();
358
+ const result = engine.recordSuccess('some_unknown_tool'); // trivial
359
+ // base 1 * tier4Trivial 0.1 = 0.1, max(1, floor(0.1)) = 1
360
+ expect(result.pointsAwarded).toBe(1);
361
+ });
362
+
363
+ test('Forest tier gets reduced points for normal tasks', () => {
364
+ vi.mocked(fs.existsSync).mockReturnValue(true);
365
+ vi.mocked(fs.readFileSync).mockReturnValue(
366
+ buildStoredScorecard({
367
+ totalPoints: 1000,
368
+ availablePoints: 1000,
369
+ currentTier: EvolutionTier.Forest,
370
+ })
371
+ );
372
+ const engine = createEngine();
373
+ const result = engine.recordSuccess('write_file'); // normal
374
+ // base 3 * tier5Normal 0.5 = 1.5, floor = 1
375
+ expect(result.pointsAwarded).toBe(1);
376
+ });
377
+ });
378
+
379
+ // ── beforeToolCall (Gate) ─────────────────────────────────────────────────
380
+
381
+ describe('beforeToolCall', () => {
382
+ test('allows normal tool for Seed tier', () => {
383
+ const engine = createEngine();
384
+ const decision = engine.beforeToolCall({ toolName: 'write_file' });
385
+ expect(decision.allowed).toBe(true);
386
+ expect(decision.currentTier).toBe(EvolutionTier.Seed);
387
+ });
388
+
389
+ test('blocks risk path for Seed tier', () => {
390
+ const engine = createEngine();
391
+ const decision = engine.beforeToolCall({
392
+ toolName: 'write_file',
393
+ isRiskPath: true,
394
+ });
395
+ expect(decision.allowed).toBe(false);
396
+ expect(decision.reason).toContain('未解锁风险路径权限');
397
+ });
398
+
399
+ test('blocks high-risk tool for Seed tier', () => {
400
+ const engine = createEngine();
401
+ const decision = engine.beforeToolCall({ toolName: 'bash' });
402
+ expect(decision.allowed).toBe(false);
403
+ expect(decision.reason).toContain('未解锁高风险工具权限');
404
+ });
405
+
406
+ test('allows sessions_spawn for Seed tier (all tiers allow subagent)', () => {
407
+ const engine = createEngine();
408
+ const decision = engine.beforeToolCall({ toolName: 'sessions_spawn' });
409
+ expect(decision.allowed).toBe(true);
410
+ });
411
+
412
+ test('allows risk path for Sapling tier', () => {
413
+ vi.mocked(fs.existsSync).mockReturnValue(true);
414
+ vi.mocked(fs.readFileSync).mockReturnValue(
415
+ buildStoredScorecard({
416
+ totalPoints: 200,
417
+ availablePoints: 200,
418
+ currentTier: EvolutionTier.Sapling,
419
+ })
420
+ );
421
+ const engine = createEngine();
422
+ const decision = engine.beforeToolCall({
423
+ toolName: 'write_file',
424
+ isRiskPath: true,
425
+ });
426
+ expect(decision.allowed).toBe(true);
427
+ });
428
+
429
+ test('allows high-risk tool for Sapling tier', () => {
430
+ vi.mocked(fs.existsSync).mockReturnValue(true);
431
+ vi.mocked(fs.readFileSync).mockReturnValue(
432
+ buildStoredScorecard({
433
+ totalPoints: 200,
434
+ availablePoints: 200,
435
+ currentTier: EvolutionTier.Sapling,
436
+ })
437
+ );
438
+ const engine = createEngine();
439
+ const decision = engine.beforeToolCall({ toolName: 'bash' });
440
+ expect(decision.allowed).toBe(true);
441
+ });
442
+ });
443
+
444
+ // ── Persistence ───────────────────────────────────────────────────────────
445
+
446
+ describe('persistence', () => {
447
+ test('saves scorecard after recordSuccess', () => {
448
+ const engine = createEngine();
449
+ engine.recordSuccess('write_file');
450
+ expect(vi.mocked(fs.writeFileSync)).toHaveBeenCalled();
451
+ expect(vi.mocked(fs.renameSync)).toHaveBeenCalled();
452
+ });
453
+
454
+ test('saves scorecard after recordFailure', () => {
455
+ const engine = createEngine();
456
+ engine.recordFailure('write_file');
457
+ expect(vi.mocked(fs.writeFileSync)).toHaveBeenCalled();
458
+ });
459
+
460
+ test('creates directory if it does not exist', () => {
461
+ vi.mocked(fs.existsSync).mockReturnValue(false);
462
+ createEngine();
463
+ // After constructor, recordSuccess should trigger save → mkdir
464
+ vi.mocked(fs.existsSync).mockReturnValue(false); // dir check in saveScorecard
465
+ const engine = createEngine();
466
+ engine.recordSuccess('write_file');
467
+ expect(vi.mocked(fs.mkdirSync)).toHaveBeenCalled();
468
+ });
469
+ });
470
+
471
+ // ── Double Reward Cooldown ────────────────────────────────────────────────
472
+
473
+ describe('double reward cooldown', () => {
474
+ test('does not grant double reward within cooldown period', () => {
475
+ const engine = createEngine({ doubleRewardCooldownMs: 60_000 });
476
+ engine.recordFailure('write_file', { filePath: 'test.ts' });
477
+ const r1 = engine.recordSuccess('write_file', { filePath: 'test.ts' });
478
+ expect(r1.isDoubleReward).toBe(true);
479
+
480
+ // Second failure + success within cooldown
481
+ engine.recordFailure('write_file', { filePath: 'test.ts' });
482
+ const r2 = engine.recordSuccess('write_file', { filePath: 'test.ts' });
483
+ expect(r2.isDoubleReward).toBe(false);
484
+ });
485
+
486
+ test('grants double reward after cooldown expires', () => {
487
+ const engine = createEngine({ doubleRewardCooldownMs: 0 });
488
+ engine.recordFailure('write_file', { filePath: 'test.ts' });
489
+ const r1 = engine.recordSuccess('write_file', { filePath: 'test.ts' });
490
+ expect(r1.isDoubleReward).toBe(true);
491
+
492
+ engine.recordFailure('write_file', { filePath: 'test.ts' });
493
+ const r2 = engine.recordSuccess('write_file', { filePath: 'test.ts' });
494
+ expect(r2.isDoubleReward).toBe(true);
495
+ });
496
+
497
+ test('does not grant double reward without prior failure', () => {
498
+ const engine = createEngine({ doubleRewardCooldownMs: 0 });
499
+ const result = engine.recordSuccess('write_file', { filePath: 'test.ts' });
500
+ expect(result.isDoubleReward).toBe(false);
501
+ });
502
+ });
503
+
504
+ // ── Event History ─────────────────────────────────────────────────────────
505
+
506
+ describe('event history', () => {
507
+ test('records success events with correct shape', () => {
508
+ const engine = createEngine();
509
+ engine.recordSuccess('write_file', { filePath: 'test.ts', reason: 'good' });
510
+ const sc = engine.getScorecard();
511
+ expect(sc.recentEvents).toHaveLength(1);
512
+ const ev = sc.recentEvents[0];
513
+ expect(ev.type).toBe('success');
514
+ expect(ev.toolName).toBe('write_file');
515
+ expect(ev.filePath).toBe('test.ts');
516
+ expect(ev.reason).toBe('good');
517
+ expect(ev.pointsAwarded).toBeGreaterThan(0);
518
+ expect(ev.id).toBeDefined();
519
+ expect(ev.timestamp).toBeDefined();
520
+ });
521
+
522
+ test('records failure events with 0 points', () => {
523
+ const engine = createEngine();
524
+ engine.recordFailure('write_file', { filePath: 'test.ts' });
525
+ const sc = engine.getScorecard();
526
+ expect(sc.recentEvents).toHaveLength(1);
527
+ expect(sc.recentEvents[0].type).toBe('failure');
528
+ expect(sc.recentEvents[0].pointsAwarded).toBe(0);
529
+ });
530
+
531
+ test('trims events beyond maxRecentEvents', () => {
532
+ const engine = createEngine({ maxRecentEvents: 3 });
533
+ for (let i = 0; i < 5; i++) {
534
+ engine.recordSuccess('write_file', { filePath: `f${i}.ts` });
535
+ }
536
+ const sc = engine.getScorecard();
537
+ expect(sc.recentEvents).toHaveLength(3);
538
+ // Oldest events are removed
539
+ expect(sc.recentEvents[0].filePath).toBe('f2.ts');
540
+ });
541
+ });
542
+
543
+ // ── dispose ───────────────────────────────────────────────────────────────
544
+
545
+ describe('dispose', () => {
546
+ test('clears retry timer and queue', () => {
547
+ const engine = createEngine();
548
+ // Should not throw
549
+ engine.dispose();
550
+ });
551
+ });
552
+ });
553
+
554
+ // ── Convenience Functions ───────────────────────────────────────────────────
555
+
556
+ describe('convenience functions', () => {
557
+ beforeEach(() => {
558
+ vi.clearAllMocks();
559
+ vi.mocked(fs.existsSync).mockReturnValue(false);
560
+ disposeAllEvolutionEngines();
561
+ });
562
+
563
+ test('getEvolutionEngine returns same instance for same workspace', () => {
564
+ const e1 = getEvolutionEngine(WORKSPACE);
565
+ const e2 = getEvolutionEngine(WORKSPACE);
566
+ expect(e1).toBe(e2);
567
+ });
568
+
569
+ test('getEvolutionEngine returns different instance for different workspace', () => {
570
+ const e1 = getEvolutionEngine('/ws-1');
571
+ const e2 = getEvolutionEngine('/ws-2');
572
+ expect(e1).not.toBe(e2);
573
+ });
574
+
575
+ test('disposeEvolutionEngine removes instance', () => {
576
+ const e1 = getEvolutionEngine(WORKSPACE);
577
+ disposeEvolutionEngine(WORKSPACE);
578
+ const e2 = getEvolutionEngine(WORKSPACE);
579
+ expect(e1).not.toBe(e2);
580
+ });
581
+
582
+ test('disposeEvolutionEngine is no-op for unknown workspace', () => {
583
+ expect(() => disposeEvolutionEngine('/nonexistent')).not.toThrow();
584
+ });
585
+
586
+ test('disposeAllEvolutionEngines clears all instances', () => {
587
+ getEvolutionEngine('/ws-1');
588
+ getEvolutionEngine('/ws-2');
589
+ disposeAllEvolutionEngines();
590
+ // New instances should be created
591
+ const e1 = getEvolutionEngine('/ws-1');
592
+ expect(e1.getPoints()).toBe(0);
593
+ });
594
+
595
+ test('recordEvolutionSuccess delegates to engine', () => {
596
+ const result = recordEvolutionSuccess(WORKSPACE, 'write_file');
597
+ expect(result.pointsAwarded).toBeGreaterThan(0);
598
+ });
599
+
600
+ test('recordEvolutionFailure delegates to engine', () => {
601
+ const result = recordEvolutionFailure(WORKSPACE, 'write_file');
602
+ expect(result.lessonRecorded).toBe(true);
603
+ expect(result.pointsAwarded).toBe(0);
604
+ });
605
+
606
+ test('checkEvolutionGate delegates to engine', () => {
607
+ const decision = checkEvolutionGate(WORKSPACE, { toolName: 'write_file' });
608
+ expect(decision.allowed).toBe(true);
609
+ });
610
+ });