@rpamis/comet 0.4.0-beta.3 → 0.4.0-beta.4

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 (508) hide show
  1. package/README.md +10 -0
  2. package/assets/manifest.json +2 -1
  3. package/assets/skills/comet/SKILL.md +25 -1
  4. package/assets/skills/comet/reference/comet-yaml-fields.md +5 -2
  5. package/assets/skills/comet/reference/context-recovery.md +10 -0
  6. package/assets/skills/comet/reference/scripts.md +47 -15
  7. package/assets/skills/comet/rules/comet-phase-guard.en.md +8 -0
  8. package/assets/skills/comet/rules/comet-phase-guard.md +9 -1
  9. package/assets/skills/comet/scripts/comet-resume-probe.mjs +3 -0
  10. package/assets/skills/comet/scripts/comet-runtime.mjs +1387 -424
  11. package/assets/skills/comet-archive/SKILL.md +24 -11
  12. package/assets/skills/comet-build/SKILL.md +42 -25
  13. package/assets/skills/comet-design/SKILL.md +1 -0
  14. package/assets/skills/comet-hotfix/SKILL.md +3 -1
  15. package/assets/skills/comet-open/SKILL.md +11 -1
  16. package/assets/skills/comet-tweak/SKILL.md +3 -1
  17. package/assets/skills/comet-verify/SKILL.md +29 -20
  18. package/assets/skills-zh/comet/SKILL.md +25 -1
  19. package/assets/skills-zh/comet/reference/comet-yaml-fields.md +5 -2
  20. package/assets/skills-zh/comet/reference/context-recovery.md +10 -0
  21. package/assets/skills-zh/comet/reference/scripts.md +47 -15
  22. package/assets/skills-zh/comet-archive/SKILL.md +24 -11
  23. package/assets/skills-zh/comet-build/SKILL.md +42 -25
  24. package/assets/skills-zh/comet-design/SKILL.md +1 -0
  25. package/assets/skills-zh/comet-hotfix/SKILL.md +3 -1
  26. package/assets/skills-zh/comet-open/SKILL.md +11 -1
  27. package/assets/skills-zh/comet-tweak/SKILL.md +3 -1
  28. package/assets/skills-zh/comet-verify/SKILL.md +30 -21
  29. package/dist/app/cli/comet-banner.d.ts +25 -0
  30. package/dist/app/cli/comet-banner.d.ts.map +1 -0
  31. package/dist/app/cli/comet-banner.js +265 -0
  32. package/dist/app/cli/comet-banner.js.map +1 -0
  33. package/dist/app/cli/index.js +36 -2
  34. package/dist/app/cli/index.js.map +1 -1
  35. package/dist/app/commands/classic.d.ts +4 -0
  36. package/dist/app/commands/classic.d.ts.map +1 -0
  37. package/dist/app/commands/classic.js +11 -0
  38. package/dist/app/commands/classic.js.map +1 -0
  39. package/dist/app/commands/doctor.d.ts.map +1 -1
  40. package/dist/app/commands/doctor.js +39 -24
  41. package/dist/app/commands/doctor.js.map +1 -1
  42. package/dist/app/commands/eval.d.ts.map +1 -1
  43. package/dist/app/commands/eval.js +57 -20
  44. package/dist/app/commands/eval.js.map +1 -1
  45. package/dist/app/commands/i18n.d.ts +1 -1
  46. package/dist/app/commands/i18n.d.ts.map +1 -1
  47. package/dist/app/commands/i18n.js +12 -4
  48. package/dist/app/commands/i18n.js.map +1 -1
  49. package/dist/app/commands/init.d.ts.map +1 -1
  50. package/dist/app/commands/init.js +16 -13
  51. package/dist/app/commands/init.js.map +1 -1
  52. package/dist/app/commands/project-scope-selection.d.ts +13 -0
  53. package/dist/app/commands/project-scope-selection.d.ts.map +1 -0
  54. package/dist/app/commands/project-scope-selection.js +33 -0
  55. package/dist/app/commands/project-scope-selection.js.map +1 -0
  56. package/dist/app/commands/resume-probe.d.ts +11 -0
  57. package/dist/app/commands/resume-probe.d.ts.map +1 -0
  58. package/dist/app/commands/resume-probe.js +63 -0
  59. package/dist/app/commands/resume-probe.js.map +1 -0
  60. package/dist/app/commands/status.d.ts +31 -0
  61. package/dist/app/commands/status.d.ts.map +1 -1
  62. package/dist/app/commands/status.js +109 -20
  63. package/dist/app/commands/status.js.map +1 -1
  64. package/dist/app/commands/uninstall.d.ts +2 -0
  65. package/dist/app/commands/uninstall.d.ts.map +1 -1
  66. package/dist/app/commands/uninstall.js +217 -40
  67. package/dist/app/commands/uninstall.js.map +1 -1
  68. package/dist/app/commands/update.d.ts +6 -0
  69. package/dist/app/commands/update.d.ts.map +1 -1
  70. package/dist/app/commands/update.js +361 -68
  71. package/dist/app/commands/update.js.map +1 -1
  72. package/dist/config/repository-layout.json +4 -2
  73. package/dist/domains/bundle/bundle-platform.d.ts.map +1 -1
  74. package/dist/domains/bundle/bundle-platform.js +3 -1
  75. package/dist/domains/bundle/bundle-platform.js.map +1 -1
  76. package/dist/domains/bundle/eval-manifest-runtime.d.ts +6 -0
  77. package/dist/domains/bundle/eval-manifest-runtime.d.ts.map +1 -0
  78. package/dist/domains/bundle/eval-manifest-runtime.js +58 -0
  79. package/dist/domains/bundle/eval-manifest-runtime.js.map +1 -0
  80. package/dist/domains/bundle/types.d.ts +1 -1
  81. package/dist/domains/bundle/types.d.ts.map +1 -1
  82. package/dist/domains/comet-classic/classic-archive.d.ts +1 -0
  83. package/dist/domains/comet-classic/classic-archive.d.ts.map +1 -1
  84. package/dist/domains/comet-classic/classic-archive.js +35 -38
  85. package/dist/domains/comet-classic/classic-archive.js.map +1 -1
  86. package/dist/domains/comet-classic/classic-cli.d.ts +1 -1
  87. package/dist/domains/comet-classic/classic-cli.d.ts.map +1 -1
  88. package/dist/domains/comet-classic/classic-cli.js +3 -0
  89. package/dist/domains/comet-classic/classic-cli.js.map +1 -1
  90. package/dist/domains/comet-classic/classic-command-checks.d.ts +20 -0
  91. package/dist/domains/comet-classic/classic-command-checks.d.ts.map +1 -0
  92. package/dist/domains/comet-classic/classic-command-checks.js +97 -0
  93. package/dist/domains/comet-classic/classic-command-checks.js.map +1 -0
  94. package/dist/domains/comet-classic/classic-current-change.d.ts +19 -0
  95. package/dist/domains/comet-classic/classic-current-change.d.ts.map +1 -0
  96. package/dist/domains/comet-classic/classic-current-change.js +132 -0
  97. package/dist/domains/comet-classic/classic-current-change.js.map +1 -0
  98. package/dist/domains/comet-classic/classic-diagnostics.d.ts +2 -1
  99. package/dist/domains/comet-classic/classic-diagnostics.d.ts.map +1 -1
  100. package/dist/domains/comet-classic/classic-diagnostics.js +54 -1
  101. package/dist/domains/comet-classic/classic-diagnostics.js.map +1 -1
  102. package/dist/domains/comet-classic/classic-evidence.d.ts.map +1 -1
  103. package/dist/domains/comet-classic/classic-evidence.js +4 -0
  104. package/dist/domains/comet-classic/classic-evidence.js.map +1 -1
  105. package/dist/domains/comet-classic/classic-guard.d.ts.map +1 -1
  106. package/dist/domains/comet-classic/classic-guard.js +68 -69
  107. package/dist/domains/comet-classic/classic-guard.js.map +1 -1
  108. package/dist/domains/comet-classic/classic-hook-guard.d.ts.map +1 -1
  109. package/dist/domains/comet-classic/classic-hook-guard.js +66 -23
  110. package/dist/domains/comet-classic/classic-hook-guard.js.map +1 -1
  111. package/dist/domains/comet-classic/classic-project-config.d.ts +16 -0
  112. package/dist/domains/comet-classic/classic-project-config.d.ts.map +1 -0
  113. package/dist/domains/comet-classic/classic-project-config.js +40 -0
  114. package/dist/domains/comet-classic/classic-project-config.js.map +1 -0
  115. package/dist/domains/comet-classic/classic-resolver.d.ts.map +1 -1
  116. package/dist/domains/comet-classic/classic-resolver.js +3 -3
  117. package/dist/domains/comet-classic/classic-resolver.js.map +1 -1
  118. package/dist/domains/comet-classic/classic-resume-probe-command.d.ts +3 -0
  119. package/dist/domains/comet-classic/classic-resume-probe-command.d.ts.map +1 -0
  120. package/dist/domains/comet-classic/classic-resume-probe-command.js +58 -0
  121. package/dist/domains/comet-classic/classic-resume-probe-command.js.map +1 -0
  122. package/dist/domains/comet-classic/classic-resume-probe-entry.d.ts +2 -0
  123. package/dist/domains/comet-classic/classic-resume-probe-entry.d.ts.map +1 -0
  124. package/dist/domains/comet-classic/classic-resume-probe-entry.js +4 -0
  125. package/dist/domains/comet-classic/classic-resume-probe-entry.js.map +1 -0
  126. package/dist/domains/comet-classic/classic-resume-probe.d.ts +29 -0
  127. package/dist/domains/comet-classic/classic-resume-probe.d.ts.map +1 -0
  128. package/dist/domains/comet-classic/classic-resume-probe.js +386 -0
  129. package/dist/domains/comet-classic/classic-resume-probe.js.map +1 -0
  130. package/dist/domains/comet-classic/classic-runtime-run.d.ts +2 -1
  131. package/dist/domains/comet-classic/classic-runtime-run.d.ts.map +1 -1
  132. package/dist/domains/comet-classic/classic-runtime-run.js +38 -0
  133. package/dist/domains/comet-classic/classic-runtime-run.js.map +1 -1
  134. package/dist/domains/comet-classic/classic-state-command.d.ts.map +1 -1
  135. package/dist/domains/comet-classic/classic-state-command.js +128 -12
  136. package/dist/domains/comet-classic/classic-state-command.js.map +1 -1
  137. package/dist/domains/comet-classic/classic-state.d.ts +3 -1
  138. package/dist/domains/comet-classic/classic-state.d.ts.map +1 -1
  139. package/dist/domains/comet-classic/classic-state.js +4 -0
  140. package/dist/domains/comet-classic/classic-state.js.map +1 -1
  141. package/dist/domains/comet-classic/classic-store.d.ts +4 -1
  142. package/dist/domains/comet-classic/classic-store.d.ts.map +1 -1
  143. package/dist/domains/comet-classic/classic-store.js +4 -3
  144. package/dist/domains/comet-classic/classic-store.js.map +1 -1
  145. package/dist/domains/comet-classic/classic-transitions.d.ts +1 -1
  146. package/dist/domains/comet-classic/classic-transitions.d.ts.map +1 -1
  147. package/dist/domains/comet-classic/classic-transitions.js +20 -1
  148. package/dist/domains/comet-classic/classic-transitions.js.map +1 -1
  149. package/dist/domains/comet-classic/classic-validate-command.d.ts.map +1 -1
  150. package/dist/domains/comet-classic/classic-validate-command.js +1 -0
  151. package/dist/domains/comet-classic/classic-validate-command.js.map +1 -1
  152. package/dist/domains/comet-classic/index.d.ts +3 -0
  153. package/dist/domains/comet-classic/index.d.ts.map +1 -1
  154. package/dist/domains/comet-classic/index.js +3 -0
  155. package/dist/domains/comet-classic/index.js.map +1 -1
  156. package/dist/domains/dashboard/collector.js +10 -2
  157. package/dist/domains/dashboard/collector.js.map +1 -1
  158. package/dist/domains/dashboard/web/assets/{index-CjU3VXVu.js → index-CIvN-PL8.js} +11 -11
  159. package/dist/domains/dashboard/web/assets/{index-BcO3_QlT.css → index-DcyRPBnT.css} +1 -1
  160. package/dist/domains/dashboard/web/index.html +2 -2
  161. package/dist/domains/engine/types.d.ts +1 -1
  162. package/dist/domains/engine/types.d.ts.map +1 -1
  163. package/dist/domains/integrations/openspec.d.ts.map +1 -1
  164. package/dist/domains/integrations/openspec.js +6 -6
  165. package/dist/domains/integrations/openspec.js.map +1 -1
  166. package/dist/domains/skill/find.d.ts.map +1 -1
  167. package/dist/domains/skill/find.js +1 -6
  168. package/dist/domains/skill/find.js.map +1 -1
  169. package/dist/domains/skill/managed-markdown.d.ts +14 -0
  170. package/dist/domains/skill/managed-markdown.d.ts.map +1 -0
  171. package/dist/domains/skill/managed-markdown.js +126 -0
  172. package/dist/domains/skill/managed-markdown.js.map +1 -0
  173. package/dist/domains/skill/platform-install.d.ts +4 -3
  174. package/dist/domains/skill/platform-install.d.ts.map +1 -1
  175. package/dist/domains/skill/platform-install.js +96 -26
  176. package/dist/domains/skill/platform-install.js.map +1 -1
  177. package/dist/domains/skill/project-instructions.d.ts +22 -0
  178. package/dist/domains/skill/project-instructions.d.ts.map +1 -0
  179. package/dist/domains/skill/project-instructions.js +61 -0
  180. package/dist/domains/skill/project-instructions.js.map +1 -0
  181. package/dist/domains/skill/uninstall.d.ts +3 -1
  182. package/dist/domains/skill/uninstall.d.ts.map +1 -1
  183. package/dist/domains/skill/uninstall.js +86 -39
  184. package/dist/domains/skill/uninstall.js.map +1 -1
  185. package/dist/platform/install/detect.d.ts +2 -1
  186. package/dist/platform/install/detect.d.ts.map +1 -1
  187. package/dist/platform/install/detect.js +10 -1
  188. package/dist/platform/install/detect.js.map +1 -1
  189. package/dist/platform/install/platforms.d.ts +5 -1
  190. package/dist/platform/install/platforms.d.ts.map +1 -1
  191. package/dist/platform/install/platforms.js +21 -4
  192. package/dist/platform/install/platforms.js.map +1 -1
  193. package/dist/platform/install/project-registry.d.ts +37 -0
  194. package/dist/platform/install/project-registry.d.ts.map +1 -0
  195. package/dist/platform/install/project-registry.js +205 -0
  196. package/dist/platform/install/project-registry.js.map +1 -0
  197. package/eval/.env +28 -0
  198. package/eval/.env.example +52 -0
  199. package/eval/CLAUDE.md +43 -0
  200. package/eval/README.md +538 -0
  201. package/eval/langsmith/.env.example +16 -0
  202. package/eval/langsmith/README.md +93 -0
  203. package/eval/langsmith/skills/README.md +5 -0
  204. package/eval/langsmith/tasks/README.md +5 -0
  205. package/eval/langsmith/tests/conftest.py +187 -0
  206. package/eval/langsmith/tests/tasks/test_tasks.py +287 -0
  207. package/eval/langsmith/treatments/README.md +5 -0
  208. package/eval/local/README.md +80 -0
  209. package/eval/local/regression_baseline.json +13 -0
  210. package/eval/local/report-style-demo-assets/quality_cost.en.svg +41 -0
  211. package/eval/local/report-style-demo-assets/quality_cost.zh.svg +41 -0
  212. package/eval/local/report-style-demo-assets/rubric_delta.en.svg +56 -0
  213. package/eval/local/report-style-demo-assets/rubric_delta.zh.svg +56 -0
  214. package/eval/local/report-style-demo-assets/task_outcomes.en.svg +46 -0
  215. package/eval/local/report-style-demo-assets/task_outcomes.zh.svg +46 -0
  216. package/eval/local/report-style-demo.html +867 -0
  217. package/eval/local/scripts/compare_baselines.py +1018 -0
  218. package/eval/local/scripts/generate_report_style_demo_charts.py +322 -0
  219. package/eval/local/scripts/regression_check.py +171 -0
  220. package/eval/local/scripts/render_readme_benchmark_figures.py +416 -0
  221. package/eval/local/scripts/rescore_rubric.py +120 -0
  222. package/eval/local/skills/benchmarks/039-release/comet-classic-039/SKILL.md +282 -0
  223. package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/auto-transition.md +27 -0
  224. package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/comet-yaml-fields.md +68 -0
  225. package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/context-recovery.md +35 -0
  226. package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/debug-gate.md +17 -0
  227. package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/decision-point.md +20 -0
  228. package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/dirty-worktree.md +59 -0
  229. package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/file-structure.md +28 -0
  230. package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/subagent-dispatch.md +113 -0
  231. package/eval/local/skills/benchmarks/039-release/comet-classic-039/rules/comet-phase-guard.md +125 -0
  232. package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-archive.sh +311 -0
  233. package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-env.sh +110 -0
  234. package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-guard.sh +778 -0
  235. package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-handoff.sh +390 -0
  236. package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-hook-guard.sh +336 -0
  237. package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-state.sh +1338 -0
  238. package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-yaml-validate.sh +225 -0
  239. package/eval/local/skills/benchmarks/039-release/comet-classic-039-archive/SKILL.md +100 -0
  240. package/eval/local/skills/benchmarks/039-release/comet-classic-039-build/SKILL.md +304 -0
  241. package/eval/local/skills/benchmarks/039-release/comet-classic-039-design/SKILL.md +263 -0
  242. package/eval/local/skills/benchmarks/039-release/comet-classic-039-hotfix/SKILL.md +204 -0
  243. package/eval/local/skills/benchmarks/039-release/comet-classic-039-open/SKILL.md +220 -0
  244. package/eval/local/skills/benchmarks/039-release/comet-classic-039-tweak/SKILL.md +180 -0
  245. package/eval/local/skills/benchmarks/039-release/comet-classic-039-verify/SKILL.md +234 -0
  246. package/eval/local/skills/benchmarks/040-beta/comet/SKILL.md +261 -0
  247. package/eval/local/skills/benchmarks/040-beta/comet/reference/auto-transition.md +27 -0
  248. package/eval/local/skills/benchmarks/040-beta/comet/reference/comet-yaml-fields.md +73 -0
  249. package/eval/local/skills/benchmarks/040-beta/comet/reference/context-recovery.md +45 -0
  250. package/eval/local/skills/benchmarks/040-beta/comet/reference/debug-gate.md +33 -0
  251. package/eval/local/skills/benchmarks/040-beta/comet/reference/decision-point.md +31 -0
  252. package/eval/local/skills/benchmarks/040-beta/comet/reference/dirty-worktree.md +59 -0
  253. package/eval/local/skills/benchmarks/040-beta/comet/reference/file-structure.md +28 -0
  254. package/eval/local/skills/benchmarks/040-beta/comet/reference/intent-frame.md +74 -0
  255. package/eval/local/skills/benchmarks/040-beta/comet/reference/scripts.md +69 -0
  256. package/eval/local/skills/benchmarks/040-beta/comet/reference/subagent-dispatch.md +169 -0
  257. package/eval/local/skills/benchmarks/040-beta/comet/rules/comet-phase-guard.md +130 -0
  258. package/eval/local/skills/benchmarks/040-beta/comet/runtime/classic/checks.yaml +6 -0
  259. package/eval/local/skills/benchmarks/040-beta/comet/runtime/classic/guardrails.yaml +13 -0
  260. package/eval/local/skills/benchmarks/040-beta/comet/runtime/classic/skill.yaml +122 -0
  261. package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-archive.mjs +9515 -0
  262. package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-env.mjs +15 -0
  263. package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-guard.mjs +10173 -0
  264. package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-handoff.mjs +9491 -0
  265. package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-hook-guard.mjs +9175 -0
  266. package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-intent.mjs +404 -0
  267. package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-state.mjs +9273 -0
  268. package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-yaml-validate.mjs +7627 -0
  269. package/eval/local/skills/benchmarks/040-beta/comet-archive/SKILL.md +110 -0
  270. package/eval/local/skills/benchmarks/040-beta/comet-build/SKILL.md +315 -0
  271. package/eval/local/skills/benchmarks/040-beta/comet-design/SKILL.md +260 -0
  272. package/eval/local/skills/benchmarks/040-beta/comet-hotfix/SKILL.md +190 -0
  273. package/eval/local/skills/benchmarks/040-beta/comet-open/SKILL.md +210 -0
  274. package/eval/local/skills/benchmarks/040-beta/comet-tweak/SKILL.md +183 -0
  275. package/eval/local/skills/benchmarks/040-beta/comet-verify/SKILL.md +230 -0
  276. package/eval/local/skills/benchmarks/dependency/claude-md/comet-workflow/CLAUDE.md +12 -0
  277. package/eval/local/skills/benchmarks/dependency/openspec/openspec-apply-change/SKILL.md +156 -0
  278. package/eval/local/skills/benchmarks/dependency/openspec/openspec-archive-change/SKILL.md +114 -0
  279. package/eval/local/skills/benchmarks/dependency/openspec/openspec-bulk-archive-change/SKILL.md +246 -0
  280. package/eval/local/skills/benchmarks/dependency/openspec/openspec-continue-change/SKILL.md +118 -0
  281. package/eval/local/skills/benchmarks/dependency/openspec/openspec-explore/SKILL.md +288 -0
  282. package/eval/local/skills/benchmarks/dependency/openspec/openspec-ff-change/SKILL.md +101 -0
  283. package/eval/local/skills/benchmarks/dependency/openspec/openspec-new-change/SKILL.md +74 -0
  284. package/eval/local/skills/benchmarks/dependency/openspec/openspec-onboard/SKILL.md +554 -0
  285. package/eval/local/skills/benchmarks/dependency/openspec/openspec-propose/SKILL.md +110 -0
  286. package/eval/local/skills/benchmarks/dependency/openspec/openspec-sync-specs/SKILL.md +138 -0
  287. package/eval/local/skills/benchmarks/dependency/openspec/openspec-verify-change/SKILL.md +168 -0
  288. package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/SKILL.md +159 -0
  289. package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/scripts/frame-template.html +213 -0
  290. package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/scripts/helper.js +167 -0
  291. package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/scripts/server.cjs +723 -0
  292. package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/scripts/start-server.sh +209 -0
  293. package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/scripts/stop-server.sh +120 -0
  294. package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/spec-document-reviewer-prompt.md +49 -0
  295. package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/visual-companion.md +291 -0
  296. package/eval/local/skills/benchmarks/dependency/superpowers/dispatching-parallel-agents/SKILL.md +185 -0
  297. package/eval/local/skills/benchmarks/dependency/superpowers/executing-plans/SKILL.md +70 -0
  298. package/eval/local/skills/benchmarks/dependency/superpowers/finishing-a-development-branch/SKILL.md +241 -0
  299. package/eval/local/skills/benchmarks/dependency/superpowers/receiving-code-review/SKILL.md +213 -0
  300. package/eval/local/skills/benchmarks/dependency/superpowers/requesting-code-review/SKILL.md +103 -0
  301. package/eval/local/skills/benchmarks/dependency/superpowers/requesting-code-review/code-reviewer.md +172 -0
  302. package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/SKILL.md +418 -0
  303. package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/implementer-prompt.md +139 -0
  304. package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/scripts/review-package +44 -0
  305. package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/scripts/sdd-workspace +22 -0
  306. package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/scripts/task-brief +40 -0
  307. package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/task-reviewer-prompt.md +188 -0
  308. package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/CREATION-LOG.md +119 -0
  309. package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/SKILL.md +296 -0
  310. package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/condition-based-waiting-example.ts +158 -0
  311. package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/condition-based-waiting.md +115 -0
  312. package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/defense-in-depth.md +122 -0
  313. package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/find-polluter.sh +63 -0
  314. package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/root-cause-tracing.md +169 -0
  315. package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/test-academic.md +14 -0
  316. package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/test-pressure-1.md +58 -0
  317. package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/test-pressure-2.md +68 -0
  318. package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/test-pressure-3.md +69 -0
  319. package/eval/local/skills/benchmarks/dependency/superpowers/test-driven-development/SKILL.md +371 -0
  320. package/eval/local/skills/benchmarks/dependency/superpowers/test-driven-development/testing-anti-patterns.md +299 -0
  321. package/eval/local/skills/benchmarks/dependency/superpowers/using-git-worktrees/SKILL.md +202 -0
  322. package/eval/local/skills/benchmarks/dependency/superpowers/verification-before-completion/SKILL.md +139 -0
  323. package/eval/local/skills/benchmarks/dependency/superpowers/writing-plans/SKILL.md +174 -0
  324. package/eval/local/skills/benchmarks/dependency/superpowers/writing-plans/plan-document-reviewer-prompt.md +49 -0
  325. package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/SKILL.md +689 -0
  326. package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/anthropic-best-practices.md +1150 -0
  327. package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/examples/CLAUDE_MD_TESTING.md +189 -0
  328. package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/graphviz-conventions.dot +172 -0
  329. package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/persuasion-principles.md +187 -0
  330. package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/render-graphs.js +168 -0
  331. package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/testing-skills-with-subagents.md +384 -0
  332. package/eval/local/tasks/authoring-skill-smoke/environment/Dockerfile +2 -0
  333. package/eval/local/tasks/authoring-skill-smoke/instruction.md +4 -0
  334. package/eval/local/tasks/authoring-skill-smoke/task.toml +21 -0
  335. package/eval/local/tasks/authoring-skill-smoke/validation/test_authoring_skill_smoke.py +54 -0
  336. package/eval/local/tasks/comet-agent-memory-routing/environment/Dockerfile +28 -0
  337. package/eval/local/tasks/comet-agent-memory-routing/environment/agent_system.py +40 -0
  338. package/eval/local/tasks/comet-agent-memory-routing/environment/test_agent_system.py +29 -0
  339. package/eval/local/tasks/comet-agent-memory-routing/instruction.md +20 -0
  340. package/eval/local/tasks/comet-agent-memory-routing/task.toml +24 -0
  341. package/eval/local/tasks/comet-agent-memory-routing/validation/test_agent_memory_routing.py +24 -0
  342. package/eval/local/tasks/comet-api-cache-ttl/environment/Dockerfile +39 -0
  343. package/eval/local/tasks/comet-api-cache-ttl/environment/cache.py +39 -0
  344. package/eval/local/tasks/comet-api-cache-ttl/environment/test_cache.py +81 -0
  345. package/eval/local/tasks/comet-api-cache-ttl/instruction.md +33 -0
  346. package/eval/local/tasks/comet-api-cache-ttl/task.toml +24 -0
  347. package/eval/local/tasks/comet-api-cache-ttl/validation/test_api_cache_ttl.py +58 -0
  348. package/eval/local/tasks/comet-cross-file-refactor/environment/Dockerfile +15 -0
  349. package/eval/local/tasks/comet-cross-file-refactor/environment/cli.py +13 -0
  350. package/eval/local/tasks/comet-cross-file-refactor/environment/counting.py +13 -0
  351. package/eval/local/tasks/comet-cross-file-refactor/environment/test_textkit.py +21 -0
  352. package/eval/local/tasks/comet-cross-file-refactor/instruction.md +16 -0
  353. package/eval/local/tasks/comet-cross-file-refactor/task.toml +20 -0
  354. package/eval/local/tasks/comet-cross-file-refactor/validation/test_cross_file_refactor.py +20 -0
  355. package/eval/local/tasks/comet-dependency-confusion/environment/Dockerfile +28 -0
  356. package/eval/local/tasks/comet-dependency-confusion/environment/app.py +8 -0
  357. package/eval/local/tasks/comet-dependency-confusion/environment/settings_loader.py +14 -0
  358. package/eval/local/tasks/comet-dependency-confusion/environment/test_settings_service.py +19 -0
  359. package/eval/local/tasks/comet-dependency-confusion/instruction.md +18 -0
  360. package/eval/local/tasks/comet-dependency-confusion/task.toml +24 -0
  361. package/eval/local/tasks/comet-dependency-confusion/validation/test_dependency_confusion.py +24 -0
  362. package/eval/local/tasks/comet-fix-median/environment/Dockerfile +50 -0
  363. package/eval/local/tasks/comet-fix-median/environment/stats.py +54 -0
  364. package/eval/local/tasks/comet-fix-median/environment/test_stats.py +68 -0
  365. package/eval/local/tasks/comet-fix-median/instruction.md +25 -0
  366. package/eval/local/tasks/comet-fix-median/task.toml +24 -0
  367. package/eval/local/tasks/comet-fix-median/validation/test_fix_median.py +60 -0
  368. package/eval/local/tasks/comet-framework-selection/environment/Dockerfile +28 -0
  369. package/eval/local/tasks/comet-framework-selection/environment/architecture.py +12 -0
  370. package/eval/local/tasks/comet-framework-selection/environment/test_architecture.py +30 -0
  371. package/eval/local/tasks/comet-framework-selection/instruction.md +22 -0
  372. package/eval/local/tasks/comet-framework-selection/task.toml +24 -0
  373. package/eval/local/tasks/comet-framework-selection/validation/test_framework_selection.py +24 -0
  374. package/eval/local/tasks/comet-full-workflow/environment/Dockerfile +53 -0
  375. package/eval/local/tasks/comet-full-workflow/environment/test_wordcount.py +29 -0
  376. package/eval/local/tasks/comet-full-workflow/environment/wordcount.py +40 -0
  377. package/eval/local/tasks/comet-full-workflow/instruction.md +18 -0
  378. package/eval/local/tasks/comet-full-workflow/task.toml +24 -0
  379. package/eval/local/tasks/comet-full-workflow/validation/test_full_workflow.py +171 -0
  380. package/eval/local/tasks/comet-graph-execution-review/environment/Dockerfile +28 -0
  381. package/eval/local/tasks/comet-graph-execution-review/environment/pipeline.py +19 -0
  382. package/eval/local/tasks/comet-graph-execution-review/environment/test_pipeline.py +53 -0
  383. package/eval/local/tasks/comet-graph-execution-review/instruction.md +21 -0
  384. package/eval/local/tasks/comet-graph-execution-review/task.toml +24 -0
  385. package/eval/local/tasks/comet-graph-execution-review/validation/test_graph_execution_review.py +24 -0
  386. package/eval/local/tasks/comet-human-approval-flow/environment/Dockerfile +15 -0
  387. package/eval/local/tasks/comet-human-approval-flow/environment/approvals.py +17 -0
  388. package/eval/local/tasks/comet-human-approval-flow/environment/test_approvals.py +30 -0
  389. package/eval/local/tasks/comet-human-approval-flow/instruction.md +15 -0
  390. package/eval/local/tasks/comet-human-approval-flow/task.toml +20 -0
  391. package/eval/local/tasks/comet-human-approval-flow/validation/test_human_approval_flow.py +20 -0
  392. package/eval/local/tasks/comet-layered-streaming-fix/environment/Dockerfile +20 -0
  393. package/eval/local/tasks/comet-layered-streaming-fix/environment/chat_app.py +19 -0
  394. package/eval/local/tasks/comet-layered-streaming-fix/environment/test_chat_app.py +15 -0
  395. package/eval/local/tasks/comet-layered-streaming-fix/instruction.md +14 -0
  396. package/eval/local/tasks/comet-layered-streaming-fix/task.toml +20 -0
  397. package/eval/local/tasks/comet-layered-streaming-fix/validation/test_layered_streaming_fix.py +20 -0
  398. package/eval/local/tasks/comet-noise-distractor/environment/Dockerfile +15 -0
  399. package/eval/local/tasks/comet-noise-distractor/environment/distractor.md +4 -0
  400. package/eval/local/tasks/comet-noise-distractor/environment/invoice.py +5 -0
  401. package/eval/local/tasks/comet-noise-distractor/environment/test_invoice.py +18 -0
  402. package/eval/local/tasks/comet-noise-distractor/instruction.md +17 -0
  403. package/eval/local/tasks/comet-noise-distractor/task.toml +20 -0
  404. package/eval/local/tasks/comet-noise-distractor/validation/test_noise_distractor.py +20 -0
  405. package/eval/local/tasks/comet-observability-env-template/environment/Dockerfile +15 -0
  406. package/eval/local/tasks/comet-observability-env-template/environment/env_writer.py +17 -0
  407. package/eval/local/tasks/comet-observability-env-template/environment/test_env_writer.py +17 -0
  408. package/eval/local/tasks/comet-observability-env-template/instruction.md +20 -0
  409. package/eval/local/tasks/comet-observability-env-template/task.toml +20 -0
  410. package/eval/local/tasks/comet-observability-env-template/validation/test_observability_env_template.py +46 -0
  411. package/eval/local/tasks/comet-perf-dedupe/environment/Dockerfile +39 -0
  412. package/eval/local/tasks/comet-perf-dedupe/environment/dedupe.py +22 -0
  413. package/eval/local/tasks/comet-perf-dedupe/environment/test_dedupe.py +43 -0
  414. package/eval/local/tasks/comet-perf-dedupe/instruction.md +25 -0
  415. package/eval/local/tasks/comet-perf-dedupe/task.toml +24 -0
  416. package/eval/local/tasks/comet-perf-dedupe/validation/test_perf_dedupe.py +40 -0
  417. package/eval/local/tasks/comet-persistence-threading/environment/Dockerfile +15 -0
  418. package/eval/local/tasks/comet-persistence-threading/environment/session_store.py +15 -0
  419. package/eval/local/tasks/comet-persistence-threading/environment/test_session_store.py +21 -0
  420. package/eval/local/tasks/comet-persistence-threading/instruction.md +14 -0
  421. package/eval/local/tasks/comet-persistence-threading/task.toml +20 -0
  422. package/eval/local/tasks/comet-persistence-threading/validation/test_persistence_threading.py +20 -0
  423. package/eval/local/tasks/comet-refactor-counter/environment/Dockerfile +39 -0
  424. package/eval/local/tasks/comet-refactor-counter/environment/test_text_processor.py +57 -0
  425. package/eval/local/tasks/comet-refactor-counter/environment/text_processor.py +49 -0
  426. package/eval/local/tasks/comet-refactor-counter/instruction.md +31 -0
  427. package/eval/local/tasks/comet-refactor-counter/task.toml +24 -0
  428. package/eval/local/tasks/comet-refactor-counter/validation/test_refactor_counter.py +75 -0
  429. package/eval/local/tasks/comet-robust-config/environment/Dockerfile +39 -0
  430. package/eval/local/tasks/comet-robust-config/environment/config_loader.py +56 -0
  431. package/eval/local/tasks/comet-robust-config/environment/test_config_loader.py +72 -0
  432. package/eval/local/tasks/comet-robust-config/instruction.md +30 -0
  433. package/eval/local/tasks/comet-robust-config/task.toml +24 -0
  434. package/eval/local/tasks/comet-robust-config/validation/test_robust_config.py +37 -0
  435. package/eval/local/tasks/generic-skill-smoke/environment/Dockerfile +2 -0
  436. package/eval/local/tasks/generic-skill-smoke/instruction.md +7 -0
  437. package/eval/local/tasks/generic-skill-smoke/task.toml +21 -0
  438. package/eval/local/tasks/generic-skill-smoke/validation/test_generic_skill_smoke.py +36 -0
  439. package/eval/local/tasks/index.yaml +155 -0
  440. package/eval/local/tasks/workflow-overlay-contract/environment/Dockerfile +5 -0
  441. package/eval/local/tasks/workflow-overlay-contract/instruction.md +5 -0
  442. package/eval/local/tasks/workflow-overlay-contract/task.toml +21 -0
  443. package/eval/local/tasks/workflow-overlay-contract/validation/test_workflow_overlay_contract.py +235 -0
  444. package/eval/local/tasks/workflow-route-conformance/environment/Dockerfile +2 -0
  445. package/eval/local/tasks/workflow-route-conformance/instruction.md +5 -0
  446. package/eval/local/tasks/workflow-route-conformance/task.toml +21 -0
  447. package/eval/local/tasks/workflow-route-conformance/validation/test_workflow_route_conformance.py +84 -0
  448. package/eval/local/tests/conftest.py +1148 -0
  449. package/eval/local/tests/scaffold/test_attribution.py +48 -0
  450. package/eval/local/tests/scaffold/test_compare_baselines.py +999 -0
  451. package/eval/local/tests/scaffold/test_conftest_helpers.py +534 -0
  452. package/eval/local/tests/scaffold/test_evidence.py +15 -0
  453. package/eval/local/tests/scaffold/test_langsmith_conftest.py +244 -0
  454. package/eval/local/tests/scaffold/test_logging.py +243 -0
  455. package/eval/local/tests/scaffold/test_manifests.py +132 -0
  456. package/eval/local/tests/scaffold/test_profiles.py +866 -0
  457. package/eval/local/tests/scaffold/test_regression_check.py +19 -0
  458. package/eval/local/tests/scaffold/test_report_style_demo_charts.py +45 -0
  459. package/eval/local/tests/scaffold/test_sample_quality.py +211 -0
  460. package/eval/local/tests/scaffold/test_tasks.py +168 -0
  461. package/eval/local/tests/scaffold/test_treatments.py +244 -0
  462. package/eval/local/tests/scaffold/test_utils.py +139 -0
  463. package/eval/local/tests/tasks/test_tasks.py +445 -0
  464. package/eval/local/tests/tasks/test_validation_scripts.py +143 -0
  465. package/eval/local/treatments/comet/comet_full_039.yaml +141 -0
  466. package/eval/local/treatments/comet/comet_full_040_beta.yaml +140 -0
  467. package/eval/local/treatments/common/control.yaml +4 -0
  468. package/eval/pyproject.toml +41 -0
  469. package/eval/report-html-config.json +6 -0
  470. package/eval/scaffold/__init__.py +67 -0
  471. package/eval/scaffold/python/__init__.py +95 -0
  472. package/eval/scaffold/python/attribution.py +43 -0
  473. package/eval/scaffold/python/evidence.py +38 -0
  474. package/eval/scaffold/python/external_data_handler.py +18 -0
  475. package/eval/scaffold/python/generic_llm_judge.py +235 -0
  476. package/eval/scaffold/python/judge_config.py +168 -0
  477. package/eval/scaffold/python/llm_judge.py +191 -0
  478. package/eval/scaffold/python/logging.py +705 -0
  479. package/eval/scaffold/python/manifests.py +129 -0
  480. package/eval/scaffold/python/paper_charts.py +25 -0
  481. package/eval/scaffold/python/pass_at_k.py +107 -0
  482. package/eval/scaffold/python/paths.py +56 -0
  483. package/eval/scaffold/python/profiles.py +127 -0
  484. package/eval/scaffold/python/report_outputs.py +1391 -0
  485. package/eval/scaffold/python/sample_quality.py +339 -0
  486. package/eval/scaffold/python/schema.py +39 -0
  487. package/eval/scaffold/python/skill_parser.py +469 -0
  488. package/eval/scaffold/python/tasks.py +330 -0
  489. package/eval/scaffold/python/treatments.py +271 -0
  490. package/eval/scaffold/python/utils.py +366 -0
  491. package/eval/scaffold/python/validation/__init__.py +21 -0
  492. package/eval/scaffold/python/validation/authoring_rubric.py +326 -0
  493. package/eval/scaffold/python/validation/comet_workflow.py +187 -0
  494. package/eval/scaffold/python/validation/core.py +264 -0
  495. package/eval/scaffold/python/validation/dataset.py +337 -0
  496. package/eval/scaffold/python/validation/docker.py +106 -0
  497. package/eval/scaffold/python/validation/evaluator.py +549 -0
  498. package/eval/scaffold/python/validation/generic_rubric.py +169 -0
  499. package/eval/scaffold/python/validation/rubric.py +740 -0
  500. package/eval/scaffold/python/validation/runner.py +237 -0
  501. package/eval/scaffold/python/validation/scripts.py +58 -0
  502. package/eval/scaffold/python/validation/tracing.py +313 -0
  503. package/eval/scaffold/shell/common.sh +126 -0
  504. package/eval/scaffold/shell/docker.sh +482 -0
  505. package/eval/scaffold/shell/run-claude-loop.sh +181 -0
  506. package/eval/scaffold/shell/setup.sh +259 -0
  507. package/eval/simulator-instruction.md +9 -0
  508. package/package.json +24 -2
@@ -0,0 +1,205 @@
1
+ import { randomUUID } from 'crypto';
2
+ import { promises as fs } from 'fs';
3
+ import os from 'os';
4
+ import path from 'path';
5
+ import { ensureDir } from '../fs/file-system.js';
6
+ export const PROJECT_REGISTRY_SCHEMA_VERSION = 1;
7
+ export class ProjectRegistryError extends Error {
8
+ code;
9
+ registryPath;
10
+ constructor(code, message, registryPath) {
11
+ super(message);
12
+ this.code = code;
13
+ this.registryPath = registryPath;
14
+ this.name = 'ProjectRegistryError';
15
+ }
16
+ }
17
+ function nowIso(options) {
18
+ return (options.now ?? new Date()).toISOString();
19
+ }
20
+ export function getProjectRegistryPath(homeDir = os.homedir()) {
21
+ return path.join(homeDir, '.comet', 'installations.json');
22
+ }
23
+ function emptyRegistry(updatedAt) {
24
+ return {
25
+ schemaVersion: PROJECT_REGISTRY_SCHEMA_VERSION,
26
+ updatedAt,
27
+ projects: [],
28
+ };
29
+ }
30
+ function isMissingRegistryFile(error) {
31
+ const code = error?.code;
32
+ return code === 'ENOENT' || code === 'ENOTDIR';
33
+ }
34
+ async function registryFileExists(registryPath) {
35
+ try {
36
+ await fs.access(registryPath);
37
+ return true;
38
+ }
39
+ catch (error) {
40
+ if (isMissingRegistryFile(error))
41
+ return false;
42
+ throw error;
43
+ }
44
+ }
45
+ function canonicalKey(canonicalPath) {
46
+ return process.platform === 'win32' ? canonicalPath.toLowerCase() : canonicalPath;
47
+ }
48
+ function isProjectRegistrySource(value) {
49
+ return value === 'init' || value === 'update' || value === 'repair';
50
+ }
51
+ function isProjectRegistryTarget(value) {
52
+ return (Boolean(value) &&
53
+ typeof value === 'object' &&
54
+ typeof value.platform === 'string' &&
55
+ (value.language === 'en' ||
56
+ value.language === 'zh'));
57
+ }
58
+ function assertProjectRegistry(value, registryPath) {
59
+ if (!value || typeof value !== 'object') {
60
+ throw new ProjectRegistryError('invalid-schema', 'Project registry must be a JSON object', registryPath);
61
+ }
62
+ const candidate = value;
63
+ if (candidate.schemaVersion !== PROJECT_REGISTRY_SCHEMA_VERSION) {
64
+ throw new ProjectRegistryError('invalid-schema', `Unsupported project registry schema version: ${String(candidate.schemaVersion)}`, registryPath);
65
+ }
66
+ if (typeof candidate.updatedAt !== 'string' || !Array.isArray(candidate.projects)) {
67
+ throw new ProjectRegistryError('invalid-schema', 'Project registry must contain updatedAt and projects', registryPath);
68
+ }
69
+ const projects = candidate.projects.map((entry, index) => {
70
+ if (!entry || typeof entry !== 'object') {
71
+ throw new ProjectRegistryError('invalid-schema', `Project registry entry ${index} must be an object`, registryPath);
72
+ }
73
+ const project = entry;
74
+ if (typeof project.path !== 'string' ||
75
+ typeof project.canonicalPath !== 'string' ||
76
+ typeof project.addedAt !== 'string' ||
77
+ typeof project.updatedAt !== 'string' ||
78
+ typeof project.lastSeenAt !== 'string' ||
79
+ !isProjectRegistrySource(project.lastSource) ||
80
+ !Array.isArray(project.lastTargets)) {
81
+ throw new ProjectRegistryError('invalid-schema', `Project registry entry ${index} has invalid fields`, registryPath);
82
+ }
83
+ return {
84
+ path: project.path,
85
+ canonicalPath: project.canonicalPath,
86
+ addedAt: project.addedAt,
87
+ updatedAt: project.updatedAt,
88
+ lastSeenAt: project.lastSeenAt,
89
+ lastSource: project.lastSource,
90
+ lastTargets: project.lastTargets.map((target, targetIndex) => {
91
+ if (!isProjectRegistryTarget(target)) {
92
+ throw new ProjectRegistryError('invalid-schema', `Project registry entry ${index} target ${targetIndex} has invalid fields`, registryPath);
93
+ }
94
+ return {
95
+ platform: target.platform,
96
+ language: target.language,
97
+ };
98
+ }),
99
+ };
100
+ });
101
+ return {
102
+ schemaVersion: PROJECT_REGISTRY_SCHEMA_VERSION,
103
+ updatedAt: candidate.updatedAt,
104
+ projects,
105
+ };
106
+ }
107
+ async function resolveProjectPath(projectPath) {
108
+ const resolved = path.resolve(projectPath);
109
+ try {
110
+ return {
111
+ path: resolved,
112
+ canonicalPath: await fs.realpath(resolved),
113
+ };
114
+ }
115
+ catch {
116
+ return {
117
+ path: resolved,
118
+ canonicalPath: resolved,
119
+ };
120
+ }
121
+ }
122
+ async function writeProjectRegistry(registry, registryPath) {
123
+ await ensureDir(path.dirname(registryPath));
124
+ const temporary = path.join(path.dirname(registryPath), `installations.${randomUUID()}.tmp`);
125
+ await fs.writeFile(temporary, `${JSON.stringify(registry, null, 2)}\n`, 'utf-8');
126
+ await fs.rename(temporary, registryPath);
127
+ }
128
+ export async function readProjectRegistry(options = {}) {
129
+ const registryPath = getProjectRegistryPath(options.homeDir);
130
+ const updatedAt = nowIso(options);
131
+ if (!(await registryFileExists(registryPath)))
132
+ return emptyRegistry(updatedAt);
133
+ let content;
134
+ try {
135
+ content = await fs.readFile(registryPath, 'utf-8');
136
+ }
137
+ catch (error) {
138
+ if (isMissingRegistryFile(error))
139
+ return emptyRegistry(updatedAt);
140
+ throw error;
141
+ }
142
+ let parsed;
143
+ try {
144
+ parsed = JSON.parse(content);
145
+ }
146
+ catch (error) {
147
+ if (options.strict) {
148
+ throw new ProjectRegistryError('invalid-json', `Project registry is invalid JSON: ${error.message}`, registryPath);
149
+ }
150
+ return emptyRegistry(updatedAt);
151
+ }
152
+ try {
153
+ return assertProjectRegistry(parsed, registryPath);
154
+ }
155
+ catch (error) {
156
+ if (options.strict)
157
+ throw error;
158
+ return emptyRegistry(updatedAt);
159
+ }
160
+ }
161
+ export async function listProjectRegistryEntries(options = {}) {
162
+ return (await readProjectRegistry(options)).projects;
163
+ }
164
+ export async function upsertProjectInstallation(projectPath, targets, source, options = {}) {
165
+ const registryPath = getProjectRegistryPath(options.homeDir);
166
+ const timestamp = nowIso(options);
167
+ const registry = await readProjectRegistry({ ...options, strict: false });
168
+ const resolved = await resolveProjectPath(projectPath);
169
+ const key = canonicalKey(resolved.canonicalPath);
170
+ const existing = registry.projects.find((entry) => canonicalKey(entry.canonicalPath) === key);
171
+ const entry = {
172
+ path: resolved.path,
173
+ canonicalPath: resolved.canonicalPath,
174
+ addedAt: existing?.addedAt ?? timestamp,
175
+ updatedAt: timestamp,
176
+ lastSeenAt: timestamp,
177
+ lastSource: source,
178
+ lastTargets: targets,
179
+ };
180
+ const projects = registry.projects.filter((project) => canonicalKey(project.canonicalPath) !== key);
181
+ projects.push(entry);
182
+ projects.sort((left, right) => left.path.localeCompare(right.path));
183
+ await writeProjectRegistry({
184
+ schemaVersion: PROJECT_REGISTRY_SCHEMA_VERSION,
185
+ updatedAt: timestamp,
186
+ projects,
187
+ }, registryPath);
188
+ return entry;
189
+ }
190
+ export async function removeProjectInstallation(projectPath, options = {}) {
191
+ const registryPath = getProjectRegistryPath(options.homeDir);
192
+ const registry = await readProjectRegistry({ ...options, strict: false });
193
+ const resolved = await resolveProjectPath(projectPath);
194
+ const key = canonicalKey(resolved.canonicalPath);
195
+ const projects = registry.projects.filter((project) => canonicalKey(project.canonicalPath) !== key);
196
+ if (projects.length === registry.projects.length)
197
+ return false;
198
+ await writeProjectRegistry({
199
+ schemaVersion: PROJECT_REGISTRY_SCHEMA_VERSION,
200
+ updatedAt: nowIso(options),
201
+ projects,
202
+ }, registryPath);
203
+ return true;
204
+ }
205
+ //# sourceMappingURL=project-registry.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"project-registry.js","sourceRoot":"","sources":["../../../platform/install/project-registry.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,QAAQ,CAAC;AACpC,OAAO,EAAE,QAAQ,IAAI,EAAE,EAAE,MAAM,IAAI,CAAC;AACpC,OAAO,EAAE,MAAM,IAAI,CAAC;AACpB,OAAO,IAAI,MAAM,MAAM,CAAC;AAExB,OAAO,EAAE,SAAS,EAAE,MAAM,sBAAsB,CAAC;AAEjD,MAAM,CAAC,MAAM,+BAA+B,GAAG,CAAC,CAAC;AAgCjD,MAAM,OAAO,oBAAqB,SAAQ,KAAK;IAE3B;IAEA;IAHlB,YACkB,IAA8B,EAC9C,OAAe,EACC,YAAoB;QAEpC,KAAK,CAAC,OAAO,CAAC,CAAC;QAJC,SAAI,GAAJ,IAAI,CAA0B;QAE9B,iBAAY,GAAZ,YAAY,CAAQ;QAGpC,IAAI,CAAC,IAAI,GAAG,sBAAsB,CAAC;IACrC,CAAC;CACF;AAED,SAAS,MAAM,CAAC,OAA+B;IAC7C,OAAO,CAAC,OAAO,CAAC,GAAG,IAAI,IAAI,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC;AACnD,CAAC;AAED,MAAM,UAAU,sBAAsB,CAAC,OAAO,GAAG,EAAE,CAAC,OAAO,EAAE;IAC3D,OAAO,IAAI,CAAC,IAAI,CAAC,OAAO,EAAE,QAAQ,EAAE,oBAAoB,CAAC,CAAC;AAC5D,CAAC;AAED,SAAS,aAAa,CAAC,SAAiB;IACtC,OAAO;QACL,aAAa,EAAE,+BAA+B;QAC9C,SAAS;QACT,QAAQ,EAAE,EAAE;KACb,CAAC;AACJ,CAAC;AAED,SAAS,qBAAqB,CAAC,KAAc;IAC3C,MAAM,IAAI,GAAI,KAA2C,EAAE,IAAI,CAAC;IAChE,OAAO,IAAI,KAAK,QAAQ,IAAI,IAAI,KAAK,SAAS,CAAC;AACjD,CAAC;AAED,KAAK,UAAU,kBAAkB,CAAC,YAAoB;IACpD,IAAI,CAAC;QACH,MAAM,EAAE,CAAC,MAAM,CAAC,YAAY,CAAC,CAAC;QAC9B,OAAO,IAAI,CAAC;IACd,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,IAAI,qBAAqB,CAAC,KAAK,CAAC;YAAE,OAAO,KAAK,CAAC;QAC/C,MAAM,KAAK,CAAC;IACd,CAAC;AACH,CAAC;AAED,SAAS,YAAY,CAAC,aAAqB;IACzC,OAAO,OAAO,CAAC,QAAQ,KAAK,OAAO,CAAC,CAAC,CAAC,aAAa,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,aAAa,CAAC;AACpF,CAAC;AAED,SAAS,uBAAuB,CAAC,KAAc;IAC7C,OAAO,KAAK,KAAK,MAAM,IAAI,KAAK,KAAK,QAAQ,IAAI,KAAK,KAAK,QAAQ,CAAC;AACtE,CAAC;AAED,SAAS,uBAAuB,CAAC,KAAc;IAC7C,OAAO,CACL,OAAO,CAAC,KAAK,CAAC;QACd,OAAO,KAAK,KAAK,QAAQ;QACzB,OAAQ,KAA+B,CAAC,QAAQ,KAAK,QAAQ;QAC7D,CAAE,KAA+B,CAAC,QAAQ,KAAK,IAAI;YAChD,KAA+B,CAAC,QAAQ,KAAK,IAAI,CAAC,CACtD,CAAC;AACJ,CAAC;AAED,SAAS,qBAAqB,CAAC,KAAc,EAAE,YAAoB;IACjE,IAAI,CAAC,KAAK,IAAI,OAAO,KAAK,KAAK,QAAQ,EAAE,CAAC;QACxC,MAAM,IAAI,oBAAoB,CAC5B,gBAAgB,EAChB,wCAAwC,EACxC,YAAY,CACb,CAAC;IACJ,CAAC;IACD,MAAM,SAAS,GAAG,KAA6E,CAAC;IAChG,IAAI,SAAS,CAAC,aAAa,KAAK,+BAA+B,EAAE,CAAC;QAChE,MAAM,IAAI,oBAAoB,CAC5B,gBAAgB,EAChB,gDAAgD,MAAM,CAAC,SAAS,CAAC,aAAa,CAAC,EAAE,EACjF,YAAY,CACb,CAAC;IACJ,CAAC;IACD,IAAI,OAAO,SAAS,CAAC,SAAS,KAAK,QAAQ,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,SAAS,CAAC,QAAQ,CAAC,EAAE,CAAC;QAClF,MAAM,IAAI,oBAAoB,CAC5B,gBAAgB,EAChB,sDAAsD,EACtD,YAAY,CACb,CAAC;IACJ,CAAC;IAED,MAAM,QAAQ,GAAG,SAAS,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,KAAK,EAAwB,EAAE;QAC7E,IAAI,CAAC,KAAK,IAAI,OAAO,KAAK,KAAK,QAAQ,EAAE,CAAC;YACxC,MAAM,IAAI,oBAAoB,CAC5B,gBAAgB,EAChB,0BAA0B,KAAK,oBAAoB,EACnD,YAAY,CACb,CAAC;QACJ,CAAC;QACD,MAAM,OAAO,GAAG,KAAsC,CAAC;QACvD,IACE,OAAO,OAAO,CAAC,IAAI,KAAK,QAAQ;YAChC,OAAO,OAAO,CAAC,aAAa,KAAK,QAAQ;YACzC,OAAO,OAAO,CAAC,OAAO,KAAK,QAAQ;YACnC,OAAO,OAAO,CAAC,SAAS,KAAK,QAAQ;YACrC,OAAO,OAAO,CAAC,UAAU,KAAK,QAAQ;YACtC,CAAC,uBAAuB,CAAC,OAAO,CAAC,UAAU,CAAC;YAC5C,CAAC,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,WAAW,CAAC,EACnC,CAAC;YACD,MAAM,IAAI,oBAAoB,CAC5B,gBAAgB,EAChB,0BAA0B,KAAK,qBAAqB,EACpD,YAAY,CACb,CAAC;QACJ,CAAC;QAED,OAAO;YACL,IAAI,EAAE,OAAO,CAAC,IAAI;YAClB,aAAa,EAAE,OAAO,CAAC,aAAa;YACpC,OAAO,EAAE,OAAO,CAAC,OAAO;YACxB,SAAS,EAAE,OAAO,CAAC,SAAS;YAC5B,UAAU,EAAE,OAAO,CAAC,UAAU;YAC9B,UAAU,EAAE,OAAO,CAAC,UAAU;YAC9B,WAAW,EAAE,OAAO,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,WAAW,EAAE,EAAE;gBAC3D,IAAI,CAAC,uBAAuB,CAAC,MAAM,CAAC,EAAE,CAAC;oBACrC,MAAM,IAAI,oBAAoB,CAC5B,gBAAgB,EAChB,0BAA0B,KAAK,WAAW,WAAW,qBAAqB,EAC1E,YAAY,CACb,CAAC;gBACJ,CAAC;gBAED,OAAO;oBACL,QAAQ,EAAE,MAAM,CAAC,QAAQ;oBACzB,QAAQ,EAAE,MAAM,CAAC,QAAQ;iBAC1B,CAAC;YACJ,CAAC,CAAC;SACH,CAAC;IACJ,CAAC,CAAC,CAAC;IAEH,OAAO;QACL,aAAa,EAAE,+BAA+B;QAC9C,SAAS,EAAE,SAAS,CAAC,SAAS;QAC9B,QAAQ;KACT,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,kBAAkB,CAAC,WAAmB;IAInD,MAAM,QAAQ,GAAG,IAAI,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;IAC3C,IAAI,CAAC;QACH,OAAO;YACL,IAAI,EAAE,QAAQ;YACd,aAAa,EAAE,MAAM,EAAE,CAAC,QAAQ,CAAC,QAAQ,CAAC;SAC3C,CAAC;IACJ,CAAC;IAAC,MAAM,CAAC;QACP,OAAO;YACL,IAAI,EAAE,QAAQ;YACd,aAAa,EAAE,QAAQ;SACxB,CAAC;IACJ,CAAC;AACH,CAAC;AAED,KAAK,UAAU,oBAAoB,CACjC,QAAyB,EACzB,YAAoB;IAEpB,MAAM,SAAS,CAAC,IAAI,CAAC,OAAO,CAAC,YAAY,CAAC,CAAC,CAAC;IAC5C,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,YAAY,CAAC,EAAE,iBAAiB,UAAU,EAAE,MAAM,CAAC,CAAC;IAC7F,MAAM,EAAE,CAAC,SAAS,CAAC,SAAS,EAAE,GAAG,IAAI,CAAC,SAAS,CAAC,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,OAAO,CAAC,CAAC;IACjF,MAAM,EAAE,CAAC,MAAM,CAAC,SAAS,EAAE,YAAY,CAAC,CAAC;AAC3C,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,mBAAmB,CACvC,UAAkC,EAAE;IAEpC,MAAM,YAAY,GAAG,sBAAsB,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC;IAC7D,MAAM,SAAS,GAAG,MAAM,CAAC,OAAO,CAAC,CAAC;IAClC,IAAI,CAAC,CAAC,MAAM,kBAAkB,CAAC,YAAY,CAAC,CAAC;QAAE,OAAO,aAAa,CAAC,SAAS,CAAC,CAAC;IAE/E,IAAI,OAAe,CAAC;IACpB,IAAI,CAAC;QACH,OAAO,GAAG,MAAM,EAAE,CAAC,QAAQ,CAAC,YAAY,EAAE,OAAO,CAAC,CAAC;IACrD,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,IAAI,qBAAqB,CAAC,KAAK,CAAC;YAAE,OAAO,aAAa,CAAC,SAAS,CAAC,CAAC;QAClE,MAAM,KAAK,CAAC;IACd,CAAC;IAED,IAAI,MAAe,CAAC;IACpB,IAAI,CAAC;QACH,MAAM,GAAG,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;IAC/B,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,IAAI,OAAO,CAAC,MAAM,EAAE,CAAC;YACnB,MAAM,IAAI,oBAAoB,CAC5B,cAAc,EACd,qCAAsC,KAAe,CAAC,OAAO,EAAE,EAC/D,YAAY,CACb,CAAC;QACJ,CAAC;QACD,OAAO,aAAa,CAAC,SAAS,CAAC,CAAC;IAClC,CAAC;IAED,IAAI,CAAC;QACH,OAAO,qBAAqB,CAAC,MAAM,EAAE,YAAY,CAAC,CAAC;IACrD,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,IAAI,OAAO,CAAC,MAAM;YAAE,MAAM,KAAK,CAAC;QAChC,OAAO,aAAa,CAAC,SAAS,CAAC,CAAC;IAClC,CAAC;AACH,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,0BAA0B,CAC9C,UAAkC,EAAE;IAEpC,OAAO,CAAC,MAAM,mBAAmB,CAAC,OAAO,CAAC,CAAC,CAAC,QAAQ,CAAC;AACvD,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,yBAAyB,CAC7C,WAAmB,EACnB,OAAgC,EAChC,MAA6B,EAC7B,UAAkC,EAAE;IAEpC,MAAM,YAAY,GAAG,sBAAsB,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC;IAC7D,MAAM,SAAS,GAAG,MAAM,CAAC,OAAO,CAAC,CAAC;IAClC,MAAM,QAAQ,GAAG,MAAM,mBAAmB,CAAC,EAAE,GAAG,OAAO,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,CAAC;IAC1E,MAAM,QAAQ,GAAG,MAAM,kBAAkB,CAAC,WAAW,CAAC,CAAC;IACvD,MAAM,GAAG,GAAG,YAAY,CAAC,QAAQ,CAAC,aAAa,CAAC,CAAC;IACjD,MAAM,QAAQ,GAAG,QAAQ,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,YAAY,CAAC,KAAK,CAAC,aAAa,CAAC,KAAK,GAAG,CAAC,CAAC;IAC9F,MAAM,KAAK,GAAyB;QAClC,IAAI,EAAE,QAAQ,CAAC,IAAI;QACnB,aAAa,EAAE,QAAQ,CAAC,aAAa;QACrC,OAAO,EAAE,QAAQ,EAAE,OAAO,IAAI,SAAS;QACvC,SAAS,EAAE,SAAS;QACpB,UAAU,EAAE,SAAS;QACrB,UAAU,EAAE,MAAM;QAClB,WAAW,EAAE,OAAO;KACrB,CAAC;IACF,MAAM,QAAQ,GAAG,QAAQ,CAAC,QAAQ,CAAC,MAAM,CACvC,CAAC,OAAO,EAAE,EAAE,CAAC,YAAY,CAAC,OAAO,CAAC,aAAa,CAAC,KAAK,GAAG,CACzD,CAAC;IACF,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IACrB,QAAQ,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC;IAEpE,MAAM,oBAAoB,CACxB;QACE,aAAa,EAAE,+BAA+B;QAC9C,SAAS,EAAE,SAAS;QACpB,QAAQ;KACT,EACD,YAAY,CACb,CAAC;IAEF,OAAO,KAAK,CAAC;AACf,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,yBAAyB,CAC7C,WAAmB,EACnB,UAAkC,EAAE;IAEpC,MAAM,YAAY,GAAG,sBAAsB,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC;IAC7D,MAAM,QAAQ,GAAG,MAAM,mBAAmB,CAAC,EAAE,GAAG,OAAO,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,CAAC;IAC1E,MAAM,QAAQ,GAAG,MAAM,kBAAkB,CAAC,WAAW,CAAC,CAAC;IACvD,MAAM,GAAG,GAAG,YAAY,CAAC,QAAQ,CAAC,aAAa,CAAC,CAAC;IACjD,MAAM,QAAQ,GAAG,QAAQ,CAAC,QAAQ,CAAC,MAAM,CACvC,CAAC,OAAO,EAAE,EAAE,CAAC,YAAY,CAAC,OAAO,CAAC,aAAa,CAAC,KAAK,GAAG,CACzD,CAAC;IACF,IAAI,QAAQ,CAAC,MAAM,KAAK,QAAQ,CAAC,QAAQ,CAAC,MAAM;QAAE,OAAO,KAAK,CAAC;IAE/D,MAAM,oBAAoB,CACxB;QACE,aAAa,EAAE,+BAA+B;QAC9C,SAAS,EAAE,MAAM,CAAC,OAAO,CAAC;QAC1B,QAAQ;KACT,EACD,YAAY,CACb,CAAC;IACF,OAAO,IAAI,CAAC;AACd,CAAC"}
package/eval/.env ADDED
@@ -0,0 +1,28 @@
1
+ # Local eval environment (generated; uses mimo proxy in lieu of native ANTHROPIC_API_KEY).
2
+ # Claude Code authenticates via the Anthropic-compatible proxy below.
3
+
4
+ # Anthropic-compatible proxy (mimo). Mirrors ~/.claude/settings.json env block.
5
+ ANTHROPIC_AUTH_TOKEN=tp-c0v2yajbthwu7ntb5reiaidghtdkr60dfm7dljdh7snbmxuw
6
+ ANTHROPIC_BASE_URL=https://token-plan-cn.xiaomimimo.com/anthropic
7
+ ANTHROPIC_MODEL=mimo-v2.5-pro
8
+ ANTHROPIC_DEFAULT_HAIKU_MODEL=mimo-v2.5
9
+ ANTHROPIC_DEFAULT_SONNET_MODEL=mimo-v2.5-pro
10
+ ANTHROPIC_DEFAULT_OPUS_MODEL=mimo-v2.5-pro
11
+ ANTHROPIC_DEFAULT_OPUS_MODEL_NAME=mimo-v2.5-pro
12
+ ANTHROPIC_DEFAULT_SONNET_MODEL_NAME=mimo-v2.5-pro
13
+ CLAUDE_CODE_SUBAGENT_MODEL=mimo-v2.5
14
+
15
+ # Optional Claude Code model override (leave blank to use ANTHROPIC_MODEL).
16
+ BENCH_CC_MODEL=
17
+ BENCH_CC_VERSION=latest
18
+
19
+ # LangSmith (left blank for local-only runs).
20
+ LANGSMITH_API_KEY=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
21
+ LANGSMITH_TRACING=true
22
+ TRACE_TO_LANGSMITH=true
23
+ LANGSMITH_ENDPOINT=https://api.smith.langchain.com
24
+ LANGSMITH_PROJECT=comet-skill-eval
25
+ BENCH_LLM_JUDGE=1
26
+ BENCH_JUDGE_MODEL=glm-5.2
27
+ BENCH_JUDGE_AUTH_TOKEN=70505c697ee343bba5d4480da6be4882.h7NoPY3zaEkETS4i
28
+ BENCH_JUDGE_BASE_URL=https://open.bigmodel.cn/api/anthropic
@@ -0,0 +1,52 @@
1
+ # Required for local and LangSmith eval runs unless ANTHROPIC_AUTH_TOKEN is set.
2
+ # Keep values commented when you prefer system environment variables.
3
+ # ANTHROPIC_API_KEY=
4
+
5
+ # Optional Claude Code model override.
6
+ # BENCH_CC_MODEL=
7
+ # BENCH_CC_VERSION=latest
8
+
9
+ # Optional: path to a custom user-simulator prompt for auto_user workflow evals.
10
+ # Relative paths resolve from eval/. Defaults to eval/simulator-instruction.md.
11
+ # BENCH_SIMULATOR_PROMPT_FILE=simulator-instruction.md
12
+
13
+ # Optional LLM-as-judge. Judge provider settings are intentionally separate
14
+ # from the subject agent's ANTHROPIC_* settings; BENCH_JUDGE_MODEL is required
15
+ # when BENCH_LLM_JUDGE=1.
16
+ # BENCH_LLM_JUDGE=1
17
+ # BENCH_JUDGE_MODEL=
18
+ # BENCH_JUDGE_AUTH_TOKEN=
19
+ # BENCH_JUDGE_BASE_URL=
20
+ # BENCH_JUDGE_API_KEY=
21
+
22
+ # Claude Code via Anthropic-compatible proxy (BigModel / mimo / OpenRouter etc.).
23
+ # When ANTHROPIC_API_KEY is unset, claude authenticates with these instead.
24
+ # ANTHROPIC_AUTH_TOKEN=
25
+ # ANTHROPIC_BASE_URL=
26
+ # ANTHROPIC_MODEL=
27
+ # ANTHROPIC_DEFAULT_HAIKU_MODEL=
28
+ # ANTHROPIC_DEFAULT_SONNET_MODEL=
29
+ # ANTHROPIC_DEFAULT_OPUS_MODEL=
30
+ # ANTHROPIC_DEFAULT_OPUS_MODEL_NAME=
31
+ # ANTHROPIC_DEFAULT_SONNET_MODEL_NAME=
32
+ # CLAUDE_CODE_SUBAGENT_MODEL=
33
+
34
+ # Required only for eval/langsmith.
35
+ # LANGSMITH_API_KEY=
36
+ # LANGSMITH_TRACING=true
37
+ # LANGSMITH_ENDPOINT=https://api.smith.langchain.com
38
+ # LANGSMITH_PROJECT=comet-skill-eval
39
+ # The Claude Code plugin variables (TRACE_TO_LANGSMITH and CC_LANGSMITH_*) are
40
+ # derived from the LANGSMITH_* settings by eval/langsmith/tests/conftest.py.
41
+
42
+ # Optional: name the LangSmith experiment (project) per treatment so CONTROL vs
43
+ # skill-injected runs compare in the experiment view.
44
+ # LANGSMITH_EXPERIMENT=COMET_FULL_040_BETA
45
+
46
+ # Optional trajectory tracing via the official langsmith-tracing Claude Code
47
+ # plugin. When LANGSMITH_TRACING=true, the LangSmith suite auto-builds the
48
+ # plugin into eval/.cache/langsmith-cc-plugin via node:20 and reuses that cache.
49
+ # Do not mount a Windows-host-built node_modules directory into the Linux eval container.
50
+ # Unset = rubric + comparison still logged, just without the nested trajectory.
51
+ # CC_LANGSMITH_PLUGIN_DIR=/abs/path/to/comet/eval/.cache/langsmith-cc-plugin
52
+ # CC_LANGSMITH_PLUGIN_AUTO_BUILD=true
package/eval/CLAUDE.md ADDED
@@ -0,0 +1,43 @@
1
+ # Comet Skill Evaluation
2
+
3
+ Benchmarks for evaluating the Comet skill workflow.
4
+
5
+ ## Structure
6
+
7
+ ```text
8
+ scaffold/ # Shared Python runner, Docker helpers, loaders, validators
9
+ local/ # Local suite: task corpus, treatments, skills, tests, logs
10
+ langsmith/ # LangSmith suite entrypoint and logs
11
+ ```
12
+
13
+ The LangSmith suite intentionally reuses `local/tasks`, `local/treatments`, and
14
+ `local/skills` through environment path overrides. Keep shared runtime code in
15
+ `scaffold/`; add suite-specific behavior under `local/` or `langsmith/`.
16
+
17
+ ## Running Local Eval
18
+
19
+ ```bash
20
+ uv run pytest local/tests/tasks/test_tasks.py --task=comet-hotfix --treatment=COMET_FULL_040_BETA -v
21
+ uv run pytest local/tests/tasks/test_tasks.py --task=comet-full-workflow --treatment=CONTROL,COMET_FULL_040_BETA -v
22
+ uv run pytest local/tests/tasks/test_tasks.py -v
23
+ ```
24
+
25
+ Local logs are written to `local/logs/experiments/`.
26
+
27
+ ## Running LangSmith Eval
28
+
29
+ ```bash
30
+ uv run pytest langsmith/tests/tasks/test_tasks.py --task=comet-hotfix --treatment=COMET_FULL_040_BETA -v
31
+ ```
32
+
33
+ LangSmith runs require `LANGSMITH_API_KEY` and write local reports to
34
+ `langsmith/logs/experiments/`.
35
+
36
+ ## Adding Tasks
37
+
38
+ For the default corpus, add tasks under `local/tasks/` and update
39
+ `local/tasks/index.yaml`. Add task-specific prompt, Docker environment, and
40
+ validation script together.
41
+
42
+ If a task should be LangSmith-only, create a dedicated `langsmith/tasks/` corpus
43
+ and set `BENCH_TASKS_DIR` in `langsmith/tests/conftest.py` accordingly.