@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 +1,235 @@
1
+ import json
2
+ import re
3
+ from pathlib import Path
4
+
5
+ import yaml
6
+
7
+ from scaffold.python.validation.core import load_test_context, write_test_results
8
+
9
+
10
+ HASH_RE = re.compile(r"^[a-f0-9]{64}$")
11
+
12
+
13
+ def _package_root(context: dict) -> Path:
14
+ raw = context.get("skill_package_path")
15
+ if not raw:
16
+ return Path(".")
17
+ path = Path(raw)
18
+ return path if path.is_absolute() else Path(".") / path
19
+
20
+
21
+ def _contains_evidence(actual: list[dict], expected: dict) -> bool:
22
+ return any(
23
+ item.get("node") == expected.get("node")
24
+ and item.get("check") == expected.get("check")
25
+ and (
26
+ "enforcement" not in expected
27
+ or expected.get("enforcement") is None
28
+ or item.get("enforcement") == expected.get("enforcement")
29
+ )
30
+ for item in actual
31
+ if isinstance(item, dict)
32
+ )
33
+
34
+
35
+ def _read_required_text(
36
+ package: Path,
37
+ relative_path: str,
38
+ passed: list[str],
39
+ failed: list[str],
40
+ ) -> str:
41
+ path = package / relative_path
42
+ if not path.exists():
43
+ failed.append(f"{relative_path} missing")
44
+ return ""
45
+ passed.append(f"{relative_path} present")
46
+ return path.read_text(encoding="utf-8")
47
+
48
+
49
+ def _require_markers(
50
+ text: str,
51
+ relative_path: str,
52
+ markers: list[tuple[str, str]],
53
+ passed: list[str],
54
+ failed: list[str],
55
+ ) -> None:
56
+ if not text:
57
+ return
58
+ missing = [label for label, marker in markers if marker not in text]
59
+ if missing:
60
+ failed.append(f"{relative_path} missing contract markers: {', '.join(missing)}")
61
+ else:
62
+ passed.append(f"{relative_path} declares required contract markers")
63
+
64
+
65
+ def _check_workflow_protocol(package: Path, passed: list[str], failed: list[str]) -> None:
66
+ protocol_text = _read_required_text(package, "reference/workflow-protocol.json", passed, failed)
67
+ if not protocol_text:
68
+ return
69
+ try:
70
+ protocol = json.loads(protocol_text)
71
+ except json.JSONDecodeError as exc:
72
+ failed.append(f"reference/workflow-protocol.json invalid: {exc}")
73
+ return
74
+
75
+ if protocol.get("kind") == "comet-five-phase-overlay":
76
+ passed.append("workflow protocol kind is comet-five-phase-overlay")
77
+ else:
78
+ failed.append(
79
+ "workflow protocol kind mismatch: expected comet-five-phase-overlay, "
80
+ f"got {protocol.get('kind')}"
81
+ )
82
+
83
+ nodes = protocol.get("nodes")
84
+ if isinstance(nodes, list) and nodes:
85
+ passed.append(f"workflow protocol declares {len(nodes)} node(s)")
86
+ else:
87
+ failed.append("workflow protocol nodes missing or empty")
88
+
89
+
90
+ def _check_runtime_scripts(package: Path, passed: list[str], failed: list[str]) -> None:
91
+ state = _read_required_text(package, "scripts/workflow-state.mjs", passed, failed)
92
+ _require_markers(
93
+ state,
94
+ "scripts/workflow-state.mjs",
95
+ [
96
+ ("activeCometChanges", "activeCometChanges"),
97
+ ("resolveCometOverlayChange", "resolveCometOverlayChange"),
98
+ ("sidecar workflow-evidence", "workflow-evidence"),
99
+ ("overlay protocol branch", "isCometOverlay(protocol)"),
100
+ ("init rejection branch", "command === 'init'"),
101
+ ("/comet-open guidance", "/comet-open"),
102
+ ],
103
+ passed,
104
+ failed,
105
+ )
106
+
107
+ guard = _read_required_text(package, "scripts/workflow-guard.mjs", passed, failed)
108
+ _require_markers(
109
+ guard,
110
+ "scripts/workflow-guard.mjs",
111
+ [
112
+ ("overlay evidence reader", "readOverlayEvidence"),
113
+ ("sidecar workflow-evidence", "workflow-evidence"),
114
+ ("augmentation enforcement", "missing augmentation evidence"),
115
+ ("unchanged Comet state message", "COMET STATE: unchanged"),
116
+ ],
117
+ passed,
118
+ failed,
119
+ )
120
+
121
+ handoff = _read_required_text(package, "scripts/workflow-handoff.mjs", passed, failed)
122
+ _require_markers(
123
+ handoff,
124
+ "scripts/workflow-handoff.mjs",
125
+ [
126
+ ("workflow protocol input", "workflow-protocol.json"),
127
+ ("workflow output field", "workflow: protocol.name"),
128
+ ("protocol nodes output", "protocol.nodes.map"),
129
+ ("required skill calls", "requiredSkillCalls"),
130
+ ("augmentations", "augmentations"),
131
+ ("output schemas", "outputSchemas"),
132
+ ],
133
+ passed,
134
+ failed,
135
+ )
136
+
137
+
138
+ def main():
139
+ context = load_test_context()
140
+ package = _package_root(context)
141
+ passed = []
142
+ failed = []
143
+
144
+ _check_workflow_protocol(package, passed, failed)
145
+ _check_runtime_scripts(package, passed, failed)
146
+
147
+ manifest_path = package / "comet" / "eval.yaml"
148
+ if not manifest_path.exists():
149
+ failed.append("comet/eval.yaml missing")
150
+ write_test_results({"passed": passed, "failed": failed})
151
+ return
152
+
153
+ try:
154
+ manifest = yaml.safe_load(manifest_path.read_text(encoding="utf-8")) or {}
155
+ passed.append("comet/eval.yaml parseable")
156
+ except yaml.YAMLError as exc:
157
+ failed.append(f"comet/eval.yaml invalid: {exc}")
158
+ write_test_results({"passed": passed, "failed": failed})
159
+ return
160
+
161
+ metadata = manifest.get("metadata") or {}
162
+ evaluation = manifest.get("evaluation") or {}
163
+
164
+ draft_hash = metadata.get("draftHash") or metadata.get("draft_hash")
165
+ expected_draft_hash = context.get("draft_hash")
166
+ if expected_draft_hash and draft_hash != expected_draft_hash:
167
+ failed.append("metadata.draftHash does not match manifest parser context")
168
+ elif isinstance(draft_hash, str) and HASH_RE.match(draft_hash):
169
+ passed.append("metadata.draftHash is stable sha256 hex")
170
+ else:
171
+ failed.append("metadata.draftHash missing or not 64 hex characters")
172
+
173
+ recommended = evaluation.get("recommendedTasks") or []
174
+ required_tasks = [
175
+ "workflow-overlay-contract",
176
+ "comet-full-workflow",
177
+ "comet-fix-median",
178
+ ]
179
+ missing_tasks = [task for task in required_tasks if task not in recommended]
180
+ if missing_tasks:
181
+ failed.append(f"recommendedTasks missing: {', '.join(missing_tasks)}")
182
+ else:
183
+ passed.append("recommendedTasks includes overlay contract suite")
184
+
185
+ baseline_treatments = evaluation.get("baselineTreatments") or []
186
+ expected_baselines = context.get("baseline_treatments") or ["CONTROL", "COMET_FULL_040_BETA"]
187
+ if baseline_treatments == expected_baselines:
188
+ passed.append("baselineTreatments match expected overlay baselines")
189
+ else:
190
+ failed.append(
191
+ f"baselineTreatments mismatch: expected {expected_baselines}, got {baseline_treatments}"
192
+ )
193
+
194
+ gates = evaluation.get("qualityGates") or {}
195
+ expected_gates = context.get("quality_gates") or {
196
+ "minWeightedScore": 0.8,
197
+ "minPassAt1": 0.6,
198
+ "maxInstabilityGap": 0.4,
199
+ }
200
+ if all(gates.get(key) == value for key, value in expected_gates.items()):
201
+ passed.append("qualityGates declare required minimums")
202
+ else:
203
+ failed.append(f"qualityGates mismatch: expected {expected_gates}, got {gates}")
204
+
205
+ required_schemas = evaluation.get("requiredOutputSchemas") or []
206
+ expected_schemas = context.get("required_output_schemas") or []
207
+ missing_schemas = [schema for schema in expected_schemas if schema not in required_schemas]
208
+ if missing_schemas:
209
+ failed.append(f"requiredOutputSchemas missing: {', '.join(missing_schemas)}")
210
+ elif not required_schemas:
211
+ failed.append("requiredOutputSchemas empty")
212
+ elif isinstance(required_schemas, list):
213
+ passed.append("requiredOutputSchemas present")
214
+ else:
215
+ failed.append("requiredOutputSchemas is not a list")
216
+
217
+ expected_evidence = evaluation.get("expectedEvidence") or []
218
+ context_evidence = context.get("expected_evidence") or []
219
+ missing_evidence = [
220
+ item for item in context_evidence if not _contains_evidence(expected_evidence, item)
221
+ ]
222
+ if missing_evidence:
223
+ failed.append(f"expectedEvidence missing checks: {missing_evidence}")
224
+ elif not expected_evidence:
225
+ failed.append("expectedEvidence empty")
226
+ elif isinstance(expected_evidence, list):
227
+ passed.append("expectedEvidence present")
228
+ else:
229
+ failed.append("expectedEvidence is not a list")
230
+
231
+ write_test_results({"passed": passed, "failed": failed})
232
+
233
+
234
+ if __name__ == "__main__":
235
+ main()
@@ -0,0 +1,2 @@
1
+ FROM python:3.11-slim
2
+ WORKDIR /workspace
@@ -0,0 +1,5 @@
1
+ Inspect the generated Skill package available in this eval run.
2
+
3
+ Confirm that the generated workflow route recorded in `reference/workflow-protocol.json`
4
+ matches the route declared in `comet/eval.yaml`, and that every generated internal
5
+ Node Skill exists beside the entry Skill package.
@@ -0,0 +1,21 @@
1
+ [metadata]
2
+ name = "workflow-route-conformance"
3
+ description = "Validate generated Skill workflow route metadata."
4
+ difficulty = "easy"
5
+ category = "generic"
6
+ tags = ["authoring", "skill", "comet-any", "route"]
7
+ default_treatments = ["CONTROL"]
8
+
9
+ [environment]
10
+ description = "Workspace for generated Skill route inspection."
11
+ dockerfile = "environment/Dockerfile"
12
+ timeout_sec = 600
13
+
14
+ [validation]
15
+ test_scripts = ["test_workflow_route_conformance.py"]
16
+ target_artifacts = []
17
+ timeout = 60
18
+
19
+ [evaluation]
20
+ profile = "authoring-skill"
21
+ expected_artifacts = []
@@ -0,0 +1,84 @@
1
+ import json
2
+ from pathlib import Path
3
+
4
+ from scaffold.python.validation.core import load_test_context, write_test_results
5
+
6
+
7
+ def _package_root(context: dict) -> Path:
8
+ raw = context.get("skill_package_path")
9
+ if not raw:
10
+ return Path(".")
11
+ path = Path(raw)
12
+ return path if path.is_absolute() else Path(".") / path
13
+
14
+
15
+ def _protocol_route(protocol: dict) -> list[str]:
16
+ return [
17
+ str(node.get("id"))
18
+ for node in protocol.get("nodes") or []
19
+ if isinstance(node, dict) and node.get("id") and not node.get("disabled")
20
+ ]
21
+
22
+
23
+ def main():
24
+ context = load_test_context()
25
+ package = _package_root(context)
26
+ expected_nodes = context.get("route_conformance_expected_node_order") or []
27
+ generated_node_skills = context.get("generated_node_skills") or []
28
+ passed = []
29
+ failed = []
30
+
31
+ if not expected_nodes:
32
+ failed.append("routeConformance expectedNodeOrder missing")
33
+ else:
34
+ passed.append(f"routeConformance declares {len(expected_nodes)} node(s)")
35
+
36
+ protocol_path = package / "reference" / "workflow-protocol.json"
37
+ if not protocol_path.exists():
38
+ failed.append("reference/workflow-protocol.json missing")
39
+ protocol_route = []
40
+ else:
41
+ try:
42
+ protocol_route = _protocol_route(json.loads(protocol_path.read_text(encoding="utf-8")))
43
+ passed.append("workflow-protocol.json parseable")
44
+ except json.JSONDecodeError as exc:
45
+ failed.append(f"workflow-protocol.json invalid: {exc}")
46
+ protocol_route = []
47
+
48
+ if expected_nodes and protocol_route == expected_nodes:
49
+ passed.append("workflow protocol route matches expectedNodeOrder")
50
+ elif expected_nodes:
51
+ failed.append(
52
+ f"workflow protocol route mismatch: expected {expected_nodes}, got {protocol_route}"
53
+ )
54
+
55
+ eval_manifest = package / "comet" / "eval.yaml"
56
+ if not eval_manifest.exists():
57
+ failed.append("comet/eval.yaml missing")
58
+ else:
59
+ text = eval_manifest.read_text(encoding="utf-8")
60
+ missing = [
61
+ item
62
+ for item in ["workflow-route-conformance", *expected_nodes, *generated_node_skills]
63
+ if item not in text
64
+ ]
65
+ if missing:
66
+ failed.append(f"comet/eval.yaml missing route entries: {', '.join(missing)}")
67
+ else:
68
+ passed.append("comet/eval.yaml lists route conformance task and Nodes")
69
+
70
+ missing_node_skills = [
71
+ node_skill
72
+ for node_skill in generated_node_skills
73
+ if not (package.parent / node_skill / "SKILL.md").exists()
74
+ ]
75
+ if missing_node_skills:
76
+ failed.append(f"internal Node Skill missing: {', '.join(missing_node_skills)}")
77
+ elif generated_node_skills:
78
+ passed.append("internal Node Skills present")
79
+
80
+ write_test_results({"passed": passed, "failed": failed})
81
+
82
+
83
+ if __name__ == "__main__":
84
+ main()