@hassangameryt/freeflow 0.3.0 → 0.5.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (692) hide show
  1. package/.claude-plugin/marketplace.json +4 -4
  2. package/.claude-plugin/plugin.json +6 -2
  3. package/.codex-plugin/plugin.json +9 -9
  4. package/README.md +190 -127
  5. package/assets/feedback-loop.png +0 -0
  6. package/assets/freeflow_workflow_map.png +0 -0
  7. package/assets/workflow.png +0 -0
  8. package/{skills → capabilities}/output-router/SKILL.md +21 -17
  9. package/{skills → capabilities}/output-router/references/safety-policy.md +1 -1
  10. package/capabilities/output-router/references/setup.md +110 -0
  11. package/command-surface.json +62 -7
  12. package/hooks/freeflow-runtime-context.mjs +572 -154
  13. package/hooks/hooks.json +26 -1
  14. package/hooks/tests/check-runtime-context-hook.sh +375 -0
  15. package/package.json +24 -24
  16. package/pi-extension/dist/index.js +264 -80
  17. package/pi-extension/dist/integrations/mcp-config.js +29 -0
  18. package/pi-extension/dist/output-router/host-producer-identification.js +232 -0
  19. package/pi-extension/dist/output-router/native-safety-net.js +216 -0
  20. package/pi-extension/dist/output-router/observed-tool-routing.js +122 -0
  21. package/pi-extension/dist/output-router/renderers.js +1023 -0
  22. package/pi-extension/dist/output-router/router-tools.js +554 -0
  23. package/pi-extension/dist/output-router/schemas.js +383 -0
  24. package/pi-extension/dist/output-router/status.js +744 -0
  25. package/pi-extension/dist/output-router/utils.js +502 -0
  26. package/pi-extension/dist/runtime/runtime-context.js +798 -0
  27. package/pi-extension/dist/settings/settings-tui.js +314 -0
  28. package/pi-extension/dist/settings/settings-ui.js +1487 -0
  29. package/pi-extension/freeflow/index.js +1 -0
  30. package/pi-extension/src/index.ts +230 -56
  31. package/pi-extension/src/{host-producer-identification.ts → output-router/host-producer-identification.ts} +37 -7
  32. package/pi-extension/src/{native-safety-net.ts → output-router/native-safety-net.ts} +8 -12
  33. package/pi-extension/src/{observed-tool-routing.ts → output-router/observed-tool-routing.ts} +19 -11
  34. package/pi-extension/src/{renderers.ts → output-router/renderers.ts} +246 -55
  35. package/pi-extension/src/{router-tools.ts → output-router/router-tools.ts} +130 -29
  36. package/pi-extension/src/{schemas.ts → output-router/schemas.ts} +171 -43
  37. package/pi-extension/src/output-router/status.ts +791 -0
  38. package/pi-extension/src/{utils.ts → output-router/utils.ts} +80 -18
  39. package/pi-extension/src/runtime/runtime-context.ts +895 -0
  40. package/pi-extension/src/settings/settings-tui.ts +408 -0
  41. package/pi-extension/src/settings/settings-ui.ts +1730 -0
  42. package/pi-extension/tests/integration/pi-extension.test.js +4020 -0
  43. package/pi-extension/tests/output-router/observed-producers.test.js +132 -0
  44. package/pi-extension/tests/output-router/search.test.js +722 -0
  45. package/pi-extension/tests/settings/settings-tui.test.js +243 -0
  46. package/router/dist/benchmarks/benchmark-harness.d.ts +16 -13
  47. package/router/dist/benchmarks/benchmark-harness.js +62 -62
  48. package/router/dist/benchmarks/benchmarks.d.ts +80 -73
  49. package/router/dist/benchmarks/benchmarks.js +860 -761
  50. package/router/dist/benchmarks/codex-qa-benchmarks.d.ts +71 -67
  51. package/router/dist/benchmarks/codex-qa-benchmarks.js +429 -390
  52. package/router/dist/benchmarks/command-benchmarks.d.ts +107 -92
  53. package/router/dist/benchmarks/command-benchmarks.js +616 -571
  54. package/router/dist/benchmarks/context-mode-normalized-benchmarks.d.ts +64 -56
  55. package/router/dist/benchmarks/context-mode-normalized-benchmarks.js +679 -613
  56. package/router/dist/benchmarks/context-mode-real-deep-benchmark.d.ts +103 -95
  57. package/router/dist/benchmarks/context-mode-real-deep-benchmark.js +1188 -1103
  58. package/router/dist/benchmarks/context-saving-baseline.d.ts +47 -41
  59. package/router/dist/benchmarks/context-saving-baseline.js +405 -374
  60. package/router/dist/benchmarks/index-benchmarks.d.ts +74 -69
  61. package/router/dist/benchmarks/index-benchmarks.js +761 -661
  62. package/router/dist/benchmarks/storage-policy-benchmarks.d.ts +80 -69
  63. package/router/dist/benchmarks/storage-policy-benchmarks.js +549 -469
  64. package/router/dist/benchmarks/vault-index-benchmarks.d.ts +43 -34
  65. package/router/dist/benchmarks/vault-index-benchmarks.js +294 -229
  66. package/router/dist/config/config.d.ts +62 -55
  67. package/router/dist/config/config.js +552 -373
  68. package/router/dist/config/router-contract.d.ts +2 -2
  69. package/router/dist/config/router-contract.js +38 -38
  70. package/router/dist/config/schema.d.ts +19 -10
  71. package/router/dist/config/schema.js +586 -538
  72. package/router/dist/config/types.d.ts +413 -361
  73. package/router/dist/config/types.js +19 -8
  74. package/router/dist/evidence/bounded-evidence.d.ts +26 -26
  75. package/router/dist/evidence/bounded-evidence.js +265 -252
  76. package/router/dist/evidence/evidence-range-selector.d.ts +16 -14
  77. package/router/dist/evidence/evidence-range-selector.js +192 -191
  78. package/router/dist/evidence/evidence-search.d.ts +18 -16
  79. package/router/dist/evidence/evidence-search.js +401 -377
  80. package/router/dist/evidence/evidence.d.ts +17 -17
  81. package/router/dist/evidence/evidence.js +163 -159
  82. package/router/dist/evidence/failure-contracts.d.ts +25 -15
  83. package/router/dist/evidence/failure-contracts.js +132 -126
  84. package/router/dist/evidence/line-ranges.d.ts +17 -15
  85. package/router/dist/evidence/line-ranges.js +18 -18
  86. package/router/dist/experiments/local-index.d.ts +47 -41
  87. package/router/dist/experiments/local-index.js +477 -458
  88. package/router/dist/local/local-traversal.d.ts +18 -0
  89. package/router/dist/local/local-traversal.js +334 -0
  90. package/router/dist/processing/engine.d.ts +94 -70
  91. package/router/dist/processing/engine.js +462 -364
  92. package/router/dist/processing/reducers.d.ts +208 -194
  93. package/router/dist/processing/reducers.js +1434 -1256
  94. package/router/dist/processing/renderers.d.ts +24 -18
  95. package/router/dist/processing/renderers.js +161 -152
  96. package/router/dist/processing/scripts.d.ts +80 -67
  97. package/router/dist/processing/scripts.js +343 -290
  98. package/router/dist/repo/repo-traversal.d.ts +9 -9
  99. package/router/dist/repo/repo-traversal.js +205 -202
  100. package/router/dist/routing/observed-reducers.d.ts +25 -19
  101. package/router/dist/routing/observed-reducers.js +559 -545
  102. package/router/dist/routing/observed-routing.d.ts +23 -14
  103. package/router/dist/routing/observed-routing.js +319 -318
  104. package/router/dist/routing/parsers.d.ts +10 -10
  105. package/router/dist/routing/parsers.js +454 -406
  106. package/router/dist/routing/run-filters.d.ts +45 -41
  107. package/router/dist/routing/run-filters.js +215 -207
  108. package/router/dist/routing/run-reducers.d.ts +45 -26
  109. package/router/dist/routing/run-reducers.js +102 -90
  110. package/router/dist/sandbox/adapter-roots.d.ts +34 -26
  111. package/router/dist/sandbox/adapter-roots.js +43 -41
  112. package/router/dist/sandbox/eryx-python-adapter.d.ts +9 -5
  113. package/router/dist/sandbox/eryx-python-adapter.js +659 -588
  114. package/router/dist/sandbox/jq-wasm-adapter.d.ts +3 -3
  115. package/router/dist/sandbox/jq-wasm-adapter.js +319 -311
  116. package/router/dist/sandbox/quickjs-wasi-adapter.d.ts +9 -5
  117. package/router/dist/sandbox/quickjs-wasi-adapter.js +336 -333
  118. package/router/dist/sandbox/script-sandbox.d.ts +105 -84
  119. package/router/dist/sandbox/script-sandbox.js +294 -260
  120. package/router/dist/setup/script-transform-adapters.d.ts +23 -19
  121. package/router/dist/setup/script-transform-adapters.js +223 -204
  122. package/router/dist/tools/batch.d.ts +27 -16
  123. package/router/dist/tools/batch.js +493 -416
  124. package/router/dist/tools/run.d.ts +47 -35
  125. package/router/dist/tools/run.js +1172 -1087
  126. package/router/dist/tools/search.d.ts +53 -31
  127. package/router/dist/tools/search.js +1224 -1065
  128. package/router/dist/transform/engine.d.ts +121 -96
  129. package/router/dist/transform/engine.js +1853 -1736
  130. package/router/dist/vault/vault-index.d.ts +97 -78
  131. package/router/dist/vault/vault-index.js +347 -342
  132. package/router/dist/vault/vault.d.ts +109 -74
  133. package/router/dist/vault/vault.js +528 -533
  134. package/runtime/interaction-contract.md +16 -0
  135. package/skills/bypass/SKILL.md +52 -38
  136. package/skills/commit-work/SKILL.md +54 -46
  137. package/skills/commit-work/references/staging-decisions.md +46 -24
  138. package/skills/decision-gate/SKILL.md +48 -0
  139. package/skills/design-for-depth/SKILL.md +75 -59
  140. package/skills/design-for-depth/references/design-pressure-signals.md +56 -7
  141. package/skills/design-for-depth/references/interface-design-loop.md +156 -0
  142. package/skills/design-for-depth/references/software-design-philosophy.md +32 -3
  143. package/skills/diagnose-failure/SKILL.md +65 -60
  144. package/skills/diagnose-failure/references/diagnostic-loop-catalog.md +36 -0
  145. package/skills/diagnose-failure/references/flaky-and-performance.md +30 -18
  146. package/skills/discuss/SKILL.md +121 -0
  147. package/skills/discuss/references/checkpoints.md +66 -0
  148. package/skills/evaluate-skill/SKILL.md +62 -53
  149. package/skills/evaluate-skill/references/definition-schema.md +345 -0
  150. package/skills/evaluate-skill/references/evaluation-design.md +86 -0
  151. package/skills/evaluate-skill/references/execution-and-evidence.md +85 -0
  152. package/skills/evaluate-skill/references/review-and-revision.md +51 -0
  153. package/skills/evaluate-skill/scripts/lib/definitions.mjs +296 -0
  154. package/skills/evaluate-skill/scripts/lib/evidence.mjs +46 -0
  155. package/skills/evaluate-skill/scripts/lib/grade-comparison.mjs +60 -0
  156. package/skills/evaluate-skill/scripts/lib/grade-interaction.mjs +148 -0
  157. package/skills/evaluate-skill/scripts/lib/grade-support.mjs +126 -0
  158. package/skills/evaluate-skill/scripts/lib/grade-workspace.mjs +192 -0
  159. package/skills/evaluate-skill/scripts/lib/grade.mjs +56 -0
  160. package/skills/evaluate-skill/scripts/lib/pi.mjs +489 -0
  161. package/skills/evaluate-skill/scripts/lib/process.mjs +79 -0
  162. package/skills/evaluate-skill/scripts/lib/rpc.mjs +444 -0
  163. package/skills/evaluate-skill/scripts/lib/runner.mjs +346 -0
  164. package/skills/evaluate-skill/scripts/lib/sandbox.mjs +409 -0
  165. package/skills/evaluate-skill/scripts/lib/view.mjs +337 -0
  166. package/skills/evaluate-skill/scripts/pi-guard.mjs +164 -0
  167. package/skills/evaluate-skill/scripts/skill-eval.mjs +101 -0
  168. package/skills/execute-work/SKILL.md +99 -0
  169. package/skills/execute-work/references/code-practices.md +78 -0
  170. package/skills/execute-work/references/execution-loop.md +77 -0
  171. package/skills/finish-branch/SKILL.md +117 -0
  172. package/skills/finish-branch/references/integration-options.md +80 -0
  173. package/skills/handoff/SKILL.md +65 -39
  174. package/skills/handoff/references/templates.md +104 -27
  175. package/skills/launch-work/SKILL.md +116 -0
  176. package/skills/launch-work/references/launch-readiness.md +85 -0
  177. package/skills/migration-work/SKILL.md +115 -0
  178. package/skills/migration-work/references/migration-lifecycle.md +82 -0
  179. package/skills/mode-contract/SKILL.md +72 -52
  180. package/skills/release-work/SKILL.md +118 -0
  181. package/skills/release-work/references/release-evidence.md +78 -0
  182. package/skills/review-artifact/SKILL.md +77 -69
  183. package/skills/review-artifact/references/reviewer-prompt.md +133 -42
  184. package/skills/review-work/SKILL.md +82 -57
  185. package/skills/review-work/references/reviewer-prompt.md +97 -60
  186. package/skills/review-work/references/security-risk-lens.md +67 -0
  187. package/skills/setup-freeflow/SKILL.md +54 -68
  188. package/skills/setup-freeflow/references/activation-contract.md +84 -69
  189. package/skills/setup-freeflow/references/host-setup.md +50 -17
  190. package/skills/simplify-code/SKILL.md +80 -0
  191. package/skills/simplify-code/references/simplification-patterns.md +70 -0
  192. package/skills/tdd/SKILL.md +96 -0
  193. package/skills/tdd/references/test-design.md +96 -0
  194. package/skills/track-work/SKILL.md +84 -0
  195. package/skills/track-work/references/working-record-schema.md +378 -0
  196. package/skills/verify-work/SKILL.md +59 -38
  197. package/skills/verify-work/references/browser-runtime-evidence.md +55 -0
  198. package/skills/verify-work/references/integration-evidence.md +51 -0
  199. package/skills/verify-work/references/performance-evidence.md +57 -0
  200. package/skills/workflow/SKILL.md +53 -59
  201. package/skills/workflow/references/domain-skill-composition.md +57 -0
  202. package/skills/workflow/references/workflow-loop.md +92 -0
  203. package/skills/write-plan/SKILL.md +85 -58
  204. package/skills/write-plan/references/plan-shapes.md +132 -46
  205. package/skills/write-skill/SKILL.md +82 -51
  206. package/skills/write-skill/references/activation-boundaries.md +62 -0
  207. package/skills/write-skill/references/agent-first-instructions.md +87 -0
  208. package/skills/write-skill/references/progressive-disclosure.md +63 -0
  209. package/skills/write-skill/scripts/lib/skill-author.mjs +653 -0
  210. package/skills/write-skill/scripts/skill-author.mjs +104 -0
  211. package/skills/write-spec/SKILL.md +65 -54
  212. package/skills/write-spec/references/artifact-standards.md +60 -41
  213. package/skills/write-spec/references/decision-records.md +77 -0
  214. package/skills/write-spec/references/spec-shapes.md +119 -60
  215. package/evals/README.md +0 -32
  216. package/evals/fixtures/copy-conventions.md +0 -31
  217. package/evals/fixtures/output-router/README.md +0 -12
  218. package/evals/fixtures/output-router/failed-command-output.txt +0 -9
  219. package/evals/fixtures/output-router/large-router-manual.md +0 -63
  220. package/evals/fixtures/output-router/native-large-output.txt +0 -40
  221. package/evals/fixtures/output-router/noisy-test-output.txt +0 -30
  222. package/evals/fixtures/output-router/verification-output.txt +0 -8
  223. package/evals/fixtures/tiny-artifact-review-app/README.md +0 -5
  224. package/evals/fixtures/tiny-artifact-review-app/docs/billing-policy.md +0 -10
  225. package/evals/fixtures/tiny-artifact-review-app/docs/specs/billing-webhook-api-draft.md +0 -21
  226. package/evals/fixtures/tiny-artifact-review-app/docs/specs/failed-payment-grace-period.md +0 -24
  227. package/evals/fixtures/tiny-artifact-review-app/docs/specs/immediate-downgrade.md +0 -17
  228. package/evals/fixtures/tiny-artifact-review-app/tests/billing.test.md +0 -8
  229. package/evals/fixtures/tiny-commit-ambiguous-app/.freeflow-eval-setup.sh +0 -15
  230. package/evals/fixtures/tiny-commit-ambiguous-app/README.md +0 -3
  231. package/evals/fixtures/tiny-commit-ambiguous-app/src/billing.ts +0 -5
  232. package/evals/fixtures/tiny-commit-ambiguous-app/src/settings-page.ts +0 -1
  233. package/evals/fixtures/tiny-commit-ambiguous-app/tests/settings.test.md +0 -5
  234. package/evals/fixtures/tiny-commit-app/.freeflow-eval-setup.sh +0 -14
  235. package/evals/fixtures/tiny-commit-app/README.md +0 -3
  236. package/evals/fixtures/tiny-commit-app/docs/specs/settings-title.md +0 -5
  237. package/evals/fixtures/tiny-commit-app/src/billing.ts +0 -5
  238. package/evals/fixtures/tiny-commit-app/src/settings-page.ts +0 -1
  239. package/evals/fixtures/tiny-commit-app/tests/settings.test.md +0 -5
  240. package/evals/fixtures/tiny-commit-everything-app/.freeflow-eval-setup.sh +0 -15
  241. package/evals/fixtures/tiny-commit-everything-app/README.md +0 -3
  242. package/evals/fixtures/tiny-commit-everything-app/docs/specs/settings-title.md +0 -5
  243. package/evals/fixtures/tiny-commit-everything-app/src/billing.ts +0 -5
  244. package/evals/fixtures/tiny-commit-everything-app/src/settings-page.ts +0 -1
  245. package/evals/fixtures/tiny-commit-everything-app/tests/settings.test.md +0 -5
  246. package/evals/fixtures/tiny-commit-staged-app/.freeflow-eval-setup.sh +0 -15
  247. package/evals/fixtures/tiny-commit-staged-app/README.md +0 -3
  248. package/evals/fixtures/tiny-commit-staged-app/docs/specs/settings-title.md +0 -5
  249. package/evals/fixtures/tiny-commit-staged-app/src/billing.ts +0 -5
  250. package/evals/fixtures/tiny-commit-staged-app/src/settings-page.ts +0 -1
  251. package/evals/fixtures/tiny-commit-staged-app/tests/settings.test.md +0 -5
  252. package/evals/fixtures/tiny-commit-staged-mixed-app/.freeflow-eval-setup.sh +0 -15
  253. package/evals/fixtures/tiny-commit-staged-mixed-app/README.md +0 -3
  254. package/evals/fixtures/tiny-commit-staged-mixed-app/docs/billing-policy.md +0 -3
  255. package/evals/fixtures/tiny-commit-staged-mixed-app/docs/release-notes.md +0 -3
  256. package/evals/fixtures/tiny-commit-staged-mixed-app/src/billing.ts +0 -5
  257. package/evals/fixtures/tiny-dashboard-stale-app/README.md +0 -11
  258. package/evals/fixtures/tiny-dashboard-stale-app/src/api-client.ts +0 -13
  259. package/evals/fixtures/tiny-dashboard-stale-app/src/dashboard-data.ts +0 -19
  260. package/evals/fixtures/tiny-dashboard-stale-app/tests/dashboard-data.test.md +0 -9
  261. package/evals/fixtures/tiny-decision-destination-app/README.md +0 -6
  262. package/evals/fixtures/tiny-decision-destination-app/src/risk.ts +0 -8
  263. package/evals/fixtures/tiny-decision-destination-app/tests/risk.test.md +0 -4
  264. package/evals/fixtures/tiny-design-depth-app/README.md +0 -15
  265. package/evals/fixtures/tiny-design-depth-app/src/routes.ts +0 -25
  266. package/evals/fixtures/tiny-design-depth-app/src/sendEmail.ts +0 -3
  267. package/evals/fixtures/tiny-design-depth-app/src/sendSms.ts +0 -3
  268. package/evals/fixtures/tiny-design-depth-app/src/telemetry.ts +0 -3
  269. package/evals/fixtures/tiny-design-depth-app/tests/routes.test.md +0 -12
  270. package/evals/fixtures/tiny-eval-method-app/README.md +0 -8
  271. package/evals/fixtures/tiny-eval-method-app/evals/reports/review-pr-eval-result.md +0 -5
  272. package/evals/fixtures/tiny-eval-method-app/evals/reports/triage-question-failure.md +0 -17
  273. package/evals/fixtures/tiny-eval-method-app/evals/runs/review-pr-with-skill-output.diff +0 -11
  274. package/evals/fixtures/tiny-eval-method-app/evals/runs/review-pr-with-skill-output.md +0 -3
  275. package/evals/fixtures/tiny-eval-method-app/skills/review-pr/SKILL.md +0 -10
  276. package/evals/fixtures/tiny-eval-method-app/skills/triage-question/SKILL.md +0 -10
  277. package/evals/fixtures/tiny-execute-plan-app/README.md +0 -5
  278. package/evals/fixtures/tiny-execute-plan-app/checks/settings-and-billing-check.sh +0 -5
  279. package/evals/fixtures/tiny-execute-plan-app/docs/billing-policy.md +0 -10
  280. package/evals/fixtures/tiny-execute-plan-app/docs/plans/immediate-downgrade-plan.md +0 -11
  281. package/evals/fixtures/tiny-execute-plan-app/docs/plans/settings-title-plan.md +0 -12
  282. package/evals/fixtures/tiny-execute-plan-app/docs/plans/settings-title-with-bad-check.md +0 -15
  283. package/evals/fixtures/tiny-execute-plan-app/docs/plans/unverified-billing-plan.md +0 -9
  284. package/evals/fixtures/tiny-execute-plan-app/docs/specs/failed-payment-grace-period.md +0 -9
  285. package/evals/fixtures/tiny-execute-plan-app/docs/specs/settings-title.md +0 -9
  286. package/evals/fixtures/tiny-execute-plan-app/src/billing.ts +0 -7
  287. package/evals/fixtures/tiny-execute-plan-app/src/settings-page.ts +0 -1
  288. package/evals/fixtures/tiny-execute-plan-app/tests/billing.test.md +0 -7
  289. package/evals/fixtures/tiny-execute-plan-app/tests/settings.test.md +0 -5
  290. package/evals/fixtures/tiny-execute-review-loop-app/README.md +0 -5
  291. package/evals/fixtures/tiny-execute-review-loop-app/docs/billing-policy.md +0 -9
  292. package/evals/fixtures/tiny-execute-review-loop-app/docs/plans/settings-title-plan.md +0 -12
  293. package/evals/fixtures/tiny-execute-review-loop-app/docs/review/previous-agent-summary.md +0 -15
  294. package/evals/fixtures/tiny-execute-review-loop-app/docs/review/review-pass-1-non-pass.md +0 -11
  295. package/evals/fixtures/tiny-execute-review-loop-app/docs/specs/settings-title.md +0 -9
  296. package/evals/fixtures/tiny-execute-review-loop-app/src/billing.ts +0 -7
  297. package/evals/fixtures/tiny-execute-review-loop-app/src/settings-page.ts +0 -1
  298. package/evals/fixtures/tiny-execute-review-loop-app/tests/billing.test.md +0 -7
  299. package/evals/fixtures/tiny-execute-review-loop-app/tests/settings.test.md +0 -5
  300. package/evals/fixtures/tiny-flaky-session-app/README.md +0 -10
  301. package/evals/fixtures/tiny-flaky-session-app/src/session-timeout.ts +0 -13
  302. package/evals/fixtures/tiny-flaky-session-app/tests/session-timeout.test.md +0 -8
  303. package/evals/fixtures/tiny-handoff-app/README.md +0 -5
  304. package/evals/fixtures/tiny-handoff-app/docs/billing-policy.md +0 -10
  305. package/evals/fixtures/tiny-handoff-app/docs/handoffs/old-agent-handoff.md +0 -8
  306. package/evals/fixtures/tiny-handoff-app/docs/plans/billing-retry-plan.md +0 -11
  307. package/evals/fixtures/tiny-handoff-app/src/billing.ts +0 -7
  308. package/evals/fixtures/tiny-handoff-report-app/README.md +0 -3
  309. package/evals/fixtures/tiny-handoff-report-app/evals/runs/handoff-3/hof-003/with-skill-output.diff +0 -1
  310. package/evals/fixtures/tiny-handoff-report-app/evals/runs/handoff-3/hof-003/with-skill-output.md +0 -1
  311. package/evals/fixtures/tiny-handoff-report-app/evals/scores/hof-003-score.txt +0 -4
  312. package/evals/fixtures/tiny-plan-app/README.md +0 -5
  313. package/evals/fixtures/tiny-plan-app/docs/billing-policy.md +0 -10
  314. package/evals/fixtures/tiny-plan-app/docs/specs/failed-payment-grace-period.md +0 -25
  315. package/evals/fixtures/tiny-plan-app/src/billing.ts +0 -17
  316. package/evals/fixtures/tiny-plan-app/src/settings-page.ts +0 -1
  317. package/evals/fixtures/tiny-plan-app/tests/billing.test.md +0 -8
  318. package/evals/fixtures/tiny-plan-app/tests/settings.test.md +0 -5
  319. package/evals/fixtures/tiny-plan-strict-api-app/README.md +0 -3
  320. package/evals/fixtures/tiny-plan-strict-api-app/docs/billing-policy.md +0 -5
  321. package/evals/fixtures/tiny-plan-strict-api-app/docs/specs/billing-webhook-api.md +0 -25
  322. package/evals/fixtures/tiny-plan-strict-api-app/src/billing.ts +0 -5
  323. package/evals/fixtures/tiny-plan-strict-api-app/src/webhooks.ts +0 -3
  324. package/evals/fixtures/tiny-plan-strict-api-app/tests/billing-webhook.test.md +0 -8
  325. package/evals/fixtures/tiny-post-setup-invalid-config-app/.freeflow/config.json +0 -3
  326. package/evals/fixtures/tiny-post-setup-invalid-config-app/AGENTS.md +0 -15
  327. package/evals/fixtures/tiny-post-setup-invalid-config-app/README.md +0 -16
  328. package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/auth-review.md +0 -15
  329. package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/billing-policy.md +0 -10
  330. package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/copy-conventions.md +0 -15
  331. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/auth-middleware.ts +0 -12
  332. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/billing.ts +0 -20
  333. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/login-copy.ts +0 -1
  334. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/settings-page.ts +0 -1
  335. package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/auth-middleware.test.md +0 -8
  336. package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/billing.test.md +0 -8
  337. package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/copy.test.md +0 -7
  338. package/evals/fixtures/tiny-post-setup-missing-config-app/AGENTS.md +0 -15
  339. package/evals/fixtures/tiny-post-setup-missing-config-app/README.md +0 -16
  340. package/evals/fixtures/tiny-post-setup-missing-config-app/docs/auth-review.md +0 -15
  341. package/evals/fixtures/tiny-post-setup-missing-config-app/docs/billing-policy.md +0 -10
  342. package/evals/fixtures/tiny-post-setup-missing-config-app/docs/copy-conventions.md +0 -15
  343. package/evals/fixtures/tiny-post-setup-missing-config-app/src/auth-middleware.ts +0 -12
  344. package/evals/fixtures/tiny-post-setup-missing-config-app/src/billing.ts +0 -20
  345. package/evals/fixtures/tiny-post-setup-missing-config-app/src/login-copy.ts +0 -1
  346. package/evals/fixtures/tiny-post-setup-missing-config-app/src/settings-page.ts +0 -1
  347. package/evals/fixtures/tiny-post-setup-missing-config-app/tests/auth-middleware.test.md +0 -8
  348. package/evals/fixtures/tiny-post-setup-missing-config-app/tests/billing.test.md +0 -8
  349. package/evals/fixtures/tiny-post-setup-missing-config-app/tests/copy.test.md +0 -7
  350. package/evals/fixtures/tiny-post-setup-source-conflict-app/.freeflow/config.json +0 -3
  351. package/evals/fixtures/tiny-post-setup-source-conflict-app/AGENTS.md +0 -15
  352. package/evals/fixtures/tiny-post-setup-source-conflict-app/README.md +0 -16
  353. package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/auth-review.md +0 -15
  354. package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/billing-policy.md +0 -10
  355. package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/copy-conventions.md +0 -15
  356. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/auth-middleware.ts +0 -12
  357. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/billing.ts +0 -20
  358. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/login-copy.ts +0 -1
  359. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/settings-page.ts +0 -1
  360. package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/auth-middleware.test.md +0 -8
  361. package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/billing.test.md +0 -8
  362. package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/copy.test.md +0 -7
  363. package/evals/fixtures/tiny-report-performance-app/README.md +0 -11
  364. package/evals/fixtures/tiny-report-performance-app/docs/performance.md +0 -10
  365. package/evals/fixtures/tiny-report-performance-app/src/report-summary.ts +0 -29
  366. package/evals/fixtures/tiny-report-performance-app/tests/report-performance.test.md +0 -8
  367. package/evals/fixtures/tiny-review-request-app/README.md +0 -3
  368. package/evals/fixtures/tiny-review-request-app/docs/billing-policy.md +0 -5
  369. package/evals/fixtures/tiny-review-request-app/docs/plans/billing-webhook-api.md +0 -19
  370. package/evals/fixtures/tiny-review-request-app/docs/review/previous-agent-summary.md +0 -20
  371. package/evals/fixtures/tiny-review-request-app/docs/specs/billing-webhook-api.md +0 -25
  372. package/evals/fixtures/tiny-review-request-app/src/billing.ts +0 -11
  373. package/evals/fixtures/tiny-review-request-app/src/webhooks.ts +0 -19
  374. package/evals/fixtures/tiny-review-request-app/tests/billing-webhook.test.md +0 -8
  375. package/evals/fixtures/tiny-review-work-app/README.md +0 -5
  376. package/evals/fixtures/tiny-review-work-app/docs/billing-policy.md +0 -9
  377. package/evals/fixtures/tiny-review-work-app/docs/plans/settings-title-plan.md +0 -12
  378. package/evals/fixtures/tiny-review-work-app/docs/review/previous-agent-summary.md +0 -15
  379. package/evals/fixtures/tiny-review-work-app/docs/specs/settings-title.md +0 -9
  380. package/evals/fixtures/tiny-review-work-app/src/billing.ts +0 -7
  381. package/evals/fixtures/tiny-review-work-app/src/settings-page.ts +0 -1
  382. package/evals/fixtures/tiny-review-work-app/tests/billing.test.md +0 -7
  383. package/evals/fixtures/tiny-review-work-app/tests/settings.test.md +0 -5
  384. package/evals/fixtures/tiny-saas-app/README.md +0 -16
  385. package/evals/fixtures/tiny-saas-app/docs/auth-review.md +0 -15
  386. package/evals/fixtures/tiny-saas-app/docs/billing-policy.md +0 -10
  387. package/evals/fixtures/tiny-saas-app/docs/copy-conventions.md +0 -15
  388. package/evals/fixtures/tiny-saas-app/docs/specs/settings-title.md +0 -13
  389. package/evals/fixtures/tiny-saas-app/src/auth-middleware.ts +0 -12
  390. package/evals/fixtures/tiny-saas-app/src/billing.ts +0 -20
  391. package/evals/fixtures/tiny-saas-app/src/login-copy.ts +0 -1
  392. package/evals/fixtures/tiny-saas-app/src/settings-page.ts +0 -1
  393. package/evals/fixtures/tiny-saas-app/tests/auth-middleware.test.md +0 -8
  394. package/evals/fixtures/tiny-saas-app/tests/billing.test.md +0 -8
  395. package/evals/fixtures/tiny-saas-app/tests/copy.test.md +0 -7
  396. package/evals/fixtures/tiny-setup-agents-app/AGENTS.md +0 -6
  397. package/evals/fixtures/tiny-setup-both-app/AGENTS.md +0 -5
  398. package/evals/fixtures/tiny-setup-both-app/CLAUDE.md +0 -5
  399. package/evals/fixtures/tiny-setup-claude-app/CLAUDE.md +0 -6
  400. package/evals/fixtures/tiny-setup-codex-rules-app/.codex/rules/shell.rules +0 -5
  401. package/evals/fixtures/tiny-setup-codex-rules-app/AGENTS.md +0 -6
  402. package/evals/fixtures/tiny-setup-conflict-app/AGENTS.md +0 -6
  403. package/evals/fixtures/tiny-setup-existing-block-app/AGENTS.md +0 -14
  404. package/evals/fixtures/tiny-setup-four-rules-app/CLAUDE.md +0 -6
  405. package/evals/fixtures/tiny-skill-dev-app/README.md +0 -10
  406. package/evals/fixtures/tiny-skill-dev-app/evals/prompts/review-pr-001.txt +0 -8
  407. package/evals/fixtures/tiny-skill-dev-app/evals/reports/review-pr-failure.md +0 -17
  408. package/evals/fixtures/tiny-skill-dev-app/skills/review-pr/SKILL.md +0 -13
  409. package/evals/fixtures/tiny-team-app/README.md +0 -5
  410. package/evals/fixtures/tiny-team-app/docs/product.md +0 -6
  411. package/evals/fixtures/tiny-team-app/src/teams.ts +0 -9
  412. package/evals/fixtures/tiny-team-app/src/users.ts +0 -5
  413. package/evals/fixtures/tiny-team-app/tests/teams.test.md +0 -7
  414. package/evals/fixtures/tiny-verify-app/README.md +0 -5
  415. package/evals/fixtures/tiny-verify-app/src/settings-nav.ts +0 -1
  416. package/evals/fixtures/tiny-verify-app/src/settings-page.ts +0 -1
  417. package/evals/fixtures/tiny-verify-app/tests/settings.test.md +0 -7
  418. package/evals/prompts/aon-001.txt +0 -2
  419. package/evals/prompts/byp-001.txt +0 -2
  420. package/evals/prompts/byp-002.txt +0 -2
  421. package/evals/prompts/cap-001.txt +0 -3
  422. package/evals/prompts/cap-002.txt +0 -3
  423. package/evals/prompts/cmd-001.txt +0 -3
  424. package/evals/prompts/cmd-002.txt +0 -3
  425. package/evals/prompts/cmd-003.txt +0 -6
  426. package/evals/prompts/cmd-004.txt +0 -5
  427. package/evals/prompts/cmd-005.txt +0 -5
  428. package/evals/prompts/cmd-006.txt +0 -5
  429. package/evals/prompts/cmd-007.txt +0 -5
  430. package/evals/prompts/cmd-008.txt +0 -5
  431. package/evals/prompts/cmd-009.txt +0 -8
  432. package/evals/prompts/cmd-010.txt +0 -5
  433. package/evals/prompts/cmd-011.txt +0 -5
  434. package/evals/prompts/cmd-012.txt +0 -5
  435. package/evals/prompts/cmd-013.txt +0 -5
  436. package/evals/prompts/cmd-014.txt +0 -7
  437. package/evals/prompts/cmd-015.txt +0 -7
  438. package/evals/prompts/cmd-016.txt +0 -5
  439. package/evals/prompts/cmt-001.txt +0 -1
  440. package/evals/prompts/cmt-002.txt +0 -1
  441. package/evals/prompts/cmt-003.txt +0 -1
  442. package/evals/prompts/cmt-004.txt +0 -1
  443. package/evals/prompts/cmt-005.txt +0 -1
  444. package/evals/prompts/dfd-001.txt +0 -3
  445. package/evals/prompts/dia-001.txt +0 -3
  446. package/evals/prompts/dia-002.txt +0 -3
  447. package/evals/prompts/dia-003.txt +0 -3
  448. package/evals/prompts/dis-001.txt +0 -5
  449. package/evals/prompts/dis-002.txt +0 -5
  450. package/evals/prompts/esk-001.txt +0 -5
  451. package/evals/prompts/esk-002.txt +0 -5
  452. package/evals/prompts/esk-003.txt +0 -5
  453. package/evals/prompts/grc-001.txt +0 -3
  454. package/evals/prompts/hof-001.txt +0 -3
  455. package/evals/prompts/hof-002.txt +0 -1
  456. package/evals/prompts/hof-003.txt +0 -1
  457. package/evals/prompts/hof-004.txt +0 -1
  458. package/evals/prompts/hof-005.txt +0 -1
  459. package/evals/prompts/ivg-001.txt +0 -1
  460. package/evals/prompts/ivg-002.txt +0 -11
  461. package/evals/prompts/ivg-003.txt +0 -1
  462. package/evals/prompts/ivg-004.txt +0 -1
  463. package/evals/prompts/mode-001.txt +0 -3
  464. package/evals/prompts/mode-002.txt +0 -1
  465. package/evals/prompts/mode-003.txt +0 -3
  466. package/evals/prompts/mode-004.txt +0 -3
  467. package/evals/prompts/mode-005.txt +0 -3
  468. package/evals/prompts/mode-006.txt +0 -3
  469. package/evals/prompts/mode-007.txt +0 -3
  470. package/evals/prompts/otr-001.txt +0 -3
  471. package/evals/prompts/otr-002.txt +0 -3
  472. package/evals/prompts/rar-001.txt +0 -5
  473. package/evals/prompts/rar-002.txt +0 -3
  474. package/evals/prompts/rar-003.txt +0 -6
  475. package/evals/prompts/rar-004.txt +0 -15
  476. package/evals/prompts/rar-005.txt +0 -10
  477. package/evals/prompts/rbr-001.txt +0 -3
  478. package/evals/prompts/rbr-002.txt +0 -3
  479. package/evals/prompts/rbr-003.txt +0 -7
  480. package/evals/prompts/rev-001.txt +0 -3
  481. package/evals/prompts/rev-002.txt +0 -5
  482. package/evals/prompts/rev-003.txt +0 -6
  483. package/evals/prompts/rev-004.txt +0 -1
  484. package/evals/prompts/rev-005.txt +0 -15
  485. package/evals/prompts/rev-006.txt +0 -5
  486. package/evals/prompts/stp-001.txt +0 -1
  487. package/evals/prompts/stp-002.txt +0 -1
  488. package/evals/prompts/stp-003.txt +0 -1
  489. package/evals/prompts/stp-004.txt +0 -1
  490. package/evals/prompts/stp-005.txt +0 -1
  491. package/evals/prompts/stp-006.txt +0 -1
  492. package/evals/prompts/stp-007.txt +0 -1
  493. package/evals/prompts/stp-008.txt +0 -1
  494. package/evals/prompts/stp-009.txt +0 -1
  495. package/evals/prompts/stp-010.txt +0 -1
  496. package/evals/prompts/stp-011.txt +0 -1
  497. package/evals/prompts/vfy-003.txt +0 -1
  498. package/evals/prompts/wpl-001.txt +0 -3
  499. package/evals/prompts/wpl-002.txt +0 -5
  500. package/evals/prompts/wpl-003.txt +0 -3
  501. package/evals/prompts/wpl-004.txt +0 -5
  502. package/evals/prompts/wpl-005.txt +0 -1
  503. package/evals/prompts/wrc-001.txt +0 -10
  504. package/evals/prompts/wrc-002.txt +0 -3
  505. package/evals/prompts/wsk-001.txt +0 -6
  506. package/evals/prompts/wsp-001.txt +0 -5
  507. package/evals/prompts/wsp-002.txt +0 -15
  508. package/evals/prompts/wsp-003.txt +0 -3
  509. package/evals/prompts/wsp-004.txt +0 -15
  510. package/evals/prompts/wsp-005.txt +0 -5
  511. package/evals/prompts/wsp-006.txt +0 -12
  512. package/evals/prompts/wsp-007.txt +0 -9
  513. package/evals/prompts/wsp-008.txt +0 -13
  514. package/evals/prompts/xpl-001.txt +0 -1
  515. package/evals/prompts/xpl-002.txt +0 -3
  516. package/evals/prompts/xpl-003.txt +0 -3
  517. package/evals/prompts/xpl-004.txt +0 -3
  518. package/evals/prompts/xpl-005.txt +0 -5
  519. package/evals/prompts/xpl-006.txt +0 -3
  520. package/evals/registries/adversarial-evals.json +0 -39
  521. package/evals/registries/fixture-evals.json +0 -2513
  522. package/evals/registries/handoff-evals.json +0 -74
  523. package/evals/registries/legacy-evals.json +0 -147
  524. package/evals/registries/skill-evidence.json +0 -193
  525. package/evals/registries/verify-work-evals.json +0 -46
  526. package/evals/reports/acceptance/v0.1-acceptance-report.md +0 -130
  527. package/evals/reports/by-command-surface/command-surface-1-report.md +0 -45
  528. package/evals/reports/by-command-surface/command-surface-10-report.md +0 -76
  529. package/evals/reports/by-command-surface/command-surface-11-report.md +0 -77
  530. package/evals/reports/by-command-surface/command-surface-12-report.md +0 -91
  531. package/evals/reports/by-command-surface/command-surface-13-report.md +0 -64
  532. package/evals/reports/by-command-surface/command-surface-14-report.md +0 -66
  533. package/evals/reports/by-command-surface/command-surface-15-report.md +0 -124
  534. package/evals/reports/by-command-surface/command-surface-16-report.md +0 -39
  535. package/evals/reports/by-command-surface/command-surface-2-report.md +0 -80
  536. package/evals/reports/by-command-surface/command-surface-3-report.md +0 -86
  537. package/evals/reports/by-command-surface/command-surface-4-report.md +0 -76
  538. package/evals/reports/by-command-surface/command-surface-5-report.md +0 -80
  539. package/evals/reports/by-command-surface/command-surface-6-report.md +0 -74
  540. package/evals/reports/by-command-surface/command-surface-7-report.md +0 -84
  541. package/evals/reports/by-command-surface/command-surface-8-report.md +0 -79
  542. package/evals/reports/by-command-surface/command-surface-9-report.md +0 -79
  543. package/evals/reports/by-command-surface/command-surface-matrix.md +0 -91
  544. package/evals/reports/by-skill/bypass-1-report.md +0 -124
  545. package/evals/reports/by-skill/capture-decisions-1-report.md +0 -99
  546. package/evals/reports/by-skill/capture-decisions-2-report.md +0 -102
  547. package/evals/reports/by-skill/commit-work-1-report.md +0 -165
  548. package/evals/reports/by-skill/commit-work-2-report.md +0 -109
  549. package/evals/reports/by-skill/design-for-depth-1-report.md +0 -95
  550. package/evals/reports/by-skill/diagnose-failure-1-report.md +0 -91
  551. package/evals/reports/by-skill/diagnose-failure-2-report.md +0 -94
  552. package/evals/reports/by-skill/discover-1-report.md +0 -118
  553. package/evals/reports/by-skill/evaluate-skill-2-report.md +0 -71
  554. package/evals/reports/by-skill/execute-plan-1-report.md +0 -103
  555. package/evals/reports/by-skill/execute-plan-2-report.md +0 -112
  556. package/evals/reports/by-skill/execute-plan-3-report.md +0 -87
  557. package/evals/reports/by-skill/grill-context-1-report.md +0 -103
  558. package/evals/reports/by-skill/handoff-1-report.md +0 -123
  559. package/evals/reports/by-skill/handoff-2-report.md +0 -105
  560. package/evals/reports/by-skill/handoff-3-report.md +0 -100
  561. package/evals/reports/by-skill/handoff-7-report.md +0 -77
  562. package/evals/reports/by-skill/interview-gate-1-report.md +0 -63
  563. package/evals/reports/by-skill/interview-gate-2-report.md +0 -105
  564. package/evals/reports/by-skill/mode-contract-1-report.md +0 -74
  565. package/evals/reports/by-skill/mode-contract-2-report.md +0 -87
  566. package/evals/reports/by-skill/mode-contract-3-report.md +0 -65
  567. package/evals/reports/by-skill/mode-contract-4-report.md +0 -71
  568. package/evals/reports/by-skill/mode-contract-5-report.md +0 -70
  569. package/evals/reports/by-skill/output-router-1-report.md +0 -76
  570. package/evals/reports/by-skill/output-router-2-report.md +0 -65
  571. package/evals/reports/by-skill/research-1-report.md +0 -144
  572. package/evals/reports/by-skill/research-brief-1-report.md +0 -94
  573. package/evals/reports/by-skill/research-brief-2-report.md +0 -75
  574. package/evals/reports/by-skill/review-artifact-1-report.md +0 -91
  575. package/evals/reports/by-skill/review-artifact-2-report.md +0 -79
  576. package/evals/reports/by-skill/review-artifact-3-report.md +0 -120
  577. package/evals/reports/by-skill/review-artifact-4-report.md +0 -89
  578. package/evals/reports/by-skill/review-artifact-5-report.md +0 -66
  579. package/evals/reports/by-skill/review-work-1-report.md +0 -85
  580. package/evals/reports/by-skill/review-work-2-report.md +0 -87
  581. package/evals/reports/by-skill/review-work-3-report.md +0 -104
  582. package/evals/reports/by-skill/review-work-4-report.md +0 -108
  583. package/evals/reports/by-skill/review-work-5-report.md +0 -73
  584. package/evals/reports/by-skill/review-work-6-report.md +0 -66
  585. package/evals/reports/by-skill/setup-freeflow-1-report.md +0 -199
  586. package/evals/reports/by-skill/setup-freeflow-2-report.md +0 -105
  587. package/evals/reports/by-skill/setup-freeflow-3-report.md +0 -105
  588. package/evals/reports/by-skill/setup-freeflow-4-report.md +0 -88
  589. package/evals/reports/by-skill/setup-freeflow-5-report.md +0 -115
  590. package/evals/reports/by-skill/skill-authoring-1-report.md +0 -81
  591. package/evals/reports/by-skill/verify-work-1-report.md +0 -111
  592. package/evals/reports/by-skill/verify-work-2-report.md +0 -120
  593. package/evals/reports/by-skill/workflow-1-report.md +0 -65
  594. package/evals/reports/by-skill/write-plan-1-report.md +0 -123
  595. package/evals/reports/by-skill/write-plan-2-report.md +0 -98
  596. package/evals/reports/by-skill/write-plan-3-report.md +0 -110
  597. package/evals/reports/by-skill/write-spec-1-report.md +0 -88
  598. package/evals/reports/by-skill/write-spec-2-report.md +0 -89
  599. package/evals/reports/by-skill/write-spec-3-report.md +0 -90
  600. package/evals/reports/by-skill/write-spec-4-report.md +0 -167
  601. package/evals/reports/harness/claude-harness-1-report.md +0 -103
  602. package/evals/reports/harness/eval-harness-1-report.md +0 -91
  603. package/evals/reports/iterations/iteration-1-report.md +0 -71
  604. package/evals/reports/iterations/iteration-2-report.md +0 -78
  605. package/evals/reports/iterations/iteration-3-report.md +0 -118
  606. package/evals/reports/iterations/iteration-4-report.md +0 -131
  607. package/evals/reports/iterations/iteration-5-report.md +0 -149
  608. package/evals/reports/iterations/iteration-6-report.md +0 -136
  609. package/evals/reports/runtime/always-on-runtime-1-report.md +0 -107
  610. package/evals/reports/runtime/context-mode-normalized-benchmark-1-report.md +0 -52
  611. package/evals/reports/runtime/context-mode-real-deep-baseline-1-report.md +0 -410
  612. package/evals/reports/runtime/context-mode-real-deep-final-slice-11-report.md +0 -203
  613. package/evals/reports/runtime/context-mode-real-deep-final-slice-11-review.md +0 -51
  614. package/evals/reports/runtime/context-saving-native-tools-baseline-1-report.md +0 -99
  615. package/evals/reports/runtime/eryx-python-compatibility-reprobe-1-report.md +0 -166
  616. package/evals/reports/runtime/eryx-python-proof-spike-1-report.md +0 -96
  617. package/evals/reports/runtime/eryx-python-proof-spike-2-report.md +0 -151
  618. package/evals/reports/runtime/eryx-python-script-derive-execution-1-report.md +0 -233
  619. package/evals/reports/runtime/jq-script-derive-execution-1-report.md +0 -215
  620. package/evals/reports/runtime/jq-wasm-proof-spike-1-report.md +0 -67
  621. package/evals/reports/runtime/output-router-benchmark-1-report.md +0 -81
  622. package/evals/reports/runtime/output-router-capture-derive-provider-eval-1-report.md +0 -35
  623. package/evals/reports/runtime/output-router-codex-large-index-sqlite-adhoc-report.md +0 -150
  624. package/evals/reports/runtime/output-router-codex-qa-benchmark-1-report.md +0 -46
  625. package/evals/reports/runtime/output-router-command-benchmark-1-report.md +0 -62
  626. package/evals/reports/runtime/output-router-index-benchmark-1-report.md +0 -64
  627. package/evals/reports/runtime/output-router-regression-1-report.md +0 -81
  628. package/evals/reports/runtime/output-router-transform-eval-1-report.md +0 -28
  629. package/evals/reports/runtime/pi-observed-routing-eval-1-report.md +0 -44
  630. package/evals/reports/runtime/quickjs-script-derive-execution-1-report.md +0 -159
  631. package/evals/reports/runtime/quickjs-wasi-proof-spike-1-report.md +0 -55
  632. package/evals/reports/runtime/render-format-row-protocol-1-report.md +0 -58
  633. package/evals/reports/runtime/script-sandbox-adapter-selection-review-1-report.md +0 -84
  634. package/evals/reports/runtime/script-sandbox-probe-resource-hardening-1-report.md +0 -51
  635. package/evals/reports/runtime/storage-policy-benchmark-1-report.md +0 -176
  636. package/evals/reports/runtime/vault-index-storage-spike-1-report.md +0 -39
  637. package/evals/reports/runtime/workflow-context-hook-1-report.md +0 -82
  638. package/evals/runbooks/adversarial-eval-runbook.md +0 -28
  639. package/evals/runbooks/fixture-eval-runbook.md +0 -137
  640. package/evals/runbooks/handoff-eval-runbook.md +0 -22
  641. package/evals/runbooks/verify-work-eval-runbook.md +0 -27
  642. package/evals/scripts/audit-command-surface.sh +0 -160
  643. package/evals/scripts/check-activation-contract.sh +0 -121
  644. package/evals/scripts/check-runtime-context-hook.sh +0 -183
  645. package/evals/scripts/grade-fixture-eval.sh +0 -446
  646. package/evals/scripts/run-claude-fixture-eval.sh +0 -26
  647. package/evals/scripts/run-codex-fixture-eval.sh +0 -26
  648. package/evals/scripts/run-eryx-python-proof-spike.js +0 -559
  649. package/evals/scripts/run-fixture-eval-by-id.sh +0 -23
  650. package/evals/scripts/run-fixture-eval.sh +0 -464
  651. package/evals/scripts/run-jq-wasm-proof-spike.js +0 -299
  652. package/evals/scripts/run-output-router-transform-eval.js +0 -115
  653. package/evals/scripts/run-pi-observed-routing-eval.js +0 -478
  654. package/evals/scripts/run-quickjs-wasi-proof-spike.js +0 -339
  655. package/evals/scripts/skill-evidence.sh +0 -316
  656. package/evals/scripts/validate-release-metadata.sh +0 -486
  657. package/evals/suites/v0.1-acceptance-suite.md +0 -131
  658. package/pi-extension/dist/host-producer-identification.js +0 -186
  659. package/pi-extension/dist/mcp-config.js +0 -30
  660. package/pi-extension/dist/native-safety-net.js +0 -209
  661. package/pi-extension/dist/observed-tool-routing.js +0 -114
  662. package/pi-extension/dist/renderers.js +0 -835
  663. package/pi-extension/dist/router-tools.js +0 -438
  664. package/pi-extension/dist/runtime-context.js +0 -288
  665. package/pi-extension/dist/schemas.js +0 -254
  666. package/pi-extension/dist/status.js +0 -449
  667. package/pi-extension/dist/utils.js +0 -467
  668. package/pi-extension/src/runtime-context.ts +0 -347
  669. package/pi-extension/src/status.ts +0 -505
  670. package/plugin-docs/README.md +0 -40
  671. package/plugin-docs/adr/0001-three-modes.md +0 -27
  672. package/plugin-docs/adr/0002-evals-before-hooks.md +0 -17
  673. package/plugin-docs/adr/0003-release-boundary.md +0 -21
  674. package/plugin-docs/adr/0004-discover-replaces-shallow-discovery-skills.md +0 -26
  675. package/plugin-docs/adr/README.md +0 -10
  676. package/plugin-docs/architecture.md +0 -89
  677. package/plugin-docs/output-router.md +0 -396
  678. package/plugin-docs/release-evidence.md +0 -77
  679. package/plugin-docs/skills.md +0 -44
  680. package/plugin-docs/workflow.md +0 -57
  681. package/skills/diagnose-failure/references/feedback-loop-catalog.md +0 -25
  682. package/skills/discover/ARTIFACT-DESTINATIONS.md +0 -58
  683. package/skills/discover/CHECKPOINTS.md +0 -74
  684. package/skills/discover/SKILL.md +0 -173
  685. package/skills/evaluate-skill/references/eval-patterns.md +0 -41
  686. package/skills/evaluate-skill/references/grading-priority.md +0 -33
  687. package/skills/execute-plan/SKILL.md +0 -133
  688. package/skills/execute-plan/references/execution-map.md +0 -122
  689. package/skills/interview-gate/SKILL.md +0 -90
  690. package/skills/setup-freeflow/references/output-router-setup.md +0 -102
  691. package/skills/workflow/references/workflow-map.md +0 -104
  692. /package/pi-extension/src/{mcp-config.ts → integrations/mcp-config.ts} +0 -0
@@ -1,473 +1,521 @@
1
- import { DEFAULT_MAX_IMPORTANT_LINES, assembleImportantLines, lineEntries, nonEmptyLineEntries, splitLines, } from "../evidence/evidence.js";
1
+ import {
2
+ DEFAULT_MAX_IMPORTANT_LINES,
3
+ assembleImportantLines,
4
+ lineEntries,
5
+ nonEmptyLineEntries,
6
+ splitLines,
7
+ } from "../evidence/evidence.js";
2
8
  const MAX_IMPORTANT_LINES = DEFAULT_MAX_IMPORTANT_LINES;
3
9
  const COMMAND_PARSERS = [
4
- { name: "test-runner", parse: parseTestRunnerOutput },
5
- { name: "typescript-lint", parse: parseTypeScriptOrLintOutput },
6
- { name: "git-status-diffstat", parse: parseGitOutput },
7
- { name: "build-toolchain", parse: parseBuildOutput },
10
+ { name: "test-runner", parse: parseTestRunnerOutput },
11
+ { name: "typescript-lint", parse: parseTypeScriptOrLintOutput },
12
+ { name: "git-status-diffstat", parse: parseGitOutput },
13
+ { name: "build-toolchain", parse: parseBuildOutput },
8
14
  ];
9
15
  export function parseCommandOutput(input) {
10
- for (const parser of COMMAND_PARSERS) {
11
- const parsed = parser.parse(input);
12
- if (parsed) {
13
- return parsed;
14
- }
16
+ for (const parser of COMMAND_PARSERS) {
17
+ const parsed = parser.parse(input);
18
+ if (parsed) {
19
+ return parsed;
15
20
  }
16
- return parseGenericOutput(input);
21
+ }
22
+ return parseGenericOutput(input);
17
23
  }
18
24
  function parseTestRunnerOutput(input) {
19
- const command = commandText(input.command);
20
- const combined = input.combined;
21
- const commandLooksLikeTest = commandLooksLikeTestRunner(command);
22
- const summaryEvidence = testSummaryEvidence(combined);
23
- if (!commandLooksLikeTest) {
24
- return null;
25
- }
26
- const evidenceBlocks = [];
27
- const failureBlock = firstFailureBlock(input.stderr, "stderr") ?? firstFailureBlock(input.stdout, "stdout") ?? firstFailureBlock(input.combined, "combined");
28
- if (failureBlock) {
29
- evidenceBlocks.push(failureBlock);
30
- }
31
- if (summaryEvidence) {
32
- evidenceBlocks.push(summaryEvidence);
33
- }
34
- const selected = selectEvidenceLines(evidenceBlocks, 2);
35
- if (selected.importantLines.length === 0) {
36
- return null;
37
- }
38
- const counts = testCounts(input.combined);
39
- return {
40
- parser: {
41
- name: "test-runner",
42
- confidence: 0.92,
43
- fidelity: selected.fidelity,
44
- compressed: selected.compressed,
45
- counts,
46
- },
47
- summary: testSummaryText(counts, input.executionStatus, input.exitCode),
48
- importantLines: selected.importantLines,
49
- };
25
+ const command = commandText(input.command);
26
+ const combined = input.combined;
27
+ const commandLooksLikeTest = commandLooksLikeTestRunner(command);
28
+ const summaryEvidence = testSummaryEvidence(combined);
29
+ if (!commandLooksLikeTest) {
30
+ return null;
31
+ }
32
+ const evidenceBlocks = [];
33
+ const failureBlock =
34
+ firstFailureBlock(input.stderr, "stderr") ??
35
+ firstFailureBlock(input.stdout, "stdout") ??
36
+ firstFailureBlock(input.combined, "combined");
37
+ if (failureBlock) {
38
+ evidenceBlocks.push(failureBlock);
39
+ }
40
+ if (summaryEvidence) {
41
+ evidenceBlocks.push(summaryEvidence);
42
+ }
43
+ const selected = selectEvidenceLines(evidenceBlocks, 2);
44
+ if (selected.importantLines.length === 0) {
45
+ return null;
46
+ }
47
+ const counts = testCounts(input.combined);
48
+ return {
49
+ parser: {
50
+ name: "test-runner",
51
+ confidence: 0.92,
52
+ fidelity: selected.fidelity,
53
+ compressed: selected.compressed,
54
+ counts,
55
+ },
56
+ summary: testSummaryText(counts, input.executionStatus, input.exitCode),
57
+ importantLines: selected.importantLines,
58
+ };
50
59
  }
51
60
  function parseTypeScriptOrLintOutput(input) {
52
- const command = commandText(input.command);
53
- if (!commandLooksLikeTypeScriptOrLint(command)) {
54
- return null;
55
- }
56
- const streams = [
57
- { stream: "stderr", text: input.stderr },
58
- { stream: "stdout", text: input.stdout },
59
- { stream: "combined", text: input.combined },
60
- ];
61
- for (const { stream, text } of streams) {
62
- const entries = lineEntries(text);
63
- const matches = diagnosticMatches(entries);
64
- if (matches.length === 0) {
65
- continue;
66
- }
67
- const references = matches.map((match) => match.reference);
68
- const importantEntries = diagnosticImportantEntries(matches).slice(0, MAX_IMPORTANT_LINES);
69
- const evidence = assembleImportantLines({ stream, entries: importantEntries, sourceText: text });
70
- if (evidence.importantLines.length === 0) {
71
- continue;
72
- }
73
- const counts = diagnosticCounts(references);
74
- return {
75
- parser: {
76
- name: "typescript-lint",
77
- confidence: 0.88,
78
- fidelity: evidence.fidelity,
79
- compressed: evidence.compressed,
80
- counts,
81
- references: references.slice(0, 10),
82
- },
83
- summary: `Detected ${counts.errors ?? 0} error(s) and ${counts.warnings ?? 0} warning(s) in TypeScript/lint diagnostics.`,
84
- importantLines: evidence.importantLines,
85
- };
86
- }
61
+ const command = commandText(input.command);
62
+ if (!commandLooksLikeTypeScriptOrLint(command)) {
87
63
  return null;
88
- }
89
- function parseGitOutput(input) {
90
- const command = commandText(input.command);
91
- const text = input.combined;
92
- const commandLooksLikeStatusOrDiffstat = /^\s*git\s+(status\b|diff\b.*--stat|show\b.*--stat|diffstat\b)/i.test(command);
93
- if (!commandLooksLikeStatusOrDiffstat) {
94
- return null;
64
+ }
65
+ const streams = [
66
+ { stream: "stderr", text: input.stderr },
67
+ { stream: "stdout", text: input.stdout },
68
+ { stream: "combined", text: input.combined },
69
+ ];
70
+ for (const { stream, text } of streams) {
71
+ const entries = lineEntries(text);
72
+ const matches = diagnosticMatches(entries);
73
+ if (matches.length === 0) {
74
+ continue;
95
75
  }
96
- const entries = lineEntries(text).filter((entry) => isGitEvidenceLine(entry.line));
97
- const selected = entries.length > 0 ? entries : nonEmptyLineEntries(text).slice(0, MAX_IMPORTANT_LINES);
98
- const selectedForEvidence = selected.slice(0, MAX_IMPORTANT_LINES);
99
- const evidence = assembleImportantLines({ stream: "combined", entries: selectedForEvidence, sourceText: text });
76
+ const references = matches.map((match) => match.reference);
77
+ const importantEntries = diagnosticImportantEntries(matches).slice(0, MAX_IMPORTANT_LINES);
78
+ const evidence = assembleImportantLines({ stream, entries: importantEntries, sourceText: text });
100
79
  if (evidence.importantLines.length === 0) {
101
- return null;
80
+ continue;
102
81
  }
103
- const counts = gitCounts(text);
82
+ const counts = diagnosticCounts(references);
104
83
  return {
105
- parser: {
106
- name: "git-status-diffstat",
107
- confidence: 0.76,
108
- fidelity: evidence.fidelity,
109
- compressed: evidence.compressed,
110
- counts,
111
- },
112
- summary: "Detected git status/diffstat output.",
113
- importantLines: evidence.importantLines,
84
+ parser: {
85
+ name: "typescript-lint",
86
+ confidence: 0.88,
87
+ fidelity: evidence.fidelity,
88
+ compressed: evidence.compressed,
89
+ counts,
90
+ references: references.slice(0, 10),
91
+ },
92
+ summary: `Detected ${counts.errors ?? 0} error(s) and ${counts.warnings ?? 0} warning(s) in TypeScript/lint diagnostics.`,
93
+ importantLines: evidence.importantLines,
114
94
  };
95
+ }
96
+ return null;
97
+ }
98
+ function parseGitOutput(input) {
99
+ const command = commandText(input.command);
100
+ const text = input.combined;
101
+ const commandLooksLikeStatusOrDiffstat = /^\s*git\s+(status\b|diff\b.*--stat|show\b.*--stat|diffstat\b)/i.test(
102
+ command,
103
+ );
104
+ if (!commandLooksLikeStatusOrDiffstat) {
105
+ return null;
106
+ }
107
+ const entries = lineEntries(text).filter((entry) => isGitEvidenceLine(entry.line));
108
+ const selected = entries.length > 0 ? entries : nonEmptyLineEntries(text).slice(0, MAX_IMPORTANT_LINES);
109
+ const selectedForEvidence = selected.slice(0, MAX_IMPORTANT_LINES);
110
+ const evidence = assembleImportantLines({ stream: "combined", entries: selectedForEvidence, sourceText: text });
111
+ if (evidence.importantLines.length === 0) {
112
+ return null;
113
+ }
114
+ const counts = gitCounts(text);
115
+ return {
116
+ parser: {
117
+ name: "git-status-diffstat",
118
+ confidence: 0.76,
119
+ fidelity: evidence.fidelity,
120
+ compressed: evidence.compressed,
121
+ counts,
122
+ },
123
+ summary: "Detected git status/diffstat output.",
124
+ importantLines: evidence.importantLines,
125
+ };
115
126
  }
116
127
  function parseBuildOutput(input) {
117
- const text = input.combined;
118
- const command = commandText(input.command);
119
- const entries = lineEntries(text);
120
- const commandLooksLikeBuild = commandLooksLikeBuildTool(command);
121
- if (!commandLooksLikeBuild) {
122
- return null;
123
- }
124
- const errorPattern = commandLooksLikeBuild
125
- ? /(?:\berror\b|\bfatal\b|failed to compile|build failed|module not found|cannot find module|npm ERR!)/i
126
- : /(failed to compile|build failed|npm ERR!)/i;
127
- const firstErrorIndex = entries.findIndex((entry) => errorPattern.test(entry.line));
128
- if (firstErrorIndex === -1) {
129
- return null;
130
- }
131
- const selected = entries.slice(firstErrorIndex, Math.min(entries.length, firstErrorIndex + MAX_IMPORTANT_LINES));
132
- const evidence = assembleImportantLines({ stream: "combined", entries: selected, sourceText: text });
133
- if (evidence.importantLines.length === 0) {
134
- return null;
135
- }
136
- const counts = {
137
- errors: countMatches(text, /(?:\berror\b|\bfatal\b|npm ERR!)/gi),
138
- failed: countMatches(text, /\bfailed\b/gi),
139
- };
140
- return {
141
- parser: {
142
- name: "build-toolchain",
143
- confidence: 0.66,
144
- fidelity: evidence.fidelity,
145
- compressed: evidence.compressed,
146
- counts,
147
- },
148
- summary: "Detected build/toolchain error output.",
149
- importantLines: evidence.importantLines,
150
- };
128
+ const text = input.combined;
129
+ const command = commandText(input.command);
130
+ const entries = lineEntries(text);
131
+ const commandLooksLikeBuild = commandLooksLikeBuildTool(command);
132
+ if (!commandLooksLikeBuild) {
133
+ return null;
134
+ }
135
+ const errorPattern = commandLooksLikeBuild
136
+ ? /(?:\berror\b|\bfatal\b|failed to compile|build failed|module not found|cannot find module|npm ERR!)/i
137
+ : /(failed to compile|build failed|npm ERR!)/i;
138
+ const firstErrorIndex = entries.findIndex((entry) => errorPattern.test(entry.line));
139
+ if (firstErrorIndex === -1) {
140
+ return null;
141
+ }
142
+ const selected = entries.slice(firstErrorIndex, Math.min(entries.length, firstErrorIndex + MAX_IMPORTANT_LINES));
143
+ const evidence = assembleImportantLines({ stream: "combined", entries: selected, sourceText: text });
144
+ if (evidence.importantLines.length === 0) {
145
+ return null;
146
+ }
147
+ const counts = {
148
+ errors: countMatches(text, /(?:\berror\b|\bfatal\b|npm ERR!)/gi),
149
+ failed: countMatches(text, /\bfailed\b/gi),
150
+ };
151
+ return {
152
+ parser: {
153
+ name: "build-toolchain",
154
+ confidence: 0.66,
155
+ fidelity: evidence.fidelity,
156
+ compressed: evidence.compressed,
157
+ counts,
158
+ },
159
+ summary: "Detected build/toolchain error output.",
160
+ importantLines: evidence.importantLines,
161
+ };
151
162
  }
152
163
  function parseGenericOutput(input) {
153
- const evidence = selectGenericImportantLines(input);
154
- const outputLines = splitLines(input.combined).length;
155
- return {
156
- parser: {
157
- name: "generic",
158
- confidence: 0.35,
159
- fidelity: evidence.fidelity,
160
- compressed: evidence.compressed,
161
- counts: { outputLines },
162
- },
163
- importantLines: evidence.importantLines,
164
- };
164
+ const evidence = selectGenericImportantLines(input);
165
+ const outputLines = splitLines(input.combined).length;
166
+ return {
167
+ parser: {
168
+ name: "generic",
169
+ confidence: 0.35,
170
+ fidelity: evidence.fidelity,
171
+ compressed: evidence.compressed,
172
+ counts: { outputLines },
173
+ },
174
+ importantLines: evidence.importantLines,
175
+ };
165
176
  }
166
177
  function selectGenericImportantLines(input) {
167
- if (isVerificationGoal(input.goal)) {
168
- const verificationLines = verificationSummaryEvidence(input.combined);
169
- if (verificationLines) {
170
- return verificationLines;
171
- }
172
- }
173
- if (input.executionStatus !== "success") {
174
- const failureLines = firstFailureBlock(input.stderr, "stderr") ?? firstFailureBlock(input.combined, "combined");
175
- if (failureLines) {
176
- return failureLines;
177
- }
178
- const stderrLines = firstAndLastNonEmptyImportantLines(input.stderr, "stderr");
179
- if (stderrLines) {
180
- return stderrLines;
181
- }
182
- }
183
- return firstNonEmptyImportantLine(input.combined, "combined") ?? emptyEvidence(input.combined);
178
+ if (isVerificationGoal(input.goal)) {
179
+ const verificationLines = verificationSummaryEvidence(input.combined);
180
+ if (verificationLines) {
181
+ return verificationLines;
182
+ }
183
+ }
184
+ if (input.executionStatus !== "success") {
185
+ const failureLines = firstFailureBlock(input.stderr, "stderr") ?? firstFailureBlock(input.combined, "combined");
186
+ if (failureLines) {
187
+ return failureLines;
188
+ }
189
+ const stderrLines = firstAndLastNonEmptyImportantLines(input.stderr, "stderr");
190
+ if (stderrLines) {
191
+ return stderrLines;
192
+ }
193
+ }
194
+ return firstNonEmptyImportantLine(input.combined, "combined") ?? emptyEvidence(input.combined);
184
195
  }
185
196
  function firstFailureBlock(text, stream) {
186
- const entries = lineEntries(text);
187
- const firstFailureIndex = entries.findIndex((entry) => /^\s*(FAIL|FAILED|FAILURES)(?:\s|$)/i.test(entry.line) ||
188
- /(?:\bAssertionError\b|assertion failed|\bexpected\b|\bExpected\b|\bReceived\b|\bstack\b|\bTraceback\b|\bError:|\bfatal(?:\b|_)|\bpanic\b|\bexception\b)/i.test(entry.line));
189
- if (firstFailureIndex === -1) {
190
- return null;
191
- }
192
- const block = entries.slice(firstFailureIndex, Math.min(entries.length, firstFailureIndex + MAX_IMPORTANT_LINES));
193
- return assembleImportantLines({ stream, entries: block, sourceText: text });
197
+ const entries = lineEntries(text);
198
+ const firstFailureIndex = entries.findIndex(
199
+ (entry) =>
200
+ /^\s*(FAIL|FAILED|FAILURES)(?:\s|$)/i.test(entry.line) ||
201
+ /(?:\bAssertionError\b|assertion failed|\bexpected\b|\bExpected\b|\bReceived\b|\bstack\b|\bTraceback\b|\bError:|\bfatal(?:\b|_)|\bpanic\b|\bexception\b)/i.test(
202
+ entry.line,
203
+ ),
204
+ );
205
+ if (firstFailureIndex === -1) {
206
+ return null;
207
+ }
208
+ const block = entries.slice(firstFailureIndex, Math.min(entries.length, firstFailureIndex + MAX_IMPORTANT_LINES));
209
+ return assembleImportantLines({ stream, entries: block, sourceText: text });
194
210
  }
195
211
  function testSummaryEvidence(text) {
196
- const matches = lineEntries(text).filter((entry) => /\b(Test Suites?:|Tests?:|FAILURES)/i.test(entry.line) ||
197
- /^\s*FAILED\s+.+\btests?\b/i.test(entry.line) ||
198
- /^\s*(?:\d+\s+(?:failed|passed|skipped|deselected|xfailed|xpassed|errors?)(?:,?\s+|$))+in\s+[\d.]+s\b/i.test(entry.line) ||
199
- /^\s*(?:ℹ\s*)?(?:tests?|pass|fail|cancelled|skipped|todo)\s+\d+\b/i.test(entry.line));
200
- const evidence = assembleImportantLines({ stream: "combined", entries: matches.slice(0, MAX_IMPORTANT_LINES), sourceText: text });
201
- return evidence.importantLines.length > 0 ? evidence : null;
212
+ const matches = lineEntries(text).filter(
213
+ (entry) =>
214
+ /\b(Test Suites?:|Tests?:|FAILURES)/i.test(entry.line) ||
215
+ /^\s*FAILED\s+.+\btests?\b/i.test(entry.line) ||
216
+ /^\s*(?:\d+\s+(?:failed|passed|skipped|deselected|xfailed|xpassed|errors?)(?:,?\s+|$))+in\s+[\d.]+s\b/i.test(
217
+ entry.line,
218
+ ) ||
219
+ /^\s*(?:ℹ\s*)?(?:tests?|pass|fail|cancelled|skipped|todo)\s+\d+\b/i.test(entry.line),
220
+ );
221
+ const evidence = assembleImportantLines({
222
+ stream: "combined",
223
+ entries: matches.slice(0, MAX_IMPORTANT_LINES),
224
+ sourceText: text,
225
+ });
226
+ return evidence.importantLines.length > 0 ? evidence : null;
202
227
  }
203
228
  function verificationSummaryEvidence(text) {
204
- const matches = lineEntries(text).filter((entry) => /\b(Tests?|Test Suites?|passed|failed|total)\b/i.test(entry.line));
205
- const evidence = assembleImportantLines({ stream: "combined", entries: matches.slice(0, MAX_IMPORTANT_LINES), sourceText: text });
206
- return evidence.importantLines.length > 0 ? evidence : null;
229
+ const matches = lineEntries(text).filter((entry) =>
230
+ /\b(Tests?|Test Suites?|passed|failed|total)\b/i.test(entry.line),
231
+ );
232
+ const evidence = assembleImportantLines({
233
+ stream: "combined",
234
+ entries: matches.slice(0, MAX_IMPORTANT_LINES),
235
+ sourceText: text,
236
+ });
237
+ return evidence.importantLines.length > 0 ? evidence : null;
207
238
  }
208
239
  function firstNonEmptyImportantLine(text, stream) {
209
- const evidence = assembleImportantLines({ stream, entries: nonEmptyLineEntries(text).slice(0, MAX_IMPORTANT_LINES), sourceText: text });
210
- return evidence.importantLines.length > 0 ? evidence : null;
240
+ const evidence = assembleImportantLines({
241
+ stream,
242
+ entries: nonEmptyLineEntries(text).slice(0, MAX_IMPORTANT_LINES),
243
+ sourceText: text,
244
+ });
245
+ return evidence.importantLines.length > 0 ? evidence : null;
211
246
  }
212
247
  function firstAndLastNonEmptyImportantLines(text, stream) {
213
- const entries = nonEmptyLineEntries(text);
214
- if (entries.length === 0) {
215
- return null;
216
- }
217
- if (entries.length <= MAX_IMPORTANT_LINES) {
218
- return firstNonEmptyImportantLine(text, stream);
219
- }
220
- const headCount = Math.floor(MAX_IMPORTANT_LINES / 2);
221
- const tailCount = MAX_IMPORTANT_LINES - headCount;
222
- const selected = [...entries.slice(0, headCount), ...entries.slice(-tailCount)];
223
- const evidence = assembleImportantLines({ stream, entries: selected, sourceText: text });
224
- return evidence.importantLines.length > 0 ? evidence : null;
248
+ const entries = nonEmptyLineEntries(text);
249
+ if (entries.length === 0) {
250
+ return null;
251
+ }
252
+ if (entries.length <= MAX_IMPORTANT_LINES) {
253
+ return firstNonEmptyImportantLine(text, stream);
254
+ }
255
+ const headCount = Math.floor(MAX_IMPORTANT_LINES / 2);
256
+ const tailCount = MAX_IMPORTANT_LINES - headCount;
257
+ const selected = [...entries.slice(0, headCount), ...entries.slice(-tailCount)];
258
+ const evidence = assembleImportantLines({ stream, entries: selected, sourceText: text });
259
+ return evidence.importantLines.length > 0 ? evidence : null;
225
260
  }
226
261
  function selectEvidenceLines(evidenceBlocks, maxImportantLines) {
227
- const importantLines = [];
228
- const seen = new Set();
229
- let fidelity = "exact";
230
- let compressed = false;
231
- for (const evidence of evidenceBlocks) {
232
- fidelity = fidelity === "lossy" || evidence.fidelity === "lossy" ? "lossy" : "exact";
233
- compressed = compressed || evidence.compressed;
234
- for (const line of evidence.importantLines) {
235
- const key = `${line.stream}:${line.lines}:${line.excerpt}`;
236
- if (seen.has(key)) {
237
- continue;
238
- }
239
- seen.add(key);
240
- if (importantLines.length >= maxImportantLines) {
241
- compressed = true;
242
- continue;
243
- }
244
- importantLines.push(line);
245
- }
246
- }
247
- return { importantLines, fidelity, compressed };
262
+ const importantLines = [];
263
+ const seen = new Set();
264
+ let fidelity = "exact";
265
+ let compressed = false;
266
+ for (const evidence of evidenceBlocks) {
267
+ fidelity = fidelity === "lossy" || evidence.fidelity === "lossy" ? "lossy" : "exact";
268
+ compressed = compressed || evidence.compressed;
269
+ for (const line of evidence.importantLines) {
270
+ const key = `${line.stream}:${line.lines}:${line.excerpt}`;
271
+ if (seen.has(key)) {
272
+ continue;
273
+ }
274
+ seen.add(key);
275
+ if (importantLines.length >= maxImportantLines) {
276
+ compressed = true;
277
+ continue;
278
+ }
279
+ importantLines.push(line);
280
+ }
281
+ }
282
+ return { importantLines, fidelity, compressed };
248
283
  }
249
284
  function emptyEvidence(sourceText) {
250
- return {
251
- importantLines: [],
252
- fidelity: "exact",
253
- compressed: false,
254
- selectedLineCount: 0,
255
- sourceLineCount: splitLines(sourceText).length,
256
- };
285
+ return {
286
+ importantLines: [],
287
+ fidelity: "exact",
288
+ compressed: false,
289
+ selectedLineCount: 0,
290
+ sourceLineCount: splitLines(sourceText).length,
291
+ };
257
292
  }
258
293
  function isGitEvidenceLine(line) {
259
- return (/\b(On branch|Your branch|Changes to be committed|Changes not staged|Untracked files|modified:|new file:|deleted:|files? changed|insertions?\(\+\)|deletions?\(-\))\b/i.test(line) ||
260
- /^([ MARCUD?!]{2})\s+/.test(line) ||
261
- /\|\s+\d+\s+[+\-]+/.test(line));
294
+ return (
295
+ /\b(On branch|Your branch|Changes to be committed|Changes not staged|Untracked files|modified:|new file:|deleted:|files? changed|insertions?\(\+\)|deletions?\(-\))\b/i.test(
296
+ line,
297
+ ) ||
298
+ /^([ MARCUD?!]{2})\s+/.test(line) ||
299
+ /\|\s+\d+\s+[+\-]+/.test(line)
300
+ );
262
301
  }
263
302
  function gitCounts(text) {
264
- const counts = {};
265
- addCount(counts, "modified", countMatches(text, /modified:/gi));
266
- addCount(counts, "added", countMatches(text, /new file:/gi));
267
- addCount(counts, "deleted", countMatches(text, /deleted:/gi));
268
- for (const entry of lineEntries(text)) {
269
- const porcelain = /^([ MARCUD?!]{2})\s+/.exec(entry.line);
270
- if (!porcelain) {
271
- continue;
272
- }
273
- const status = porcelain[1] ?? "";
274
- if (status.includes("M")) {
275
- addCount(counts, "modified", 1);
276
- }
277
- if (status.includes("A") || status === "??") {
278
- addCount(counts, status === "??" ? "untracked" : "added", 1);
279
- }
280
- if (status.includes("D")) {
281
- addCount(counts, "deleted", 1);
282
- }
283
- if (status.includes("R")) {
284
- addCount(counts, "renamed", 1);
285
- }
286
- }
287
- const diffstat = /\b(\d+)\s+files? changed\b/i.exec(text);
288
- if (diffstat?.[1]) {
289
- addCount(counts, "filesChanged", Number(diffstat[1]));
290
- }
291
- return counts;
303
+ const counts = {};
304
+ addCount(counts, "modified", countMatches(text, /modified:/gi));
305
+ addCount(counts, "added", countMatches(text, /new file:/gi));
306
+ addCount(counts, "deleted", countMatches(text, /deleted:/gi));
307
+ for (const entry of lineEntries(text)) {
308
+ const porcelain = /^([ MARCUD?!]{2})\s+/.exec(entry.line);
309
+ if (!porcelain) {
310
+ continue;
311
+ }
312
+ const status = porcelain[1] ?? "";
313
+ if (status.includes("M")) {
314
+ addCount(counts, "modified", 1);
315
+ }
316
+ if (status.includes("A") || status === "??") {
317
+ addCount(counts, status === "??" ? "untracked" : "added", 1);
318
+ }
319
+ if (status.includes("D")) {
320
+ addCount(counts, "deleted", 1);
321
+ }
322
+ if (status.includes("R")) {
323
+ addCount(counts, "renamed", 1);
324
+ }
325
+ }
326
+ const diffstat = /\b(\d+)\s+files? changed\b/i.exec(text);
327
+ if (diffstat?.[1]) {
328
+ addCount(counts, "filesChanged", Number(diffstat[1]));
329
+ }
330
+ return counts;
292
331
  }
293
332
  function addCount(counts, key, value) {
294
- if (value > 0) {
295
- counts[key] = (counts[key] ?? 0) + value;
296
- }
333
+ if (value > 0) {
334
+ counts[key] = (counts[key] ?? 0) + value;
335
+ }
297
336
  }
298
337
  function testCounts(text) {
299
- const counts = {};
300
- const testsLine = /Tests?:\s*(?:(\d+)\s+failed,?\s*)?(?:(\d+)\s+passed,?\s*)?(?:(\d+)\s+total)?/i.exec(text);
301
- if (testsLine?.[1]) {
302
- counts.testsFailed = Number(testsLine[1]);
303
- }
304
- if (testsLine?.[2]) {
305
- counts.testsPassed = Number(testsLine[2]);
306
- }
307
- if (testsLine?.[3]) {
308
- counts.testsTotal = Number(testsLine[3]);
309
- }
310
- for (const match of text.matchAll(/\b(\d+)\s+(passed|failed|skipped|deselected|xfailed|xpassed|errors?)\b/gi)) {
311
- const value = Number(match[1]);
312
- const kind = match[2]?.toLowerCase();
313
- if (kind === "passed" && counts.testsPassed === undefined) {
314
- counts.testsPassed = value;
315
- }
316
- if ((kind === "failed" || kind === "error" || kind === "errors") && counts.testsFailed === undefined) {
317
- counts.testsFailed = value;
318
- }
319
- if ((kind === "skipped" || kind === "deselected" || kind === "xfailed" || kind === "xpassed") && counts.testsSkipped === undefined) {
320
- counts.testsSkipped = value;
321
- }
322
- }
323
- for (const match of text.matchAll(/^\s*(?:ℹ\s*)?(tests?|pass|fail|cancelled|skipped|todo)\s+(\d+)\b/gim)) {
324
- const kind = match[1]?.toLowerCase();
325
- const value = Number(match[2]);
326
- if (kind === "test" || kind === "tests") {
327
- counts.testsTotal ??= value;
328
- }
329
- if (kind === "pass") {
330
- counts.testsPassed ??= value;
331
- }
332
- if (kind === "fail") {
333
- counts.testsFailed ??= value;
334
- }
335
- if (kind === "skipped") {
336
- counts.testsSkipped ??= value;
337
- }
338
- }
339
- const suitesLine = /Test Suites?:\s*(?:(\d+)\s+failed,?\s*)?(?:(\d+)\s+passed,?\s*)?(?:(\d+)\s+total)?/i.exec(text);
340
- if (suitesLine?.[1]) {
341
- counts.suitesFailed = Number(suitesLine[1]);
342
- }
343
- if (suitesLine?.[2]) {
344
- counts.suitesPassed = Number(suitesLine[2]);
345
- }
346
- if (suitesLine?.[3]) {
347
- counts.suitesTotal = Number(suitesLine[3]);
348
- }
349
- return counts;
338
+ const counts = {};
339
+ const testsLine = /Tests?:\s*(?:(\d+)\s+failed,?\s*)?(?:(\d+)\s+passed,?\s*)?(?:(\d+)\s+total)?/i.exec(text);
340
+ if (testsLine?.[1]) {
341
+ counts.testsFailed = Number(testsLine[1]);
342
+ }
343
+ if (testsLine?.[2]) {
344
+ counts.testsPassed = Number(testsLine[2]);
345
+ }
346
+ if (testsLine?.[3]) {
347
+ counts.testsTotal = Number(testsLine[3]);
348
+ }
349
+ for (const match of text.matchAll(/\b(\d+)\s+(passed|failed|skipped|deselected|xfailed|xpassed|errors?)\b/gi)) {
350
+ const value = Number(match[1]);
351
+ const kind = match[2]?.toLowerCase();
352
+ if (kind === "passed" && counts.testsPassed === undefined) {
353
+ counts.testsPassed = value;
354
+ }
355
+ if ((kind === "failed" || kind === "error" || kind === "errors") && counts.testsFailed === undefined) {
356
+ counts.testsFailed = value;
357
+ }
358
+ if (
359
+ (kind === "skipped" || kind === "deselected" || kind === "xfailed" || kind === "xpassed") &&
360
+ counts.testsSkipped === undefined
361
+ ) {
362
+ counts.testsSkipped = value;
363
+ }
364
+ }
365
+ for (const match of text.matchAll(/^\s*(?:ℹ\s*)?(tests?|pass|fail|cancelled|skipped|todo)\s+(\d+)\b/gim)) {
366
+ const kind = match[1]?.toLowerCase();
367
+ const value = Number(match[2]);
368
+ if (kind === "test" || kind === "tests") {
369
+ counts.testsTotal ??= value;
370
+ }
371
+ if (kind === "pass") {
372
+ counts.testsPassed ??= value;
373
+ }
374
+ if (kind === "fail") {
375
+ counts.testsFailed ??= value;
376
+ }
377
+ if (kind === "skipped") {
378
+ counts.testsSkipped ??= value;
379
+ }
380
+ }
381
+ const suitesLine = /Test Suites?:\s*(?:(\d+)\s+failed,?\s*)?(?:(\d+)\s+passed,?\s*)?(?:(\d+)\s+total)?/i.exec(text);
382
+ if (suitesLine?.[1]) {
383
+ counts.suitesFailed = Number(suitesLine[1]);
384
+ }
385
+ if (suitesLine?.[2]) {
386
+ counts.suitesPassed = Number(suitesLine[2]);
387
+ }
388
+ if (suitesLine?.[3]) {
389
+ counts.suitesTotal = Number(suitesLine[3]);
390
+ }
391
+ return counts;
350
392
  }
351
393
  function testSummaryText(counts, status, exitCode) {
352
- const parts = [];
353
- if (counts.testsFailed !== undefined) {
354
- parts.push(`${counts.testsFailed} failed`);
355
- }
356
- if (counts.testsPassed !== undefined) {
357
- parts.push(`${counts.testsPassed} passed`);
358
- }
359
- if (counts.testsTotal !== undefined) {
360
- parts.push(`${counts.testsTotal} total`);
361
- }
362
- return parts.length > 0
363
- ? `Test runner output parsed (${parts.join(", ")}).`
364
- : `Test runner output parsed for command ${status} with exitCode=${exitCode}.`;
394
+ const parts = [];
395
+ if (counts.testsFailed !== undefined) {
396
+ parts.push(`${counts.testsFailed} failed`);
397
+ }
398
+ if (counts.testsPassed !== undefined) {
399
+ parts.push(`${counts.testsPassed} passed`);
400
+ }
401
+ if (counts.testsTotal !== undefined) {
402
+ parts.push(`${counts.testsTotal} total`);
403
+ }
404
+ return parts.length > 0
405
+ ? `Test runner output parsed (${parts.join(", ")}).`
406
+ : `Test runner output parsed for command ${status} with exitCode=${exitCode}.`;
365
407
  }
366
408
  function diagnosticMatches(entries) {
367
- const matches = [];
368
- let headerEntry;
369
- for (const entry of entries) {
370
- const directReference = diagnosticReference(entry.line);
371
- if (directReference) {
372
- matches.push({ entry, reference: directReference });
373
- headerEntry = undefined;
374
- continue;
375
- }
376
- const header = /^\s*(.+\.(?:ts|tsx|js|jsx))\s*$/.exec(entry.line);
377
- if (header) {
378
- headerEntry = entry;
379
- continue;
380
- }
381
- const stylish = /^\s*(\d+):(\d+)\s+(error|warning)\s+(.+?)(?:\s{2,}([@\w./-]+))?\s*$/.exec(entry.line);
382
- if (stylish && headerEntry) {
383
- const reference = {
384
- path: headerEntry.line.trim(),
385
- line: Number(stylish[1]),
386
- column: Number(stylish[2]),
387
- severity: stylish[3]?.toLowerCase() ?? "error",
388
- message: stylish[4] ?? "",
389
- };
390
- if (stylish[5] !== undefined) {
391
- reference.code = stylish[5];
392
- }
393
- matches.push({ entry, headerEntry, reference });
394
- }
395
- }
396
- return matches;
409
+ const matches = [];
410
+ let headerEntry;
411
+ for (const entry of entries) {
412
+ const directReference = diagnosticReference(entry.line);
413
+ if (directReference) {
414
+ matches.push({ entry, reference: directReference });
415
+ headerEntry = undefined;
416
+ continue;
417
+ }
418
+ const header = /^\s*(.+\.(?:ts|tsx|js|jsx))\s*$/.exec(entry.line);
419
+ if (header) {
420
+ headerEntry = entry;
421
+ continue;
422
+ }
423
+ const stylish = /^\s*(\d+):(\d+)\s+(error|warning)\s+(.+?)(?:\s{2,}([@\w./-]+))?\s*$/.exec(entry.line);
424
+ if (stylish && headerEntry) {
425
+ const reference = {
426
+ path: headerEntry.line.trim(),
427
+ line: Number(stylish[1]),
428
+ column: Number(stylish[2]),
429
+ severity: stylish[3]?.toLowerCase() ?? "error",
430
+ message: stylish[4] ?? "",
431
+ };
432
+ if (stylish[5] !== undefined) {
433
+ reference.code = stylish[5];
434
+ }
435
+ matches.push({ entry, headerEntry, reference });
436
+ }
437
+ }
438
+ return matches;
397
439
  }
398
440
  function diagnosticImportantEntries(matches) {
399
- const selected = [];
400
- const seen = new Set();
401
- for (const match of matches) {
402
- if (match.headerEntry && !seen.has(match.headerEntry.lineNumber)) {
403
- selected.push(match.headerEntry);
404
- seen.add(match.headerEntry.lineNumber);
405
- }
406
- if (!seen.has(match.entry.lineNumber)) {
407
- selected.push(match.entry);
408
- seen.add(match.entry.lineNumber);
409
- }
410
- }
411
- return selected.sort((a, b) => a.lineNumber - b.lineNumber);
441
+ const selected = [];
442
+ const seen = new Set();
443
+ for (const match of matches) {
444
+ if (match.headerEntry && !seen.has(match.headerEntry.lineNumber)) {
445
+ selected.push(match.headerEntry);
446
+ seen.add(match.headerEntry.lineNumber);
447
+ }
448
+ if (!seen.has(match.entry.lineNumber)) {
449
+ selected.push(match.entry);
450
+ seen.add(match.entry.lineNumber);
451
+ }
452
+ }
453
+ return selected.sort((a, b) => a.lineNumber - b.lineNumber);
412
454
  }
413
455
  function diagnosticReference(line) {
414
- const tsc = /^(.*?\.(?:ts|tsx|js|jsx))\((\d+),(\d+)\):\s+(error|warning)\s+(TS\d+):\s+(.+)$/.exec(line);
415
- if (tsc) {
416
- return {
417
- path: tsc[1] ?? "",
418
- line: Number(tsc[2]),
419
- column: Number(tsc[3]),
420
- code: tsc[5] ?? "",
421
- severity: tsc[4]?.toLowerCase() ?? "error",
422
- message: tsc[6] ?? "",
423
- };
424
- }
425
- const lint = /^(.*?\.(?:ts|tsx|js|jsx)):(\d+):(\d+)\s+(error|warning)\s+(.+?)(?:\s{2,}([@\w./-]+))?$/.exec(line);
426
- if (lint) {
427
- const reference = {
428
- path: lint[1] ?? "",
429
- line: Number(lint[2]),
430
- column: Number(lint[3]),
431
- severity: lint[4]?.toLowerCase() ?? "error",
432
- message: lint[5] ?? "",
433
- };
434
- if (lint[6] !== undefined) {
435
- reference.code = lint[6];
436
- }
437
- return reference;
456
+ const tsc = /^(.*?\.(?:ts|tsx|js|jsx))\((\d+),(\d+)\):\s+(error|warning)\s+(TS\d+):\s+(.+)$/.exec(line);
457
+ if (tsc) {
458
+ return {
459
+ path: tsc[1] ?? "",
460
+ line: Number(tsc[2]),
461
+ column: Number(tsc[3]),
462
+ code: tsc[5] ?? "",
463
+ severity: tsc[4]?.toLowerCase() ?? "error",
464
+ message: tsc[6] ?? "",
465
+ };
466
+ }
467
+ const lint = /^(.*?\.(?:ts|tsx|js|jsx)):(\d+):(\d+)\s+(error|warning)\s+(.+?)(?:\s{2,}([@\w./-]+))?$/.exec(line);
468
+ if (lint) {
469
+ const reference = {
470
+ path: lint[1] ?? "",
471
+ line: Number(lint[2]),
472
+ column: Number(lint[3]),
473
+ severity: lint[4]?.toLowerCase() ?? "error",
474
+ message: lint[5] ?? "",
475
+ };
476
+ if (lint[6] !== undefined) {
477
+ reference.code = lint[6];
438
478
  }
439
- return null;
479
+ return reference;
480
+ }
481
+ return null;
440
482
  }
441
483
  function diagnosticCounts(references) {
442
- return {
443
- errors: references.filter((reference) => reference.severity === "error").length,
444
- warnings: references.filter((reference) => reference.severity === "warning").length,
445
- };
484
+ return {
485
+ errors: references.filter((reference) => reference.severity === "error").length,
486
+ warnings: references.filter((reference) => reference.severity === "warning").length,
487
+ };
446
488
  }
447
489
  function commandLooksLikeTestRunner(command) {
448
- return (/^\s*(?:npm|pnpm|yarn)\s+(?:run\s+)?(?:test|tests)\b/i.test(command) ||
449
- /^\s*(?:npx\s+)?(?:jest|vitest|mocha|tap|pytest)\b/i.test(command) ||
450
- /(?:^|\s)cargo\s+test\b/i.test(command) ||
451
- /(?:^|\s)go\s+test\b/i.test(command) ||
452
- /^\s*node\s+--test\b/i.test(command));
490
+ return (
491
+ /^\s*(?:npm|pnpm|yarn)\s+(?:run\s+)?(?:test|tests)\b/i.test(command) ||
492
+ /^\s*(?:npx\s+)?(?:jest|vitest|mocha|tap|pytest)\b/i.test(command) ||
493
+ /(?:^|\s)cargo\s+test\b/i.test(command) ||
494
+ /(?:^|\s)go\s+test\b/i.test(command) ||
495
+ /^\s*node\s+--test\b/i.test(command)
496
+ );
453
497
  }
454
498
  function commandLooksLikeTypeScriptOrLint(command) {
455
- return (/\b(?:tsc|typecheck|eslint|biome|lint)\b/i.test(command) ||
456
- /^\s*(?:npm|pnpm|yarn)\s+(?:run\s+)?(?:build|typecheck|lint)\b/i.test(command));
499
+ return (
500
+ /\b(?:tsc|typecheck|eslint|biome|lint)\b/i.test(command) ||
501
+ /^\s*(?:npm|pnpm|yarn)\s+(?:run\s+)?(?:build|typecheck|lint)\b/i.test(command)
502
+ );
457
503
  }
458
504
  function commandLooksLikeBuildTool(command) {
459
- return (/^\s*(?:npm|pnpm|yarn)\s+(?:run\s+)?(?:build|install|ci)\b/i.test(command) ||
460
- /^\s*(?:npx\s+)?(?:webpack|rollup|vite|esbuild|babel)\b/i.test(command) ||
461
- /^\s*(?:build|compile)\b/i.test(command) ||
462
- /(?:^|\s)cargo\s+build\b/i.test(command) ||
463
- /(?:^|\s)go\s+build\b/i.test(command));
505
+ return (
506
+ /^\s*(?:npm|pnpm|yarn)\s+(?:run\s+)?(?:build|install|ci)\b/i.test(command) ||
507
+ /^\s*(?:npx\s+)?(?:webpack|rollup|vite|esbuild|babel)\b/i.test(command) ||
508
+ /^\s*(?:build|compile)\b/i.test(command) ||
509
+ /(?:^|\s)cargo\s+build\b/i.test(command) ||
510
+ /(?:^|\s)go\s+build\b/i.test(command)
511
+ );
464
512
  }
465
513
  function isVerificationGoal(goal) {
466
- return Boolean(goal && /\b(verify|verification|test|tests|check|ci)\b/i.test(goal));
514
+ return Boolean(goal && /\b(verify|verification|test|tests|check|ci)\b/i.test(goal));
467
515
  }
468
516
  function countMatches(text, pattern) {
469
- return Array.from(text.matchAll(pattern)).length;
517
+ return Array.from(text.matchAll(pattern)).length;
470
518
  }
471
519
  function commandText(command) {
472
- return typeof command === "string" ? command : command.join(" ");
520
+ return typeof command === "string" ? command : command.join(" ");
473
521
  }