@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
@@ -0,0 +1,346 @@
1
+ import { mkdir, realpath } from "node:fs/promises";
2
+ import path from "node:path";
3
+
4
+ import { loadDefinition, selectDefinition } from "./definitions.mjs";
5
+ import { createInvocationId, fileIdentity, writeJson, writeText } from "./evidence.mjs";
6
+ import { gradeDeterministic } from "./grade.mjs";
7
+ import { runBody, runDescription, VariantSetupError } from "./pi.mjs";
8
+ import { prepareFixture } from "./sandbox.mjs";
9
+
10
+ const VARIANTS = ["baseline", "candidate"];
11
+ const DESCRIPTION_TOOLS = new Set(["read"]);
12
+ const BODY_TOOLS = new Set(["read", "write", "edit"]);
13
+
14
+ /**
15
+ * @param {string} definitionFile
16
+ * @param {any} selectors
17
+ * @param {{root?: string, signal?: AbortSignal}} options
18
+ */
19
+ export async function runEvaluation(definitionFile, selectors = {}, { root = process.cwd(), signal } = {}) {
20
+ const definitionPath = await realpath(path.resolve(root, definitionFile));
21
+ const definition = await loadDefinition(definitionPath, { root });
22
+ const selection = selectDefinition(definition, selectors);
23
+ assertSupportedSelection(selection);
24
+ const invocationId = createInvocationId();
25
+ const runsDirectory = path.join(root, ".skill-eval", "runs");
26
+ const resultDirectory = path.join(runsDirectory, invocationId);
27
+ await mkdir(runsDirectory, { recursive: true });
28
+ await mkdir(resultDirectory);
29
+ await writeJson(path.join(resultDirectory, "invocation.json"), {
30
+ schema_version: 1,
31
+ id: invocationId,
32
+ definition: definitionPath,
33
+ selection: {
34
+ group: selectors.group ?? null,
35
+ variant: selectors.variant ?? null,
36
+ groups: selection.groups.map((entry) => ({
37
+ id: entry.group.id,
38
+ position: entry.position,
39
+ variants: entry.variants,
40
+ })),
41
+ },
42
+ startedAt: new Date().toISOString(),
43
+ });
44
+
45
+ const groups = [];
46
+ for (const selected of selection.groups) {
47
+ groups.push(await runGroup({ selected, root, resultDirectory, signal }));
48
+ }
49
+ const state = batchState(groups);
50
+ const summary = {
51
+ schema_version: 1,
52
+ id: invocationId,
53
+ state,
54
+ definitionKind: selection.definitionKind,
55
+ groups,
56
+ completedAt: new Date().toISOString(),
57
+ };
58
+ await writeJson(path.join(resultDirectory, "summary.json"), summary);
59
+ return { id: invocationId, path: resultDirectory, state, summary };
60
+ }
61
+
62
+ function assertSupportedSelection(selection) {
63
+ for (const selected of selection.groups) {
64
+ const { group } = selected;
65
+ if (group.type !== "description" && group.type !== "body") {
66
+ throw new Error("skill-eval run currently supports description and body groups only");
67
+ }
68
+ if (group.expectations.some((expectation) => expectation.kind === "command")) {
69
+ throw new Error("command expectations are not supported");
70
+ }
71
+ const supportedTools = group.type === "body" ? BODY_TOOLS : DESCRIPTION_TOOLS;
72
+ if (group.tools.some((tool) => !supportedTools.has(tool))) {
73
+ throw new Error(`${group.type} execution currently supports only ${[...supportedTools].join(", ")} tools`);
74
+ }
75
+ }
76
+ }
77
+
78
+ async function runGroup({ selected, root, resultDirectory, signal }) {
79
+ const { group } = selected;
80
+ const groupDirectory = path.join(resultDirectory, "groups", group.id);
81
+ await mkdir(groupDirectory, { recursive: true });
82
+ await writeJson(path.join(groupDirectory, "definition.json"), group);
83
+
84
+ let fixture = null;
85
+ let fixtureError = null;
86
+ if (!signal?.aborted) {
87
+ try {
88
+ fixture = await prepareFixture({ declaredPath: group.fixture, root, groupDirectory });
89
+ } catch (error) {
90
+ fixtureError = error instanceof Error ? error.message : String(error);
91
+ }
92
+ }
93
+
94
+ const runs = {};
95
+ const runFiles = {};
96
+ for (const variant of VARIANTS) {
97
+ const variantDirectory = path.join(groupDirectory, variant);
98
+ await mkdir(variantDirectory, { recursive: true });
99
+ if (selected.variants[variant] === "not-selected") {
100
+ runs[variant] = notSelectedRun(group, variant);
101
+ } else if (signal?.aborted) {
102
+ runs[variant] = cancelledRun(group, variant);
103
+ } else if (fixtureError !== null) {
104
+ runs[variant] = invalidRun(group, variant, fixtureError);
105
+ } else {
106
+ runs[variant] = await executeVariant({ group, variant, root, variantDirectory, fixture, signal });
107
+ }
108
+ const persisted = await persistRunOrFailure(variantDirectory, runs[variant]);
109
+ runs[variant] = persisted.run;
110
+ runFiles[variant] = persisted.file;
111
+ }
112
+
113
+ const evidence = {
114
+ baseline: await fileIdentity(runFiles.baseline),
115
+ candidate: await fileIdentity(runFiles.candidate),
116
+ };
117
+ const grade = await createGrade(group, runs, evidence);
118
+ const persistedGrade = await persistGrade(groupDirectory, grade);
119
+ const selectedRuns = VARIANTS.filter((variant) => selected.variants[variant] === "selected").map(
120
+ (variant) => runs[variant],
121
+ );
122
+ const selectedState = selectedGroupState(selectedRuns, persistedGrade.grade);
123
+ const groupState = selectedState === "cancelled" ? selectedState : fixtureError === null ? selectedState : "invalid";
124
+ const groupResult = {
125
+ id: group.id,
126
+ position: selected.position,
127
+ state: groupState,
128
+ variants: Object.fromEntries(VARIANTS.map((variant) => [variant, runs[variant].state])),
129
+ grade: persistedGrade.grade.state,
130
+ artifacts: { grade: persistedGrade.artifact, group: "group.json" },
131
+ errors: persistedGrade.errors,
132
+ };
133
+ return persistGroupResult(groupDirectory, groupResult);
134
+ }
135
+
136
+ function batchState(groups) {
137
+ if (groups.some((group) => group.state === "cancelled")) return "cancelled";
138
+ if (groups.every((group) => group.state === "complete")) return "complete";
139
+ return "partially-complete";
140
+ }
141
+
142
+ function selectedGroupState(runs, grade) {
143
+ if (runs.some((run) => run.state === "cancelled")) return "cancelled";
144
+ if (runs.every((run) => run.state === "complete") && grade.state !== "grade-error") return "complete";
145
+ return "partially-complete";
146
+ }
147
+
148
+ async function createGrade(group, runs, evidence) {
149
+ try {
150
+ return await gradeDeterministic(group, runs, evidence);
151
+ } catch (error) {
152
+ return gradeErrorReport(evidence, `deterministic grading failed: ${errorMessage(error)}`);
153
+ }
154
+ }
155
+
156
+ async function persistGrade(groupDirectory, grade) {
157
+ const artifact = "deterministic-grade.json";
158
+ try {
159
+ await writeJson(path.join(groupDirectory, artifact), grade);
160
+ return { grade, artifact, errors: [] };
161
+ } catch (error) {
162
+ const reason = `failed to persist ${artifact}: ${errorMessage(error)}`;
163
+ const failed = gradeErrorReport(grade.evidence, reason, grade);
164
+ const fallback = "deterministic-grade-error.json";
165
+ await writeJson(path.join(groupDirectory, fallback), failed);
166
+ return {
167
+ grade: failed,
168
+ artifact: fallback,
169
+ errors: [{ kind: "persistence", artifact, message: reason }],
170
+ };
171
+ }
172
+ }
173
+
174
+ async function persistGroupResult(groupDirectory, groupResult) {
175
+ const artifact = "group.json";
176
+ try {
177
+ await writeJson(path.join(groupDirectory, artifact), groupResult);
178
+ return groupResult;
179
+ } catch (error) {
180
+ const message = `failed to persist ${artifact}: ${errorMessage(error)}`;
181
+ const fallback = "group-error.json";
182
+ const failed = {
183
+ ...groupResult,
184
+ state: groupResult.state === "complete" ? "partially-complete" : groupResult.state,
185
+ artifacts: { ...groupResult.artifacts, group: fallback },
186
+ errors: [...groupResult.errors, { kind: "persistence", artifact, message }],
187
+ };
188
+ await writeJson(path.join(groupDirectory, fallback), failed);
189
+ return failed;
190
+ }
191
+ }
192
+
193
+ function gradeErrorReport(evidence, reason, grade = null) {
194
+ return {
195
+ schema_version: 1,
196
+ state: "grade-error",
197
+ evidence,
198
+ checks: grade?.checks ?? [],
199
+ comparisons: grade?.comparisons ?? [],
200
+ errors: [...(grade?.errors ?? []), { id: null, reason }],
201
+ };
202
+ }
203
+
204
+ function errorMessage(error) {
205
+ return error instanceof Error ? error.message : String(error);
206
+ }
207
+
208
+ async function executeVariant({ group, variant, root, variantDirectory, fixture, signal }) {
209
+ try {
210
+ const run = group.type === "body" ? runBody : runDescription;
211
+ return await run({ group, variant, root, variantDirectory, fixture, signal });
212
+ } catch (error) {
213
+ if (error instanceof VariantSetupError) return invalidRun(group, variant, error.message);
214
+ return infrastructureFailedRun(group, variant, error);
215
+ }
216
+ }
217
+
218
+ async function persistRunOrFailure(variantDirectory, run) {
219
+ try {
220
+ return { run, file: await persistRun(variantDirectory, run) };
221
+ } catch (error) {
222
+ const failed = persistenceFailedRun(run, error);
223
+ const runFile = path.join(variantDirectory, "run.json");
224
+ await writeJson(runFile, {
225
+ ...failed,
226
+ transcript: failed.transcript ?? [],
227
+ artifacts: {
228
+ events: failed.process === undefined ? null : "events.jsonl",
229
+ final: null,
230
+ stderr: failed.process === undefined ? null : "stderr.log",
231
+ },
232
+ });
233
+ return { run: failed, file: runFile };
234
+ }
235
+ }
236
+
237
+ async function persistRun(variantDirectory, run) {
238
+ const transcript = run.transcript ?? [];
239
+ const response = run.response ?? "";
240
+ await writeJson(path.join(variantDirectory, "transcript.json"), transcript);
241
+ await writeText(path.join(variantDirectory, "final.md"), response === "" ? "" : `${response}\n`);
242
+ const runFile = path.join(variantDirectory, "run.json");
243
+ const hasProcessEvidence = run.process !== undefined;
244
+ await writeJson(runFile, {
245
+ ...run,
246
+ ...(Array.isArray(run.turns) ? { turns: externalizeTurnTranscripts(run.turns) } : {}),
247
+ transcript: "transcript.json",
248
+ artifacts: {
249
+ events: hasProcessEvidence ? "events.jsonl" : null,
250
+ final: "final.md",
251
+ stderr: hasProcessEvidence ? "stderr.log" : null,
252
+ },
253
+ });
254
+ return runFile;
255
+ }
256
+
257
+ function externalizeTurnTranscripts(turns) {
258
+ let offset = 0;
259
+ return turns.map((turn) => {
260
+ const length = Array.isArray(turn.transcript) ? turn.transcript.length : 0;
261
+ const transcript = { file: "transcript.json", start: offset, end: offset + length };
262
+ offset += length;
263
+ return { ...turn, transcript };
264
+ });
265
+ }
266
+
267
+ function notSelectedRun(group, variant) {
268
+ return {
269
+ schema_version: 1,
270
+ variant,
271
+ state: "not-selected",
272
+ evaluationType: group.type,
273
+ prompt: group.input.prompt ?? null,
274
+ prompts: group.input.turns ?? null,
275
+ activation: unavailableActivation(),
276
+ response: "",
277
+ transcript: [],
278
+ error: null,
279
+ };
280
+ }
281
+
282
+ function cancelledRun(group, variant) {
283
+ return {
284
+ schema_version: 1,
285
+ variant,
286
+ state: "cancelled",
287
+ evaluationType: group.type,
288
+ prompt: group.input.prompt ?? null,
289
+ prompts: group.input.turns ?? null,
290
+ activation: unavailableActivation(),
291
+ response: "",
292
+ transcript: [],
293
+ error: { kind: "cancellation", message: "Cancelled before subject execution" },
294
+ };
295
+ }
296
+
297
+ function invalidRun(group, variant, message) {
298
+ return {
299
+ schema_version: 1,
300
+ variant,
301
+ state: "invalid",
302
+ evaluationType: group.type,
303
+ prompt: group.input.prompt ?? null,
304
+ prompts: group.input.turns ?? null,
305
+ activation: unavailableActivation(),
306
+ response: "",
307
+ transcript: [],
308
+ error: { kind: "setup", message },
309
+ };
310
+ }
311
+
312
+ function persistenceFailedRun(run, error) {
313
+ return {
314
+ ...run,
315
+ state: "infrastructure-failed",
316
+ error: {
317
+ kind: "persistence",
318
+ message: error instanceof Error ? error.message : String(error),
319
+ cause: run.error ?? null,
320
+ },
321
+ };
322
+ }
323
+
324
+ function infrastructureFailedRun(group, variant, error) {
325
+ return {
326
+ schema_version: 1,
327
+ variant,
328
+ state: "infrastructure-failed",
329
+ evaluationType: group.type,
330
+ prompt: group.input.prompt ?? null,
331
+ prompts: group.input.turns ?? null,
332
+ activation: unavailableActivation(),
333
+ response: "",
334
+ transcript: [],
335
+ error: { kind: "infrastructure", message: error instanceof Error ? error.message : String(error) },
336
+ };
337
+ }
338
+
339
+ function unavailableActivation() {
340
+ return {
341
+ targetRead: null,
342
+ firstReadTurn: null,
343
+ readTurns: [],
344
+ successfulReadPaths: [],
345
+ };
346
+ }