@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
@@ -8,19 +8,52 @@ export declare const EXECUTION_STATUSES: readonly ["success", "failed", "timed_o
8
8
  export type ExecutionStatus = (typeof EXECUTION_STATUSES)[number];
9
9
  export declare const ROUTING_STATUSES: readonly ["routed", "passed_through", "partial", "failed"];
10
10
  export type RoutingStatus = (typeof ROUTING_STATUSES)[number];
11
- export declare const ROUTE_KINDS: readonly ["retrieve", "run", "transform", "batch", "observed", "safety-net", "pass-through"];
11
+ export declare const ROUTE_KINDS: readonly [
12
+ "retrieve",
13
+ "run",
14
+ "transform",
15
+ "batch",
16
+ "observed",
17
+ "safety-net",
18
+ "pass-through",
19
+ ];
12
20
  export type RouteKind = (typeof ROUTE_KINDS)[number];
13
21
  export declare const BATCH_STEP_KINDS: readonly ["run", "search"];
14
22
  export type BatchStepKind = (typeof BATCH_STEP_KINDS)[number];
15
- export declare const PRODUCER_KINDS: readonly ["command", "script", "native", "repo", "web", "fetch", "code_search", "mcp", "transform", "other"];
23
+ export declare const PRODUCER_KINDS: readonly [
24
+ "command",
25
+ "script",
26
+ "native",
27
+ "repo",
28
+ "web",
29
+ "fetch",
30
+ "code_search",
31
+ "mcp",
32
+ "transform",
33
+ "other",
34
+ ];
16
35
  export type ProducerKind = (typeof PRODUCER_KINDS)[number];
17
36
  export declare const PERSISTENCE_STATUSES: readonly ["vaulted", "redacted", "metadata_only", "not_persisted"];
18
37
  export type PersistenceStatus = (typeof PERSISTENCE_STATUSES)[number];
19
38
  export declare const RECOVERABILITY_MODES: readonly ["exact", "redacted", "metadata_only", "none"];
20
39
  export type RecoverabilityMode = (typeof RECOVERABILITY_MODES)[number];
21
- export declare const ROUTER_FAILURE_KINDS: readonly ["adapter_unavailable", "storage_failure", "observed_routing_failure", "script_transform_disabled", "transform_source_unavailable", "transform_validation_failure", "transform_execution_failure"];
40
+ export declare const ROUTER_FAILURE_KINDS: readonly [
41
+ "adapter_unavailable",
42
+ "storage_failure",
43
+ "observed_routing_failure",
44
+ "script_transform_disabled",
45
+ "transform_source_unavailable",
46
+ "transform_validation_failure",
47
+ "transform_execution_failure",
48
+ ];
22
49
  export type RouterFailureKind = (typeof ROUTER_FAILURE_KINDS)[number];
23
- export declare const FAILURE_EXECUTION_STATUSES: readonly ["unavailable", "unsupported", "rejected", "failed", "partial"];
50
+ export declare const FAILURE_EXECUTION_STATUSES: readonly [
51
+ "unavailable",
52
+ "unsupported",
53
+ "rejected",
54
+ "failed",
55
+ "partial",
56
+ ];
24
57
  export type FailureExecutionStatus = (typeof FAILURE_EXECUTION_STATUSES)[number];
25
58
  export declare const EVIDENCE_WINDOWS: readonly ["exact", "small", "lines_30", "lines_80", "section", "full"];
26
59
  export type EvidenceWindow = (typeof EVIDENCE_WINDOWS)[number];
@@ -39,453 +72,472 @@ export type ObservedRoutingPersistenceMode = (typeof OBSERVED_ROUTING_PERSISTENC
39
72
  export declare const RESERVED_OBSERVED_ROUTING_PERSISTENCE_MODES: readonly ["redacted"];
40
73
  export type ReservedObservedRoutingPersistenceMode = (typeof RESERVED_OBSERVED_ROUTING_PERSISTENCE_MODES)[number];
41
74
  export interface RepoSourceRef {
42
- kind: "repo";
43
- path: string;
75
+ kind: "repo";
76
+ path: string;
44
77
  }
45
78
  export interface VaultSourceRef {
46
- kind: "vault";
47
- outputId: string;
48
- stream?: OutputStream;
79
+ kind: "vault";
80
+ outputId: string;
81
+ stream?: OutputStream;
82
+ }
83
+ export interface LocalSourceRef {
84
+ kind: "local";
85
+ root: string;
86
+ path: string;
49
87
  }
50
88
  export interface NativeToolSourceRef {
51
- kind: "native";
52
- tool: string;
53
- outputId: string;
89
+ kind: "native";
90
+ tool: string;
91
+ outputId: string;
54
92
  }
55
- export type SourceRef = RepoSourceRef | VaultSourceRef | NativeToolSourceRef;
93
+ export type SourceRef = RepoSourceRef | VaultSourceRef | LocalSourceRef | NativeToolSourceRef;
56
94
  export interface ProducerDescriptor {
57
- kind: ProducerKind;
58
- adapter?: string;
59
- name?: string;
60
- server?: string;
61
- tool?: string;
95
+ kind: ProducerKind;
96
+ adapter?: string;
97
+ name?: string;
98
+ server?: string;
99
+ tool?: string;
62
100
  }
63
101
  export interface EvidencePersistence {
64
- status: PersistenceStatus;
65
- recoverability: RecoverabilityMode;
66
- recoveryOutputId?: string;
67
- outputId?: string;
102
+ status: PersistenceStatus;
103
+ recoverability: RecoverabilityMode;
104
+ recoveryOutputId?: string;
105
+ outputId?: string;
68
106
  }
69
107
  export interface EvidenceLineage {
70
- sourceRecordIds?: string[];
71
- sourceOutputIds?: string[];
72
- operation?: string;
73
- operationHash?: string;
108
+ sourceRecordIds?: string[];
109
+ sourceOutputIds?: string[];
110
+ operation?: string;
111
+ operationHash?: string;
74
112
  }
75
113
  export interface RouterFailure {
76
- kind: RouterFailureKind;
77
- message: string;
114
+ kind: RouterFailureKind;
115
+ message: string;
78
116
  }
79
117
  export interface TransformExecutionFailure {
80
- status: FailureExecutionStatus;
81
- failureKind: RouterFailureKind;
82
- message: string;
118
+ status: FailureExecutionStatus;
119
+ failureKind: RouterFailureKind;
120
+ message: string;
83
121
  }
84
122
  export interface EvidenceRecordIdentity {
85
- recordId: string;
86
- recoveryOutputId?: string;
87
- outputId?: string;
123
+ recordId: string;
124
+ recoveryOutputId?: string;
125
+ outputId?: string;
88
126
  }
89
127
  export interface EvidenceMatchMetadata {
90
- type: "exact_phrase" | "lexical" | "metadata";
91
- confidence: number;
128
+ type: "exact_phrase" | "lexical" | "metadata";
129
+ confidence: number;
92
130
  }
93
131
  export interface EvidencePacket {
94
- id: string;
95
- source: SourceRef;
96
- excerpt: string;
97
- why: string;
98
- window: EvidenceWindow;
99
- expandable: boolean;
100
- path?: string;
101
- lines?: string;
102
- match?: EvidenceMatchMetadata;
132
+ id: string;
133
+ source: SourceRef;
134
+ excerpt: string;
135
+ why: string;
136
+ window: EvidenceWindow;
137
+ expandable: boolean;
138
+ path?: string;
139
+ lines?: string;
140
+ match?: EvidenceMatchMetadata;
103
141
  }
104
142
  export interface RecoveryHint {
105
- how: string;
106
- outputId?: string;
107
- evidenceId?: string;
143
+ how: string;
144
+ outputId?: string;
145
+ evidenceId?: string;
108
146
  }
109
147
  export interface RoutingDecision {
110
- status: RoutingStatus;
111
- route: RouteKind;
112
- reason: string;
148
+ status: RoutingStatus;
149
+ route: RouteKind;
150
+ reason: string;
113
151
  }
114
152
  export interface CommandExecution {
115
- status: ExecutionStatus;
116
- exitCode: number | null;
117
- durationMs?: number;
153
+ status: ExecutionStatus;
154
+ exitCode: number | null;
155
+ durationMs?: number;
118
156
  }
119
157
  export interface ImportantLine {
120
- stream: Exclude<OutputStream, "raw">;
121
- lines: string;
122
- excerpt: string;
158
+ stream: Exclude<OutputStream, "raw">;
159
+ lines: string;
160
+ excerpt: string;
123
161
  }
124
162
  export interface CommandParserReference {
125
- path: string;
126
- line?: number;
127
- column?: number;
128
- code?: string;
129
- severity?: "error" | "warning" | "info";
130
- message: string;
163
+ path: string;
164
+ line?: number;
165
+ column?: number;
166
+ code?: string;
167
+ severity?: "error" | "warning" | "info";
168
+ message: string;
131
169
  }
132
170
  export interface RunOutputFilterMetadata {
133
- stream: Exclude<OutputStream, "raw">;
134
- include?: string[];
135
- exclude?: string[];
136
- flags?: string;
137
- head?: number;
138
- tail?: number;
139
- maxLines?: number;
140
- maxBytes?: number;
141
- sourceLines: number;
142
- selectedLines: number;
143
- fallbackPreservedFailureEvidence?: boolean;
171
+ stream: Exclude<OutputStream, "raw">;
172
+ include?: string[];
173
+ exclude?: string[];
174
+ flags?: string;
175
+ head?: number;
176
+ tail?: number;
177
+ maxLines?: number;
178
+ maxBytes?: number;
179
+ sourceLines: number;
180
+ selectedLines: number;
181
+ fallbackPreservedFailureEvidence?: boolean;
144
182
  }
145
183
  export interface RunScriptProducerMetadata {
146
- status: "success" | "failed" | "timed_out" | "policy_violation" | "unavailable";
147
- language: ScriptTransformLanguage;
148
- policy: "sandboxed";
149
- rawScriptPersistence: ScriptTransformRawScriptPersistence;
150
- codeSha256: string;
151
- limits: ScriptTransformLimits;
152
- label?: string;
153
- adapterId?: string;
154
- adapterVersion?: string;
155
- runtime?: {
156
- name: string;
157
- version?: string;
158
- };
159
- stdoutBytes?: number;
160
- stderrBytes?: number;
161
- exitCode?: number | null;
162
- durationMs?: number;
163
- operation?: Record<string, unknown>;
164
- failure?: RouterFailure;
165
- transformExecution?: TransformExecutionFailure;
184
+ status: "success" | "failed" | "timed_out" | "policy_violation" | "unavailable";
185
+ language: ScriptTransformLanguage;
186
+ policy: "sandboxed";
187
+ rawScriptPersistence: ScriptTransformRawScriptPersistence;
188
+ codeSha256: string;
189
+ limits: ScriptTransformLimits;
190
+ label?: string;
191
+ adapterId?: string;
192
+ adapterVersion?: string;
193
+ runtime?: {
194
+ name: string;
195
+ version?: string;
196
+ };
197
+ stdoutBytes?: number;
198
+ stderrBytes?: number;
199
+ exitCode?: number | null;
200
+ durationMs?: number;
201
+ operation?: Record<string, unknown>;
202
+ failure?: RouterFailure;
203
+ transformExecution?: TransformExecutionFailure;
166
204
  }
167
205
  export interface RunScriptFilterMetadata {
168
- status: "success" | FailureExecutionStatus;
169
- language: ScriptTransformLanguage;
170
- sourceAliases: string[];
171
- rawOutputId: string;
172
- label?: string;
173
- operation?: Record<string, unknown>;
174
- outputId?: string;
175
- recordId?: string;
176
- persistence?: EvidencePersistence;
177
- lineage?: EvidenceLineage;
178
- failure?: RouterFailure;
179
- transformExecution?: TransformExecutionFailure;
180
- summary?: string;
206
+ status: "success" | FailureExecutionStatus;
207
+ language: ScriptTransformLanguage;
208
+ sourceAliases: string[];
209
+ rawOutputId: string;
210
+ label?: string;
211
+ operation?: Record<string, unknown>;
212
+ outputId?: string;
213
+ recordId?: string;
214
+ persistence?: EvidencePersistence;
215
+ lineage?: EvidenceLineage;
216
+ failure?: RouterFailure;
217
+ transformExecution?: TransformExecutionFailure;
218
+ summary?: string;
181
219
  }
182
220
  export interface RunReducerMetadata {
183
- status: "selected" | "success";
221
+ status: "selected" | "success";
222
+ name: string;
223
+ version: string;
224
+ confidence: number;
225
+ rawOutputId: string;
226
+ facts: Array<{
184
227
  name: string;
185
- version: string;
186
- confidence: number;
187
- rawOutputId: string;
188
- facts: Array<{
189
- name: string;
190
- value: string | number | boolean;
191
- }>;
192
- summary?: string;
193
- outputId?: string;
194
- recordId?: string;
195
- persistence?: EvidencePersistence;
196
- lineage?: EvidenceLineage;
228
+ value: string | number | boolean;
229
+ }>;
230
+ summary?: string;
231
+ outputId?: string;
232
+ recordId?: string;
233
+ persistence?: EvidencePersistence;
234
+ lineage?: EvidenceLineage;
197
235
  }
198
236
  export interface CommandParserMetadata {
199
- name: string;
200
- confidence: number;
201
- fidelity: "exact" | "lossy";
202
- compressed: boolean;
203
- counts?: Record<string, number>;
204
- references?: CommandParserReference[];
237
+ name: string;
238
+ confidence: number;
239
+ fidelity: "exact" | "lossy";
240
+ compressed: boolean;
241
+ counts?: Record<string, number>;
242
+ references?: CommandParserReference[];
205
243
  }
206
244
  export interface RoutedResultBase {
207
- toolStatus: ToolStatus;
208
- decisionId: string;
209
- preserve: PreserveMode;
210
- routing: RoutingDecision;
211
- recordId?: string;
212
- producer?: ProducerDescriptor;
213
- persistence?: EvidencePersistence;
214
- lineage?: EvidenceLineage;
215
- failure?: RouterFailure;
216
- transformExecution?: TransformExecutionFailure;
217
- recovery?: RecoveryHint;
218
- evidence?: EvidencePacket[];
245
+ toolStatus: ToolStatus;
246
+ decisionId: string;
247
+ preserve: PreserveMode;
248
+ routing: RoutingDecision;
249
+ recordId?: string;
250
+ producer?: ProducerDescriptor;
251
+ persistence?: EvidencePersistence;
252
+ lineage?: EvidenceLineage;
253
+ failure?: RouterFailure;
254
+ transformExecution?: TransformExecutionFailure;
255
+ recovery?: RecoveryHint;
256
+ evidence?: EvidencePacket[];
219
257
  }
220
258
  export interface RetrievalRoutedResult extends RoutedResultBase {
221
- source?: SourceRef;
259
+ source?: SourceRef;
222
260
  }
223
261
  export interface CommandRoutedResult extends RoutedResultBase {
224
- outputId: string;
225
- execution: CommandExecution;
226
- summary?: string;
227
- importantLines?: ImportantLine[];
228
- parser?: CommandParserMetadata;
229
- filters?: RunOutputFilterMetadata;
230
- scriptProducer?: RunScriptProducerMetadata;
231
- scriptFilter?: RunScriptFilterMetadata;
232
- reducer?: RunReducerMetadata;
262
+ outputId: string;
263
+ execution: CommandExecution;
264
+ summary?: string;
265
+ importantLines?: ImportantLine[];
266
+ parser?: CommandParserMetadata;
267
+ filters?: RunOutputFilterMetadata;
268
+ scriptProducer?: RunScriptProducerMetadata;
269
+ scriptFilter?: RunScriptFilterMetadata;
270
+ reducer?: RunReducerMetadata;
233
271
  }
234
272
  export interface ObservedHostDescriptor {
235
- name: string;
236
- toolName: string;
273
+ name: string;
274
+ toolName: string;
237
275
  }
238
276
  export declare const OBSERVED_PRODUCER_RISK_CLASSES: readonly ["read", "write", "unknown"];
239
277
  export type ObservedProducerRiskClass = (typeof OBSERVED_PRODUCER_RISK_CLASSES)[number];
240
- export declare const OBSERVED_PRODUCER_RISK_SOURCES: readonly ["configured", "mcp_annotation", "manifest", "heuristic", "unknown"];
278
+ export declare const OBSERVED_PRODUCER_RISK_SOURCES: readonly [
279
+ "configured",
280
+ "mcp_annotation",
281
+ "manifest",
282
+ "heuristic",
283
+ "unknown",
284
+ ];
241
285
  export type ObservedProducerRiskSource = (typeof OBSERVED_PRODUCER_RISK_SOURCES)[number];
242
286
  export interface ObservedProducerRisk {
243
- classification: ObservedProducerRiskClass;
244
- source: ObservedProducerRiskSource;
245
- reason: string;
287
+ classification: ObservedProducerRiskClass;
288
+ source: ObservedProducerRiskSource;
289
+ reason: string;
246
290
  }
247
291
  export interface ObservedOutputNormalization {
248
- shape: "text" | "json" | "content_blocks" | "stdio" | "structured";
249
- mediaType?: string;
250
- byteCount: number;
251
- lineCount: number;
292
+ shape: "text" | "json" | "content_blocks" | "stdio" | "structured";
293
+ mediaType?: string;
294
+ byteCount: number;
295
+ lineCount: number;
252
296
  }
253
297
  export interface ObservedRoutedResult extends RoutedResultBase {
254
- outputId?: string;
255
- host: ObservedHostDescriptor;
256
- normalized: ObservedOutputNormalization;
257
- risk?: ObservedProducerRisk;
258
- summary?: string;
259
- passthrough?: {
260
- text: string;
261
- reason: string;
262
- };
298
+ outputId?: string;
299
+ host: ObservedHostDescriptor;
300
+ normalized: ObservedOutputNormalization;
301
+ risk?: ObservedProducerRisk;
302
+ summary?: string;
303
+ passthrough?: {
304
+ text: string;
305
+ reason: string;
306
+ };
263
307
  }
264
308
  export interface TransformRoutedResult extends RoutedResultBase {
265
- outputId: string;
266
- source: SourceRef;
267
- operation: Record<string, unknown>;
268
- summary?: string;
309
+ outputId: string;
310
+ source: SourceRef;
311
+ operation: Record<string, unknown>;
312
+ summary?: string;
269
313
  }
270
314
  export interface BatchStepRoutedResult {
271
- id: string;
272
- index: number;
273
- kind: BatchStepKind;
274
- status: "ok" | "failed";
275
- toolStatus?: ToolStatus;
276
- durationMs: number;
277
- result?: RoutedResult;
278
- error?: string;
315
+ id: string;
316
+ index: number;
317
+ kind: BatchStepKind;
318
+ status: "ok" | "failed";
319
+ toolStatus?: ToolStatus;
320
+ durationMs: number;
321
+ result?: RoutedResult;
322
+ error?: string;
279
323
  }
280
324
  export interface BatchQueryMatch {
281
- stepId: string;
282
- stepIndex: number;
283
- stepKind: BatchStepKind;
284
- source: SourceRef;
285
- excerpt: string;
286
- why: string;
287
- score: number;
288
- outputId?: string;
289
- evidenceId?: string;
290
- lines?: string;
325
+ stepId: string;
326
+ stepIndex: number;
327
+ stepKind: BatchStepKind;
328
+ source: SourceRef;
329
+ excerpt: string;
330
+ why: string;
331
+ score: number;
332
+ outputId?: string;
333
+ evidenceId?: string;
334
+ lines?: string;
291
335
  }
292
336
  export interface BatchQueryAnswer {
293
- query: string;
294
- status: "answered" | "no_match";
295
- summary: string;
296
- matches: BatchQueryMatch[];
337
+ query: string;
338
+ status: "answered" | "no_match";
339
+ summary: string;
340
+ matches: BatchQueryMatch[];
297
341
  }
298
342
  export interface BatchRoutedResult extends RoutedResultBase {
299
- summary: string;
300
- concurrency: number;
301
- stepCount: number;
302
- okCount: number;
303
- failedCount: number;
304
- steps: BatchStepRoutedResult[];
305
- queries?: BatchQueryAnswer[];
343
+ summary: string;
344
+ concurrency: number;
345
+ stepCount: number;
346
+ okCount: number;
347
+ failedCount: number;
348
+ steps: BatchStepRoutedResult[];
349
+ queries?: BatchQueryAnswer[];
306
350
  }
307
351
  export interface FailureRoutedResult extends RoutedResultBase {
308
- outputId?: string;
309
- }
310
- export type RoutedResult = RetrievalRoutedResult | CommandRoutedResult | ObservedRoutedResult | TransformRoutedResult | BatchRoutedResult | FailureRoutedResult;
352
+ outputId?: string;
353
+ }
354
+ export type RoutedResult =
355
+ | RetrievalRoutedResult
356
+ | CommandRoutedResult
357
+ | ObservedRoutedResult
358
+ | TransformRoutedResult
359
+ | BatchRoutedResult
360
+ | FailureRoutedResult;
311
361
  export interface LineByteCounts {
312
- lines: number;
313
- bytes: number;
362
+ lines: number;
363
+ bytes: number;
314
364
  }
315
365
  export interface CommandOutputPaths {
316
- meta: string;
317
- stdout: string;
318
- stderr: string;
319
- combined: string;
366
+ meta: string;
367
+ stdout: string;
368
+ stderr: string;
369
+ combined: string;
320
370
  }
321
371
  export interface OutputFingerprints {
322
- exactSha256: string;
323
- normalizedSha256: string;
324
- commandFingerprintSha256?: string;
372
+ exactSha256: string;
373
+ normalizedSha256: string;
374
+ commandFingerprintSha256?: string;
325
375
  }
326
376
  export interface VaultRecordBase {
327
- outputId: string;
328
- recordId: string;
329
- objectId: string;
330
- createdAt: string;
331
- paths: {
332
- meta: string;
333
- };
334
- decisionIds: string[];
335
- producer: ProducerDescriptor;
336
- persistence: EvidencePersistence;
337
- lineage?: EvidenceLineage;
338
- contentHashSha256: string;
339
- fingerprints?: OutputFingerprints;
340
- retention?: VaultRetentionPolicy;
341
- expiresAt?: string;
377
+ outputId: string;
378
+ recordId: string;
379
+ objectId: string;
380
+ createdAt: string;
381
+ paths: {
382
+ meta: string;
383
+ };
384
+ decisionIds: string[];
385
+ producer: ProducerDescriptor;
386
+ persistence: EvidencePersistence;
387
+ lineage?: EvidenceLineage;
388
+ contentHashSha256: string;
389
+ fingerprints?: OutputFingerprints;
390
+ retention?: VaultRetentionPolicy;
391
+ expiresAt?: string;
342
392
  }
343
393
  export interface CommandOutputRecord extends VaultRecordBase {
344
- kind: "command";
345
- command: string | readonly string[];
346
- executionStatus: ExecutionStatus;
347
- exitCode: number | null;
348
- paths: CommandOutputPaths;
349
- lineCounts: {
350
- stdout: number;
351
- stderr: number;
352
- combined: number;
353
- };
354
- byteCounts: {
355
- stdout: number;
356
- stderr: number;
357
- combined: number;
358
- };
359
- hashes: {
360
- stdoutSha256?: string;
361
- stderrSha256?: string;
362
- combinedSha256?: string;
363
- };
364
- fingerprints: OutputFingerprints & {
365
- commandFingerprintSha256: string;
366
- };
367
- cwd?: string;
368
- durationMs?: number;
394
+ kind: "command";
395
+ command: string | readonly string[];
396
+ executionStatus: ExecutionStatus;
397
+ exitCode: number | null;
398
+ paths: CommandOutputPaths;
399
+ lineCounts: {
400
+ stdout: number;
401
+ stderr: number;
402
+ combined: number;
403
+ };
404
+ byteCounts: {
405
+ stdout: number;
406
+ stderr: number;
407
+ combined: number;
408
+ };
409
+ hashes: {
410
+ stdoutSha256?: string;
411
+ stderrSha256?: string;
412
+ combinedSha256?: string;
413
+ };
414
+ fingerprints: OutputFingerprints & {
415
+ commandFingerprintSha256: string;
416
+ };
417
+ cwd?: string;
418
+ durationMs?: number;
369
419
  }
370
420
  export interface TextOutputRecord extends VaultRecordBase {
371
- kind: "text";
372
- sourceKind: "native" | "script" | "mcp" | "web" | "fetch" | "code_search" | "transform" | "other";
373
- paths: {
374
- meta: string;
375
- raw: string;
376
- };
377
- lineCounts: {
378
- raw: number;
379
- };
380
- byteCounts: {
381
- raw: number;
382
- };
383
- hashes: {
384
- rawSha256?: string;
385
- };
386
- fingerprints: OutputFingerprints;
421
+ kind: "text";
422
+ sourceKind: "native" | "script" | "mcp" | "web" | "fetch" | "code_search" | "transform" | "other";
423
+ paths: {
424
+ meta: string;
425
+ raw: string;
426
+ };
427
+ lineCounts: {
428
+ raw: number;
429
+ };
430
+ byteCounts: {
431
+ raw: number;
432
+ };
433
+ hashes: {
434
+ rawSha256?: string;
435
+ };
436
+ fingerprints: OutputFingerprints;
387
437
  }
388
438
  export interface RepoFileReferenceRecord extends VaultRecordBase {
389
- kind: "repo-file";
390
- path: string;
391
- paths: {
392
- meta: string;
393
- };
394
- hashSha256?: string;
439
+ kind: "repo-file";
440
+ path: string;
441
+ paths: {
442
+ meta: string;
443
+ };
444
+ hashSha256?: string;
395
445
  }
396
446
  export interface MetadataOutputRecord extends VaultRecordBase {
397
- kind: "metadata";
398
- sourceKind: TextOutputRecord["sourceKind"];
399
- paths: {
400
- meta: string;
401
- };
402
- lineCounts: {
403
- raw: number;
404
- };
405
- byteCounts: {
406
- raw: number;
407
- };
408
- hashes: {
409
- rawSha256?: string;
410
- };
411
- metadata?: Record<string, unknown>;
447
+ kind: "metadata";
448
+ sourceKind: TextOutputRecord["sourceKind"];
449
+ paths: {
450
+ meta: string;
451
+ };
452
+ lineCounts: {
453
+ raw: number;
454
+ };
455
+ byteCounts: {
456
+ raw: number;
457
+ };
458
+ hashes: {
459
+ rawSha256?: string;
460
+ };
461
+ metadata?: Record<string, unknown>;
412
462
  }
413
463
  export type VaultRecord = CommandOutputRecord | TextOutputRecord | RepoFileReferenceRecord | MetadataOutputRecord;
414
464
  export interface SessionIndexEntry {
415
- outputId: string;
416
- recordId?: string;
417
- objectId: string;
418
- kind: VaultRecord["kind"];
419
- createdAt: string;
420
- producer?: ProducerDescriptor;
421
- persistence?: EvidencePersistence;
422
- lineage?: EvidenceLineage;
423
- executionStatus?: ExecutionStatus;
424
- fingerprints?: OutputFingerprints;
465
+ outputId: string;
466
+ recordId?: string;
467
+ objectId: string;
468
+ kind: VaultRecord["kind"];
469
+ createdAt: string;
470
+ producer?: ProducerDescriptor;
471
+ persistence?: EvidencePersistence;
472
+ lineage?: EvidenceLineage;
473
+ executionStatus?: ExecutionStatus;
474
+ fingerprints?: OutputFingerprints;
425
475
  }
426
476
  export interface VaultSessionIndex {
427
- version: 1;
428
- sessionId: string;
429
- createdAt: string;
430
- updatedAt: string;
431
- outputs: string[];
432
- records: Record<string, SessionIndexEntry>;
433
- successful: string[];
434
- failed: string[];
435
- timedOut: string[];
436
- cancelled: string[];
477
+ version: 1;
478
+ sessionId: string;
479
+ createdAt: string;
480
+ updatedAt: string;
481
+ outputs: string[];
482
+ records: Record<string, SessionIndexEntry>;
483
+ successful: string[];
484
+ failed: string[];
485
+ timedOut: string[];
486
+ cancelled: string[];
437
487
  }
438
488
  export interface DecisionRecord {
439
- decisionId: string;
440
- createdAt: string;
441
- route: RouteKind;
442
- preserve: PreserveMode;
443
- reason: string;
444
- source?: SourceRef;
445
- outputId?: string;
446
- evidenceIds?: string[];
489
+ decisionId: string;
490
+ createdAt: string;
491
+ route: RouteKind;
492
+ preserve: PreserveMode;
493
+ reason: string;
494
+ source?: SourceRef;
495
+ outputId?: string;
496
+ evidenceIds?: string[];
447
497
  }
448
498
  export interface RouterThresholds {
449
- largeOutputBytes: number;
450
- largeOutputLines: number;
451
- }
452
- export type VaultRetentionPolicy = {
453
- strategy: "ttl";
454
- ttlDays: number;
455
- } | {
456
- strategy: "manual";
457
- };
499
+ largeOutputBytes: number;
500
+ largeOutputLines: number;
501
+ }
502
+ export type VaultRetentionPolicy =
503
+ | {
504
+ strategy: "ttl";
505
+ ttlDays: number;
506
+ }
507
+ | {
508
+ strategy: "manual";
509
+ };
458
510
  export interface RouterVaultConfig {
459
- root: string;
460
- retention?: VaultRetentionPolicy;
511
+ root: string;
512
+ retention?: VaultRetentionPolicy;
461
513
  }
462
514
  export interface RouterHints {
463
- generatedPathGlobs?: string[];
464
- noisyCommandPatterns?: string[];
515
+ generatedPathGlobs?: string[];
516
+ noisyCommandPatterns?: string[];
465
517
  }
466
518
  export interface RouterConfig {
467
- enabled: boolean;
468
- profile: OutputRouterProfile;
469
- postToolRouting: PostToolRoutingMode;
470
- storagePolicy: StoragePolicyMode;
471
- thresholds: RouterThresholds;
472
- vault: RouterVaultConfig;
473
- hints?: RouterHints;
519
+ enabled: boolean;
520
+ profile: OutputRouterProfile;
521
+ postToolRouting: PostToolRoutingMode;
522
+ storagePolicy: StoragePolicyMode;
523
+ thresholds: RouterThresholds;
524
+ vault: RouterVaultConfig;
525
+ hints?: RouterHints;
474
526
  }
475
527
  export interface ObservedRoutingProducerConfig {
476
- enabled: boolean;
477
- persistence: ObservedRoutingPersistenceMode;
528
+ enabled: boolean;
529
+ persistence: ObservedRoutingPersistenceMode;
478
530
  }
479
531
  export interface ObservedRoutingMcpConfig {
480
- servers: Record<string, ObservedRoutingProducerConfig>;
532
+ servers: Record<string, ObservedRoutingProducerConfig>;
481
533
  }
482
534
  export interface ObservedRoutingConfig {
483
- enabled: boolean;
484
- onRoutingFailure: ObservedRoutingFailureMode;
485
- mcp: ObservedRoutingMcpConfig;
486
- web: ObservedRoutingProducerConfig;
487
- fetch: ObservedRoutingProducerConfig;
488
- codeSearch: ObservedRoutingProducerConfig;
535
+ enabled: boolean;
536
+ onRoutingFailure: ObservedRoutingFailureMode;
537
+ mcp: ObservedRoutingMcpConfig;
538
+ web: ObservedRoutingProducerConfig;
539
+ fetch: ObservedRoutingProducerConfig;
540
+ codeSearch: ObservedRoutingProducerConfig;
489
541
  }
490
542
  export type ScriptTransformLanguage = "javascript" | "python" | "jq";
491
543
  export type ScriptTransformNetworkPolicy = "off";
@@ -493,29 +545,29 @@ export type ScriptTransformSandboxMode = "auto";
493
545
  export type ScriptTransformRawScriptPersistence = "disabled";
494
546
  export type ProcessingScriptPolicy = "sandboxed" | "unsafe-unsandboxed";
495
547
  export interface ScriptTransformLimits {
496
- timeoutMs: number;
497
- maxInputBytes: number;
498
- maxOutputBytes: number;
548
+ timeoutMs: number;
549
+ maxInputBytes: number;
550
+ maxOutputBytes: number;
499
551
  }
500
552
  export interface ScriptTransformConfig {
501
- enabled: boolean;
502
- sandbox: ScriptTransformSandboxMode;
503
- languages: ScriptTransformLanguage[];
504
- network: ScriptTransformNetworkPolicy;
505
- limits: ScriptTransformLimits;
506
- rawScriptPersistence: ScriptTransformRawScriptPersistence;
553
+ enabled: boolean;
554
+ sandbox: ScriptTransformSandboxMode;
555
+ languages: ScriptTransformLanguage[];
556
+ network: ScriptTransformNetworkPolicy;
557
+ limits: ScriptTransformLimits;
558
+ rawScriptPersistence: ScriptTransformRawScriptPersistence;
507
559
  }
508
560
  export interface ProcessingUnsafeUnsandboxedConfig {
509
- enabled: boolean;
561
+ enabled: boolean;
510
562
  }
511
563
  export interface LocalProcessingConfig {
512
- unsafeUnsandboxed: ProcessingUnsafeUnsandboxedConfig;
564
+ unsafeUnsandboxed: ProcessingUnsafeUnsandboxedConfig;
513
565
  }
514
566
  export interface LocalFreeflowConfig {
515
- processing: LocalProcessingConfig;
567
+ processing: LocalProcessingConfig;
516
568
  }
517
569
  export interface FreeflowConfig {
518
- outputRouter: RouterConfig;
519
- observedRouting: ObservedRoutingConfig;
520
- scriptTransform: ScriptTransformConfig;
570
+ outputRouter: RouterConfig;
571
+ observedRouting: ObservedRoutingConfig;
572
+ scriptTransform: ScriptTransformConfig;
521
573
  }