@hassangameryt/freeflow 0.3.0 → 0.5.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (692) hide show
  1. package/.claude-plugin/marketplace.json +4 -4
  2. package/.claude-plugin/plugin.json +6 -2
  3. package/.codex-plugin/plugin.json +9 -9
  4. package/README.md +190 -127
  5. package/assets/feedback-loop.png +0 -0
  6. package/assets/freeflow_workflow_map.png +0 -0
  7. package/assets/workflow.png +0 -0
  8. package/{skills → capabilities}/output-router/SKILL.md +21 -17
  9. package/{skills → capabilities}/output-router/references/safety-policy.md +1 -1
  10. package/capabilities/output-router/references/setup.md +110 -0
  11. package/command-surface.json +62 -7
  12. package/hooks/freeflow-runtime-context.mjs +572 -154
  13. package/hooks/hooks.json +26 -1
  14. package/hooks/tests/check-runtime-context-hook.sh +375 -0
  15. package/package.json +24 -24
  16. package/pi-extension/dist/index.js +264 -80
  17. package/pi-extension/dist/integrations/mcp-config.js +29 -0
  18. package/pi-extension/dist/output-router/host-producer-identification.js +232 -0
  19. package/pi-extension/dist/output-router/native-safety-net.js +216 -0
  20. package/pi-extension/dist/output-router/observed-tool-routing.js +122 -0
  21. package/pi-extension/dist/output-router/renderers.js +1023 -0
  22. package/pi-extension/dist/output-router/router-tools.js +554 -0
  23. package/pi-extension/dist/output-router/schemas.js +383 -0
  24. package/pi-extension/dist/output-router/status.js +744 -0
  25. package/pi-extension/dist/output-router/utils.js +502 -0
  26. package/pi-extension/dist/runtime/runtime-context.js +798 -0
  27. package/pi-extension/dist/settings/settings-tui.js +314 -0
  28. package/pi-extension/dist/settings/settings-ui.js +1487 -0
  29. package/pi-extension/freeflow/index.js +1 -0
  30. package/pi-extension/src/index.ts +230 -56
  31. package/pi-extension/src/{host-producer-identification.ts → output-router/host-producer-identification.ts} +37 -7
  32. package/pi-extension/src/{native-safety-net.ts → output-router/native-safety-net.ts} +8 -12
  33. package/pi-extension/src/{observed-tool-routing.ts → output-router/observed-tool-routing.ts} +19 -11
  34. package/pi-extension/src/{renderers.ts → output-router/renderers.ts} +246 -55
  35. package/pi-extension/src/{router-tools.ts → output-router/router-tools.ts} +130 -29
  36. package/pi-extension/src/{schemas.ts → output-router/schemas.ts} +171 -43
  37. package/pi-extension/src/output-router/status.ts +791 -0
  38. package/pi-extension/src/{utils.ts → output-router/utils.ts} +80 -18
  39. package/pi-extension/src/runtime/runtime-context.ts +895 -0
  40. package/pi-extension/src/settings/settings-tui.ts +408 -0
  41. package/pi-extension/src/settings/settings-ui.ts +1730 -0
  42. package/pi-extension/tests/integration/pi-extension.test.js +4020 -0
  43. package/pi-extension/tests/output-router/observed-producers.test.js +132 -0
  44. package/pi-extension/tests/output-router/search.test.js +722 -0
  45. package/pi-extension/tests/settings/settings-tui.test.js +243 -0
  46. package/router/dist/benchmarks/benchmark-harness.d.ts +16 -13
  47. package/router/dist/benchmarks/benchmark-harness.js +62 -62
  48. package/router/dist/benchmarks/benchmarks.d.ts +80 -73
  49. package/router/dist/benchmarks/benchmarks.js +860 -761
  50. package/router/dist/benchmarks/codex-qa-benchmarks.d.ts +71 -67
  51. package/router/dist/benchmarks/codex-qa-benchmarks.js +429 -390
  52. package/router/dist/benchmarks/command-benchmarks.d.ts +107 -92
  53. package/router/dist/benchmarks/command-benchmarks.js +616 -571
  54. package/router/dist/benchmarks/context-mode-normalized-benchmarks.d.ts +64 -56
  55. package/router/dist/benchmarks/context-mode-normalized-benchmarks.js +679 -613
  56. package/router/dist/benchmarks/context-mode-real-deep-benchmark.d.ts +103 -95
  57. package/router/dist/benchmarks/context-mode-real-deep-benchmark.js +1188 -1103
  58. package/router/dist/benchmarks/context-saving-baseline.d.ts +47 -41
  59. package/router/dist/benchmarks/context-saving-baseline.js +405 -374
  60. package/router/dist/benchmarks/index-benchmarks.d.ts +74 -69
  61. package/router/dist/benchmarks/index-benchmarks.js +761 -661
  62. package/router/dist/benchmarks/storage-policy-benchmarks.d.ts +80 -69
  63. package/router/dist/benchmarks/storage-policy-benchmarks.js +549 -469
  64. package/router/dist/benchmarks/vault-index-benchmarks.d.ts +43 -34
  65. package/router/dist/benchmarks/vault-index-benchmarks.js +294 -229
  66. package/router/dist/config/config.d.ts +62 -55
  67. package/router/dist/config/config.js +552 -373
  68. package/router/dist/config/router-contract.d.ts +2 -2
  69. package/router/dist/config/router-contract.js +38 -38
  70. package/router/dist/config/schema.d.ts +19 -10
  71. package/router/dist/config/schema.js +586 -538
  72. package/router/dist/config/types.d.ts +413 -361
  73. package/router/dist/config/types.js +19 -8
  74. package/router/dist/evidence/bounded-evidence.d.ts +26 -26
  75. package/router/dist/evidence/bounded-evidence.js +265 -252
  76. package/router/dist/evidence/evidence-range-selector.d.ts +16 -14
  77. package/router/dist/evidence/evidence-range-selector.js +192 -191
  78. package/router/dist/evidence/evidence-search.d.ts +18 -16
  79. package/router/dist/evidence/evidence-search.js +401 -377
  80. package/router/dist/evidence/evidence.d.ts +17 -17
  81. package/router/dist/evidence/evidence.js +163 -159
  82. package/router/dist/evidence/failure-contracts.d.ts +25 -15
  83. package/router/dist/evidence/failure-contracts.js +132 -126
  84. package/router/dist/evidence/line-ranges.d.ts +17 -15
  85. package/router/dist/evidence/line-ranges.js +18 -18
  86. package/router/dist/experiments/local-index.d.ts +47 -41
  87. package/router/dist/experiments/local-index.js +477 -458
  88. package/router/dist/local/local-traversal.d.ts +18 -0
  89. package/router/dist/local/local-traversal.js +334 -0
  90. package/router/dist/processing/engine.d.ts +94 -70
  91. package/router/dist/processing/engine.js +462 -364
  92. package/router/dist/processing/reducers.d.ts +208 -194
  93. package/router/dist/processing/reducers.js +1434 -1256
  94. package/router/dist/processing/renderers.d.ts +24 -18
  95. package/router/dist/processing/renderers.js +161 -152
  96. package/router/dist/processing/scripts.d.ts +80 -67
  97. package/router/dist/processing/scripts.js +343 -290
  98. package/router/dist/repo/repo-traversal.d.ts +9 -9
  99. package/router/dist/repo/repo-traversal.js +205 -202
  100. package/router/dist/routing/observed-reducers.d.ts +25 -19
  101. package/router/dist/routing/observed-reducers.js +559 -545
  102. package/router/dist/routing/observed-routing.d.ts +23 -14
  103. package/router/dist/routing/observed-routing.js +319 -318
  104. package/router/dist/routing/parsers.d.ts +10 -10
  105. package/router/dist/routing/parsers.js +454 -406
  106. package/router/dist/routing/run-filters.d.ts +45 -41
  107. package/router/dist/routing/run-filters.js +215 -207
  108. package/router/dist/routing/run-reducers.d.ts +45 -26
  109. package/router/dist/routing/run-reducers.js +102 -90
  110. package/router/dist/sandbox/adapter-roots.d.ts +34 -26
  111. package/router/dist/sandbox/adapter-roots.js +43 -41
  112. package/router/dist/sandbox/eryx-python-adapter.d.ts +9 -5
  113. package/router/dist/sandbox/eryx-python-adapter.js +659 -588
  114. package/router/dist/sandbox/jq-wasm-adapter.d.ts +3 -3
  115. package/router/dist/sandbox/jq-wasm-adapter.js +319 -311
  116. package/router/dist/sandbox/quickjs-wasi-adapter.d.ts +9 -5
  117. package/router/dist/sandbox/quickjs-wasi-adapter.js +336 -333
  118. package/router/dist/sandbox/script-sandbox.d.ts +105 -84
  119. package/router/dist/sandbox/script-sandbox.js +294 -260
  120. package/router/dist/setup/script-transform-adapters.d.ts +23 -19
  121. package/router/dist/setup/script-transform-adapters.js +223 -204
  122. package/router/dist/tools/batch.d.ts +27 -16
  123. package/router/dist/tools/batch.js +493 -416
  124. package/router/dist/tools/run.d.ts +47 -35
  125. package/router/dist/tools/run.js +1172 -1087
  126. package/router/dist/tools/search.d.ts +53 -31
  127. package/router/dist/tools/search.js +1224 -1065
  128. package/router/dist/transform/engine.d.ts +121 -96
  129. package/router/dist/transform/engine.js +1853 -1736
  130. package/router/dist/vault/vault-index.d.ts +97 -78
  131. package/router/dist/vault/vault-index.js +347 -342
  132. package/router/dist/vault/vault.d.ts +109 -74
  133. package/router/dist/vault/vault.js +528 -533
  134. package/runtime/interaction-contract.md +16 -0
  135. package/skills/bypass/SKILL.md +52 -38
  136. package/skills/commit-work/SKILL.md +54 -46
  137. package/skills/commit-work/references/staging-decisions.md +46 -24
  138. package/skills/decision-gate/SKILL.md +48 -0
  139. package/skills/design-for-depth/SKILL.md +75 -59
  140. package/skills/design-for-depth/references/design-pressure-signals.md +56 -7
  141. package/skills/design-for-depth/references/interface-design-loop.md +156 -0
  142. package/skills/design-for-depth/references/software-design-philosophy.md +32 -3
  143. package/skills/diagnose-failure/SKILL.md +65 -60
  144. package/skills/diagnose-failure/references/diagnostic-loop-catalog.md +36 -0
  145. package/skills/diagnose-failure/references/flaky-and-performance.md +30 -18
  146. package/skills/discuss/SKILL.md +121 -0
  147. package/skills/discuss/references/checkpoints.md +66 -0
  148. package/skills/evaluate-skill/SKILL.md +62 -53
  149. package/skills/evaluate-skill/references/definition-schema.md +345 -0
  150. package/skills/evaluate-skill/references/evaluation-design.md +86 -0
  151. package/skills/evaluate-skill/references/execution-and-evidence.md +85 -0
  152. package/skills/evaluate-skill/references/review-and-revision.md +51 -0
  153. package/skills/evaluate-skill/scripts/lib/definitions.mjs +296 -0
  154. package/skills/evaluate-skill/scripts/lib/evidence.mjs +46 -0
  155. package/skills/evaluate-skill/scripts/lib/grade-comparison.mjs +60 -0
  156. package/skills/evaluate-skill/scripts/lib/grade-interaction.mjs +148 -0
  157. package/skills/evaluate-skill/scripts/lib/grade-support.mjs +126 -0
  158. package/skills/evaluate-skill/scripts/lib/grade-workspace.mjs +192 -0
  159. package/skills/evaluate-skill/scripts/lib/grade.mjs +56 -0
  160. package/skills/evaluate-skill/scripts/lib/pi.mjs +489 -0
  161. package/skills/evaluate-skill/scripts/lib/process.mjs +79 -0
  162. package/skills/evaluate-skill/scripts/lib/rpc.mjs +444 -0
  163. package/skills/evaluate-skill/scripts/lib/runner.mjs +346 -0
  164. package/skills/evaluate-skill/scripts/lib/sandbox.mjs +409 -0
  165. package/skills/evaluate-skill/scripts/lib/view.mjs +337 -0
  166. package/skills/evaluate-skill/scripts/pi-guard.mjs +164 -0
  167. package/skills/evaluate-skill/scripts/skill-eval.mjs +101 -0
  168. package/skills/execute-work/SKILL.md +99 -0
  169. package/skills/execute-work/references/code-practices.md +78 -0
  170. package/skills/execute-work/references/execution-loop.md +77 -0
  171. package/skills/finish-branch/SKILL.md +117 -0
  172. package/skills/finish-branch/references/integration-options.md +80 -0
  173. package/skills/handoff/SKILL.md +65 -39
  174. package/skills/handoff/references/templates.md +104 -27
  175. package/skills/launch-work/SKILL.md +116 -0
  176. package/skills/launch-work/references/launch-readiness.md +85 -0
  177. package/skills/migration-work/SKILL.md +115 -0
  178. package/skills/migration-work/references/migration-lifecycle.md +82 -0
  179. package/skills/mode-contract/SKILL.md +72 -52
  180. package/skills/release-work/SKILL.md +118 -0
  181. package/skills/release-work/references/release-evidence.md +78 -0
  182. package/skills/review-artifact/SKILL.md +77 -69
  183. package/skills/review-artifact/references/reviewer-prompt.md +133 -42
  184. package/skills/review-work/SKILL.md +82 -57
  185. package/skills/review-work/references/reviewer-prompt.md +97 -60
  186. package/skills/review-work/references/security-risk-lens.md +67 -0
  187. package/skills/setup-freeflow/SKILL.md +54 -68
  188. package/skills/setup-freeflow/references/activation-contract.md +84 -69
  189. package/skills/setup-freeflow/references/host-setup.md +50 -17
  190. package/skills/simplify-code/SKILL.md +80 -0
  191. package/skills/simplify-code/references/simplification-patterns.md +70 -0
  192. package/skills/tdd/SKILL.md +96 -0
  193. package/skills/tdd/references/test-design.md +96 -0
  194. package/skills/track-work/SKILL.md +84 -0
  195. package/skills/track-work/references/working-record-schema.md +378 -0
  196. package/skills/verify-work/SKILL.md +59 -38
  197. package/skills/verify-work/references/browser-runtime-evidence.md +55 -0
  198. package/skills/verify-work/references/integration-evidence.md +51 -0
  199. package/skills/verify-work/references/performance-evidence.md +57 -0
  200. package/skills/workflow/SKILL.md +53 -59
  201. package/skills/workflow/references/domain-skill-composition.md +57 -0
  202. package/skills/workflow/references/workflow-loop.md +92 -0
  203. package/skills/write-plan/SKILL.md +85 -58
  204. package/skills/write-plan/references/plan-shapes.md +132 -46
  205. package/skills/write-skill/SKILL.md +82 -51
  206. package/skills/write-skill/references/activation-boundaries.md +62 -0
  207. package/skills/write-skill/references/agent-first-instructions.md +87 -0
  208. package/skills/write-skill/references/progressive-disclosure.md +63 -0
  209. package/skills/write-skill/scripts/lib/skill-author.mjs +653 -0
  210. package/skills/write-skill/scripts/skill-author.mjs +104 -0
  211. package/skills/write-spec/SKILL.md +65 -54
  212. package/skills/write-spec/references/artifact-standards.md +60 -41
  213. package/skills/write-spec/references/decision-records.md +77 -0
  214. package/skills/write-spec/references/spec-shapes.md +119 -60
  215. package/evals/README.md +0 -32
  216. package/evals/fixtures/copy-conventions.md +0 -31
  217. package/evals/fixtures/output-router/README.md +0 -12
  218. package/evals/fixtures/output-router/failed-command-output.txt +0 -9
  219. package/evals/fixtures/output-router/large-router-manual.md +0 -63
  220. package/evals/fixtures/output-router/native-large-output.txt +0 -40
  221. package/evals/fixtures/output-router/noisy-test-output.txt +0 -30
  222. package/evals/fixtures/output-router/verification-output.txt +0 -8
  223. package/evals/fixtures/tiny-artifact-review-app/README.md +0 -5
  224. package/evals/fixtures/tiny-artifact-review-app/docs/billing-policy.md +0 -10
  225. package/evals/fixtures/tiny-artifact-review-app/docs/specs/billing-webhook-api-draft.md +0 -21
  226. package/evals/fixtures/tiny-artifact-review-app/docs/specs/failed-payment-grace-period.md +0 -24
  227. package/evals/fixtures/tiny-artifact-review-app/docs/specs/immediate-downgrade.md +0 -17
  228. package/evals/fixtures/tiny-artifact-review-app/tests/billing.test.md +0 -8
  229. package/evals/fixtures/tiny-commit-ambiguous-app/.freeflow-eval-setup.sh +0 -15
  230. package/evals/fixtures/tiny-commit-ambiguous-app/README.md +0 -3
  231. package/evals/fixtures/tiny-commit-ambiguous-app/src/billing.ts +0 -5
  232. package/evals/fixtures/tiny-commit-ambiguous-app/src/settings-page.ts +0 -1
  233. package/evals/fixtures/tiny-commit-ambiguous-app/tests/settings.test.md +0 -5
  234. package/evals/fixtures/tiny-commit-app/.freeflow-eval-setup.sh +0 -14
  235. package/evals/fixtures/tiny-commit-app/README.md +0 -3
  236. package/evals/fixtures/tiny-commit-app/docs/specs/settings-title.md +0 -5
  237. package/evals/fixtures/tiny-commit-app/src/billing.ts +0 -5
  238. package/evals/fixtures/tiny-commit-app/src/settings-page.ts +0 -1
  239. package/evals/fixtures/tiny-commit-app/tests/settings.test.md +0 -5
  240. package/evals/fixtures/tiny-commit-everything-app/.freeflow-eval-setup.sh +0 -15
  241. package/evals/fixtures/tiny-commit-everything-app/README.md +0 -3
  242. package/evals/fixtures/tiny-commit-everything-app/docs/specs/settings-title.md +0 -5
  243. package/evals/fixtures/tiny-commit-everything-app/src/billing.ts +0 -5
  244. package/evals/fixtures/tiny-commit-everything-app/src/settings-page.ts +0 -1
  245. package/evals/fixtures/tiny-commit-everything-app/tests/settings.test.md +0 -5
  246. package/evals/fixtures/tiny-commit-staged-app/.freeflow-eval-setup.sh +0 -15
  247. package/evals/fixtures/tiny-commit-staged-app/README.md +0 -3
  248. package/evals/fixtures/tiny-commit-staged-app/docs/specs/settings-title.md +0 -5
  249. package/evals/fixtures/tiny-commit-staged-app/src/billing.ts +0 -5
  250. package/evals/fixtures/tiny-commit-staged-app/src/settings-page.ts +0 -1
  251. package/evals/fixtures/tiny-commit-staged-app/tests/settings.test.md +0 -5
  252. package/evals/fixtures/tiny-commit-staged-mixed-app/.freeflow-eval-setup.sh +0 -15
  253. package/evals/fixtures/tiny-commit-staged-mixed-app/README.md +0 -3
  254. package/evals/fixtures/tiny-commit-staged-mixed-app/docs/billing-policy.md +0 -3
  255. package/evals/fixtures/tiny-commit-staged-mixed-app/docs/release-notes.md +0 -3
  256. package/evals/fixtures/tiny-commit-staged-mixed-app/src/billing.ts +0 -5
  257. package/evals/fixtures/tiny-dashboard-stale-app/README.md +0 -11
  258. package/evals/fixtures/tiny-dashboard-stale-app/src/api-client.ts +0 -13
  259. package/evals/fixtures/tiny-dashboard-stale-app/src/dashboard-data.ts +0 -19
  260. package/evals/fixtures/tiny-dashboard-stale-app/tests/dashboard-data.test.md +0 -9
  261. package/evals/fixtures/tiny-decision-destination-app/README.md +0 -6
  262. package/evals/fixtures/tiny-decision-destination-app/src/risk.ts +0 -8
  263. package/evals/fixtures/tiny-decision-destination-app/tests/risk.test.md +0 -4
  264. package/evals/fixtures/tiny-design-depth-app/README.md +0 -15
  265. package/evals/fixtures/tiny-design-depth-app/src/routes.ts +0 -25
  266. package/evals/fixtures/tiny-design-depth-app/src/sendEmail.ts +0 -3
  267. package/evals/fixtures/tiny-design-depth-app/src/sendSms.ts +0 -3
  268. package/evals/fixtures/tiny-design-depth-app/src/telemetry.ts +0 -3
  269. package/evals/fixtures/tiny-design-depth-app/tests/routes.test.md +0 -12
  270. package/evals/fixtures/tiny-eval-method-app/README.md +0 -8
  271. package/evals/fixtures/tiny-eval-method-app/evals/reports/review-pr-eval-result.md +0 -5
  272. package/evals/fixtures/tiny-eval-method-app/evals/reports/triage-question-failure.md +0 -17
  273. package/evals/fixtures/tiny-eval-method-app/evals/runs/review-pr-with-skill-output.diff +0 -11
  274. package/evals/fixtures/tiny-eval-method-app/evals/runs/review-pr-with-skill-output.md +0 -3
  275. package/evals/fixtures/tiny-eval-method-app/skills/review-pr/SKILL.md +0 -10
  276. package/evals/fixtures/tiny-eval-method-app/skills/triage-question/SKILL.md +0 -10
  277. package/evals/fixtures/tiny-execute-plan-app/README.md +0 -5
  278. package/evals/fixtures/tiny-execute-plan-app/checks/settings-and-billing-check.sh +0 -5
  279. package/evals/fixtures/tiny-execute-plan-app/docs/billing-policy.md +0 -10
  280. package/evals/fixtures/tiny-execute-plan-app/docs/plans/immediate-downgrade-plan.md +0 -11
  281. package/evals/fixtures/tiny-execute-plan-app/docs/plans/settings-title-plan.md +0 -12
  282. package/evals/fixtures/tiny-execute-plan-app/docs/plans/settings-title-with-bad-check.md +0 -15
  283. package/evals/fixtures/tiny-execute-plan-app/docs/plans/unverified-billing-plan.md +0 -9
  284. package/evals/fixtures/tiny-execute-plan-app/docs/specs/failed-payment-grace-period.md +0 -9
  285. package/evals/fixtures/tiny-execute-plan-app/docs/specs/settings-title.md +0 -9
  286. package/evals/fixtures/tiny-execute-plan-app/src/billing.ts +0 -7
  287. package/evals/fixtures/tiny-execute-plan-app/src/settings-page.ts +0 -1
  288. package/evals/fixtures/tiny-execute-plan-app/tests/billing.test.md +0 -7
  289. package/evals/fixtures/tiny-execute-plan-app/tests/settings.test.md +0 -5
  290. package/evals/fixtures/tiny-execute-review-loop-app/README.md +0 -5
  291. package/evals/fixtures/tiny-execute-review-loop-app/docs/billing-policy.md +0 -9
  292. package/evals/fixtures/tiny-execute-review-loop-app/docs/plans/settings-title-plan.md +0 -12
  293. package/evals/fixtures/tiny-execute-review-loop-app/docs/review/previous-agent-summary.md +0 -15
  294. package/evals/fixtures/tiny-execute-review-loop-app/docs/review/review-pass-1-non-pass.md +0 -11
  295. package/evals/fixtures/tiny-execute-review-loop-app/docs/specs/settings-title.md +0 -9
  296. package/evals/fixtures/tiny-execute-review-loop-app/src/billing.ts +0 -7
  297. package/evals/fixtures/tiny-execute-review-loop-app/src/settings-page.ts +0 -1
  298. package/evals/fixtures/tiny-execute-review-loop-app/tests/billing.test.md +0 -7
  299. package/evals/fixtures/tiny-execute-review-loop-app/tests/settings.test.md +0 -5
  300. package/evals/fixtures/tiny-flaky-session-app/README.md +0 -10
  301. package/evals/fixtures/tiny-flaky-session-app/src/session-timeout.ts +0 -13
  302. package/evals/fixtures/tiny-flaky-session-app/tests/session-timeout.test.md +0 -8
  303. package/evals/fixtures/tiny-handoff-app/README.md +0 -5
  304. package/evals/fixtures/tiny-handoff-app/docs/billing-policy.md +0 -10
  305. package/evals/fixtures/tiny-handoff-app/docs/handoffs/old-agent-handoff.md +0 -8
  306. package/evals/fixtures/tiny-handoff-app/docs/plans/billing-retry-plan.md +0 -11
  307. package/evals/fixtures/tiny-handoff-app/src/billing.ts +0 -7
  308. package/evals/fixtures/tiny-handoff-report-app/README.md +0 -3
  309. package/evals/fixtures/tiny-handoff-report-app/evals/runs/handoff-3/hof-003/with-skill-output.diff +0 -1
  310. package/evals/fixtures/tiny-handoff-report-app/evals/runs/handoff-3/hof-003/with-skill-output.md +0 -1
  311. package/evals/fixtures/tiny-handoff-report-app/evals/scores/hof-003-score.txt +0 -4
  312. package/evals/fixtures/tiny-plan-app/README.md +0 -5
  313. package/evals/fixtures/tiny-plan-app/docs/billing-policy.md +0 -10
  314. package/evals/fixtures/tiny-plan-app/docs/specs/failed-payment-grace-period.md +0 -25
  315. package/evals/fixtures/tiny-plan-app/src/billing.ts +0 -17
  316. package/evals/fixtures/tiny-plan-app/src/settings-page.ts +0 -1
  317. package/evals/fixtures/tiny-plan-app/tests/billing.test.md +0 -8
  318. package/evals/fixtures/tiny-plan-app/tests/settings.test.md +0 -5
  319. package/evals/fixtures/tiny-plan-strict-api-app/README.md +0 -3
  320. package/evals/fixtures/tiny-plan-strict-api-app/docs/billing-policy.md +0 -5
  321. package/evals/fixtures/tiny-plan-strict-api-app/docs/specs/billing-webhook-api.md +0 -25
  322. package/evals/fixtures/tiny-plan-strict-api-app/src/billing.ts +0 -5
  323. package/evals/fixtures/tiny-plan-strict-api-app/src/webhooks.ts +0 -3
  324. package/evals/fixtures/tiny-plan-strict-api-app/tests/billing-webhook.test.md +0 -8
  325. package/evals/fixtures/tiny-post-setup-invalid-config-app/.freeflow/config.json +0 -3
  326. package/evals/fixtures/tiny-post-setup-invalid-config-app/AGENTS.md +0 -15
  327. package/evals/fixtures/tiny-post-setup-invalid-config-app/README.md +0 -16
  328. package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/auth-review.md +0 -15
  329. package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/billing-policy.md +0 -10
  330. package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/copy-conventions.md +0 -15
  331. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/auth-middleware.ts +0 -12
  332. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/billing.ts +0 -20
  333. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/login-copy.ts +0 -1
  334. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/settings-page.ts +0 -1
  335. package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/auth-middleware.test.md +0 -8
  336. package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/billing.test.md +0 -8
  337. package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/copy.test.md +0 -7
  338. package/evals/fixtures/tiny-post-setup-missing-config-app/AGENTS.md +0 -15
  339. package/evals/fixtures/tiny-post-setup-missing-config-app/README.md +0 -16
  340. package/evals/fixtures/tiny-post-setup-missing-config-app/docs/auth-review.md +0 -15
  341. package/evals/fixtures/tiny-post-setup-missing-config-app/docs/billing-policy.md +0 -10
  342. package/evals/fixtures/tiny-post-setup-missing-config-app/docs/copy-conventions.md +0 -15
  343. package/evals/fixtures/tiny-post-setup-missing-config-app/src/auth-middleware.ts +0 -12
  344. package/evals/fixtures/tiny-post-setup-missing-config-app/src/billing.ts +0 -20
  345. package/evals/fixtures/tiny-post-setup-missing-config-app/src/login-copy.ts +0 -1
  346. package/evals/fixtures/tiny-post-setup-missing-config-app/src/settings-page.ts +0 -1
  347. package/evals/fixtures/tiny-post-setup-missing-config-app/tests/auth-middleware.test.md +0 -8
  348. package/evals/fixtures/tiny-post-setup-missing-config-app/tests/billing.test.md +0 -8
  349. package/evals/fixtures/tiny-post-setup-missing-config-app/tests/copy.test.md +0 -7
  350. package/evals/fixtures/tiny-post-setup-source-conflict-app/.freeflow/config.json +0 -3
  351. package/evals/fixtures/tiny-post-setup-source-conflict-app/AGENTS.md +0 -15
  352. package/evals/fixtures/tiny-post-setup-source-conflict-app/README.md +0 -16
  353. package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/auth-review.md +0 -15
  354. package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/billing-policy.md +0 -10
  355. package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/copy-conventions.md +0 -15
  356. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/auth-middleware.ts +0 -12
  357. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/billing.ts +0 -20
  358. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/login-copy.ts +0 -1
  359. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/settings-page.ts +0 -1
  360. package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/auth-middleware.test.md +0 -8
  361. package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/billing.test.md +0 -8
  362. package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/copy.test.md +0 -7
  363. package/evals/fixtures/tiny-report-performance-app/README.md +0 -11
  364. package/evals/fixtures/tiny-report-performance-app/docs/performance.md +0 -10
  365. package/evals/fixtures/tiny-report-performance-app/src/report-summary.ts +0 -29
  366. package/evals/fixtures/tiny-report-performance-app/tests/report-performance.test.md +0 -8
  367. package/evals/fixtures/tiny-review-request-app/README.md +0 -3
  368. package/evals/fixtures/tiny-review-request-app/docs/billing-policy.md +0 -5
  369. package/evals/fixtures/tiny-review-request-app/docs/plans/billing-webhook-api.md +0 -19
  370. package/evals/fixtures/tiny-review-request-app/docs/review/previous-agent-summary.md +0 -20
  371. package/evals/fixtures/tiny-review-request-app/docs/specs/billing-webhook-api.md +0 -25
  372. package/evals/fixtures/tiny-review-request-app/src/billing.ts +0 -11
  373. package/evals/fixtures/tiny-review-request-app/src/webhooks.ts +0 -19
  374. package/evals/fixtures/tiny-review-request-app/tests/billing-webhook.test.md +0 -8
  375. package/evals/fixtures/tiny-review-work-app/README.md +0 -5
  376. package/evals/fixtures/tiny-review-work-app/docs/billing-policy.md +0 -9
  377. package/evals/fixtures/tiny-review-work-app/docs/plans/settings-title-plan.md +0 -12
  378. package/evals/fixtures/tiny-review-work-app/docs/review/previous-agent-summary.md +0 -15
  379. package/evals/fixtures/tiny-review-work-app/docs/specs/settings-title.md +0 -9
  380. package/evals/fixtures/tiny-review-work-app/src/billing.ts +0 -7
  381. package/evals/fixtures/tiny-review-work-app/src/settings-page.ts +0 -1
  382. package/evals/fixtures/tiny-review-work-app/tests/billing.test.md +0 -7
  383. package/evals/fixtures/tiny-review-work-app/tests/settings.test.md +0 -5
  384. package/evals/fixtures/tiny-saas-app/README.md +0 -16
  385. package/evals/fixtures/tiny-saas-app/docs/auth-review.md +0 -15
  386. package/evals/fixtures/tiny-saas-app/docs/billing-policy.md +0 -10
  387. package/evals/fixtures/tiny-saas-app/docs/copy-conventions.md +0 -15
  388. package/evals/fixtures/tiny-saas-app/docs/specs/settings-title.md +0 -13
  389. package/evals/fixtures/tiny-saas-app/src/auth-middleware.ts +0 -12
  390. package/evals/fixtures/tiny-saas-app/src/billing.ts +0 -20
  391. package/evals/fixtures/tiny-saas-app/src/login-copy.ts +0 -1
  392. package/evals/fixtures/tiny-saas-app/src/settings-page.ts +0 -1
  393. package/evals/fixtures/tiny-saas-app/tests/auth-middleware.test.md +0 -8
  394. package/evals/fixtures/tiny-saas-app/tests/billing.test.md +0 -8
  395. package/evals/fixtures/tiny-saas-app/tests/copy.test.md +0 -7
  396. package/evals/fixtures/tiny-setup-agents-app/AGENTS.md +0 -6
  397. package/evals/fixtures/tiny-setup-both-app/AGENTS.md +0 -5
  398. package/evals/fixtures/tiny-setup-both-app/CLAUDE.md +0 -5
  399. package/evals/fixtures/tiny-setup-claude-app/CLAUDE.md +0 -6
  400. package/evals/fixtures/tiny-setup-codex-rules-app/.codex/rules/shell.rules +0 -5
  401. package/evals/fixtures/tiny-setup-codex-rules-app/AGENTS.md +0 -6
  402. package/evals/fixtures/tiny-setup-conflict-app/AGENTS.md +0 -6
  403. package/evals/fixtures/tiny-setup-existing-block-app/AGENTS.md +0 -14
  404. package/evals/fixtures/tiny-setup-four-rules-app/CLAUDE.md +0 -6
  405. package/evals/fixtures/tiny-skill-dev-app/README.md +0 -10
  406. package/evals/fixtures/tiny-skill-dev-app/evals/prompts/review-pr-001.txt +0 -8
  407. package/evals/fixtures/tiny-skill-dev-app/evals/reports/review-pr-failure.md +0 -17
  408. package/evals/fixtures/tiny-skill-dev-app/skills/review-pr/SKILL.md +0 -13
  409. package/evals/fixtures/tiny-team-app/README.md +0 -5
  410. package/evals/fixtures/tiny-team-app/docs/product.md +0 -6
  411. package/evals/fixtures/tiny-team-app/src/teams.ts +0 -9
  412. package/evals/fixtures/tiny-team-app/src/users.ts +0 -5
  413. package/evals/fixtures/tiny-team-app/tests/teams.test.md +0 -7
  414. package/evals/fixtures/tiny-verify-app/README.md +0 -5
  415. package/evals/fixtures/tiny-verify-app/src/settings-nav.ts +0 -1
  416. package/evals/fixtures/tiny-verify-app/src/settings-page.ts +0 -1
  417. package/evals/fixtures/tiny-verify-app/tests/settings.test.md +0 -7
  418. package/evals/prompts/aon-001.txt +0 -2
  419. package/evals/prompts/byp-001.txt +0 -2
  420. package/evals/prompts/byp-002.txt +0 -2
  421. package/evals/prompts/cap-001.txt +0 -3
  422. package/evals/prompts/cap-002.txt +0 -3
  423. package/evals/prompts/cmd-001.txt +0 -3
  424. package/evals/prompts/cmd-002.txt +0 -3
  425. package/evals/prompts/cmd-003.txt +0 -6
  426. package/evals/prompts/cmd-004.txt +0 -5
  427. package/evals/prompts/cmd-005.txt +0 -5
  428. package/evals/prompts/cmd-006.txt +0 -5
  429. package/evals/prompts/cmd-007.txt +0 -5
  430. package/evals/prompts/cmd-008.txt +0 -5
  431. package/evals/prompts/cmd-009.txt +0 -8
  432. package/evals/prompts/cmd-010.txt +0 -5
  433. package/evals/prompts/cmd-011.txt +0 -5
  434. package/evals/prompts/cmd-012.txt +0 -5
  435. package/evals/prompts/cmd-013.txt +0 -5
  436. package/evals/prompts/cmd-014.txt +0 -7
  437. package/evals/prompts/cmd-015.txt +0 -7
  438. package/evals/prompts/cmd-016.txt +0 -5
  439. package/evals/prompts/cmt-001.txt +0 -1
  440. package/evals/prompts/cmt-002.txt +0 -1
  441. package/evals/prompts/cmt-003.txt +0 -1
  442. package/evals/prompts/cmt-004.txt +0 -1
  443. package/evals/prompts/cmt-005.txt +0 -1
  444. package/evals/prompts/dfd-001.txt +0 -3
  445. package/evals/prompts/dia-001.txt +0 -3
  446. package/evals/prompts/dia-002.txt +0 -3
  447. package/evals/prompts/dia-003.txt +0 -3
  448. package/evals/prompts/dis-001.txt +0 -5
  449. package/evals/prompts/dis-002.txt +0 -5
  450. package/evals/prompts/esk-001.txt +0 -5
  451. package/evals/prompts/esk-002.txt +0 -5
  452. package/evals/prompts/esk-003.txt +0 -5
  453. package/evals/prompts/grc-001.txt +0 -3
  454. package/evals/prompts/hof-001.txt +0 -3
  455. package/evals/prompts/hof-002.txt +0 -1
  456. package/evals/prompts/hof-003.txt +0 -1
  457. package/evals/prompts/hof-004.txt +0 -1
  458. package/evals/prompts/hof-005.txt +0 -1
  459. package/evals/prompts/ivg-001.txt +0 -1
  460. package/evals/prompts/ivg-002.txt +0 -11
  461. package/evals/prompts/ivg-003.txt +0 -1
  462. package/evals/prompts/ivg-004.txt +0 -1
  463. package/evals/prompts/mode-001.txt +0 -3
  464. package/evals/prompts/mode-002.txt +0 -1
  465. package/evals/prompts/mode-003.txt +0 -3
  466. package/evals/prompts/mode-004.txt +0 -3
  467. package/evals/prompts/mode-005.txt +0 -3
  468. package/evals/prompts/mode-006.txt +0 -3
  469. package/evals/prompts/mode-007.txt +0 -3
  470. package/evals/prompts/otr-001.txt +0 -3
  471. package/evals/prompts/otr-002.txt +0 -3
  472. package/evals/prompts/rar-001.txt +0 -5
  473. package/evals/prompts/rar-002.txt +0 -3
  474. package/evals/prompts/rar-003.txt +0 -6
  475. package/evals/prompts/rar-004.txt +0 -15
  476. package/evals/prompts/rar-005.txt +0 -10
  477. package/evals/prompts/rbr-001.txt +0 -3
  478. package/evals/prompts/rbr-002.txt +0 -3
  479. package/evals/prompts/rbr-003.txt +0 -7
  480. package/evals/prompts/rev-001.txt +0 -3
  481. package/evals/prompts/rev-002.txt +0 -5
  482. package/evals/prompts/rev-003.txt +0 -6
  483. package/evals/prompts/rev-004.txt +0 -1
  484. package/evals/prompts/rev-005.txt +0 -15
  485. package/evals/prompts/rev-006.txt +0 -5
  486. package/evals/prompts/stp-001.txt +0 -1
  487. package/evals/prompts/stp-002.txt +0 -1
  488. package/evals/prompts/stp-003.txt +0 -1
  489. package/evals/prompts/stp-004.txt +0 -1
  490. package/evals/prompts/stp-005.txt +0 -1
  491. package/evals/prompts/stp-006.txt +0 -1
  492. package/evals/prompts/stp-007.txt +0 -1
  493. package/evals/prompts/stp-008.txt +0 -1
  494. package/evals/prompts/stp-009.txt +0 -1
  495. package/evals/prompts/stp-010.txt +0 -1
  496. package/evals/prompts/stp-011.txt +0 -1
  497. package/evals/prompts/vfy-003.txt +0 -1
  498. package/evals/prompts/wpl-001.txt +0 -3
  499. package/evals/prompts/wpl-002.txt +0 -5
  500. package/evals/prompts/wpl-003.txt +0 -3
  501. package/evals/prompts/wpl-004.txt +0 -5
  502. package/evals/prompts/wpl-005.txt +0 -1
  503. package/evals/prompts/wrc-001.txt +0 -10
  504. package/evals/prompts/wrc-002.txt +0 -3
  505. package/evals/prompts/wsk-001.txt +0 -6
  506. package/evals/prompts/wsp-001.txt +0 -5
  507. package/evals/prompts/wsp-002.txt +0 -15
  508. package/evals/prompts/wsp-003.txt +0 -3
  509. package/evals/prompts/wsp-004.txt +0 -15
  510. package/evals/prompts/wsp-005.txt +0 -5
  511. package/evals/prompts/wsp-006.txt +0 -12
  512. package/evals/prompts/wsp-007.txt +0 -9
  513. package/evals/prompts/wsp-008.txt +0 -13
  514. package/evals/prompts/xpl-001.txt +0 -1
  515. package/evals/prompts/xpl-002.txt +0 -3
  516. package/evals/prompts/xpl-003.txt +0 -3
  517. package/evals/prompts/xpl-004.txt +0 -3
  518. package/evals/prompts/xpl-005.txt +0 -5
  519. package/evals/prompts/xpl-006.txt +0 -3
  520. package/evals/registries/adversarial-evals.json +0 -39
  521. package/evals/registries/fixture-evals.json +0 -2513
  522. package/evals/registries/handoff-evals.json +0 -74
  523. package/evals/registries/legacy-evals.json +0 -147
  524. package/evals/registries/skill-evidence.json +0 -193
  525. package/evals/registries/verify-work-evals.json +0 -46
  526. package/evals/reports/acceptance/v0.1-acceptance-report.md +0 -130
  527. package/evals/reports/by-command-surface/command-surface-1-report.md +0 -45
  528. package/evals/reports/by-command-surface/command-surface-10-report.md +0 -76
  529. package/evals/reports/by-command-surface/command-surface-11-report.md +0 -77
  530. package/evals/reports/by-command-surface/command-surface-12-report.md +0 -91
  531. package/evals/reports/by-command-surface/command-surface-13-report.md +0 -64
  532. package/evals/reports/by-command-surface/command-surface-14-report.md +0 -66
  533. package/evals/reports/by-command-surface/command-surface-15-report.md +0 -124
  534. package/evals/reports/by-command-surface/command-surface-16-report.md +0 -39
  535. package/evals/reports/by-command-surface/command-surface-2-report.md +0 -80
  536. package/evals/reports/by-command-surface/command-surface-3-report.md +0 -86
  537. package/evals/reports/by-command-surface/command-surface-4-report.md +0 -76
  538. package/evals/reports/by-command-surface/command-surface-5-report.md +0 -80
  539. package/evals/reports/by-command-surface/command-surface-6-report.md +0 -74
  540. package/evals/reports/by-command-surface/command-surface-7-report.md +0 -84
  541. package/evals/reports/by-command-surface/command-surface-8-report.md +0 -79
  542. package/evals/reports/by-command-surface/command-surface-9-report.md +0 -79
  543. package/evals/reports/by-command-surface/command-surface-matrix.md +0 -91
  544. package/evals/reports/by-skill/bypass-1-report.md +0 -124
  545. package/evals/reports/by-skill/capture-decisions-1-report.md +0 -99
  546. package/evals/reports/by-skill/capture-decisions-2-report.md +0 -102
  547. package/evals/reports/by-skill/commit-work-1-report.md +0 -165
  548. package/evals/reports/by-skill/commit-work-2-report.md +0 -109
  549. package/evals/reports/by-skill/design-for-depth-1-report.md +0 -95
  550. package/evals/reports/by-skill/diagnose-failure-1-report.md +0 -91
  551. package/evals/reports/by-skill/diagnose-failure-2-report.md +0 -94
  552. package/evals/reports/by-skill/discover-1-report.md +0 -118
  553. package/evals/reports/by-skill/evaluate-skill-2-report.md +0 -71
  554. package/evals/reports/by-skill/execute-plan-1-report.md +0 -103
  555. package/evals/reports/by-skill/execute-plan-2-report.md +0 -112
  556. package/evals/reports/by-skill/execute-plan-3-report.md +0 -87
  557. package/evals/reports/by-skill/grill-context-1-report.md +0 -103
  558. package/evals/reports/by-skill/handoff-1-report.md +0 -123
  559. package/evals/reports/by-skill/handoff-2-report.md +0 -105
  560. package/evals/reports/by-skill/handoff-3-report.md +0 -100
  561. package/evals/reports/by-skill/handoff-7-report.md +0 -77
  562. package/evals/reports/by-skill/interview-gate-1-report.md +0 -63
  563. package/evals/reports/by-skill/interview-gate-2-report.md +0 -105
  564. package/evals/reports/by-skill/mode-contract-1-report.md +0 -74
  565. package/evals/reports/by-skill/mode-contract-2-report.md +0 -87
  566. package/evals/reports/by-skill/mode-contract-3-report.md +0 -65
  567. package/evals/reports/by-skill/mode-contract-4-report.md +0 -71
  568. package/evals/reports/by-skill/mode-contract-5-report.md +0 -70
  569. package/evals/reports/by-skill/output-router-1-report.md +0 -76
  570. package/evals/reports/by-skill/output-router-2-report.md +0 -65
  571. package/evals/reports/by-skill/research-1-report.md +0 -144
  572. package/evals/reports/by-skill/research-brief-1-report.md +0 -94
  573. package/evals/reports/by-skill/research-brief-2-report.md +0 -75
  574. package/evals/reports/by-skill/review-artifact-1-report.md +0 -91
  575. package/evals/reports/by-skill/review-artifact-2-report.md +0 -79
  576. package/evals/reports/by-skill/review-artifact-3-report.md +0 -120
  577. package/evals/reports/by-skill/review-artifact-4-report.md +0 -89
  578. package/evals/reports/by-skill/review-artifact-5-report.md +0 -66
  579. package/evals/reports/by-skill/review-work-1-report.md +0 -85
  580. package/evals/reports/by-skill/review-work-2-report.md +0 -87
  581. package/evals/reports/by-skill/review-work-3-report.md +0 -104
  582. package/evals/reports/by-skill/review-work-4-report.md +0 -108
  583. package/evals/reports/by-skill/review-work-5-report.md +0 -73
  584. package/evals/reports/by-skill/review-work-6-report.md +0 -66
  585. package/evals/reports/by-skill/setup-freeflow-1-report.md +0 -199
  586. package/evals/reports/by-skill/setup-freeflow-2-report.md +0 -105
  587. package/evals/reports/by-skill/setup-freeflow-3-report.md +0 -105
  588. package/evals/reports/by-skill/setup-freeflow-4-report.md +0 -88
  589. package/evals/reports/by-skill/setup-freeflow-5-report.md +0 -115
  590. package/evals/reports/by-skill/skill-authoring-1-report.md +0 -81
  591. package/evals/reports/by-skill/verify-work-1-report.md +0 -111
  592. package/evals/reports/by-skill/verify-work-2-report.md +0 -120
  593. package/evals/reports/by-skill/workflow-1-report.md +0 -65
  594. package/evals/reports/by-skill/write-plan-1-report.md +0 -123
  595. package/evals/reports/by-skill/write-plan-2-report.md +0 -98
  596. package/evals/reports/by-skill/write-plan-3-report.md +0 -110
  597. package/evals/reports/by-skill/write-spec-1-report.md +0 -88
  598. package/evals/reports/by-skill/write-spec-2-report.md +0 -89
  599. package/evals/reports/by-skill/write-spec-3-report.md +0 -90
  600. package/evals/reports/by-skill/write-spec-4-report.md +0 -167
  601. package/evals/reports/harness/claude-harness-1-report.md +0 -103
  602. package/evals/reports/harness/eval-harness-1-report.md +0 -91
  603. package/evals/reports/iterations/iteration-1-report.md +0 -71
  604. package/evals/reports/iterations/iteration-2-report.md +0 -78
  605. package/evals/reports/iterations/iteration-3-report.md +0 -118
  606. package/evals/reports/iterations/iteration-4-report.md +0 -131
  607. package/evals/reports/iterations/iteration-5-report.md +0 -149
  608. package/evals/reports/iterations/iteration-6-report.md +0 -136
  609. package/evals/reports/runtime/always-on-runtime-1-report.md +0 -107
  610. package/evals/reports/runtime/context-mode-normalized-benchmark-1-report.md +0 -52
  611. package/evals/reports/runtime/context-mode-real-deep-baseline-1-report.md +0 -410
  612. package/evals/reports/runtime/context-mode-real-deep-final-slice-11-report.md +0 -203
  613. package/evals/reports/runtime/context-mode-real-deep-final-slice-11-review.md +0 -51
  614. package/evals/reports/runtime/context-saving-native-tools-baseline-1-report.md +0 -99
  615. package/evals/reports/runtime/eryx-python-compatibility-reprobe-1-report.md +0 -166
  616. package/evals/reports/runtime/eryx-python-proof-spike-1-report.md +0 -96
  617. package/evals/reports/runtime/eryx-python-proof-spike-2-report.md +0 -151
  618. package/evals/reports/runtime/eryx-python-script-derive-execution-1-report.md +0 -233
  619. package/evals/reports/runtime/jq-script-derive-execution-1-report.md +0 -215
  620. package/evals/reports/runtime/jq-wasm-proof-spike-1-report.md +0 -67
  621. package/evals/reports/runtime/output-router-benchmark-1-report.md +0 -81
  622. package/evals/reports/runtime/output-router-capture-derive-provider-eval-1-report.md +0 -35
  623. package/evals/reports/runtime/output-router-codex-large-index-sqlite-adhoc-report.md +0 -150
  624. package/evals/reports/runtime/output-router-codex-qa-benchmark-1-report.md +0 -46
  625. package/evals/reports/runtime/output-router-command-benchmark-1-report.md +0 -62
  626. package/evals/reports/runtime/output-router-index-benchmark-1-report.md +0 -64
  627. package/evals/reports/runtime/output-router-regression-1-report.md +0 -81
  628. package/evals/reports/runtime/output-router-transform-eval-1-report.md +0 -28
  629. package/evals/reports/runtime/pi-observed-routing-eval-1-report.md +0 -44
  630. package/evals/reports/runtime/quickjs-script-derive-execution-1-report.md +0 -159
  631. package/evals/reports/runtime/quickjs-wasi-proof-spike-1-report.md +0 -55
  632. package/evals/reports/runtime/render-format-row-protocol-1-report.md +0 -58
  633. package/evals/reports/runtime/script-sandbox-adapter-selection-review-1-report.md +0 -84
  634. package/evals/reports/runtime/script-sandbox-probe-resource-hardening-1-report.md +0 -51
  635. package/evals/reports/runtime/storage-policy-benchmark-1-report.md +0 -176
  636. package/evals/reports/runtime/vault-index-storage-spike-1-report.md +0 -39
  637. package/evals/reports/runtime/workflow-context-hook-1-report.md +0 -82
  638. package/evals/runbooks/adversarial-eval-runbook.md +0 -28
  639. package/evals/runbooks/fixture-eval-runbook.md +0 -137
  640. package/evals/runbooks/handoff-eval-runbook.md +0 -22
  641. package/evals/runbooks/verify-work-eval-runbook.md +0 -27
  642. package/evals/scripts/audit-command-surface.sh +0 -160
  643. package/evals/scripts/check-activation-contract.sh +0 -121
  644. package/evals/scripts/check-runtime-context-hook.sh +0 -183
  645. package/evals/scripts/grade-fixture-eval.sh +0 -446
  646. package/evals/scripts/run-claude-fixture-eval.sh +0 -26
  647. package/evals/scripts/run-codex-fixture-eval.sh +0 -26
  648. package/evals/scripts/run-eryx-python-proof-spike.js +0 -559
  649. package/evals/scripts/run-fixture-eval-by-id.sh +0 -23
  650. package/evals/scripts/run-fixture-eval.sh +0 -464
  651. package/evals/scripts/run-jq-wasm-proof-spike.js +0 -299
  652. package/evals/scripts/run-output-router-transform-eval.js +0 -115
  653. package/evals/scripts/run-pi-observed-routing-eval.js +0 -478
  654. package/evals/scripts/run-quickjs-wasi-proof-spike.js +0 -339
  655. package/evals/scripts/skill-evidence.sh +0 -316
  656. package/evals/scripts/validate-release-metadata.sh +0 -486
  657. package/evals/suites/v0.1-acceptance-suite.md +0 -131
  658. package/pi-extension/dist/host-producer-identification.js +0 -186
  659. package/pi-extension/dist/mcp-config.js +0 -30
  660. package/pi-extension/dist/native-safety-net.js +0 -209
  661. package/pi-extension/dist/observed-tool-routing.js +0 -114
  662. package/pi-extension/dist/renderers.js +0 -835
  663. package/pi-extension/dist/router-tools.js +0 -438
  664. package/pi-extension/dist/runtime-context.js +0 -288
  665. package/pi-extension/dist/schemas.js +0 -254
  666. package/pi-extension/dist/status.js +0 -449
  667. package/pi-extension/dist/utils.js +0 -467
  668. package/pi-extension/src/runtime-context.ts +0 -347
  669. package/pi-extension/src/status.ts +0 -505
  670. package/plugin-docs/README.md +0 -40
  671. package/plugin-docs/adr/0001-three-modes.md +0 -27
  672. package/plugin-docs/adr/0002-evals-before-hooks.md +0 -17
  673. package/plugin-docs/adr/0003-release-boundary.md +0 -21
  674. package/plugin-docs/adr/0004-discover-replaces-shallow-discovery-skills.md +0 -26
  675. package/plugin-docs/adr/README.md +0 -10
  676. package/plugin-docs/architecture.md +0 -89
  677. package/plugin-docs/output-router.md +0 -396
  678. package/plugin-docs/release-evidence.md +0 -77
  679. package/plugin-docs/skills.md +0 -44
  680. package/plugin-docs/workflow.md +0 -57
  681. package/skills/diagnose-failure/references/feedback-loop-catalog.md +0 -25
  682. package/skills/discover/ARTIFACT-DESTINATIONS.md +0 -58
  683. package/skills/discover/CHECKPOINTS.md +0 -74
  684. package/skills/discover/SKILL.md +0 -173
  685. package/skills/evaluate-skill/references/eval-patterns.md +0 -41
  686. package/skills/evaluate-skill/references/grading-priority.md +0 -33
  687. package/skills/execute-plan/SKILL.md +0 -133
  688. package/skills/execute-plan/references/execution-map.md +0 -122
  689. package/skills/interview-gate/SKILL.md +0 -90
  690. package/skills/setup-freeflow/references/output-router-setup.md +0 -102
  691. package/skills/workflow/references/workflow-map.md +0 -104
  692. /package/pi-extension/src/{mcp-config.ts → integrations/mcp-config.ts} +0 -0
@@ -1,435 +1,533 @@
1
1
  import { createHash } from "node:crypto";
2
2
  import { readFile, stat } from "node:fs/promises";
3
3
  import { relative } from "node:path";
4
+ import { resolveLocalPath } from "../local/local-traversal.js";
4
5
  import { resolveRepoPath } from "../repo/repo-traversal.js";
5
6
  import { renderProcessingResult, classifyProcessingRecovery } from "./renderers.js";
6
7
  import { selectProcessingReducer } from "./reducers.js";
7
- import { processingScriptNotConfigured, processingScriptUnavailableForUnloadedSource, runProcessingScript, } from "./scripts.js";
8
- import { createVault, readOutputText, readVaultRecord, storeRepoFileReference, storeTextOutput } from "../vault/vault.js";
8
+ import {
9
+ processingScriptNotConfigured,
10
+ processingScriptUnavailableForUnloadedSource,
11
+ runProcessingScript,
12
+ } from "./scripts.js";
13
+ import {
14
+ createVault,
15
+ readOutputText,
16
+ readVaultRecord,
17
+ storeRepoFileReference,
18
+ storeTextOutput,
19
+ } from "../vault/vault.js";
9
20
  export const PROCESSING_ENGINE_IMPLEMENTATION = "processing-engine-skeleton-v1";
10
21
  const DEFAULT_PROCESSING_LIMITS = {
11
- maxSourceBytes: 2 * 1024 * 1024,
12
- maxVisibleBytes: 4_096,
22
+ maxSourceBytes: 2 * 1024 * 1024,
23
+ maxVisibleBytes: 4_096,
13
24
  };
14
25
  export async function loadProcessingSource(source, options = {}) {
15
- const limits = normalizeLimits(options.limits);
16
- switch (source.kind) {
17
- case "repo-file":
18
- return loadRepoFileSource(source, options, limits);
19
- case "vault-output":
20
- return loadVaultOutputSource(source, options, limits);
21
- case "command-output":
22
- return loadCapturedCommandOutputSource(source, limits);
23
- }
26
+ const limits = normalizeLimits(options.limits);
27
+ switch (source.kind) {
28
+ case "repo-file":
29
+ return loadRepoFileSource(source, options, limits);
30
+ case "vault-output":
31
+ return loadVaultOutputSource(source, options, limits);
32
+ case "local-file":
33
+ return loadLocalFileSource(source, limits);
34
+ case "command-output":
35
+ return loadCapturedCommandOutputSource(source, limits);
36
+ }
24
37
  }
25
38
  export async function processSource(source, options = {}) {
26
- const loaded = await loadProcessingSource(source, options);
27
- const limits = normalizeLimits(options.limits);
28
- const reducer = notSelectedReducer("Source was not loaded; reducer selection was skipped.");
29
- const script = options.script
30
- ? processingScriptUnavailableForUnloadedSource(options.script, "Source was not loaded; script processing was skipped.")
31
- : processingScriptNotConfigured();
32
- if (loaded.status === "blocked") {
33
- return {
34
- implementation: PROCESSING_ENGINE_IMPLEMENTATION,
35
- status: "blocked",
36
- source: loaded.source,
37
- reason: loaded.reason,
38
- policy: loaded.policy,
39
- visibleText: renderProcessingResult({
40
- status: "blocked",
41
- source: loaded.source,
42
- facts: [],
43
- maxVisibleBytes: limits.maxVisibleBytes,
44
- failure: { policy: loaded.policy, reason: loaded.reason },
45
- }),
46
- facts: [],
47
- reducer,
48
- script,
49
- };
50
- }
51
- if (loaded.status === "unavailable") {
52
- return {
53
- implementation: PROCESSING_ENGINE_IMPLEMENTATION,
54
- status: "unavailable",
55
- source: loaded.source,
56
- reason: loaded.reason,
57
- visibleText: renderProcessingResult({
58
- status: "unavailable",
59
- source: loaded.source,
60
- facts: [],
61
- maxVisibleBytes: limits.maxVisibleBytes,
62
- failure: { reason: loaded.reason },
63
- }),
64
- facts: [],
65
- reducer,
66
- script,
67
- };
68
- }
69
- const selectedScript = options.script
70
- ? await runProcessingScript({
71
- loaded,
72
- script: options.script,
73
- ...(options.scriptTransform !== undefined ? { scriptTransform: options.scriptTransform } : {}),
74
- ...(options.localConfig !== undefined ? { localConfig: options.localConfig } : {}),
75
- ...(options.scriptSandboxAdapters !== undefined ? { adapters: options.scriptSandboxAdapters } : {}),
76
- })
77
- : processingScriptNotConfigured();
78
- const selectedReducer = scriptSkipsReducer(selectedScript)
79
- ? notSelectedReducer(scriptReducerSkipReason(selectedScript))
80
- : selectProcessingReducer({ text: loaded.text, ...(options.goal !== undefined ? { goal: options.goal } : {}) });
81
- const facts = selectedReducer.status === "selected" ? [...selectedReducer.result.facts, ...sourceFacts(loaded)] : sourceFacts(loaded);
82
- const visibleText = renderProcessingResult({
83
- status: "ok",
39
+ const loaded = await loadProcessingSource(source, options);
40
+ const limits = normalizeLimits(options.limits);
41
+ const reducer = notSelectedReducer("Source was not loaded; reducer selection was skipped.");
42
+ const script = options.script
43
+ ? processingScriptUnavailableForUnloadedSource(
44
+ options.script,
45
+ "Source was not loaded; script processing was skipped.",
46
+ )
47
+ : processingScriptNotConfigured();
48
+ if (loaded.status === "blocked") {
49
+ return {
50
+ implementation: PROCESSING_ENGINE_IMPLEMENTATION,
51
+ status: "blocked",
52
+ source: loaded.source,
53
+ reason: loaded.reason,
54
+ policy: loaded.policy,
55
+ visibleText: renderProcessingResult({
56
+ status: "blocked",
84
57
  source: loaded.source,
85
- stats: loaded.stats,
86
- facts,
87
- reducer: selectedReducer,
88
- script: selectedScript,
89
- ...(loaded.recovery !== undefined ? { recovery: loaded.recovery } : {}),
90
- ...(loaded.persistence !== undefined ? { persistence: loaded.persistence } : {}),
91
- recoveryClass: classifyProcessingRecovery({
92
- ...(loaded.recovery !== undefined ? { recovery: loaded.recovery } : {}),
93
- ...(loaded.persistence !== undefined ? { persistence: loaded.persistence } : {}),
94
- resultWillBePersisted: options.sessionId !== undefined,
95
- }),
58
+ facts: [],
96
59
  maxVisibleBytes: limits.maxVisibleBytes,
97
- });
98
- const persisted = await persistProcessingResultText({
99
- resultText: selectedScript.status === "executed" ? selectedScript.outputText : visibleText,
100
- loaded,
101
- options,
102
- operation: selectedScript.status === "executed" ? `processing-script:${selectedScript.language}` : "processing-fact-summary",
103
- producerName: selectedScript.status === "executed" ? `processing-script:${selectedScript.language}` : "processing-engine",
104
- operationHashSeed: selectedScript.status === "executed"
105
- ? { source: loaded.source, stats: loaded.stats, script: { language: selectedScript.language, codeHashSha256: selectedScript.codeHashSha256 } }
106
- : { source: loaded.source, stats: loaded.stats },
107
- });
108
- const result = {
109
- implementation: PROCESSING_ENGINE_IMPLEMENTATION,
110
- status: "ok",
60
+ failure: { policy: loaded.policy, reason: loaded.reason },
61
+ }),
62
+ facts: [],
63
+ reducer,
64
+ script,
65
+ };
66
+ }
67
+ if (loaded.status === "unavailable") {
68
+ return {
69
+ implementation: PROCESSING_ENGINE_IMPLEMENTATION,
70
+ status: "unavailable",
71
+ source: loaded.source,
72
+ reason: loaded.reason,
73
+ visibleText: renderProcessingResult({
74
+ status: "unavailable",
111
75
  source: loaded.source,
112
- stats: loaded.stats,
113
- visibleText,
114
- facts,
115
- reducer: selectedReducer,
116
- script: selectedScript,
76
+ facts: [],
77
+ maxVisibleBytes: limits.maxVisibleBytes,
78
+ failure: { reason: loaded.reason },
79
+ }),
80
+ facts: [],
81
+ reducer,
82
+ script,
117
83
  };
118
- const lineage = persisted.lineage ?? loaded.lineage;
119
- const persistence = persisted.persistence ?? loaded.persistence;
120
- const recovery = persisted.recovery ?? loaded.recovery;
121
- if (lineage !== undefined) {
122
- result.lineage = lineage;
123
- }
124
- if (persistence !== undefined) {
125
- result.persistence = persistence;
126
- }
127
- if (recovery !== undefined) {
128
- result.recovery = recovery;
129
- }
130
- return result;
84
+ }
85
+ const selectedScript = options.script
86
+ ? await runProcessingScript({
87
+ loaded,
88
+ script: options.script,
89
+ ...(options.scriptTransform !== undefined ? { scriptTransform: options.scriptTransform } : {}),
90
+ ...(options.localConfig !== undefined ? { localConfig: options.localConfig } : {}),
91
+ ...(options.scriptSandboxAdapters !== undefined ? { adapters: options.scriptSandboxAdapters } : {}),
92
+ })
93
+ : processingScriptNotConfigured();
94
+ const selectedReducer = scriptSkipsReducer(selectedScript)
95
+ ? notSelectedReducer(scriptReducerSkipReason(selectedScript))
96
+ : selectProcessingReducer({ text: loaded.text, ...(options.goal !== undefined ? { goal: options.goal } : {}) });
97
+ const facts =
98
+ selectedReducer.status === "selected"
99
+ ? [...selectedReducer.result.facts, ...sourceFacts(loaded)]
100
+ : sourceFacts(loaded);
101
+ const visibleText = renderProcessingResult({
102
+ status: "ok",
103
+ source: loaded.source,
104
+ stats: loaded.stats,
105
+ facts,
106
+ reducer: selectedReducer,
107
+ script: selectedScript,
108
+ ...(loaded.recovery !== undefined ? { recovery: loaded.recovery } : {}),
109
+ ...(loaded.persistence !== undefined ? { persistence: loaded.persistence } : {}),
110
+ recoveryClass: classifyProcessingRecovery({
111
+ ...(loaded.recovery !== undefined ? { recovery: loaded.recovery } : {}),
112
+ ...(loaded.persistence !== undefined ? { persistence: loaded.persistence } : {}),
113
+ resultWillBePersisted: options.sessionId !== undefined,
114
+ }),
115
+ maxVisibleBytes: limits.maxVisibleBytes,
116
+ });
117
+ const persisted = await persistProcessingResultText({
118
+ resultText: selectedScript.status === "executed" ? selectedScript.outputText : visibleText,
119
+ loaded,
120
+ options,
121
+ operation:
122
+ selectedScript.status === "executed" ? `processing-script:${selectedScript.language}` : "processing-fact-summary",
123
+ producerName:
124
+ selectedScript.status === "executed" ? `processing-script:${selectedScript.language}` : "processing-engine",
125
+ operationHashSeed:
126
+ selectedScript.status === "executed"
127
+ ? {
128
+ source: loaded.source,
129
+ stats: loaded.stats,
130
+ script: { language: selectedScript.language, codeHashSha256: selectedScript.codeHashSha256 },
131
+ }
132
+ : { source: loaded.source, stats: loaded.stats },
133
+ });
134
+ const result = {
135
+ implementation: PROCESSING_ENGINE_IMPLEMENTATION,
136
+ status: "ok",
137
+ source: loaded.source,
138
+ stats: loaded.stats,
139
+ visibleText,
140
+ facts,
141
+ reducer: selectedReducer,
142
+ script: selectedScript,
143
+ };
144
+ const lineage = persisted.lineage ?? loaded.lineage;
145
+ const persistence = persisted.persistence ?? loaded.persistence;
146
+ const recovery = persisted.recovery ?? loaded.recovery;
147
+ if (lineage !== undefined) {
148
+ result.lineage = lineage;
149
+ }
150
+ if (persistence !== undefined) {
151
+ result.persistence = persistence;
152
+ }
153
+ if (recovery !== undefined) {
154
+ result.recovery = recovery;
155
+ }
156
+ return result;
131
157
  }
132
158
  async function loadRepoFileSource(source, options, limits) {
133
- const descriptor = repoSourceDescriptor(source.path);
134
- let resolved;
135
- try {
136
- resolved = await resolveRepoPath(source.root, source.path);
137
- }
138
- catch (error) {
139
- const message = errorMessage(error);
140
- const blocked = message.includes("escapes root");
141
- return blocked
142
- ? { status: "blocked", source: descriptor, policy: "repo_containment", reason: message }
143
- : { status: "unavailable", source: descriptor, reason: message };
144
- }
145
- const resolvedDescriptor = repoSourceDescriptor(resolved.relativePath || ".");
146
- const fileStat = await stat(resolved.absolutePath);
147
- if (!fileStat.isFile()) {
148
- return { status: "unavailable", source: resolvedDescriptor, reason: `Repo source is not a file: ${resolved.relativePath || "."}` };
149
- }
150
- if (fileStat.size > limits.maxSourceBytes) {
151
- return {
152
- status: "blocked",
153
- source: resolvedDescriptor,
154
- policy: "source_limit",
155
- reason: `Repo source ${resolved.relativePath} is ${fileStat.size} bytes, above maxSourceBytes=${limits.maxSourceBytes}.`,
156
- stats: { bytes: fileStat.size },
157
- };
158
- }
159
- const text = await readFile(resolved.absolutePath, "utf8");
160
- const stats = textStats(text);
161
- const lineage = await persistRepoFileReferenceIfRequested({ sourcePath: resolved.relativePath, text, options });
159
+ const descriptor = repoSourceDescriptor(source.path);
160
+ let resolved;
161
+ try {
162
+ resolved = await resolveRepoPath(source.root, source.path);
163
+ } catch (error) {
164
+ const message = errorMessage(error);
165
+ const blocked = message.includes("escapes root");
166
+ return blocked
167
+ ? { status: "blocked", source: descriptor, policy: "repo_containment", reason: message }
168
+ : { status: "unavailable", source: descriptor, reason: message };
169
+ }
170
+ const resolvedDescriptor = repoSourceDescriptor(resolved.relativePath || ".");
171
+ const fileStat = await stat(resolved.absolutePath);
172
+ if (!fileStat.isFile()) {
162
173
  return {
163
- status: "ok",
164
- source: resolvedDescriptor,
165
- text,
166
- stats,
167
- ...(lineage !== undefined ? { lineage } : {}),
174
+ status: "unavailable",
175
+ source: resolvedDescriptor,
176
+ reason: `Repo source is not a file: ${resolved.relativePath || "."}`,
168
177
  };
169
- }
170
- async function loadVaultOutputSource(source, options, limits) {
171
- const requestedStream = source.stream;
172
- const unavailableDescriptor = vaultSourceDescriptor(source.outputId, requestedStream ?? "combined");
173
- const vaultOptions = {};
174
- const vaultRoot = source.vaultRoot ?? options.vaultRoot;
175
- if (vaultRoot !== undefined) {
176
- vaultOptions.root = vaultRoot;
177
- }
178
- if (options.vaultRetention !== undefined) {
179
- vaultOptions.retention = options.vaultRetention;
180
- }
181
- const vault = createVault(vaultOptions);
182
- let record;
183
- try {
184
- record = await readVaultRecord(vault, source.sessionId, source.outputId);
185
- }
186
- catch (error) {
187
- return { status: "unavailable", source: unavailableDescriptor, reason: errorMessage(error) };
188
- }
189
- const stream = resolveProcessingVaultStream(record, requestedStream);
190
- const descriptor = vaultSourceDescriptor(source.outputId, stream);
191
- const sourceBytes = byteCountForVaultStream(record, stream);
192
- if (sourceBytes !== undefined && sourceBytes > limits.maxSourceBytes) {
193
- return {
194
- status: "blocked",
195
- source: descriptor,
196
- policy: "source_limit",
197
- reason: `Vault source ${source.outputId}:${stream} is ${sourceBytes} bytes, above maxSourceBytes=${limits.maxSourceBytes}.`,
198
- stats: { bytes: sourceBytes },
199
- };
200
- }
201
- try {
202
- const text = await readOutputText(vault, source.sessionId, source.outputId, stream);
203
- const stats = textStats(text);
204
- if (stats.bytes > limits.maxSourceBytes) {
205
- return {
206
- status: "blocked",
207
- source: descriptor,
208
- policy: "source_limit",
209
- reason: `Vault source ${source.outputId}:${stream} is ${stats.bytes} bytes, above maxSourceBytes=${limits.maxSourceBytes}.`,
210
- stats: { bytes: stats.bytes },
211
- };
212
- }
213
- const lineage = {
214
- sourceRecordIds: record.recordId ? [record.recordId] : [],
215
- sourceOutputIds: [source.outputId],
216
- operation: "processing-source-load",
217
- };
218
- return {
219
- status: "ok",
220
- source: descriptor,
221
- text,
222
- stats,
223
- lineage,
224
- recovery: { how: `Recover source with freeflow_search action=retrieve outputId=${source.outputId} stream=${stream}.`, outputId: source.outputId },
225
- };
226
- }
227
- catch (error) {
228
- return { status: "unavailable", source: descriptor, reason: errorMessage(error) };
229
- }
230
- }
231
- function resolveProcessingVaultStream(record, requested) {
232
- if (requested !== undefined) {
233
- return requested;
234
- }
235
- return record.kind === "text" ? "raw" : "combined";
236
- }
237
- function vaultSourceDescriptor(outputId, stream) {
178
+ }
179
+ if (fileStat.size > limits.maxSourceBytes) {
238
180
  return {
239
- kind: "vault-output",
240
- ref: { kind: "vault", outputId, stream },
241
- displayPath: `${outputId}:${stream}`,
242
- stream,
181
+ status: "blocked",
182
+ source: resolvedDescriptor,
183
+ policy: "source_limit",
184
+ reason: `Repo source ${resolved.relativePath} is ${fileStat.size} bytes, above maxSourceBytes=${limits.maxSourceBytes}.`,
185
+ stats: { bytes: fileStat.size },
243
186
  };
187
+ }
188
+ const text = await readFile(resolved.absolutePath, "utf8");
189
+ const stats = textStats(text);
190
+ const lineage = await persistRepoFileReferenceIfRequested({ sourcePath: resolved.relativePath, text, options });
191
+ return {
192
+ status: "ok",
193
+ source: resolvedDescriptor,
194
+ text,
195
+ stats,
196
+ ...(lineage !== undefined ? { lineage } : {}),
197
+ };
244
198
  }
245
- function loadCapturedCommandOutputSource(source, limits) {
246
- const stream = source.stream ?? "combined";
247
- const descriptor = {
248
- kind: "command-output",
249
- ref: { kind: "native", tool: "command", outputId: source.outputId ?? "inline-command-output" },
250
- displayPath: source.outputId ? `${source.outputId}:${stream}` : `inline-command-output:${stream}`,
251
- stream,
199
+ async function loadLocalFileSource(source, limits) {
200
+ const descriptor = localSourceDescriptor(source.root, source.path);
201
+ let resolved;
202
+ try {
203
+ resolved = await resolveLocalPath(source.root, source.path);
204
+ } catch (error) {
205
+ const message = errorMessage(error);
206
+ const blocked =
207
+ message.includes("escapes root") ||
208
+ message.includes("absolute path") ||
209
+ message.includes("too broad") ||
210
+ message.includes("source.root");
211
+ return blocked
212
+ ? { status: "blocked", source: descriptor, policy: "repo_containment", reason: message }
213
+ : { status: "unavailable", source: descriptor, reason: message };
214
+ }
215
+ const resolvedDescriptor = localSourceDescriptor(resolved.root, resolved.relativePath || ".");
216
+ const fileStat = await stat(resolved.absolutePath);
217
+ if (!fileStat.isFile()) {
218
+ return {
219
+ status: "unavailable",
220
+ source: resolvedDescriptor,
221
+ reason: `Local source is not a file: ${resolved.relativePath || "."}`,
252
222
  };
253
- const text = commandOutputStreamText(source, stream);
254
- const stats = textStats(text);
255
- if (stats.bytes > limits.maxSourceBytes) {
256
- return {
257
- status: "blocked",
258
- source: descriptor,
259
- policy: "source_limit",
260
- reason: `Captured command output ${descriptor.displayPath} is ${stats.bytes} bytes, above maxSourceBytes=${limits.maxSourceBytes}.`,
261
- stats: { bytes: stats.bytes },
262
- };
263
- }
264
- const lineage = source.outputId
265
- ? { sourceOutputIds: [source.outputId], operation: "processing-source-load" }
266
- : undefined;
223
+ }
224
+ if (fileStat.size > limits.maxSourceBytes) {
267
225
  return {
268
- status: "ok",
269
- source: descriptor,
270
- text,
271
- stats,
272
- ...(lineage !== undefined ? { lineage } : {}),
273
- ...(source.outputId !== undefined
274
- ? { recovery: { how: `Recover source from captured command outputId=${source.outputId} stream=${stream}.`, outputId: source.outputId } }
275
- : {}),
226
+ status: "blocked",
227
+ source: resolvedDescriptor,
228
+ policy: "source_limit",
229
+ reason: `Local source ${resolved.relativePath} is ${fileStat.size} bytes, above maxSourceBytes=${limits.maxSourceBytes}.`,
230
+ stats: { bytes: fileStat.size },
276
231
  };
232
+ }
233
+ const text = await readFile(resolved.absolutePath, "utf8");
234
+ const stats = textStats(text);
235
+ return {
236
+ status: "ok",
237
+ source: resolvedDescriptor,
238
+ text,
239
+ stats,
240
+ recovery: {
241
+ how: `Recover source with freeflow_search action=retrieve source.kind=local root=${resolved.root} path=${resolved.relativePath}.`,
242
+ },
243
+ };
277
244
  }
278
- async function persistRepoFileReferenceIfRequested(input) {
279
- if (input.options.sessionId === undefined) {
280
- return undefined;
281
- }
282
- const vaultOptions = {};
283
- if (input.options.vaultRoot !== undefined) {
284
- vaultOptions.root = input.options.vaultRoot;
285
- }
286
- if (input.options.vaultRetention !== undefined) {
287
- vaultOptions.retention = input.options.vaultRetention;
288
- }
289
- const record = await storeRepoFileReference(createVault(vaultOptions), {
290
- sessionId: input.options.sessionId,
291
- path: input.sourcePath,
292
- hashSha256: sha256(input.text),
293
- producer: { kind: "repo", name: "processing-source-loader" },
294
- persistence: { status: "metadata_only", recoverability: "metadata_only" },
295
- });
245
+ async function loadVaultOutputSource(source, options, limits) {
246
+ const requestedStream = source.stream;
247
+ const unavailableDescriptor = vaultSourceDescriptor(source.outputId, requestedStream ?? "combined");
248
+ const vaultOptions = {};
249
+ const vaultRoot = source.vaultRoot ?? options.vaultRoot;
250
+ if (vaultRoot !== undefined) {
251
+ vaultOptions.root = vaultRoot;
252
+ }
253
+ if (options.vaultRetention !== undefined) {
254
+ vaultOptions.retention = options.vaultRetention;
255
+ }
256
+ const vault = createVault(vaultOptions);
257
+ let record;
258
+ try {
259
+ record = await readVaultRecord(vault, source.sessionId, source.outputId);
260
+ } catch (error) {
261
+ return { status: "unavailable", source: unavailableDescriptor, reason: errorMessage(error) };
262
+ }
263
+ const stream = resolveProcessingVaultStream(record, requestedStream);
264
+ const descriptor = vaultSourceDescriptor(source.outputId, stream);
265
+ const sourceBytes = byteCountForVaultStream(record, stream);
266
+ if (sourceBytes !== undefined && sourceBytes > limits.maxSourceBytes) {
296
267
  return {
297
- sourceRecordIds: [record.recordId],
298
- sourceOutputIds: [record.outputId],
299
- operation: "processing-source-load",
268
+ status: "blocked",
269
+ source: descriptor,
270
+ policy: "source_limit",
271
+ reason: `Vault source ${source.outputId}:${stream} is ${sourceBytes} bytes, above maxSourceBytes=${limits.maxSourceBytes}.`,
272
+ stats: { bytes: sourceBytes },
300
273
  };
301
- }
302
- async function persistProcessingResultText(input) {
303
- if (input.options.sessionId === undefined) {
304
- return {};
305
- }
306
- const vaultOptions = {};
307
- if (input.options.vaultRoot !== undefined) {
308
- vaultOptions.root = input.options.vaultRoot;
309
- }
310
- if (input.options.vaultRetention !== undefined) {
311
- vaultOptions.retention = input.options.vaultRetention;
274
+ }
275
+ try {
276
+ const text = await readOutputText(vault, source.sessionId, source.outputId, stream);
277
+ const stats = textStats(text);
278
+ if (stats.bytes > limits.maxSourceBytes) {
279
+ return {
280
+ status: "blocked",
281
+ source: descriptor,
282
+ policy: "source_limit",
283
+ reason: `Vault source ${source.outputId}:${stream} is ${stats.bytes} bytes, above maxSourceBytes=${limits.maxSourceBytes}.`,
284
+ stats: { bytes: stats.bytes },
285
+ };
312
286
  }
313
287
  const lineage = {
314
- ...(input.loaded.lineage?.sourceRecordIds !== undefined ? { sourceRecordIds: input.loaded.lineage.sourceRecordIds } : {}),
315
- ...(input.loaded.lineage?.sourceOutputIds !== undefined ? { sourceOutputIds: input.loaded.lineage.sourceOutputIds } : {}),
316
- operation: input.operation,
317
- operationHash: sha256(JSON.stringify(input.operationHashSeed)),
288
+ sourceRecordIds: record.recordId ? [record.recordId] : [],
289
+ sourceOutputIds: [source.outputId],
290
+ operation: "processing-source-load",
318
291
  };
319
- const record = await storeTextOutput(createVault(vaultOptions), {
320
- sessionId: input.options.sessionId,
321
- raw: input.resultText,
322
- sourceKind: "transform",
323
- producer: { kind: "transform", name: input.producerName },
324
- persistence: { status: "vaulted", recoverability: "exact" },
325
- lineage,
326
- });
327
- const persistence = { status: "vaulted", recoverability: "exact", outputId: record.outputId };
328
292
  return {
329
- lineage,
330
- persistence,
331
- recovery: { how: `Recover processing result with freeflow_search action=retrieve outputId=${record.outputId} stream=raw.`, outputId: record.outputId },
293
+ status: "ok",
294
+ source: descriptor,
295
+ text,
296
+ stats,
297
+ lineage,
298
+ recovery: {
299
+ how: `Recover source with freeflow_search action=retrieve outputId=${source.outputId} stream=${stream}.`,
300
+ outputId: source.outputId,
301
+ },
332
302
  };
303
+ } catch (error) {
304
+ return { status: "unavailable", source: descriptor, reason: errorMessage(error) };
305
+ }
333
306
  }
334
- function notSelectedReducer(reason) {
307
+ function resolveProcessingVaultStream(record, requested) {
308
+ if (requested !== undefined) {
309
+ return requested;
310
+ }
311
+ return record.kind === "text" ? "raw" : "combined";
312
+ }
313
+ function vaultSourceDescriptor(outputId, stream) {
314
+ return {
315
+ kind: "vault-output",
316
+ ref: { kind: "vault", outputId, stream },
317
+ displayPath: `${outputId}:${stream}`,
318
+ stream,
319
+ };
320
+ }
321
+ function loadCapturedCommandOutputSource(source, limits) {
322
+ const stream = source.stream ?? "combined";
323
+ const descriptor = {
324
+ kind: "command-output",
325
+ ref: { kind: "native", tool: "command", outputId: source.outputId ?? "inline-command-output" },
326
+ displayPath: source.outputId ? `${source.outputId}:${stream}` : `inline-command-output:${stream}`,
327
+ stream,
328
+ };
329
+ const text = commandOutputStreamText(source, stream);
330
+ const stats = textStats(text);
331
+ if (stats.bytes > limits.maxSourceBytes) {
335
332
  return {
336
- status: "not_selected",
337
- candidates: [],
338
- reason,
333
+ status: "blocked",
334
+ source: descriptor,
335
+ policy: "source_limit",
336
+ reason: `Captured command output ${descriptor.displayPath} is ${stats.bytes} bytes, above maxSourceBytes=${limits.maxSourceBytes}.`,
337
+ stats: { bytes: stats.bytes },
339
338
  };
339
+ }
340
+ const lineage = source.outputId
341
+ ? { sourceOutputIds: [source.outputId], operation: "processing-source-load" }
342
+ : undefined;
343
+ return {
344
+ status: "ok",
345
+ source: descriptor,
346
+ text,
347
+ stats,
348
+ ...(lineage !== undefined ? { lineage } : {}),
349
+ ...(source.outputId !== undefined
350
+ ? {
351
+ recovery: {
352
+ how: `Recover source from captured command outputId=${source.outputId} stream=${stream}.`,
353
+ outputId: source.outputId,
354
+ },
355
+ }
356
+ : {}),
357
+ };
358
+ }
359
+ async function persistRepoFileReferenceIfRequested(input) {
360
+ if (input.options.sessionId === undefined) {
361
+ return undefined;
362
+ }
363
+ const vaultOptions = {};
364
+ if (input.options.vaultRoot !== undefined) {
365
+ vaultOptions.root = input.options.vaultRoot;
366
+ }
367
+ if (input.options.vaultRetention !== undefined) {
368
+ vaultOptions.retention = input.options.vaultRetention;
369
+ }
370
+ const record = await storeRepoFileReference(createVault(vaultOptions), {
371
+ sessionId: input.options.sessionId,
372
+ path: input.sourcePath,
373
+ hashSha256: sha256(input.text),
374
+ producer: { kind: "repo", name: "processing-source-loader" },
375
+ persistence: { status: "metadata_only", recoverability: "metadata_only" },
376
+ });
377
+ return {
378
+ sourceRecordIds: [record.recordId],
379
+ sourceOutputIds: [record.outputId],
380
+ operation: "processing-source-load",
381
+ };
382
+ }
383
+ async function persistProcessingResultText(input) {
384
+ if (input.options.sessionId === undefined) {
385
+ return {};
386
+ }
387
+ const vaultOptions = {};
388
+ if (input.options.vaultRoot !== undefined) {
389
+ vaultOptions.root = input.options.vaultRoot;
390
+ }
391
+ if (input.options.vaultRetention !== undefined) {
392
+ vaultOptions.retention = input.options.vaultRetention;
393
+ }
394
+ const lineage = {
395
+ ...(input.loaded.lineage?.sourceRecordIds !== undefined
396
+ ? { sourceRecordIds: input.loaded.lineage.sourceRecordIds }
397
+ : {}),
398
+ ...(input.loaded.lineage?.sourceOutputIds !== undefined
399
+ ? { sourceOutputIds: input.loaded.lineage.sourceOutputIds }
400
+ : {}),
401
+ operation: input.operation,
402
+ operationHash: sha256(JSON.stringify(input.operationHashSeed)),
403
+ };
404
+ const record = await storeTextOutput(createVault(vaultOptions), {
405
+ sessionId: input.options.sessionId,
406
+ raw: input.resultText,
407
+ sourceKind: "transform",
408
+ producer: { kind: "transform", name: input.producerName },
409
+ persistence: { status: "vaulted", recoverability: "exact" },
410
+ lineage,
411
+ });
412
+ const persistence = { status: "vaulted", recoverability: "exact", outputId: record.outputId };
413
+ return {
414
+ lineage,
415
+ persistence,
416
+ recovery: {
417
+ how: `Recover processing result with freeflow_search action=retrieve outputId=${record.outputId} stream=raw.`,
418
+ outputId: record.outputId,
419
+ },
420
+ };
421
+ }
422
+ function notSelectedReducer(reason) {
423
+ return {
424
+ status: "not_selected",
425
+ candidates: [],
426
+ reason,
427
+ };
340
428
  }
341
429
  function scriptSkipsReducer(script) {
342
- return script.status === "executed" || ("policy" in script && script.policy === "unsafe-unsandboxed");
430
+ return script.status === "executed" || ("policy" in script && script.policy === "unsafe-unsandboxed");
343
431
  }
344
432
  function scriptReducerSkipReason(script) {
345
- if (script.status === "executed" && script.policy === "unsafe-unsandboxed") {
346
- return "Unsafe unsandboxed script processing produced output; reducer selection was skipped.";
347
- }
348
- if (script.status === "executed") {
349
- return "Sandboxed script processing produced output; reducer selection was skipped.";
350
- }
351
- return "Unsafe unsandboxed script processing was requested; reducer fallback was skipped to avoid silent fallback.";
433
+ if (script.status === "executed" && script.policy === "unsafe-unsandboxed") {
434
+ return "Unsafe unsandboxed script processing produced output; reducer selection was skipped.";
435
+ }
436
+ if (script.status === "executed") {
437
+ return "Sandboxed script processing produced output; reducer selection was skipped.";
438
+ }
439
+ return "Unsafe unsandboxed script processing was requested; reducer fallback was skipped to avoid silent fallback.";
352
440
  }
353
441
  function sourceFacts(loaded) {
354
- return [
355
- { name: "source.kind", value: loaded.source.kind },
356
- { name: "source.path", value: loaded.source.displayPath },
357
- { name: "source.bytes", value: loaded.stats.bytes },
358
- { name: "source.lines", value: loaded.stats.lines },
359
- { name: "source.sha256", value: loaded.stats.sha256 },
360
- ];
442
+ return [
443
+ { name: "source.kind", value: loaded.source.kind },
444
+ { name: "source.path", value: loaded.source.displayPath },
445
+ { name: "source.bytes", value: loaded.stats.bytes },
446
+ { name: "source.lines", value: loaded.stats.lines },
447
+ { name: "source.sha256", value: loaded.stats.sha256 },
448
+ ];
361
449
  }
362
450
  function commandOutputStreamText(source, stream) {
451
+ if (stream === "stdout") {
452
+ return source.stdout ?? "";
453
+ }
454
+ if (stream === "stderr") {
455
+ return source.stderr ?? "";
456
+ }
457
+ return source.combined ?? combineOutput(source.stdout ?? "", source.stderr ?? "");
458
+ }
459
+ function byteCountForVaultStream(record, stream) {
460
+ if (record.kind === "command") {
363
461
  if (stream === "stdout") {
364
- return source.stdout ?? "";
462
+ return record.byteCounts.stdout;
365
463
  }
366
464
  if (stream === "stderr") {
367
- return source.stderr ?? "";
368
- }
369
- return source.combined ?? combineOutput(source.stdout ?? "", source.stderr ?? "");
370
- }
371
- function byteCountForVaultStream(record, stream) {
372
- if (record.kind === "command") {
373
- if (stream === "stdout") {
374
- return record.byteCounts.stdout;
375
- }
376
- if (stream === "stderr") {
377
- return record.byteCounts.stderr;
378
- }
379
- if (stream === "combined" || stream === "raw") {
380
- return record.byteCounts.combined;
381
- }
465
+ return record.byteCounts.stderr;
382
466
  }
383
- if (record.kind === "text" && stream === "raw") {
384
- return record.byteCounts.raw;
467
+ if (stream === "combined" || stream === "raw") {
468
+ return record.byteCounts.combined;
385
469
  }
386
- return undefined;
470
+ }
471
+ if (record.kind === "text" && stream === "raw") {
472
+ return record.byteCounts.raw;
473
+ }
474
+ return undefined;
387
475
  }
388
476
  function normalizeLimits(limits) {
389
- return {
390
- maxSourceBytes: positiveInteger(limits?.maxSourceBytes) ?? DEFAULT_PROCESSING_LIMITS.maxSourceBytes,
391
- maxVisibleBytes: positiveInteger(limits?.maxVisibleBytes) ?? DEFAULT_PROCESSING_LIMITS.maxVisibleBytes,
392
- };
477
+ return {
478
+ maxSourceBytes: positiveInteger(limits?.maxSourceBytes) ?? DEFAULT_PROCESSING_LIMITS.maxSourceBytes,
479
+ maxVisibleBytes: positiveInteger(limits?.maxVisibleBytes) ?? DEFAULT_PROCESSING_LIMITS.maxVisibleBytes,
480
+ };
393
481
  }
394
482
  function positiveInteger(value) {
395
- return typeof value === "number" && Number.isFinite(value) && value > 0 ? Math.floor(value) : undefined;
483
+ return typeof value === "number" && Number.isFinite(value) && value > 0 ? Math.floor(value) : undefined;
396
484
  }
397
485
  function repoSourceDescriptor(displayPath) {
398
- return {
399
- kind: "repo-file",
400
- ref: { kind: "repo", path: displayPath },
401
- displayPath,
402
- };
486
+ return {
487
+ kind: "repo-file",
488
+ ref: { kind: "repo", path: displayPath },
489
+ displayPath,
490
+ };
491
+ }
492
+ function localSourceDescriptor(root, displayPath) {
493
+ return {
494
+ kind: "local-file",
495
+ ref: { kind: "local", root, path: displayPath },
496
+ displayPath,
497
+ };
403
498
  }
404
499
  function textStats(text) {
405
- return {
406
- bytes: byteLength(text),
407
- lines: countLines(text),
408
- sha256: sha256(text),
409
- };
500
+ return {
501
+ bytes: byteLength(text),
502
+ lines: countLines(text),
503
+ sha256: sha256(text),
504
+ };
410
505
  }
411
506
  function byteLength(text) {
412
- return Buffer.byteLength(text, "utf8");
507
+ return Buffer.byteLength(text, "utf8");
413
508
  }
414
509
  function countLines(text) {
415
- if (text.length === 0) {
416
- return 0;
417
- }
418
- return text.split(/\r?\n/).length;
510
+ if (text.length === 0) {
511
+ return 0;
512
+ }
513
+ return text.split(/\r?\n/).length;
419
514
  }
420
515
  function sha256(text) {
421
- return createHash("sha256").update(text).digest("hex");
516
+ return createHash("sha256").update(text).digest("hex");
422
517
  }
423
518
  function combineOutput(stdout, stderr) {
424
- if (stdout && stderr) {
425
- return `[stdout]\n${stdout}\n[stderr]\n${stderr}`;
426
- }
427
- return stdout || stderr;
519
+ if (stdout && stderr) {
520
+ return `[stdout]\n${stdout}\n[stderr]\n${stderr}`;
521
+ }
522
+ return stdout || stderr;
428
523
  }
429
524
  function errorMessage(error) {
430
- return error instanceof Error ? error.message : String(error);
525
+ return error instanceof Error ? error.message : String(error);
431
526
  }
432
527
  export function isProcessingPathInsideRoot(root, absolutePath) {
433
- const relativePath = relative(root, absolutePath);
434
- return relativePath === "" || (!relativePath.startsWith("..") && !relativePath.startsWith("/") && !/^[A-Za-z]:/.test(relativePath));
528
+ const relativePath = relative(root, absolutePath);
529
+ return (
530
+ relativePath === "" ||
531
+ (!relativePath.startsWith("..") && !relativePath.startsWith("/") && !/^[A-Za-z]:/.test(relativePath))
532
+ );
435
533
  }