@hassangameryt/freeflow 0.2.0 → 0.4.0

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 (312) hide show
  1. package/.agents/plugins/marketplace.json +1 -1
  2. package/.claude-plugin/marketplace.json +4 -4
  3. package/{plugins/freeflow/.claude-plugin → .claude-plugin}/plugin.json +5 -2
  4. package/{plugins/freeflow/.codex-plugin → .codex-plugin}/plugin.json +8 -9
  5. package/README.md +194 -127
  6. package/assets/feedback-loop.png +0 -0
  7. package/assets/freeflow-plugin-icon.png +0 -0
  8. package/assets/freeflow_workflow_map.png +0 -0
  9. package/assets/workflow.png +0 -0
  10. package/command-surface.json +129 -0
  11. package/hooks/freeflow-runtime-context.mjs +419 -0
  12. package/hooks/tests/check-runtime-context-hook.sh +223 -0
  13. package/package.json +41 -22
  14. package/pi-extension/dist/index.js +269 -0
  15. package/pi-extension/dist/integrations/mcp-config.js +29 -0
  16. package/pi-extension/dist/output-router/host-producer-identification.js +232 -0
  17. package/pi-extension/dist/output-router/native-safety-net.js +216 -0
  18. package/pi-extension/dist/output-router/observed-tool-routing.js +122 -0
  19. package/pi-extension/dist/output-router/renderers.js +1023 -0
  20. package/pi-extension/dist/output-router/router-tools.js +554 -0
  21. package/pi-extension/dist/output-router/schemas.js +383 -0
  22. package/pi-extension/dist/output-router/status.js +744 -0
  23. package/pi-extension/dist/output-router/utils.js +502 -0
  24. package/pi-extension/dist/runtime/runtime-context.js +798 -0
  25. package/pi-extension/dist/settings/settings-tui.js +314 -0
  26. package/pi-extension/dist/settings/settings-ui.js +1487 -0
  27. package/pi-extension/freeflow/index.js +1 -0
  28. package/pi-extension/src/index.ts +295 -0
  29. package/pi-extension/src/integrations/mcp-config.ts +32 -0
  30. package/pi-extension/src/output-router/host-producer-identification.ts +256 -0
  31. package/pi-extension/src/output-router/native-safety-net.ts +248 -0
  32. package/pi-extension/src/output-router/observed-tool-routing.ts +134 -0
  33. package/pi-extension/src/output-router/renderers.ts +1108 -0
  34. package/pi-extension/src/output-router/router-tools.ts +579 -0
  35. package/pi-extension/src/output-router/schemas.ts +387 -0
  36. package/pi-extension/src/output-router/status.ts +791 -0
  37. package/pi-extension/src/output-router/utils.ts +554 -0
  38. package/pi-extension/src/runtime/runtime-context.ts +895 -0
  39. package/pi-extension/src/settings/settings-tui.ts +408 -0
  40. package/pi-extension/src/settings/settings-ui.ts +1730 -0
  41. package/pi-extension/tests/integration/pi-extension.test.js +4018 -0
  42. package/pi-extension/tests/output-router/observed-producers.test.js +132 -0
  43. package/pi-extension/tests/output-router/search.test.js +722 -0
  44. package/pi-extension/tests/settings/settings-tui.test.js +243 -0
  45. package/pi-extension/tsconfig.json +16 -0
  46. package/{plugins/freeflow/router/dist → router/dist/benchmarks}/benchmark-harness.d.ts +16 -13
  47. package/router/dist/benchmarks/benchmark-harness.js +92 -0
  48. package/router/dist/benchmarks/benchmarks.d.ts +109 -0
  49. package/router/dist/benchmarks/benchmarks.js +979 -0
  50. package/router/dist/benchmarks/codex-qa-benchmarks.d.ts +95 -0
  51. package/router/dist/benchmarks/codex-qa-benchmarks.js +500 -0
  52. package/router/dist/benchmarks/command-benchmarks.d.ts +143 -0
  53. package/router/dist/benchmarks/command-benchmarks.js +698 -0
  54. package/router/dist/benchmarks/context-mode-normalized-benchmarks.d.ts +82 -0
  55. package/router/dist/benchmarks/context-mode-normalized-benchmarks.js +773 -0
  56. package/router/dist/benchmarks/context-mode-real-deep-benchmark.d.ts +132 -0
  57. package/router/dist/benchmarks/context-mode-real-deep-benchmark.js +1380 -0
  58. package/router/dist/benchmarks/context-saving-baseline.d.ts +60 -0
  59. package/router/dist/benchmarks/context-saving-baseline.js +470 -0
  60. package/router/dist/benchmarks/index-benchmarks.d.ts +103 -0
  61. package/router/dist/benchmarks/index-benchmarks.js +862 -0
  62. package/router/dist/benchmarks/storage-policy-benchmarks.d.ts +101 -0
  63. package/router/dist/benchmarks/storage-policy-benchmarks.js +618 -0
  64. package/router/dist/benchmarks/vault-index-benchmarks.d.ts +56 -0
  65. package/router/dist/benchmarks/vault-index-benchmarks.js +322 -0
  66. package/router/dist/config/config.d.ts +103 -0
  67. package/router/dist/config/config.js +632 -0
  68. package/{plugins/freeflow/router/dist → router/dist/config}/router-contract.d.ts +2 -2
  69. package/router/dist/config/router-contract.js +54 -0
  70. package/{plugins/freeflow/router/dist → router/dist/config}/schema.d.ts +19 -10
  71. package/router/dist/config/schema.js +648 -0
  72. package/router/dist/config/types.d.ts +573 -0
  73. package/router/dist/config/types.js +41 -0
  74. package/router/dist/evidence/bounded-evidence.d.ts +40 -0
  75. package/router/dist/evidence/bounded-evidence.js +323 -0
  76. package/router/dist/evidence/evidence-range-selector.d.ts +24 -0
  77. package/router/dist/evidence/evidence-range-selector.js +232 -0
  78. package/router/dist/evidence/evidence-search.d.ts +27 -0
  79. package/router/dist/evidence/evidence-search.js +490 -0
  80. package/{plugins/freeflow/router/dist → router/dist/evidence}/evidence.d.ts +18 -18
  81. package/router/dist/evidence/evidence.js +200 -0
  82. package/router/dist/evidence/failure-contracts.d.ts +37 -0
  83. package/router/dist/evidence/failure-contracts.js +166 -0
  84. package/router/dist/evidence/line-ranges.d.ts +24 -0
  85. package/router/dist/evidence/line-ranges.js +22 -0
  86. package/router/dist/experiments/local-index.d.ts +64 -0
  87. package/router/dist/experiments/local-index.js +581 -0
  88. package/router/dist/index.d.ts +30 -0
  89. package/router/dist/index.js +32 -0
  90. package/router/dist/local/local-traversal.d.ts +18 -0
  91. package/router/dist/local/local-traversal.js +334 -0
  92. package/router/dist/processing/engine.d.ts +132 -0
  93. package/router/dist/processing/engine.js +533 -0
  94. package/router/dist/processing/reducers.d.ts +280 -0
  95. package/router/dist/processing/reducers.js +1673 -0
  96. package/router/dist/processing/renderers.d.ts +31 -0
  97. package/router/dist/processing/renderers.js +195 -0
  98. package/router/dist/processing/scripts.d.ts +91 -0
  99. package/router/dist/processing/scripts.js +386 -0
  100. package/{plugins/freeflow/router/dist → router/dist/repo}/repo-traversal.d.ts +9 -9
  101. package/router/dist/repo/repo-traversal.js +245 -0
  102. package/router/dist/routing/observed-reducers.d.ts +41 -0
  103. package/router/dist/routing/observed-reducers.js +661 -0
  104. package/router/dist/routing/observed-routing.d.ts +26 -0
  105. package/router/dist/routing/observed-routing.js +378 -0
  106. package/router/dist/routing/parsers.d.ts +16 -0
  107. package/router/dist/routing/parsers.js +521 -0
  108. package/router/dist/routing/run-filters.d.ts +60 -0
  109. package/router/dist/routing/run-filters.js +238 -0
  110. package/router/dist/routing/run-reducers.d.ts +49 -0
  111. package/router/dist/routing/run-reducers.js +122 -0
  112. package/router/dist/sandbox/adapter-roots.d.ts +46 -0
  113. package/router/dist/sandbox/adapter-roots.js +66 -0
  114. package/router/dist/sandbox/eryx-python-adapter.d.ts +13 -0
  115. package/router/dist/sandbox/eryx-python-adapter.js +868 -0
  116. package/router/dist/sandbox/jq-wasm-adapter.d.ts +9 -0
  117. package/router/dist/sandbox/jq-wasm-adapter.js +429 -0
  118. package/router/dist/sandbox/quickjs-wasi-adapter.d.ts +13 -0
  119. package/router/dist/sandbox/quickjs-wasi-adapter.js +384 -0
  120. package/router/dist/sandbox/script-sandbox.d.ts +134 -0
  121. package/router/dist/sandbox/script-sandbox.js +337 -0
  122. package/router/dist/setup/script-transform-adapters.d.ts +32 -0
  123. package/router/dist/setup/script-transform-adapters.js +278 -0
  124. package/router/dist/tools/batch.d.ts +33 -0
  125. package/router/dist/tools/batch.js +586 -0
  126. package/router/dist/tools/run.d.ts +62 -0
  127. package/router/dist/tools/run.js +1304 -0
  128. package/router/dist/tools/search.d.ts +66 -0
  129. package/router/dist/tools/search.js +1364 -0
  130. package/router/dist/transform/engine.d.ts +168 -0
  131. package/router/dist/transform/engine.js +2072 -0
  132. package/router/dist/vault/vault-index.d.ts +125 -0
  133. package/router/dist/vault/vault-index.js +416 -0
  134. package/router/dist/vault/vault.d.ts +138 -0
  135. package/router/dist/vault/vault.js +630 -0
  136. package/runtime/interaction-contract.md +16 -0
  137. package/skills/bypass/SKILL.md +82 -0
  138. package/skills/commit-work/SKILL.md +106 -0
  139. package/skills/commit-work/references/staging-decisions.md +73 -0
  140. package/skills/decision-gate/SKILL.md +48 -0
  141. package/skills/design-for-depth/SKILL.md +106 -0
  142. package/skills/design-for-depth/references/design-pressure-signals.md +314 -0
  143. package/skills/design-for-depth/references/interface-design-loop.md +156 -0
  144. package/skills/design-for-depth/references/software-design-philosophy.md +248 -0
  145. package/skills/diagnose-failure/SKILL.md +105 -0
  146. package/skills/diagnose-failure/references/diagnostic-loop-catalog.md +36 -0
  147. package/skills/diagnose-failure/references/flaky-and-performance.md +43 -0
  148. package/skills/discuss/SKILL.md +121 -0
  149. package/skills/discuss/references/checkpoints.md +66 -0
  150. package/skills/evaluate-skill/SKILL.md +105 -0
  151. package/skills/evaluate-skill/references/definition-schema.md +345 -0
  152. package/skills/evaluate-skill/references/evaluation-design.md +86 -0
  153. package/skills/evaluate-skill/references/execution-and-evidence.md +85 -0
  154. package/skills/evaluate-skill/references/review-and-revision.md +51 -0
  155. package/skills/evaluate-skill/scripts/lib/definitions.mjs +296 -0
  156. package/skills/evaluate-skill/scripts/lib/evidence.mjs +46 -0
  157. package/skills/evaluate-skill/scripts/lib/grade-comparison.mjs +60 -0
  158. package/skills/evaluate-skill/scripts/lib/grade-interaction.mjs +148 -0
  159. package/skills/evaluate-skill/scripts/lib/grade-support.mjs +126 -0
  160. package/skills/evaluate-skill/scripts/lib/grade-workspace.mjs +192 -0
  161. package/skills/evaluate-skill/scripts/lib/grade.mjs +56 -0
  162. package/skills/evaluate-skill/scripts/lib/pi.mjs +489 -0
  163. package/skills/evaluate-skill/scripts/lib/process.mjs +79 -0
  164. package/skills/evaluate-skill/scripts/lib/rpc.mjs +444 -0
  165. package/skills/evaluate-skill/scripts/lib/runner.mjs +346 -0
  166. package/skills/evaluate-skill/scripts/lib/sandbox.mjs +409 -0
  167. package/skills/evaluate-skill/scripts/lib/view.mjs +337 -0
  168. package/skills/evaluate-skill/scripts/pi-guard.mjs +164 -0
  169. package/skills/evaluate-skill/scripts/skill-eval.mjs +101 -0
  170. package/skills/execute-work/SKILL.md +99 -0
  171. package/skills/execute-work/references/code-practices.md +78 -0
  172. package/skills/execute-work/references/execution-loop.md +77 -0
  173. package/skills/finish-branch/SKILL.md +117 -0
  174. package/skills/finish-branch/references/integration-options.md +80 -0
  175. package/skills/handoff/SKILL.md +92 -0
  176. package/skills/handoff/references/templates.md +141 -0
  177. package/skills/launch-work/SKILL.md +116 -0
  178. package/skills/launch-work/references/launch-readiness.md +85 -0
  179. package/skills/migration-work/SKILL.md +115 -0
  180. package/skills/migration-work/references/migration-lifecycle.md +82 -0
  181. package/skills/mode-contract/SKILL.md +82 -0
  182. package/skills/output-router/SKILL.md +206 -0
  183. package/skills/output-router/references/safety-policy.md +40 -0
  184. package/skills/release-work/SKILL.md +118 -0
  185. package/skills/release-work/references/release-evidence.md +78 -0
  186. package/skills/review-artifact/SKILL.md +126 -0
  187. package/skills/review-artifact/references/reviewer-prompt.md +148 -0
  188. package/skills/review-work/SKILL.md +126 -0
  189. package/skills/review-work/references/reviewer-prompt.md +134 -0
  190. package/skills/review-work/references/security-risk-lens.md +67 -0
  191. package/skills/setup-freeflow/SKILL.md +98 -0
  192. package/skills/setup-freeflow/references/activation-contract.md +120 -0
  193. package/skills/setup-freeflow/references/host-setup.md +72 -0
  194. package/skills/setup-freeflow/references/output-router-setup.md +110 -0
  195. package/skills/simplify-code/SKILL.md +80 -0
  196. package/skills/simplify-code/references/simplification-patterns.md +70 -0
  197. package/skills/tdd/SKILL.md +96 -0
  198. package/skills/tdd/references/test-design.md +96 -0
  199. package/skills/track-work/SKILL.md +84 -0
  200. package/skills/track-work/references/working-record-schema.md +378 -0
  201. package/skills/verify-work/SKILL.md +85 -0
  202. package/skills/verify-work/references/browser-runtime-evidence.md +55 -0
  203. package/skills/verify-work/references/integration-evidence.md +51 -0
  204. package/skills/verify-work/references/performance-evidence.md +57 -0
  205. package/skills/workflow/SKILL.md +91 -0
  206. package/skills/workflow/references/domain-skill-composition.md +57 -0
  207. package/skills/workflow/references/workflow-loop.md +92 -0
  208. package/skills/write-plan/SKILL.md +123 -0
  209. package/skills/write-plan/references/plan-shapes.md +156 -0
  210. package/skills/write-skill/SKILL.md +119 -0
  211. package/skills/write-skill/references/activation-boundaries.md +62 -0
  212. package/skills/write-skill/references/agent-first-instructions.md +87 -0
  213. package/skills/write-skill/references/progressive-disclosure.md +63 -0
  214. package/skills/write-skill/scripts/lib/skill-author.mjs +653 -0
  215. package/skills/write-skill/scripts/skill-author.mjs +104 -0
  216. package/skills/write-spec/SKILL.md +104 -0
  217. package/skills/write-spec/references/artifact-standards.md +86 -0
  218. package/skills/write-spec/references/decision-records.md +77 -0
  219. package/skills/write-spec/references/spec-shapes.md +128 -0
  220. package/plugins/freeflow/command-surface.json +0 -77
  221. package/plugins/freeflow/docs/README.md +0 -40
  222. package/plugins/freeflow/docs/adr/0001-three-modes.md +0 -27
  223. package/plugins/freeflow/docs/adr/0002-evals-before-hooks.md +0 -17
  224. package/plugins/freeflow/docs/adr/0003-release-boundary.md +0 -21
  225. package/plugins/freeflow/docs/adr/0004-research-replaces-shallow-discovery-skills.md +0 -26
  226. package/plugins/freeflow/docs/adr/README.md +0 -8
  227. package/plugins/freeflow/docs/architecture.md +0 -86
  228. package/plugins/freeflow/docs/output-router.md +0 -212
  229. package/plugins/freeflow/docs/release-evidence.md +0 -69
  230. package/plugins/freeflow/docs/skills.md +0 -43
  231. package/plugins/freeflow/docs/workflow.md +0 -57
  232. package/plugins/freeflow/hooks/freeflow-runtime-context.mjs +0 -257
  233. package/plugins/freeflow/pi-extension/index.js +0 -1176
  234. package/plugins/freeflow/router/dist/benchmark-harness.js +0 -92
  235. package/plugins/freeflow/router/dist/benchmarks.d.ts +0 -102
  236. package/plugins/freeflow/router/dist/benchmarks.js +0 -880
  237. package/plugins/freeflow/router/dist/bounded-evidence.d.ts +0 -40
  238. package/plugins/freeflow/router/dist/bounded-evidence.js +0 -310
  239. package/plugins/freeflow/router/dist/codex-qa-benchmarks.d.ts +0 -91
  240. package/plugins/freeflow/router/dist/codex-qa-benchmarks.js +0 -461
  241. package/plugins/freeflow/router/dist/command-benchmarks.d.ts +0 -128
  242. package/plugins/freeflow/router/dist/command-benchmarks.js +0 -652
  243. package/plugins/freeflow/router/dist/config.d.ts +0 -22
  244. package/plugins/freeflow/router/dist/config.js +0 -114
  245. package/plugins/freeflow/router/dist/evidence-range-selector.d.ts +0 -22
  246. package/plugins/freeflow/router/dist/evidence-range-selector.js +0 -180
  247. package/plugins/freeflow/router/dist/evidence-search.d.ts +0 -25
  248. package/plugins/freeflow/router/dist/evidence-search.js +0 -450
  249. package/plugins/freeflow/router/dist/evidence.js +0 -196
  250. package/plugins/freeflow/router/dist/experimental-local-index.d.ts +0 -1
  251. package/plugins/freeflow/router/dist/experimental-local-index.js +0 -1
  252. package/plugins/freeflow/router/dist/experiments/local-index.d.ts +0 -58
  253. package/plugins/freeflow/router/dist/experiments/local-index.js +0 -562
  254. package/plugins/freeflow/router/dist/index-benchmarks.d.ts +0 -84
  255. package/plugins/freeflow/router/dist/index-benchmarks.js +0 -458
  256. package/plugins/freeflow/router/dist/index.d.ts +0 -12
  257. package/plugins/freeflow/router/dist/index.js +0 -12
  258. package/plugins/freeflow/router/dist/line-ranges.d.ts +0 -22
  259. package/plugins/freeflow/router/dist/line-ranges.js +0 -22
  260. package/plugins/freeflow/router/dist/parsers.d.ts +0 -16
  261. package/plugins/freeflow/router/dist/parsers.js +0 -473
  262. package/plugins/freeflow/router/dist/repo-traversal.js +0 -242
  263. package/plugins/freeflow/router/dist/retrieve.d.ts +0 -33
  264. package/plugins/freeflow/router/dist/retrieve.js +0 -855
  265. package/plugins/freeflow/router/dist/router-contract.js +0 -54
  266. package/plugins/freeflow/router/dist/run.d.ts +0 -26
  267. package/plugins/freeflow/router/dist/run.js +0 -356
  268. package/plugins/freeflow/router/dist/schema.js +0 -354
  269. package/plugins/freeflow/router/dist/types.d.ts +0 -234
  270. package/plugins/freeflow/router/dist/types.js +0 -9
  271. package/plugins/freeflow/router/dist/vault.d.ts +0 -80
  272. package/plugins/freeflow/router/dist/vault.js +0 -484
  273. package/plugins/freeflow/skills/bypass/SKILL.md +0 -68
  274. package/plugins/freeflow/skills/commit-work/SKILL.md +0 -98
  275. package/plugins/freeflow/skills/commit-work/references/staging-decisions.md +0 -51
  276. package/plugins/freeflow/skills/diagnose-failure/SKILL.md +0 -95
  277. package/plugins/freeflow/skills/diagnose-failure/references/feedback-loop-catalog.md +0 -25
  278. package/plugins/freeflow/skills/diagnose-failure/references/flaky-and-performance.md +0 -31
  279. package/plugins/freeflow/skills/evaluate-skill/SKILL.md +0 -96
  280. package/plugins/freeflow/skills/evaluate-skill/references/eval-patterns.md +0 -41
  281. package/plugins/freeflow/skills/evaluate-skill/references/grading-priority.md +0 -33
  282. package/plugins/freeflow/skills/execute-plan/SKILL.md +0 -132
  283. package/plugins/freeflow/skills/execute-plan/references/execution-map.md +0 -122
  284. package/plugins/freeflow/skills/handoff/SKILL.md +0 -66
  285. package/plugins/freeflow/skills/handoff/references/templates.md +0 -64
  286. package/plugins/freeflow/skills/interview-gate/SKILL.md +0 -90
  287. package/plugins/freeflow/skills/mode-contract/SKILL.md +0 -79
  288. package/plugins/freeflow/skills/output-router/SKILL.md +0 -69
  289. package/plugins/freeflow/skills/output-router/references/safety-policy.md +0 -33
  290. package/plugins/freeflow/skills/research/ARTIFACT-DESTINATIONS.md +0 -58
  291. package/plugins/freeflow/skills/research/CHECKPOINTS.md +0 -74
  292. package/plugins/freeflow/skills/research/LANGUAGE.md +0 -61
  293. package/plugins/freeflow/skills/research/SKILL.md +0 -128
  294. package/plugins/freeflow/skills/review-artifact/SKILL.md +0 -115
  295. package/plugins/freeflow/skills/review-artifact/references/reviewer-prompt.md +0 -56
  296. package/plugins/freeflow/skills/review-work/SKILL.md +0 -96
  297. package/plugins/freeflow/skills/review-work/references/reviewer-prompt.md +0 -97
  298. package/plugins/freeflow/skills/setup-freeflow/SKILL.md +0 -94
  299. package/plugins/freeflow/skills/setup-freeflow/references/activation-contract.md +0 -99
  300. package/plugins/freeflow/skills/setup-freeflow/references/host-setup.md +0 -35
  301. package/plugins/freeflow/skills/setup-freeflow/references/output-router-setup.md +0 -52
  302. package/plugins/freeflow/skills/verify-work/SKILL.md +0 -62
  303. package/plugins/freeflow/skills/workflow/SKILL.md +0 -95
  304. package/plugins/freeflow/skills/workflow/references/workflow-map.md +0 -102
  305. package/plugins/freeflow/skills/write-plan/SKILL.md +0 -88
  306. package/plugins/freeflow/skills/write-plan/references/plan-shapes.md +0 -70
  307. package/plugins/freeflow/skills/write-skill/SKILL.md +0 -88
  308. package/plugins/freeflow/skills/write-spec/SKILL.md +0 -90
  309. package/plugins/freeflow/skills/write-spec/references/artifact-standards.md +0 -67
  310. package/plugins/freeflow/skills/write-spec/references/spec-shapes.md +0 -69
  311. /package/{plugins/freeflow/assets → assets}/freeflow-plugin-icon-transparent.png +0 -0
  312. /package/{plugins/freeflow/hooks → hooks}/hooks.json +0 -0
@@ -1,92 +0,0 @@
1
- import { mkdir, writeFile } from "node:fs/promises";
2
- import { basename, dirname, resolve } from "node:path";
3
- export function normalizeIterations(value, defaultIterations = 3) {
4
- if (typeof value === "number" && Number.isFinite(value) && value > 0) {
5
- return Math.max(1, Math.floor(value));
6
- }
7
- if (Number.isFinite(defaultIterations) && defaultIterations > 0) {
8
- return Math.max(1, Math.floor(defaultIterations));
9
- }
10
- return 1;
11
- }
12
- export function approximateTokens(bytes) {
13
- return Math.ceil(bytes / 4);
14
- }
15
- export function percentile(values, quantile) {
16
- if (values.length === 0) {
17
- return 0;
18
- }
19
- const sorted = [...values].sort((a, b) => a - b);
20
- const index = Math.min(sorted.length - 1, Math.max(0, Math.ceil(sorted.length * quantile) - 1));
21
- return sorted[index] ?? 0;
22
- }
23
- export function latencySummary(values) {
24
- return {
25
- p50: percentile(values, 0.5),
26
- p95: percentile(values, 0.95),
27
- };
28
- }
29
- export function averagePercent(values) {
30
- if (values.length === 0) {
31
- return 0;
32
- }
33
- return roundPercent(values.reduce((sum, value) => sum + value, 0) / values.length);
34
- }
35
- export function medianPercent(values) {
36
- return roundPercent(percentile(values, 0.5));
37
- }
38
- export function reductionPercent(raw, routed) {
39
- if (raw <= 0) {
40
- return 0;
41
- }
42
- return roundPercent(((raw - routed) / raw) * 100);
43
- }
44
- export function formatPercent(value) {
45
- return `${value.toFixed(2)}%`;
46
- }
47
- export function escapeMarkdownTableCell(value) {
48
- return value.replace(/\|/g, "\\|").replace(/\n/g, " ");
49
- }
50
- export function defaultJsonRunReportPath(markdownReportPath) {
51
- const markdownName = basename(markdownReportPath);
52
- const jsonName = markdownName.endsWith(".md") ? `${markdownName.slice(0, -".md".length)}.json` : `${markdownName}.json`;
53
- return resolve(process.cwd(), "plugins/freeflow/evals/runs/output-router", jsonName);
54
- }
55
- export function parseBenchmarkCliArgs(argv, defaults) {
56
- let iterations;
57
- let reportPath = defaults.reportPath;
58
- let jsonReportPath;
59
- for (const arg of argv) {
60
- if (arg.startsWith("--iterations=")) {
61
- const value = Number(arg.slice("--iterations=".length));
62
- if (Number.isFinite(value) && value > 0) {
63
- iterations = value;
64
- }
65
- }
66
- else if (arg.startsWith("--report=")) {
67
- reportPath = resolve(process.cwd(), arg.slice("--report=".length));
68
- }
69
- else if (arg.startsWith("--json-report=")) {
70
- const value = arg.slice("--json-report=".length);
71
- jsonReportPath = value === "off" ? false : resolve(process.cwd(), value);
72
- }
73
- }
74
- const parsed = iterations === undefined ? { reportPath } : { iterations, reportPath };
75
- return jsonReportPath === undefined ? parsed : { ...parsed, jsonReportPath };
76
- }
77
- export async function writeBenchmarkReportPair(options) {
78
- await mkdir(dirname(options.markdownReportPath), { recursive: true });
79
- await writeFile(options.markdownReportPath, options.renderMarkdown(options.report), "utf8");
80
- if (options.jsonReportPath === false) {
81
- return { markdown: options.markdownReportPath };
82
- }
83
- if (options.jsonReportPath) {
84
- await mkdir(dirname(options.jsonReportPath), { recursive: true });
85
- await writeFile(options.jsonReportPath, `${JSON.stringify(options.report, null, 2)}\n`, "utf8");
86
- return { markdown: options.markdownReportPath, json: options.jsonReportPath };
87
- }
88
- return { markdown: options.markdownReportPath };
89
- }
90
- function roundPercent(value) {
91
- return Math.round(value * 100) / 100;
92
- }
@@ -1,102 +0,0 @@
1
- export interface RunRouterBenchmarksOptions {
2
- iterations?: number;
3
- generatedAt?: string;
4
- }
5
- export interface RouterBenchmarkReport {
6
- generatedAt: string;
7
- iterations: number;
8
- summary: RouterBenchmarkSummary;
9
- fixtures: RouterBenchmarkFixtureResult[];
10
- skippedExternalTools: SkippedExternalTool[];
11
- }
12
- export interface RouterBenchmarkSummary {
13
- fixtures: number;
14
- modeResults: number;
15
- improved: ModeSummary;
16
- nativeBaseline: ModeSummary;
17
- freeflowBaseline: ModeSummary;
18
- generatedFalsePositiveCount: number;
19
- sandboxFailureFixed: boolean;
20
- }
21
- export interface ModeSummary {
22
- passed: number;
23
- failed: number;
24
- skipped: number;
25
- pathCorrect: number;
26
- spanCorrect: number;
27
- excerptComplete: number;
28
- generatedFalsePositiveCount: number;
29
- totalRawBytes: number;
30
- totalRoutedBytes: number;
31
- totalRawTokensApprox: number;
32
- totalRoutedTokensApprox: number;
33
- weightedByteReductionPercent: number;
34
- weightedTokenReductionPercent: number;
35
- averageByteReductionPercent: number;
36
- medianByteReductionPercent: number;
37
- averageTokenReductionPercent: number;
38
- medianTokenReductionPercent: number;
39
- }
40
- export interface RouterBenchmarkFixtureResult {
41
- id: string;
42
- title: string;
43
- kind: BenchmarkKind;
44
- expected: BenchmarkExpected;
45
- results: RouterBenchmarkModeResult[];
46
- }
47
- export interface RouterBenchmarkModeResult {
48
- mode: BenchmarkMode;
49
- toolPathUsed: string;
50
- skipped: boolean;
51
- skipReason?: string;
52
- rawBytes: number;
53
- rawTokensApprox: number;
54
- routedBytes: number;
55
- routedTokensApprox: number;
56
- byteReductionPercent: number;
57
- tokenReductionPercent: number;
58
- latencyMs: {
59
- p50: number;
60
- p95: number;
61
- };
62
- actualPath?: string;
63
- actualLines?: string;
64
- correctness: CorrectnessResult;
65
- recovery: RecoveryResult;
66
- notes: string[];
67
- }
68
- export interface BenchmarkExpected {
69
- path?: string;
70
- pathIncludes?: string;
71
- lines?: string;
72
- requiredExcerpt?: string[];
73
- }
74
- export interface CorrectnessResult {
75
- passed: boolean;
76
- pathCorrect: boolean;
77
- spanCorrect: boolean;
78
- excerptComplete: boolean;
79
- generatedFalsePositive: boolean;
80
- }
81
- export interface RecoveryResult {
82
- status: "passed" | "failed" | "not-applicable" | "skipped";
83
- detail: string;
84
- }
85
- export interface SkippedExternalTool {
86
- name: string;
87
- reason: string;
88
- }
89
- type BenchmarkKind = "repo-query" | "repo-expand" | "vault-query";
90
- type BenchmarkMode = "native-baseline-proxy" | "pre-hardening-freeflow-proxy" | "improved-freeflow-router";
91
- export declare function runRouterBenchmarks(options?: RunRouterBenchmarksOptions): Promise<RouterBenchmarkReport>;
92
- export declare function renderRouterBenchmarkReport(report: RouterBenchmarkReport): string;
93
- export declare function writeRouterBenchmarkReport(report: RouterBenchmarkReport, reportPath: string): Promise<void>;
94
- export declare function writeRouterBenchmarkJsonReport(report: RouterBenchmarkReport, reportPath: string): Promise<void>;
95
- export interface WriteRouterBenchmarkReportsOptions {
96
- jsonReportPath?: string | false;
97
- }
98
- export declare function writeRouterBenchmarkReports(report: RouterBenchmarkReport, markdownReportPath: string, options?: WriteRouterBenchmarkReportsOptions): Promise<{
99
- markdown: string;
100
- json?: string;
101
- }>;
102
- export {};