@hassangameryt/freeflow 0.5.0 → 0.7.0

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 (301) hide show
  1. package/.claude-plugin/marketplace.json +1 -1
  2. package/.claude-plugin/plugin.json +2 -2
  3. package/.codex-plugin/plugin.json +4 -5
  4. package/README.md +141 -163
  5. package/capabilities/cognitive-routing/SKILL.md +387 -0
  6. package/capabilities/context-virtualization/SKILL.md +103 -0
  7. package/capabilities/conversation-history/SKILL.md +53 -0
  8. package/command-surface.json +6 -37
  9. package/hooks/freeflow-runtime-context.mjs +50 -541
  10. package/hooks/hooks.json +1 -26
  11. package/hooks/tests/check-runtime-context-hook.sh +114 -308
  12. package/package.json +27 -17
  13. package/pi-extension/dist/cognitive-routing/commands.js +96 -0
  14. package/pi-extension/dist/cognitive-routing/config.js +232 -0
  15. package/pi-extension/dist/cognitive-routing/controller.js +1292 -0
  16. package/pi-extension/dist/cognitive-routing/history.js +451 -0
  17. package/pi-extension/dist/cognitive-routing/host.js +188 -0
  18. package/pi-extension/dist/cognitive-routing/pi-routing-session.js +414 -0
  19. package/pi-extension/dist/cognitive-routing/pi-session-control.js +320 -0
  20. package/pi-extension/dist/cognitive-routing/runtime.js +43 -0
  21. package/pi-extension/dist/cognitive-routing/tool.js +212 -0
  22. package/pi-extension/dist/cognitive-routing/types.js +6 -0
  23. package/pi-extension/dist/context-virtualization/commands.js +89 -0
  24. package/pi-extension/dist/context-virtualization/projector.js +42 -0
  25. package/pi-extension/dist/context-virtualization/runtime.js +356 -0
  26. package/pi-extension/dist/context-virtualization/state.js +57 -0
  27. package/pi-extension/dist/context-virtualization/types.js +10 -0
  28. package/pi-extension/dist/conversation-history/passages.js +66 -0
  29. package/pi-extension/dist/conversation-history/ranking.js +105 -0
  30. package/pi-extension/dist/conversation-history/runtime.js +226 -0
  31. package/pi-extension/dist/conversation-history/search.js +56 -0
  32. package/pi-extension/dist/conversation-history/types.js +1 -0
  33. package/pi-extension/dist/freeflow-context/resolver.js +120 -0
  34. package/pi-extension/dist/freeflow-context/runtime.js +80 -0
  35. package/pi-extension/dist/freeflow-context/source-projector.js +95 -0
  36. package/pi-extension/dist/freeflow-context/tool.js +308 -0
  37. package/pi-extension/dist/freeflow-context/types.js +12 -0
  38. package/pi-extension/dist/freeflow-context/visibility.js +28 -0
  39. package/pi-extension/dist/index.js +564 -129
  40. package/pi-extension/dist/runtime/runtime-context.js +357 -470
  41. package/pi-extension/dist/runtime/runtime-identity.js +5 -0
  42. package/pi-extension/dist/settings/settings-tui.js +78 -0
  43. package/pi-extension/dist/settings/settings-ui.js +572 -826
  44. package/pi-extension/dist/ui/text-component.js +57 -0
  45. package/pi-extension/src/cognitive-routing/commands.ts +129 -0
  46. package/pi-extension/src/cognitive-routing/config.ts +303 -0
  47. package/pi-extension/src/cognitive-routing/controller.ts +1628 -0
  48. package/pi-extension/src/cognitive-routing/history.ts +650 -0
  49. package/pi-extension/src/cognitive-routing/host.ts +266 -0
  50. package/pi-extension/src/cognitive-routing/pi-routing-session.ts +538 -0
  51. package/pi-extension/src/cognitive-routing/pi-session-control.ts +444 -0
  52. package/pi-extension/src/cognitive-routing/runtime.ts +57 -0
  53. package/pi-extension/src/cognitive-routing/tool.ts +273 -0
  54. package/pi-extension/src/cognitive-routing/types.ts +89 -0
  55. package/pi-extension/src/context-virtualization/commands.ts +111 -0
  56. package/pi-extension/src/context-virtualization/projector.ts +62 -0
  57. package/pi-extension/src/context-virtualization/runtime.ts +406 -0
  58. package/pi-extension/src/context-virtualization/state.ts +79 -0
  59. package/pi-extension/src/context-virtualization/types.ts +92 -0
  60. package/pi-extension/src/conversation-history/passages.ts +81 -0
  61. package/pi-extension/src/conversation-history/ranking.ts +155 -0
  62. package/pi-extension/src/conversation-history/runtime.ts +250 -0
  63. package/pi-extension/src/conversation-history/search.ts +79 -0
  64. package/pi-extension/src/conversation-history/types.ts +31 -0
  65. package/pi-extension/src/freeflow-context/resolver.ts +139 -0
  66. package/pi-extension/src/freeflow-context/runtime.ts +100 -0
  67. package/pi-extension/src/freeflow-context/source-projector.ts +106 -0
  68. package/pi-extension/src/freeflow-context/tool.ts +360 -0
  69. package/pi-extension/src/freeflow-context/types.ts +70 -0
  70. package/pi-extension/src/freeflow-context/visibility.ts +53 -0
  71. package/pi-extension/src/index.ts +597 -135
  72. package/pi-extension/src/runtime/runtime-context.ts +373 -491
  73. package/pi-extension/src/runtime/runtime-identity.ts +8 -0
  74. package/pi-extension/src/settings/settings-tui.ts +93 -0
  75. package/pi-extension/src/settings/settings-ui.ts +679 -910
  76. package/pi-extension/src/ui/text-component.ts +66 -0
  77. package/pi-extension/tests/cognitive-routing/commands.test.js +134 -0
  78. package/pi-extension/tests/cognitive-routing/controller.test.js +1128 -0
  79. package/pi-extension/tests/cognitive-routing/extension-lifecycle.test.js +1142 -0
  80. package/pi-extension/tests/cognitive-routing/history.test.js +274 -0
  81. package/pi-extension/tests/cognitive-routing/host-fixture.js +4 -0
  82. package/pi-extension/tests/cognitive-routing/host-identity.test.js +63 -0
  83. package/pi-extension/tests/cognitive-routing/pi-normal-lifecycle.test.js +434 -0
  84. package/pi-extension/tests/cognitive-routing/pi-session-control.test.js +174 -0
  85. package/pi-extension/tests/cognitive-routing/pi-session-history.test.js +91 -0
  86. package/pi-extension/tests/cognitive-routing/profile-resolution.test.js +279 -0
  87. package/pi-extension/tests/cognitive-routing/tool.test.js +230 -0
  88. package/pi-extension/tests/context-virtualization/extension.test.js +749 -0
  89. package/pi-extension/tests/context-virtualization/projector.test.js +110 -0
  90. package/pi-extension/tests/context-virtualization/runtime.test.js +216 -0
  91. package/pi-extension/tests/conversation-history/runtime.test.js +98 -0
  92. package/pi-extension/tests/conversation-history/search.test.js +97 -0
  93. package/pi-extension/tests/integration/mode-free-core.test.js +218 -0
  94. package/pi-extension/tests/integration/pi-extension.test.js +532 -3701
  95. package/pi-extension/tests/integration/prompt-architecture.test.js +350 -0
  96. package/pi-extension/tests/integration/unaffected-regressions.test.js +411 -0
  97. package/runtime/prompts/cognitive-routing.md +10 -0
  98. package/runtime/prompts/context-virtualization.md +3 -0
  99. package/runtime/prompts/conversation-history.md +3 -0
  100. package/runtime/prompts/core.md +84 -0
  101. package/runtime/prompts/interaction-contract.md +11 -0
  102. package/skills/action-selection/SKILL.md +140 -0
  103. package/skills/action-selection/references/trajectory-stalls.md +71 -0
  104. package/skills/bypass/SKILL.md +109 -38
  105. package/skills/commit-work/SKILL.md +94 -55
  106. package/skills/commit-work/references/git-state-edges.md +94 -0
  107. package/skills/commit-work/references/simple-push.md +92 -0
  108. package/skills/commit-work/references/staging-decisions.md +79 -46
  109. package/skills/decision-gate/SKILL.md +80 -22
  110. package/skills/design-for-depth/SKILL.md +206 -60
  111. package/skills/design-for-depth/references/design-pressure-signals.md +108 -240
  112. package/skills/design-for-depth/references/interface-design-loop.md +77 -97
  113. package/skills/design-for-depth/references/module-and-dependency-design.md +147 -0
  114. package/skills/design-for-depth/references/software-design-philosophy.md +128 -174
  115. package/skills/design-for-depth/references/state-and-failure-boundaries.md +136 -0
  116. package/skills/diagnose-failure/SKILL.md +200 -48
  117. package/skills/diagnose-failure/references/diagnostic-loop-catalog.md +18 -6
  118. package/skills/diagnose-failure/references/{flaky-and-performance.md → flaky-and-performance-diagnosis.md} +13 -5
  119. package/skills/discuss/SKILL.md +119 -65
  120. package/skills/discuss/references/discussion-continuity.md +123 -0
  121. package/skills/evaluate-skill/SKILL.md +166 -52
  122. package/skills/evaluate-skill/references/{definition-schema.md → evaluation-definition-schema.md} +43 -3
  123. package/skills/evaluate-skill/references/evaluation-design.md +56 -30
  124. package/skills/evaluate-skill/references/execution-and-evidence.md +8 -3
  125. package/skills/evaluate-skill/references/review-and-revision.md +62 -21
  126. package/skills/evaluate-skill/scripts/lib/definitions.mjs +114 -3
  127. package/skills/evaluate-skill/scripts/lib/grade-interaction.mjs +156 -1
  128. package/skills/evaluate-skill/scripts/lib/grade.mjs +9 -1
  129. package/skills/evaluate-skill/scripts/lib/pi.mjs +147 -32
  130. package/skills/evaluate-skill/scripts/lib/rpc.mjs +4 -4
  131. package/skills/evaluate-skill/scripts/lib/runner.mjs +36 -14
  132. package/skills/evaluate-skill/scripts/lib/sandbox.mjs +92 -0
  133. package/skills/evaluate-skill/scripts/pi-guard.mjs +1 -1
  134. package/skills/evaluate-skill/scripts/pi-observer.mjs +66 -0
  135. package/skills/evaluate-skill/scripts/skill-eval.mjs +6 -5
  136. package/skills/execute-work/SKILL.md +99 -57
  137. package/skills/execute-work/references/code-practices.md +4 -4
  138. package/skills/execute-work/references/execute-work-edges.md +62 -0
  139. package/skills/finish-branch/SKILL.md +2 -2
  140. package/skills/finish-branch/references/integration-options.md +1 -1
  141. package/skills/handoff/SKILL.md +3 -3
  142. package/skills/launch-work/SKILL.md +1 -1
  143. package/skills/launch-work/references/launch-readiness.md +2 -2
  144. package/skills/migration-work/SKILL.md +2 -2
  145. package/skills/migration-work/references/migration-lifecycle.md +1 -1
  146. package/skills/release-work/SKILL.md +1 -1
  147. package/skills/release-work/references/release-evidence.md +1 -1
  148. package/skills/review-artifact/SKILL.md +129 -66
  149. package/skills/review-artifact/references/adjudicate-artifact-review.md +101 -0
  150. package/skills/review-artifact/references/independent-artifact-reviewer-contract.md +159 -0
  151. package/skills/review-work/SKILL.md +113 -68
  152. package/skills/review-work/references/adjudicate-work-review.md +97 -0
  153. package/skills/review-work/references/independent-work-reviewer-contract.md +139 -0
  154. package/skills/review-work/references/security-risk-lens.md +18 -16
  155. package/skills/setup-freeflow/SKILL.md +16 -17
  156. package/skills/setup-freeflow/references/activation-contract.md +24 -30
  157. package/skills/setup-freeflow/references/host-setup.md +6 -7
  158. package/skills/simplify-code/SKILL.md +97 -39
  159. package/skills/simplify-code/references/simplification-patterns.md +1 -1
  160. package/skills/tdd/SKILL.md +100 -53
  161. package/skills/tdd/references/test-design.md +3 -3
  162. package/skills/track-work/SKILL.md +195 -58
  163. package/skills/track-work/references/working-record-format.md +515 -0
  164. package/skills/track-work/scripts/lib/document.mjs +713 -0
  165. package/skills/track-work/scripts/lib/format.mjs +166 -0
  166. package/skills/track-work/scripts/lib/store.mjs +233 -0
  167. package/skills/track-work/scripts/lib/transitions.mjs +790 -0
  168. package/skills/track-work/scripts/lib/views.mjs +40 -0
  169. package/skills/track-work/scripts/working-record.mjs +316 -0
  170. package/skills/verify-work/SKILL.md +57 -19
  171. package/skills/verify-work/references/browser-runtime-evidence.md +2 -2
  172. package/skills/verify-work/references/integration-evidence.md +1 -7
  173. package/skills/verify-work/references/performance-evidence.md +2 -2
  174. package/skills/workflow/SKILL.md +137 -55
  175. package/skills/workflow/references/domain-skill-composition.md +26 -40
  176. package/skills/write-plan/SKILL.md +1 -1
  177. package/skills/write-skill/SKILL.md +218 -61
  178. package/skills/write-skill/references/activation-boundaries.md +63 -21
  179. package/skills/write-skill/references/agent-first-instructions.md +61 -27
  180. package/skills/write-skill/references/progressive-disclosure.md +97 -33
  181. package/skills/write-skill/references/skill-dependency-graphs.md +190 -0
  182. package/capabilities/output-router/SKILL.md +0 -206
  183. package/capabilities/output-router/references/safety-policy.md +0 -40
  184. package/capabilities/output-router/references/setup.md +0 -110
  185. package/pi-extension/dist/output-router/host-producer-identification.js +0 -232
  186. package/pi-extension/dist/output-router/native-safety-net.js +0 -216
  187. package/pi-extension/dist/output-router/observed-tool-routing.js +0 -122
  188. package/pi-extension/dist/output-router/renderers.js +0 -1023
  189. package/pi-extension/dist/output-router/router-tools.js +0 -554
  190. package/pi-extension/dist/output-router/schemas.js +0 -383
  191. package/pi-extension/dist/output-router/status.js +0 -744
  192. package/pi-extension/dist/output-router/utils.js +0 -502
  193. package/pi-extension/src/output-router/host-producer-identification.ts +0 -256
  194. package/pi-extension/src/output-router/native-safety-net.ts +0 -248
  195. package/pi-extension/src/output-router/observed-tool-routing.ts +0 -134
  196. package/pi-extension/src/output-router/renderers.ts +0 -1108
  197. package/pi-extension/src/output-router/router-tools.ts +0 -579
  198. package/pi-extension/src/output-router/schemas.ts +0 -387
  199. package/pi-extension/src/output-router/status.ts +0 -791
  200. package/pi-extension/src/output-router/utils.ts +0 -554
  201. package/pi-extension/tests/output-router/observed-producers.test.js +0 -132
  202. package/pi-extension/tests/output-router/search.test.js +0 -722
  203. package/router/dist/benchmarks/benchmark-harness.d.ts +0 -35
  204. package/router/dist/benchmarks/benchmark-harness.js +0 -92
  205. package/router/dist/benchmarks/benchmarks.d.ts +0 -109
  206. package/router/dist/benchmarks/benchmarks.js +0 -979
  207. package/router/dist/benchmarks/codex-qa-benchmarks.d.ts +0 -95
  208. package/router/dist/benchmarks/codex-qa-benchmarks.js +0 -500
  209. package/router/dist/benchmarks/command-benchmarks.d.ts +0 -143
  210. package/router/dist/benchmarks/command-benchmarks.js +0 -698
  211. package/router/dist/benchmarks/context-mode-normalized-benchmarks.d.ts +0 -82
  212. package/router/dist/benchmarks/context-mode-normalized-benchmarks.js +0 -773
  213. package/router/dist/benchmarks/context-mode-real-deep-benchmark.d.ts +0 -132
  214. package/router/dist/benchmarks/context-mode-real-deep-benchmark.js +0 -1380
  215. package/router/dist/benchmarks/context-saving-baseline.d.ts +0 -60
  216. package/router/dist/benchmarks/context-saving-baseline.js +0 -470
  217. package/router/dist/benchmarks/index-benchmarks.d.ts +0 -103
  218. package/router/dist/benchmarks/index-benchmarks.js +0 -862
  219. package/router/dist/benchmarks/storage-policy-benchmarks.d.ts +0 -101
  220. package/router/dist/benchmarks/storage-policy-benchmarks.js +0 -618
  221. package/router/dist/benchmarks/vault-index-benchmarks.d.ts +0 -56
  222. package/router/dist/benchmarks/vault-index-benchmarks.js +0 -322
  223. package/router/dist/config/config.d.ts +0 -103
  224. package/router/dist/config/config.js +0 -632
  225. package/router/dist/config/router-contract.d.ts +0 -10
  226. package/router/dist/config/router-contract.js +0 -54
  227. package/router/dist/config/schema.d.ts +0 -27
  228. package/router/dist/config/schema.js +0 -648
  229. package/router/dist/config/types.d.ts +0 -573
  230. package/router/dist/config/types.js +0 -41
  231. package/router/dist/evidence/bounded-evidence.d.ts +0 -40
  232. package/router/dist/evidence/bounded-evidence.js +0 -323
  233. package/router/dist/evidence/evidence-range-selector.d.ts +0 -24
  234. package/router/dist/evidence/evidence-range-selector.js +0 -232
  235. package/router/dist/evidence/evidence-search.d.ts +0 -27
  236. package/router/dist/evidence/evidence-search.js +0 -490
  237. package/router/dist/evidence/evidence.d.ts +0 -38
  238. package/router/dist/evidence/evidence.js +0 -200
  239. package/router/dist/evidence/failure-contracts.d.ts +0 -37
  240. package/router/dist/evidence/failure-contracts.js +0 -166
  241. package/router/dist/evidence/line-ranges.d.ts +0 -24
  242. package/router/dist/evidence/line-ranges.js +0 -22
  243. package/router/dist/experiments/local-index.d.ts +0 -64
  244. package/router/dist/experiments/local-index.js +0 -581
  245. package/router/dist/index.d.ts +0 -30
  246. package/router/dist/index.js +0 -32
  247. package/router/dist/local/local-traversal.d.ts +0 -18
  248. package/router/dist/local/local-traversal.js +0 -334
  249. package/router/dist/processing/engine.d.ts +0 -132
  250. package/router/dist/processing/engine.js +0 -533
  251. package/router/dist/processing/reducers.d.ts +0 -280
  252. package/router/dist/processing/reducers.js +0 -1673
  253. package/router/dist/processing/renderers.d.ts +0 -31
  254. package/router/dist/processing/renderers.js +0 -195
  255. package/router/dist/processing/scripts.d.ts +0 -91
  256. package/router/dist/processing/scripts.js +0 -386
  257. package/router/dist/repo/repo-traversal.d.ts +0 -18
  258. package/router/dist/repo/repo-traversal.js +0 -245
  259. package/router/dist/routing/observed-reducers.d.ts +0 -41
  260. package/router/dist/routing/observed-reducers.js +0 -661
  261. package/router/dist/routing/observed-routing.d.ts +0 -26
  262. package/router/dist/routing/observed-routing.js +0 -378
  263. package/router/dist/routing/parsers.d.ts +0 -16
  264. package/router/dist/routing/parsers.js +0 -521
  265. package/router/dist/routing/run-filters.d.ts +0 -60
  266. package/router/dist/routing/run-filters.js +0 -238
  267. package/router/dist/routing/run-reducers.d.ts +0 -49
  268. package/router/dist/routing/run-reducers.js +0 -122
  269. package/router/dist/sandbox/adapter-roots.d.ts +0 -46
  270. package/router/dist/sandbox/adapter-roots.js +0 -66
  271. package/router/dist/sandbox/eryx-python-adapter.d.ts +0 -13
  272. package/router/dist/sandbox/eryx-python-adapter.js +0 -868
  273. package/router/dist/sandbox/jq-wasm-adapter.d.ts +0 -9
  274. package/router/dist/sandbox/jq-wasm-adapter.js +0 -429
  275. package/router/dist/sandbox/quickjs-wasi-adapter.d.ts +0 -13
  276. package/router/dist/sandbox/quickjs-wasi-adapter.js +0 -384
  277. package/router/dist/sandbox/script-sandbox.d.ts +0 -134
  278. package/router/dist/sandbox/script-sandbox.js +0 -337
  279. package/router/dist/setup/script-transform-adapters.d.ts +0 -32
  280. package/router/dist/setup/script-transform-adapters.js +0 -278
  281. package/router/dist/tools/batch.d.ts +0 -33
  282. package/router/dist/tools/batch.js +0 -586
  283. package/router/dist/tools/run.d.ts +0 -62
  284. package/router/dist/tools/run.js +0 -1304
  285. package/router/dist/tools/search.d.ts +0 -66
  286. package/router/dist/tools/search.js +0 -1364
  287. package/router/dist/transform/engine.d.ts +0 -168
  288. package/router/dist/transform/engine.js +0 -2072
  289. package/router/dist/vault/vault-index.d.ts +0 -125
  290. package/router/dist/vault/vault-index.js +0 -416
  291. package/router/dist/vault/vault.d.ts +0 -138
  292. package/router/dist/vault/vault.js +0 -630
  293. package/runtime/interaction-contract.md +0 -16
  294. package/skills/discuss/references/checkpoints.md +0 -66
  295. package/skills/execute-work/references/execution-loop.md +0 -77
  296. package/skills/mode-contract/SKILL.md +0 -104
  297. package/skills/review-artifact/references/reviewer-prompt.md +0 -148
  298. package/skills/review-work/references/reviewer-prompt.md +0 -134
  299. package/skills/track-work/references/working-record-schema.md +0 -378
  300. package/skills/workflow/references/workflow-loop.md +0 -92
  301. /package/skills/handoff/references/{templates.md → handoff-templates.md} +0 -0
@@ -1,35 +0,0 @@
1
- export interface LatencySummary {
2
- p50: number;
3
- p95: number;
4
- }
5
- export interface BenchmarkCliDefaults {
6
- reportPath: string;
7
- }
8
- export interface ParsedBenchmarkCliArgs {
9
- iterations?: number;
10
- reportPath: string;
11
- jsonReportPath?: string | false;
12
- }
13
- export declare function normalizeIterations(value: unknown, defaultIterations?: number): number;
14
- export declare function approximateTokens(bytes: number): number;
15
- export declare function percentile(values: readonly number[], quantile: number): number;
16
- export declare function latencySummary(values: readonly number[]): LatencySummary;
17
- export declare function averagePercent(values: readonly number[]): number;
18
- export declare function medianPercent(values: readonly number[]): number;
19
- export declare function reductionPercent(raw: number, routed: number): number;
20
- export declare function formatPercent(value: number): string;
21
- export declare function escapeMarkdownTableCell(value: string): string;
22
- export declare function defaultJsonRunReportPath(markdownReportPath: string): string;
23
- export declare function parseBenchmarkCliArgs(
24
- argv: readonly string[],
25
- defaults: BenchmarkCliDefaults,
26
- ): ParsedBenchmarkCliArgs;
27
- export declare function writeBenchmarkReportPair<TReport>(options: {
28
- report: TReport;
29
- markdownReportPath: string;
30
- jsonReportPath?: string | false | undefined;
31
- renderMarkdown(report: TReport): string;
32
- }): Promise<{
33
- markdown: string;
34
- json?: string;
35
- }>;
@@ -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 `${value.toFixed(2)}%`;
46
- }
47
- export function escapeMarkdownTableCell(value) {
48
- return value.replace(/\|/g, "\\|").replace(/\n/g, " ");
49
- }
50
- export function defaultJsonRunReportPath(markdownReportPath) {
51
- const markdownName = basename(markdownReportPath);
52
- const jsonName = markdownName.endsWith(".md")
53
- ? `${markdownName.slice(0, -".md".length)}.json`
54
- : `${markdownName}.json`;
55
- return resolve(process.cwd(), "router/evals/runs", jsonName);
56
- }
57
- export function parseBenchmarkCliArgs(argv, defaults) {
58
- let iterations;
59
- let reportPath = defaults.reportPath;
60
- let jsonReportPath;
61
- for (const arg of argv) {
62
- if (arg.startsWith("--iterations=")) {
63
- const value = Number(arg.slice("--iterations=".length));
64
- if (Number.isFinite(value) && value > 0) {
65
- iterations = value;
66
- }
67
- } else if (arg.startsWith("--report=")) {
68
- reportPath = resolve(process.cwd(), arg.slice("--report=".length));
69
- } else if (arg.startsWith("--json-report=")) {
70
- const value = arg.slice("--json-report=".length);
71
- jsonReportPath = value === "off" ? false : resolve(process.cwd(), value);
72
- }
73
- }
74
- const parsed = iterations === undefined ? { reportPath } : { iterations, reportPath };
75
- return jsonReportPath === undefined ? parsed : { ...parsed, jsonReportPath };
76
- }
77
- export async function writeBenchmarkReportPair(options) {
78
- await mkdir(dirname(options.markdownReportPath), { recursive: true });
79
- await writeFile(options.markdownReportPath, options.renderMarkdown(options.report), "utf8");
80
- if (options.jsonReportPath === false) {
81
- return { markdown: options.markdownReportPath };
82
- }
83
- if (options.jsonReportPath) {
84
- await mkdir(dirname(options.jsonReportPath), { recursive: true });
85
- await writeFile(options.jsonReportPath, `${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
- }
@@ -1,109 +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(
95
- report: RouterBenchmarkReport,
96
- reportPath: string,
97
- ): Promise<void>;
98
- export interface WriteRouterBenchmarkReportsOptions {
99
- jsonReportPath?: string | false;
100
- }
101
- export declare function writeRouterBenchmarkReports(
102
- report: RouterBenchmarkReport,
103
- markdownReportPath: string,
104
- options?: WriteRouterBenchmarkReportsOptions,
105
- ): Promise<{
106
- markdown: string;
107
- json?: string;
108
- }>;
109
- export {};