@hassangameryt/freeflow 0.5.0 → 0.6.0

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 (284) hide show
  1. package/.claude-plugin/marketplace.json +1 -1
  2. package/.claude-plugin/plugin.json +1 -1
  3. package/.codex-plugin/plugin.json +1 -1
  4. package/README.md +148 -154
  5. package/capabilities/cognitive-routing/SKILL.md +229 -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 -13
  9. package/hooks/freeflow-runtime-context.mjs +35 -91
  10. package/hooks/tests/check-runtime-context-hook.sh +56 -39
  11. package/package.json +24 -16
  12. package/pi-extension/dist/cognitive-routing/commands.js +96 -0
  13. package/pi-extension/dist/cognitive-routing/config.js +236 -0
  14. package/pi-extension/dist/cognitive-routing/controller.js +862 -0
  15. package/pi-extension/dist/cognitive-routing/history.js +439 -0
  16. package/pi-extension/dist/cognitive-routing/host.js +126 -0
  17. package/pi-extension/dist/cognitive-routing/runtime.js +43 -0
  18. package/pi-extension/dist/cognitive-routing/tool.js +211 -0
  19. package/pi-extension/dist/cognitive-routing/types.js +6 -0
  20. package/pi-extension/dist/context-virtualization/commands.js +89 -0
  21. package/pi-extension/dist/context-virtualization/projector.js +42 -0
  22. package/pi-extension/dist/context-virtualization/runtime.js +356 -0
  23. package/pi-extension/dist/context-virtualization/state.js +57 -0
  24. package/pi-extension/dist/context-virtualization/types.js +10 -0
  25. package/pi-extension/dist/conversation-history/passages.js +66 -0
  26. package/pi-extension/dist/conversation-history/ranking.js +105 -0
  27. package/pi-extension/dist/conversation-history/runtime.js +226 -0
  28. package/pi-extension/dist/conversation-history/search.js +56 -0
  29. package/pi-extension/dist/conversation-history/types.js +1 -0
  30. package/pi-extension/dist/freeflow-context/resolver.js +120 -0
  31. package/pi-extension/dist/freeflow-context/runtime.js +80 -0
  32. package/pi-extension/dist/freeflow-context/source-projector.js +95 -0
  33. package/pi-extension/dist/freeflow-context/tool.js +308 -0
  34. package/pi-extension/dist/freeflow-context/types.js +12 -0
  35. package/pi-extension/dist/freeflow-context/visibility.js +28 -0
  36. package/pi-extension/dist/index.js +516 -98
  37. package/pi-extension/dist/runtime/runtime-context.js +318 -271
  38. package/pi-extension/dist/runtime/runtime-identity.js +5 -0
  39. package/pi-extension/dist/settings/settings-tui.js +78 -0
  40. package/pi-extension/dist/settings/settings-ui.js +593 -563
  41. package/pi-extension/dist/ui/text-component.js +57 -0
  42. package/pi-extension/src/cognitive-routing/commands.ts +119 -0
  43. package/pi-extension/src/cognitive-routing/config.ts +307 -0
  44. package/pi-extension/src/cognitive-routing/controller.ts +1118 -0
  45. package/pi-extension/src/cognitive-routing/history.ts +638 -0
  46. package/pi-extension/src/cognitive-routing/host.ts +172 -0
  47. package/pi-extension/src/cognitive-routing/runtime.ts +57 -0
  48. package/pi-extension/src/cognitive-routing/tool.ts +272 -0
  49. package/pi-extension/src/cognitive-routing/types.ts +89 -0
  50. package/pi-extension/src/context-virtualization/commands.ts +111 -0
  51. package/pi-extension/src/context-virtualization/projector.ts +62 -0
  52. package/pi-extension/src/context-virtualization/runtime.ts +406 -0
  53. package/pi-extension/src/context-virtualization/state.ts +79 -0
  54. package/pi-extension/src/context-virtualization/types.ts +92 -0
  55. package/pi-extension/src/conversation-history/passages.ts +81 -0
  56. package/pi-extension/src/conversation-history/ranking.ts +155 -0
  57. package/pi-extension/src/conversation-history/runtime.ts +250 -0
  58. package/pi-extension/src/conversation-history/search.ts +79 -0
  59. package/pi-extension/src/conversation-history/types.ts +31 -0
  60. package/pi-extension/src/freeflow-context/resolver.ts +139 -0
  61. package/pi-extension/src/freeflow-context/runtime.ts +100 -0
  62. package/pi-extension/src/freeflow-context/source-projector.ts +106 -0
  63. package/pi-extension/src/freeflow-context/tool.ts +360 -0
  64. package/pi-extension/src/freeflow-context/types.ts +70 -0
  65. package/pi-extension/src/freeflow-context/visibility.ts +53 -0
  66. package/pi-extension/src/index.ts +553 -101
  67. package/pi-extension/src/runtime/runtime-context.ts +339 -281
  68. package/pi-extension/src/runtime/runtime-identity.ts +8 -0
  69. package/pi-extension/src/settings/settings-tui.ts +93 -0
  70. package/pi-extension/src/settings/settings-ui.ts +700 -613
  71. package/pi-extension/src/ui/text-component.ts +66 -0
  72. package/pi-extension/tests/cognitive-routing/commands.test.js +134 -0
  73. package/pi-extension/tests/cognitive-routing/controller.test.js +1099 -0
  74. package/pi-extension/tests/cognitive-routing/extension-lifecycle.test.js +1071 -0
  75. package/pi-extension/tests/cognitive-routing/history.test.js +274 -0
  76. package/pi-extension/tests/cognitive-routing/host-fixture.js +4 -0
  77. package/pi-extension/tests/cognitive-routing/host-identity.test.js +63 -0
  78. package/pi-extension/tests/cognitive-routing/profile-resolution.test.js +236 -0
  79. package/pi-extension/tests/cognitive-routing/tool.test.js +230 -0
  80. package/pi-extension/tests/context-virtualization/extension.test.js +749 -0
  81. package/pi-extension/tests/context-virtualization/projector.test.js +110 -0
  82. package/pi-extension/tests/context-virtualization/runtime.test.js +216 -0
  83. package/pi-extension/tests/conversation-history/runtime.test.js +98 -0
  84. package/pi-extension/tests/conversation-history/search.test.js +97 -0
  85. package/pi-extension/tests/integration/pi-extension.test.js +927 -2048
  86. package/pi-extension/tests/integration/prompt-architecture.test.js +305 -0
  87. package/runtime/prompts/cognitive-routing.md +9 -0
  88. package/runtime/prompts/context-virtualization.md +3 -0
  89. package/runtime/prompts/conversation-history.md +3 -0
  90. package/runtime/prompts/core.md +13 -0
  91. package/runtime/prompts/interaction-contract.md +7 -0
  92. package/runtime/prompts/skills.md +65 -0
  93. package/skills/action-selection/SKILL.md +91 -0
  94. package/skills/bypass/SKILL.md +3 -2
  95. package/skills/commit-work/SKILL.md +1 -1
  96. package/skills/commit-work/references/staging-decisions.md +1 -1
  97. package/skills/decision-gate/SKILL.md +1 -1
  98. package/skills/design-for-depth/SKILL.md +14 -33
  99. package/skills/design-for-depth/references/design-pressure-signals.md +1 -1
  100. package/skills/design-for-depth/references/interface-design-loop.md +1 -1
  101. package/skills/design-for-depth/references/software-design-philosophy.md +1 -1
  102. package/skills/diagnose-failure/SKILL.md +20 -14
  103. package/skills/diagnose-failure/references/diagnostic-loop-catalog.md +1 -3
  104. package/skills/diagnose-failure/references/{flaky-and-performance.md → flaky-and-performance-diagnosis.md} +1 -1
  105. package/skills/discuss/SKILL.md +34 -22
  106. package/skills/discuss/references/discussion-continuity.md +71 -0
  107. package/skills/evaluate-skill/SKILL.md +5 -5
  108. package/skills/evaluate-skill/references/{definition-schema.md → evaluation-definition-schema.md} +42 -2
  109. package/skills/evaluate-skill/references/execution-and-evidence.md +8 -3
  110. package/skills/evaluate-skill/scripts/lib/definitions.mjs +114 -3
  111. package/skills/evaluate-skill/scripts/lib/grade-interaction.mjs +156 -1
  112. package/skills/evaluate-skill/scripts/lib/grade.mjs +9 -1
  113. package/skills/evaluate-skill/scripts/lib/pi.mjs +147 -32
  114. package/skills/evaluate-skill/scripts/lib/rpc.mjs +4 -4
  115. package/skills/evaluate-skill/scripts/lib/runner.mjs +36 -14
  116. package/skills/evaluate-skill/scripts/lib/sandbox.mjs +92 -0
  117. package/skills/evaluate-skill/scripts/pi-guard.mjs +1 -1
  118. package/skills/evaluate-skill/scripts/pi-observer.mjs +66 -0
  119. package/skills/evaluate-skill/scripts/skill-eval.mjs +6 -5
  120. package/skills/execute-work/SKILL.md +18 -15
  121. package/skills/execute-work/references/code-practices.md +1 -1
  122. package/skills/execute-work/references/execute-work-edges.md +42 -0
  123. package/skills/finish-branch/SKILL.md +2 -2
  124. package/skills/finish-branch/references/integration-options.md +1 -1
  125. package/skills/handoff/SKILL.md +3 -3
  126. package/skills/launch-work/SKILL.md +1 -1
  127. package/skills/launch-work/references/launch-readiness.md +2 -2
  128. package/skills/migration-work/SKILL.md +2 -2
  129. package/skills/migration-work/references/migration-lifecycle.md +1 -1
  130. package/skills/mode-contract/SKILL.md +4 -4
  131. package/skills/release-work/SKILL.md +1 -1
  132. package/skills/release-work/references/release-evidence.md +1 -1
  133. package/skills/review-artifact/SKILL.md +28 -26
  134. package/skills/review-work/SKILL.md +28 -26
  135. package/skills/review-work/references/{reviewer-prompt.md → independent-work-reviewer-contract.md} +1 -1
  136. package/skills/review-work/references/security-risk-lens.md +1 -1
  137. package/skills/setup-freeflow/SKILL.md +3 -1
  138. package/skills/setup-freeflow/references/activation-contract.md +2 -2
  139. package/skills/setup-freeflow/references/host-setup.md +2 -2
  140. package/skills/simplify-code/SKILL.md +1 -1
  141. package/skills/simplify-code/references/simplification-patterns.md +1 -1
  142. package/skills/tdd/SKILL.md +18 -38
  143. package/skills/tdd/references/test-design.md +2 -2
  144. package/skills/track-work/SKILL.md +362 -58
  145. package/skills/track-work/scripts/lib/codec.mjs +570 -0
  146. package/skills/track-work/scripts/lib/commands.mjs +568 -0
  147. package/skills/track-work/scripts/lib/contract.mjs +303 -0
  148. package/skills/track-work/scripts/lib/model.mjs +506 -0
  149. package/skills/track-work/scripts/lib/operations.mjs +965 -0
  150. package/skills/track-work/scripts/lib/record-store.mjs +264 -0
  151. package/skills/track-work/scripts/lib/result.mjs +37 -0
  152. package/skills/track-work/scripts/lib/rewrites.mjs +740 -0
  153. package/skills/track-work/scripts/lib/schema.mjs +277 -0
  154. package/skills/track-work/scripts/lib/source-inventory.mjs +162 -0
  155. package/skills/track-work/scripts/lib/views.mjs +443 -0
  156. package/skills/track-work/scripts/lib/workspace.mjs +134 -0
  157. package/skills/track-work/scripts/working-record.mjs +122 -0
  158. package/skills/verify-work/SKILL.md +14 -2
  159. package/skills/verify-work/references/browser-runtime-evidence.md +1 -1
  160. package/skills/verify-work/references/integration-evidence.md +1 -1
  161. package/skills/verify-work/references/performance-evidence.md +1 -1
  162. package/skills/workflow/SKILL.md +105 -53
  163. package/skills/workflow/references/domain-skill-composition.md +22 -42
  164. package/skills/write-plan/SKILL.md +1 -1
  165. package/skills/write-skill/SKILL.md +3 -2
  166. package/skills/write-skill/references/progressive-disclosure.md +17 -3
  167. package/capabilities/output-router/SKILL.md +0 -206
  168. package/capabilities/output-router/references/safety-policy.md +0 -40
  169. package/capabilities/output-router/references/setup.md +0 -110
  170. package/pi-extension/dist/output-router/host-producer-identification.js +0 -232
  171. package/pi-extension/dist/output-router/native-safety-net.js +0 -216
  172. package/pi-extension/dist/output-router/observed-tool-routing.js +0 -122
  173. package/pi-extension/dist/output-router/renderers.js +0 -1023
  174. package/pi-extension/dist/output-router/router-tools.js +0 -554
  175. package/pi-extension/dist/output-router/schemas.js +0 -383
  176. package/pi-extension/dist/output-router/status.js +0 -744
  177. package/pi-extension/dist/output-router/utils.js +0 -502
  178. package/pi-extension/src/output-router/host-producer-identification.ts +0 -256
  179. package/pi-extension/src/output-router/native-safety-net.ts +0 -248
  180. package/pi-extension/src/output-router/observed-tool-routing.ts +0 -134
  181. package/pi-extension/src/output-router/renderers.ts +0 -1108
  182. package/pi-extension/src/output-router/router-tools.ts +0 -579
  183. package/pi-extension/src/output-router/schemas.ts +0 -387
  184. package/pi-extension/src/output-router/status.ts +0 -791
  185. package/pi-extension/src/output-router/utils.ts +0 -554
  186. package/pi-extension/tests/output-router/observed-producers.test.js +0 -132
  187. package/pi-extension/tests/output-router/search.test.js +0 -722
  188. package/router/dist/benchmarks/benchmark-harness.d.ts +0 -35
  189. package/router/dist/benchmarks/benchmark-harness.js +0 -92
  190. package/router/dist/benchmarks/benchmarks.d.ts +0 -109
  191. package/router/dist/benchmarks/benchmarks.js +0 -979
  192. package/router/dist/benchmarks/codex-qa-benchmarks.d.ts +0 -95
  193. package/router/dist/benchmarks/codex-qa-benchmarks.js +0 -500
  194. package/router/dist/benchmarks/command-benchmarks.d.ts +0 -143
  195. package/router/dist/benchmarks/command-benchmarks.js +0 -698
  196. package/router/dist/benchmarks/context-mode-normalized-benchmarks.d.ts +0 -82
  197. package/router/dist/benchmarks/context-mode-normalized-benchmarks.js +0 -773
  198. package/router/dist/benchmarks/context-mode-real-deep-benchmark.d.ts +0 -132
  199. package/router/dist/benchmarks/context-mode-real-deep-benchmark.js +0 -1380
  200. package/router/dist/benchmarks/context-saving-baseline.d.ts +0 -60
  201. package/router/dist/benchmarks/context-saving-baseline.js +0 -470
  202. package/router/dist/benchmarks/index-benchmarks.d.ts +0 -103
  203. package/router/dist/benchmarks/index-benchmarks.js +0 -862
  204. package/router/dist/benchmarks/storage-policy-benchmarks.d.ts +0 -101
  205. package/router/dist/benchmarks/storage-policy-benchmarks.js +0 -618
  206. package/router/dist/benchmarks/vault-index-benchmarks.d.ts +0 -56
  207. package/router/dist/benchmarks/vault-index-benchmarks.js +0 -322
  208. package/router/dist/config/config.d.ts +0 -103
  209. package/router/dist/config/config.js +0 -632
  210. package/router/dist/config/router-contract.d.ts +0 -10
  211. package/router/dist/config/router-contract.js +0 -54
  212. package/router/dist/config/schema.d.ts +0 -27
  213. package/router/dist/config/schema.js +0 -648
  214. package/router/dist/config/types.d.ts +0 -573
  215. package/router/dist/config/types.js +0 -41
  216. package/router/dist/evidence/bounded-evidence.d.ts +0 -40
  217. package/router/dist/evidence/bounded-evidence.js +0 -323
  218. package/router/dist/evidence/evidence-range-selector.d.ts +0 -24
  219. package/router/dist/evidence/evidence-range-selector.js +0 -232
  220. package/router/dist/evidence/evidence-search.d.ts +0 -27
  221. package/router/dist/evidence/evidence-search.js +0 -490
  222. package/router/dist/evidence/evidence.d.ts +0 -38
  223. package/router/dist/evidence/evidence.js +0 -200
  224. package/router/dist/evidence/failure-contracts.d.ts +0 -37
  225. package/router/dist/evidence/failure-contracts.js +0 -166
  226. package/router/dist/evidence/line-ranges.d.ts +0 -24
  227. package/router/dist/evidence/line-ranges.js +0 -22
  228. package/router/dist/experiments/local-index.d.ts +0 -64
  229. package/router/dist/experiments/local-index.js +0 -581
  230. package/router/dist/index.d.ts +0 -30
  231. package/router/dist/index.js +0 -32
  232. package/router/dist/local/local-traversal.d.ts +0 -18
  233. package/router/dist/local/local-traversal.js +0 -334
  234. package/router/dist/processing/engine.d.ts +0 -132
  235. package/router/dist/processing/engine.js +0 -533
  236. package/router/dist/processing/reducers.d.ts +0 -280
  237. package/router/dist/processing/reducers.js +0 -1673
  238. package/router/dist/processing/renderers.d.ts +0 -31
  239. package/router/dist/processing/renderers.js +0 -195
  240. package/router/dist/processing/scripts.d.ts +0 -91
  241. package/router/dist/processing/scripts.js +0 -386
  242. package/router/dist/repo/repo-traversal.d.ts +0 -18
  243. package/router/dist/repo/repo-traversal.js +0 -245
  244. package/router/dist/routing/observed-reducers.d.ts +0 -41
  245. package/router/dist/routing/observed-reducers.js +0 -661
  246. package/router/dist/routing/observed-routing.d.ts +0 -26
  247. package/router/dist/routing/observed-routing.js +0 -378
  248. package/router/dist/routing/parsers.d.ts +0 -16
  249. package/router/dist/routing/parsers.js +0 -521
  250. package/router/dist/routing/run-filters.d.ts +0 -60
  251. package/router/dist/routing/run-filters.js +0 -238
  252. package/router/dist/routing/run-reducers.d.ts +0 -49
  253. package/router/dist/routing/run-reducers.js +0 -122
  254. package/router/dist/sandbox/adapter-roots.d.ts +0 -46
  255. package/router/dist/sandbox/adapter-roots.js +0 -66
  256. package/router/dist/sandbox/eryx-python-adapter.d.ts +0 -13
  257. package/router/dist/sandbox/eryx-python-adapter.js +0 -868
  258. package/router/dist/sandbox/jq-wasm-adapter.d.ts +0 -9
  259. package/router/dist/sandbox/jq-wasm-adapter.js +0 -429
  260. package/router/dist/sandbox/quickjs-wasi-adapter.d.ts +0 -13
  261. package/router/dist/sandbox/quickjs-wasi-adapter.js +0 -384
  262. package/router/dist/sandbox/script-sandbox.d.ts +0 -134
  263. package/router/dist/sandbox/script-sandbox.js +0 -337
  264. package/router/dist/setup/script-transform-adapters.d.ts +0 -32
  265. package/router/dist/setup/script-transform-adapters.js +0 -278
  266. package/router/dist/tools/batch.d.ts +0 -33
  267. package/router/dist/tools/batch.js +0 -586
  268. package/router/dist/tools/run.d.ts +0 -62
  269. package/router/dist/tools/run.js +0 -1304
  270. package/router/dist/tools/search.d.ts +0 -66
  271. package/router/dist/tools/search.js +0 -1364
  272. package/router/dist/transform/engine.d.ts +0 -168
  273. package/router/dist/transform/engine.js +0 -2072
  274. package/router/dist/vault/vault-index.d.ts +0 -125
  275. package/router/dist/vault/vault-index.js +0 -416
  276. package/router/dist/vault/vault.d.ts +0 -138
  277. package/router/dist/vault/vault.js +0 -630
  278. package/runtime/interaction-contract.md +0 -16
  279. package/skills/discuss/references/checkpoints.md +0 -66
  280. package/skills/execute-work/references/execution-loop.md +0 -77
  281. package/skills/track-work/references/working-record-schema.md +0 -378
  282. package/skills/workflow/references/workflow-loop.md +0 -92
  283. /package/skills/handoff/references/{templates.md → handoff-templates.md} +0 -0
  284. /package/skills/review-artifact/references/{reviewer-prompt.md → independent-artifact-reviewer-contract.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 {};