nodebench-mcp 2.70.0 → 3.0.1

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 (361) hide show
  1. package/README.md +95 -41
  2. package/dist/agents/alertRouter.d.ts +38 -0
  3. package/dist/agents/alertRouter.js +151 -0
  4. package/dist/agents/alertRouter.js.map +1 -0
  5. package/dist/agents/entityMemory.d.ts +40 -0
  6. package/dist/agents/entityMemory.js +64 -0
  7. package/dist/agents/entityMemory.js.map +1 -0
  8. package/dist/agents/subAgents.d.ts +35 -0
  9. package/dist/agents/subAgents.js +62 -0
  10. package/dist/agents/subAgents.js.map +1 -0
  11. package/dist/benchmarks/benchmarkRunner.js +14 -0
  12. package/dist/benchmarks/benchmarkRunner.js.map +1 -1
  13. package/dist/benchmarks/chainEval.js +107 -0
  14. package/dist/benchmarks/chainEval.js.map +1 -1
  15. package/dist/benchmarks/llmJudgeEval.js +85 -0
  16. package/dist/benchmarks/llmJudgeEval.js.map +1 -1
  17. package/dist/benchmarks/searchQualityEval.js +118 -5
  18. package/dist/benchmarks/searchQualityEval.js.map +1 -1
  19. package/dist/cli/search.d.ts +13 -0
  20. package/dist/cli/search.js +130 -0
  21. package/dist/cli/search.js.map +1 -0
  22. package/dist/dashboard/operatingDashboardHtml.js +2 -1
  23. package/dist/dashboard/operatingDashboardHtml.js.map +1 -1
  24. package/dist/dashboard/operatingServer.js +3 -2
  25. package/dist/dashboard/operatingServer.js.map +1 -1
  26. package/dist/db.d.ts +6 -2
  27. package/dist/db.js +521 -6
  28. package/dist/db.js.map +1 -1
  29. package/dist/index.js +349 -67
  30. package/dist/index.js.map +1 -1
  31. package/dist/packageInfo.d.ts +3 -0
  32. package/dist/packageInfo.js +32 -0
  33. package/dist/packageInfo.js.map +1 -0
  34. package/dist/profiler/behaviorStore.d.ts +97 -0
  35. package/dist/profiler/behaviorStore.js +276 -0
  36. package/dist/profiler/behaviorStore.js.map +1 -0
  37. package/dist/profiler/eventCollector.d.ts +119 -0
  38. package/dist/profiler/eventCollector.js +267 -0
  39. package/dist/profiler/eventCollector.js.map +1 -0
  40. package/dist/profiler/index.d.ts +15 -0
  41. package/dist/profiler/index.js +16 -0
  42. package/dist/profiler/index.js.map +1 -0
  43. package/dist/profiler/mcpProxy.d.ts +49 -0
  44. package/dist/profiler/mcpProxy.js +123 -0
  45. package/dist/profiler/mcpProxy.js.map +1 -0
  46. package/dist/profiler/modelRouter.d.ts +30 -0
  47. package/dist/profiler/modelRouter.js +99 -0
  48. package/dist/profiler/modelRouter.js.map +1 -0
  49. package/dist/profiler/otelReceiver.d.ts +17 -0
  50. package/dist/profiler/otelReceiver.js +62 -0
  51. package/dist/profiler/otelReceiver.js.map +1 -0
  52. package/dist/profiler/proofEngine.d.ts +41 -0
  53. package/dist/profiler/proofEngine.js +93 -0
  54. package/dist/profiler/proofEngine.js.map +1 -0
  55. package/dist/profiler/workflowTemplates.d.ts +41 -0
  56. package/dist/profiler/workflowTemplates.js +95 -0
  57. package/dist/profiler/workflowTemplates.js.map +1 -0
  58. package/dist/providers/localMemoryProvider.js +3 -2
  59. package/dist/providers/localMemoryProvider.js.map +1 -1
  60. package/dist/runtimeConfig.d.ts +11 -0
  61. package/dist/runtimeConfig.js +27 -0
  62. package/dist/runtimeConfig.js.map +1 -0
  63. package/dist/sandboxApi.js +2 -1
  64. package/dist/sandboxApi.js.map +1 -1
  65. package/dist/security/auditLog.js +8 -3
  66. package/dist/security/auditLog.js.map +1 -1
  67. package/dist/subconscious/blocks.d.ts +43 -0
  68. package/dist/subconscious/blocks.js +158 -0
  69. package/dist/subconscious/blocks.js.map +1 -0
  70. package/dist/subconscious/classifier.d.ts +22 -0
  71. package/dist/subconscious/classifier.js +118 -0
  72. package/dist/subconscious/classifier.js.map +1 -0
  73. package/dist/subconscious/graphEngine.d.ts +65 -0
  74. package/dist/subconscious/graphEngine.js +234 -0
  75. package/dist/subconscious/graphEngine.js.map +1 -0
  76. package/dist/subconscious/index.d.ts +19 -0
  77. package/dist/subconscious/index.js +20 -0
  78. package/dist/subconscious/index.js.map +1 -0
  79. package/dist/subconscious/tools.d.ts +5 -0
  80. package/dist/subconscious/tools.js +255 -0
  81. package/dist/subconscious/tools.js.map +1 -0
  82. package/dist/subconscious/whisperPolicy.d.ts +20 -0
  83. package/dist/subconscious/whisperPolicy.js +171 -0
  84. package/dist/subconscious/whisperPolicy.js.map +1 -0
  85. package/dist/sweep/engine.d.ts +27 -0
  86. package/dist/sweep/engine.js +244 -0
  87. package/dist/sweep/engine.js.map +1 -0
  88. package/dist/sweep/index.d.ts +9 -0
  89. package/dist/sweep/index.js +8 -0
  90. package/dist/sweep/index.js.map +1 -0
  91. package/dist/sweep/sources/github_trending.d.ts +6 -0
  92. package/dist/sweep/sources/github_trending.js +37 -0
  93. package/dist/sweep/sources/github_trending.js.map +1 -0
  94. package/dist/sweep/sources/hackernews.d.ts +7 -0
  95. package/dist/sweep/sources/hackernews.js +57 -0
  96. package/dist/sweep/sources/hackernews.js.map +1 -0
  97. package/dist/sweep/sources/openbb_finance.d.ts +9 -0
  98. package/dist/sweep/sources/openbb_finance.js +46 -0
  99. package/dist/sweep/sources/openbb_finance.js.map +1 -0
  100. package/dist/sweep/sources/producthunt.d.ts +6 -0
  101. package/dist/sweep/sources/producthunt.js +41 -0
  102. package/dist/sweep/sources/producthunt.js.map +1 -0
  103. package/dist/sweep/sources/web_signals.d.ts +7 -0
  104. package/dist/sweep/sources/web_signals.js +63 -0
  105. package/dist/sweep/sources/web_signals.js.map +1 -0
  106. package/dist/sweep/sources/yahoo_finance.d.ts +6 -0
  107. package/dist/sweep/sources/yahoo_finance.js +47 -0
  108. package/dist/sweep/sources/yahoo_finance.js.map +1 -0
  109. package/dist/sweep/types.d.ts +50 -0
  110. package/dist/sweep/types.js +9 -0
  111. package/dist/sweep/types.js.map +1 -0
  112. package/dist/sync/founderEpisodeStore.d.ts +98 -0
  113. package/dist/sync/founderEpisodeStore.js +230 -0
  114. package/dist/sync/founderEpisodeStore.js.map +1 -0
  115. package/dist/sync/hyperloopArchive.d.ts +51 -0
  116. package/dist/sync/hyperloopArchive.js +153 -0
  117. package/dist/sync/hyperloopArchive.js.map +1 -0
  118. package/dist/sync/hyperloopEval.d.ts +123 -0
  119. package/dist/sync/hyperloopEval.js +389 -0
  120. package/dist/sync/hyperloopEval.js.map +1 -0
  121. package/dist/sync/protocol.d.ts +172 -0
  122. package/dist/sync/protocol.js +9 -0
  123. package/dist/sync/protocol.js.map +1 -0
  124. package/dist/sync/sessionMemory.d.ts +47 -0
  125. package/dist/sync/sessionMemory.js +138 -0
  126. package/dist/sync/sessionMemory.js.map +1 -0
  127. package/dist/sync/store.d.ts +384 -0
  128. package/dist/sync/store.js +1435 -0
  129. package/dist/sync/store.js.map +1 -0
  130. package/dist/sync/syncBridgeClient.d.ts +30 -0
  131. package/dist/sync/syncBridgeClient.js +172 -0
  132. package/dist/sync/syncBridgeClient.js.map +1 -0
  133. package/dist/tools/autonomousDeliveryTools.d.ts +2 -0
  134. package/dist/tools/autonomousDeliveryTools.js +1104 -0
  135. package/dist/tools/autonomousDeliveryTools.js.map +1 -0
  136. package/dist/tools/boilerplateTools.js +10 -9
  137. package/dist/tools/boilerplateTools.js.map +1 -1
  138. package/dist/tools/claudeCodeIngestTools.d.ts +10 -0
  139. package/dist/tools/claudeCodeIngestTools.js +347 -0
  140. package/dist/tools/claudeCodeIngestTools.js.map +1 -0
  141. package/dist/tools/coreWorkflowTools.d.ts +2 -0
  142. package/dist/tools/coreWorkflowTools.js +488 -0
  143. package/dist/tools/coreWorkflowTools.js.map +1 -0
  144. package/dist/tools/deltaTools.d.ts +15 -0
  145. package/dist/tools/deltaTools.js +1522 -0
  146. package/dist/tools/deltaTools.js.map +1 -0
  147. package/dist/tools/documentationTools.js +2 -1
  148. package/dist/tools/documentationTools.js.map +1 -1
  149. package/dist/tools/entityLookupTools.d.ts +14 -0
  150. package/dist/tools/entityLookupTools.js +159 -0
  151. package/dist/tools/entityLookupTools.js.map +1 -0
  152. package/dist/tools/entityTemporalTools.d.ts +12 -0
  153. package/dist/tools/entityTemporalTools.js +330 -0
  154. package/dist/tools/entityTemporalTools.js.map +1 -0
  155. package/dist/tools/founderLocalPipeline.d.ts +215 -0
  156. package/dist/tools/founderLocalPipeline.js +1516 -2
  157. package/dist/tools/founderLocalPipeline.js.map +1 -1
  158. package/dist/tools/founderOperatingModel.d.ts +120 -0
  159. package/dist/tools/founderOperatingModel.js +469 -0
  160. package/dist/tools/founderOperatingModel.js.map +1 -0
  161. package/dist/tools/founderOperatingModelTools.d.ts +2 -0
  162. package/dist/tools/founderOperatingModelTools.js +169 -0
  163. package/dist/tools/founderOperatingModelTools.js.map +1 -0
  164. package/dist/tools/founderStrategicOpsTools.d.ts +2 -0
  165. package/dist/tools/founderStrategicOpsTools.js +1310 -0
  166. package/dist/tools/founderStrategicOpsTools.js.map +1 -0
  167. package/dist/tools/graphifyTools.d.ts +19 -0
  168. package/dist/tools/graphifyTools.js +375 -0
  169. package/dist/tools/graphifyTools.js.map +1 -0
  170. package/dist/tools/index.d.ts +3 -0
  171. package/dist/tools/index.js +4 -0
  172. package/dist/tools/index.js.map +1 -1
  173. package/dist/tools/monteCarloTools.d.ts +16 -0
  174. package/dist/tools/monteCarloTools.js +225 -0
  175. package/dist/tools/monteCarloTools.js.map +1 -0
  176. package/dist/tools/packetCompilerTools.d.ts +12 -0
  177. package/dist/tools/packetCompilerTools.js +322 -0
  178. package/dist/tools/packetCompilerTools.js.map +1 -0
  179. package/dist/tools/planSynthesisTools.d.ts +15 -0
  180. package/dist/tools/planSynthesisTools.js +455 -0
  181. package/dist/tools/planSynthesisTools.js.map +1 -0
  182. package/dist/tools/profilerTools.d.ts +20 -0
  183. package/dist/tools/profilerTools.js +364 -0
  184. package/dist/tools/profilerTools.js.map +1 -0
  185. package/dist/tools/progressiveDiscoveryTools.js +2 -1
  186. package/dist/tools/progressiveDiscoveryTools.js.map +1 -1
  187. package/dist/tools/savingsTools.d.ts +11 -0
  188. package/dist/tools/savingsTools.js +155 -0
  189. package/dist/tools/savingsTools.js.map +1 -0
  190. package/dist/tools/scenarioCompilerTools.d.ts +14 -0
  191. package/dist/tools/scenarioCompilerTools.js +290 -0
  192. package/dist/tools/scenarioCompilerTools.js.map +1 -0
  193. package/dist/tools/sharedContextTools.d.ts +2 -0
  194. package/dist/tools/sharedContextTools.js +423 -0
  195. package/dist/tools/sharedContextTools.js.map +1 -0
  196. package/dist/tools/sitemapTools.d.ts +15 -0
  197. package/dist/tools/sitemapTools.js +560 -0
  198. package/dist/tools/sitemapTools.js.map +1 -0
  199. package/dist/tools/sweepTools.d.ts +9 -0
  200. package/dist/tools/sweepTools.js +112 -0
  201. package/dist/tools/sweepTools.js.map +1 -0
  202. package/dist/tools/syncBridgeTools.d.ts +2 -0
  203. package/dist/tools/syncBridgeTools.js +258 -0
  204. package/dist/tools/syncBridgeTools.js.map +1 -0
  205. package/dist/tools/toolRegistry.js +1223 -45
  206. package/dist/tools/toolRegistry.js.map +1 -1
  207. package/dist/tools/workspaceTools.d.ts +19 -0
  208. package/dist/tools/workspaceTools.js +762 -0
  209. package/dist/tools/workspaceTools.js.map +1 -0
  210. package/dist/toolsetRegistry.js +162 -3
  211. package/dist/toolsetRegistry.js.map +1 -1
  212. package/package.json +39 -38
  213. package/rules/nodebench-agentic-reliability.md +32 -0
  214. package/rules/nodebench-analyst-diagnostic.md +25 -0
  215. package/rules/nodebench-auto-qa.md +31 -0
  216. package/rules/nodebench-completion-traceability.md +22 -0
  217. package/rules/nodebench-flywheel-continuous.md +25 -0
  218. package/rules/nodebench-pre-release-review.md +24 -0
  219. package/rules/nodebench-qa-dogfood.md +26 -0
  220. package/rules/nodebench-scenario-testing.md +30 -0
  221. package/rules/nodebench-self-direction.md +23 -0
  222. package/rules/nodebench-self-judge-loop.md +24 -0
  223. package/scripts/install.sh +215 -0
  224. package/dist/__tests__/analytics.test.d.ts +0 -11
  225. package/dist/__tests__/analytics.test.js +0 -546
  226. package/dist/__tests__/analytics.test.js.map +0 -1
  227. package/dist/__tests__/architectComplex.test.d.ts +0 -1
  228. package/dist/__tests__/architectComplex.test.js +0 -373
  229. package/dist/__tests__/architectComplex.test.js.map +0 -1
  230. package/dist/__tests__/architectSmoke.test.d.ts +0 -1
  231. package/dist/__tests__/architectSmoke.test.js +0 -92
  232. package/dist/__tests__/architectSmoke.test.js.map +0 -1
  233. package/dist/__tests__/audit-registry.d.ts +0 -1
  234. package/dist/__tests__/audit-registry.js +0 -60
  235. package/dist/__tests__/audit-registry.js.map +0 -1
  236. package/dist/__tests__/batchAutopilot.test.d.ts +0 -8
  237. package/dist/__tests__/batchAutopilot.test.js +0 -218
  238. package/dist/__tests__/batchAutopilot.test.js.map +0 -1
  239. package/dist/__tests__/cliSubcommands.test.d.ts +0 -1
  240. package/dist/__tests__/cliSubcommands.test.js +0 -138
  241. package/dist/__tests__/cliSubcommands.test.js.map +0 -1
  242. package/dist/__tests__/comparativeBench.test.d.ts +0 -1
  243. package/dist/__tests__/comparativeBench.test.js +0 -722
  244. package/dist/__tests__/comparativeBench.test.js.map +0 -1
  245. package/dist/__tests__/critterCalibrationEval.d.ts +0 -8
  246. package/dist/__tests__/critterCalibrationEval.js +0 -370
  247. package/dist/__tests__/critterCalibrationEval.js.map +0 -1
  248. package/dist/__tests__/dynamicLoading.test.d.ts +0 -1
  249. package/dist/__tests__/dynamicLoading.test.js +0 -280
  250. package/dist/__tests__/dynamicLoading.test.js.map +0 -1
  251. package/dist/__tests__/embeddingProvider.test.d.ts +0 -1
  252. package/dist/__tests__/embeddingProvider.test.js +0 -86
  253. package/dist/__tests__/embeddingProvider.test.js.map +0 -1
  254. package/dist/__tests__/evalDatasetBench.test.d.ts +0 -1
  255. package/dist/__tests__/evalDatasetBench.test.js +0 -738
  256. package/dist/__tests__/evalDatasetBench.test.js.map +0 -1
  257. package/dist/__tests__/evalHarness.test.d.ts +0 -1
  258. package/dist/__tests__/evalHarness.test.js +0 -1107
  259. package/dist/__tests__/evalHarness.test.js.map +0 -1
  260. package/dist/__tests__/fixtures/bfcl_v3_long_context.sample.json +0 -264
  261. package/dist/__tests__/fixtures/generateBfclLongContextFixture.d.ts +0 -10
  262. package/dist/__tests__/fixtures/generateBfclLongContextFixture.js +0 -135
  263. package/dist/__tests__/fixtures/generateBfclLongContextFixture.js.map +0 -1
  264. package/dist/__tests__/fixtures/generateSwebenchVerifiedFixture.d.ts +0 -14
  265. package/dist/__tests__/fixtures/generateSwebenchVerifiedFixture.js +0 -189
  266. package/dist/__tests__/fixtures/generateSwebenchVerifiedFixture.js.map +0 -1
  267. package/dist/__tests__/fixtures/generateToolbenchInstructionFixture.d.ts +0 -16
  268. package/dist/__tests__/fixtures/generateToolbenchInstructionFixture.js +0 -154
  269. package/dist/__tests__/fixtures/generateToolbenchInstructionFixture.js.map +0 -1
  270. package/dist/__tests__/fixtures/swebench_verified.sample.json +0 -162
  271. package/dist/__tests__/fixtures/toolbench_instruction.sample.json +0 -109
  272. package/dist/__tests__/forecastingDogfood.test.d.ts +0 -9
  273. package/dist/__tests__/forecastingDogfood.test.js +0 -284
  274. package/dist/__tests__/forecastingDogfood.test.js.map +0 -1
  275. package/dist/__tests__/forecastingScoring.test.d.ts +0 -9
  276. package/dist/__tests__/forecastingScoring.test.js +0 -202
  277. package/dist/__tests__/forecastingScoring.test.js.map +0 -1
  278. package/dist/__tests__/gaiaCapabilityAudioEval.test.d.ts +0 -15
  279. package/dist/__tests__/gaiaCapabilityAudioEval.test.js +0 -265
  280. package/dist/__tests__/gaiaCapabilityAudioEval.test.js.map +0 -1
  281. package/dist/__tests__/gaiaCapabilityEval.test.d.ts +0 -14
  282. package/dist/__tests__/gaiaCapabilityEval.test.js +0 -1259
  283. package/dist/__tests__/gaiaCapabilityEval.test.js.map +0 -1
  284. package/dist/__tests__/gaiaCapabilityFilesEval.test.d.ts +0 -15
  285. package/dist/__tests__/gaiaCapabilityFilesEval.test.js +0 -914
  286. package/dist/__tests__/gaiaCapabilityFilesEval.test.js.map +0 -1
  287. package/dist/__tests__/gaiaCapabilityMediaEval.test.d.ts +0 -15
  288. package/dist/__tests__/gaiaCapabilityMediaEval.test.js +0 -1101
  289. package/dist/__tests__/gaiaCapabilityMediaEval.test.js.map +0 -1
  290. package/dist/__tests__/helpers/answerMatch.d.ts +0 -41
  291. package/dist/__tests__/helpers/answerMatch.js +0 -267
  292. package/dist/__tests__/helpers/answerMatch.js.map +0 -1
  293. package/dist/__tests__/helpers/textLlm.d.ts +0 -25
  294. package/dist/__tests__/helpers/textLlm.js +0 -214
  295. package/dist/__tests__/helpers/textLlm.js.map +0 -1
  296. package/dist/__tests__/localDashboard.test.d.ts +0 -1
  297. package/dist/__tests__/localDashboard.test.js +0 -226
  298. package/dist/__tests__/localDashboard.test.js.map +0 -1
  299. package/dist/__tests__/multiHopDogfood.test.d.ts +0 -12
  300. package/dist/__tests__/multiHopDogfood.test.js +0 -303
  301. package/dist/__tests__/multiHopDogfood.test.js.map +0 -1
  302. package/dist/__tests__/openDatasetParallelEval.test.d.ts +0 -7
  303. package/dist/__tests__/openDatasetParallelEval.test.js +0 -209
  304. package/dist/__tests__/openDatasetParallelEval.test.js.map +0 -1
  305. package/dist/__tests__/openDatasetParallelEvalGaia.test.d.ts +0 -7
  306. package/dist/__tests__/openDatasetParallelEvalGaia.test.js +0 -279
  307. package/dist/__tests__/openDatasetParallelEvalGaia.test.js.map +0 -1
  308. package/dist/__tests__/openDatasetParallelEvalSwebench.test.d.ts +0 -7
  309. package/dist/__tests__/openDatasetParallelEvalSwebench.test.js +0 -220
  310. package/dist/__tests__/openDatasetParallelEvalSwebench.test.js.map +0 -1
  311. package/dist/__tests__/openDatasetParallelEvalToolbench.test.d.ts +0 -7
  312. package/dist/__tests__/openDatasetParallelEvalToolbench.test.js +0 -218
  313. package/dist/__tests__/openDatasetParallelEvalToolbench.test.js.map +0 -1
  314. package/dist/__tests__/openDatasetPerfComparison.test.d.ts +0 -10
  315. package/dist/__tests__/openDatasetPerfComparison.test.js +0 -318
  316. package/dist/__tests__/openDatasetPerfComparison.test.js.map +0 -1
  317. package/dist/__tests__/openclawDogfood.test.d.ts +0 -23
  318. package/dist/__tests__/openclawDogfood.test.js +0 -535
  319. package/dist/__tests__/openclawDogfood.test.js.map +0 -1
  320. package/dist/__tests__/openclawMessaging.test.d.ts +0 -14
  321. package/dist/__tests__/openclawMessaging.test.js +0 -232
  322. package/dist/__tests__/openclawMessaging.test.js.map +0 -1
  323. package/dist/__tests__/presetRealWorldBench.test.d.ts +0 -1
  324. package/dist/__tests__/presetRealWorldBench.test.js +0 -859
  325. package/dist/__tests__/presetRealWorldBench.test.js.map +0 -1
  326. package/dist/__tests__/tools.test.d.ts +0 -1
  327. package/dist/__tests__/tools.test.js +0 -3201
  328. package/dist/__tests__/tools.test.js.map +0 -1
  329. package/dist/__tests__/toolsetGatingEval.test.d.ts +0 -1
  330. package/dist/__tests__/toolsetGatingEval.test.js +0 -1099
  331. package/dist/__tests__/toolsetGatingEval.test.js.map +0 -1
  332. package/dist/__tests__/traceabilityDogfood.test.d.ts +0 -12
  333. package/dist/__tests__/traceabilityDogfood.test.js +0 -241
  334. package/dist/__tests__/traceabilityDogfood.test.js.map +0 -1
  335. package/dist/__tests__/webmcpTools.test.d.ts +0 -7
  336. package/dist/__tests__/webmcpTools.test.js +0 -195
  337. package/dist/__tests__/webmcpTools.test.js.map +0 -1
  338. package/dist/benchmarks/testProviderBus.d.ts +0 -7
  339. package/dist/benchmarks/testProviderBus.js +0 -272
  340. package/dist/benchmarks/testProviderBus.js.map +0 -1
  341. package/dist/hooks/postCompaction.d.ts +0 -14
  342. package/dist/hooks/postCompaction.js +0 -51
  343. package/dist/hooks/postCompaction.js.map +0 -1
  344. package/dist/security/__tests__/security.test.d.ts +0 -8
  345. package/dist/security/__tests__/security.test.js +0 -295
  346. package/dist/security/__tests__/security.test.js.map +0 -1
  347. package/dist/tools/documentTools.d.ts +0 -5
  348. package/dist/tools/documentTools.js +0 -524
  349. package/dist/tools/documentTools.js.map +0 -1
  350. package/dist/tools/financialTools.d.ts +0 -10
  351. package/dist/tools/financialTools.js +0 -403
  352. package/dist/tools/financialTools.js.map +0 -1
  353. package/dist/tools/memoryTools.d.ts +0 -5
  354. package/dist/tools/memoryTools.js +0 -137
  355. package/dist/tools/memoryTools.js.map +0 -1
  356. package/dist/tools/planningTools.d.ts +0 -5
  357. package/dist/tools/planningTools.js +0 -147
  358. package/dist/tools/planningTools.js.map +0 -1
  359. package/dist/tools/searchTools.d.ts +0 -5
  360. package/dist/tools/searchTools.js +0 -145
  361. package/dist/tools/searchTools.js.map +0 -1
@@ -1,189 +0,0 @@
1
- #!/usr/bin/env npx tsx
2
- /**
3
- * Refreshes a local fixture from SWE-bench Verified (open-source GitHub issue tasks).
4
- *
5
- * Source:
6
- * - https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified
7
- * - rows API: https://datasets-server.huggingface.co/rows
8
- *
9
- * Usage:
10
- * npx tsx src/__tests__/fixtures/generateSwebenchVerifiedFixture.ts
11
- * npx tsx src/__tests__/fixtures/generateSwebenchVerifiedFixture.ts --limit 12 --min-statement-length 700 --min-fail-to-pass 2
12
- * npx tsx src/__tests__/fixtures/generateSwebenchVerifiedFixture.ts --output ./tmp/swebench.sample.json
13
- */
14
- import { mkdirSync, writeFileSync } from "node:fs";
15
- import { dirname, join } from "node:path";
16
- import { fileURLToPath } from "node:url";
17
- const DATASET = "princeton-nlp/SWE-bench_Verified";
18
- const CONFIG = "default";
19
- const SPLIT = "test";
20
- const ROWS_API = "https://datasets-server.huggingface.co/rows";
21
- const DATASET_PAGE = "https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified";
22
- function getArg(flag) {
23
- const index = process.argv.indexOf(flag);
24
- if (index < 0)
25
- return undefined;
26
- return process.argv[index + 1];
27
- }
28
- function parseIntArg(flag, fallback) {
29
- const raw = getArg(flag);
30
- if (!raw)
31
- return fallback;
32
- const value = Number.parseInt(raw, 10);
33
- if (!Number.isFinite(value))
34
- return fallback;
35
- return value;
36
- }
37
- function compactWhitespace(input) {
38
- return input.replace(/\s+/g, " ").trim();
39
- }
40
- function parseStringArray(value) {
41
- if (Array.isArray(value)) {
42
- return value.filter((item) => typeof item === "string");
43
- }
44
- if (typeof value !== "string" || value.trim().length === 0)
45
- return [];
46
- try {
47
- const parsed = JSON.parse(value);
48
- if (!Array.isArray(parsed))
49
- return [];
50
- return parsed.filter((item) => typeof item === "string");
51
- }
52
- catch {
53
- return [];
54
- }
55
- }
56
- function difficultyWeight(difficulty) {
57
- const normalized = difficulty.toLowerCase();
58
- if (normalized.includes("1-4 hours"))
59
- return 50;
60
- if (normalized.includes("15 min - 1 hour"))
61
- return 30;
62
- if (normalized.includes("<15 min"))
63
- return 10;
64
- return 20;
65
- }
66
- function toTask(raw, index) {
67
- const id = compactWhitespace(String(raw.instance_id ?? ""));
68
- const repo = compactWhitespace(String(raw.repo ?? ""));
69
- const problemStatement = compactWhitespace(String(raw.problem_statement ?? ""));
70
- if (!id || !repo || !problemStatement)
71
- return null;
72
- const hints = compactWhitespace(String(raw.hints_text ?? ""));
73
- const difficulty = compactWhitespace(String(raw.difficulty ?? "unspecified"));
74
- const failToPassCount = parseStringArray(raw.FAIL_TO_PASS).length;
75
- const passToPassCount = parseStringArray(raw.PASS_TO_PASS).length;
76
- const statementLength = problemStatement.length;
77
- const hintLength = hints.length;
78
- const complexityScore = Math.ceil(statementLength / 25) +
79
- Math.ceil(hintLength / 40) +
80
- failToPassCount * 14 +
81
- Math.ceil(passToPassCount / 8) +
82
- difficultyWeight(difficulty);
83
- const promptSections = [
84
- `Repository: ${repo}`,
85
- `Instance: ${id}`,
86
- `Difficulty: ${difficulty}`,
87
- `Problem: ${problemStatement}`,
88
- ];
89
- if (hints.length > 0) {
90
- promptSections.push(`Hints: ${hints}`);
91
- }
92
- return {
93
- id,
94
- title: `SWE-bench ${id}`,
95
- prompt: promptSections.join("\n"),
96
- repo,
97
- difficulty,
98
- statementLength,
99
- hintLength,
100
- failToPassCount,
101
- passToPassCount,
102
- complexityScore,
103
- };
104
- }
105
- async function fetchRows(offset, length) {
106
- const url = new URL(ROWS_API);
107
- url.searchParams.set("dataset", DATASET);
108
- url.searchParams.set("config", CONFIG);
109
- url.searchParams.set("split", SPLIT);
110
- url.searchParams.set("offset", String(offset));
111
- url.searchParams.set("length", String(length));
112
- const response = await fetch(url.toString());
113
- if (!response.ok) {
114
- throw new Error(`Failed to fetch SWE-bench rows: ${response.status} ${response.statusText}`);
115
- }
116
- return (await response.json());
117
- }
118
- async function loadRows(maxRows, pageSize) {
119
- const rows = [];
120
- for (let offset = 0; offset < maxRows; offset += pageSize) {
121
- const remaining = maxRows - offset;
122
- const length = Math.max(1, Math.min(pageSize, remaining));
123
- const page = await fetchRows(offset, length);
124
- const pageRows = Array.isArray(page.rows) ? page.rows : [];
125
- if (pageRows.length === 0)
126
- break;
127
- for (const entry of pageRows) {
128
- if (!entry || typeof entry !== "object")
129
- continue;
130
- const row = entry.row;
131
- if (row && typeof row === "object")
132
- rows.push(row);
133
- }
134
- if (pageRows.length < length)
135
- break;
136
- }
137
- return rows;
138
- }
139
- async function main() {
140
- const limit = Math.max(1, parseIntArg("--limit", 12));
141
- const minStatementLength = Math.max(100, parseIntArg("--min-statement-length", 700));
142
- const minFailToPass = Math.max(1, parseIntArg("--min-fail-to-pass", 2));
143
- const maxRowsScanned = Math.max(50, parseIntArg("--max-rows", 500));
144
- const pageSize = Math.max(10, parseIntArg("--page-size", 100));
145
- const here = dirname(fileURLToPath(import.meta.url));
146
- const outputPath = getArg("--output") ?? join(here, "swebench_verified.sample.json");
147
- const rawRows = await loadRows(maxRowsScanned, pageSize);
148
- const tasks = rawRows
149
- .map((row, index) => toTask(row, index))
150
- .filter((task) => task !== null);
151
- const candidates = tasks
152
- .filter((task) => task.statementLength >= minStatementLength && task.failToPassCount >= minFailToPass)
153
- .sort((a, b) => {
154
- if (b.complexityScore !== a.complexityScore)
155
- return b.complexityScore - a.complexityScore;
156
- return a.id.localeCompare(b.id);
157
- });
158
- const selected = candidates.slice(0, limit);
159
- if (selected.length === 0) {
160
- throw new Error(`No SWE-bench tasks matched filters (minStatementLength=${minStatementLength}, minFailToPass=${minFailToPass}).`);
161
- }
162
- const fixture = {
163
- dataset: DATASET,
164
- split: SPLIT,
165
- sourceUrl: DATASET_PAGE,
166
- rowsApi: ROWS_API,
167
- generatedAt: new Date().toISOString(),
168
- selection: {
169
- requestedLimit: limit,
170
- minStatementLength,
171
- minFailToPass,
172
- maxRowsScanned,
173
- pageSize,
174
- totalRecords: tasks.length,
175
- candidateRecords: candidates.length,
176
- },
177
- tasks: selected,
178
- };
179
- mkdirSync(dirname(outputPath), { recursive: true });
180
- writeFileSync(outputPath, JSON.stringify(fixture, null, 2) + "\n", "utf8");
181
- console.log(`[swebench-fixture] wrote ${selected.length} tasks to ${outputPath}`);
182
- console.log(`[swebench-fixture] total=${tasks.length}, candidates=${candidates.length}, filters=statement>=${minStatementLength}, failToPass>=${minFailToPass}`);
183
- }
184
- main().catch((error) => {
185
- const message = error instanceof Error ? error.stack ?? error.message : String(error);
186
- process.stderr.write(`${message}\n`);
187
- process.exit(1);
188
- });
189
- //# sourceMappingURL=generateSwebenchVerifiedFixture.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"generateSwebenchVerifiedFixture.js","sourceRoot":"","sources":["../../../src/__tests__/fixtures/generateSwebenchVerifiedFixture.ts"],"names":[],"mappings":";AAEA;;;;;;;;;;;GAWG;AAEH,OAAO,EAAE,SAAS,EAAE,aAAa,EAAE,MAAM,SAAS,CAAC;AACnD,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAC1C,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAC;AAEzC,MAAM,OAAO,GAAG,kCAAkC,CAAC;AACnD,MAAM,MAAM,GAAG,SAAS,CAAC;AACzB,MAAM,KAAK,GAAG,MAAM,CAAC;AACrB,MAAM,QAAQ,GAAG,6CAA6C,CAAC;AAC/D,MAAM,YAAY,GAAG,kEAAkE,CAAC;AAgDxF,SAAS,MAAM,CAAC,IAAY;IAC1B,MAAM,KAAK,GAAG,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;IACzC,IAAI,KAAK,GAAG,CAAC;QAAE,OAAO,SAAS,CAAC;IAChC,OAAO,OAAO,CAAC,IAAI,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC;AACjC,CAAC;AAED,SAAS,WAAW,CAAC,IAAY,EAAE,QAAgB;IACjD,MAAM,GAAG,GAAG,MAAM,CAAC,IAAI,CAAC,CAAC;IACzB,IAAI,CAAC,GAAG;QAAE,OAAO,QAAQ,CAAC;IAC1B,MAAM,KAAK,GAAG,MAAM,CAAC,QAAQ,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC;IACvC,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC;QAAE,OAAO,QAAQ,CAAC;IAC7C,OAAO,KAAK,CAAC;AACf,CAAC;AAED,SAAS,iBAAiB,CAAC,KAAa;IACtC,OAAO,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;AAC3C,CAAC;AAED,SAAS,gBAAgB,CAAC,KAAc;IACtC,IAAI,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;QACzB,OAAO,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAkB,EAAE,CAAC,OAAO,IAAI,KAAK,QAAQ,CAAC,CAAC;IAC1E,CAAC;IACD,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,EAAE,CAAC;IACtE,IAAI,CAAC;QACH,MAAM,MAAM,GAAG,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;QACjC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC;YAAE,OAAO,EAAE,CAAC;QACtC,OAAO,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,EAAkB,EAAE,CAAC,OAAO,IAAI,KAAK,QAAQ,CAAC,CAAC;IAC3E,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,EAAE,CAAC;IACZ,CAAC;AACH,CAAC;AAED,SAAS,gBAAgB,CAAC,UAAkB;IAC1C,MAAM,UAAU,GAAG,UAAU,CAAC,WAAW,EAAE,CAAC;IAC5C,IAAI,UAAU,CAAC,QAAQ,CAAC,WAAW,CAAC;QAAE,OAAO,EAAE,CAAC;IAChD,IAAI,UAAU,CAAC,QAAQ,CAAC,iBAAiB,CAAC;QAAE,OAAO,EAAE,CAAC;IACtD,IAAI,UAAU,CAAC,QAAQ,CAAC,SAAS,CAAC;QAAE,OAAO,EAAE,CAAC;IAC9C,OAAO,EAAE,CAAC;AACZ,CAAC;AAED,SAAS,MAAM,CAAC,GAAmB,EAAE,KAAa;IAChD,MAAM,EAAE,GAAG,iBAAiB,CAAC,MAAM,CAAC,GAAG,CAAC,WAAW,IAAI,EAAE,CAAC,CAAC,CAAC;IAC5D,MAAM,IAAI,GAAG,iBAAiB,CAAC,MAAM,CAAC,GAAG,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,CAAC;IACvD,MAAM,gBAAgB,GAAG,iBAAiB,CAAC,MAAM,CAAC,GAAG,CAAC,iBAAiB,IAAI,EAAE,CAAC,CAAC,CAAC;IAChF,IAAI,CAAC,EAAE,IAAI,CAAC,IAAI,IAAI,CAAC,gBAAgB;QAAE,OAAO,IAAI,CAAC;IAEnD,MAAM,KAAK,GAAG,iBAAiB,CAAC,MAAM,CAAC,GAAG,CAAC,UAAU,IAAI,EAAE,CAAC,CAAC,CAAC;IAC9D,MAAM,UAAU,GAAG,iBAAiB,CAAC,MAAM,CAAC,GAAG,CAAC,UAAU,IAAI,aAAa,CAAC,CAAC,CAAC;IAC9E,MAAM,eAAe,GAAG,gBAAgB,CAAC,GAAG,CAAC,YAAY,CAAC,CAAC,MAAM,CAAC;IAClE,MAAM,eAAe,GAAG,gBAAgB,CAAC,GAAG,CAAC,YAAY,CAAC,CAAC,MAAM,CAAC;IAClE,MAAM,eAAe,GAAG,gBAAgB,CAAC,MAAM,CAAC;IAChD,MAAM,UAAU,GAAG,KAAK,CAAC,MAAM,CAAC;IAEhC,MAAM,eAAe,GACnB,IAAI,CAAC,IAAI,CAAC,eAAe,GAAG,EAAE,CAAC;QAC/B,IAAI,CAAC,IAAI,CAAC,UAAU,GAAG,EAAE,CAAC;QAC1B,eAAe,GAAG,EAAE;QACpB,IAAI,CAAC,IAAI,CAAC,eAAe,GAAG,CAAC,CAAC;QAC9B,gBAAgB,CAAC,UAAU,CAAC,CAAC;IAE/B,MAAM,cAAc,GAAG;QACrB,eAAe,IAAI,EAAE;QACrB,aAAa,EAAE,EAAE;QACjB,eAAe,UAAU,EAAE;QAC3B,YAAY,gBAAgB,EAAE;KAC/B,CAAC;IACF,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACrB,cAAc,CAAC,IAAI,CAAC,UAAU,KAAK,EAAE,CAAC,CAAC;IACzC,CAAC;IAED,OAAO;QACL,EAAE;QACF,KAAK,EAAE,aAAa,EAAE,EAAE;QACxB,MAAM,EAAE,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC;QACjC,IAAI;QACJ,UAAU;QACV,eAAe;QACf,UAAU;QACV,eAAe;QACf,eAAe;QACf,eAAe;KAChB,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,SAAS,CAAC,MAAc,EAAE,MAAc;IACrD,MAAM,GAAG,GAAG,IAAI,GAAG,CAAC,QAAQ,CAAC,CAAC;IAC9B,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;IACzC,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAC;IACvC,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,OAAO,EAAE,KAAK,CAAC,CAAC;IACrC,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,QAAQ,EAAE,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC;IAC/C,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,QAAQ,EAAE,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC;IAE/C,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,CAAC,QAAQ,EAAE,CAAC,CAAC;IAC7C,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;QACjB,MAAM,IAAI,KAAK,CAAC,mCAAmC,QAAQ,CAAC,MAAM,IAAI,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAC;IAC/F,CAAC;IAED,OAAO,CAAC,MAAM,QAAQ,CAAC,IAAI,EAAE,CAAgB,CAAC;AAChD,CAAC;AAED,KAAK,UAAU,QAAQ,CAAC,OAAe,EAAE,QAAgB;IACvD,MAAM,IAAI,GAAqB,EAAE,CAAC;IAClC,KAAK,IAAI,MAAM,GAAG,CAAC,EAAE,MAAM,GAAG,OAAO,EAAE,MAAM,IAAI,QAAQ,EAAE,CAAC;QAC1D,MAAM,SAAS,GAAG,OAAO,GAAG,MAAM,CAAC;QACnC,MAAM,MAAM,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,GAAG,CAAC,QAAQ,EAAE,SAAS,CAAC,CAAC,CAAC;QAC1D,MAAM,IAAI,GAAG,MAAM,SAAS,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;QAC7C,MAAM,QAAQ,GAAG,KAAK,CAAC,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;QAC3D,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC;YAAE,MAAM;QAEjC,KAAK,MAAM,KAAK,IAAI,QAAQ,EAAE,CAAC;YAC7B,IAAI,CAAC,KAAK,IAAI,OAAO,KAAK,KAAK,QAAQ;gBAAE,SAAS;YAClD,MAAM,GAAG,GAAG,KAAK,CAAC,GAAG,CAAC;YACtB,IAAI,GAAG,IAAI,OAAO,GAAG,KAAK,QAAQ;gBAAE,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;QACrD,CAAC;QAED,IAAI,QAAQ,CAAC,MAAM,GAAG,MAAM;YAAE,MAAM;IACtC,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC;AAED,KAAK,UAAU,IAAI;IACjB,MAAM,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,WAAW,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC,CAAC;IACtD,MAAM,kBAAkB,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,WAAW,CAAC,wBAAwB,EAAE,GAAG,CAAC,CAAC,CAAC;IACrF,MAAM,aAAa,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,WAAW,CAAC,oBAAoB,EAAE,CAAC,CAAC,CAAC,CAAC;IACxE,MAAM,cAAc,GAAG,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,WAAW,CAAC,YAAY,EAAE,GAAG,CAAC,CAAC,CAAC;IACpE,MAAM,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,WAAW,CAAC,aAAa,EAAE,GAAG,CAAC,CAAC,CAAC;IAE/D,MAAM,IAAI,GAAG,OAAO,CAAC,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;IACrD,MAAM,UAAU,GAAG,MAAM,CAAC,UAAU,CAAC,IAAI,IAAI,CAAC,IAAI,EAAE,+BAA+B,CAAC,CAAC;IAErF,MAAM,OAAO,GAAG,MAAM,QAAQ,CAAC,cAAc,EAAE,QAAQ,CAAC,CAAC;IACzD,MAAM,KAAK,GAAG,OAAO;SAClB,GAAG,CAAC,CAAC,GAAG,EAAE,KAAK,EAAE,EAAE,CAAC,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,CAAC;SACvC,MAAM,CAAC,CAAC,IAAI,EAA+B,EAAE,CAAC,IAAI,KAAK,IAAI,CAAC,CAAC;IAEhE,MAAM,UAAU,GAAG,KAAK;SACrB,MAAM,CACL,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,eAAe,IAAI,kBAAkB,IAAI,IAAI,CAAC,eAAe,IAAI,aAAa,CAC9F;SACA,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE;QACb,IAAI,CAAC,CAAC,eAAe,KAAK,CAAC,CAAC,eAAe;YAAE,OAAO,CAAC,CAAC,eAAe,GAAG,CAAC,CAAC,eAAe,CAAC;QAC1F,OAAO,CAAC,CAAC,EAAE,CAAC,aAAa,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;IAClC,CAAC,CAAC,CAAC;IAEL,MAAM,QAAQ,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC;IAC5C,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC1B,MAAM,IAAI,KAAK,CACb,0DAA0D,kBAAkB,mBAAmB,aAAa,IAAI,CACjH,CAAC;IACJ,CAAC;IAED,MAAM,OAAO,GAAoB;QAC/B,OAAO,EAAE,OAAO;QAChB,KAAK,EAAE,KAAK;QACZ,SAAS,EAAE,YAAY;QACvB,OAAO,EAAE,QAAQ;QACjB,WAAW,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACrC,SAAS,EAAE;YACT,cAAc,EAAE,KAAK;YACrB,kBAAkB;YAClB,aAAa;YACb,cAAc;YACd,QAAQ;YACR,YAAY,EAAE,KAAK,CAAC,MAAM;YAC1B,gBAAgB,EAAE,UAAU,CAAC,MAAM;SACpC;QACD,KAAK,EAAE,QAAQ;KAChB,CAAC;IAEF,SAAS,CAAC,OAAO,CAAC,UAAU,CAAC,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IACpD,aAAa,CAAC,UAAU,EAAE,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,GAAG,IAAI,EAAE,MAAM,CAAC,CAAC;IAE3E,OAAO,CAAC,GAAG,CAAC,4BAA4B,QAAQ,CAAC,MAAM,aAAa,UAAU,EAAE,CAAC,CAAC;IAClF,OAAO,CAAC,GAAG,CACT,4BAA4B,KAAK,CAAC,MAAM,gBAAgB,UAAU,CAAC,MAAM,wBAAwB,kBAAkB,iBAAiB,aAAa,EAAE,CACpJ,CAAC;AACJ,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,KAAK,EAAE,EAAE;IACrB,MAAM,OAAO,GAAG,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,IAAI,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;IACtF,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,OAAO,IAAI,CAAC,CAAC;IACrC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC"}
@@ -1,16 +0,0 @@
1
- #!/usr/bin/env npx tsx
2
- /**
3
- * Refreshes a local fixture from the open-source ToolBench instruction dataset.
4
- *
5
- * Source:
6
- * - https://github.com/OpenBMB/ToolBench
7
- * - data_example/instruction/G1_query.json
8
- * - data_example/instruction/G2_query.json
9
- * - data_example/instruction/G3_query.json
10
- *
11
- * Usage:
12
- * npx tsx src/__tests__/fixtures/generateToolbenchInstructionFixture.ts
13
- * npx tsx src/__tests__/fixtures/generateToolbenchInstructionFixture.ts --limit 10 --min-api 6
14
- * npx tsx src/__tests__/fixtures/generateToolbenchInstructionFixture.ts --output ./tmp/toolbench.sample.json
15
- */
16
- export {};
@@ -1,154 +0,0 @@
1
- #!/usr/bin/env npx tsx
2
- /**
3
- * Refreshes a local fixture from the open-source ToolBench instruction dataset.
4
- *
5
- * Source:
6
- * - https://github.com/OpenBMB/ToolBench
7
- * - data_example/instruction/G1_query.json
8
- * - data_example/instruction/G2_query.json
9
- * - data_example/instruction/G3_query.json
10
- *
11
- * Usage:
12
- * npx tsx src/__tests__/fixtures/generateToolbenchInstructionFixture.ts
13
- * npx tsx src/__tests__/fixtures/generateToolbenchInstructionFixture.ts --limit 10 --min-api 6
14
- * npx tsx src/__tests__/fixtures/generateToolbenchInstructionFixture.ts --output ./tmp/toolbench.sample.json
15
- */
16
- import { mkdirSync, writeFileSync } from "node:fs";
17
- import { dirname, join } from "node:path";
18
- import { fileURLToPath } from "node:url";
19
- const SOURCES = [
20
- {
21
- group: "G1",
22
- url: "https://raw.githubusercontent.com/OpenBMB/ToolBench/master/data_example/instruction/G1_query.json",
23
- },
24
- {
25
- group: "G2",
26
- url: "https://raw.githubusercontent.com/OpenBMB/ToolBench/master/data_example/instruction/G2_query.json",
27
- },
28
- {
29
- group: "G3",
30
- url: "https://raw.githubusercontent.com/OpenBMB/ToolBench/master/data_example/instruction/G3_query.json",
31
- },
32
- ];
33
- function getArg(flag) {
34
- const index = process.argv.indexOf(flag);
35
- if (index < 0)
36
- return undefined;
37
- return process.argv[index + 1];
38
- }
39
- function parseIntArg(flag, fallback) {
40
- const raw = getArg(flag);
41
- if (!raw)
42
- return fallback;
43
- const value = Number.parseInt(raw, 10);
44
- if (!Number.isFinite(value))
45
- return fallback;
46
- return value;
47
- }
48
- function compactWhitespace(input) {
49
- return input.replace(/\s+/g, " ").trim();
50
- }
51
- function asArray(value) {
52
- return Array.isArray(value) ? value : [];
53
- }
54
- function toTask(record, group, index) {
55
- const query = compactWhitespace(String(record.query ?? ""));
56
- if (!query)
57
- return null;
58
- const apiList = asArray(record.api_list).filter((entry) => typeof entry === "object" && entry !== null);
59
- const requiredParameterCount = apiList.reduce((count, api) => {
60
- return count + asArray(api.required_parameters).length;
61
- }, 0);
62
- const optionalParameterCount = apiList.reduce((count, api) => {
63
- return count + asArray(api.optional_parameters).length;
64
- }, 0);
65
- const apiCategories = Array.from(new Set(apiList
66
- .map((api) => String(api.category_name ?? "").trim())
67
- .filter((name) => name.length > 0)));
68
- const apiCount = apiList.length;
69
- const relevantApiCount = asArray(record["relevant APIs"]).length;
70
- const rawId = String(record.query_id ?? `${group}_${index + 1}`).trim();
71
- const id = `${group}_${rawId}`;
72
- const title = `ToolBench ${group} query ${rawId}`;
73
- const complexityScore = apiCount * 12 +
74
- requiredParameterCount * 2 +
75
- optionalParameterCount +
76
- relevantApiCount * 3 +
77
- Math.ceil(query.length / 40);
78
- return {
79
- id,
80
- title,
81
- prompt: query,
82
- group,
83
- apiCount,
84
- relevantApiCount,
85
- requiredParameterCount,
86
- optionalParameterCount,
87
- apiCategories,
88
- complexityScore,
89
- };
90
- }
91
- async function fetchSource(group, url) {
92
- const response = await fetch(url);
93
- if (!response.ok) {
94
- throw new Error(`Failed to fetch ${group} dataset: ${response.status} ${response.statusText}`);
95
- }
96
- const raw = await response.json();
97
- if (!Array.isArray(raw)) {
98
- throw new Error(`Unexpected payload for ${group}: expected array`);
99
- }
100
- return raw;
101
- }
102
- async function main() {
103
- const limit = Math.max(1, parseIntArg("--limit", 10));
104
- const minApiCount = Math.max(1, parseIntArg("--min-api", 6));
105
- const minQueryLength = Math.max(1, parseIntArg("--min-query-length", 180));
106
- const here = dirname(fileURLToPath(import.meta.url));
107
- const outputPath = getArg("--output") ?? join(here, "toolbench_instruction.sample.json");
108
- const fetched = await Promise.all(SOURCES.map(async (source) => {
109
- const records = await fetchSource(source.group, source.url);
110
- return { ...source, records };
111
- }));
112
- const tasks = fetched.flatMap((entry) => entry.records
113
- .map((record, index) => toTask(record, entry.group, index))
114
- .filter((task) => task !== null));
115
- const candidates = tasks
116
- .filter((task) => task.apiCount >= minApiCount && task.prompt.length >= minQueryLength)
117
- .sort((a, b) => {
118
- if (b.complexityScore !== a.complexityScore)
119
- return b.complexityScore - a.complexityScore;
120
- return a.id.localeCompare(b.id);
121
- });
122
- const selected = candidates.slice(0, limit);
123
- if (selected.length === 0) {
124
- throw new Error(`No ToolBench tasks matched filters (minApiCount=${minApiCount}, minQueryLength=${minQueryLength}).`);
125
- }
126
- const sourceUrls = SOURCES.reduce((acc, source) => {
127
- acc[source.group] = source.url;
128
- return acc;
129
- }, {});
130
- const fixture = {
131
- dataset: "OpenBMB/ToolBench",
132
- split: "data_example/instruction (G1,G2,G3)",
133
- sourceUrls,
134
- generatedAt: new Date().toISOString(),
135
- selection: {
136
- requestedLimit: limit,
137
- minApiCount,
138
- minQueryLength,
139
- totalRecords: tasks.length,
140
- candidateRecords: candidates.length,
141
- },
142
- tasks: selected,
143
- };
144
- mkdirSync(dirname(outputPath), { recursive: true });
145
- writeFileSync(outputPath, JSON.stringify(fixture, null, 2) + "\n", "utf8");
146
- console.log(`[toolbench-fixture] wrote ${selected.length} tasks to ${outputPath}`);
147
- console.log(`[toolbench-fixture] total=${tasks.length}, candidates=${candidates.length}, filters=api>=${minApiCount}, queryLength>=${minQueryLength}`);
148
- }
149
- main().catch((error) => {
150
- const message = error instanceof Error ? error.stack ?? error.message : String(error);
151
- process.stderr.write(`${message}\n`);
152
- process.exit(1);
153
- });
154
- //# sourceMappingURL=generateToolbenchInstructionFixture.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"generateToolbenchInstructionFixture.js","sourceRoot":"","sources":["../../../src/__tests__/fixtures/generateToolbenchInstructionFixture.ts"],"names":[],"mappings":";AAEA;;;;;;;;;;;;;GAaG;AAEH,OAAO,EAAE,SAAS,EAAE,aAAa,EAAE,MAAM,SAAS,CAAC;AACnD,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAC1C,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAC;AAEzC,MAAM,OAAO,GAAG;IACd;QACE,KAAK,EAAE,IAAI;QACX,GAAG,EAAE,mGAAmG;KACzG;IACD;QACE,KAAK,EAAE,IAAI;QACX,GAAG,EAAE,mGAAmG;KACzG;IACD;QACE,KAAK,EAAE,IAAI;QACX,GAAG,EAAE,mGAAmG;KACzG;CACO,CAAC;AA+CX,SAAS,MAAM,CAAC,IAAY;IAC1B,MAAM,KAAK,GAAG,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;IACzC,IAAI,KAAK,GAAG,CAAC;QAAE,OAAO,SAAS,CAAC;IAChC,OAAO,OAAO,CAAC,IAAI,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC;AACjC,CAAC;AAED,SAAS,WAAW,CAAC,IAAY,EAAE,QAAgB;IACjD,MAAM,GAAG,GAAG,MAAM,CAAC,IAAI,CAAC,CAAC;IACzB,IAAI,CAAC,GAAG;QAAE,OAAO,QAAQ,CAAC;IAC1B,MAAM,KAAK,GAAG,MAAM,CAAC,QAAQ,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC;IACvC,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC;QAAE,OAAO,QAAQ,CAAC;IAC7C,OAAO,KAAK,CAAC;AACf,CAAC;AAED,SAAS,iBAAiB,CAAC,KAAa;IACtC,OAAO,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;AAC3C,CAAC;AAED,SAAS,OAAO,CAAI,KAAc;IAChC,OAAO,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAE,KAAa,CAAC,CAAC,CAAC,EAAE,CAAC;AACpD,CAAC;AAED,SAAS,MAAM,CAAC,MAA0B,EAAE,KAAkB,EAAE,KAAa;IAC3E,MAAM,KAAK,GAAG,iBAAiB,CAAC,MAAM,CAAC,MAAM,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC;IAC5D,IAAI,CAAC,KAAK;QAAE,OAAO,IAAI,CAAC;IAExB,MAAM,OAAO,GAAG,OAAO,CAAe,MAAM,CAAC,QAAQ,CAAC,CAAC,MAAM,CAC3D,CAAC,KAAK,EAAyB,EAAE,CAAC,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,KAAK,IAAI,CAC9E,CAAC;IAEF,MAAM,sBAAsB,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,GAAG,EAAE,EAAE;QAC3D,OAAO,KAAK,GAAG,OAAO,CAAU,GAAG,CAAC,mBAAmB,CAAC,CAAC,MAAM,CAAC;IAClE,CAAC,EAAE,CAAC,CAAC,CAAC;IACN,MAAM,sBAAsB,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,GAAG,EAAE,EAAE;QAC3D,OAAO,KAAK,GAAG,OAAO,CAAU,GAAG,CAAC,mBAAmB,CAAC,CAAC,MAAM,CAAC;IAClE,CAAC,EAAE,CAAC,CAAC,CAAC;IACN,MAAM,aAAa,GAAG,KAAK,CAAC,IAAI,CAC9B,IAAI,GAAG,CACL,OAAO;SACJ,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,aAAa,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;SACpD,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,CACrC,CACF,CAAC;IAEF,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC;IAChC,MAAM,gBAAgB,GAAG,OAAO,CAAU,MAAM,CAAC,eAAe,CAAC,CAAC,CAAC,MAAM,CAAC;IAE1E,MAAM,KAAK,GAAG,MAAM,CAAC,MAAM,CAAC,QAAQ,IAAI,GAAG,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;IACxE,MAAM,EAAE,GAAG,GAAG,KAAK,IAAI,KAAK,EAAE,CAAC;IAC/B,MAAM,KAAK,GAAG,aAAa,KAAK,UAAU,KAAK,EAAE,CAAC;IAElD,MAAM,eAAe,GACnB,QAAQ,GAAG,EAAE;QACb,sBAAsB,GAAG,CAAC;QAC1B,sBAAsB;QACtB,gBAAgB,GAAG,CAAC;QACpB,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,GAAG,EAAE,CAAC,CAAC;IAE/B,OAAO;QACL,EAAE;QACF,KAAK;QACL,MAAM,EAAE,KAAK;QACb,KAAK;QACL,QAAQ;QACR,gBAAgB;QAChB,sBAAsB;QACtB,sBAAsB;QACtB,aAAa;QACb,eAAe;KAChB,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,WAAW,CAAC,KAAkB,EAAE,GAAW;IACxD,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,CAAC,CAAC;IAClC,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;QACjB,MAAM,IAAI,KAAK,CAAC,mBAAmB,KAAK,aAAa,QAAQ,CAAC,MAAM,IAAI,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAC;IACjG,CAAC;IAED,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,IAAI,EAAE,CAAC;IAClC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC;QACxB,MAAM,IAAI,KAAK,CAAC,0BAA0B,KAAK,kBAAkB,CAAC,CAAC;IACrE,CAAC;IAED,OAAO,GAA2B,CAAC;AACrC,CAAC;AAED,KAAK,UAAU,IAAI;IACjB,MAAM,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,WAAW,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC,CAAC;IACtD,MAAM,WAAW,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,WAAW,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,CAAC;IAC7D,MAAM,cAAc,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,WAAW,CAAC,oBAAoB,EAAE,GAAG,CAAC,CAAC,CAAC;IAE3E,MAAM,IAAI,GAAG,OAAO,CAAC,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;IACrD,MAAM,UAAU,GACd,MAAM,CAAC,UAAU,CAAC,IAAI,IAAI,CAAC,IAAI,EAAE,mCAAmC,CAAC,CAAC;IAExE,MAAM,OAAO,GAAG,MAAM,OAAO,CAAC,GAAG,CAC/B,OAAO,CAAC,GAAG,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE;QAC3B,MAAM,OAAO,GAAG,MAAM,WAAW,CAAC,MAAM,CAAC,KAAK,EAAE,MAAM,CAAC,GAAG,CAAC,CAAC;QAC5D,OAAO,EAAE,GAAG,MAAM,EAAE,OAAO,EAAE,CAAC;IAChC,CAAC,CAAC,CACH,CAAC;IAEF,MAAM,KAAK,GAAG,OAAO,CAAC,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,CACtC,KAAK,CAAC,OAAO;SACV,GAAG,CAAC,CAAC,MAAM,EAAE,KAAK,EAAE,EAAE,CAAC,MAAM,CAAC,MAAM,EAAE,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;SAC1D,MAAM,CAAC,CAAC,IAAI,EAAgC,EAAE,CAAC,IAAI,KAAK,IAAI,CAAC,CACjE,CAAC;IAEF,MAAM,UAAU,GAAG,KAAK;SACrB,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,QAAQ,IAAI,WAAW,IAAI,IAAI,CAAC,MAAM,CAAC,MAAM,IAAI,cAAc,CAAC;SACtF,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE;QACb,IAAI,CAAC,CAAC,eAAe,KAAK,CAAC,CAAC,eAAe;YAAE,OAAO,CAAC,CAAC,eAAe,GAAG,CAAC,CAAC,eAAe,CAAC;QAC1F,OAAO,CAAC,CAAC,EAAE,CAAC,aAAa,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;IAClC,CAAC,CAAC,CAAC;IAEL,MAAM,QAAQ,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC;IAC5C,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC1B,MAAM,IAAI,KAAK,CACb,mDAAmD,WAAW,oBAAoB,cAAc,IAAI,CACrG,CAAC;IACJ,CAAC;IAED,MAAM,UAAU,GAAG,OAAO,CAAC,MAAM,CAC/B,CAAC,GAAG,EAAE,MAAM,EAAE,EAAE;QACd,GAAG,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,MAAM,CAAC,GAAG,CAAC;QAC/B,OAAO,GAAG,CAAC;IACb,CAAC,EACD,EAAiC,CAClC,CAAC;IAEF,MAAM,OAAO,GAAqB;QAChC,OAAO,EAAE,mBAAmB;QAC5B,KAAK,EAAE,qCAAqC;QAC5C,UAAU;QACV,WAAW,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACrC,SAAS,EAAE;YACT,cAAc,EAAE,KAAK;YACrB,WAAW;YACX,cAAc;YACd,YAAY,EAAE,KAAK,CAAC,MAAM;YAC1B,gBAAgB,EAAE,UAAU,CAAC,MAAM;SACpC;QACD,KAAK,EAAE,QAAQ;KAChB,CAAC;IAEF,SAAS,CAAC,OAAO,CAAC,UAAU,CAAC,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IACpD,aAAa,CAAC,UAAU,EAAE,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,GAAG,IAAI,EAAE,MAAM,CAAC,CAAC;IAE3E,OAAO,CAAC,GAAG,CAAC,6BAA6B,QAAQ,CAAC,MAAM,aAAa,UAAU,EAAE,CAAC,CAAC;IACnF,OAAO,CAAC,GAAG,CACT,6BAA6B,KAAK,CAAC,MAAM,gBAAgB,UAAU,CAAC,MAAM,kBAAkB,WAAW,kBAAkB,cAAc,EAAE,CAC1I,CAAC;AACJ,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,KAAK,EAAE,EAAE;IACrB,MAAM,OAAO,GAAG,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,IAAI,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;IACtF,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,OAAO,IAAI,CAAC,CAAC;IACrC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC"}