@opensearch-project/agent-health 0.3.0 → 0.5.2

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 (518) hide show
  1. package/README.md +77 -6
  2. package/cli/dist/index.js +10072 -4502
  3. package/deployment/cloudformation/agent-health-observability.yaml +762 -0
  4. package/dist/assets/index-CCQRDlO0.js +243 -0
  5. package/dist/assets/index-CNHQVbcj.css +1 -0
  6. package/dist/index.html +2 -2
  7. package/docs/ARCHITECTURE.md +450 -0
  8. package/docs/BACKEND_JOB_QUEUE.md +405 -0
  9. package/docs/CLAUDE_CODE_TELEMETRY.md +283 -0
  10. package/docs/CLI.md +431 -0
  11. package/docs/CODING_AGENT_ANALYTICS.md +298 -0
  12. package/docs/CONFIGURATION.md +388 -0
  13. package/docs/CONNECTORS.md +536 -0
  14. package/docs/INSTRUMENT_WITH_OTEL.md +390 -0
  15. package/docs/ML-COMMONS-SETUP.md +289 -0
  16. package/docs/NPX_PACKAGING.md +195 -0
  17. package/docs/PERFORMANCE-MONITORING.md +200 -0
  18. package/docs/PERFORMANCE.md +390 -0
  19. package/docs/PI_PROFILING.md +169 -0
  20. package/docs/PLAN-non-agui-agent-support.md +525 -0
  21. package/docs/SDK.md +577 -0
  22. package/docs/SKILLS.md +264 -0
  23. package/docs/blogs/2026-02-28-opensearch-agent-health.md +200 -0
  24. package/docs/blogs/getting-started-blog.md +608 -0
  25. package/docs/diagrams/Agent-health.excalidraw +5656 -0
  26. package/docs/diagrams/architecture.png +0 -0
  27. package/docs/plans/field-redesign.md +468 -0
  28. package/docs/rfcs/001-coding-agent-analytics.md +374 -0
  29. package/docs/rfcs/002-enterprise-leaderboard.md +267 -0
  30. package/docs/rfcs/003-remote-aggregation.md +146 -0
  31. package/docs/rfcs/004-test-sdk-v2.md +599 -0
  32. package/docs/skills/AGENT_HEALTH.md +598 -0
  33. package/docs/skills/AGENT_PROFILE.md +191 -0
  34. package/docs/skills/add-connector/SKILL.md +68 -0
  35. package/docs/skills/agent-health-profile/SKILL.md +40 -0
  36. package/docs/skills/config-auth/SKILL.md +194 -0
  37. package/docs/skills/config-auth/evals/evals.json +35 -0
  38. package/docs/skills/create-pr/SKILL.md +73 -0
  39. package/docs/skills/instrument-otel/SKILL.md +84 -0
  40. package/docs/skills/write-test/SKILL.md +124 -0
  41. package/docs/ui prd.md +376 -0
  42. package/examples/README.md +53 -0
  43. package/examples/config/agent-health.config.example.ts +155 -0
  44. package/examples/connectors/echo-connector.ts +131 -0
  45. package/examples/eval-files/demo.eval.js +128 -0
  46. package/examples/eval-files/sdk-hooks-demo.eval.js +99 -0
  47. package/examples/pi-profiling/README.md +77 -0
  48. package/examples/pi-profiling/agent-health-profile.ts +417 -0
  49. package/lib/dist/lib/agentUtils.d.ts +29 -0
  50. package/lib/dist/lib/agentUtils.d.ts.map +1 -0
  51. package/lib/dist/lib/agentUtils.js +43 -0
  52. package/lib/dist/lib/agentUtils.js.map +1 -0
  53. package/lib/dist/lib/benchmarkExport.d.ts +14 -0
  54. package/lib/dist/lib/benchmarkExport.d.ts.map +1 -0
  55. package/lib/dist/lib/benchmarkExport.js +41 -0
  56. package/lib/dist/lib/benchmarkExport.js.map +1 -0
  57. package/lib/dist/lib/benchmarkVersionUtils.d.ts +37 -0
  58. package/lib/dist/lib/benchmarkVersionUtils.d.ts.map +1 -0
  59. package/lib/dist/lib/benchmarkVersionUtils.js +68 -0
  60. package/lib/dist/lib/benchmarkVersionUtils.js.map +1 -0
  61. package/lib/dist/lib/config/defineConfig.d.ts +27 -0
  62. package/lib/dist/lib/config/defineConfig.d.ts.map +1 -0
  63. package/lib/dist/lib/config/defineConfig.js +28 -0
  64. package/lib/dist/lib/config/defineConfig.js.map +1 -0
  65. package/lib/dist/lib/config/index.d.ts +9 -0
  66. package/lib/dist/lib/config/index.d.ts.map +1 -0
  67. package/lib/dist/lib/config/index.js +8 -0
  68. package/lib/dist/lib/config/index.js.map +1 -0
  69. package/lib/dist/lib/config/loader.d.ts +39 -0
  70. package/lib/dist/lib/config/loader.d.ts.map +1 -0
  71. package/lib/dist/lib/config/loader.js +258 -0
  72. package/lib/dist/lib/config/loader.js.map +1 -0
  73. package/lib/dist/lib/config/statePaths.d.ts +61 -0
  74. package/lib/dist/lib/config/statePaths.d.ts.map +1 -0
  75. package/lib/dist/lib/config/statePaths.js +188 -0
  76. package/lib/dist/lib/config/statePaths.js.map +1 -0
  77. package/lib/dist/lib/config/types.d.ts +231 -0
  78. package/lib/dist/lib/config/types.d.ts.map +1 -0
  79. package/lib/dist/lib/config/types.js +6 -0
  80. package/lib/dist/lib/config/types.js.map +1 -0
  81. package/lib/dist/lib/config.d.ts +39 -0
  82. package/lib/dist/lib/config.d.ts.map +1 -0
  83. package/lib/dist/lib/config.js +118 -0
  84. package/lib/dist/lib/config.js.map +1 -0
  85. package/lib/dist/lib/constants.d.ts +70 -0
  86. package/lib/dist/lib/constants.d.ts.map +1 -0
  87. package/lib/dist/lib/constants.js +365 -0
  88. package/lib/dist/lib/constants.js.map +1 -0
  89. package/lib/dist/lib/contextUtilization.d.ts +23 -0
  90. package/lib/dist/lib/contextUtilization.d.ts.map +1 -0
  91. package/lib/dist/lib/contextUtilization.js +72 -0
  92. package/lib/dist/lib/contextUtilization.js.map +1 -0
  93. package/lib/dist/lib/dashboardMetrics.d.ts +87 -0
  94. package/lib/dist/lib/dashboardMetrics.d.ts.map +1 -0
  95. package/lib/dist/lib/dashboardMetrics.js +242 -0
  96. package/lib/dist/lib/dashboardMetrics.js.map +1 -0
  97. package/lib/dist/lib/dataSourceConfig.d.ts +108 -0
  98. package/lib/dist/lib/dataSourceConfig.d.ts.map +1 -0
  99. package/lib/dist/lib/dataSourceConfig.js +166 -0
  100. package/lib/dist/lib/dataSourceConfig.js.map +1 -0
  101. package/lib/dist/lib/debug.d.ts +26 -0
  102. package/lib/dist/lib/debug.d.ts.map +1 -0
  103. package/lib/dist/lib/debug.js +132 -0
  104. package/lib/dist/lib/debug.js.map +1 -0
  105. package/lib/dist/lib/diagnostics.d.ts +28 -0
  106. package/lib/dist/lib/diagnostics.d.ts.map +1 -0
  107. package/lib/dist/lib/diagnostics.js +65 -0
  108. package/lib/dist/lib/diagnostics.js.map +1 -0
  109. package/lib/dist/lib/envCompat.d.ts +27 -0
  110. package/lib/dist/lib/envCompat.d.ts.map +1 -0
  111. package/lib/dist/lib/envCompat.js +73 -0
  112. package/lib/dist/lib/envCompat.js.map +1 -0
  113. package/lib/dist/lib/findPackageRoot.d.ts +7 -0
  114. package/lib/dist/lib/findPackageRoot.d.ts.map +1 -0
  115. package/lib/dist/lib/findPackageRoot.js +57 -0
  116. package/lib/dist/lib/findPackageRoot.js.map +1 -0
  117. package/lib/dist/lib/hooks.d.ts +36 -0
  118. package/lib/dist/lib/hooks.d.ts.map +1 -0
  119. package/lib/dist/lib/hooks.js +112 -0
  120. package/lib/dist/lib/hooks.js.map +1 -0
  121. package/lib/dist/lib/index.d.ts +47 -0
  122. package/lib/dist/lib/index.d.ts.map +1 -0
  123. package/lib/dist/lib/index.js +62 -0
  124. package/lib/dist/lib/index.js.map +1 -0
  125. package/lib/dist/lib/labels.d.ts +90 -0
  126. package/lib/dist/lib/labels.d.ts.map +1 -0
  127. package/lib/dist/lib/labels.js +158 -0
  128. package/lib/dist/lib/labels.js.map +1 -0
  129. package/lib/dist/lib/markdown.d.ts +16 -0
  130. package/lib/dist/lib/markdown.d.ts.map +1 -0
  131. package/lib/dist/lib/markdown.js +42 -0
  132. package/lib/dist/lib/markdown.js.map +1 -0
  133. package/lib/dist/lib/matchers/expect.d.ts +3 -0
  134. package/lib/dist/lib/matchers/expect.d.ts.map +1 -0
  135. package/lib/dist/lib/matchers/expect.js +225 -0
  136. package/lib/dist/lib/matchers/expect.js.map +1 -0
  137. package/lib/dist/lib/matchers/index.d.ts +8 -0
  138. package/lib/dist/lib/matchers/index.d.ts.map +1 -0
  139. package/lib/dist/lib/matchers/index.js +9 -0
  140. package/lib/dist/lib/matchers/index.js.map +1 -0
  141. package/lib/dist/lib/matchers/judgeAccessor.d.ts +113 -0
  142. package/lib/dist/lib/matchers/judgeAccessor.d.ts.map +1 -0
  143. package/lib/dist/lib/matchers/judgeAccessor.js +183 -0
  144. package/lib/dist/lib/matchers/judgeAccessor.js.map +1 -0
  145. package/lib/dist/lib/matchers/session.d.ts +39 -0
  146. package/lib/dist/lib/matchers/session.d.ts.map +1 -0
  147. package/lib/dist/lib/matchers/session.js +116 -0
  148. package/lib/dist/lib/matchers/session.js.map +1 -0
  149. package/lib/dist/lib/matchers/traces.d.ts +55 -0
  150. package/lib/dist/lib/matchers/traces.d.ts.map +1 -0
  151. package/lib/dist/lib/matchers/traces.js +116 -0
  152. package/lib/dist/lib/matchers/traces.js.map +1 -0
  153. package/lib/dist/lib/matchers/types.d.ts +75 -0
  154. package/lib/dist/lib/matchers/types.d.ts.map +1 -0
  155. package/lib/dist/lib/matchers/types.js +6 -0
  156. package/lib/dist/lib/matchers/types.js.map +1 -0
  157. package/lib/dist/lib/packagePaths.d.ts +29 -0
  158. package/lib/dist/lib/packagePaths.d.ts.map +1 -0
  159. package/lib/dist/lib/packagePaths.js +63 -0
  160. package/lib/dist/lib/packagePaths.js.map +1 -0
  161. package/lib/dist/lib/performance.d.ts +51 -0
  162. package/lib/dist/lib/performance.d.ts.map +1 -0
  163. package/lib/dist/lib/performance.js +159 -0
  164. package/lib/dist/lib/performance.js.map +1 -0
  165. package/lib/dist/lib/portConfig.d.ts +29 -0
  166. package/lib/dist/lib/portConfig.d.ts.map +1 -0
  167. package/lib/dist/lib/portConfig.js +64 -0
  168. package/lib/dist/lib/portConfig.js.map +1 -0
  169. package/lib/dist/lib/preferences.d.ts +63 -0
  170. package/lib/dist/lib/preferences.d.ts.map +1 -0
  171. package/lib/dist/lib/preferences.js +117 -0
  172. package/lib/dist/lib/preferences.js.map +1 -0
  173. package/lib/dist/lib/resolveAgentModel.d.ts +22 -0
  174. package/lib/dist/lib/resolveAgentModel.d.ts.map +1 -0
  175. package/lib/dist/lib/resolveAgentModel.js +37 -0
  176. package/lib/dist/lib/resolveAgentModel.js.map +1 -0
  177. package/lib/dist/lib/runStats.d.ts +92 -0
  178. package/lib/dist/lib/runStats.d.ts.map +1 -0
  179. package/lib/dist/lib/runStats.js +160 -0
  180. package/lib/dist/lib/runStats.js.map +1 -0
  181. package/lib/dist/lib/telemetry/constants.d.ts +60 -0
  182. package/lib/dist/lib/telemetry/constants.d.ts.map +1 -0
  183. package/lib/dist/lib/telemetry/constants.js +87 -0
  184. package/lib/dist/lib/telemetry/constants.js.map +1 -0
  185. package/lib/dist/lib/telemetry/evalSpans.d.ts +61 -0
  186. package/lib/dist/lib/telemetry/evalSpans.d.ts.map +1 -0
  187. package/lib/dist/lib/telemetry/evalSpans.js +254 -0
  188. package/lib/dist/lib/telemetry/evalSpans.js.map +1 -0
  189. package/lib/dist/lib/telemetry/index.d.ts +11 -0
  190. package/lib/dist/lib/telemetry/index.d.ts.map +1 -0
  191. package/lib/dist/lib/telemetry/index.js +15 -0
  192. package/lib/dist/lib/telemetry/index.js.map +1 -0
  193. package/lib/dist/lib/telemetry/opensearchExporter.d.ts +43 -0
  194. package/lib/dist/lib/telemetry/opensearchExporter.d.ts.map +1 -0
  195. package/lib/dist/lib/telemetry/opensearchExporter.js +217 -0
  196. package/lib/dist/lib/telemetry/opensearchExporter.js.map +1 -0
  197. package/lib/dist/lib/telemetry/provider.d.ts +55 -0
  198. package/lib/dist/lib/telemetry/provider.d.ts.map +1 -0
  199. package/lib/dist/lib/telemetry/provider.js +140 -0
  200. package/lib/dist/lib/telemetry/provider.js.map +1 -0
  201. package/lib/dist/lib/testCaseLabels.d.ts +34 -0
  202. package/lib/dist/lib/testCaseLabels.d.ts.map +1 -0
  203. package/lib/dist/lib/testCaseLabels.js +88 -0
  204. package/lib/dist/lib/testCaseLabels.js.map +1 -0
  205. package/lib/dist/lib/testCaseValidation.d.ts +140 -0
  206. package/lib/dist/lib/testCaseValidation.d.ts.map +1 -0
  207. package/lib/dist/lib/testCaseValidation.js +162 -0
  208. package/lib/dist/lib/testCaseValidation.js.map +1 -0
  209. package/lib/dist/lib/testCases/agentFixture.d.ts +80 -0
  210. package/lib/dist/lib/testCases/agentFixture.d.ts.map +1 -0
  211. package/lib/dist/lib/testCases/agentFixture.js +43 -0
  212. package/lib/dist/lib/testCases/agentFixture.js.map +1 -0
  213. package/lib/dist/lib/testCases/authoringSurface.d.ts +10 -0
  214. package/lib/dist/lib/testCases/authoringSurface.d.ts.map +1 -0
  215. package/lib/dist/lib/testCases/authoringSurface.js +54 -0
  216. package/lib/dist/lib/testCases/authoringSurface.js.map +1 -0
  217. package/lib/dist/lib/testCases/codemod.d.ts +13 -0
  218. package/lib/dist/lib/testCases/codemod.d.ts.map +1 -0
  219. package/lib/dist/lib/testCases/codemod.js +169 -0
  220. package/lib/dist/lib/testCases/codemod.js.map +1 -0
  221. package/lib/dist/lib/testCases/define.d.ts +114 -0
  222. package/lib/dist/lib/testCases/define.d.ts.map +1 -0
  223. package/lib/dist/lib/testCases/define.js +253 -0
  224. package/lib/dist/lib/testCases/define.js.map +1 -0
  225. package/lib/dist/lib/testCases/evaluators.d.ts +80 -0
  226. package/lib/dist/lib/testCases/evaluators.d.ts.map +1 -0
  227. package/lib/dist/lib/testCases/evaluators.js +105 -0
  228. package/lib/dist/lib/testCases/evaluators.js.map +1 -0
  229. package/lib/dist/lib/testCases/index.d.ts +14 -0
  230. package/lib/dist/lib/testCases/index.d.ts.map +1 -0
  231. package/lib/dist/lib/testCases/index.js +12 -0
  232. package/lib/dist/lib/testCases/index.js.map +1 -0
  233. package/lib/dist/lib/testCases/judge.d.ts +165 -0
  234. package/lib/dist/lib/testCases/judge.d.ts.map +1 -0
  235. package/lib/dist/lib/testCases/judge.js +359 -0
  236. package/lib/dist/lib/testCases/judge.js.map +1 -0
  237. package/lib/dist/lib/testCases/loader.d.ts +26 -0
  238. package/lib/dist/lib/testCases/loader.d.ts.map +1 -0
  239. package/lib/dist/lib/testCases/loader.js +149 -0
  240. package/lib/dist/lib/testCases/loader.js.map +1 -0
  241. package/lib/dist/lib/testCases/types.d.ts +242 -0
  242. package/lib/dist/lib/testCases/types.d.ts.map +1 -0
  243. package/lib/dist/lib/testCases/types.js +6 -0
  244. package/lib/dist/lib/testCases/types.js.map +1 -0
  245. package/lib/dist/lib/theme.d.ts +6 -0
  246. package/lib/dist/lib/theme.d.ts.map +1 -0
  247. package/lib/dist/lib/theme.js +36 -0
  248. package/lib/dist/lib/theme.js.map +1 -0
  249. package/lib/dist/lib/uiTelemetry.d.ts +7 -0
  250. package/lib/dist/lib/uiTelemetry.d.ts.map +1 -0
  251. package/lib/dist/lib/uiTelemetry.js +25 -0
  252. package/lib/dist/lib/uiTelemetry.js.map +1 -0
  253. package/lib/dist/lib/utils.d.ts +96 -0
  254. package/lib/dist/lib/utils.d.ts.map +1 -0
  255. package/lib/dist/lib/utils.js +232 -0
  256. package/lib/dist/lib/utils.js.map +1 -0
  257. package/lib/dist/lib/workflow/consolidate.d.ts +12 -0
  258. package/lib/dist/lib/workflow/consolidate.d.ts.map +1 -0
  259. package/lib/dist/lib/workflow/consolidate.js +33 -0
  260. package/lib/dist/lib/workflow/consolidate.js.map +1 -0
  261. package/lib/dist/lib/workflow/index.d.ts +13 -0
  262. package/lib/dist/lib/workflow/index.d.ts.map +1 -0
  263. package/lib/dist/lib/workflow/index.js +12 -0
  264. package/lib/dist/lib/workflow/index.js.map +1 -0
  265. package/lib/dist/lib/workflow/ledger.d.ts +30 -0
  266. package/lib/dist/lib/workflow/ledger.d.ts.map +1 -0
  267. package/lib/dist/lib/workflow/ledger.js +41 -0
  268. package/lib/dist/lib/workflow/ledger.js.map +1 -0
  269. package/lib/dist/lib/workflow/pool.d.ts +13 -0
  270. package/lib/dist/lib/workflow/pool.d.ts.map +1 -0
  271. package/lib/dist/lib/workflow/pool.js +44 -0
  272. package/lib/dist/lib/workflow/pool.js.map +1 -0
  273. package/lib/dist/lib/workflow/source.d.ts +22 -0
  274. package/lib/dist/lib/workflow/source.d.ts.map +1 -0
  275. package/lib/dist/lib/workflow/source.js +29 -0
  276. package/lib/dist/lib/workflow/source.js.map +1 -0
  277. package/lib/dist/lib/workflow/stepB.d.ts +71 -0
  278. package/lib/dist/lib/workflow/stepB.d.ts.map +1 -0
  279. package/lib/dist/lib/workflow/stepB.js +99 -0
  280. package/lib/dist/lib/workflow/stepB.js.map +1 -0
  281. package/lib/dist/lib/workflow/types.d.ts +86 -0
  282. package/lib/dist/lib/workflow/types.d.ts.map +1 -0
  283. package/lib/dist/lib/workflow/types.js +6 -0
  284. package/lib/dist/lib/workflow/types.js.map +1 -0
  285. package/lib/dist/lib/workflow/workflow.d.ts +119 -0
  286. package/lib/dist/lib/workflow/workflow.d.ts.map +1 -0
  287. package/lib/dist/lib/workflow/workflow.js +195 -0
  288. package/lib/dist/lib/workflow/workflow.js.map +1 -0
  289. package/lib/dist/services/agent/aguiConverter.d.ts +50 -0
  290. package/lib/dist/services/agent/aguiConverter.d.ts.map +1 -0
  291. package/lib/dist/services/agent/aguiConverter.js +449 -0
  292. package/lib/dist/services/agent/aguiConverter.js.map +1 -0
  293. package/lib/dist/services/agent/index.d.ts +10 -0
  294. package/lib/dist/services/agent/index.d.ts.map +1 -0
  295. package/lib/dist/services/agent/index.js +12 -0
  296. package/lib/dist/services/agent/index.js.map +1 -0
  297. package/lib/dist/services/agent/payloadBuilder.d.ts +33 -0
  298. package/lib/dist/services/agent/payloadBuilder.d.ts.map +1 -0
  299. package/lib/dist/services/agent/payloadBuilder.js +75 -0
  300. package/lib/dist/services/agent/payloadBuilder.js.map +1 -0
  301. package/lib/dist/services/agent/sseStream.d.ts +43 -0
  302. package/lib/dist/services/agent/sseStream.d.ts.map +1 -0
  303. package/lib/dist/services/agent/sseStream.js +223 -0
  304. package/lib/dist/services/agent/sseStream.js.map +1 -0
  305. package/lib/dist/services/connectors/agui/AGUIStreamingConnector.d.ts +44 -0
  306. package/lib/dist/services/connectors/agui/AGUIStreamingConnector.d.ts.map +1 -0
  307. package/lib/dist/services/connectors/agui/AGUIStreamingConnector.js +95 -0
  308. package/lib/dist/services/connectors/agui/AGUIStreamingConnector.js.map +1 -0
  309. package/lib/dist/services/connectors/base/BaseConnector.d.ts +81 -0
  310. package/lib/dist/services/connectors/base/BaseConnector.d.ts.map +1 -0
  311. package/lib/dist/services/connectors/base/BaseConnector.js +170 -0
  312. package/lib/dist/services/connectors/base/BaseConnector.js.map +1 -0
  313. package/lib/dist/services/connectors/claude-code/ClaudeCodeConnector.d.ts +116 -0
  314. package/lib/dist/services/connectors/claude-code/ClaudeCodeConnector.d.ts.map +1 -0
  315. package/lib/dist/services/connectors/claude-code/ClaudeCodeConnector.js +403 -0
  316. package/lib/dist/services/connectors/claude-code/ClaudeCodeConnector.js.map +1 -0
  317. package/lib/dist/services/connectors/index.d.ts +13 -0
  318. package/lib/dist/services/connectors/index.d.ts.map +1 -0
  319. package/lib/dist/services/connectors/index.js +32 -0
  320. package/lib/dist/services/connectors/index.js.map +1 -0
  321. package/lib/dist/services/connectors/kiro/KiroConnector.d.ts +48 -0
  322. package/lib/dist/services/connectors/kiro/KiroConnector.d.ts.map +1 -0
  323. package/lib/dist/services/connectors/kiro/KiroConnector.js +158 -0
  324. package/lib/dist/services/connectors/kiro/KiroConnector.js.map +1 -0
  325. package/lib/dist/services/connectors/langgraph/LangGraphConnector.d.ts +36 -0
  326. package/lib/dist/services/connectors/langgraph/LangGraphConnector.d.ts.map +1 -0
  327. package/lib/dist/services/connectors/langgraph/LangGraphConnector.js +175 -0
  328. package/lib/dist/services/connectors/langgraph/LangGraphConnector.js.map +1 -0
  329. package/lib/dist/services/connectors/mock/MockConnector.d.ts +37 -0
  330. package/lib/dist/services/connectors/mock/MockConnector.d.ts.map +1 -0
  331. package/lib/dist/services/connectors/mock/MockConnector.js +120 -0
  332. package/lib/dist/services/connectors/mock/MockConnector.js.map +1 -0
  333. package/lib/dist/services/connectors/openai-compatible/OpenAICompatibleConnector.d.ts +42 -0
  334. package/lib/dist/services/connectors/openai-compatible/OpenAICompatibleConnector.d.ts.map +1 -0
  335. package/lib/dist/services/connectors/openai-compatible/OpenAICompatibleConnector.js +133 -0
  336. package/lib/dist/services/connectors/openai-compatible/OpenAICompatibleConnector.js.map +1 -0
  337. package/lib/dist/services/connectors/pi/PiConnector.d.ts +87 -0
  338. package/lib/dist/services/connectors/pi/PiConnector.d.ts.map +1 -0
  339. package/lib/dist/services/connectors/pi/PiConnector.js +274 -0
  340. package/lib/dist/services/connectors/pi/PiConnector.js.map +1 -0
  341. package/lib/dist/services/connectors/registry.d.ts +57 -0
  342. package/lib/dist/services/connectors/registry.d.ts.map +1 -0
  343. package/lib/dist/services/connectors/registry.js +106 -0
  344. package/lib/dist/services/connectors/registry.js.map +1 -0
  345. package/lib/dist/services/connectors/rest/RESTConnector.d.ts +38 -0
  346. package/lib/dist/services/connectors/rest/RESTConnector.d.ts.map +1 -0
  347. package/lib/dist/services/connectors/rest/RESTConnector.js +117 -0
  348. package/lib/dist/services/connectors/rest/RESTConnector.js.map +1 -0
  349. package/lib/dist/services/connectors/server.d.ts +13 -0
  350. package/lib/dist/services/connectors/server.d.ts.map +1 -0
  351. package/lib/dist/services/connectors/server.js +34 -0
  352. package/lib/dist/services/connectors/server.js.map +1 -0
  353. package/lib/dist/services/connectors/strands/StrandsConnector.d.ts +48 -0
  354. package/lib/dist/services/connectors/strands/StrandsConnector.d.ts.map +1 -0
  355. package/lib/dist/services/connectors/strands/StrandsConnector.js +221 -0
  356. package/lib/dist/services/connectors/strands/StrandsConnector.js.map +1 -0
  357. package/lib/dist/services/connectors/subprocess/SubprocessConnector.d.ts +88 -0
  358. package/lib/dist/services/connectors/subprocess/SubprocessConnector.d.ts.map +1 -0
  359. package/lib/dist/services/connectors/subprocess/SubprocessConnector.js +418 -0
  360. package/lib/dist/services/connectors/subprocess/SubprocessConnector.js.map +1 -0
  361. package/lib/dist/services/connectors/types.d.ts +213 -0
  362. package/lib/dist/services/connectors/types.d.ts.map +1 -0
  363. package/lib/dist/services/connectors/types.js +6 -0
  364. package/lib/dist/services/connectors/types.js.map +1 -0
  365. package/lib/dist/services/evaluation/bedrockJudge.d.ts +64 -0
  366. package/lib/dist/services/evaluation/bedrockJudge.d.ts.map +1 -0
  367. package/lib/dist/services/evaluation/bedrockJudge.js +167 -0
  368. package/lib/dist/services/evaluation/bedrockJudge.js.map +1 -0
  369. package/lib/dist/services/evaluation/evaluatorError.d.ts +56 -0
  370. package/lib/dist/services/evaluation/evaluatorError.d.ts.map +1 -0
  371. package/lib/dist/services/evaluation/evaluatorError.js +56 -0
  372. package/lib/dist/services/evaluation/evaluatorError.js.map +1 -0
  373. package/lib/dist/services/evaluation/index.d.ts +106 -0
  374. package/lib/dist/services/evaluation/index.d.ts.map +1 -0
  375. package/lib/dist/services/evaluation/index.js +684 -0
  376. package/lib/dist/services/evaluation/index.js.map +1 -0
  377. package/lib/dist/services/evaluation/mockTrajectory.d.ts +3 -0
  378. package/lib/dist/services/evaluation/mockTrajectory.d.ts.map +1 -0
  379. package/lib/dist/services/evaluation/mockTrajectory.js +72 -0
  380. package/lib/dist/services/evaluation/mockTrajectory.js.map +1 -0
  381. package/lib/dist/services/opensearch/client.d.ts +26 -0
  382. package/lib/dist/services/opensearch/client.d.ts.map +1 -0
  383. package/lib/dist/services/opensearch/client.js +131 -0
  384. package/lib/dist/services/opensearch/client.js.map +1 -0
  385. package/lib/dist/services/opensearch/index.d.ts +16 -0
  386. package/lib/dist/services/opensearch/index.d.ts.map +1 -0
  387. package/lib/dist/services/opensearch/index.js +25 -0
  388. package/lib/dist/services/opensearch/index.js.map +1 -0
  389. package/lib/dist/services/storage/asyncBenchmarkStorage.d.ts +123 -0
  390. package/lib/dist/services/storage/asyncBenchmarkStorage.d.ts.map +1 -0
  391. package/lib/dist/services/storage/asyncBenchmarkStorage.js +429 -0
  392. package/lib/dist/services/storage/asyncBenchmarkStorage.js.map +1 -0
  393. package/lib/dist/services/storage/asyncRunStorage.d.ts +127 -0
  394. package/lib/dist/services/storage/asyncRunStorage.d.ts.map +1 -0
  395. package/lib/dist/services/storage/asyncRunStorage.js +448 -0
  396. package/lib/dist/services/storage/asyncRunStorage.js.map +1 -0
  397. package/lib/dist/services/storage/asyncTestCaseStorage.d.ts +156 -0
  398. package/lib/dist/services/storage/asyncTestCaseStorage.d.ts.map +1 -0
  399. package/lib/dist/services/storage/asyncTestCaseStorage.js +285 -0
  400. package/lib/dist/services/storage/asyncTestCaseStorage.js.map +1 -0
  401. package/lib/dist/services/storage/index.d.ts +17 -0
  402. package/lib/dist/services/storage/index.d.ts.map +1 -0
  403. package/lib/dist/services/storage/index.js +20 -0
  404. package/lib/dist/services/storage/index.js.map +1 -0
  405. package/lib/dist/services/storage/migration.d.ts +54 -0
  406. package/lib/dist/services/storage/migration.d.ts.map +1 -0
  407. package/lib/dist/services/storage/migration.js +296 -0
  408. package/lib/dist/services/storage/migration.js.map +1 -0
  409. package/lib/dist/services/storage/opensearchClient.d.ts +924 -0
  410. package/lib/dist/services/storage/opensearchClient.d.ts.map +1 -0
  411. package/lib/dist/services/storage/opensearchClient.js +435 -0
  412. package/lib/dist/services/storage/opensearchClient.js.map +1 -0
  413. package/lib/dist/services/traces/browserRecovery.d.ts +26 -0
  414. package/lib/dist/services/traces/browserRecovery.d.ts.map +1 -0
  415. package/lib/dist/services/traces/browserRecovery.js +81 -0
  416. package/lib/dist/services/traces/browserRecovery.js.map +1 -0
  417. package/lib/dist/services/traces/categoryStyles.d.ts +21 -0
  418. package/lib/dist/services/traces/categoryStyles.d.ts.map +1 -0
  419. package/lib/dist/services/traces/categoryStyles.js +56 -0
  420. package/lib/dist/services/traces/categoryStyles.js.map +1 -0
  421. package/lib/dist/services/traces/executionOrderTransform.d.ts +35 -0
  422. package/lib/dist/services/traces/executionOrderTransform.d.ts.map +1 -0
  423. package/lib/dist/services/traces/executionOrderTransform.js +313 -0
  424. package/lib/dist/services/traces/executionOrderTransform.js.map +1 -0
  425. package/lib/dist/services/traces/fetchSpansForRun.d.ts +86 -0
  426. package/lib/dist/services/traces/fetchSpansForRun.d.ts.map +1 -0
  427. package/lib/dist/services/traces/fetchSpansForRun.js +69 -0
  428. package/lib/dist/services/traces/fetchSpansForRun.js.map +1 -0
  429. package/lib/dist/services/traces/flowTransform.d.ts +24 -0
  430. package/lib/dist/services/traces/flowTransform.d.ts.map +1 -0
  431. package/lib/dist/services/traces/flowTransform.js +228 -0
  432. package/lib/dist/services/traces/flowTransform.js.map +1 -0
  433. package/lib/dist/services/traces/index.d.ts +121 -0
  434. package/lib/dist/services/traces/index.d.ts.map +1 -0
  435. package/lib/dist/services/traces/index.js +255 -0
  436. package/lib/dist/services/traces/index.js.map +1 -0
  437. package/lib/dist/services/traces/intentTransform.d.ts +20 -0
  438. package/lib/dist/services/traces/intentTransform.d.ts.map +1 -0
  439. package/lib/dist/services/traces/intentTransform.js +131 -0
  440. package/lib/dist/services/traces/intentTransform.js.map +1 -0
  441. package/lib/dist/services/traces/judgeAgentsHints.d.ts +63 -0
  442. package/lib/dist/services/traces/judgeAgentsHints.d.ts.map +1 -0
  443. package/lib/dist/services/traces/judgeAgentsHints.js +89 -0
  444. package/lib/dist/services/traces/judgeAgentsHints.js.map +1 -0
  445. package/lib/dist/services/traces/messageExtraction.d.ts +15 -0
  446. package/lib/dist/services/traces/messageExtraction.d.ts.map +1 -0
  447. package/lib/dist/services/traces/messageExtraction.js +251 -0
  448. package/lib/dist/services/traces/messageExtraction.js.map +1 -0
  449. package/lib/dist/services/traces/spanCategorization.d.ts +63 -0
  450. package/lib/dist/services/traces/spanCategorization.d.ts.map +1 -0
  451. package/lib/dist/services/traces/spanCategorization.js +276 -0
  452. package/lib/dist/services/traces/spanCategorization.js.map +1 -0
  453. package/lib/dist/services/traces/spanPreprocessing.d.ts +37 -0
  454. package/lib/dist/services/traces/spanPreprocessing.d.ts.map +1 -0
  455. package/lib/dist/services/traces/spanPreprocessing.js +102 -0
  456. package/lib/dist/services/traces/spanPreprocessing.js.map +1 -0
  457. package/lib/dist/services/traces/spansToTrajectory.d.ts +36 -0
  458. package/lib/dist/services/traces/spansToTrajectory.d.ts.map +1 -0
  459. package/lib/dist/services/traces/spansToTrajectory.js +387 -0
  460. package/lib/dist/services/traces/spansToTrajectory.js.map +1 -0
  461. package/lib/dist/services/traces/toolSimilarity.d.ts +35 -0
  462. package/lib/dist/services/traces/toolSimilarity.d.ts.map +1 -0
  463. package/lib/dist/services/traces/toolSimilarity.js +203 -0
  464. package/lib/dist/services/traces/toolSimilarity.js.map +1 -0
  465. package/lib/dist/services/traces/traceComparison.d.ts +31 -0
  466. package/lib/dist/services/traces/traceComparison.d.ts.map +1 -0
  467. package/lib/dist/services/traces/traceComparison.js +318 -0
  468. package/lib/dist/services/traces/traceComparison.js.map +1 -0
  469. package/lib/dist/services/traces/traceGrouping.d.ts +19 -0
  470. package/lib/dist/services/traces/traceGrouping.d.ts.map +1 -0
  471. package/lib/dist/services/traces/traceGrouping.js +107 -0
  472. package/lib/dist/services/traces/traceGrouping.js.map +1 -0
  473. package/lib/dist/services/traces/tracePoller.d.ts +84 -0
  474. package/lib/dist/services/traces/tracePoller.d.ts.map +1 -0
  475. package/lib/dist/services/traces/tracePoller.js +309 -0
  476. package/lib/dist/services/traces/tracePoller.js.map +1 -0
  477. package/lib/dist/services/traces/traceStats.d.ts +45 -0
  478. package/lib/dist/services/traces/traceStats.d.ts.map +1 -0
  479. package/lib/dist/services/traces/traceStats.js +114 -0
  480. package/lib/dist/services/traces/traceStats.js.map +1 -0
  481. package/lib/dist/services/traces/traceSummary.d.ts +47 -0
  482. package/lib/dist/services/traces/traceSummary.d.ts.map +1 -0
  483. package/lib/dist/services/traces/traceSummary.js +68 -0
  484. package/lib/dist/services/traces/traceSummary.js.map +1 -0
  485. package/lib/dist/services/traces/utils.d.ts +33 -0
  486. package/lib/dist/services/traces/utils.d.ts.map +1 -0
  487. package/lib/dist/services/traces/utils.js +114 -0
  488. package/lib/dist/services/traces/utils.js.map +1 -0
  489. package/lib/dist/types/agui.d.ts +13 -0
  490. package/lib/dist/types/agui.d.ts.map +1 -0
  491. package/lib/dist/types/agui.js +16 -0
  492. package/lib/dist/types/agui.js.map +1 -0
  493. package/lib/dist/types/index.d.ts +1175 -0
  494. package/lib/dist/types/index.d.ts.map +1 -0
  495. package/lib/dist/types/index.js +12 -0
  496. package/lib/dist/types/index.js.map +1 -0
  497. package/lib/dist/types/skills.d.ts +146 -0
  498. package/lib/dist/types/skills.d.ts.map +1 -0
  499. package/lib/dist/types/skills.js +6 -0
  500. package/lib/dist/types/skills.js.map +1 -0
  501. package/observio-sample-agent/pi-package/README.md +112 -0
  502. package/observio-sample-agent/pi-package/extensions/agent-health.ts +373 -0
  503. package/observio-sample-agent/pi-package/package.json +17 -0
  504. package/observio-sample-agent/pi-package/prompts/agent-health.md +37 -0
  505. package/observio-sample-agent/pi-package/skills/create-pr/SKILL.md +88 -0
  506. package/observio-sample-agent/pi-package/skills/fix-bug/SKILL.md +71 -0
  507. package/observio-sample-agent/pi-package/skills/implement-feature/SKILL.md +156 -0
  508. package/observio-sample-agent/pi-package/skills/instrument-otel/SKILL.md +208 -0
  509. package/observio-sample-agent/pi-package/skills/setup-collector/SKILL.md +146 -0
  510. package/observio-sample-agent/pi-package/skills/write-test/SKILL.md +115 -0
  511. package/package.json +64 -13
  512. package/server/dist/app.js +32651 -17637
  513. package/server/dist/index.js +29875 -14638
  514. package/tsconfig.lib.json +71 -0
  515. package/dist/assets/index-EvPLSTAS.js +0 -267
  516. package/dist/assets/index-RXasQKUs.css +0 -1
  517. package/lib/dist/config/index.js +0 -404
  518. package/lib/dist/index.js +0 -1665
@@ -0,0 +1 @@
1
+ {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../matchers/index.ts"],"names":[],"mappings":"AAKA,OAAO,EAAE,MAAM,EAAE,MAAM,aAAa,CAAC;AACrC,YAAY,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAClD,OAAO,EAAE,mBAAmB,EAAE,mBAAmB,EAAE,yBAAyB,EAAE,MAAM,aAAa,CAAC;AAClG,YAAY,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AAC/D,OAAO,EACL,sBAAsB,EACtB,qBAAqB,EACrB,wBAAwB,EACxB,sBAAsB,EACtB,6BAA6B,GAC9B,MAAM,oBAAoB,CAAC;AAC5B,YAAY,EAAE,iBAAiB,EAAE,eAAe,EAAE,MAAM,oBAAoB,CAAC;AAC7E,OAAO,EACL,YAAY,EACZ,UAAU,EACV,eAAe,EACf,aAAa,EACb,gBAAgB,EAChB,YAAY,GACb,MAAM,cAAc,CAAC"}
@@ -0,0 +1,9 @@
1
+ /*
2
+ * Copyright OpenSearch Contributors
3
+ * SPDX-License-Identifier: Apache-2.0
4
+ */
5
+ export { expect } from './expect.js';
6
+ export { buildTracesAccessor, emptyTracesAccessor, unavailableTracesAccessor } from './traces.js';
7
+ export { getJudgeMatcherResults, getJudgeReasoningText, recordJudgeMatcherResult, buildJudgeMatcherEntry, formatExpectedOutcomesAsClaim, } from './judgeAccessor.js';
8
+ export { startSession, endSession, isSessionActive, recordVerdict, recordWithTiming, runInSession, } from './session.js';
9
+ //# sourceMappingURL=index.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"index.js","sourceRoot":"","sources":["../../../matchers/index.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,EAAE,MAAM,EAAE,MAAM,aAAa,CAAC;AAErC,OAAO,EAAE,mBAAmB,EAAE,mBAAmB,EAAE,yBAAyB,EAAE,MAAM,aAAa,CAAC;AAElG,OAAO,EACL,sBAAsB,EACtB,qBAAqB,EACrB,wBAAwB,EACxB,sBAAsB,EACtB,6BAA6B,GAC9B,MAAM,oBAAoB,CAAC;AAE5B,OAAO,EACL,YAAY,EACZ,UAAU,EACV,eAAe,EACf,aAAa,EACb,gBAAgB,EAChB,YAAY,GACb,MAAM,cAAc,CAAC"}
@@ -0,0 +1,113 @@
1
+ /**
2
+ * Unified judge accessor — single source of truth for "what the LLM judge
3
+ * said" on an EvaluationReport.
4
+ *
5
+ * Background: historically the judge verdict + reasoning lived in two
6
+ * parallel surfaces:
7
+ *
8
+ * 1. report.llmJudgeReasoning (string) — written by the legacy
9
+ * auto-judge path (services/evaluation/index.ts and the various
10
+ * runners that call callBedrockJudge against expectedOutcomes).
11
+ * One per report, last writer wins.
12
+ *
13
+ * 2. report.matcherResults[*] with method: 'llm-judge' — written by
14
+ * the SDK `judge(result, claim)` matcher. Many per report.
15
+ *
16
+ * Both ultimately come from the same Bedrock Judge endpoint. Storing
17
+ * them in two places caused real bugs (notably issue #230, where the
18
+ * trace-mode placeholder leaked into the legacy field and bled through
19
+ * to the UI for deterministic SDK runs).
20
+ *
21
+ * The fix: `matcherResults[]` is the canonical surface. The legacy
22
+ * `llmJudgeReasoning` field is kept populated as a derived
23
+ * convenience for backward-compat readers, but new code MUST use
24
+ * {@link getJudgeMatcherResults} on the read side and
25
+ * {@link recordJudgeMatcherResult} on the write side.
26
+ */
27
+ import type { MatcherResult } from './types.js';
28
+ /** A minimal duck-typed report shape — accepts any object with the two fields. */
29
+ export interface JudgeAccessReport {
30
+ matcherResults?: MatcherResult[];
31
+ llmJudgeReasoning?: string;
32
+ }
33
+ /**
34
+ * Returns every llm-judge MatcherResult on the report, including a
35
+ * synthetic entry derived from the legacy `llmJudgeReasoning` field
36
+ * when the report pre-dates the unified surface.
37
+ *
38
+ * Read-only: nothing is written back to the report.
39
+ *
40
+ * Behaviour matrix:
41
+ *
42
+ * | matcherResults has [llm-judge] | llmJudgeReasoning | Returns |
43
+ * |--------------------------------|------------------------|----------------------------|
44
+ * | yes | anything | the existing entries |
45
+ * | no | empty / placeholder | [] |
46
+ * | no | real reasoning | [<synthetic entry>] |
47
+ *
48
+ * The placeholder string `Waiting for traces to become available...`
49
+ * is treated as "no judge ran yet" \u2014 see issue #230.
50
+ */
51
+ export declare function getJudgeMatcherResults(report: JudgeAccessReport): MatcherResult[];
52
+ /**
53
+ * Convenience: the single most recent llm-judge reasoning string, or
54
+ * empty when no judge ran. Used by surfaces that historically read
55
+ * `llmJudgeReasoning` directly (HTML report, skills grader, compare
56
+ * view) and only need a flat string.
57
+ */
58
+ export declare function getJudgeReasoningText(report: JudgeAccessReport): string;
59
+ /**
60
+ * Convert a `JudgeResult` from `callBedrockJudge` into a `MatcherResult`.
61
+ * Pure: doesn't touch any report. Used by inline-return code paths in
62
+ * services/evaluation/index.ts where building a fresh report object is
63
+ * cleaner than the mutate-then-return pattern.
64
+ */
65
+ export declare function buildJudgeMatcherEntry(judgeResult: JudgeResultLike, options?: {
66
+ claim?: string;
67
+ model?: string;
68
+ }): MatcherResult;
69
+ /**
70
+ * Format an arbitrary `expectedOutcomes` value into a single description
71
+ * fragment suitable for the matcher entry's `description` field. Accepts
72
+ * the SDK's flat `string[]` *and* the legacy `{ rootCauses, requiredFacts,
73
+ * conclusions }` object — both shapes appear on persisted test cases.
74
+ */
75
+ export declare function formatExpectedOutcomesAsClaim(outcomes?: unknown): string;
76
+ /**
77
+ * Convert a `JudgeResult` from `callBedrockJudge` into a `MatcherResult`
78
+ * and append it to `report.matcherResults`. Also keeps the legacy
79
+ * `report.llmJudgeReasoning` field populated as a derived
80
+ * backward-compat shim (it equals the reasoning of the just-pushed
81
+ * entry, so direct readers continue to work).
82
+ *
83
+ * Mutates the passed report and returns the matcher entry.
84
+ *
85
+ * The `claim` argument is what the auto-judge was evaluating against
86
+ * (the test case's expected outcomes). The matcher description ends
87
+ * up as `judge: <claim>` matching the SDK convention.
88
+ */
89
+ export declare function recordJudgeMatcherResult(report: JudgeAccessReport & {
90
+ matcherResults?: MatcherResult[];
91
+ llmJudgeReasoning?: string;
92
+ }, judgeResult: JudgeResultLike, options?: {
93
+ claim?: string;
94
+ model?: string;
95
+ }): MatcherResult;
96
+ /** Subset of `JudgeResult` we depend on \u2014 keeps this module type-import-light. */
97
+ export interface JudgeResultLike {
98
+ passFailStatus: 'passed' | 'failed';
99
+ metrics: {
100
+ accuracy?: number;
101
+ [k: string]: number | undefined;
102
+ };
103
+ llmJudgeReasoning: string;
104
+ judgeDurationMs?: number;
105
+ improvementStrategies?: Array<{
106
+ category: string;
107
+ issue: string;
108
+ recommendation: string;
109
+ priority: 'high' | 'medium' | 'low';
110
+ }>;
111
+ }
112
+ export type { JudgeResult } from '../../types/index.js';
113
+ //# sourceMappingURL=judgeAccessor.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"judgeAccessor.d.ts","sourceRoot":"","sources":["../../../matchers/judgeAccessor.ts"],"names":[],"mappings":"AAKA;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AAEH,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AAGhD,kFAAkF;AAClF,MAAM,WAAW,iBAAiB;IAChC,cAAc,CAAC,EAAE,aAAa,EAAE,CAAC;IACjC,iBAAiB,CAAC,EAAE,MAAM,CAAC;CAC5B;AAED;;;;;;;;;;;;;;;;;GAiBG;AACH,wBAAgB,sBAAsB,CAAC,MAAM,EAAE,iBAAiB,GAAG,aAAa,EAAE,CAuBjF;AAED;;;;;GAKG;AACH,wBAAgB,qBAAqB,CAAC,MAAM,EAAE,iBAAiB,GAAG,MAAM,CAevE;AAED;;;;;GAKG;AACH,wBAAgB,sBAAsB,CACpC,WAAW,EAAE,eAAe,EAC5B,OAAO,CAAC,EAAE;IAAE,KAAK,CAAC,EAAE,MAAM,CAAC;IAAC,KAAK,CAAC,EAAE,MAAM,CAAA;CAAE,GAC3C,aAAa,CA0Bf;AAED;;;;;GAKG;AACH,wBAAgB,6BAA6B,CAAC,QAAQ,CAAC,EAAE,OAAO,GAAG,MAAM,CAoBxE;AAED;;;;;;;;;;;;GAYG;AACH,wBAAgB,wBAAwB,CACtC,MAAM,EAAE,iBAAiB,GAAG;IAAE,cAAc,CAAC,EAAE,aAAa,EAAE,CAAC;IAAC,iBAAiB,CAAC,EAAE,MAAM,CAAA;CAAE,EAC5F,WAAW,EAAE,eAAe,EAC5B,OAAO,CAAC,EAAE;IAAE,KAAK,CAAC,EAAE,MAAM,CAAC;IAAC,KAAK,CAAC,EAAE,MAAM,CAAA;CAAE,GAC3C,aAAa,CAcf;AAED,uFAAuF;AACvF,MAAM,WAAW,eAAe;IAC9B,cAAc,EAAE,QAAQ,GAAG,QAAQ,CAAC;IACpC,OAAO,EAAE;QAAE,QAAQ,CAAC,EAAE,MAAM,CAAC;QAAC,CAAC,CAAC,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAAA;KAAE,CAAC;IAChE,iBAAiB,EAAE,MAAM,CAAC;IAC1B,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,qBAAqB,CAAC,EAAE,KAAK,CAAC;QAC5B,QAAQ,EAAE,MAAM,CAAC;QACjB,KAAK,EAAE,MAAM,CAAC;QACd,cAAc,EAAE,MAAM,CAAC;QACvB,QAAQ,EAAE,MAAM,GAAG,QAAQ,GAAG,KAAK,CAAC;KACrC,CAAC,CAAC;CACJ;AA+BD,YAAY,EAAE,WAAW,EAAE,MAAM,sBAAsB,CAAC"}
@@ -0,0 +1,183 @@
1
+ /*
2
+ * Copyright OpenSearch Contributors
3
+ * SPDX-License-Identifier: Apache-2.0
4
+ */
5
+ /**
6
+ * Returns every llm-judge MatcherResult on the report, including a
7
+ * synthetic entry derived from the legacy `llmJudgeReasoning` field
8
+ * when the report pre-dates the unified surface.
9
+ *
10
+ * Read-only: nothing is written back to the report.
11
+ *
12
+ * Behaviour matrix:
13
+ *
14
+ * | matcherResults has [llm-judge] | llmJudgeReasoning | Returns |
15
+ * |--------------------------------|------------------------|----------------------------|
16
+ * | yes | anything | the existing entries |
17
+ * | no | empty / placeholder | [] |
18
+ * | no | real reasoning | [<synthetic entry>] |
19
+ *
20
+ * The placeholder string `Waiting for traces to become available...`
21
+ * is treated as "no judge ran yet" \u2014 see issue #230.
22
+ */
23
+ export function getJudgeMatcherResults(report) {
24
+ const fromMatcher = (report.matcherResults ?? []).filter(m => m.method === 'llm-judge');
25
+ if (fromMatcher.length > 0) {
26
+ return fromMatcher;
27
+ }
28
+ const legacy = report.llmJudgeReasoning?.trim();
29
+ if (!legacy || isPlaceholderReasoning(legacy)) {
30
+ return [];
31
+ }
32
+ // Old report: synthesize a single virtual matcher entry so UIs that
33
+ // render only matcherResults still have something to show.
34
+ return [
35
+ {
36
+ description: 'judge: expected outcomes',
37
+ pass: inferPassFromReport(report),
38
+ method: 'llm-judge',
39
+ reasoning: legacy,
40
+ },
41
+ ];
42
+ }
43
+ /**
44
+ * Convenience: the single most recent llm-judge reasoning string, or
45
+ * empty when no judge ran. Used by surfaces that historically read
46
+ * `llmJudgeReasoning` directly (HTML report, skills grader, compare
47
+ * view) and only need a flat string.
48
+ */
49
+ export function getJudgeReasoningText(report) {
50
+ const entries = getJudgeMatcherResults(report);
51
+ if (entries.length === 0)
52
+ return '';
53
+ // Most-recent-first: prefer the last entry the runner pushed. If
54
+ // multiple entries exist (SDK with several judge() calls) we join
55
+ // them with horizontal-rule markers so a flat-string consumer still
56
+ // sees every claim.
57
+ if (entries.length === 1)
58
+ return entries[0].reasoning ?? '';
59
+ return entries
60
+ .map((m, i) => {
61
+ const claim = m.description?.replace(/^judge:\s*/, '') ?? `claim ${i + 1}`;
62
+ const verdict = m.pass ? 'PASS' : 'FAIL';
63
+ return `### ${verdict} \u2014 ${claim}\n\n${m.reasoning ?? ''}`;
64
+ })
65
+ .join('\n\n---\n\n');
66
+ }
67
+ /**
68
+ * Convert a `JudgeResult` from `callBedrockJudge` into a `MatcherResult`.
69
+ * Pure: doesn't touch any report. Used by inline-return code paths in
70
+ * services/evaluation/index.ts where building a fresh report object is
71
+ * cleaner than the mutate-then-return pattern.
72
+ */
73
+ export function buildJudgeMatcherEntry(judgeResult, options) {
74
+ const claim = options?.claim?.trim() || 'expected outcomes';
75
+ const accuracy = judgeResult.metrics?.accuracy;
76
+ const score = typeof accuracy === 'number' ? accuracy / 100 : undefined;
77
+ const pass = judgeResult.passFailStatus === 'passed';
78
+ const reasoning = judgeResult.llmJudgeReasoning ?? '';
79
+ return {
80
+ description: `judge: ${claim}`,
81
+ pass,
82
+ method: 'llm-judge',
83
+ durationMs: judgeResult.judgeDurationMs,
84
+ score,
85
+ reasoning,
86
+ ...(options?.model ? { model: options.model } : {}),
87
+ ...(pass ? {} : { errorMessage: reasoning }),
88
+ // Carry the rest of the judge payload through so SDK
89
+ // `getJudgeMatcherResults()` consumers see the same data the
90
+ // legacy report-level fields used to expose. See MatcherResult.
91
+ ...(Array.isArray(judgeResult.improvementStrategies) && judgeResult.improvementStrategies.length > 0
92
+ ? { improvementStrategies: judgeResult.improvementStrategies }
93
+ : {}),
94
+ ...(judgeResult.metrics && typeof judgeResult.metrics === 'object'
95
+ ? { judgeMetrics: { ...judgeResult.metrics } }
96
+ : {}),
97
+ };
98
+ }
99
+ /**
100
+ * Format an arbitrary `expectedOutcomes` value into a single description
101
+ * fragment suitable for the matcher entry's `description` field. Accepts
102
+ * the SDK's flat `string[]` *and* the legacy `{ rootCauses, requiredFacts,
103
+ * conclusions }` object — both shapes appear on persisted test cases.
104
+ */
105
+ export function formatExpectedOutcomesAsClaim(outcomes) {
106
+ const items = [];
107
+ if (Array.isArray(outcomes)) {
108
+ for (const o of outcomes) {
109
+ if (typeof o === 'string' && o.trim())
110
+ items.push(o.trim());
111
+ }
112
+ }
113
+ else if (outcomes && typeof outcomes === 'object') {
114
+ // Legacy shape: { rootCauses?: string[]; requiredFacts?: string[]; conclusions?: string[] }
115
+ for (const key of Object.keys(outcomes)) {
116
+ const v = outcomes[key];
117
+ if (Array.isArray(v)) {
118
+ for (const s of v) {
119
+ if (typeof s === 'string' && s.trim())
120
+ items.push(s.trim());
121
+ }
122
+ }
123
+ }
124
+ }
125
+ if (items.length === 0)
126
+ return 'expected outcomes';
127
+ if (items.length === 1)
128
+ return items[0];
129
+ return `${items.length} expected outcomes`;
130
+ }
131
+ /**
132
+ * Convert a `JudgeResult` from `callBedrockJudge` into a `MatcherResult`
133
+ * and append it to `report.matcherResults`. Also keeps the legacy
134
+ * `report.llmJudgeReasoning` field populated as a derived
135
+ * backward-compat shim (it equals the reasoning of the just-pushed
136
+ * entry, so direct readers continue to work).
137
+ *
138
+ * Mutates the passed report and returns the matcher entry.
139
+ *
140
+ * The `claim` argument is what the auto-judge was evaluating against
141
+ * (the test case's expected outcomes). The matcher description ends
142
+ * up as `judge: <claim>` matching the SDK convention.
143
+ */
144
+ export function recordJudgeMatcherResult(report, judgeResult, options) {
145
+ const entry = buildJudgeMatcherEntry(judgeResult, options);
146
+ const existing = report.matcherResults ?? [];
147
+ report.matcherResults = [...existing, entry];
148
+ // Backward-compat shim: keep the legacy field populated with the most
149
+ // recent reasoning so external readers that haven't migrated still
150
+ // work. Empty string is a deliberate signal for SDK-multi-judge runs
151
+ // (the field can't represent multiple verdicts; consumers must look
152
+ // at matcherResults).
153
+ report.llmJudgeReasoning = entry.reasoning ?? '';
154
+ return entry;
155
+ }
156
+ // ─── internal helpers ───────────────────────────────────────────────────────
157
+ /**
158
+ * The trace-mode init path sets `llmJudgeReasoning` to a placeholder
159
+ * before any real verdict exists. We must not synthesize a virtual
160
+ * matcher entry from that string \u2014 it's a "judge has not run yet"
161
+ * signal, not real reasoning.
162
+ */
163
+ function isPlaceholderReasoning(s) {
164
+ return /^Waiting for traces/i.test(s);
165
+ }
166
+ /**
167
+ * Best-effort guess at the verdict for a synthesized entry on an old
168
+ * report. Prefers an explicit `passFailStatus` if present; otherwise
169
+ * falls back to the report's metrics.accuracy (>=70 ~ pass), and
170
+ * finally defaults to `false` so a missing verdict never silently
171
+ * looks green.
172
+ */
173
+ function inferPassFromReport(report) {
174
+ if (report.passFailStatus === 'passed')
175
+ return true;
176
+ if (report.passFailStatus === 'failed')
177
+ return false;
178
+ const acc = report.metrics?.accuracy;
179
+ if (typeof acc === 'number')
180
+ return acc >= 70;
181
+ return false;
182
+ }
183
+ //# sourceMappingURL=judgeAccessor.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"judgeAccessor.js","sourceRoot":"","sources":["../../../matchers/judgeAccessor.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAsCH;;;;;;;;;;;;;;;;;GAiBG;AACH,MAAM,UAAU,sBAAsB,CAAC,MAAyB;IAC9D,MAAM,WAAW,GAAG,CAAC,MAAM,CAAC,cAAc,IAAI,EAAE,CAAC,CAAC,MAAM,CACtD,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,MAAM,KAAK,WAAW,CAC9B,CAAC;IACF,IAAI,WAAW,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC3B,OAAO,WAAW,CAAC;IACrB,CAAC;IAED,MAAM,MAAM,GAAG,MAAM,CAAC,iBAAiB,EAAE,IAAI,EAAE,CAAC;IAChD,IAAI,CAAC,MAAM,IAAI,sBAAsB,CAAC,MAAM,CAAC,EAAE,CAAC;QAC9C,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,oEAAoE;IACpE,2DAA2D;IAC3D,OAAO;QACL;YACE,WAAW,EAAE,0BAA0B;YACvC,IAAI,EAAE,mBAAmB,CAAC,MAAM,CAAC;YACjC,MAAM,EAAE,WAAW;YACnB,SAAS,EAAE,MAAM;SAClB;KACF,CAAC;AACJ,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,qBAAqB,CAAC,MAAyB;IAC7D,MAAM,OAAO,GAAG,sBAAsB,CAAC,MAAM,CAAC,CAAC;IAC/C,IAAI,OAAO,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,EAAE,CAAC;IACpC,iEAAiE;IACjE,kEAAkE;IAClE,oEAAoE;IACpE,oBAAoB;IACpB,IAAI,OAAO,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,OAAO,CAAC,CAAC,CAAC,CAAC,SAAS,IAAI,EAAE,CAAC;IAC5D,OAAO,OAAO;SACX,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE;QACZ,MAAM,KAAK,GAAG,CAAC,CAAC,WAAW,EAAE,OAAO,CAAC,YAAY,EAAE,EAAE,CAAC,IAAI,SAAS,CAAC,GAAG,CAAC,EAAE,CAAC;QAC3E,MAAM,OAAO,GAAG,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC;QACzC,OAAO,OAAO,OAAO,WAAW,KAAK,OAAO,CAAC,CAAC,SAAS,IAAI,EAAE,EAAE,CAAC;IAClE,CAAC,CAAC;SACD,IAAI,CAAC,aAAa,CAAC,CAAC;AACzB,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,sBAAsB,CACpC,WAA4B,EAC5B,OAA4C;IAE5C,MAAM,KAAK,GAAG,OAAO,EAAE,KAAK,EAAE,IAAI,EAAE,IAAI,mBAAmB,CAAC;IAC5D,MAAM,QAAQ,GAAG,WAAW,CAAC,OAAO,EAAE,QAAQ,CAAC;IAC/C,MAAM,KAAK,GAAG,OAAO,QAAQ,KAAK,QAAQ,CAAC,CAAC,CAAC,QAAQ,GAAG,GAAG,CAAC,CAAC,CAAC,SAAS,CAAC;IACxE,MAAM,IAAI,GAAG,WAAW,CAAC,cAAc,KAAK,QAAQ,CAAC;IACrD,MAAM,SAAS,GAAG,WAAW,CAAC,iBAAiB,IAAI,EAAE,CAAC;IAEtD,OAAO;QACL,WAAW,EAAE,UAAU,KAAK,EAAE;QAC9B,IAAI;QACJ,MAAM,EAAE,WAAW;QACnB,UAAU,EAAE,WAAW,CAAC,eAAe;QACvC,KAAK;QACL,SAAS;QACT,GAAG,CAAC,OAAO,EAAE,KAAK,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,OAAO,CAAC,KAAK,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;QACnD,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,YAAY,EAAE,SAAS,EAAE,CAAC;QAC5C,qDAAqD;QACrD,6DAA6D;QAC7D,gEAAgE;QAChE,GAAG,CAAC,KAAK,CAAC,OAAO,CAAC,WAAW,CAAC,qBAAqB,CAAC,IAAI,WAAW,CAAC,qBAAqB,CAAC,MAAM,GAAG,CAAC;YAClG,CAAC,CAAC,EAAE,qBAAqB,EAAE,WAAW,CAAC,qBAAqB,EAAE;YAC9D,CAAC,CAAC,EAAE,CAAC;QACP,GAAG,CAAC,WAAW,CAAC,OAAO,IAAI,OAAO,WAAW,CAAC,OAAO,KAAK,QAAQ;YAChE,CAAC,CAAC,EAAE,YAAY,EAAE,EAAE,GAAG,WAAW,CAAC,OAAO,EAAS,EAAE;YACrD,CAAC,CAAC,EAAE,CAAC;KACR,CAAC;AACJ,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,6BAA6B,CAAC,QAAkB;IAC9D,MAAM,KAAK,GAAa,EAAE,CAAC;IAC3B,IAAI,KAAK,CAAC,OAAO,CAAC,QAAQ,CAAC,EAAE,CAAC;QAC5B,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;YACzB,IAAI,OAAO,CAAC,KAAK,QAAQ,IAAI,CAAC,CAAC,IAAI,EAAE;gBAAE,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;QAC9D,CAAC;IACH,CAAC;SAAM,IAAI,QAAQ,IAAI,OAAO,QAAQ,KAAK,QAAQ,EAAE,CAAC;QACpD,4FAA4F;QAC5F,KAAK,MAAM,GAAG,IAAI,MAAM,CAAC,IAAI,CAAC,QAAmC,CAAC,EAAE,CAAC;YACnE,MAAM,CAAC,GAAI,QAAoC,CAAC,GAAG,CAAC,CAAC;YACrD,IAAI,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC;gBACrB,KAAK,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC;oBAClB,IAAI,OAAO,CAAC,KAAK,QAAQ,IAAI,CAAC,CAAC,IAAI,EAAE;wBAAE,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;gBAC9D,CAAC;YACH,CAAC;QACH,CAAC;IACH,CAAC;IACD,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,mBAAmB,CAAC;IACnD,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,KAAK,CAAC,CAAC,CAAC,CAAC;IACxC,OAAO,GAAG,KAAK,CAAC,MAAM,oBAAoB,CAAC;AAC7C,CAAC;AAED;;;;;;;;;;;;GAYG;AACH,MAAM,UAAU,wBAAwB,CACtC,MAA4F,EAC5F,WAA4B,EAC5B,OAA4C;IAE5C,MAAM,KAAK,GAAG,sBAAsB,CAAC,WAAW,EAAE,OAAO,CAAC,CAAC;IAE3D,MAAM,QAAQ,GAAG,MAAM,CAAC,cAAc,IAAI,EAAE,CAAC;IAC7C,MAAM,CAAC,cAAc,GAAG,CAAC,GAAG,QAAQ,EAAE,KAAK,CAAC,CAAC;IAE7C,sEAAsE;IACtE,mEAAmE;IACnE,qEAAqE;IACrE,oEAAoE;IACpE,sBAAsB;IACtB,MAAM,CAAC,iBAAiB,GAAG,KAAK,CAAC,SAAS,IAAI,EAAE,CAAC;IAEjD,OAAO,KAAK,CAAC;AACf,CAAC;AAgBD,+EAA+E;AAE/E;;;;;GAKG;AACH,SAAS,sBAAsB,CAAC,CAAS;IACvC,OAAO,sBAAsB,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AACxC,CAAC;AAED;;;;;;GAMG;AACH,SAAS,mBAAmB,CAAC,MAAwF;IACnH,IAAI,MAAM,CAAC,cAAc,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAC;IACpD,IAAI,MAAM,CAAC,cAAc,KAAK,QAAQ;QAAE,OAAO,KAAK,CAAC;IACrD,MAAM,GAAG,GAAG,MAAM,CAAC,OAAO,EAAE,QAAQ,CAAC;IACrC,IAAI,OAAO,GAAG,KAAK,QAAQ;QAAE,OAAO,GAAG,IAAI,EAAE,CAAC;IAC9C,OAAO,KAAK,CAAC;AACf,CAAC"}
@@ -0,0 +1,39 @@
1
+ import type { MatcherResult, MatcherMethod } from './types.js';
2
+ export interface MatcherSession {
3
+ results: MatcherResult[];
4
+ startedAt: number;
5
+ }
6
+ /**
7
+ * Run `fn` with a fresh, isolated matcher session and return the verdicts
8
+ * recorded during it. Concurrency-safe: each call gets its own session via
9
+ * AsyncLocalStorage, so interleaved bodies never share verdicts.
10
+ *
11
+ * Results are returned even when `fn` throws — the caller can inspect both
12
+ * the partial results and the error (cleanup hooks that record after a body
13
+ * failure therefore still surface in the breakdown).
14
+ */
15
+ export declare function runInSession<T>(fn: () => Promise<T> | T): Promise<{
16
+ results: MatcherResult[];
17
+ value?: T;
18
+ error?: unknown;
19
+ }>;
20
+ /**
21
+ * Begin a fresh global session and make it active (legacy API).
22
+ *
23
+ * Prefer {@link runInSession} for anything that may run concurrently. This
24
+ * remains for synchronous, single-threaded callers.
25
+ */
26
+ export declare function startSession(): MatcherSession;
27
+ /** Stop the current global session and return its results (legacy API). */
28
+ export declare function endSession(): MatcherResult[];
29
+ /** True when a session is active (ALS scope or legacy global). */
30
+ export declare function isSessionActive(): boolean;
31
+ /** Record a single matcher verdict on the active session. No-op when none. */
32
+ export declare function recordVerdict(result: MatcherResult): void;
33
+ /**
34
+ * Record a verdict computed from a try/catch around the matcher body.
35
+ * Convenience wrapper used by judge() and traces helpers; chai matchers go
36
+ * through the chai plugin in `./expect.ts`.
37
+ */
38
+ export declare function recordWithTiming<T>(description: string, method: MatcherMethod, fn: () => Promise<T> | T): Promise<T>;
39
+ //# sourceMappingURL=session.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"session.d.ts","sourceRoot":"","sources":["../../../matchers/session.ts"],"names":[],"mappings":"AA8BA,OAAO,KAAK,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AAE/D,MAAM,WAAW,cAAc;IAC7B,OAAO,EAAE,aAAa,EAAE,CAAC;IACzB,SAAS,EAAE,MAAM,CAAC;CACnB;AAiBD;;;;;;;;GAQG;AACH,wBAAsB,YAAY,CAAC,CAAC,EAClC,EAAE,EAAE,MAAM,OAAO,CAAC,CAAC,CAAC,GAAG,CAAC,GACvB,OAAO,CAAC;IAAE,OAAO,EAAE,aAAa,EAAE,CAAC;IAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IAAC,KAAK,CAAC,EAAE,OAAO,CAAA;CAAE,CAAC,CAQnE;AAED;;;;;GAKG;AACH,wBAAgB,YAAY,IAAI,cAAc,CAG7C;AAED,2EAA2E;AAC3E,wBAAgB,UAAU,IAAI,aAAa,EAAE,CAK5C;AAED,kEAAkE;AAClE,wBAAgB,eAAe,IAAI,OAAO,CAEzC;AAED,8EAA8E;AAC9E,wBAAgB,aAAa,CAAC,MAAM,EAAE,aAAa,GAAG,IAAI,CAIzD;AAED;;;;GAIG;AACH,wBAAsB,gBAAgB,CAAC,CAAC,EACtC,WAAW,EAAE,MAAM,EACnB,MAAM,EAAE,aAAa,EACrB,EAAE,EAAE,MAAM,OAAO,CAAC,CAAC,CAAC,GAAG,CAAC,GACvB,OAAO,CAAC,CAAC,CAAC,CAqBZ"}
@@ -0,0 +1,116 @@
1
+ /*
2
+ * Copyright OpenSearch Contributors
3
+ * SPDX-License-Identifier: Apache-2.0
4
+ */
5
+ /**
6
+ * Matcher session — collects MatcherResult[] for the currently-executing
7
+ * test body. Matchers (expect/judge/traces) record into the active session
8
+ * via `recordVerdict`.
9
+ *
10
+ * Concurrency model (RFC 004, "kills the global session"):
11
+ *
12
+ * The session is held in an AsyncLocalStorage so that bodies running
13
+ * concurrently (the runners dispatch up to `concurrency` tests at once,
14
+ * interleaving at every `await`) each record into their OWN session.
15
+ * Before this, a single module-level `activeSession` was shared by all
16
+ * in-flight bodies, so verdicts cross-contaminated between tests.
17
+ *
18
+ * `runInSession(fn)` is the concurrency-safe entry point and is what the
19
+ * runners use: it establishes a fresh session for the duration of `fn`
20
+ * (and everything it `await`s) and returns the collected results.
21
+ *
22
+ * The legacy `startSession()` / `endSession()` pair is retained for
23
+ * synchronous, non-interleaved callers (unit tests, simple scripts). It
24
+ * uses a module-global fallback session. When an AsyncLocalStorage scope
25
+ * is active (i.e. we're inside `runInSession`), the ALS session always
26
+ * takes precedence over the global, so the two never collide.
27
+ */
28
+ import { AsyncLocalStorage } from 'async_hooks';
29
+ /** Per-async-context session. Set for the duration of `runInSession(fn)`. */
30
+ const sessionStore = new AsyncLocalStorage();
31
+ /** Legacy module-global session for direct startSession()/endSession() callers. */
32
+ let legacySession = null;
33
+ function newSession() {
34
+ return { results: [], startedAt: Date.now() };
35
+ }
36
+ /** The session verdicts should be recorded into right now, if any. */
37
+ function currentSession() {
38
+ return sessionStore.getStore() ?? legacySession;
39
+ }
40
+ /**
41
+ * Run `fn` with a fresh, isolated matcher session and return the verdicts
42
+ * recorded during it. Concurrency-safe: each call gets its own session via
43
+ * AsyncLocalStorage, so interleaved bodies never share verdicts.
44
+ *
45
+ * Results are returned even when `fn` throws — the caller can inspect both
46
+ * the partial results and the error (cleanup hooks that record after a body
47
+ * failure therefore still surface in the breakdown).
48
+ */
49
+ export async function runInSession(fn) {
50
+ const session = newSession();
51
+ try {
52
+ const value = await sessionStore.run(session, fn);
53
+ return { results: session.results, value };
54
+ }
55
+ catch (error) {
56
+ return { results: session.results, error };
57
+ }
58
+ }
59
+ /**
60
+ * Begin a fresh global session and make it active (legacy API).
61
+ *
62
+ * Prefer {@link runInSession} for anything that may run concurrently. This
63
+ * remains for synchronous, single-threaded callers.
64
+ */
65
+ export function startSession() {
66
+ legacySession = newSession();
67
+ return legacySession;
68
+ }
69
+ /** Stop the current global session and return its results (legacy API). */
70
+ export function endSession() {
71
+ if (!legacySession)
72
+ return [];
73
+ const out = legacySession.results;
74
+ legacySession = null;
75
+ return out;
76
+ }
77
+ /** True when a session is active (ALS scope or legacy global). */
78
+ export function isSessionActive() {
79
+ return currentSession() !== null;
80
+ }
81
+ /** Record a single matcher verdict on the active session. No-op when none. */
82
+ export function recordVerdict(result) {
83
+ const session = currentSession();
84
+ if (!session)
85
+ return;
86
+ session.results.push(result);
87
+ }
88
+ /**
89
+ * Record a verdict computed from a try/catch around the matcher body.
90
+ * Convenience wrapper used by judge() and traces helpers; chai matchers go
91
+ * through the chai plugin in `./expect.ts`.
92
+ */
93
+ export async function recordWithTiming(description, method, fn) {
94
+ const start = Date.now();
95
+ try {
96
+ const value = await fn();
97
+ recordVerdict({
98
+ description,
99
+ pass: true,
100
+ method,
101
+ durationMs: Date.now() - start,
102
+ });
103
+ return value;
104
+ }
105
+ catch (err) {
106
+ recordVerdict({
107
+ description,
108
+ pass: false,
109
+ method,
110
+ durationMs: Date.now() - start,
111
+ errorMessage: err?.message || String(err),
112
+ });
113
+ throw err;
114
+ }
115
+ }
116
+ //# sourceMappingURL=session.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"session.js","sourceRoot":"","sources":["../../../matchers/session.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH;;;;;;;;;;;;;;;;;;;;;;GAsBG;AAEH,OAAO,EAAE,iBAAiB,EAAE,MAAM,aAAa,CAAC;AAQhD,6EAA6E;AAC7E,MAAM,YAAY,GAAG,IAAI,iBAAiB,EAAkB,CAAC;AAE7D,mFAAmF;AACnF,IAAI,aAAa,GAA0B,IAAI,CAAC;AAEhD,SAAS,UAAU;IACjB,OAAO,EAAE,OAAO,EAAE,EAAE,EAAE,SAAS,EAAE,IAAI,CAAC,GAAG,EAAE,EAAE,CAAC;AAChD,CAAC;AAED,sEAAsE;AACtE,SAAS,cAAc;IACrB,OAAO,YAAY,CAAC,QAAQ,EAAE,IAAI,aAAa,CAAC;AAClD,CAAC;AAED;;;;;;;;GAQG;AACH,MAAM,CAAC,KAAK,UAAU,YAAY,CAChC,EAAwB;IAExB,MAAM,OAAO,GAAG,UAAU,EAAE,CAAC;IAC7B,IAAI,CAAC;QACH,MAAM,KAAK,GAAG,MAAM,YAAY,CAAC,GAAG,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC;QAClD,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,OAAO,EAAE,KAAK,EAAE,CAAC;IAC7C,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,OAAO,EAAE,KAAK,EAAE,CAAC;IAC7C,CAAC;AACH,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,YAAY;IAC1B,aAAa,GAAG,UAAU,EAAE,CAAC;IAC7B,OAAO,aAAa,CAAC;AACvB,CAAC;AAED,2EAA2E;AAC3E,MAAM,UAAU,UAAU;IACxB,IAAI,CAAC,aAAa;QAAE,OAAO,EAAE,CAAC;IAC9B,MAAM,GAAG,GAAG,aAAa,CAAC,OAAO,CAAC;IAClC,aAAa,GAAG,IAAI,CAAC;IACrB,OAAO,GAAG,CAAC;AACb,CAAC;AAED,kEAAkE;AAClE,MAAM,UAAU,eAAe;IAC7B,OAAO,cAAc,EAAE,KAAK,IAAI,CAAC;AACnC,CAAC;AAED,8EAA8E;AAC9E,MAAM,UAAU,aAAa,CAAC,MAAqB;IACjD,MAAM,OAAO,GAAG,cAAc,EAAE,CAAC;IACjC,IAAI,CAAC,OAAO;QAAE,OAAO;IACrB,OAAO,CAAC,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;AAC/B,CAAC;AAED;;;;GAIG;AACH,MAAM,CAAC,KAAK,UAAU,gBAAgB,CACpC,WAAmB,EACnB,MAAqB,EACrB,EAAwB;IAExB,MAAM,KAAK,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;IACzB,IAAI,CAAC;QACH,MAAM,KAAK,GAAG,MAAM,EAAE,EAAE,CAAC;QACzB,aAAa,CAAC;YACZ,WAAW;YACX,IAAI,EAAE,IAAI;YACV,MAAM;YACN,UAAU,EAAE,IAAI,CAAC,GAAG,EAAE,GAAG,KAAK;SAC/B,CAAC,CAAC;QACH,OAAO,KAAK,CAAC;IACf,CAAC;IAAC,OAAO,GAAQ,EAAE,CAAC;QAClB,aAAa,CAAC;YACZ,WAAW;YACX,IAAI,EAAE,KAAK;YACX,MAAM;YACN,UAAU,EAAE,IAAI,CAAC,GAAG,EAAE,GAAG,KAAK;YAC9B,YAAY,EAAE,GAAG,EAAE,OAAO,IAAI,MAAM,CAAC,GAAG,CAAC;SAC1C,CAAC,CAAC;QACH,MAAM,GAAG,CAAC;IACZ,CAAC;AACH,CAAC"}
@@ -0,0 +1,55 @@
1
+ /**
2
+ * `traces` fixture — read-only access to the OTel traces emitted by the
3
+ * agent during this run. Pre-loaded by the runner before the test body
4
+ * starts; sync access from inside the body.
5
+ *
6
+ * Three construction modes (the runner picks one):
7
+ * - `buildTracesAccessor(spans)` — real spans available, real numbers.
8
+ * - `emptyTracesAccessor()` — agent opted out (`useTraces=false`).
9
+ * Every accessor returns 0/[] so user matchers don't blow up.
10
+ * - `unavailableTracesAccessor(reason)` — agent opted in (`useTraces=true`)
11
+ * but spans were not fetchable (no runId, fetch failed, or polling
12
+ * timed out). Every accessor *throws* so silent false-passes like
13
+ * `expect(traces.totalTokens).to.be.lessThan(10_000)` against an
14
+ * empty fixture become loud failures (see issue #230).
15
+ *
16
+ * Built on top of `services/traces/index.ts:fetchTracesByRunIds` —
17
+ * the runner is responsible for invoking that and constructing the
18
+ * accessor.
19
+ */
20
+ import type { Span } from '../../types/index.js';
21
+ export interface TracesAccessor {
22
+ /** Sum of all `gen_ai.usage.prompt_tokens + completion_tokens` across LLM spans. */
23
+ totalTokens: number;
24
+ /** Sum of all `gen_ai.usage.cost_usd` (or derived) across LLM spans. */
25
+ totalCost: number;
26
+ /** Tool invocation summary derived from spans. */
27
+ toolCalls: ReadonlyArray<{
28
+ name: string;
29
+ durationMs: number;
30
+ }>;
31
+ /** Duration of the first span matching the given name, or 0 when not found. */
32
+ spanDuration(name: string): number;
33
+ /** All spans (read-only). */
34
+ spans: ReadonlyArray<Span>;
35
+ }
36
+ /**
37
+ * Empty accessor — silent zeros. Used when the agent opted out of traces
38
+ * (`useTraces: false`). Reading any accessor returns `0` / `[]` so user
39
+ * matchers in opt-out scenarios don't throw.
40
+ */
41
+ export declare function emptyTracesAccessor(): TracesAccessor;
42
+ /**
43
+ * Loud-failure accessor — every read throws. Used when the agent opted
44
+ * in to traces (`useTraces: true`) but spans were not retrievable. This
45
+ * turns the silent false-pass described in issue #230 into an actionable
46
+ * error, e.g.:
47
+ *
48
+ * Error: traces fixture unavailable: no spans found for runId=…
49
+ *
50
+ * Construction never throws — only attribute / method access does.
51
+ */
52
+ export declare function unavailableTracesAccessor(reason: string): TracesAccessor;
53
+ /** Build a TracesAccessor from a flat list of spans. */
54
+ export declare function buildTracesAccessor(spans: Span[]): TracesAccessor;
55
+ //# sourceMappingURL=traces.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"traces.d.ts","sourceRoot":"","sources":["../../../matchers/traces.ts"],"names":[],"mappings":"AAKA;;;;;;;;;;;;;;;;;;GAkBG;AAEH,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,sBAAsB,CAAC;AAEjD,MAAM,WAAW,cAAc;IAC7B,oFAAoF;IACpF,WAAW,EAAE,MAAM,CAAC;IACpB,wEAAwE;IACxE,SAAS,EAAE,MAAM,CAAC;IAClB,kDAAkD;IAClD,SAAS,EAAE,aAAa,CAAC;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,UAAU,EAAE,MAAM,CAAA;KAAE,CAAC,CAAC;IAC/D,+EAA+E;IAC/E,YAAY,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAAC;IACnC,6BAA6B;IAC7B,KAAK,EAAE,aAAa,CAAC,IAAI,CAAC,CAAC;CAC5B;AAED;;;;GAIG;AACH,wBAAgB,mBAAmB,IAAI,cAAc,CAQpD;AAED;;;;;;;;;GASG;AACH,wBAAgB,yBAAyB,CAAC,MAAM,EAAE,MAAM,GAAG,cAAc,CAWxE;AAED,wDAAwD;AACxD,wBAAgB,mBAAmB,CAAC,KAAK,EAAE,IAAI,EAAE,GAAG,cAAc,CA4CjE"}