niceeval 0.9.1 → 0.10.2

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 (432) hide show
  1. package/INDEX.md +31 -33
  2. package/dist/agents/types.d.ts +20 -17
  3. package/dist/context/types.d.ts +21 -21
  4. package/dist/i18n/en.d.ts +10 -2
  5. package/dist/i18n/zh-CN.d.ts +14 -6
  6. package/dist/o11y/execution-tree.d.ts +103 -0
  7. package/dist/o11y/otlp/select.d.ts +22 -0
  8. package/dist/report/{react → assets}/colors.d.ts +8 -0
  9. package/dist/report/{react → assets}/colors.js +23 -0
  10. package/dist/report/built-in/index.d.ts +2 -2
  11. package/dist/report/built-in/index.js +2 -2
  12. package/dist/report/built-in/standard.d.ts +8 -1
  13. package/dist/report/built-in/standard.js +17 -7
  14. package/dist/report/components/attempt-detail/AttemptAssertions.d.ts +6 -0
  15. package/dist/report/components/attempt-detail/AttemptAssertions.js +17 -0
  16. package/dist/report/components/attempt-detail/AttemptConversation.d.ts +10 -0
  17. package/dist/report/components/attempt-detail/AttemptConversation.js +74 -0
  18. package/dist/report/components/attempt-detail/AttemptDiagnostics.d.ts +6 -0
  19. package/dist/report/components/attempt-detail/AttemptDiagnostics.js +7 -0
  20. package/dist/report/components/attempt-detail/AttemptDiff.d.ts +6 -0
  21. package/dist/report/components/attempt-detail/AttemptDiff.js +11 -0
  22. package/dist/report/components/attempt-detail/AttemptError.d.ts +6 -0
  23. package/dist/report/components/attempt-detail/AttemptError.js +16 -0
  24. package/dist/report/components/attempt-detail/AttemptFixPrompt.d.ts +6 -0
  25. package/dist/report/components/attempt-detail/AttemptFixPrompt.js +7 -0
  26. package/dist/report/components/attempt-detail/AttemptSource.d.ts +6 -0
  27. package/dist/report/components/attempt-detail/AttemptSource.js +97 -0
  28. package/dist/report/components/attempt-detail/AttemptSummary.d.ts +8 -0
  29. package/dist/report/components/attempt-detail/AttemptSummary.js +20 -0
  30. package/dist/report/components/attempt-detail/AttemptTimeline.d.ts +6 -0
  31. package/dist/report/components/attempt-detail/AttemptTimeline.js +28 -0
  32. package/dist/report/components/attempt-detail/AttemptTrace.d.ts +6 -0
  33. package/dist/report/components/attempt-detail/AttemptTrace.js +29 -0
  34. package/dist/report/components/attempt-detail/AttemptUsage.d.ts +6 -0
  35. package/dist/report/components/attempt-detail/AttemptUsage.js +20 -0
  36. package/dist/report/components/attempt-detail/compute.d.ts +24 -0
  37. package/dist/report/components/attempt-detail/compute.js +297 -0
  38. package/dist/report/components/attempt-detail/faces.d.ts +14 -0
  39. package/dist/report/components/attempt-detail/faces.js +239 -0
  40. package/dist/report/components/attempt-detail/index.d.ts +38 -0
  41. package/dist/report/components/attempt-detail/index.js +547 -0
  42. package/dist/report/{react → components}/cell.d.ts +5 -3
  43. package/dist/report/{react → components}/cell.js +3 -3
  44. package/dist/report/{react → components/entity-lists}/AttemptList.d.ts +8 -4
  45. package/dist/report/{react → components/entity-lists}/AttemptList.js +16 -10
  46. package/dist/report/{react → components/entity-lists}/EvalList.d.ts +3 -3
  47. package/dist/report/{react → components/entity-lists}/EvalList.js +0 -0
  48. package/dist/report/{react → components/entity-lists}/ExperimentList.d.ts +4 -5
  49. package/dist/report/{react → components/entity-lists}/ExperimentList.js +12 -11
  50. package/dist/report/components/entity-lists/compute.d.ts +23 -0
  51. package/dist/report/components/entity-lists/compute.js +171 -0
  52. package/dist/report/components/entity-lists/faces.d.ts +5 -0
  53. package/dist/report/components/entity-lists/faces.js +175 -0
  54. package/dist/report/components/entity-lists/index.d.ts +49 -0
  55. package/dist/report/components/entity-lists/index.js +169 -0
  56. package/dist/report/{react → components}/fixtures.d.ts +2 -2
  57. package/dist/report/{react → components}/fixtures.js +1 -1
  58. package/dist/report/{react → components/metric-views}/DeltaTable.d.ts +2 -2
  59. package/dist/report/{react → components/metric-views}/DeltaTable.js +4 -4
  60. package/dist/report/{react → components/metric-views}/MetricBars.d.ts +3 -3
  61. package/dist/report/{react → components/metric-views}/MetricBars.js +3 -3
  62. package/dist/report/{react → components/metric-views}/MetricLine.d.ts +2 -2
  63. package/dist/report/{react → components/metric-views}/MetricLine.js +8 -5
  64. package/dist/report/{react → components/metric-views}/MetricMatrix.d.ts +3 -3
  65. package/dist/report/{react → components/metric-views}/MetricMatrix.js +4 -4
  66. package/dist/report/components/metric-views/MetricScatter.d.ts +11 -0
  67. package/dist/report/{react → components/metric-views}/MetricScatter.js +27 -60
  68. package/dist/report/{react → components/metric-views}/MetricTable.d.ts +3 -3
  69. package/dist/report/{react → components/metric-views}/MetricTable.js +4 -4
  70. package/dist/report/{react → components/metric-views}/Scoreboard.d.ts +2 -2
  71. package/dist/report/{react → components/metric-views}/Scoreboard.js +3 -3
  72. package/dist/report/components/metric-views/compute.d.ts +89 -0
  73. package/dist/report/{compute.js → components/metric-views/compute.js} +32 -415
  74. package/dist/report/components/metric-views/faces.d.ts +13 -0
  75. package/dist/report/components/metric-views/faces.js +381 -0
  76. package/dist/report/components/metric-views/index.d.ts +50 -0
  77. package/dist/report/components/metric-views/index.js +273 -0
  78. package/dist/report/{text → components/metric-views}/plot.js +1 -1
  79. package/dist/report/components/shared-compute.d.ts +22 -0
  80. package/dist/report/components/shared-compute.js +47 -0
  81. package/dist/report/components/shared-faces.d.ts +9 -0
  82. package/dist/report/components/shared-faces.js +26 -0
  83. package/dist/report/components/shared.d.ts +68 -0
  84. package/dist/report/components/shared.js +125 -0
  85. package/dist/report/{react → components/site-components}/CopyFixPrompt.d.ts +2 -2
  86. package/dist/report/{react → components/site-components}/CopyFixPrompt.js +2 -2
  87. package/dist/report/{react → components/site-components}/HeroCard.d.ts +2 -2
  88. package/dist/report/{react → components/site-components}/HeroCard.js +2 -2
  89. package/dist/report/{react → components/site-components}/ScopeWarnings.d.ts +2 -2
  90. package/dist/report/{react → components/site-components}/ScopeWarnings.js +3 -3
  91. package/dist/report/{react → components/site-components}/TraceWaterfall.d.ts +3 -3
  92. package/dist/report/{react → components/site-components}/TraceWaterfall.js +5 -5
  93. package/dist/report/components/site-components/compute.d.ts +28 -0
  94. package/dist/report/components/site-components/compute.js +132 -0
  95. package/dist/report/components/site-components/faces.d.ts +21 -0
  96. package/dist/report/components/site-components/faces.js +75 -0
  97. package/dist/report/components/site-components/index.d.ts +74 -0
  98. package/dist/report/components/site-components/index.js +220 -0
  99. package/dist/report/{scope-warnings.d.ts → components/site-components/scope-warnings.d.ts} +2 -2
  100. package/dist/report/{scope-warnings.js → components/site-components/scope-warnings.js} +2 -2
  101. package/dist/report/{react → components/summaries}/ScopeSummary.d.ts +2 -2
  102. package/dist/report/{react → components/summaries}/ScopeSummary.js +17 -8
  103. package/dist/report/components/summaries/compute.d.ts +7 -0
  104. package/dist/report/components/summaries/compute.js +51 -0
  105. package/dist/report/components/summaries/faces.d.ts +7 -0
  106. package/dist/report/components/summaries/faces.js +38 -0
  107. package/dist/report/components/summaries/index.d.ts +27 -0
  108. package/dist/report/components/summaries/index.js +78 -0
  109. package/dist/report/definition/grid-layout.d.ts +50 -0
  110. package/dist/report/definition/grid-layout.js +89 -0
  111. package/dist/report/{primitives.d.ts → definition/primitives.d.ts} +34 -4
  112. package/dist/report/{primitives.js → definition/primitives.js} +101 -10
  113. package/dist/report/{report.d.ts → definition/report.d.ts} +36 -65
  114. package/dist/report/{report.js → definition/report.js} +58 -90
  115. package/dist/report/{text/table.d.ts → definition/table-text.d.ts} +2 -2
  116. package/dist/report/{text/table.js → definition/table-text.js} +2 -2
  117. package/dist/report/{tree.d.ts → definition/tree.d.ts} +43 -11
  118. package/dist/report/{tree.js → definition/tree.js} +9 -11
  119. package/dist/report/index.d.ts +33 -18
  120. package/dist/report/index.js +23 -14
  121. package/dist/report/{aggregate.d.ts → model/aggregate.d.ts} +12 -4
  122. package/dist/report/{aggregate.js → model/aggregate.js} +28 -8
  123. package/dist/report/{flag.d.ts → model/flag.d.ts} +14 -1
  124. package/dist/report/{flag.js → model/flag.js} +35 -0
  125. package/dist/report/{format.d.ts → model/format.d.ts} +13 -7
  126. package/dist/report/{format.js → model/format.js} +79 -9
  127. package/dist/report/{locale.d.ts → model/locale.d.ts} +17 -17
  128. package/dist/report/{locale.js → model/locale.js} +31 -33
  129. package/dist/report/{metrics.d.ts → model/metrics.d.ts} +2 -2
  130. package/dist/report/{metrics.js → model/metrics.js} +2 -2
  131. package/dist/report/{types.d.ts → model/types.d.ts} +154 -20
  132. package/dist/report/react/index.d.ts +32 -21
  133. package/dist/report/react/index.js +33 -21
  134. package/dist/report/{load.d.ts → runtime/load.d.ts} +1 -1
  135. package/dist/report/{load.js → runtime/load.js} +1 -1
  136. package/dist/report/runtime/text.d.ts +67 -0
  137. package/dist/report/runtime/text.js +114 -0
  138. package/dist/report/runtime/web.d.ts +35 -0
  139. package/dist/report/runtime/web.js +70 -0
  140. package/dist/results/annotated-source.d.ts +87 -0
  141. package/dist/results/attempt-evidence.d.ts +74 -0
  142. package/dist/results/attempt-source.d.ts +15 -0
  143. package/dist/results/select.d.ts +11 -1
  144. package/dist/results/select.js +27 -5
  145. package/dist/runner/eval-selection.d.ts +26 -0
  146. package/dist/runner/feedback/sink.d.ts +26 -1
  147. package/dist/runner/types.d.ts +151 -24
  148. package/dist/sandbox/docker.d.ts +6 -0
  149. package/dist/sandbox/e2b.d.ts +0 -1
  150. package/dist/sandbox/types.d.ts +23 -21
  151. package/dist/scoring/display.d.ts +7 -2
  152. package/dist/scoring/display.js +42 -4
  153. package/dist/scoring/types.d.ts +3 -3
  154. package/dist/shared/aggregate.d.ts +14 -0
  155. package/dist/shared/aggregate.js +31 -0
  156. package/dist/shared/types.d.ts +6 -1
  157. package/docs-site/images/logo-dark.svg +7 -0
  158. package/docs-site/images/logo.svg +6 -5
  159. package/docs-site/zh/README.md +8 -7
  160. package/docs-site/zh/examples/ai-agent-application.mdx +5 -5
  161. package/docs-site/zh/examples/coding-agent-extensions.mdx +4 -4
  162. package/docs-site/zh/examples/index.mdx +3 -3
  163. package/docs-site/zh/examples/integrations/ai-sdk-v7.mdx +6 -6
  164. package/docs-site/zh/examples/integrations/claude-sdk.mdx +3 -3
  165. package/docs-site/zh/examples/integrations/codex-sdk.mdx +3 -3
  166. package/docs-site/zh/examples/integrations/langgraph.mdx +3 -3
  167. package/docs-site/zh/examples/integrations/pi-sdk.mdx +2 -2
  168. package/docs-site/zh/explanation/adapter.mdx +19 -19
  169. package/docs-site/zh/explanation/assert.mdx +9 -9
  170. package/docs-site/zh/explanation/drive.mdx +4 -4
  171. package/docs-site/zh/explanation/evals.mdx +8 -8
  172. package/docs-site/zh/explanation/experiment.mdx +8 -8
  173. package/docs-site/zh/explanation/hitl.mdx +13 -13
  174. package/docs-site/zh/explanation/judge.mdx +3 -3
  175. package/docs-site/zh/explanation/overview.mdx +7 -7
  176. package/docs-site/zh/explanation/runner.mdx +17 -13
  177. package/docs-site/zh/explanation/tier.mdx +6 -6
  178. package/docs-site/zh/index.mdx +14 -14
  179. package/docs-site/zh/introduction.mdx +13 -16
  180. package/docs-site/zh/reference/builtin-agents.mdx +61 -28
  181. package/docs-site/zh/reference/capabilities.mdx +7 -27
  182. package/docs-site/zh/reference/cli.mdx +36 -33
  183. package/docs-site/zh/reference/define-agent.mdx +32 -31
  184. package/docs-site/zh/reference/define-config.mdx +6 -6
  185. package/docs-site/zh/reference/define-eval.mdx +33 -20
  186. package/docs-site/zh/reference/events.mdx +4 -4
  187. package/docs-site/zh/reference/expect.mdx +3 -3
  188. package/docs-site/zh/reference/official-adapters.mdx +17 -17
  189. package/docs-site/zh/reference/report-components.mdx +195 -121
  190. package/docs-site/zh/reference/results-data.mdx +13 -13
  191. package/docs-site/zh/troubleshooting/debug-sandbox.mdx +11 -11
  192. package/docs-site/zh/troubleshooting/debugging.mdx +40 -16
  193. package/docs-site/zh/{how-to → tutorials}/agent-feedback-loop.mdx +38 -38
  194. package/docs-site/zh/tutorials/agent-onboarding.mdx +100 -0
  195. package/docs-site/zh/tutorials/authoring.mdx +211 -0
  196. package/docs-site/zh/{how-to → tutorials}/ci-integration.mdx +8 -8
  197. package/docs-site/zh/{how-to → tutorials}/connect-otel.mdx +22 -22
  198. package/docs-site/zh/{how-to → tutorials}/connect-your-agent.mdx +58 -63
  199. package/docs-site/zh/tutorials/custom-reports.mdx +453 -0
  200. package/docs-site/zh/{how-to → tutorials}/dataset-fanout.mdx +4 -4
  201. package/docs-site/zh/tutorials/experiments.mdx +102 -0
  202. package/docs-site/zh/{how-to → tutorials}/fixtures.mdx +9 -9
  203. package/docs-site/zh/{how-to → tutorials}/publish-report.mdx +6 -6
  204. package/docs-site/zh/tutorials/quickstart.mdx +18 -18
  205. package/docs-site/zh/{how-to → tutorials}/reporters.mdx +6 -6
  206. package/docs-site/zh/{how-to → tutorials}/sandbox-agent.mdx +6 -6
  207. package/docs-site/zh/{how-to → tutorials}/sandbox-providers.mdx +41 -19
  208. package/docs-site/zh/{how-to → tutorials}/scoring-guide.mdx +4 -4
  209. package/docs-site/zh/{how-to → tutorials}/viewing-results.mdx +60 -57
  210. package/docs-site/zh/tutorials/write-experiment.mdx +353 -0
  211. package/docs-site/zh/{how-to → tutorials}/write-send.mdx +40 -40
  212. package/package.json +10 -7
  213. package/src/agents/bub.ts +21 -8
  214. package/src/agents/claude-code.ts +23 -10
  215. package/src/agents/codex.test.ts +22 -7
  216. package/src/agents/codex.ts +22 -9
  217. package/src/agents/index.ts +2 -2
  218. package/src/agents/openai-compat.ts +1 -1
  219. package/src/agents/post-setup.ts +45 -22
  220. package/src/agents/streaming.ts +1 -1
  221. package/src/agents/types.ts +20 -17
  222. package/src/agents/ui-message-stream.test.ts +10 -0
  223. package/src/agents/ui-message-stream.ts +12 -1
  224. package/src/cli.ts +75 -59
  225. package/src/context/types.ts +21 -21
  226. package/src/define.ts +13 -0
  227. package/src/i18n/en.ts +27 -12
  228. package/src/i18n/zh-CN.ts +27 -12
  229. package/src/index.ts +2 -0
  230. package/src/o11y/prices.json +176 -99
  231. package/src/report/{react → assets}/colors.ts +22 -0
  232. package/src/report/{react → assets}/enhance.js +1 -33
  233. package/src/report/assets/styles.css +1785 -0
  234. package/src/report/built-in/index.tsx +2 -2
  235. package/src/report/built-in/standard.tsx +18 -6
  236. package/src/report/components/attempt-detail/AttemptAssertions.tsx +67 -0
  237. package/src/report/components/attempt-detail/AttemptConversation.tsx +158 -0
  238. package/src/report/components/attempt-detail/AttemptDiagnostics.tsx +38 -0
  239. package/src/report/components/attempt-detail/AttemptDiff.tsx +35 -0
  240. package/src/report/components/attempt-detail/AttemptError.tsx +31 -0
  241. package/src/report/components/attempt-detail/AttemptFixPrompt.tsx +26 -0
  242. package/src/report/components/attempt-detail/AttemptSource.tsx +224 -0
  243. package/src/report/components/attempt-detail/AttemptSummary.tsx +74 -0
  244. package/src/report/components/attempt-detail/AttemptTimeline.tsx +108 -0
  245. package/src/report/components/attempt-detail/AttemptTrace.tsx +63 -0
  246. package/src/report/components/attempt-detail/AttemptUsage.tsx +29 -0
  247. package/src/report/components/attempt-detail/attempt-components.test.tsx +758 -0
  248. package/src/report/components/attempt-detail/compute.ts +336 -0
  249. package/src/report/components/attempt-detail/faces.ts +260 -0
  250. package/src/report/components/attempt-detail/index.tsx +600 -0
  251. package/src/report/components/attempt-detail/validate.test.ts +252 -0
  252. package/src/report/{react → components}/cell.tsx +6 -3
  253. package/src/report/{report.test.ts → components/compute.test.ts} +316 -46
  254. package/src/report/{react → components/entity-lists}/AttemptList.tsx +24 -16
  255. package/src/report/{react → components/entity-lists}/EvalList.tsx +0 -0
  256. package/src/report/{react → components/entity-lists}/ExperimentList.tsx +33 -27
  257. package/src/report/components/entity-lists/compute.ts +196 -0
  258. package/src/report/components/entity-lists/faces.ts +208 -0
  259. package/src/report/components/entity-lists/index.tsx +238 -0
  260. package/src/report/components/entity-lists/validate.test.ts +114 -0
  261. package/src/report/{react → components}/fixtures.ts +2 -2
  262. package/src/report/{react → components/metric-views}/DeltaTable.tsx +5 -5
  263. package/src/report/{react → components/metric-views}/MetricBars.tsx +5 -5
  264. package/src/report/{react → components/metric-views}/MetricLine.tsx +9 -6
  265. package/src/report/{react → components/metric-views}/MetricMatrix.tsx +6 -6
  266. package/src/report/{react → components/metric-views}/MetricScatter.tsx +42 -70
  267. package/src/report/{react → components/metric-views}/MetricTable.tsx +6 -6
  268. package/src/report/{react → components/metric-views}/Scoreboard.tsx +4 -4
  269. package/src/report/{compute.ts → components/metric-views/compute.ts} +51 -477
  270. package/src/report/components/metric-views/faces.ts +423 -0
  271. package/src/report/components/metric-views/index.tsx +352 -0
  272. package/src/report/{text → components/metric-views}/plot.ts +1 -1
  273. package/src/report/components/metric-views/validate.test.ts +211 -0
  274. package/src/report/{react → components}/render.test.tsx +66 -26
  275. package/src/report/components/shared-compute.ts +59 -0
  276. package/src/report/components/shared-faces.ts +30 -0
  277. package/src/report/components/shared.ts +192 -0
  278. package/src/report/{react → components/site-components}/CopyFixPrompt.tsx +3 -3
  279. package/src/report/{react → components/site-components}/HeroCard.tsx +3 -3
  280. package/src/report/{react → components/site-components}/ScopeWarnings.tsx +4 -4
  281. package/src/report/{react → components/site-components}/TraceWaterfall.tsx +13 -10
  282. package/src/report/components/site-components/compute.ts +144 -0
  283. package/src/report/components/site-components/faces.ts +80 -0
  284. package/src/report/components/site-components/index.tsx +265 -0
  285. package/src/report/{scope-warnings.ts → components/site-components/scope-warnings.ts} +3 -3
  286. package/src/report/{site-components.test.tsx → components/site-components/site-components.test.tsx} +23 -21
  287. package/src/report/components/site-components/validate.test.ts +89 -0
  288. package/src/report/{react → components/summaries}/ScopeSummary.tsx +26 -11
  289. package/src/report/components/summaries/compute.ts +56 -0
  290. package/src/report/components/summaries/faces.ts +48 -0
  291. package/src/report/components/summaries/index.tsx +127 -0
  292. package/src/report/components/summaries/validate.test.ts +49 -0
  293. package/src/report/definition/grid-layout.test.ts +124 -0
  294. package/src/report/definition/grid-layout.ts +146 -0
  295. package/src/report/{primitives.tsx → definition/primitives.tsx} +168 -18
  296. package/src/report/{report.ts → definition/report.ts} +98 -165
  297. package/src/report/{shell-head.test.ts → definition/shell-head.test.ts} +2 -2
  298. package/src/report/{text/table.ts → definition/table-text.ts} +4 -4
  299. package/src/report/{tree.ts → definition/tree.ts} +56 -20
  300. package/src/report/index.ts +128 -66
  301. package/src/report/{aggregate.ts → model/aggregate.ts} +31 -9
  302. package/src/report/{flag.ts → model/flag.ts} +39 -1
  303. package/src/report/{format.ts → model/format.ts} +89 -10
  304. package/src/report/{locale.ts → model/locale.ts} +34 -36
  305. package/src/report/{metrics.ts → model/metrics.ts} +3 -3
  306. package/src/report/{types.ts → model/types.ts} +159 -22
  307. package/src/report/react/index.tsx +54 -26
  308. package/src/report/{dual-render.test.tsx → runtime/dual-render.test.tsx} +601 -53
  309. package/src/report/runtime/host.test.ts +44 -0
  310. package/src/report/runtime/host.ts +138 -0
  311. package/src/report/{load.ts → runtime/load.ts} +1 -1
  312. package/src/report/runtime/text.ts +192 -0
  313. package/src/report/runtime/web.ts +106 -0
  314. package/src/results/attempt-evidence.ts +5 -1
  315. package/src/results/host-equivalence.test.ts +53 -2
  316. package/src/results/select.ts +29 -5
  317. package/src/runner/attempt.test.ts +48 -1
  318. package/src/runner/attempt.ts +62 -42
  319. package/src/runner/cleanup-timeout.test.ts +16 -0
  320. package/src/runner/cleanup-timeout.ts +23 -0
  321. package/src/runner/discover.ts +1 -2
  322. package/src/runner/eval-selection.test.ts +187 -0
  323. package/src/runner/eval-selection.ts +109 -0
  324. package/src/runner/experiment-cleanup-registry.test.ts +89 -0
  325. package/src/runner/experiment-cleanup-registry.ts +39 -0
  326. package/src/runner/experiment-labels.test.ts +71 -0
  327. package/src/runner/feedback/agent.test.ts +33 -1
  328. package/src/runner/feedback/agent.ts +12 -16
  329. package/src/runner/feedback/ci.test.ts +35 -1
  330. package/src/runner/feedback/ci.ts +16 -18
  331. package/src/runner/feedback/coordinator.ts +28 -0
  332. package/src/runner/feedback/human.test.ts +108 -1
  333. package/src/runner/feedback/human.ts +71 -21
  334. package/src/runner/feedback/reducer.test.ts +64 -0
  335. package/src/runner/feedback/reducer.ts +26 -0
  336. package/src/runner/feedback/sink.ts +40 -1
  337. package/src/runner/fingerprint.ts +2 -1
  338. package/src/runner/report.test.ts +14 -0
  339. package/src/runner/report.ts +3 -1
  340. package/src/runner/run.test.ts +390 -12
  341. package/src/runner/run.ts +259 -26
  342. package/src/runner/sandbox-selection.test.ts +13 -3
  343. package/src/runner/sandbox-selection.ts +4 -2
  344. package/src/runner/types.ts +160 -24
  345. package/src/sandbox/docker.ts +7 -0
  346. package/src/sandbox/e2b-reconcile.test.ts +125 -0
  347. package/src/sandbox/e2b.ts +47 -12
  348. package/src/sandbox/types.ts +23 -21
  349. package/src/scoring/display.test.ts +28 -2
  350. package/src/scoring/display.ts +38 -5
  351. package/src/scoring/types.ts +3 -3
  352. package/src/shared/aggregate.test.ts +52 -0
  353. package/src/shared/aggregate.ts +29 -0
  354. package/src/shared/types.ts +6 -1
  355. package/src/show/command.test.ts +34 -0
  356. package/src/show/command.ts +16 -0
  357. package/src/show/compose.ts +1 -1
  358. package/src/show/index.ts +56 -20
  359. package/src/show/render.ts +15 -239
  360. package/src/show/show.test.ts +127 -34
  361. package/src/view/app/App.test.tsx +1 -1
  362. package/src/view/app/App.tsx +119 -47
  363. package/src/view/app/i18n.ts +7 -147
  364. package/src/view/app/lib/attempt-dialog.test.ts +65 -0
  365. package/src/view/app/lib/attempt-dialog.ts +69 -0
  366. package/src/view/app/main.tsx +0 -1
  367. package/src/view/app/types.ts +3 -86
  368. package/src/view/artifact-serving.test.ts +22 -38
  369. package/src/view/client-dist/app.css +1 -1
  370. package/src/view/client-dist/app.js +15 -22
  371. package/src/view/data.test.ts +48 -36
  372. package/src/view/data.ts +105 -83
  373. package/src/view/index.ts +1 -1
  374. package/src/view/server.ts +32 -2
  375. package/src/view/shared/types.ts +6 -31
  376. package/src/view/site-parity.test.ts +24 -1
  377. package/src/view/site.ts +144 -17
  378. package/src/view/styles.css +0 -805
  379. package/src/view/view-report.test.ts +143 -22
  380. package/dist/report/components.d.ts +0 -179
  381. package/dist/report/components.js +0 -544
  382. package/dist/report/compute.d.ts +0 -139
  383. package/dist/report/react/ExperimentComparison.d.ts +0 -10
  384. package/dist/report/react/ExperimentComparison.js +0 -12
  385. package/dist/report/react/MetricScatter.d.ts +0 -9
  386. package/dist/report/react/format.d.ts +0 -3
  387. package/dist/report/react/format.js +0 -7
  388. package/dist/report/text/faces.d.ts +0 -45
  389. package/dist/report/text/faces.js +0 -671
  390. package/dist/report/web.d.ts +0 -32
  391. package/dist/report/web.js +0 -48
  392. package/docs-site/zh/how-to/authoring.mdx +0 -162
  393. package/docs-site/zh/how-to/custom-reports.mdx +0 -414
  394. package/docs-site/zh/how-to/experiments.mdx +0 -86
  395. package/docs-site/zh/how-to/write-experiment.mdx +0 -164
  396. package/src/report/components.tsx +0 -925
  397. package/src/report/react/ExperimentComparison.tsx +0 -73
  398. package/src/report/react/format.ts +0 -9
  399. package/src/report/react/styles.css +0 -945
  400. package/src/report/text/faces.ts +0 -767
  401. package/src/report/web.ts +0 -77
  402. package/src/show/report-host.test.ts +0 -205
  403. package/src/show/report-host.ts +0 -389
  404. package/src/view/app/components/AttemptModal.tsx +0 -496
  405. package/src/view/app/components/CodeView.test.tsx +0 -142
  406. package/src/view/app/components/CodeView.tsx +0 -310
  407. package/src/view/app/components/CopyControls.tsx +0 -106
  408. package/src/view/app/components/Trace.tsx +0 -100
  409. package/src/view/app/components/Transcript.tsx +0 -157
  410. package/src/view/app/components/ui/badge.tsx +0 -21
  411. package/src/view/app/lib/artifact-url.ts +0 -17
  412. package/src/view/app/lib/attempt-route.test.ts +0 -80
  413. package/src/view/app/lib/attempt-route.ts +0 -52
  414. package/src/view/app/lib/format.ts +0 -70
  415. package/src/view/app/lib/guards.test.ts +0 -108
  416. package/src/view/app/lib/guards.ts +0 -71
  417. package/src/view/app/lib/rows.ts +0 -22
  418. package/src/view/app/lib/transcript-data.tsx +0 -151
  419. package/src/view/app/lib/verdict.ts +0 -23
  420. package/src/view/app/shared.ts +0 -8
  421. /package/dist/report/{react → components/metric-views}/chart-math.d.ts +0 -0
  422. /package/dist/report/{react → components/metric-views}/chart-math.js +0 -0
  423. /package/dist/report/{text → components/metric-views}/plot.d.ts +0 -0
  424. /package/dist/report/{react → components/site-components}/PoweredBy.d.ts +0 -0
  425. /package/dist/report/{react → components/site-components}/PoweredBy.js +0 -0
  426. /package/dist/report/{text/layout.d.ts → model/text-layout.d.ts} +0 -0
  427. /package/dist/report/{text/layout.js → model/text-layout.js} +0 -0
  428. /package/dist/report/{types.js → model/types.js} +0 -0
  429. /package/src/report/{react → components/metric-views}/chart-math.test.ts +0 -0
  430. /package/src/report/{react → components/metric-views}/chart-math.ts +0 -0
  431. /package/src/report/{react → components/site-components}/PoweredBy.tsx +0 -0
  432. /package/src/report/{text/layout.ts → model/text-layout.ts} +0 -0
@@ -0,0 +1,252 @@
1
+ // cases: docs/engineering/unit-tests/reports/cases.md
2
+ // "validate*Data 递归覆盖到嵌套字段" 行:attempt-detail 十一个叶子的 validate*Data 表驱动字段突变覆盖,重点是 AttemptConversationData
3
+ // 的 AttemptConversationReply 判别联合(每个 kind 分支各自的必填字段)与其余嵌套结构
4
+ // (AttemptIdentity / AssertionResult 判别联合 / TraceSpan / AttemptDiffFileEntry 的 net 枚举)。
5
+
6
+ import { describe, expect, it } from "vitest";
7
+ import {
8
+ validateAssertionsData,
9
+ validateConversationData,
10
+ validateDiagnosticsData,
11
+ validateDiffData,
12
+ validateErrorData,
13
+ validateSourceData,
14
+ validateSummaryData,
15
+ validateTimelineData,
16
+ validateTraceData,
17
+ validateUsageData,
18
+ } from "./index.tsx";
19
+
20
+ const validIdentity = { experimentId: "compare/codex", snapshotStartedAt: "2026-07-01T00:00:00Z", evalId: "q1", attempt: 0 };
21
+ const validCapabilities = { source: true, execution: true, timing: false, diff: false };
22
+
23
+ describe("validateSummaryData", () => {
24
+ const valid = {
25
+ locator: "@1abcdef2",
26
+ identity: validIdentity,
27
+ verdict: "passed",
28
+ durationMs: 1000,
29
+ costUSD: 0.01,
30
+ capabilities: validCapabilities,
31
+ };
32
+
33
+ it("合规 literal 通过", () => {
34
+ expect(validateSummaryData(valid)).toBeNull();
35
+ });
36
+
37
+ it("costUSD 为 null 合法(缺失不冒充 0)", () => {
38
+ expect(validateSummaryData({ ...valid, costUSD: null })).toBeNull();
39
+ });
40
+
41
+ it("identity 缺 snapshotStartedAt 报错定位到嵌套字段", () => {
42
+ const bad = { ...valid, identity: { experimentId: "compare/codex", evalId: "q1", attempt: 0 } };
43
+ expect(validateSummaryData(bad)).toMatch(/"identity\.snapshotStartedAt"/);
44
+ });
45
+
46
+ it("capabilities.timing 非布尔报错", () => {
47
+ const bad = { ...valid, capabilities: { ...validCapabilities, timing: "false" } };
48
+ expect(validateSummaryData(bad)).toMatch(/"capabilities\.timing"/);
49
+ });
50
+ });
51
+
52
+ describe("validateErrorData", () => {
53
+ const valid = { code: "unexpected-error", message: "boom", phase: "eval.run" };
54
+
55
+ it("合规 literal 通过", () => {
56
+ expect(validateErrorData(valid)).toBeNull();
57
+ });
58
+
59
+ it("缺 phase 报错", () => {
60
+ expect(validateErrorData({ code: "x", message: "boom" })).toMatch(/"phase"/);
61
+ });
62
+ });
63
+
64
+ describe("validateAssertionsData", () => {
65
+ const passed = { name: "eq", severity: "gate", outcome: "passed", score: 1 };
66
+ const unavailable = { name: "judge", severity: "soft", outcome: "unavailable", reason: "judge-model-unresolved" };
67
+
68
+ it("合规 literal 通过(含 unavailable 分支)", () => {
69
+ const valid = { attention: [unavailable], passedGroups: [{ group: "", items: [passed] }] };
70
+ expect(validateAssertionsData(valid)).toBeNull();
71
+ });
72
+
73
+ it("passed/failed 分支缺 score 报错", () => {
74
+ const bad = { attention: [{ name: "eq", severity: "gate", outcome: "passed" }], passedGroups: [] };
75
+ expect(validateAssertionsData(bad)).toMatch(/"attention\[0\]\.score"/);
76
+ });
77
+
78
+ it("unavailable 分支缺 reason 报错", () => {
79
+ const bad = { attention: [{ name: "judge", severity: "soft", outcome: "unavailable" }], passedGroups: [] };
80
+ expect(validateAssertionsData(bad)).toMatch(/"attention\[0\]\.reason"/);
81
+ });
82
+
83
+ it("outcome 不在判别集合内报错", () => {
84
+ const bad = { attention: [{ name: "eq", severity: "gate", outcome: "flaky", score: 1 }], passedGroups: [] };
85
+ expect(validateAssertionsData(bad)).toMatch(/"attention\[0\]\.outcome"/);
86
+ });
87
+
88
+ it("passedGroups[i].items 嵌套断言报错定位到分组内下标", () => {
89
+ const bad = { attention: [], passedGroups: [{ group: "setup", items: [{ name: "eq", severity: "gate" }] }] };
90
+ expect(validateAssertionsData(bad)).toMatch(/"passedGroups\[0\]\.items\[0\]\.outcome"/);
91
+ });
92
+ });
93
+
94
+ describe("validateSourceData", () => {
95
+ const validSummary = {
96
+ totalAssertions: 1,
97
+ mappedAssertions: 1,
98
+ unmappedAssertions: 0,
99
+ passed: 1,
100
+ failed: 0,
101
+ gate: 1,
102
+ soft: 0,
103
+ totalLines: 10,
104
+ annotatedLines: 1,
105
+ };
106
+ const valid = {
107
+ locator: "@1abcdef2",
108
+ sourcePath: "eval.ts",
109
+ lines: [{ line: 1, text: "t.send(...)", assertions: [], sends: [], turns: [] }],
110
+ unmapped: [],
111
+ unlocatedTurns: [],
112
+ summary: validSummary,
113
+ };
114
+
115
+ it("合规 literal 通过", () => {
116
+ expect(validateSourceData(valid)).toBeNull();
117
+ });
118
+
119
+ it("summary 缺 totalLines 报错", () => {
120
+ const bad = { ...valid, summary: { ...validSummary, totalLines: undefined } };
121
+ expect(validateSourceData(bad)).toMatch(/"summary\.totalLines"/);
122
+ });
123
+
124
+ it("summary 缺 annotatedLines 报错", () => {
125
+ const bad = { ...valid, summary: { ...validSummary, annotatedLines: undefined } };
126
+ expect(validateSourceData(bad)).toMatch(/"summary\.annotatedLines"/);
127
+ });
128
+
129
+ it("lines[i].assertions 嵌套断言结构错误报错", () => {
130
+ const bad = { ...valid, lines: [{ line: 1, text: "x", assertions: [{ name: "eq" }], sends: [], turns: [] }] };
131
+ expect(validateSourceData(bad)).toMatch(/"lines\[0\]\.assertions\[0\]\.severity"/);
132
+ });
133
+
134
+ it("lines[i].turns[j].replies[k] 递归校验回复判别联合", () => {
135
+ const bad = {
136
+ ...valid,
137
+ lines: [
138
+ {
139
+ line: 1,
140
+ text: "x",
141
+ assertions: [],
142
+ sends: [],
143
+ turns: [{ label: "s1/t1", status: "completed", sentText: "go", replies: [{ kind: "assistant" }] }],
144
+ },
145
+ ],
146
+ };
147
+ expect(validateSourceData(bad)).toMatch(/"lines\[0\]\.turns\[0\]\.replies\[0\]\.text"/);
148
+ });
149
+ });
150
+
151
+ describe("validateTimelineData", () => {
152
+ const valid = { locator: "@1abcdef2", phases: [{ name: "eval.run", durationMs: 500 }], trace: null };
153
+
154
+ it("合规 literal 通过(trace 为 null)", () => {
155
+ expect(validateTimelineData(valid)).toBeNull();
156
+ });
157
+
158
+ it("trace 为数组时逐项校验 TraceSpan", () => {
159
+ const bad = { ...valid, trace: [{ traceId: "t1", spanId: "s1", name: "turn", startMs: 0 }] };
160
+ expect(validateTimelineData(bad)).toMatch(/"trace\[0\]\.endMs"/);
161
+ });
162
+
163
+ it("phases[i] 缺 durationMs 报错", () => {
164
+ const bad = { ...valid, phases: [{ name: "eval.run" }] };
165
+ expect(validateTimelineData(bad)).toMatch(/"phases\[0\]\.durationMs"/);
166
+ });
167
+ });
168
+
169
+ describe("validateConversationData — AttemptConversationReply 判别联合", () => {
170
+ const valid = {
171
+ locator: "@1abcdef2",
172
+ rounds: [{ sentText: "go", replies: [{ kind: "assistant", text: "ok" }] }],
173
+ };
174
+
175
+ it("合规 literal 通过", () => {
176
+ expect(validateConversationData(valid)).toBeNull();
177
+ });
178
+
179
+ it.each([
180
+ ["assistant", { kind: "assistant" }, /"rounds\[0\]\.replies\[0\]\.text"/],
181
+ ["tool 缺 callId", { kind: "tool", name: "shell", input: "ls" }, /"rounds\[0\]\.replies\[0\]\.callId"/],
182
+ ["tool 缺 input", { kind: "tool", callId: "c1", name: "shell" }, /"rounds\[0\]\.replies\[0\]\.input"/],
183
+ ["skill 缺 skill", { kind: "skill" }, /"rounds\[0\]\.replies\[0\]\.skill"/],
184
+ ["subagent 缺 name", { kind: "subagent", callId: "c1" }, /"rounds\[0\]\.replies\[0\]\.name"/],
185
+ ["input 缺 request", { kind: "input" }, /"rounds\[0\]\.replies\[0\]\.request"/],
186
+ ["raw 缺 raw", { kind: "raw" }, /"rounds\[0\]\.replies\[0\]\.raw"/],
187
+ ["未知 kind", { kind: "unknown-future-kind" }, /"rounds\[0\]\.replies\[0\]\.kind"/],
188
+ ])("%s 报错定位到具体缺失字段", (_label, reply, expected) => {
189
+ const bad = { locator: "@1abcdef2", rounds: [{ sentText: "go", replies: [reply] }] };
190
+ expect(validateConversationData(bad)).toMatch(expected);
191
+ });
192
+
193
+ it("compaction 分支无必填字段,裸 { kind: 'compaction' } 合法", () => {
194
+ const ok = { locator: "@1abcdef2", rounds: [{ sentText: "go", replies: [{ kind: "compaction" }] }] };
195
+ expect(validateConversationData(ok)).toBeNull();
196
+ });
197
+
198
+ it("round.loc 存在时校验 SourceLoc 结构;省略 loc 合法(流首无位置信息的兜底轮)", () => {
199
+ expect(validateConversationData(valid)).toBeNull();
200
+ const withLoc = { locator: "@1abcdef2", rounds: [{ loc: { file: "eval.ts", line: 3 }, sentText: "go", replies: [] }] };
201
+ expect(validateConversationData(withLoc)).toBeNull();
202
+ const badLoc = { locator: "@1abcdef2", rounds: [{ loc: { file: "eval.ts" }, sentText: "go", replies: [] }] };
203
+ expect(validateConversationData(badLoc)).toMatch(/"rounds\[0\]\.loc\.line"/);
204
+ });
205
+ });
206
+
207
+ describe("validateDiagnosticsData", () => {
208
+ it("合规 literal 通过", () => {
209
+ const valid = { groups: [{ phase: "eval.run", items: [{ code: "x", level: "warning", message: "m", phase: "eval.run" }] }] };
210
+ expect(validateDiagnosticsData(valid)).toBeNull();
211
+ });
212
+
213
+ it("level 不在 warning/error 内报错", () => {
214
+ const bad = { groups: [{ phase: "eval.run", items: [{ code: "x", level: "info", message: "m", phase: "eval.run" }] }] };
215
+ expect(validateDiagnosticsData(bad)).toMatch(/"groups\[0\]\.items\[0\]\.level"/);
216
+ });
217
+ });
218
+
219
+ describe("validateUsageData", () => {
220
+ it("合规 literal 通过,costUSD 为 null 合法", () => {
221
+ expect(validateUsageData({ usage: { inputTokens: 1, outputTokens: 2 }, costUSD: null })).toBeNull();
222
+ });
223
+
224
+ it("usage 缺 outputTokens 报错", () => {
225
+ expect(validateUsageData({ usage: { inputTokens: 1 }, costUSD: null })).toMatch(/"usage\.outputTokens"/);
226
+ });
227
+ });
228
+
229
+ describe("validateTraceData", () => {
230
+ it("spans[i] 缺 spanId 报错", () => {
231
+ const bad = { locator: "@1abcdef2", spans: [{ traceId: "t1", name: "turn", startMs: 0, endMs: 1 }] };
232
+ expect(validateTraceData(bad)).toMatch(/"spans\[0\]\.spanId"/);
233
+ });
234
+ });
235
+
236
+ describe("validateDiffData", () => {
237
+ const valid = { locator: "@1abcdef2", files: [{ path: "a.ts", net: "modified", lines: { added: 1, deleted: 0 }, windows: ["s1/t1"] }] };
238
+
239
+ it("合规 literal 通过", () => {
240
+ expect(validateDiffData(valid)).toBeNull();
241
+ });
242
+
243
+ it("net 不在三态枚举内报错", () => {
244
+ const bad = { ...valid, files: [{ ...valid.files[0], net: "none" }] };
245
+ expect(validateDiffData(bad)).toMatch(/"files\[0\]\.net"/);
246
+ });
247
+
248
+ it("lines 结构错误报错", () => {
249
+ const bad = { ...valid, files: [{ ...valid.files[0], lines: { added: 1 } }] };
250
+ expect(validateDiffData(bad)).toMatch(/"files\[0\]\.lines"/);
251
+ });
252
+ });
@@ -3,18 +3,21 @@
3
3
  // 纯渲染、零 hooks;交互只有普通 <a>(下钻由使用者的 attemptHref 决定去处)。
4
4
 
5
5
  import type { ReactElement } from "react";
6
- import type { MetricCell } from "../types.ts";
6
+ import type { MetricCell } from "../model/types.ts";
7
7
  import type { AttemptLocator } from "../../results/locator.ts";
8
- import { DEFAULT_REPORT_LOCALE, localeText, resolveLocalizedText, type ReportLocale } from "../locale.ts";
8
+ import { DEFAULT_REPORT_LOCALE, localeText, resolveLocalizedText, type ReportLocale } from "../model/locale.ts";
9
9
 
10
10
  export function MetricCellView({
11
11
  cell,
12
12
  attemptHref,
13
13
  locale = DEFAULT_REPORT_LOCALE,
14
+ showCoverage = true,
14
15
  }: {
15
16
  cell: MetricCell;
16
17
  attemptHref?: (locator: AttemptLocator) => string;
17
18
  locale?: ReportLocale;
19
+ /** 默认用紧凑角标显示覆盖率;已有展开说明的摘要卡可关闭角标。 */
20
+ showCoverage?: boolean;
18
21
  }): ReactElement {
19
22
  // 全 null(没有任何有效样本)→ 缺数据文案,绝不画 0;total 仍如实入 title
20
23
  if (cell.value === null) {
@@ -35,7 +38,7 @@ export function MetricCellView({
35
38
  {resolveLocalizedText(cell.display, locale)}
36
39
  </span>
37
40
  {/* samples < total:有 attempt 测不了这个指标,覆盖率角标如实标出 */}
38
- {cell.samples < cell.total && (
41
+ {showCoverage && cell.samples < cell.total && (
39
42
  <sup
40
43
  className="nre-coverage"
41
44
  title={localeText(locale, "cell.coverageTitle", { samples: cell.samples, total: cell.total })}