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
@@ -1176,11 +1176,6 @@
1176
1176
  "in": 2,
1177
1177
  "out": 8
1178
1178
  },
1179
- "aion-labs-aion-2-0": {
1180
- "in": 1,
1181
- "out": 2,
1182
- "cacheRead": 0.25
1183
- },
1184
1179
  "aion-labs-aion-3-0": {
1185
1180
  "in": 3.75,
1186
1181
  "out": 7.5,
@@ -1375,6 +1370,22 @@
1375
1370
  "in": 0.15,
1376
1371
  "out": 0.5
1377
1372
  },
1373
+ "amazon--nova-lite": {
1374
+ "in": 0.3,
1375
+ "out": 2.37
1376
+ },
1377
+ "amazon--nova-micro": {
1378
+ "in": 0.03,
1379
+ "out": 0.1
1380
+ },
1381
+ "amazon--nova-pro": {
1382
+ "in": 0.56,
1383
+ "out": 2.13
1384
+ },
1385
+ "amazon--titan-embed-text": {
1386
+ "in": 0.14,
1387
+ "out": 0
1388
+ },
1378
1389
  "amazon.nova-2-lite-v1:0": {
1379
1390
  "in": 0.33,
1380
1391
  "out": 2.75
@@ -1434,6 +1445,12 @@
1434
1445
  "in": 0.8,
1435
1446
  "out": 3.2
1436
1447
  },
1448
+ "ambient/large": {
1449
+ "in": 1.05,
1450
+ "out": 4.4,
1451
+ "cacheRead": 0.2,
1452
+ "cacheWrite": 0
1453
+ },
1437
1454
  "anthracite-org/magnum-v2-72b": {
1438
1455
  "in": 2.006,
1439
1456
  "out": 2.992
@@ -1979,10 +1996,6 @@
1979
1996
  "in": 0.18,
1980
1997
  "out": 0.18
1981
1998
  },
1982
- "arcee-ai/trinity-large-preview": {
1983
- "in": 0.25,
1984
- "out": 1
1985
- },
1986
1999
  "arcee-ai/trinity-large-thinking": {
1987
2000
  "in": 0.22,
1988
2001
  "out": 0.85
@@ -2721,6 +2734,10 @@
2721
2734
  "in": 0.2,
2722
2735
  "out": 0.9
2723
2736
  },
2737
+ "cohere--command-a-reasoning": {
2738
+ "in": 0.63,
2739
+ "out": 5.05
2740
+ },
2724
2741
  "cohere-command-a": {
2725
2742
  "in": 2.5,
2726
2743
  "out": 10
@@ -2927,6 +2944,21 @@
2927
2944
  "out": 30,
2928
2945
  "cacheRead": 0.5
2929
2946
  },
2947
+ "databricks-gpt-5-6-luna": {
2948
+ "in": 1,
2949
+ "out": 6,
2950
+ "cacheRead": 0.1
2951
+ },
2952
+ "databricks-gpt-5-6-sol": {
2953
+ "in": 5,
2954
+ "out": 30,
2955
+ "cacheRead": 0.5
2956
+ },
2957
+ "databricks-gpt-5-6-terra": {
2958
+ "in": 2.5,
2959
+ "out": 15,
2960
+ "cacheRead": 0.25
2961
+ },
2930
2962
  "databricks-gpt-5-mini": {
2931
2963
  "in": 0.25,
2932
2964
  "out": 2,
@@ -3309,10 +3341,10 @@
3309
3341
  "out": 0.42000000000000004
3310
3342
  },
3311
3343
  "deepseek/deepseek-v4-flash": {
3312
- "in": 0.16,
3313
- "out": 0.32,
3314
- "cacheRead": 0.004,
3315
- "cacheWrite": 0.16
3344
+ "in": 0.5,
3345
+ "out": 0.8,
3346
+ "cacheRead": 0.2,
3347
+ "cacheWrite": 0
3316
3348
  },
3317
3349
  "deepseek/deepseek-v4-flash:thinking": {
3318
3350
  "in": 0.14,
@@ -3892,13 +3924,13 @@
3892
3924
  "out": 4.998
3893
3925
  },
3894
3926
  "gemini-flash-latest": {
3895
- "in": 0.3,
3896
- "out": 2.5,
3897
- "cacheRead": 0.075
3927
+ "in": 1.5,
3928
+ "out": 9,
3929
+ "cacheRead": 0.15
3898
3930
  },
3899
3931
  "gemini-flash-lite-latest": {
3900
- "in": 0.1,
3901
- "out": 0.4,
3932
+ "in": 0.25,
3933
+ "out": 1.5,
3902
3934
  "cacheRead": 0.025
3903
3935
  },
3904
3936
  "gemini-omni-flash-preview": {
@@ -4431,13 +4463,13 @@
4431
4463
  "out": 0.306
4432
4464
  },
4433
4465
  "google/gemini-flash-latest": {
4434
- "in": 0.3,
4435
- "out": 2.5,
4436
- "cacheRead": 0.075
4466
+ "in": 1.5,
4467
+ "out": 9,
4468
+ "cacheRead": 0.15
4437
4469
  },
4438
4470
  "google/gemini-flash-lite-latest": {
4439
- "in": 0.1,
4440
- "out": 0.4,
4471
+ "in": 0.25,
4472
+ "out": 1.5,
4441
4473
  "cacheRead": 0.025
4442
4474
  },
4443
4475
  "google/gemini-omni-flash-preview": {
@@ -4861,6 +4893,11 @@
4861
4893
  "cacheRead": 0.25,
4862
4894
  "cacheWrite": 3.125
4863
4895
  },
4896
+ "gpt-chat-latest": {
4897
+ "in": 5,
4898
+ "out": 30,
4899
+ "cacheRead": 0.5
4900
+ },
4864
4901
  "gpt-image-1": {
4865
4902
  "in": 5,
4866
4903
  "out": 40,
@@ -5028,7 +5065,7 @@
5028
5065
  "grok-4.5": {
5029
5066
  "in": 2,
5030
5067
  "out": 6,
5031
- "cacheRead": 0.5
5068
+ "cacheRead": 0.3
5032
5069
  },
5033
5070
  "grok-build-0-1": {
5034
5071
  "in": 1,
@@ -5145,6 +5182,11 @@
5145
5182
  "in": 0.187,
5146
5183
  "out": 0.374
5147
5184
  },
5185
+ "hy3-preview": {
5186
+ "in": 0.17,
5187
+ "out": 0.566661,
5188
+ "cacheRead": 0.051
5189
+ },
5148
5190
  "ibm-granite/granite-4.0-h-micro": {
5149
5191
  "in": 0.017,
5150
5192
  "out": 0.11
@@ -5204,6 +5246,11 @@
5204
5246
  "in": 2.5,
5205
5247
  "out": 10
5206
5248
  },
5249
+ "inkling": {
5250
+ "in": 3.74,
5251
+ "out": 9.36,
5252
+ "cacheRead": 0.748
5253
+ },
5207
5254
  "intellect-3": {
5208
5255
  "in": 0.219,
5209
5256
  "out": 1.202
@@ -5387,9 +5434,9 @@
5387
5434
  "out": 1.1
5388
5435
  },
5389
5436
  "kimi-k2.7-code": {
5390
- "in": 1.28,
5391
- "out": 4.63,
5392
- "cacheRead": 0.32
5437
+ "in": 0.95,
5438
+ "out": 3.9995,
5439
+ "cacheRead": 0.160835
5393
5440
  },
5394
5441
  "kimi-k2.7-code-flex": {
5395
5442
  "in": 0.475,
@@ -5398,13 +5445,17 @@
5398
5445
  },
5399
5446
  "kimi-k2.7-code-highspeed": {
5400
5447
  "in": 1.9,
5401
- "out": 8,
5402
- "cacheRead": 0.38
5448
+ "out": 7.999,
5449
+ "cacheRead": 0.32167
5403
5450
  },
5404
5451
  "kimi-k2.7-code-nitro": {
5405
5452
  "in": 0.275,
5406
5453
  "out": 1.1
5407
5454
  },
5455
+ "kimi-k3": {
5456
+ "in": 3,
5457
+ "out": 15
5458
+ },
5408
5459
  "kimi-thinking-preview": {
5409
5460
  "in": 31.46,
5410
5461
  "out": 31.46
@@ -5461,10 +5512,6 @@
5461
5512
  "in": 0.51,
5462
5513
  "out": 0.74
5463
5514
  },
5464
- "llama-3-8b-instruct": {
5465
- "in": 0.04,
5466
- "out": 0.04
5467
- },
5468
5515
  "llama-3.1-70b-instruct": {
5469
5516
  "in": 0.72,
5470
5517
  "out": 0.72
@@ -5815,34 +5862,18 @@
5815
5862
  "in": 0.025,
5816
5863
  "out": 0.025
5817
5864
  },
5818
- "meta/llama-3.2-11b": {
5819
- "in": 0.16,
5820
- "out": 0.16
5821
- },
5822
5865
  "meta/llama-3.2-11b-vision-instruct": {
5823
5866
  "in": 0.055,
5824
5867
  "out": 0.055
5825
5868
  },
5826
- "meta/llama-3.2-1b": {
5827
- "in": 0.1,
5828
- "out": 0.1
5829
- },
5830
5869
  "meta/llama-3.2-1b-instruct": {
5831
5870
  "in": 0.01,
5832
5871
  "out": 0.01
5833
5872
  },
5834
- "meta/llama-3.2-3b": {
5835
- "in": 0.15,
5836
- "out": 0.15
5837
- },
5838
5873
  "meta/llama-3.2-3b-instruct": {
5839
5874
  "in": 0.02,
5840
5875
  "out": 0.02
5841
5876
  },
5842
- "meta/llama-3.2-90b": {
5843
- "in": 0.72,
5844
- "out": 0.72
5845
- },
5846
5877
  "meta/llama-3.3-70b-instruct-maas": {
5847
5878
  "in": 0.72,
5848
5879
  "out": 0.72
@@ -6212,6 +6243,10 @@
6212
6243
  "in": 0.1,
6213
6244
  "out": 0.3
6214
6245
  },
6246
+ "mistral-small-4": {
6247
+ "in": 0.15,
6248
+ "out": 0.6
6249
+ },
6215
6250
  "mistral-small-4-119b": {
6216
6251
  "in": 0.75,
6217
6252
  "out": 3
@@ -6284,10 +6319,6 @@
6284
6319
  "in": 0.4,
6285
6320
  "out": 2
6286
6321
  },
6287
- "mistral/devstral-small": {
6288
- "in": 0.1,
6289
- "out": 0.3
6290
- },
6291
6322
  "mistral/devstral-small-2": {
6292
6323
  "in": 0.1,
6293
6324
  "out": 0.3
@@ -6376,14 +6407,18 @@
6376
6407
  "in": 0.15,
6377
6408
  "out": 0.15
6378
6409
  },
6379
- "mistral/pixtral-large": {
6380
- "in": 2,
6381
- "out": 6
6382
- },
6383
6410
  "mistral/pixtral-large-latest": {
6384
6411
  "in": 2,
6385
6412
  "out": 6
6386
6413
  },
6414
+ "mistralai--mistral-medium-instruct": {
6415
+ "in": 0.36,
6416
+ "out": 1.22
6417
+ },
6418
+ "mistralai--mistral-small": {
6419
+ "in": 0.07,
6420
+ "out": 0.28
6421
+ },
6387
6422
  "mistralai/Devstral-Small-2505": {
6388
6423
  "in": 0.05,
6389
6424
  "out": 0.22,
@@ -6606,6 +6641,12 @@
6606
6641
  "cacheRead": 0.18,
6607
6642
  "cacheWrite": 1
6608
6643
  },
6644
+ "moonshot/kimi-k3": {
6645
+ "in": 3,
6646
+ "out": 15,
6647
+ "cacheRead": 0.3,
6648
+ "cacheWrite": 3
6649
+ },
6609
6650
  "moonshotai.kimi-k2.5": {
6610
6651
  "in": 0.6,
6611
6652
  "out": 3
@@ -6722,9 +6763,9 @@
6722
6763
  "out": 2.73
6723
6764
  },
6724
6765
  "moonshotai/kimi-k2.7-code": {
6725
- "in": 0.84,
6726
- "out": 3.99,
6727
- "cacheRead": 0.16,
6766
+ "in": 0.85,
6767
+ "out": 3.8,
6768
+ "cacheRead": 0.17,
6728
6769
  "cacheWrite": 0
6729
6770
  },
6730
6771
  "moonshotai/kimi-k2.7-code-highspeed": {
@@ -6732,6 +6773,11 @@
6732
6773
  "out": 8,
6733
6774
  "cacheRead": 0.38
6734
6775
  },
6776
+ "moonshotai/kimi-k3": {
6777
+ "in": 3,
6778
+ "out": 15,
6779
+ "cacheRead": 0.3
6780
+ },
6735
6781
  "moonshotai/kimi-latest": {
6736
6782
  "in": 0.5,
6737
6783
  "out": 2.6,
@@ -6880,6 +6926,10 @@
6880
6926
  "out": 4.04,
6881
6927
  "cacheRead": 0.16
6882
6928
  },
6929
+ "nvidia--llama-3.2-nv-embedqa-1b": {
6930
+ "in": 0.07,
6931
+ "out": 0
6932
+ },
6883
6933
  "nvidia-nemotron-3-nano-30b-a3b": {
6884
6934
  "in": 0.075,
6885
6935
  "out": 0.3
@@ -7300,6 +7350,24 @@
7300
7350
  "out": 33,
7301
7351
  "cacheRead": 0.55
7302
7352
  },
7353
+ "openai.gpt-5.6-luna": {
7354
+ "in": 1,
7355
+ "out": 6,
7356
+ "cacheRead": 0.1,
7357
+ "cacheWrite": 1.25
7358
+ },
7359
+ "openai.gpt-5.6-sol": {
7360
+ "in": 5,
7361
+ "out": 30,
7362
+ "cacheRead": 0.5,
7363
+ "cacheWrite": 6.25
7364
+ },
7365
+ "openai.gpt-5.6-terra": {
7366
+ "in": 2.5,
7367
+ "out": 15,
7368
+ "cacheRead": 0.25,
7369
+ "cacheWrite": 3.125
7370
+ },
7303
7371
  "openai.gpt-oss-120b": {
7304
7372
  "in": 0.15,
7305
7373
  "out": 0.6
@@ -7638,8 +7706,7 @@
7638
7706
  "openai/gpt-5.6-luna": {
7639
7707
  "in": 1,
7640
7708
  "out": 6,
7641
- "cacheRead": 0.1,
7642
- "cacheWrite": 1.25
7709
+ "cacheRead": 0.1
7643
7710
  },
7644
7711
  "openai/gpt-5.6-luna-pro": {
7645
7712
  "in": 1,
@@ -7650,8 +7717,7 @@
7650
7717
  "openai/gpt-5.6-sol": {
7651
7718
  "in": 5,
7652
7719
  "out": 30,
7653
- "cacheRead": 0.5,
7654
- "cacheWrite": 6.25
7720
+ "cacheRead": 0.5
7655
7721
  },
7656
7722
  "openai/gpt-5.6-sol-pro": {
7657
7723
  "in": 5,
@@ -7662,8 +7728,7 @@
7662
7728
  "openai/gpt-5.6-terra": {
7663
7729
  "in": 2.5,
7664
7730
  "out": 15,
7665
- "cacheRead": 0.25,
7666
- "cacheWrite": 3.125
7731
+ "cacheRead": 0.25
7667
7732
  },
7668
7733
  "openai/gpt-5.6-terra-pro": {
7669
7734
  "in": 2.5,
@@ -8556,10 +8621,6 @@
8556
8621
  "in": 0.7,
8557
8622
  "out": 2.8
8558
8623
  },
8559
- "qwen3-4b-fp8": {
8560
- "in": 0.03,
8561
- "out": 0.03
8562
- },
8563
8624
  "qwen3-5-122b-a10b": {
8564
8625
  "in": 0.115,
8565
8626
  "out": 0.917
@@ -8727,14 +8788,6 @@
8727
8788
  "in": 0.2,
8728
8789
  "out": 0.7
8729
8790
  },
8730
- "qwen3-vl-30b-a3b-thinking": {
8731
- "in": 0.2,
8732
- "out": 1
8733
- },
8734
- "qwen3-vl-8b-instruct": {
8735
- "in": 0.08,
8736
- "out": 0.5
8737
- },
8738
8791
  "qwen3-vl-flash": {
8739
8792
  "in": 0.05,
8740
8793
  "out": 0.4,
@@ -8928,6 +8981,10 @@
8928
8981
  "in": 0.65,
8929
8982
  "out": 0.75
8930
8983
  },
8984
+ "sap-abap-1": {
8985
+ "in": 0.48,
8986
+ "out": 1.7
8987
+ },
8931
8988
  "sapiens-ai/agnes-1.5-lite": {
8932
8989
  "in": 0.12,
8933
8990
  "out": 0.6
@@ -9154,9 +9211,10 @@
9154
9211
  "cacheRead": 0.02
9155
9212
  },
9156
9213
  "stepfun/step-3.7-flash": {
9157
- "in": 0.2,
9158
- "out": 1.15,
9159
- "cacheRead": 0.04
9214
+ "in": 0.19,
9215
+ "out": 1.14,
9216
+ "cacheRead": 0.03,
9217
+ "cacheWrite": 0
9160
9218
  },
9161
9219
  "stepfun/step-3.7-flash:thinking": {
9162
9220
  "in": 0.2,
@@ -9195,9 +9253,9 @@
9195
9253
  "out": 0.57
9196
9254
  },
9197
9255
  "tencent/hy3": {
9198
- "in": 0.14,
9199
- "out": 0.58,
9200
- "cacheRead": 0.035
9256
+ "in": 0.2,
9257
+ "out": 0.8,
9258
+ "cacheRead": 0.05
9201
9259
  },
9202
9260
  "tencent/hy3-preview": {
9203
9261
  "in": 0.19,
@@ -9233,6 +9291,15 @@
9233
9291
  "in": 0.4,
9234
9292
  "out": 0.4
9235
9293
  },
9294
+ "thinkingmachines/Inkling": {
9295
+ "in": 1,
9296
+ "out": 4.05,
9297
+ "cacheRead": 0.17
9298
+ },
9299
+ "thinkingmachines/inkling": {
9300
+ "in": 1,
9301
+ "out": 4.05
9302
+ },
9236
9303
  "tongyi-intent-detect-v3": {
9237
9304
  "in": 0.058,
9238
9305
  "out": 0.144
@@ -9586,6 +9653,11 @@
9586
9653
  "in": 0.06,
9587
9654
  "out": 0.4
9588
9655
  },
9656
+ "workers-ai/@cf/zai-org/glm-5.2": {
9657
+ "in": 1.4,
9658
+ "out": 4.4,
9659
+ "cacheRead": 0.26
9660
+ },
9589
9661
  "writer.palmyra-x4-v1:0": {
9590
9662
  "in": 2.5,
9591
9663
  "out": 10
@@ -9639,16 +9711,21 @@
9639
9711
  },
9640
9712
  "x-ai/grok-4.3": {
9641
9713
  "in": 1.25,
9642
- "out": 2.5
9714
+ "out": 2.5,
9715
+ "cacheRead": 0.2,
9716
+ "cacheWrite": 1.25
9643
9717
  },
9644
9718
  "x-ai/grok-4.5": {
9645
9719
  "in": 2,
9646
9720
  "out": 6,
9647
- "cacheRead": 0.5
9721
+ "cacheRead": 0.5,
9722
+ "cacheWrite": 2
9648
9723
  },
9649
9724
  "x-ai/grok-build-0.1": {
9650
9725
  "in": 1,
9651
- "out": 2
9726
+ "out": 2,
9727
+ "cacheRead": 0.2,
9728
+ "cacheWrite": 1
9652
9729
  },
9653
9730
  "x-ai/grok-code-fast-1": {
9654
9731
  "in": 0.2,
@@ -9809,10 +9886,10 @@
9809
9886
  "cacheRead": 0.2
9810
9887
  },
9811
9888
  "xiaomi/mimo-v2.5": {
9812
- "in": 0.16,
9813
- "out": 0.32,
9814
- "cacheRead": 0.004,
9815
- "cacheWrite": 0.16
9889
+ "in": 0.4,
9890
+ "out": 2,
9891
+ "cacheRead": 0.08,
9892
+ "cacheWrite": 0
9816
9893
  },
9817
9894
  "xiaomi/mimo-v2.5-pro": {
9818
9895
  "in": 0.47,
@@ -9943,10 +10020,10 @@
9943
10020
  "cacheWrite": 1
9944
10021
  },
9945
10022
  "z-ai/glm-5.2": {
9946
- "in": 1.2,
10023
+ "in": 1.05,
9947
10024
  "out": 4.4,
9948
- "cacheRead": 0.3,
9949
- "cacheWrite": 1.2
10025
+ "cacheRead": 0.2,
10026
+ "cacheWrite": 0
9950
10027
  },
9951
10028
  "z-ai/glm-5v-turbo": {
9952
10029
  "in": 1.2,
@@ -9961,7 +10038,7 @@
9961
10038
  "zai-glm-4.7": {
9962
10039
  "in": 2.25,
9963
10040
  "out": 2.75,
9964
- "cacheRead": 0,
10041
+ "cacheRead": 2.25,
9965
10042
  "cacheWrite": 0
9966
10043
  },
9967
10044
  "zai-glm-5-1": {
@@ -10330,9 +10407,9 @@
10330
10407
  "cacheWrite": 3.75
10331
10408
  },
10332
10409
  "~google/gemini-flash-latest": {
10333
- "in": 0.5,
10334
- "out": 3,
10335
- "cacheRead": 0.05,
10410
+ "in": 1.5,
10411
+ "out": 9,
10412
+ "cacheRead": 0.15,
10336
10413
  "cacheWrite": 0.08333333333333334
10337
10414
  },
10338
10415
  "~google/gemini-pro-latest": {
@@ -10359,7 +10436,7 @@
10359
10436
  "~x-ai/grok-latest": {
10360
10437
  "in": 2,
10361
10438
  "out": 6,
10362
- "cacheRead": 0.5
10439
+ "cacheRead": 0.3
10363
10440
  }
10364
10441
  }
10365
10442
  }
@@ -32,6 +32,28 @@ export function colorIndexForKey(key: string): number {
32
32
  return hash % NRE_PALETTE_SIZE;
33
33
  }
34
34
 
35
+ /**
36
+ * 同一张图内 series 键集合的配色:每个键仍以稳定散列为起点(无冲突时与跨图配色一致),
37
+ * 图内撞色时按传入顺序(图例顺序)线性探测下一个空色格——跨图稳定让位给图内可辨;
38
+ * 键数超过色板后无空格可探,回落散列格(复用不可避免)。返回键 → 色板下标。
39
+ * 契约见 docs/feature/reports/library/metric-views.md「MetricScatter」;
40
+ * 修法台账见 memory/scatter-series-color-collision.md。
41
+ */
42
+ export function colorIndicesForKeys(keys: readonly string[]): Map<string, number> {
43
+ const used = new Set<number>();
44
+ const out = new Map<string, number>();
45
+ for (const key of keys) {
46
+ if (out.has(key)) continue;
47
+ let idx = colorIndexForKey(key);
48
+ if (used.size < NRE_PALETTE_SIZE) {
49
+ while (used.has(idx)) idx = (idx + 1) % NRE_PALETTE_SIZE;
50
+ }
51
+ used.add(idx);
52
+ out.set(key, idx);
53
+ }
54
+ return out;
55
+ }
56
+
35
57
  /** 键对应的稳定 class 名("nre-c3"),配 styles.css 的 .nre-cN 上文字色。 */
36
58
  export function colorClassForKey(key: string): string {
37
59
  return `nre-c${colorIndexForKey(key)}`;
@@ -1,5 +1,5 @@
1
1
  // niceeval 报告的渐进增强 runtime:纯 vanilla JS、零依赖、IIFE、幂等。
2
- // 只作用于 .nre DOM 与 data-nre-* 属性;六个行为——实验组切换、Tabs 单选切换、表格排序、
2
+ // 只作用于 .nre DOM 与 data-nre-* 属性;五个行为——Tabs 单选切换、表格排序、
3
3
  // 行过滤、SVG 点 tooltip、警告命令复制。全部只改浏览状态,不改数据、指标口径或初始 HTML 数值。
4
4
  // 静态 HTML 无 JS 时内容完整可读是硬约束:排序有数据侧预排、tooltip 退化为原生 <title>、
5
5
  // 过滤输入框静默无功能、Tabs 退化为原生 <details> 手风琴、命令块退化为点击全选。
@@ -19,38 +19,6 @@
19
19
  return target && target.closest ? target.closest(selector) : null;
20
20
  }
21
21
 
22
- // ───────────────────────── 实验组:[data-nre-experiment-group-select] ─────────────────────────
23
- // 数据侧已经把每组的摘要、散点和列表分别算好;这里仅在同一报告节点内切换 <details>,
24
- // 不重新请求、不重算,也不触碰 Runs / Traces / Attempt 证据室。
25
-
26
- function selectExperimentGroup(control) {
27
- var root = control.closest("[data-nre-experiment-groups]");
28
- if (!root) return;
29
- var selected = control.getAttribute("data-nre-experiment-group-select");
30
- var controls = root.querySelectorAll("[data-nre-experiment-group-select]");
31
- var panels = root.querySelectorAll("[data-nre-experiment-group-panel]");
32
- for (var i = 0; i < controls.length; i++) {
33
- var active = controls[i].getAttribute("data-nre-experiment-group-select") === selected;
34
- controls[i].setAttribute("aria-selected", active ? "true" : "false");
35
- controls[i].tabIndex = active ? 0 : -1;
36
- }
37
- for (var j = 0; j < panels.length; j++) {
38
- panels[j].open = panels[j].getAttribute("data-nre-experiment-group-panel") === selected;
39
- }
40
- }
41
-
42
- document.addEventListener("click", function (e) {
43
- var control = closest(e.target, "[data-nre-experiment-group-select]");
44
- if (control) selectExperimentGroup(control);
45
- });
46
-
47
- document.addEventListener("keydown", function (e) {
48
- var control = closest(e.target, "[data-nre-experiment-group-select]");
49
- if (!control || (e.key !== "Enter" && e.key !== " ")) return;
50
- e.preventDefault();
51
- selectExperimentGroup(control);
52
- });
53
-
54
22
  // ───────────────────────── Tabs:[data-nre-tabs] 单选切换 ─────────────────────────
55
23
  // 静态 HTML 每 tab 一个 <details> 且仅首个 open;点击 summary 时接管原生 toggle:
56
24
  // 打开所点 tab、收起同组其余,点已开的 tab 保持打开(单选语义,恒有一个面板可见)。