niceeval 0.6.1 → 0.7.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (378) hide show
  1. package/INDEX.md +23 -23
  2. package/README.zh.md +6 -6
  3. package/dist/agents/types.d.ts +69 -7
  4. package/dist/context/types.d.ts +32 -12
  5. package/dist/i18n/en.d.ts +54 -0
  6. package/dist/i18n/zh-CN.d.ts +57 -3
  7. package/dist/o11y/types.d.ts +16 -2
  8. package/dist/report/aggregate.d.ts +32 -24
  9. package/dist/report/aggregate.js +158 -50
  10. package/dist/report/built-in/index.d.ts +2 -0
  11. package/dist/report/built-in/index.js +8 -0
  12. package/dist/report/components.d.ts +93 -160
  13. package/dist/report/components.js +377 -114
  14. package/dist/report/compute.d.ts +87 -81
  15. package/dist/report/compute.js +597 -417
  16. package/dist/report/flag.d.ts +32 -6
  17. package/dist/report/flag.js +92 -4
  18. package/dist/report/format.d.ts +19 -11
  19. package/dist/report/format.js +30 -13
  20. package/dist/report/index.d.ts +16 -16
  21. package/dist/report/index.js +20 -21
  22. package/dist/report/load.js +3 -2
  23. package/dist/report/locale.d.ts +57 -33
  24. package/dist/report/locale.js +122 -56
  25. package/dist/report/metrics.d.ts +23 -4
  26. package/dist/report/metrics.js +110 -25
  27. package/dist/report/primitives.d.ts +48 -15
  28. package/dist/report/primitives.js +135 -26
  29. package/dist/report/react/AttemptList.d.ts +9 -7
  30. package/dist/report/react/AttemptList.js +17 -10
  31. package/dist/report/react/DeltaTable.js +19 -18
  32. package/dist/report/react/EvalList.d.ts +4 -4
  33. package/dist/report/react/EvalList.js +0 -0
  34. package/dist/report/react/ExperimentComparison.d.ts +10 -0
  35. package/dist/report/react/ExperimentComparison.js +12 -0
  36. package/dist/report/react/ExperimentList.d.ts +4 -3
  37. package/dist/report/react/ExperimentList.js +17 -18
  38. package/dist/report/react/MetricBars.js +5 -4
  39. package/dist/report/react/MetricLine.js +12 -5
  40. package/dist/report/react/MetricMatrix.js +1 -1
  41. package/dist/report/react/MetricScatter.js +59 -28
  42. package/dist/report/react/MetricTable.js +2 -12
  43. package/dist/report/react/ScopeSummary.d.ts +10 -0
  44. package/dist/report/react/ScopeSummary.js +17 -0
  45. package/dist/report/react/Scoreboard.js +6 -6
  46. package/dist/report/react/cell.js +2 -2
  47. package/dist/report/react/chart-math.d.ts +23 -6
  48. package/dist/report/react/chart-math.js +71 -19
  49. package/dist/report/react/fixtures.d.ts +5 -9
  50. package/dist/report/react/fixtures.js +110 -147
  51. package/dist/report/react/index.d.ts +15 -5
  52. package/dist/report/react/index.js +18 -7
  53. package/dist/report/report.d.ts +137 -16
  54. package/dist/report/report.js +259 -28
  55. package/dist/report/text/faces.d.ts +17 -19
  56. package/dist/report/text/faces.js +253 -184
  57. package/dist/report/text/plot.js +1 -1
  58. package/dist/report/text/table.js +38 -7
  59. package/dist/report/tree.d.ts +90 -40
  60. package/dist/report/tree.js +252 -94
  61. package/dist/report/types.d.ts +247 -284
  62. package/dist/report/types.js +4 -3
  63. package/dist/report/web.d.ts +21 -5
  64. package/dist/report/web.js +42 -16
  65. package/dist/results/select.d.ts +38 -16
  66. package/dist/results/select.js +73 -25
  67. package/dist/results/types.d.ts +49 -14
  68. package/dist/runner/feedback/sink.d.ts +110 -0
  69. package/dist/runner/types.d.ts +513 -22
  70. package/dist/sandbox/docker.d.ts +23 -2
  71. package/dist/sandbox/e2b.d.ts +15 -1
  72. package/dist/sandbox/errors.d.ts +30 -3
  73. package/dist/sandbox/io-retry.d.ts +17 -0
  74. package/dist/sandbox/registry.d.ts +2 -0
  75. package/dist/sandbox/resolve.d.ts +18 -5
  76. package/dist/sandbox/retry.d.ts +11 -1
  77. package/dist/sandbox/types.d.ts +39 -5
  78. package/dist/sandbox/vercel.d.ts +7 -1
  79. package/dist/scoring/coverage.d.ts +30 -0
  80. package/dist/scoring/display.d.ts +21 -0
  81. package/dist/scoring/display.js +120 -0
  82. package/dist/scoring/types.d.ts +103 -20
  83. package/dist/shared/aggregate.d.ts +4 -2
  84. package/dist/shared/aggregate.js +8 -7
  85. package/dist/shared/types.d.ts +28 -0
  86. package/dist/tty-line.d.ts +0 -4
  87. package/dist/util.d.ts +23 -0
  88. package/docs-site/zh/README.md +44 -0
  89. package/docs-site/zh/examples/ai-agent-application.mdx +63 -0
  90. package/docs-site/zh/examples/coding-agent-extensions.mdx +57 -0
  91. package/docs-site/zh/examples/index.mdx +50 -0
  92. package/docs-site/zh/{concepts → explanation}/adapter.mdx +31 -13
  93. package/docs-site/zh/{concepts → explanation}/assert.mdx +7 -7
  94. package/docs-site/zh/{concepts → explanation}/drive.mdx +8 -8
  95. package/docs-site/zh/{concepts → explanation}/evals.mdx +4 -4
  96. package/docs-site/zh/{concepts → explanation}/experiment.mdx +8 -8
  97. package/docs-site/zh/{concepts → explanation}/hitl.mdx +8 -8
  98. package/docs-site/zh/{concepts → explanation}/judge.mdx +5 -5
  99. package/docs-site/zh/{concepts → explanation}/overview.mdx +11 -11
  100. package/docs-site/zh/{guides → explanation}/runner.mdx +18 -8
  101. package/docs-site/zh/{concepts → explanation}/tier.mdx +6 -6
  102. package/docs-site/zh/{guides → how-to}/agent-feedback-loop.mdx +35 -33
  103. package/docs-site/zh/{guides → how-to}/authoring.mdx +35 -2
  104. package/docs-site/zh/{guides → how-to}/ci-integration.mdx +23 -12
  105. package/docs-site/zh/{guides → how-to}/connect-otel.mdx +6 -6
  106. package/docs-site/zh/{guides → how-to}/connect-your-agent.mdx +47 -21
  107. package/docs-site/zh/{guides → how-to}/custom-reports.mdx +34 -39
  108. package/docs-site/zh/{guides → how-to}/dataset-fanout.mdx +25 -3
  109. package/docs-site/zh/{guides → how-to}/experiments.mdx +12 -5
  110. package/docs-site/zh/how-to/publish-report.mdx +105 -0
  111. package/docs-site/zh/{guides → how-to}/reporters.mdx +2 -2
  112. package/docs-site/zh/{guides → how-to}/sandbox-agent.mdx +56 -7
  113. package/docs-site/zh/how-to/sandbox-providers.mdx +350 -0
  114. package/docs-site/zh/{guides → how-to}/scoring-guide.mdx +4 -4
  115. package/docs-site/zh/{guides → how-to}/viewing-results.mdx +82 -39
  116. package/docs-site/zh/{guides → how-to}/write-experiment.mdx +6 -4
  117. package/docs-site/zh/{guides → how-to}/write-send.mdx +30 -14
  118. package/docs-site/zh/index.mdx +24 -26
  119. package/docs-site/zh/introduction.mdx +8 -8
  120. package/docs-site/zh/reference/builtin-agents.mdx +32 -5
  121. package/docs-site/zh/reference/capabilities.mdx +8 -8
  122. package/docs-site/zh/reference/cli.mdx +40 -12
  123. package/docs-site/zh/reference/define-agent.mdx +58 -5
  124. package/docs-site/zh/reference/define-config.mdx +1 -1
  125. package/docs-site/zh/reference/define-eval.mdx +42 -9
  126. package/docs-site/zh/reference/events.mdx +3 -3
  127. package/docs-site/zh/reference/expect.mdx +26 -1
  128. package/docs-site/zh/{guides → reference}/official-adapters.mdx +32 -8
  129. package/docs-site/zh/{guides → reference}/report-components.mdx +45 -33
  130. package/docs-site/zh/{guides → reference}/results-data.mdx +21 -13
  131. package/docs-site/zh/troubleshooting/debug-sandbox.mdx +57 -0
  132. package/docs-site/zh/troubleshooting/debugging.mdx +212 -0
  133. package/docs-site/zh/{quickstart.mdx → tutorials/quickstart.mdx} +5 -17
  134. package/package.json +10 -2
  135. package/src/agents/ai-sdk-otel.test.ts +1 -0
  136. package/src/agents/ai-sdk.test.ts +3 -0
  137. package/src/agents/ai-sdk.ts +3 -0
  138. package/src/agents/bub-install-spec.test.ts +34 -0
  139. package/src/agents/bub-install-spec.ts +32 -0
  140. package/src/agents/bub.ts +31 -32
  141. package/src/agents/claude-code.test.ts +130 -9
  142. package/src/agents/claude-code.ts +76 -4
  143. package/src/agents/codex.test.ts +189 -40
  144. package/src/agents/codex.ts +155 -14
  145. package/src/agents/coding-cli-versions.test.ts +15 -0
  146. package/src/agents/coding-cli-versions.ts +3 -0
  147. package/src/agents/index.ts +13 -2
  148. package/src/agents/langgraph.test.ts +204 -0
  149. package/src/agents/langgraph.ts +495 -0
  150. package/src/agents/marketplace.ts +85 -0
  151. package/src/agents/native-config.test.ts +179 -0
  152. package/src/agents/native-config.ts +267 -0
  153. package/src/agents/openai-compat.test.ts +1 -0
  154. package/src/agents/openai-compat.ts +1 -1
  155. package/src/agents/openclaw.test.ts +31 -0
  156. package/src/agents/openclaw.ts +171 -0
  157. package/src/agents/plugin-config.test.ts +1 -0
  158. package/src/agents/sdk-streams.test.ts +79 -0
  159. package/src/agents/sdk-streams.ts +55 -10
  160. package/src/agents/skills.test.ts +1 -0
  161. package/src/agents/streaming.test.ts +3 -9
  162. package/src/agents/streaming.ts +2 -2
  163. package/src/agents/types.ts +71 -8
  164. package/src/agents/ui-message-stream.test.ts +3 -0
  165. package/src/cli.ts +446 -124
  166. package/src/context/context.test.ts +51 -12
  167. package/src/context/context.ts +162 -30
  168. package/src/context/session.test.ts +2 -1
  169. package/src/context/session.ts +115 -7
  170. package/src/context/types.ts +30 -12
  171. package/src/define.test.ts +13 -8
  172. package/src/define.ts +25 -4
  173. package/src/expect/index.ts +53 -23
  174. package/src/i18n/en.ts +81 -17
  175. package/src/i18n/zh-CN.ts +80 -17
  176. package/src/o11y/cost.test.ts +1 -0
  177. package/src/o11y/execution-tree.test.ts +1 -20
  178. package/src/o11y/otlp/mappers/claude-code.test.ts +1 -0
  179. package/src/o11y/otlp/parse.test.ts +1 -0
  180. package/src/o11y/otlp/turn-otel.test.ts +1 -0
  181. package/src/o11y/parsers/bub.test.ts +1 -0
  182. package/src/o11y/parsers/claude-code.test.ts +1 -34
  183. package/src/o11y/parsers/openclaw.test.ts +154 -0
  184. package/src/o11y/parsers/openclaw.ts +310 -0
  185. package/src/o11y/prices.json +746 -311
  186. package/src/o11y/tool-names.test.ts +1 -0
  187. package/src/o11y/types.ts +16 -2
  188. package/src/report/aggregate.ts +178 -61
  189. package/src/report/built-in/index.tsx +9 -0
  190. package/src/report/components.tsx +625 -279
  191. package/src/report/compute.ts +723 -491
  192. package/src/report/dual-render.test.tsx +741 -1024
  193. package/src/report/flag.ts +104 -12
  194. package/src/report/format.ts +32 -12
  195. package/src/report/index.ts +119 -46
  196. package/src/report/load.ts +3 -2
  197. package/src/report/locale.ts +136 -65
  198. package/src/report/metrics.ts +108 -25
  199. package/src/report/primitives.tsx +196 -45
  200. package/src/report/react/AttemptList.tsx +30 -43
  201. package/src/report/react/DeltaTable.tsx +63 -45
  202. package/src/report/react/EvalList.tsx +0 -0
  203. package/src/report/react/ExperimentComparison.tsx +73 -0
  204. package/src/report/react/ExperimentList.tsx +50 -32
  205. package/src/report/react/MetricBars.tsx +5 -4
  206. package/src/report/react/MetricLine.tsx +13 -8
  207. package/src/report/react/MetricMatrix.tsx +2 -2
  208. package/src/report/react/MetricScatter.tsx +86 -34
  209. package/src/report/react/MetricTable.tsx +4 -76
  210. package/src/report/react/ScopeSummary.tsx +86 -0
  211. package/src/report/react/Scoreboard.tsx +28 -10
  212. package/src/report/react/cell.tsx +2 -2
  213. package/src/report/react/chart-math.test.ts +85 -0
  214. package/src/report/react/chart-math.ts +101 -22
  215. package/src/report/react/enhance.js +89 -5
  216. package/src/report/react/fixtures.ts +114 -154
  217. package/src/report/react/index.tsx +24 -39
  218. package/src/report/react/render.test.tsx +138 -158
  219. package/src/report/react/styles.css +243 -82
  220. package/src/report/report.test.ts +779 -841
  221. package/src/report/report.ts +423 -41
  222. package/src/report/text/faces.ts +290 -193
  223. package/src/report/text/plot.ts +1 -1
  224. package/src/report/text/table.ts +44 -7
  225. package/src/report/tree.ts +362 -104
  226. package/src/report/types.ts +261 -271
  227. package/src/report/web.ts +63 -20
  228. package/src/results/annotated-source.test.ts +62 -9
  229. package/src/results/annotated-source.ts +64 -6
  230. package/src/results/attempt-evidence.test.ts +13 -11
  231. package/src/results/attempt-evidence.ts +20 -13
  232. package/src/results/attempt-source.ts +6 -3
  233. package/src/results/copy.ts +150 -60
  234. package/src/results/host-equivalence.test.ts +34 -20
  235. package/src/results/index.ts +12 -4
  236. package/src/results/locator.test.ts +1 -22
  237. package/src/results/open.ts +15 -5
  238. package/src/results/publish.ts +149 -0
  239. package/src/results/results.test.ts +89 -54
  240. package/src/results/select.ts +104 -34
  241. package/src/results/truncate.ts +90 -0
  242. package/src/results/types.ts +43 -14
  243. package/src/results/writer.ts +31 -13
  244. package/src/runner/attempt.test.ts +138 -7
  245. package/src/runner/attempt.ts +603 -104
  246. package/src/runner/discover.test.ts +47 -0
  247. package/src/runner/discover.ts +36 -2
  248. package/src/runner/eval-source.test.ts +1 -27
  249. package/src/runner/feedback/agent.test.ts +504 -0
  250. package/src/runner/feedback/agent.ts +409 -0
  251. package/src/runner/feedback/ci.test.ts +562 -0
  252. package/src/runner/feedback/ci.ts +401 -0
  253. package/src/runner/feedback/coordinator.test.ts +317 -0
  254. package/src/runner/feedback/coordinator.ts +397 -0
  255. package/src/runner/feedback/failure.ts +40 -0
  256. package/src/runner/feedback/human.test.ts +616 -0
  257. package/src/runner/feedback/human.ts +535 -0
  258. package/src/runner/feedback/index.ts +66 -0
  259. package/src/runner/feedback/io.ts +78 -0
  260. package/src/runner/feedback/profile.test.ts +50 -0
  261. package/src/runner/feedback/profile.ts +58 -0
  262. package/src/runner/feedback/reducer.test.ts +395 -0
  263. package/src/runner/feedback/reducer.ts +260 -0
  264. package/src/runner/feedback/renderer.ts +82 -0
  265. package/src/runner/feedback/sink.ts +203 -0
  266. package/src/runner/feedback/testing.ts +106 -0
  267. package/src/runner/ledger.test.ts +230 -0
  268. package/src/runner/ledger.ts +329 -0
  269. package/src/runner/report.test.ts +128 -3
  270. package/src/runner/report.ts +33 -9
  271. package/src/runner/reporters/artifacts.ts +8 -2
  272. package/src/runner/reporters/braintrust.test.ts +8 -7
  273. package/src/runner/reporters/braintrust.ts +9 -2
  274. package/src/runner/reporters/index.ts +2 -2
  275. package/src/runner/reporters/json.test.ts +162 -0
  276. package/src/runner/reporters/json.ts +35 -8
  277. package/src/runner/reporters/shared.ts +1 -5
  278. package/src/runner/run.test.ts +760 -3
  279. package/src/runner/run.ts +243 -37
  280. package/src/runner/sandbox-prep.ts +3 -42
  281. package/src/runner/timing.ts +158 -0
  282. package/src/runner/types.ts +518 -22
  283. package/src/sandbox/checkpoint.test.ts +55 -0
  284. package/src/sandbox/checkpoint.ts +29 -8
  285. package/src/sandbox/cli-commands.ts +407 -0
  286. package/src/sandbox/docker.ts +115 -16
  287. package/src/sandbox/e2b-agent-template.test.ts +56 -0
  288. package/src/sandbox/e2b-agent-template.ts +94 -0
  289. package/src/sandbox/e2b.ts +74 -9
  290. package/src/sandbox/errors.ts +111 -4
  291. package/src/sandbox/index.ts +2 -0
  292. package/src/sandbox/io-retry.test.ts +58 -0
  293. package/src/sandbox/io-retry.ts +45 -0
  294. package/src/sandbox/keep-registry.test.ts +86 -0
  295. package/src/sandbox/keep-registry.ts +142 -0
  296. package/src/sandbox/keep.ts +178 -0
  297. package/src/sandbox/paths.test.ts +1 -0
  298. package/src/sandbox/paths.ts +19 -8
  299. package/src/sandbox/registry.ts +20 -3
  300. package/src/sandbox/resolve.ts +76 -11
  301. package/src/sandbox/retry.test.ts +70 -0
  302. package/src/sandbox/retry.ts +46 -4
  303. package/src/sandbox/types.ts +44 -6
  304. package/src/sandbox/vercel.ts +43 -20
  305. package/src/scoring/collector.ts +60 -17
  306. package/src/scoring/coverage.ts +95 -0
  307. package/src/scoring/diff.ts +81 -0
  308. package/src/scoring/display.test.ts +121 -0
  309. package/src/scoring/display.ts +133 -0
  310. package/src/scoring/evidence.test.ts +189 -0
  311. package/src/scoring/judge.test.ts +142 -0
  312. package/src/scoring/judge.ts +15 -18
  313. package/src/scoring/scoped.ts +217 -50
  314. package/src/scoring/types.ts +117 -20
  315. package/src/scoring/verdict.ts +16 -4
  316. package/src/shared/aggregate.ts +8 -6
  317. package/src/shared/types.ts +31 -0
  318. package/src/show/compose.ts +50 -67
  319. package/src/show/index.ts +127 -56
  320. package/src/show/render.ts +662 -131
  321. package/src/show/report-host.test.ts +188 -0
  322. package/src/show/report-host.ts +375 -0
  323. package/src/show/show.test.ts +320 -54
  324. package/src/tty-line.ts +8 -26
  325. package/src/util.test.ts +1 -0
  326. package/src/util.ts +41 -0
  327. package/src/view/app/App.test.tsx +69 -0
  328. package/src/view/app/App.tsx +144 -48
  329. package/src/view/app/components/AttemptModal.tsx +423 -11
  330. package/src/view/app/components/CodeView.tsx +41 -14
  331. package/src/view/app/components/CopyControls.tsx +2 -2
  332. package/src/view/app/i18n.ts +37 -17
  333. package/src/view/app/lib/attempt-route.test.ts +1 -0
  334. package/src/view/app/lib/verdict.ts +7 -9
  335. package/src/view/app/main.tsx +13 -8
  336. package/src/view/app/pages/{RunsPage.tsx → AttemptsPage.tsx} +6 -6
  337. package/src/view/app/types.ts +4 -1
  338. package/src/view/artifact-serving.test.ts +2 -1
  339. package/src/view/client-dist/app.css +1 -1
  340. package/src/view/client-dist/app.js +17 -17
  341. package/src/view/data.test.ts +10 -3
  342. package/src/view/data.ts +155 -49
  343. package/src/view/index.ts +56 -41
  344. package/src/view/server.ts +37 -15
  345. package/src/view/shared/types.ts +34 -5
  346. package/src/view/styles.css +227 -0
  347. package/src/view/view-report.test.ts +167 -62
  348. package/dist/report/built-ins/experiment-comparison.d.ts +0 -1
  349. package/dist/report/built-ins/experiment-comparison.js +0 -13
  350. package/dist/report/built-ins/index.d.ts +0 -1
  351. package/dist/report/built-ins/index.js +0 -2
  352. package/dist/report/react/GroupSummary.d.ts +0 -8
  353. package/dist/report/react/GroupSummary.js +0 -8
  354. package/dist/report/react/RunOverview.d.ts +0 -8
  355. package/dist/report/react/RunOverview.js +0 -12
  356. package/docs-site/zh/example/ai-agent-application.mdx +0 -152
  357. package/docs-site/zh/example/claude-code-codex-plugin.mdx +0 -167
  358. package/docs-site/zh/example/claude-code-codex-skill.mdx +0 -152
  359. package/docs-site/zh/example/showcase.mdx +0 -39
  360. package/docs-site/zh/guides/publish-report.mdx +0 -91
  361. package/docs-site/zh/guides/sandbox-providers.mdx +0 -102
  362. package/src/report/built-in-user-parity.test.tsx +0 -640
  363. package/src/report/built-ins/experiment-comparison.tsx +0 -19
  364. package/src/report/built-ins/index.ts +0 -2
  365. package/src/report/react/GroupSummary.tsx +0 -66
  366. package/src/report/react/RunOverview.tsx +0 -109
  367. package/src/runner/reporters/console.ts +0 -70
  368. package/src/runner/reporters/live.test.ts +0 -56
  369. package/src/runner/reporters/live.ts +0 -247
  370. package/src/runner/reporters/quiet.test.ts +0 -66
  371. package/src/runner/reporters/quiet.ts +0 -49
  372. package/src/runner/reporters/table.ts +0 -277
  373. /package/docs-site/zh/{example/tier1-ai-sdk-v7.mdx → examples/integrations/ai-sdk-v7.mdx} +0 -0
  374. /package/docs-site/zh/{example/tier1-claude-sdk.mdx → examples/integrations/claude-sdk.mdx} +0 -0
  375. /package/docs-site/zh/{example/tier1-codex-sdk.mdx → examples/integrations/codex-sdk.mdx} +0 -0
  376. /package/docs-site/zh/{example/tier1-langgraph.mdx → examples/integrations/langgraph.mdx} +0 -0
  377. /package/docs-site/zh/{example/tier1-pi-sdk.mdx → examples/integrations/pi-sdk.mdx} +0 -0
  378. /package/docs-site/zh/{guides → how-to}/fixtures.mdx +0 -0
@@ -61,20 +61,102 @@
61
61
  .nre-attempt-list .nre-attempt-experiment,
62
62
  .nre-attempt-list .nre-attempt-duration,
63
63
  .nre-attempt-list .nre-attempt-cost { color:var(--muted); font-size:.9em; font-variant-numeric:tabular-nums; }
64
- .nre-attempt-list .nre-attempt-error { margin:.4rem 0 0; padding:6px 10px; border:1px solid color-mix(in oklch,var(--bad),var(--line) 50%); border-radius:7px; background:color-mix(in oklch,var(--bad),var(--panel) 92%); color:var(--bad); font-family:ui-monospace,SFMono-Regular,Menlo,monospace; font-size:.85em; white-space:pre-wrap; word-break:break-word; }
65
- .nre-attempt-list .nre-assertions { list-style:none; margin:.4rem 0 0; padding:0; display:grid; gap:6px; }
66
- .nre-attempt-list .nre-assertion { padding-left:.25rem; }
67
- .nre-attempt-list .nre-assertion-failed { color: var(--bad); }
68
- .nre-attempt-list .nre-assertion-severity { color:var(--soft); font-size:.8em; text-transform:uppercase; letter-spacing:.04em; margin-right:.5em; }
69
- .nre-attempt-list .nre-assertion-name { font-family:ui-monospace,SFMono-Regular,Menlo,monospace; font-size:.92em; }
70
- .nre-attempt-list .nre-assertion-score { color:var(--muted); margin-left:.75em; font-size:.9em; }
71
- .nre-attempt-list .nre-assertion-more summary { cursor:pointer; color:var(--muted); font-size:.85em; user-select:none; }
72
- .nre-attempt-list .nre-assertion-more summary:hover { color:var(--text); }
73
- .nre-attempt-list .nre-assertion-detail { margin:.25rem 0; white-space:pre-wrap; }
74
- .nre-attempt-list .nre-assertion-evidence { margin:.25rem 0 .25rem .75rem; padding-left:.5rem; border-left:2px solid var(--line-strong); color:var(--muted); white-space:pre-wrap; }
64
+ .nre-attempt-list .nre-attempt-result { display:-webkit-box; overflow:hidden; -webkit-box-orient:vertical; -webkit-line-clamp:2; margin:.4rem 0 0; color:color-mix(in oklch,var(--muted),var(--text) 12%); overflow-wrap:anywhere; }
75
65
  .nre-attempt-list .nre-truncated { color:var(--warn); font-size:.9em; }
76
66
  .nre-attempt-list .nre-attempt-list-empty { border:1px dashed var(--line-strong); border-radius:8px; padding:18px; color:var(--muted); text-align:center; background:var(--panel); }
77
67
 
68
+ /* ---- ExperimentComparison:完整组索引 + 当前组独立 panel ---- */
69
+ .nre-experiment-comparison .nre-experiment-group-tabs {
70
+ display:grid;
71
+ grid-template-columns:repeat(auto-fit,minmax(320px,1fr));
72
+ gap:12px;
73
+ margin-bottom:20px;
74
+ }
75
+ .nre-experiment-comparison .nre-experiment-group-tab {
76
+ min-width:0;
77
+ border:1px solid var(--line);
78
+ border-radius:9px;
79
+ padding:14px 16px 8px;
80
+ background:var(--panel);
81
+ cursor:pointer;
82
+ transition:border-color .12s,background .12s;
83
+ }
84
+ .nre-experiment-comparison .nre-experiment-group-tab:hover {
85
+ border-color:var(--line-strong);
86
+ background:color-mix(in oklch,var(--panel-2),var(--panel) 35%);
87
+ }
88
+ .nre-experiment-comparison .nre-experiment-group-tab:focus-visible {
89
+ outline:2px solid var(--nre-c0);
90
+ outline-offset:2px;
91
+ }
92
+ .nre-experiment-comparison .nre-experiment-group-name {
93
+ display:block;
94
+ margin-bottom:10px;
95
+ color:var(--text);
96
+ font-size:15px;
97
+ overflow-wrap:anywhere;
98
+ }
99
+ /* 组卡里嵌的 ScopeSummary 降为紧凑行:去掉满宽 KPI 条的边框,收小数字 */
100
+ .nre-experiment-comparison .nre-experiment-group-tab .nre-scope-summary { margin:0; }
101
+ .nre-experiment-comparison .nre-experiment-group-tab .nre-scope-kpis {
102
+ display:flex;
103
+ flex-wrap:wrap;
104
+ column-gap:16px;
105
+ row-gap:6px;
106
+ margin:0 0 6px;
107
+ border:0;
108
+ border-radius:0;
109
+ background:transparent;
110
+ overflow:visible;
111
+ }
112
+ .nre-experiment-comparison .nre-experiment-group-tab .nre-scope-kpi {
113
+ min-width:58px;
114
+ padding:0;
115
+ border-right:0;
116
+ }
117
+ .nre-experiment-comparison .nre-experiment-group-tab .nre-scope-kpi dd {
118
+ margin:3px 0 0;
119
+ font-size:16px;
120
+ line-height:1.15;
121
+ font-weight:650;
122
+ }
123
+ .nre-experiment-comparison .nre-experiment-group-tab .nre-scope-kpi-rate dd { font-size:18px; }
124
+ .nre-experiment-comparison .nre-experiment-group-panel {
125
+ padding:16px 0;
126
+ }
127
+ .nre-experiment-comparison .nre-experiment-group-panel > summary {
128
+ cursor:pointer;
129
+ font-size:16px;
130
+ font-weight:700;
131
+ overflow-wrap:anywhere;
132
+ }
133
+ .nre-experiment-comparison .nre-experiment-group-panel[open] > summary {
134
+ margin-bottom:16px;
135
+ }
136
+ .nre-experiment-comparison .nre-experiment-group-panel > .nre {
137
+ margin:0 0 18px;
138
+ }
139
+ /* group panel 已经是内容的唯一外框;内嵌图表不再重复套一层卡片边框 */
140
+ .nre-experiment-comparison .nre-experiment-group-panel .nre-metric-scatter,
141
+ .nre-experiment-comparison .nre-experiment-group-panel .nre-metric-line,
142
+ .nre-experiment-comparison .nre-experiment-group-panel .nre-metric-bars {
143
+ border:0;
144
+ border-radius:0;
145
+ background:transparent;
146
+ padding:14px 0 8px;
147
+ }
148
+ .nre-experiment-comparison .nre-experiment-group-panel > .nre:last-child {
149
+ margin-bottom:0;
150
+ }
151
+ .nre-experiment-comparison .nre-experiment-groups-empty {
152
+ border:1px dashed var(--line-strong);
153
+ border-radius:8px;
154
+ padding:18px;
155
+ color:var(--muted);
156
+ text-align:center;
157
+ background:var(--panel);
158
+ }
159
+
78
160
  /* ---- EvalList:实体列表的第二级,一条 <details> 一个 experimentId × evalId ---- */
79
161
  .nre-eval-list .nre-evals { list-style:none; margin:0; padding:0; }
80
162
  .nre-eval-list .nre-eval { border-bottom:1px solid var(--line); }
@@ -88,7 +170,6 @@
88
170
  .nre-eval-list .nre-eval-attempts-count,
89
171
  .nre-eval-list .nre-eval-duration,
90
172
  .nre-eval-list .nre-eval-cost { color:var(--muted); font-size:.9em; font-variant-numeric:tabular-nums; }
91
- .nre-eval-list .nre-eval-reason { color:color-mix(in oklch,var(--muted),var(--text) 6%); }
92
173
  .nre-eval-list .nre-attempts { list-style:none; margin:0 0 12px; padding:0 0 0 20px; border-left:2px solid color-mix(in oklch,var(--nre-c0),transparent 55%); }
93
174
  .nre-eval-list .nre-eval-list-empty { border:1px dashed var(--line-strong); border-radius:8px; padding:18px; color:var(--muted); text-align:center; background:var(--panel); }
94
175
 
@@ -132,7 +213,7 @@
132
213
  .nre-experiment-list .nre-experiment-attempt-row { padding:5px 0 5px 20px; color:var(--muted); }
133
214
  .nre-experiment-list .nre-eval-id { font-weight:560; overflow-wrap:anywhere; }
134
215
  .nre-experiment-list .nre-eval-attempt-count { color:var(--soft); font-size:12px; }
135
- .nre-experiment-list .nre-eval-summary { color:var(--muted); font-size:.92em; overflow-wrap:anywhere; }
216
+ .nre-experiment-list .nre-eval-rollup { color:var(--muted); font-size:.92em; overflow-wrap:anywhere; }
136
217
  .nre-experiment-list .nre-attempt-branch { color:var(--line-strong); font-variant-numeric:tabular-nums; }
137
218
  .nre-experiment-list .nre-eval-attempt-badges { display:inline-flex; flex-wrap:wrap; gap:.6em; }
138
219
  .nre-experiment-list .nre-eval-attempt-metrics,
@@ -140,10 +221,8 @@
140
221
  .nre-experiment-list .nre-experiment-list-empty { border:1px dashed var(--line-strong); border-radius:8px; padding:18px; color:var(--muted); text-align:center; background:var(--panel); }
141
222
  @media(max-width:1000px){.nre-experiment-table{overflow-x:auto}.nre-experiment-head,.nre-experiment-summary{min-width:1040px}.nre-experiment-detail{min-width:1040px}}
142
223
 
143
- /* ---- verdict 判定色(AttemptList/EvalList/ExperimentList verdict 文字与判定符共用) ---- */
144
- .nre .nre-verdict-passed { color:var(--good); }
145
- .nre .nre-eval-verdict.nre-verdict-passed,
146
- .nre-attempt-list .nre-attempt-verdict.nre-verdict-passed { color:var(--good); }
224
+ /* ---- verdict 判定色(EvalList/ExperimentList 的判定符;errored 在这里按 bad 收敛) ---- */
225
+ .nre .nre-eval-verdict.nre-verdict-passed { color:var(--good); }
147
226
  .nre .nre-eval-verdict.nre-verdict-failed,
148
227
  .nre .nre-eval-verdict.nre-verdict-errored { color:var(--bad); }
149
228
  .nre .nre-eval-verdict.nre-verdict-skipped { color:var(--soft); }
@@ -201,14 +280,6 @@ table.nre,
201
280
  .nre tbody th[scope="row"] {
202
281
  font-weight: 610;
203
282
  }
204
- /* rows: "experiment" 专属:行键下的紧凑摘要(eval/attempt 数、最后运行时间) */
205
- .nre .nre-row-meta-sub {
206
- margin-top: 2px;
207
- color: var(--muted);
208
- font-weight: 400;
209
- font-size: 0.82em;
210
- font-variant-numeric: tabular-nums;
211
- }
212
283
  .nre td {
213
284
  font-variant-numeric: tabular-nums;
214
285
  font-feature-settings: "tnum";
@@ -292,6 +363,11 @@ table.nre,
292
363
  .nre .nre-td-empty {
293
364
  background: var(--panel-2);
294
365
  }
366
+ /* 数据侧没给的格子:呈现层画软色缺失符,不进 textContent、不参与排序取值 */
367
+ .nre .nre-empty::before {
368
+ content: "—";
369
+ color: var(--soft);
370
+ }
295
371
 
296
372
  /* ---- verdict 语义色与计票 pill ---- */
297
373
  .nre .nre-verdict-passed { color: var(--good); }
@@ -318,8 +394,9 @@ table.nre,
318
394
  .nre .nre-verdict-pill.nre-verdict-failed { border-color: color-mix(in oklch, var(--bad), var(--line) 55%); }
319
395
  .nre .nre-verdict-pill.nre-verdict-errored { border-color: color-mix(in oklch, var(--warn), var(--line) 55%); }
320
396
 
321
- /* ---- RunOverview:KPI 条(对齐 view 的 .summary/.metric 密度) ---- */
322
- .nre-overview .nre-kpis {
397
+ /* ---- ScopeSummary:范围摘要卡,满宽 KPI 条(对齐 view 的 .summary/.metric 密度);
398
+ 嵌进 ExperimentComparison 组卡时降为紧凑行(规则在上面的比较块里) ---- */
399
+ .nre-scope-summary .nre-scope-kpis {
323
400
  display: grid;
324
401
  grid-template-columns: repeat(auto-fit, minmax(120px, 1fr));
325
402
  border: 1px solid var(--line);
@@ -328,19 +405,19 @@ table.nre,
328
405
  margin: 0 0 10px;
329
406
  background: var(--panel);
330
407
  }
331
- .nre-overview .nre-kpi {
408
+ .nre-scope-summary .nre-scope-kpi {
332
409
  padding: 12px 16px 13px;
333
410
  border-right: 1px solid var(--line);
334
411
  min-width: 0;
335
412
  }
336
- .nre-overview .nre-kpi:last-child { border-right: 0; }
337
- .nre-overview .nre-kpi dt {
413
+ .nre-scope-summary .nre-scope-kpi:last-child { border-right: 0; }
414
+ .nre-scope-summary .nre-scope-kpi dt {
338
415
  color: var(--soft);
339
416
  font-size: 11px;
340
417
  text-transform: uppercase;
341
418
  letter-spacing: 0.08em;
342
419
  }
343
- .nre-overview .nre-kpi dd {
420
+ .nre-scope-summary .nre-scope-kpi dd {
344
421
  margin: 6px 0 0;
345
422
  font-size: 20px;
346
423
  line-height: 1;
@@ -348,25 +425,21 @@ table.nre,
348
425
  font-variant-numeric: tabular-nums;
349
426
  white-space: nowrap;
350
427
  }
351
- .nre-overview .nre-verdicts {
352
- margin: 0.25rem 0;
353
- color: var(--muted);
354
- font-variant-numeric: tabular-nums;
355
- }
356
- .nre-overview .nre-verdict {
357
- margin-right: 1em;
428
+ /* 计票格装的是 pill 组:允许换行,行高回到常规 */
429
+ .nre-scope-summary .nre-scope-kpi-verdicts dd {
430
+ white-space: normal;
431
+ line-height: 1.4;
358
432
  }
359
- .nre-overview .nre-source {
433
+ .nre .nre-scope-summary-range {
360
434
  color: var(--soft);
361
435
  font-size: 0.85em;
362
- margin: 0.25rem 0;
363
- }
364
- .nre-overview .nre-source-snapshot {
365
- margin-left: 0.75em;
436
+ margin: 0.25rem 0 0;
366
437
  }
438
+
439
+ /* ---- 宿主警告块:.nre-report-warnings 外壳 + ul.nre-warnings + li.nre-warning[data-kind] ---- */
367
440
  .nre .nre-warnings {
368
441
  list-style: none;
369
- margin: 0.5rem 0 0;
442
+ margin: 0;
370
443
  padding: 10px 14px;
371
444
  border: 1px solid color-mix(in oklch, var(--warn), var(--line) 45%);
372
445
  border-left: 3px solid var(--warn);
@@ -375,37 +448,26 @@ table.nre,
375
448
  color: var(--text);
376
449
  font-size: 13px;
377
450
  }
378
-
379
- /* ---- GroupSummary:组摘要块(嵌在 Section 内的紧凑统计,不是 RunOverview 那种满宽页头 KPI 条)---- */
380
- .nre-group-summary .nre-group-kpis {
381
- display: flex;
382
- flex-wrap: wrap;
383
- column-gap: 22px;
384
- row-gap: 6px;
385
- margin: 0 0 6px;
386
- }
387
- .nre-group-summary .nre-group-kpi {
388
- min-width: 68px;
389
- }
390
- .nre-group-summary .nre-group-kpi dt {
391
- color: var(--soft);
392
- font-size: 11px;
393
- text-transform: uppercase;
394
- letter-spacing: 0.08em;
395
- }
396
- .nre-group-summary .nre-group-kpi dd {
397
- margin: 3px 0 0;
398
- font-size: 16px;
399
- line-height: 1.15;
400
- font-weight: 650;
401
- font-variant-numeric: tabular-nums;
402
- white-space: nowrap;
403
- }
404
- .nre-group-summary .nre-group-kpi-rate dd { font-size: 18px; }
405
- .nre-group-summary-time {
406
- color: var(--soft);
407
- font-size: 0.85em;
408
- margin: 0 0 0.75rem;
451
+ .nre .nre-warning + .nre-warning { margin-top: 8px; }
452
+ /* 警告携带的下一步命令:等宽块,无 JS 时点击即全选;enhance.js 在场时点击复制 */
453
+ .nre .nre-warning-command {
454
+ display: block;
455
+ margin-top: 6px;
456
+ padding: 6px 10px;
457
+ border: 1px solid var(--line);
458
+ border-radius: 7px;
459
+ background: var(--panel);
460
+ font-family: ui-monospace, SFMono-Regular, Menlo, monospace;
461
+ font-size: 0.9em;
462
+ overflow-wrap: anywhere;
463
+ user-select: all;
464
+ }
465
+ :root.nre-js .nre .nre-warning-command { cursor: copy; }
466
+ :root.nre-js .nre .nre-warning-command:hover { border-color: var(--line-strong); }
467
+ .nre .nre-warning-command[data-nre-copied]::after {
468
+ content: "✓";
469
+ margin-left: 0.6em;
470
+ color: var(--good);
409
471
  }
410
472
 
411
473
  /* ---- MetricMatrix ---- */
@@ -430,10 +492,23 @@ table.nre,
430
492
  font-weight: 400;
431
493
  margin-left: 0.25em;
432
494
  }
433
- .nre-scoreboard .nre-subject-missing {
495
+ /* 两种 0 分的注脚分开着色:没去考(notRun)偏警示,考了判不了(unscorable)偏软 */
496
+ .nre-scoreboard .nre-total-not-run,
497
+ .nre-scoreboard .nre-total-unscorable,
498
+ .nre-scoreboard .nre-subject-not-run,
499
+ .nre-scoreboard .nre-subject-unscorable {
434
500
  display: block;
435
- color: var(--warn);
436
501
  font-size: 0.8em;
502
+ font-weight: 400;
503
+ }
504
+ .nre-scoreboard .nre-total-not-run,
505
+ .nre-scoreboard .nre-subject-not-run { color: var(--warn); }
506
+ .nre-scoreboard .nre-total-unscorable,
507
+ .nre-scoreboard .nre-subject-unscorable { color: var(--soft); }
508
+ .nre-scoreboard .nre-scoreboard-ignored {
509
+ color: var(--muted);
510
+ font-size: 0.85em;
511
+ margin: 0.25rem 0 0;
437
512
  }
438
513
  .nre-scoreboard .nre-weights {
439
514
  color: var(--muted);
@@ -562,11 +637,21 @@ table.nre,
562
637
  color: var(--soft);
563
638
  font-size: 0.8em;
564
639
  }
565
- .nre .nre-delta-good { color: var(--good); }
566
- .nre .nre-delta-bad { color: var(--bad); }
567
- .nre .nre-delta-flat { color: var(--muted); }
568
- .nre .nre-delta-neutral { color: var(--text); }
569
- .nre .nre-delta-missing { color: var(--soft); }
640
+ /* Δ 行按数据侧算好的 outcome 着色:涨跌好坏不由正负号决定 */
641
+ .nre .nre-delta-d[data-outcome="improved"] { color: var(--good); }
642
+ .nre .nre-delta-d[data-outcome="regressed"] { color: var(--bad); }
643
+ .nre .nre-delta-d[data-outcome="unchanged"] { color: var(--muted); }
644
+ .nre .nre-delta-d[data-outcome="unavailable"] { color: var(--soft); }
645
+ /* 0 对不是错误:明确空态,与各列表 empty 同一姿势 */
646
+ .nre-delta-table-empty {
647
+ border: 1px dashed var(--line-strong);
648
+ border-radius: 8px;
649
+ padding: 18px;
650
+ color: var(--muted);
651
+ text-align: center;
652
+ background: var(--panel);
653
+ }
654
+ .nre-delta-table-empty .nre-missing { margin: 0; }
570
655
 
571
656
  /* ---- 排版原语 Row / Col / Section / Text ---- */
572
657
  .nre-col {
@@ -596,3 +681,79 @@ table.nre,
596
681
  color: var(--muted);
597
682
  margin: 0.25rem 0;
598
683
  }
684
+
685
+ /* ---- Tabs:静态 HTML 每 tab 一个 <details> 且仅首个 open(无 JS = 手风琴卡片,内容完整);
686
+ enhance.js 在 <html> 上打 nre-js 后升级为单选 tab 条:收起的 tab 缩成一枚标题排在首行,
687
+ 唯一展开的 tab 以 100% 宽 + order:1 换行到下方,活动标题带高亮下划线、贴着面板顶部。
688
+ 不能用 display:contents 把 summary/body 直接投影进 flex 容器——Chrome 里 <details> 的
689
+ UA shadow slot 会成为 flex item,子元素的 order 失效、收起面板还留 0 宽盒 ---- */
690
+ .nre-tabs > .nre-tab {
691
+ border: 1px solid var(--line);
692
+ border-radius: 8px;
693
+ background: var(--panel);
694
+ margin-bottom: 8px;
695
+ }
696
+ .nre-tabs > .nre-tab > .nre-tab-title {
697
+ padding: 10px 14px;
698
+ cursor: pointer;
699
+ user-select: none;
700
+ font-weight: 620;
701
+ list-style: none;
702
+ }
703
+ .nre-tabs > .nre-tab > .nre-tab-title::-webkit-details-marker { display: none; }
704
+ .nre-tabs > .nre-tab > .nre-tab-title::before {
705
+ content: "";
706
+ display: inline-block;
707
+ width: 7px;
708
+ height: 7px;
709
+ margin-right: 10px;
710
+ border-right: 1.5px solid var(--muted);
711
+ border-bottom: 1.5px solid var(--muted);
712
+ transform: rotate(-45deg);
713
+ transition: transform 0.15s;
714
+ vertical-align: 1px;
715
+ }
716
+ .nre-tabs > .nre-tab[open] > .nre-tab-title::before { transform: rotate(45deg); }
717
+ .nre-tabs > .nre-tab > .nre-tab-body { padding: 2px 14px 12px; }
718
+ .nre-tabs .nre-tab-body > .nre:first-child { margin-top: 0; }
719
+ .nre-tabs .nre-tab-body > .nre:last-child { margin-bottom: 0; }
720
+
721
+ :root.nre-js .nre-tabs {
722
+ display: flex;
723
+ flex-wrap: wrap;
724
+ align-items: stretch;
725
+ column-gap: 2px;
726
+ }
727
+ :root.nre-js .nre-tabs > .nre-tab {
728
+ margin: 0;
729
+ border: 0;
730
+ border-radius: 0;
731
+ background: transparent;
732
+ flex: 0 0 auto;
733
+ min-width: 0;
734
+ }
735
+ :root.nre-js .nre-tabs > .nre-tab[open] {
736
+ flex: 1 1 100%;
737
+ order: 1;
738
+ }
739
+ :root.nre-js .nre-tabs > .nre-tab > .nre-tab-title {
740
+ padding: 8px 14px 9px;
741
+ border-radius: 7px 7px 0 0;
742
+ color: var(--muted);
743
+ font-weight: 560;
744
+ box-shadow: inset 0 -1px 0 var(--line);
745
+ }
746
+ :root.nre-js .nre-tabs > .nre-tab > .nre-tab-title::before { content: none; }
747
+ :root.nre-js .nre-tabs > .nre-tab > .nre-tab-title:hover {
748
+ color: var(--text);
749
+ background: color-mix(in oklch, var(--panel-2), var(--panel) 35%);
750
+ }
751
+ :root.nre-js .nre-tabs > .nre-tab[open] > .nre-tab-title {
752
+ width: max-content;
753
+ max-width: 100%;
754
+ color: var(--text);
755
+ font-weight: 650;
756
+ box-shadow: inset 0 -2px 0 var(--nre-c0);
757
+ cursor: default;
758
+ }
759
+ :root.nre-js .nre-tabs > .nre-tab > .nre-tab-body { padding: 14px 0 0; }