inspect-ai 0.3.62__py3-none-any.whl → 0.3.64__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (518) hide show
  1. inspect_ai/_cli/cache.py +8 -7
  2. inspect_ai/_cli/common.py +0 -12
  3. inspect_ai/_cli/eval.py +32 -4
  4. inspect_ai/_cli/info.py +1 -0
  5. inspect_ai/_cli/list.py +1 -1
  6. inspect_ai/_cli/log.py +2 -0
  7. inspect_ai/_cli/main.py +1 -1
  8. inspect_ai/_cli/sandbox.py +4 -1
  9. inspect_ai/_cli/score.py +181 -32
  10. inspect_ai/_cli/trace.py +10 -0
  11. inspect_ai/_cli/view.py +4 -2
  12. inspect_ai/_display/core/active.py +2 -3
  13. inspect_ai/_display/core/config.py +7 -1
  14. inspect_ai/_display/textual/widgets/samples.py +4 -3
  15. inspect_ai/_display/textual/widgets/sandbox.py +6 -0
  16. inspect_ai/_eval/eval.py +104 -101
  17. inspect_ai/_eval/evalset.py +75 -75
  18. inspect_ai/_eval/loader.py +122 -12
  19. inspect_ai/_eval/registry.py +1 -1
  20. inspect_ai/_eval/run.py +14 -0
  21. inspect_ai/_eval/score.py +125 -36
  22. inspect_ai/_eval/task/log.py +105 -4
  23. inspect_ai/_eval/task/results.py +92 -38
  24. inspect_ai/_eval/task/run.py +9 -2
  25. inspect_ai/_eval/task/sandbox.py +35 -2
  26. inspect_ai/_eval/task/task.py +49 -46
  27. inspect_ai/_util/constants.py +1 -1
  28. inspect_ai/_util/content.py +8 -0
  29. inspect_ai/_util/error.py +2 -0
  30. inspect_ai/_util/file.py +15 -1
  31. inspect_ai/_util/hash.py +1 -1
  32. inspect_ai/_util/logger.py +4 -2
  33. inspect_ai/_util/registry.py +7 -1
  34. inspect_ai/_view/view.py +1 -2
  35. inspect_ai/_view/www/.vscode/extensions.json +3 -0
  36. inspect_ai/_view/www/.vscode/settings.json +8 -0
  37. inspect_ai/_view/www/App.css +97 -29
  38. inspect_ai/_view/www/README.md +1 -1
  39. inspect_ai/_view/www/dist/assets/index.css +16663 -14674
  40. inspect_ai/_view/www/dist/assets/index.js +58808 -51348
  41. inspect_ai/_view/www/dist/index.html +1 -1
  42. inspect_ai/_view/www/index.html +2 -2
  43. inspect_ai/_view/www/log-schema.json +87 -73
  44. inspect_ai/_view/www/package.json +22 -4
  45. inspect_ai/_view/www/postcss.config.cjs +8 -9
  46. inspect_ai/_view/www/src/{App.mjs → App.tsx} +356 -365
  47. inspect_ai/_view/www/src/AppErrorBoundary.tsx +47 -0
  48. inspect_ai/_view/www/src/api/api-browser.ts +2 -2
  49. inspect_ai/_view/www/src/api/api-http.ts +3 -5
  50. inspect_ai/_view/www/src/api/api-vscode.ts +6 -6
  51. inspect_ai/_view/www/src/api/client-api.ts +4 -4
  52. inspect_ai/_view/www/src/api/index.ts +4 -4
  53. inspect_ai/_view/www/src/api/{Types.ts → types.ts} +25 -9
  54. inspect_ai/_view/www/src/appearance/colors.ts +9 -0
  55. inspect_ai/_view/www/src/appearance/fonts.ts +39 -0
  56. inspect_ai/_view/www/src/appearance/icons.ts +100 -0
  57. inspect_ai/_view/www/src/appearance/{Styles.mjs → styles.ts} +2 -32
  58. inspect_ai/_view/www/src/components/AnsiDisplay.tsx +198 -0
  59. inspect_ai/_view/www/src/components/AsciinemaPlayer.tsx +86 -0
  60. inspect_ai/_view/www/src/components/Card.css +60 -0
  61. inspect_ai/_view/www/src/components/Card.tsx +109 -0
  62. inspect_ai/_view/www/src/components/CopyButton.module.css +11 -0
  63. inspect_ai/_view/www/src/components/CopyButton.tsx +58 -0
  64. inspect_ai/_view/www/src/components/DownloadButton.css +4 -0
  65. inspect_ai/_view/www/src/components/DownloadButton.tsx +25 -0
  66. inspect_ai/_view/www/src/components/DownloadPanel.css +10 -0
  67. inspect_ai/_view/www/src/components/DownloadPanel.tsx +30 -0
  68. inspect_ai/_view/www/src/components/EmptyPanel.css +12 -0
  69. inspect_ai/_view/www/src/components/EmptyPanel.tsx +15 -0
  70. inspect_ai/_view/www/src/components/ErrorPanel.css +37 -0
  71. inspect_ai/_view/www/src/components/ErrorPanel.tsx +39 -0
  72. inspect_ai/_view/www/src/components/ExpandablePanel.css +40 -0
  73. inspect_ai/_view/www/src/components/ExpandablePanel.tsx +115 -0
  74. inspect_ai/_view/www/src/components/FindBand.css +49 -0
  75. inspect_ai/_view/www/src/components/FindBand.tsx +130 -0
  76. inspect_ai/_view/www/src/components/HumanBaselineView.css +41 -0
  77. inspect_ai/_view/www/src/components/HumanBaselineView.tsx +162 -0
  78. inspect_ai/_view/www/src/components/JsonPanel.css +20 -0
  79. inspect_ai/_view/www/src/components/JsonPanel.tsx +82 -0
  80. inspect_ai/_view/www/src/components/LabeledValue.css +20 -0
  81. inspect_ai/_view/www/src/components/LabeledValue.tsx +41 -0
  82. inspect_ai/_view/www/src/components/LargeModal.module.css +54 -0
  83. inspect_ai/_view/www/src/components/LargeModal.tsx +189 -0
  84. inspect_ai/_view/www/src/components/LightboxCarousel.css +95 -0
  85. inspect_ai/_view/www/src/components/LightboxCarousel.tsx +132 -0
  86. inspect_ai/_view/www/src/components/MarkdownDiv.css +3 -0
  87. inspect_ai/_view/www/src/components/MarkdownDiv.tsx +133 -0
  88. inspect_ai/_view/www/src/components/MessageBand.css +43 -0
  89. inspect_ai/_view/www/src/components/MessageBand.tsx +39 -0
  90. inspect_ai/_view/www/src/components/MorePopOver.css +0 -0
  91. inspect_ai/_view/www/src/components/MorePopOver.tsx +67 -0
  92. inspect_ai/_view/www/src/components/NavPills.module.css +18 -0
  93. inspect_ai/_view/www/src/components/NavPills.tsx +101 -0
  94. inspect_ai/_view/www/src/components/ProgressBar.module.css +37 -0
  95. inspect_ai/_view/www/src/components/ProgressBar.tsx +22 -0
  96. inspect_ai/_view/www/src/components/TabSet.module.css +40 -0
  97. inspect_ai/_view/www/src/components/TabSet.tsx +215 -0
  98. inspect_ai/_view/www/src/components/ToolButton.css +3 -0
  99. inspect_ai/_view/www/src/components/ToolButton.tsx +27 -0
  100. inspect_ai/_view/www/src/components/VirtualList.module.css +19 -0
  101. inspect_ai/_view/www/src/components/VirtualList.tsx +292 -0
  102. inspect_ai/_view/www/src/{index.js → index.tsx} +45 -19
  103. inspect_ai/_view/www/src/{log → logfile}/remoteLogFile.ts +3 -8
  104. inspect_ai/_view/www/src/{utils/remoteZipFile.mjs → logfile/remoteZipFile.ts} +86 -80
  105. inspect_ai/_view/www/src/metadata/MetaDataGrid.tsx +83 -0
  106. inspect_ai/_view/www/src/metadata/MetaDataView.module.css +35 -0
  107. inspect_ai/_view/www/src/metadata/MetaDataView.tsx +95 -0
  108. inspect_ai/_view/www/src/metadata/MetadataGrid.module.css +15 -0
  109. inspect_ai/_view/www/src/metadata/RenderedContent.module.css +12 -0
  110. inspect_ai/_view/www/src/{components/RenderedContent/RenderedContent.mjs → metadata/RenderedContent.tsx} +92 -73
  111. inspect_ai/_view/www/src/metadata/types.ts +18 -0
  112. inspect_ai/_view/www/src/plan/DatasetDetailView.module.css +3 -0
  113. inspect_ai/_view/www/src/plan/DatasetDetailView.tsx +37 -0
  114. inspect_ai/_view/www/src/plan/DetailStep.module.css +9 -0
  115. inspect_ai/_view/www/src/plan/DetailStep.tsx +31 -0
  116. inspect_ai/_view/www/src/plan/PlanCard.tsx +28 -0
  117. inspect_ai/_view/www/src/plan/PlanDetailView.module.css +48 -0
  118. inspect_ai/_view/www/src/plan/PlanDetailView.tsx +324 -0
  119. inspect_ai/_view/www/src/plan/ScorerDetailView.module.css +3 -0
  120. inspect_ai/_view/www/src/plan/ScorerDetailView.tsx +30 -0
  121. inspect_ai/_view/www/src/plan/SolverDetailView.module.css +15 -0
  122. inspect_ai/_view/www/src/plan/SolverDetailView.tsx +32 -0
  123. inspect_ai/_view/www/src/samples/InlineSampleDisplay.module.css +8 -0
  124. inspect_ai/_view/www/src/samples/InlineSampleDisplay.tsx +53 -0
  125. inspect_ai/_view/www/src/samples/SampleDialog.tsx +122 -0
  126. inspect_ai/_view/www/src/samples/SampleDisplay.module.css +29 -0
  127. inspect_ai/_view/www/src/samples/SampleDisplay.tsx +331 -0
  128. inspect_ai/_view/www/src/samples/SampleSummaryView.module.css +24 -0
  129. inspect_ai/_view/www/src/samples/SampleSummaryView.tsx +177 -0
  130. inspect_ai/_view/www/src/samples/SamplesTools.tsx +52 -0
  131. inspect_ai/_view/www/src/samples/chat/ChatMessage.module.css +29 -0
  132. inspect_ai/_view/www/src/samples/chat/ChatMessage.tsx +76 -0
  133. inspect_ai/_view/www/src/samples/chat/ChatMessageRenderer.tsx +60 -0
  134. inspect_ai/_view/www/src/samples/chat/ChatMessageRow.module.css +9 -0
  135. inspect_ai/_view/www/src/samples/chat/ChatMessageRow.tsx +57 -0
  136. inspect_ai/_view/www/src/samples/chat/ChatView.tsx +47 -0
  137. inspect_ai/_view/www/src/samples/chat/ChatViewVirtualList.module.css +4 -0
  138. inspect_ai/_view/www/src/samples/chat/ChatViewVirtualList.tsx +58 -0
  139. inspect_ai/_view/www/src/samples/chat/MessageContent.module.css +4 -0
  140. inspect_ai/_view/www/src/samples/chat/MessageContent.tsx +157 -0
  141. inspect_ai/_view/www/src/samples/chat/MessageContents.module.css +3 -0
  142. inspect_ai/_view/www/src/samples/chat/MessageContents.tsx +133 -0
  143. inspect_ai/_view/www/src/samples/chat/messages.ts +112 -0
  144. inspect_ai/_view/www/src/samples/chat/tools/ToolCallView.tsx +147 -0
  145. inspect_ai/_view/www/src/samples/chat/tools/ToolInput.module.css +14 -0
  146. inspect_ai/_view/www/src/samples/chat/tools/ToolInput.tsx +76 -0
  147. inspect_ai/_view/www/src/samples/chat/tools/ToolOutput.module.css +19 -0
  148. inspect_ai/_view/www/src/samples/chat/tools/ToolOutput.tsx +60 -0
  149. inspect_ai/_view/www/src/samples/chat/tools/ToolTitle.module.css +4 -0
  150. inspect_ai/_view/www/src/samples/chat/tools/ToolTitle.tsx +18 -0
  151. inspect_ai/_view/www/src/samples/chat/tools/tool.ts +92 -0
  152. inspect_ai/_view/www/src/samples/descriptor/samplesDescriptor.tsx +365 -0
  153. inspect_ai/_view/www/src/samples/descriptor/score/BooleanScoreDescriptor.module.css +22 -0
  154. inspect_ai/_view/www/src/samples/descriptor/score/BooleanScoreDescriptor.tsx +26 -0
  155. inspect_ai/_view/www/src/samples/descriptor/score/CategoricalScoreDescriptor.tsx +18 -0
  156. inspect_ai/_view/www/src/samples/descriptor/score/NumericScoreDescriptor.tsx +27 -0
  157. inspect_ai/_view/www/src/samples/descriptor/score/ObjectScoreDescriptor.module.css +18 -0
  158. inspect_ai/_view/www/src/samples/descriptor/score/ObjectScoreDescriptor.tsx +71 -0
  159. inspect_ai/_view/www/src/samples/descriptor/score/OtherScoreDescriptor.tsx +20 -0
  160. inspect_ai/_view/www/src/samples/descriptor/score/PassFailScoreDescriptor.module.css +28 -0
  161. inspect_ai/_view/www/src/samples/descriptor/score/PassFailScoreDescriptor.tsx +81 -0
  162. inspect_ai/_view/www/src/samples/descriptor/score/ScoreDescriptor.tsx +99 -0
  163. inspect_ai/_view/www/src/samples/descriptor/types.ts +55 -0
  164. inspect_ai/_view/www/src/samples/error/FlatSampleErrorView.module.css +19 -0
  165. inspect_ai/_view/www/src/samples/error/FlatSampleErrorView.tsx +22 -0
  166. inspect_ai/_view/www/src/samples/error/SampleErrorView.module.css +17 -0
  167. inspect_ai/_view/www/src/samples/error/SampleErrorView.tsx +31 -0
  168. inspect_ai/_view/www/src/samples/error/error.ts +15 -0
  169. inspect_ai/_view/www/src/samples/list/SampleFooter.module.css +9 -0
  170. inspect_ai/_view/www/src/samples/list/SampleFooter.tsx +14 -0
  171. inspect_ai/_view/www/src/samples/list/SampleHeader.module.css +13 -0
  172. inspect_ai/_view/www/src/samples/list/SampleHeader.tsx +36 -0
  173. inspect_ai/_view/www/src/samples/list/SampleList.module.css +11 -0
  174. inspect_ai/_view/www/src/samples/list/SampleList.tsx +247 -0
  175. inspect_ai/_view/www/src/samples/list/SampleRow.module.css +33 -0
  176. inspect_ai/_view/www/src/samples/list/SampleRow.tsx +98 -0
  177. inspect_ai/_view/www/src/samples/list/SampleSeparator.module.css +6 -0
  178. inspect_ai/_view/www/src/samples/list/SampleSeparator.tsx +24 -0
  179. inspect_ai/_view/www/src/samples/sample-tools/EpochFilter.module.css +9 -0
  180. inspect_ai/_view/www/src/samples/sample-tools/EpochFilter.tsx +51 -0
  181. inspect_ai/_view/www/src/samples/sample-tools/SelectScorer.module.css +16 -0
  182. inspect_ai/_view/www/src/samples/sample-tools/SelectScorer.tsx +175 -0
  183. inspect_ai/_view/www/src/samples/sample-tools/SortFilter.module.css +9 -0
  184. inspect_ai/_view/www/src/samples/sample-tools/SortFilter.tsx +186 -0
  185. inspect_ai/_view/www/src/samples/{tools/filters.mjs → sample-tools/filters.ts} +86 -81
  186. inspect_ai/_view/www/src/samples/sample-tools/sample-filter/SampleFilter.module.css +16 -0
  187. inspect_ai/_view/www/src/samples/sample-tools/sample-filter/SampleFilter.tsx +288 -0
  188. inspect_ai/_view/www/src/samples/sample-tools/sample-filter/completions.ts +346 -0
  189. inspect_ai/_view/www/src/samples/sample-tools/sample-filter/language.ts +19 -0
  190. inspect_ai/_view/www/src/samples/sample-tools/sample-filter/tokenize.ts +97 -0
  191. inspect_ai/_view/www/src/samples/{SampleLimit.mjs → sampleLimit.ts} +3 -6
  192. inspect_ai/_view/www/src/samples/scores/SampleScoreView.module.css +53 -0
  193. inspect_ai/_view/www/src/samples/scores/SampleScoreView.tsx +168 -0
  194. inspect_ai/_view/www/src/samples/scores/SampleScores.module.css +5 -0
  195. inspect_ai/_view/www/src/samples/scores/SampleScores.tsx +37 -0
  196. inspect_ai/_view/www/src/samples/transcript/ApprovalEventView.tsx +66 -0
  197. inspect_ai/_view/www/src/samples/transcript/ErrorEventView.tsx +51 -0
  198. inspect_ai/_view/www/src/samples/transcript/InfoEventView.module.css +3 -0
  199. inspect_ai/_view/www/src/samples/transcript/InfoEventView.tsx +54 -0
  200. inspect_ai/_view/www/src/samples/transcript/InputEventView.tsx +48 -0
  201. inspect_ai/_view/www/src/samples/transcript/LoggerEventView.module.css +6 -0
  202. inspect_ai/_view/www/src/samples/transcript/LoggerEventView.tsx +36 -0
  203. inspect_ai/_view/www/src/samples/transcript/ModelEventView.module.css +43 -0
  204. inspect_ai/_view/www/src/samples/transcript/ModelEventView.tsx +223 -0
  205. inspect_ai/_view/www/src/samples/transcript/SampleInitEventView.module.css +23 -0
  206. inspect_ai/_view/www/src/samples/transcript/SampleInitEventView.tsx +112 -0
  207. inspect_ai/_view/www/src/samples/transcript/SampleLimitEventView.tsx +75 -0
  208. inspect_ai/_view/www/src/samples/transcript/SampleTranscript.tsx +22 -0
  209. inspect_ai/_view/www/src/samples/transcript/ScoreEventView.module.css +15 -0
  210. inspect_ai/_view/www/src/samples/transcript/ScoreEventView.tsx +100 -0
  211. inspect_ai/_view/www/src/samples/transcript/StepEventView.tsx +171 -0
  212. inspect_ai/_view/www/src/samples/transcript/SubtaskEventView.module.css +19 -0
  213. inspect_ai/_view/www/src/samples/transcript/SubtaskEventView.tsx +133 -0
  214. inspect_ai/_view/www/src/samples/transcript/ToolEventView.module.css +10 -0
  215. inspect_ai/_view/www/src/samples/transcript/ToolEventView.tsx +92 -0
  216. inspect_ai/_view/www/src/samples/transcript/TranscriptView.module.css +49 -0
  217. inspect_ai/_view/www/src/samples/transcript/TranscriptView.tsx +449 -0
  218. inspect_ai/_view/www/src/samples/transcript/event/EventNav.module.css +5 -0
  219. inspect_ai/_view/www/src/samples/transcript/event/EventNav.tsx +43 -0
  220. inspect_ai/_view/www/src/samples/transcript/event/EventNavs.module.css +3 -0
  221. inspect_ai/_view/www/src/samples/transcript/event/EventNavs.tsx +39 -0
  222. inspect_ai/_view/www/src/samples/transcript/event/EventPanel.module.css +25 -0
  223. inspect_ai/_view/www/src/samples/transcript/event/EventPanel.tsx +191 -0
  224. inspect_ai/_view/www/src/samples/transcript/event/EventRow.module.css +13 -0
  225. inspect_ai/_view/www/src/samples/transcript/event/EventRow.tsx +32 -0
  226. inspect_ai/_view/www/src/samples/transcript/event/EventSection.module.css +8 -0
  227. inspect_ai/_view/www/src/samples/transcript/event/EventSection.tsx +29 -0
  228. inspect_ai/_view/www/src/samples/transcript/state/StateDiffView.tsx +67 -0
  229. inspect_ai/_view/www/src/samples/transcript/state/StateEventRenderers.tsx +285 -0
  230. inspect_ai/_view/www/src/samples/transcript/state/StateEventRenders.module.css +10 -0
  231. inspect_ai/_view/www/src/samples/transcript/state/StateEventView.module.css +9 -0
  232. inspect_ai/_view/www/src/samples/transcript/state/StateEventView.tsx +346 -0
  233. inspect_ai/_view/www/src/samples/transcript/types.ts +58 -0
  234. inspect_ai/_view/www/src/types/log.d.ts +108 -19
  235. inspect_ai/_view/www/src/types/prism.d.ts +11 -0
  236. inspect_ai/_view/www/src/types.ts +71 -0
  237. inspect_ai/_view/www/src/usage/ModelTokenTable.tsx +28 -0
  238. inspect_ai/_view/www/src/usage/ModelUsagePanel.module.css +24 -0
  239. inspect_ai/_view/www/src/usage/ModelUsagePanel.tsx +97 -0
  240. inspect_ai/_view/www/src/usage/TokenTable.module.css +17 -0
  241. inspect_ai/_view/www/src/usage/TokenTable.tsx +91 -0
  242. inspect_ai/_view/www/src/usage/UsageCard.module.css +15 -0
  243. inspect_ai/_view/www/src/usage/UsageCard.tsx +67 -0
  244. inspect_ai/_view/www/src/utils/attachments.ts +42 -0
  245. inspect_ai/_view/www/src/utils/{Base64.mjs → base64.ts} +1 -6
  246. inspect_ai/_view/www/src/{components/Browser.mjs → utils/browser.ts} +0 -1
  247. inspect_ai/_view/www/src/utils/debugging.ts +28 -0
  248. inspect_ai/_view/www/src/utils/dom.ts +30 -0
  249. inspect_ai/_view/www/src/utils/format.ts +194 -0
  250. inspect_ai/_view/www/src/utils/git.ts +7 -0
  251. inspect_ai/_view/www/src/utils/html.ts +6 -0
  252. inspect_ai/_view/www/src/utils/http.ts +14 -0
  253. inspect_ai/_view/www/src/utils/{Path.mjs → path.ts} +2 -9
  254. inspect_ai/_view/www/src/utils/{Print.mjs → print.ts} +34 -26
  255. inspect_ai/_view/www/src/utils/queue.ts +51 -0
  256. inspect_ai/_view/www/src/utils/sync.ts +114 -0
  257. inspect_ai/_view/www/src/utils/{Type.mjs → type.ts} +3 -6
  258. inspect_ai/_view/www/src/utils/vscode.ts +13 -0
  259. inspect_ai/_view/www/src/workspace/WorkSpace.tsx +324 -0
  260. inspect_ai/_view/www/src/workspace/WorkSpaceView.module.css +33 -0
  261. inspect_ai/_view/www/src/workspace/WorkSpaceView.tsx +158 -0
  262. inspect_ai/_view/www/src/workspace/error/TaskErrorPanel.module.css +3 -0
  263. inspect_ai/_view/www/src/workspace/error/TaskErrorPanel.tsx +28 -0
  264. inspect_ai/_view/www/src/workspace/navbar/Navbar.module.css +54 -0
  265. inspect_ai/_view/www/src/workspace/navbar/Navbar.tsx +68 -0
  266. inspect_ai/_view/www/src/workspace/navbar/PrimaryBar.module.css +52 -0
  267. inspect_ai/_view/www/src/workspace/navbar/PrimaryBar.tsx +114 -0
  268. inspect_ai/_view/www/src/workspace/navbar/ResultsPanel.module.css +90 -0
  269. inspect_ai/_view/www/src/workspace/navbar/ResultsPanel.tsx +180 -0
  270. inspect_ai/_view/www/src/workspace/navbar/SecondaryBar.module.css +28 -0
  271. inspect_ai/_view/www/src/workspace/navbar/SecondaryBar.tsx +226 -0
  272. inspect_ai/_view/www/src/workspace/navbar/StatusPanel.module.css +14 -0
  273. inspect_ai/_view/www/src/workspace/navbar/StatusPanel.tsx +61 -0
  274. inspect_ai/_view/www/src/workspace/sidebar/EvalStatus.module.css +15 -0
  275. inspect_ai/_view/www/src/workspace/sidebar/EvalStatus.tsx +71 -0
  276. inspect_ai/_view/www/src/workspace/sidebar/LogDirectoryTitleView.module.css +5 -0
  277. inspect_ai/_view/www/src/workspace/sidebar/LogDirectoryTitleView.tsx +56 -0
  278. inspect_ai/_view/www/src/workspace/sidebar/Sidebar.module.css +68 -0
  279. inspect_ai/_view/www/src/workspace/sidebar/Sidebar.tsx +85 -0
  280. inspect_ai/_view/www/src/workspace/sidebar/SidebarLogEntry.module.css +29 -0
  281. inspect_ai/_view/www/src/workspace/sidebar/SidebarLogEntry.tsx +95 -0
  282. inspect_ai/_view/www/src/workspace/sidebar/SidebarScoreView.module.css +23 -0
  283. inspect_ai/_view/www/src/workspace/sidebar/SidebarScoreView.tsx +43 -0
  284. inspect_ai/_view/www/src/workspace/sidebar/SidebarScoresView.module.css +35 -0
  285. inspect_ai/_view/www/src/workspace/sidebar/SidebarScoresView.tsx +63 -0
  286. inspect_ai/_view/www/src/workspace/tabs/InfoTab.module.css +0 -0
  287. inspect_ai/_view/www/src/workspace/tabs/InfoTab.tsx +70 -0
  288. inspect_ai/_view/www/src/workspace/tabs/JsonTab.module.css +5 -0
  289. inspect_ai/_view/www/src/workspace/tabs/JsonTab.tsx +46 -0
  290. inspect_ai/_view/www/src/workspace/tabs/SamplesTab.tsx +204 -0
  291. inspect_ai/_view/www/src/workspace/tabs/grouping.ts +195 -0
  292. inspect_ai/_view/www/src/workspace/tabs/types.ts +19 -0
  293. inspect_ai/_view/www/src/workspace/types.ts +10 -0
  294. inspect_ai/_view/www/src/workspace/utils.ts +34 -0
  295. inspect_ai/_view/www/tsconfig.json +23 -9
  296. inspect_ai/_view/www/vite.config.js +8 -17
  297. inspect_ai/_view/www/yarn.lock +627 -556
  298. inspect_ai/approval/_approval.py +2 -0
  299. inspect_ai/approval/_approver.py +4 -4
  300. inspect_ai/approval/_auto.py +1 -1
  301. inspect_ai/approval/_human/approver.py +3 -0
  302. inspect_ai/approval/_policy.py +5 -0
  303. inspect_ai/approval/_registry.py +2 -2
  304. inspect_ai/dataset/_dataset.py +64 -37
  305. inspect_ai/dataset/_sources/__init__.py +0 -0
  306. inspect_ai/dataset/_sources/csv.py +20 -12
  307. inspect_ai/dataset/_sources/file.py +4 -0
  308. inspect_ai/dataset/_sources/hf.py +39 -29
  309. inspect_ai/dataset/_sources/json.py +17 -9
  310. inspect_ai/log/__init__.py +2 -0
  311. inspect_ai/log/_convert.py +3 -3
  312. inspect_ai/log/_file.py +24 -9
  313. inspect_ai/log/_log.py +101 -13
  314. inspect_ai/log/_message.py +4 -2
  315. inspect_ai/log/_recorders/file.py +4 -0
  316. inspect_ai/log/_recorders/json.py +5 -7
  317. inspect_ai/log/_recorders/recorder.py +3 -0
  318. inspect_ai/log/_transcript.py +19 -8
  319. inspect_ai/model/__init__.py +2 -0
  320. inspect_ai/model/_cache.py +39 -21
  321. inspect_ai/model/_call_tools.py +4 -3
  322. inspect_ai/model/_chat_message.py +14 -4
  323. inspect_ai/model/_generate_config.py +1 -1
  324. inspect_ai/model/_model.py +31 -24
  325. inspect_ai/model/_model_output.py +14 -1
  326. inspect_ai/model/_openai.py +10 -18
  327. inspect_ai/model/_providers/anthropic.py +3 -3
  328. inspect_ai/model/_providers/google.py +9 -5
  329. inspect_ai/model/_providers/openai.py +5 -9
  330. inspect_ai/model/_providers/openai_o1.py +3 -5
  331. inspect_ai/model/_providers/openrouter.py +86 -0
  332. inspect_ai/model/_providers/providers.py +11 -0
  333. inspect_ai/scorer/__init__.py +6 -1
  334. inspect_ai/scorer/_answer.py +7 -7
  335. inspect_ai/scorer/_classification.py +38 -18
  336. inspect_ai/scorer/_common.py +2 -8
  337. inspect_ai/scorer/_match.py +4 -5
  338. inspect_ai/scorer/_metric.py +87 -28
  339. inspect_ai/scorer/_metrics/__init__.py +3 -3
  340. inspect_ai/scorer/_metrics/accuracy.py +8 -10
  341. inspect_ai/scorer/_metrics/mean.py +3 -17
  342. inspect_ai/scorer/_metrics/std.py +111 -30
  343. inspect_ai/scorer/_model.py +12 -12
  344. inspect_ai/scorer/_pattern.py +3 -3
  345. inspect_ai/scorer/_reducer/reducer.py +36 -21
  346. inspect_ai/scorer/_reducer/registry.py +2 -2
  347. inspect_ai/scorer/_reducer/types.py +7 -1
  348. inspect_ai/scorer/_score.py +11 -1
  349. inspect_ai/scorer/_scorer.py +110 -16
  350. inspect_ai/solver/__init__.py +1 -1
  351. inspect_ai/solver/_basic_agent.py +19 -22
  352. inspect_ai/solver/_bridge/__init__.py +0 -3
  353. inspect_ai/solver/_bridge/bridge.py +3 -3
  354. inspect_ai/solver/_chain.py +1 -2
  355. inspect_ai/solver/_critique.py +3 -3
  356. inspect_ai/solver/_fork.py +2 -2
  357. inspect_ai/solver/_human_agent/__init__.py +0 -0
  358. inspect_ai/solver/_human_agent/agent.py +5 -8
  359. inspect_ai/solver/_human_agent/commands/clock.py +14 -10
  360. inspect_ai/solver/_human_agent/commands/note.py +1 -1
  361. inspect_ai/solver/_human_agent/commands/score.py +0 -11
  362. inspect_ai/solver/_multiple_choice.py +38 -26
  363. inspect_ai/solver/_prompt.py +7 -7
  364. inspect_ai/solver/_solver.py +53 -52
  365. inspect_ai/solver/_task_state.py +80 -69
  366. inspect_ai/solver/_use_tools.py +9 -9
  367. inspect_ai/tool/__init__.py +4 -1
  368. inspect_ai/tool/_tool.py +43 -14
  369. inspect_ai/tool/_tool_call.py +6 -2
  370. inspect_ai/tool/_tool_choice.py +3 -1
  371. inspect_ai/tool/_tool_def.py +10 -8
  372. inspect_ai/tool/_tool_params.py +24 -0
  373. inspect_ai/tool/_tool_with.py +7 -7
  374. inspect_ai/tool/_tools/__init__.py +0 -0
  375. inspect_ai/tool/{beta → _tools}/_computer/_common.py +2 -2
  376. inspect_ai/tool/{beta → _tools}/_computer/_computer.py +13 -5
  377. inspect_ai/tool/_tools/_computer/_resources/tool/__init__.py +0 -0
  378. inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_x11_client.py +1 -1
  379. inspect_ai/tool/_tools/_computer/_resources/tool/requirements.txt +0 -0
  380. inspect_ai/tool/_tools/_execute.py +23 -11
  381. inspect_ai/tool/_tools/_web_browser/_resources/README.md +2 -2
  382. inspect_ai/tool/_tools/_web_browser/_web_browser.py +5 -3
  383. inspect_ai/tool/_tools/_web_search.py +7 -5
  384. inspect_ai/tool/beta.py +3 -0
  385. inspect_ai/util/_concurrency.py +3 -3
  386. inspect_ai/util/_panel.py +2 -0
  387. inspect_ai/util/_resource.py +12 -12
  388. inspect_ai/util/_sandbox/docker/compose.py +23 -20
  389. inspect_ai/util/_sandbox/docker/config.py +2 -1
  390. inspect_ai/util/_sandbox/docker/docker.py +42 -86
  391. inspect_ai/util/_sandbox/docker/service.py +100 -0
  392. inspect_ai/util/_sandbox/environment.py +99 -96
  393. inspect_ai/util/_sandbox/self_check.py +124 -16
  394. inspect_ai/util/_subprocess.py +5 -3
  395. inspect_ai/util/_subtask.py +15 -16
  396. {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.64.dist-info}/LICENSE +1 -1
  397. {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.64.dist-info}/METADATA +11 -6
  398. inspect_ai-0.3.64.dist-info/RECORD +625 -0
  399. inspect_ai/_view/www/src/Register.mjs +0 -3
  400. inspect_ai/_view/www/src/Types.mjs +0 -38
  401. inspect_ai/_view/www/src/appearance/Colors.mjs +0 -27
  402. inspect_ai/_view/www/src/appearance/Fonts.mjs +0 -66
  403. inspect_ai/_view/www/src/appearance/Icons.mjs +0 -240
  404. inspect_ai/_view/www/src/components/AnsiDisplay.mjs +0 -184
  405. inspect_ai/_view/www/src/components/AppErrorBoundary.mjs +0 -34
  406. inspect_ai/_view/www/src/components/AsciiCinemaPlayer.mjs +0 -74
  407. inspect_ai/_view/www/src/components/Card.mjs +0 -126
  408. inspect_ai/_view/www/src/components/ChatView.mjs +0 -441
  409. inspect_ai/_view/www/src/components/CopyButton.mjs +0 -48
  410. inspect_ai/_view/www/src/components/Dialog.mjs +0 -61
  411. inspect_ai/_view/www/src/components/DownloadButton.mjs +0 -15
  412. inspect_ai/_view/www/src/components/DownloadPanel.mjs +0 -29
  413. inspect_ai/_view/www/src/components/EmptyPanel.mjs +0 -23
  414. inspect_ai/_view/www/src/components/ErrorPanel.mjs +0 -66
  415. inspect_ai/_view/www/src/components/ExpandablePanel.mjs +0 -136
  416. inspect_ai/_view/www/src/components/FindBand.mjs +0 -157
  417. inspect_ai/_view/www/src/components/HumanBaselineView.mjs +0 -168
  418. inspect_ai/_view/www/src/components/JsonPanel.mjs +0 -61
  419. inspect_ai/_view/www/src/components/LabeledValue.mjs +0 -32
  420. inspect_ai/_view/www/src/components/LargeModal.mjs +0 -190
  421. inspect_ai/_view/www/src/components/LightboxCarousel.mjs +0 -217
  422. inspect_ai/_view/www/src/components/MarkdownDiv.mjs +0 -118
  423. inspect_ai/_view/www/src/components/MessageBand.mjs +0 -48
  424. inspect_ai/_view/www/src/components/MessageContent.mjs +0 -111
  425. inspect_ai/_view/www/src/components/MetaDataGrid.mjs +0 -92
  426. inspect_ai/_view/www/src/components/MetaDataView.mjs +0 -109
  427. inspect_ai/_view/www/src/components/MorePopOver.mjs +0 -50
  428. inspect_ai/_view/www/src/components/NavPills.mjs +0 -63
  429. inspect_ai/_view/www/src/components/ProgressBar.mjs +0 -51
  430. inspect_ai/_view/www/src/components/RenderedContent/ChatMessageRenderer.mjs +0 -54
  431. inspect_ai/_view/www/src/components/RenderedContent/Types.mjs +0 -19
  432. inspect_ai/_view/www/src/components/TabSet.mjs +0 -184
  433. inspect_ai/_view/www/src/components/ToolButton.mjs +0 -16
  434. inspect_ai/_view/www/src/components/Tools.mjs +0 -376
  435. inspect_ai/_view/www/src/components/VirtualList.mjs +0 -280
  436. inspect_ai/_view/www/src/components/ansi-output.js +0 -932
  437. inspect_ai/_view/www/src/json/JsonTab.mjs +0 -48
  438. inspect_ai/_view/www/src/log-reader/Log-Reader.mjs +0 -25
  439. inspect_ai/_view/www/src/log-reader/Native-Log-Reader.mjs +0 -13
  440. inspect_ai/_view/www/src/log-reader/Open-AI-Log-Reader.mjs +0 -263
  441. inspect_ai/_view/www/src/navbar/Navbar.mjs +0 -418
  442. inspect_ai/_view/www/src/navbar/SecondaryBar.mjs +0 -175
  443. inspect_ai/_view/www/src/plan/PlanCard.mjs +0 -418
  444. inspect_ai/_view/www/src/samples/SampleDialog.mjs +0 -123
  445. inspect_ai/_view/www/src/samples/SampleDisplay.mjs +0 -516
  446. inspect_ai/_view/www/src/samples/SampleError.mjs +0 -99
  447. inspect_ai/_view/www/src/samples/SampleList.mjs +0 -427
  448. inspect_ai/_view/www/src/samples/SampleScoreView.mjs +0 -172
  449. inspect_ai/_view/www/src/samples/SampleScores.mjs +0 -34
  450. inspect_ai/_view/www/src/samples/SampleTranscript.mjs +0 -20
  451. inspect_ai/_view/www/src/samples/SamplesDescriptor.mjs +0 -771
  452. inspect_ai/_view/www/src/samples/SamplesTab.mjs +0 -399
  453. inspect_ai/_view/www/src/samples/SamplesTools.mjs +0 -64
  454. inspect_ai/_view/www/src/samples/tools/EpochFilter.mjs +0 -38
  455. inspect_ai/_view/www/src/samples/tools/SampleFilter.mjs +0 -756
  456. inspect_ai/_view/www/src/samples/tools/SelectScorer.mjs +0 -141
  457. inspect_ai/_view/www/src/samples/tools/SortFilter.mjs +0 -151
  458. inspect_ai/_view/www/src/samples/transcript/ApprovalEventView.mjs +0 -71
  459. inspect_ai/_view/www/src/samples/transcript/ErrorEventView.mjs +0 -44
  460. inspect_ai/_view/www/src/samples/transcript/EventPanel.mjs +0 -271
  461. inspect_ai/_view/www/src/samples/transcript/EventRow.mjs +0 -46
  462. inspect_ai/_view/www/src/samples/transcript/EventSection.mjs +0 -33
  463. inspect_ai/_view/www/src/samples/transcript/InfoEventView.mjs +0 -59
  464. inspect_ai/_view/www/src/samples/transcript/InputEventView.mjs +0 -44
  465. inspect_ai/_view/www/src/samples/transcript/LoggerEventView.mjs +0 -32
  466. inspect_ai/_view/www/src/samples/transcript/ModelEventView.mjs +0 -216
  467. inspect_ai/_view/www/src/samples/transcript/SampleInitEventView.mjs +0 -107
  468. inspect_ai/_view/www/src/samples/transcript/SampleLimitEventView.mjs +0 -74
  469. inspect_ai/_view/www/src/samples/transcript/ScoreEventView.mjs +0 -100
  470. inspect_ai/_view/www/src/samples/transcript/StepEventView.mjs +0 -187
  471. inspect_ai/_view/www/src/samples/transcript/SubtaskEventView.mjs +0 -133
  472. inspect_ai/_view/www/src/samples/transcript/ToolEventView.mjs +0 -88
  473. inspect_ai/_view/www/src/samples/transcript/TranscriptView.mjs +0 -459
  474. inspect_ai/_view/www/src/samples/transcript/Types.mjs +0 -44
  475. inspect_ai/_view/www/src/samples/transcript/state/StateDiffView.mjs +0 -53
  476. inspect_ai/_view/www/src/samples/transcript/state/StateEventRenderers.mjs +0 -254
  477. inspect_ai/_view/www/src/samples/transcript/state/StateEventView.mjs +0 -313
  478. inspect_ai/_view/www/src/sidebar/Sidebar.mjs +0 -418
  479. inspect_ai/_view/www/src/usage/ModelTokenTable.mjs +0 -72
  480. inspect_ai/_view/www/src/usage/UsageCard.mjs +0 -159
  481. inspect_ai/_view/www/src/utils/Format.mjs +0 -260
  482. inspect_ai/_view/www/src/utils/Git.mjs +0 -12
  483. inspect_ai/_view/www/src/utils/Html.mjs +0 -21
  484. inspect_ai/_view/www/src/utils/attachments.mjs +0 -31
  485. inspect_ai/_view/www/src/utils/debugging.mjs +0 -23
  486. inspect_ai/_view/www/src/utils/http.mjs +0 -18
  487. inspect_ai/_view/www/src/utils/queue.mjs +0 -67
  488. inspect_ai/_view/www/src/utils/sync.mjs +0 -101
  489. inspect_ai/_view/www/src/workspace/TaskErrorPanel.mjs +0 -17
  490. inspect_ai/_view/www/src/workspace/WorkSpace.mjs +0 -516
  491. inspect_ai/tool/beta/__init__.py +0 -5
  492. inspect_ai-0.3.62.dist-info/RECORD +0 -481
  493. /inspect_ai/{tool/beta/_computer/_resources/tool → _eval}/__init__.py +0 -0
  494. /inspect_ai/{tool/beta/_computer/_resources/tool/requirements.txt → _util/__init__.py} +0 -0
  495. /inspect_ai/_view/www/src/{constants.mjs → constants.ts} +0 -0
  496. /inspect_ai/tool/{beta → _tools}/_computer/__init__.py +0 -0
  497. /inspect_ai/tool/{beta → _tools}/_computer/_computer_split.py +0 -0
  498. /inspect_ai/tool/{beta → _tools}/_computer/_resources/Dockerfile +0 -0
  499. /inspect_ai/tool/{beta → _tools}/_computer/_resources/README.md +0 -0
  500. /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/entrypoint.sh +0 -0
  501. /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/novnc_startup.sh +0 -0
  502. /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/x11vnc_startup.sh +0 -0
  503. /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/xfce_startup.sh +0 -0
  504. /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/xvfb_startup.sh +0 -0
  505. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/Code/User/globalStorage/state.vscdb +0 -0
  506. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/Code/User/settings.json +0 -0
  507. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/xfce4/xfconf/xfce-perchannel-xml/xfce4-panel.xml +0 -0
  508. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/xfce4/xfconf/xfce-perchannel-xml/xfce4-screensaver.xml +0 -0
  509. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/Desktop/Firefox Web Browser.desktop +0 -0
  510. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/Desktop/Terminal.desktop +0 -0
  511. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/Desktop/Visual Studio Code.desktop +0 -0
  512. /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_logger.py +0 -0
  513. /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_run.py +0 -0
  514. /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_tool_result.py +0 -0
  515. /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/computer_tool.py +0 -0
  516. {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.64.dist-info}/WHEEL +0 -0
  517. {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.64.dist-info}/entry_points.txt +0 -0
  518. {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.64.dist-info}/top_level.txt +0 -0
@@ -1,516 +0,0 @@
1
- import { html } from "htm/preact";
2
-
3
- import { ChatViewVirtualList } from "../components/ChatView.mjs";
4
- import { MetaDataView } from "../components/MetaDataView.mjs";
5
- import { TabSet, TabPanel } from "../components/TabSet.mjs";
6
-
7
- import { inputString } from "../utils/Format.mjs";
8
- import { escapeSelector, isVscode } from "../utils/Html.mjs";
9
-
10
- import { ApplicationStyles } from "../appearance/Styles.mjs";
11
- import { FontSize, TextStyle } from "../appearance/Fonts.mjs";
12
- import { arrayToString } from "../utils/Format.mjs";
13
-
14
- import { SampleScoreView } from "./SampleScoreView.mjs";
15
- import { MarkdownDiv } from "../components/MarkdownDiv.mjs";
16
- import { SampleTranscript } from "./SampleTranscript.mjs";
17
- import { ANSIDisplay } from "../components/AnsiDisplay.mjs";
18
- import { FlatSampleError } from "./SampleError.mjs";
19
- import { ToolButton } from "../components/ToolButton.mjs";
20
- import { ApplicationIcons } from "../appearance/Icons.mjs";
21
-
22
- import { ProgressBar } from "../components/ProgressBar.mjs";
23
-
24
- import { printHeadingHtml, printHtml } from "../utils/Print.mjs";
25
- import { ErrorPanel } from "../components/ErrorPanel.mjs";
26
- import { EmptyPanel } from "../components/EmptyPanel.mjs";
27
- import { JSONPanel } from "../components/JsonPanel.mjs";
28
- import { ModelTokenTable } from "../usage/ModelTokenTable.mjs";
29
- import { Card, CardBody, CardHeader } from "../components/Card.mjs";
30
- import {
31
- kSampleErrorTabId,
32
- kSampleJsonTabId,
33
- kSampleMessagesTabId,
34
- kSampleMetdataTabId,
35
- kSampleScoringTabId,
36
- kSampleTranscriptTabId,
37
- } from "../constants.mjs";
38
-
39
- /**
40
- * Inline Sample Display
41
- *
42
- * @param {Object} props - The parameters for the component.
43
- * @param {string} props.id - The task id
44
- * @param {string} props.sampleStatus - the sample status
45
- * @param {Error} [props.sampleError] - sample error
46
- * @param {import("../types/log").EvalSample} [props.sample] - the sample
47
- * @param {import("../samples/SamplesDescriptor.mjs").SamplesDescriptor} props.sampleDescriptor - the sample descriptor
48
- * @param {string} props.selectedTab - The selected tab
49
- * @param {(tab: string) => void} props.setSelectedTab - function to set the selected tab
50
- * @param {import("htm/preact").MutableRef<HTMLElement>} props.scrollRef - The scrollable element whic contains this display
51
- * @returns {import("preact").JSX.Element} The TranscriptView component.
52
- */
53
- export const InlineSampleDisplay = ({
54
- id,
55
- sample,
56
- sampleStatus,
57
- sampleError,
58
- sampleDescriptor,
59
- selectedTab,
60
- setSelectedTab,
61
- scrollRef,
62
- }) => {
63
- return html`<div style=${{ flexDirection: "row", width: "100%" }}>
64
- <${ProgressBar}
65
- animating=${sampleStatus === "loading"}
66
- containerStyle=${{
67
- background: "var(--bs-body-bg)",
68
- }}
69
- />
70
- <div style=${{ margin: "1em 1em 1em 1em" }}>
71
- ${sampleError
72
- ? html`<${ErrorPanel}
73
- title="Unable to load sample"
74
- error=${sampleError}
75
- />`
76
- : html` <${SampleDisplay}
77
- id=${id}
78
- sample=${sample}
79
- sampleDescriptor=${sampleDescriptor}
80
- selectedTab=${selectedTab}
81
- setSelectedTab=${setSelectedTab}
82
- scrollRef=${scrollRef}
83
- />`}
84
- </div>
85
- </div>`;
86
- };
87
-
88
- /**
89
- * Component to display a sample with relevant context and visibility control.
90
- *
91
- * @param {Object} props - The properties passed to the component.
92
- * @param {string} props.id - The unique identifier for the sample.
93
- * @param {import("../types/log").EvalSample} [props.sample] - the sample
94
- * @param {import("../samples/SamplesDescriptor.mjs").SamplesDescriptor} props.sampleDescriptor - the sample descriptor
95
- * @param {string} props.selectedTab - The selected tab
96
- * @param {(tab: string) => void} props.setSelectedTab - function to set the selected tab
97
- * @param {import("htm/preact").MutableRef<HTMLElement>} props.scrollRef - The scrollable parent element
98
- * @returns {import("preact").JSX.Element} The TranscriptView component.
99
- */
100
- export const SampleDisplay = ({
101
- id,
102
- sample,
103
- sampleDescriptor,
104
- selectedTab,
105
- setSelectedTab,
106
- scrollRef,
107
- }) => {
108
- // Tab ids
109
- const baseId = `sample-dialog`;
110
-
111
- if (!sample) {
112
- // Placeholder
113
- return html`<${EmptyPanel} />`;
114
- }
115
-
116
- // Tab selection
117
- const onSelectedTab = (e) => {
118
- const id = e.currentTarget.id;
119
- setSelectedTab(id);
120
- return false;
121
- };
122
-
123
- // The core tabs
124
- const tabs = [
125
- html`
126
- <${TabPanel} id=${kSampleMessagesTabId} classes="sample-tab" title="Messages" onSelected=${onSelectedTab} selected=${
127
- selectedTab === kSampleMessagesTabId
128
- } scrollable=${false} style=${{ width: "100%" }}>
129
- <${ChatViewVirtualList}
130
- key=${`${baseId}-chat-${id}`}
131
- id=${`${baseId}-chat-${id}`}
132
- messages=${sample.messages}
133
- style=${{ marginLeft: ".8em", marginTop: "1em" }}
134
- indented=${true}
135
- scrollRef=${scrollRef}
136
- />
137
- </${TabPanel}>`,
138
- ];
139
-
140
- if (sample.events && sample.events.length > 0) {
141
- tabs.unshift(html`
142
- <${TabPanel} id=${kSampleTranscriptTabId} classes="sample-tab" title="Transcript" onSelected=${onSelectedTab} selected=${
143
- selectedTab === kSampleTranscriptTabId || selectedTab === undefined
144
- } scrollable=${false}>
145
- <${SampleTranscript} key=${`${baseId}-transcript-display-${id}`} id=${`${baseId}-transcript-display-${id}`} evalEvents=${sample.events} scrollRef=${scrollRef}/>
146
- </${TabPanel}>`);
147
- }
148
-
149
- const scorerNames = Object.keys(sample.scores);
150
- if (scorerNames.length === 1) {
151
- tabs.push(html`
152
- <${TabPanel} id=${kSampleScoringTabId} classes="sample-tab" title="Scoring" onSelected=${onSelectedTab} selected=${
153
- selectedTab === kSampleScoringTabId
154
- }>
155
- <${SampleScoreView}
156
- sample=${sample}
157
- sampleDescriptor=${sampleDescriptor}
158
- scorer=${Object.keys(sample.scores)[0]}
159
- />
160
- </${TabPanel}>`);
161
- } else {
162
- for (const scorer of Object.keys(sample.scores)) {
163
- const tabId = `score-${scorer}`;
164
- tabs.push(html`
165
- <${TabPanel} id="${tabId}" classes="sample-tab" title="${scorer}" onSelected=${onSelectedTab} selected=${
166
- selectedTab === tabId
167
- }>
168
- <${SampleScoreView}
169
- sample=${sample}
170
- sampleDescriptor=${sampleDescriptor}
171
- scorer=${scorer}
172
- />
173
- </${TabPanel}>`);
174
- }
175
- }
176
-
177
- const sampleMetadatas = metadataViewsForSample(`${baseId}-${id}`, sample);
178
- if (sampleMetadatas.length > 0) {
179
- tabs.push(
180
- html`
181
- <${TabPanel}
182
- id=${kSampleMetdataTabId}
183
- classes="sample-tab"
184
- title="Metadata"
185
- onSelected=${onSelectedTab}
186
- selected=${selectedTab === kSampleMetdataTabId}>
187
- <div style=${{ display: "flex", flexWrap: "wrap", alignItems: "flex-start", gap: "1em", paddingLeft: "0", marginTop: "0.5em" }}>
188
- ${sampleMetadatas}
189
- </div>
190
- </${TabPanel}>`,
191
- );
192
- }
193
-
194
- if (sample.error) {
195
- tabs.push(
196
- html`
197
- <${TabPanel}
198
- id=${kSampleErrorTabId}
199
- classes="sample-tab"
200
- title="Error"
201
- onSelected=${onSelectedTab}
202
- selected=${selectedTab === kSampleErrorTabId}>
203
- <div style=${{ paddingLeft: "0.8em", marginTop: "0.4em" }}>
204
- <${ANSIDisplay} output=${sample.error.traceback_ansi} style=${{ fontSize: FontSize.small, margin: "1em 0" }}/>
205
- </div>
206
- </${TabPanel}>`,
207
- );
208
- }
209
-
210
- if (sample.messages.length < 100) {
211
- tabs.push(html`<${TabPanel}
212
- id=${kSampleJsonTabId}
213
- classes="sample-tab"
214
- title="JSON"
215
- onSelected=${onSelectedTab}
216
- selected=${selectedTab === kSampleJsonTabId}>
217
- <div style=${{ paddingLeft: "0.8em", marginTop: "0.4em" }}>
218
- <${JSONPanel} data=${sample} simple=${true}/>
219
- </div>
220
- </${TabPanel}>`);
221
- }
222
-
223
- const tabsetId = `task-sample-details-tab-${id}`;
224
- const targetId = `${tabsetId}-content`;
225
- const printSample = () => {
226
- // The active tab
227
- const targetTabEl = document.querySelector(
228
- `#${escapeSelector(targetId)} .sample-tab.tab-pane.show.active`,
229
- );
230
- if (targetTabEl) {
231
- // The target element
232
- const targetEl = targetTabEl.firstElementChild;
233
- if (targetEl) {
234
- // Get the sample heading to include
235
- const headingId = `sample-heading-${id}`;
236
- const headingEl = document.getElementById(headingId);
237
-
238
- // Print the document
239
- const headingHtml = printHeadingHtml();
240
- const css = `
241
- html { font-size: 9pt }
242
- /* Allow content to break anywhere without any forced page breaks */
243
- * {
244
- break-inside: auto; /* Let elements break anywhere */
245
- page-break-inside: auto; /* Legacy support */
246
- break-before: auto;
247
- page-break-before: auto;
248
- break-after: auto;
249
- page-break-after: auto;
250
- }
251
- /* Specifically disable all page breaks for divs */
252
- div {
253
- break-inside: auto;
254
- page-break-inside: auto;
255
- }
256
- body > .transcript-step {
257
- break-inside: avoid;
258
- }
259
- body{
260
- -webkit-print-color-adjust:exact !important;
261
- print-color-adjust:exact !important;
262
- }
263
- /* Allow preformatted text and code blocks to break across pages */
264
- pre, code {
265
- white-space: pre-wrap; /* Wrap long lines instead of keeping them on one line */
266
- overflow-wrap: break-word; /* Ensure long words are broken to fit within the page */
267
- break-inside: auto; /* Allow page breaks inside the element */
268
- page-break-inside: auto; /* Older equivalent */
269
- }
270
-
271
- /* Additional control for long lines within code/preformatted blocks */
272
- pre {
273
- word-wrap: break-word; /* Break long words if needed */
274
- }
275
-
276
- `;
277
- printHtml(
278
- [headingHtml, headingEl.outerHTML, targetEl.innerHTML].join("\n"),
279
- css,
280
- );
281
- }
282
- }
283
- };
284
-
285
- const tools = [];
286
- if (!isVscode()) {
287
- tools.push(
288
- html`<${ToolButton}
289
- name=${html`Print`}
290
- icon="${ApplicationIcons.copy}"
291
- onclick="${printSample}"
292
- />`,
293
- );
294
- }
295
-
296
- return html`<${SampleSummary}
297
- id=${id}
298
- sample=${sample}
299
- sampleDescriptor=${sampleDescriptor}/>
300
-
301
- <${TabSet} id=${tabsetId} styles=${{
302
- tabs: {
303
- fontSize: FontSize.base,
304
- },
305
- tabBody: { paddingBottom: "1em" },
306
- }}
307
- tools=${tools}>
308
- ${tabs}
309
- </${TabSet}>`;
310
- };
311
-
312
- const metadataViewsForSample = (id, sample) => {
313
- const sampleMetadatas = [];
314
- if (sample.model_usage && Object.keys(sample.model_usage).length > 0) {
315
- sampleMetadatas.push(html`
316
- <${Card}>
317
- <${CardHeader} label="Usage"/>
318
- <${CardBody}>
319
- <${ModelTokenTable} model_usage=${sample.model_usage} style=${{ marginTop: 0 }}/>
320
- </${CardBody}>
321
- </${Card}>`);
322
- }
323
-
324
- if (Object.keys(sample?.metadata).length > 0) {
325
- sampleMetadatas.push(
326
- html`
327
- <${Card}>
328
- <${CardHeader} label="Metadata"/>
329
- <${CardBody}>
330
- <${MetaDataView}
331
- id="task-sample-metadata-${id}"
332
- classes="tab-pane"
333
- entries="${sample?.metadata}"
334
- style=${{ marginTop: "0" }}
335
- />
336
- </${CardBody}>
337
- </${Card}>`,
338
- );
339
- }
340
-
341
- if (Object.keys(sample?.store).length > 0) {
342
- sampleMetadatas.push(
343
- html`
344
- <${Card}>
345
- <${CardHeader} label="Store"/>
346
- <${CardBody}>
347
- <${MetaDataView}
348
- id="task-sample-store-${id}"
349
- classes="tab-pane"
350
- entries="${sample?.store}"
351
- style=${{ marginTop: "0" }}
352
- />
353
- </${CardBody}>
354
- </${Card}>`,
355
- );
356
- }
357
-
358
- return sampleMetadatas;
359
- };
360
-
361
- /**
362
- * Component to display a sample with relevant context and visibility control.
363
- *
364
- * @param {Object} props - The properties passed to the component.
365
- * @param {string} props.parent_id - The id of the parent com
366
- * @param {import("../types/log").EvalSample} [props.sample] - the sample
367
- * @param {Object} [props.style] - Inline styles for the table element.
368
- * @param {import("../samples/SamplesDescriptor.mjs").SamplesDescriptor} props.sampleDescriptor - the sample descriptor
369
- * @returns {import("preact").JSX.Element} The TranscriptView component.
370
- */
371
- const SampleSummary = ({ parent_id, sample, style, sampleDescriptor }) => {
372
- const input =
373
- sampleDescriptor?.messageShape.normalized.input > 0
374
- ? Math.max(0.15, sampleDescriptor.messageShape.normalized.input)
375
- : 0;
376
- const target =
377
- sampleDescriptor?.messageShape.normalized.target > 0
378
- ? Math.max(0.15, sampleDescriptor.messageShape.normalized.target)
379
- : 0;
380
- const answer =
381
- sampleDescriptor?.messageShape.normalized.answer > 0
382
- ? Math.max(0.15, sampleDescriptor.messageShape.normalized.answer)
383
- : 0;
384
- const limitSize =
385
- sampleDescriptor?.messageShape.normalized.limit > 0
386
- ? Math.max(0.15, sampleDescriptor.messageShape.normalized.limit)
387
- : 0;
388
- const idSize = Math.max(
389
- 2,
390
- Math.min(10, sampleDescriptor?.messageShape.raw.id),
391
- );
392
-
393
- const scoreInput = inputString(sample.input);
394
- if (sample.choices && sample.choices.length > 0) {
395
- scoreInput.push("");
396
- scoreInput.push(
397
- ...sample.choices.map((choice, index) => {
398
- return `${String.fromCharCode(65 + index)}) ${choice}`;
399
- }),
400
- );
401
- }
402
-
403
- // The columns for the sample
404
- const columns = [];
405
- columns.push({
406
- label: "Id",
407
- value: sample.id,
408
- size: `${idSize}em`,
409
- });
410
-
411
- columns.push({
412
- label: "Input",
413
- value: scoreInput,
414
- size: `${input}fr`,
415
- clamp: true,
416
- });
417
-
418
- if (sample.target) {
419
- columns.push({
420
- label: "Target",
421
- value: html`<${MarkdownDiv}
422
- markdown=${arrayToString(arrayToString(sample?.target || "none"))}
423
- style=${{ paddingLeft: "0" }}
424
- class="no-last-para-padding"
425
- />`,
426
- size: `${target}fr`,
427
- clamp: true,
428
- });
429
- }
430
-
431
- const fullAnswer =
432
- sample && sampleDescriptor
433
- ? sampleDescriptor.selectedScorerDescriptor(sample).answer()
434
- : undefined;
435
- if (fullAnswer) {
436
- columns.push({
437
- label: "Answer",
438
- value: sample
439
- ? html`<${MarkdownDiv}
440
- markdown=${fullAnswer}
441
- style=${{ paddingLeft: "0" }}
442
- class="no-last-para-padding"
443
- />`
444
- : "",
445
- size: `${answer}fr`,
446
- clamp: true,
447
- });
448
- }
449
-
450
- if (sample.limit && limitSize > 0) {
451
- columns.push({
452
- label: "Limit",
453
- value: sample.limit.type,
454
- size: `${limitSize}fr`,
455
- center: true,
456
- });
457
- }
458
-
459
- columns.push({
460
- label: "Score",
461
- value: sample.error
462
- ? html`<${FlatSampleError}
463
- message=${sample.error.message}
464
- style=${{ marginTop: "0.4rem" }}
465
- />`
466
- : // TODO: Cleanup once the PR lands which makes sample / sample summary share common interface
467
- // @ts-ignore
468
- sampleDescriptor?.selectedScore(sample).render(),
469
- size: "minmax(2em, auto)",
470
- center: true,
471
- });
472
-
473
- return html`
474
- <div
475
- id=${`sample-heading-${parent_id}`}
476
- style=${{
477
- display: "grid",
478
- gridTemplateColumns: `${columns
479
- .map((col) => {
480
- return col.size;
481
- })
482
- .join(" ")}`,
483
- gridColumnGap: "0.5em",
484
- fontSize: FontSize.base,
485
- borderBottom: "solid var(--bs-border-color) 1px",
486
- marginBottom: "1em",
487
- padding: "0em 1em 1em 1em",
488
- ...style,
489
- }}
490
- >
491
- ${columns.map((col) => {
492
- const style = {
493
- ...TextStyle.label,
494
- ...TextStyle.secondary,
495
- fontSize: FontSize.base,
496
- };
497
- if (col.center) {
498
- style["display"] = "flex";
499
- style["justifyContent"] = "center";
500
- }
501
- return html`<div style=${{ ...style }}>${col.label}</div>`;
502
- })}
503
- ${columns.map((col) => {
504
- const style = {
505
- ...(col.clamp ? ApplicationStyles.threeLineClamp : {}),
506
- };
507
- if (col.center) {
508
- style.display = "flex";
509
- style.justifyContent = "center";
510
- }
511
- style.wordWrap = "anywhere";
512
- return html`<div style=${{ ...style }}>${col.value}</div>`;
513
- })}
514
- </div>
515
- `;
516
- };
@@ -1,99 +0,0 @@
1
- //@ts-check
2
- import { html } from "htm/preact";
3
-
4
- import { FontSize } from "../appearance/Fonts.mjs";
5
- import { ApplicationIcons } from "../appearance/Icons.mjs";
6
- import { ApplicationStyles } from "../appearance/Styles.mjs";
7
-
8
- /**
9
- * Component to display a styled error message.
10
- *
11
- * @param {Object} props - The component properties.
12
- * @param {string} [props.message] - The error message
13
- * @param {string} [props.align="center"] - The alignment for the error message. Defaults to "center".
14
- * @param {Object} [props.style] - Styles to add for this component
15
- * @returns {import("preact").JSX.Element} The error component.
16
- */
17
- export const SampleError = ({ message, align, style }) => {
18
- align = align || "center";
19
-
20
- return html`<div
21
- style=${{
22
- color: "var(--bs-danger)",
23
- display: "grid",
24
- gridTemplateColumns: "1fr",
25
- alignContent: align,
26
- justifyItems: "center",
27
- ...style,
28
- }}
29
- >
30
- <i
31
- class=${ApplicationIcons.error}
32
- style=${{
33
- fontSize: FontSize.small,
34
- lineHeight: FontSize.small,
35
- height: FontSize.small,
36
- }}
37
- />
38
- <div style=${{ maxWidth: "300px", ...ApplicationStyles.lineClamp(2) }}>
39
- ${errorType(message)}
40
- </div>
41
- </div>`;
42
- };
43
-
44
- /**
45
- * Component to display a styled error message.
46
- *
47
- * @param {Object} props - The component properties.
48
- * @param {string} [props.message] - The message to display
49
- * @param {Object} [props.style] - Styles to add for this component
50
- * @returns {import("preact").JSX.Element} The error component.
51
- */
52
- export const FlatSampleError = ({ message, style }) => {
53
- return html`<div
54
- style=${{
55
- color: "var(--bs-danger)",
56
- display: "grid",
57
- gridTemplateColumns: "max-content max-content",
58
- columnGap: "0.2em",
59
- ...style,
60
- }}
61
- >
62
- <i
63
- class=${ApplicationIcons.error}
64
- style=${{
65
- fontSize: FontSize.base,
66
- lineHeight: FontSize.base,
67
- height: FontSize.base,
68
- }}
69
- />
70
- <div
71
- style=${{
72
- fontSize: FontSize.base,
73
- lineHeight: FontSize.base,
74
- height: FontSize.base,
75
- }}
76
- >
77
- ${errorType(message)}
78
- </div>
79
- </div>`;
80
- };
81
-
82
- /**
83
- * Extracts the error type from a given message.
84
- * If the message contains parentheses, it returns the substring before the first parenthesis.
85
- * Otherwise, it returns "Error".
86
- *
87
- * @param {string | undefined} message - The error message from which to extract the type.
88
- * @returns {string} The extracted error type or "Error" if not found.
89
- */
90
- const errorType = (message) => {
91
- if (!message) {
92
- return "Error";
93
- }
94
-
95
- if (message.includes("(")) {
96
- return message.split("(")[0];
97
- }
98
- return "Error";
99
- };