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
@@ -0,0 +1,68 @@
1
+ .sidebar {
2
+ position: fixed;
3
+ left: 0;
4
+ top: 0;
5
+ width: var(--sidebar-width);
6
+ height: 100%;
7
+ background-color: #fff;
8
+ border-right: 1px solid var(--bs-light-border-subtle);
9
+ display: flex;
10
+ flex-direction: column;
11
+ z-index: 9999; /* Sit above main content */
12
+ transition: transform 0.3s ease-in-out;
13
+ }
14
+
15
+ .sidebarClosed {
16
+ transform: translateX(-100%);
17
+ }
18
+
19
+ .sidebarOpen {
20
+ transform: translateX(0);
21
+ }
22
+
23
+ .header {
24
+ display: grid;
25
+ grid-template-columns: minmax(0, 1fr) auto;
26
+ column-gap: 0.2rem;
27
+ align-items: center;
28
+ opacity: 0.7;
29
+ position: sticky;
30
+ top: 0;
31
+ width: var(--sidebar-width);
32
+ border-bottom: 1px solid var(--bs-light-border-subtle);
33
+ padding: 0.5rem 0 0.5rem 1rem;
34
+ height: 3.6em;
35
+ background-color: #fff;
36
+ z-index: 10;
37
+ }
38
+
39
+ .toggle {
40
+ padding: 0.1rem;
41
+ align-self: end;
42
+ width: 40px;
43
+ flex: 0 0 auto;
44
+ }
45
+
46
+ .progress {
47
+ z-index: 3;
48
+ }
49
+
50
+ .list {
51
+ flex-grow: 1;
52
+ overflow-y: auto;
53
+ }
54
+
55
+ .backdrop {
56
+ position: fixed;
57
+ inset: 0; /* top: 0; left: 0; right: 0; bottom: 0; */
58
+ background-color: rgba(0, 0, 0, 0.5);
59
+ z-index: 9998;
60
+ }
61
+
62
+ .active {
63
+ background-color: var(--bs-secondary-bg-subtle);
64
+ }
65
+
66
+ .item {
67
+ cursor: pointer;
68
+ }
@@ -0,0 +1,85 @@
1
+ import clsx from "clsx";
2
+ import { Fragment } from "react/jsx-runtime";
3
+ import { EvalLogHeader, LogFiles } from "../../api/types";
4
+ import { ApplicationIcons } from "../../appearance/icons";
5
+ import { ProgressBar } from "../../components/ProgressBar";
6
+ import { LogDirectoryTitleView } from "./LogDirectoryTitleView";
7
+ import styles from "./Sidebar.module.css";
8
+ import { SidebarLogEntry } from "./SidebarLogEntry";
9
+
10
+ interface SidebarProps {
11
+ logs: LogFiles;
12
+ logHeaders: Record<string, EvalLogHeader>;
13
+ offcanvas: boolean;
14
+ setOffcanvas: (offcanvas: boolean) => void;
15
+ loading: boolean;
16
+ selectedIndex: number;
17
+ onSelectedIndexChanged: (index: number) => void;
18
+ }
19
+
20
+ export const Sidebar: React.FC<SidebarProps> = ({
21
+ logs,
22
+ logHeaders,
23
+ offcanvas,
24
+ setOffcanvas,
25
+ loading,
26
+ selectedIndex,
27
+ onSelectedIndexChanged,
28
+ }) => {
29
+ const handleToggle = () => {
30
+ setOffcanvas(!offcanvas);
31
+ };
32
+
33
+ return (
34
+ <Fragment>
35
+ {/* Optional backdrop for small screens, appears only when offcanvas is open */}
36
+ {offcanvas && <div className={styles.backdrop} onClick={handleToggle} />}
37
+
38
+ <div
39
+ className={clsx(
40
+ styles.sidebar,
41
+ offcanvas ? styles.sidebarOpen : styles.sidebarClosed,
42
+ )}
43
+ >
44
+ <div className={styles.header}>
45
+ <LogDirectoryTitleView log_dir={logs.log_dir} offcanvas={offcanvas} />
46
+ <button
47
+ onClick={handleToggle}
48
+ className={clsx("btn", styles.toggle)}
49
+ type="button"
50
+ aria-label="Close sidebar"
51
+ >
52
+ <i className={ApplicationIcons.close}></i>
53
+ </button>
54
+ </div>
55
+
56
+ <div className={styles.progress}>
57
+ <ProgressBar animating={loading} />
58
+ </div>
59
+
60
+ <ul className={clsx("list-group", styles.list)}>
61
+ {logs.files.map((file, index) => {
62
+ const logHeader = logHeaders[file.name];
63
+ return (
64
+ <li
65
+ key={file.name}
66
+ className={clsx(
67
+ "list-group-item",
68
+ "list-group-item-action",
69
+ styles.item,
70
+ selectedIndex === index ? styles.active : undefined,
71
+ )}
72
+ onClick={() => onSelectedIndexChanged(index)}
73
+ >
74
+ <SidebarLogEntry
75
+ logHeader={logHeader}
76
+ task={file.task || "unknown task"}
77
+ />
78
+ </li>
79
+ );
80
+ })}
81
+ </ul>
82
+ </div>
83
+ </Fragment>
84
+ );
85
+ };
@@ -0,0 +1,29 @@
1
+ .entry {
2
+ display: flex;
3
+ flex-direction: row;
4
+ justify-content: space-between;
5
+ }
6
+
7
+ .title {
8
+ overflow: hidden;
9
+ min-width: 33%;
10
+ }
11
+
12
+ .task {
13
+ white-space: nowrap;
14
+ overflow: hidden;
15
+ text-overflow: ellipsis;
16
+ }
17
+
18
+ .params {
19
+ margin-top: 1em;
20
+ }
21
+
22
+ .scores {
23
+ width: 100%;
24
+ display: grid;
25
+ grid-template-columns: minmax(auto, 1fr) minmax(1fr, 1fr);
26
+ column-gap: 1rem;
27
+ justify-content: space-between;
28
+ margin-top: 0em;
29
+ }
@@ -0,0 +1,95 @@
1
+ import clsx from "clsx";
2
+ import { Fragment } from "react";
3
+ import { EvalLogHeader } from "../../api/types";
4
+ import { EvalStatus } from "./EvalStatus";
5
+ import styles from "./SidebarLogEntry.module.css";
6
+
7
+ interface SidebarLogEntryProps {
8
+ logHeader?: EvalLogHeader;
9
+ task: string;
10
+ }
11
+
12
+ export const SidebarLogEntry: React.FC<SidebarLogEntryProps> = ({
13
+ logHeader,
14
+ task,
15
+ }) => {
16
+ const hyperparameters: Record<string, unknown> = {
17
+ ...(logHeader?.plan?.config || {}),
18
+ ...(logHeader?.eval?.task_args || {}),
19
+ };
20
+
21
+ const model = logHeader?.eval?.model;
22
+ const datasetName = logHeader?.eval?.dataset.name;
23
+
24
+ const uniqScorers = new Set();
25
+ logHeader?.results?.scores?.forEach((scorer) => {
26
+ uniqScorers.add(scorer.name);
27
+ });
28
+ const scorerNames = Array.from(uniqScorers).join(",");
29
+
30
+ const scorerLabel =
31
+ Object.keys(logHeader?.results?.scores || {}).length === 1
32
+ ? "scorer"
33
+ : "scorers";
34
+
35
+ const completed = logHeader?.stats?.completed_at;
36
+ const time = completed ? new Date(completed) : undefined;
37
+ const timeStr = time
38
+ ? `${time.toDateString()}
39
+ ${time.toLocaleTimeString([], {
40
+ hour: "2-digit",
41
+ minute: "2-digit",
42
+ })}`
43
+ : "";
44
+
45
+ return (
46
+ <Fragment>
47
+ <div className={styles.entry}>
48
+ <div className={styles.title}>
49
+ <div className={clsx(styles.task, "text-size-title-secondary")}>
50
+ {logHeader?.eval?.task || task}
51
+ </div>
52
+ <small className={clsx("mb-1", "text-size-small")}>{timeStr}</small>
53
+
54
+ {model ? (
55
+ <div>
56
+ <small className={clsx("mb-1", "text-size-small")}>{model}</small>
57
+ </div>
58
+ ) : (
59
+ ""
60
+ )}
61
+ </div>
62
+ <EvalStatus logHeader={logHeader} />
63
+ </div>
64
+ <div className={clsx(styles.params, "three-line-clamp")}>
65
+ <small className={"mb-1"}>
66
+ {hyperparameters
67
+ ? Object.keys(hyperparameters)
68
+ .map((key) => {
69
+ const val = hyperparameters[key];
70
+ if (Array.isArray(val) || typeof val === "object") {
71
+ return `${key}: ${JSON.stringify(val)}`;
72
+ } else {
73
+ return `${key}: ${val}`;
74
+ }
75
+ })
76
+ .join(", ")
77
+ : ""}
78
+ </small>
79
+ </div>
80
+ {(logHeader?.eval?.dataset || logHeader?.results?.scores) &&
81
+ logHeader?.status === "success" ? (
82
+ <div
83
+ className={clsx("text-truncate", "text-size-small", styles.scores)}
84
+ >
85
+ <div>dataset: {datasetName || "(samples)"}</div>
86
+ <div className={clsx("text-truncate", styles.scoreInfo)}>
87
+ {scorerLabel}: {scorerNames || "(none)"}
88
+ </div>
89
+ </div>
90
+ ) : (
91
+ ""
92
+ )}
93
+ </Fragment>
94
+ );
95
+ };
@@ -0,0 +1,23 @@
1
+ .container {
2
+ display: flex;
3
+ flex-direction: row;
4
+ flex-wrap: wrap;
5
+ justify-content: flex-end;
6
+ }
7
+
8
+ .metric {
9
+ display: flex;
10
+ flex-direction: column;
11
+ align-items: flex-end;
12
+ margin-left: 1em;
13
+ margin-bottom: 0.4em;
14
+ margin-top: 0.5rem;
15
+ }
16
+
17
+ .metricName {
18
+ margin-bottom: -0.3em;
19
+ }
20
+
21
+ .metricReducer {
22
+ margin-bottom: -0.2rem;
23
+ }
@@ -0,0 +1,43 @@
1
+ import clsx from "clsx";
2
+ import { EvalScore } from "../../types/log";
3
+ import { formatPrettyDecimal } from "../../utils/format";
4
+
5
+ import { metricDisplayName } from "../utils";
6
+ import styles from "./SidebarScoreView.module.css";
7
+ interface SidebarScoreProps {
8
+ scorer: EvalScore;
9
+ }
10
+
11
+ export const SidebarScoreView: React.FC<SidebarScoreProps> = ({ scorer }) => {
12
+ const showReducer = !!scorer.reducer;
13
+ return (
14
+ <div className={styles.container}>
15
+ {Object.keys(scorer.metrics).map((metric) => {
16
+ return (
17
+ <div className={styles.metric} key={metric}>
18
+ <div
19
+ className={clsx(
20
+ "text-style-secondary",
21
+ "text-style-label",
22
+ "text-size-small",
23
+ styles.metricName,
24
+ )}
25
+ >
26
+ {metricDisplayName(scorer.metrics[metric])}
27
+ </div>
28
+ {showReducer ? (
29
+ <div className={clsx("text-size-small", styles.metricReducer)}>
30
+ {scorer.reducer || "default"}
31
+ </div>
32
+ ) : (
33
+ ""
34
+ )}
35
+ <div className={"text-size-title-secondary"}>
36
+ {formatPrettyDecimal(scorer.metrics[metric].value)}
37
+ </div>
38
+ </div>
39
+ );
40
+ })}
41
+ </div>
42
+ );
43
+ };
@@ -0,0 +1,35 @@
1
+ .container {
2
+ display: flex;
3
+ flex-direction: row;
4
+ flex-wrap: wrap;
5
+ justify-content: flex-end;
6
+ row-gap: 1em;
7
+ }
8
+
9
+ .scoreWrapper {
10
+ display: flex;
11
+ flex-direction: column;
12
+ align-items: center;
13
+ margin-left: 1em;
14
+ }
15
+
16
+ .metricName {
17
+ width: 100%;
18
+ font-weight: 300;
19
+ border-bottom: solid var(--bs-border-color) 1px;
20
+ }
21
+
22
+ .metricReducer {
23
+ width: 100%;
24
+ font-weight: 300;
25
+ }
26
+
27
+ .metricValues {
28
+ display: grid;
29
+ grid-template-columns: max-content max-content;
30
+ grid-gap: 0 0.3rem;
31
+ }
32
+
33
+ .metricValue {
34
+ font-weight: 600;
35
+ }
@@ -0,0 +1,63 @@
1
+ import clsx from "clsx";
2
+ import { Fragment } from "react";
3
+ import { Scores } from "../../types/log";
4
+ import { formatPrettyDecimal } from "../../utils/format";
5
+ import { metricDisplayName } from "../utils";
6
+ import styles from "./SidebarScoresView.module.css";
7
+
8
+ interface SidebarScoresProps {
9
+ scores: Scores;
10
+ }
11
+
12
+ export const SidebarScoresView: React.FC<SidebarScoresProps> = ({ scores }) => {
13
+ const showReducer = scores.findIndex((score) => !!score.reducer) !== -1;
14
+ return (
15
+ <div className={styles.container}>
16
+ {scores.map((score, idx) => {
17
+ const name = score.name;
18
+ const reducer = score.reducer;
19
+ return (
20
+ <div className={styles.scoreWrapper} key={`scorer-${name}-${idx}`}>
21
+ <div
22
+ className={clsx(
23
+ "text-style-secondary",
24
+ "text-style-label",
25
+ "text-size-small",
26
+ styles.metricName,
27
+ )}
28
+ >
29
+ {name}
30
+ </div>
31
+ {showReducer ? (
32
+ <div
33
+ className={clsx(
34
+ "text-size-small",
35
+ "text-style-label",
36
+ "text-style-secondary",
37
+ styles.metricReducer,
38
+ )}
39
+ >
40
+ {reducer || "default"}
41
+ </div>
42
+ ) : (
43
+ ""
44
+ )}
45
+ <div className={clsx("text-size-small", styles.metricValues)}>
46
+ {Object.keys(score.metrics).map((key) => {
47
+ const metric = score.metrics[key];
48
+ return (
49
+ <Fragment key={key}>
50
+ <div className={clsx()}>{metricDisplayName(metric)}</div>
51
+ <div className={styles.metricValue}>
52
+ {formatPrettyDecimal(metric.value)}
53
+ </div>
54
+ </Fragment>
55
+ );
56
+ })}
57
+ </div>
58
+ </div>
59
+ );
60
+ })}
61
+ </div>
62
+ );
63
+ };
@@ -0,0 +1,70 @@
1
+ import { useEffect, useState } from "react";
2
+ import { SampleSummary } from "../../api/types";
3
+ import { MessageBand } from "../../components/MessageBand";
4
+ import { PlanCard } from "../../plan/PlanCard";
5
+ import {
6
+ EvalError,
7
+ EvalPlan,
8
+ EvalResults,
9
+ EvalSpec,
10
+ EvalStats,
11
+ } from "../../types/log";
12
+ import { UsageCard } from "../../usage/UsageCard";
13
+ import { TaskErrorCard } from "../error/TaskErrorPanel";
14
+
15
+ interface PlanTabProps {
16
+ evalSpec?: EvalSpec;
17
+ evalPlan?: EvalPlan;
18
+ evalStats?: EvalStats;
19
+ evalResults?: EvalResults;
20
+ samples?: SampleSummary[];
21
+ evalStatus?: "started" | "error" | "cancelled" | "success";
22
+ evalError?: EvalError;
23
+ }
24
+
25
+ export const InfoTab: React.FC<PlanTabProps> = ({
26
+ evalSpec,
27
+ evalPlan,
28
+ evalResults,
29
+ evalStats,
30
+ samples,
31
+ evalStatus,
32
+ evalError,
33
+ }) => {
34
+ const [hidden, setHidden] = useState(false);
35
+ useEffect(() => {
36
+ setHidden(false);
37
+ }, [evalSpec, evalPlan, evalResults, evalStats, samples]);
38
+
39
+ const showWarning =
40
+ (!samples || samples.length === 0) &&
41
+ evalStatus === "success" &&
42
+ evalSpec?.dataset.samples &&
43
+ evalSpec.dataset.samples > 0;
44
+
45
+ return (
46
+ <div style={{ width: "100%" }}>
47
+ {showWarning ? (
48
+ <MessageBand
49
+ message="Unable to display samples (this evaluation log may be too large)."
50
+ hidden={hidden}
51
+ setHidden={setHidden}
52
+ type="warning"
53
+ />
54
+ ) : (
55
+ ""
56
+ )}
57
+ <div style={{ padding: "0.5em 1em 0 1em", width: "100%" }}>
58
+ <PlanCard
59
+ evalSpec={evalSpec}
60
+ evalPlan={evalPlan}
61
+ scores={evalResults?.scores}
62
+ />
63
+ {evalStatus !== "started" ? <UsageCard stats={evalStats} /> : undefined}
64
+ {evalStatus === "error" && evalError ? (
65
+ <TaskErrorCard error={evalError} />
66
+ ) : undefined}
67
+ </div>
68
+ </div>
69
+ );
70
+ };
@@ -0,0 +1,5 @@
1
+ .jsonTab {
2
+ padding: 0.5rem;
3
+ font-size: var(--inspect-font-size-small);
4
+ width: 100%;
5
+ }
@@ -0,0 +1,46 @@
1
+ import { filename } from "../../utils/path";
2
+
3
+ import { Capabilities } from "../../api/types";
4
+ import { DownloadPanel } from "../../components/DownloadPanel";
5
+ import { JSONPanel } from "../../components/JsonPanel";
6
+ import styles from "./JsonTab.module.css";
7
+
8
+ const kJsonMaxSize = 10000000;
9
+
10
+ interface JsonTabProps {
11
+ logFile?: string;
12
+ capabilities: Capabilities;
13
+ selected: boolean;
14
+ json: string;
15
+ }
16
+
17
+ /**
18
+ * Renders JSON tab
19
+ */
20
+ export const JsonTab: React.FC<JsonTabProps> = ({
21
+ logFile,
22
+ capabilities,
23
+ json,
24
+ }) => {
25
+ if (logFile && json.length > kJsonMaxSize && capabilities.downloadFiles) {
26
+ // This JSON file is so large we can't really productively render it
27
+ // we should instead just provide a DL link
28
+ const file = `${filename(logFile)}.json`;
29
+ return (
30
+ <div className={styles.jsonTab}>
31
+ <DownloadPanel
32
+ message="The JSON for this log file is too large to render."
33
+ buttonLabel="Download JSON File"
34
+ fileName={file}
35
+ fileContents={json}
36
+ />
37
+ </div>
38
+ );
39
+ } else {
40
+ return (
41
+ <div className={styles.jsonTab}>
42
+ <JSONPanel id="task-json-contents" json={json} simple={true} />
43
+ </div>
44
+ );
45
+ }
46
+ };