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
@@ -1,418 +0,0 @@
1
- import { html } from "htm/preact";
2
-
3
- import { ApplicationIcons } from "./../appearance/Icons.mjs";
4
- import { FontSize, TextStyle } from "../appearance/Fonts.mjs";
5
- import { formatPrettyDecimal } from "../utils/Format.mjs";
6
- import { ProgressBar } from "../components/ProgressBar.mjs";
7
- import { ApplicationStyles } from "../appearance/Styles.mjs";
8
-
9
- export const Sidebar = ({
10
- offcanvas,
11
- logs,
12
- loading,
13
- logHeaders,
14
- selectedIndex,
15
- onSelectedIndexChanged,
16
- }) => {
17
- const btnOffCanClass = offcanvas ? "" : " d-md-none";
18
- const sidebarOffCanClass = offcanvas ? " offcanvas" : " offcanvas-md";
19
-
20
- return html`
21
- <div
22
- class="sidebar border-end offcanvas-start${sidebarOffCanClass}"
23
- id="sidebarOffCanvas"
24
- style=${{ display: "flex", flexDirection: "column", height: "100%" }}
25
- >
26
- <div
27
- style=${{
28
- display: "grid",
29
- gridTemplateColumns: "minmax(0, 1fr) auto",
30
- columnGap: "0.2rem",
31
- alignItems: "center",
32
- paddingLeft: "0.5rem",
33
- opacity: "0.7",
34
- position: "fixed",
35
- width: "var(--sidebar-width)",
36
- zIndex: 10,
37
- borderBottom: "solid var(--bs-light-border-subtle) 1px",
38
- paddingBottom: "0.5rem",
39
- paddingTop: "0.5rem",
40
- height: "3.6em",
41
- }}
42
- >
43
- <${LogDirectoryTitle} log_dir=${logs.log_dir} offcanvas=${offcanvas} />
44
- <button
45
- id="sidebarToggle"
46
- class="btn d-inline${btnOffCanClass}"
47
- type="button"
48
- data-bs-toggle="offcanvas"
49
- data-bs-target="#sidebarOffCanvas"
50
- aria-controls="sidebarOffCanvas"
51
- style=${{
52
- padding: ".1rem",
53
- alignSelf: "end",
54
- width: "40px",
55
- flex: "0 0 content",
56
- }}
57
- >
58
- <i class=${ApplicationIcons.close}></i>
59
- </button>
60
- </div>
61
- <div style=${{ marginTop: "3.6em", zIndex: 3 }}>
62
- <${ProgressBar} animating=${loading} style=${{ marginTop: "-2px" }} />
63
- </div>
64
- <ul
65
- class="list-group"
66
- style=${{ flexGrow: 1, overflowY: "auto", marginTop: "-3px" }}
67
- >
68
- ${logs.files.map((file, index) => {
69
- const active = index === selectedIndex ? " active" : "";
70
- const logHeader = logHeaders[file.name];
71
- const hyperparameters = logHeader
72
- ? {
73
- ...logHeader.plan?.config,
74
- ...logHeader.eval?.task_args,
75
- }
76
- : undefined;
77
-
78
- const model = logHeader?.eval?.model;
79
- const dataset = logHeader?.eval?.dataset;
80
-
81
- const uniqScorers = new Set();
82
- logHeader?.results?.scores?.forEach((scorer) => {
83
- uniqScorers.add(scorer.name);
84
- });
85
- const scorer = Array.from(uniqScorers).join(",");
86
-
87
- const scorerLabel =
88
- Object.keys(logHeader?.results?.scores || {}).length === 1
89
- ? "scorer"
90
- : "scorers";
91
-
92
- const completed = logHeader?.stats?.completed_at;
93
- const time = completed ? new Date(completed) : undefined;
94
- const timeStr = time
95
- ? `${time.toDateString()}
96
- ${time.toLocaleTimeString([], {
97
- hour: "2-digit",
98
- minute: "2-digit",
99
- })}`
100
- : "";
101
-
102
- return html`
103
- <li
104
- class="list-group-item list-group-item-action${active}"
105
- onclick=${() => onSelectedIndexChanged(index)}
106
- >
107
- <div
108
- style=${{
109
- display: "flex",
110
- flexDirection: "row",
111
- justifyContent: "space-between",
112
- }}
113
- >
114
- <div style=${{ overflow: "hidden" }}>
115
- <div
116
- style=${{
117
- fontSize: FontSize["title-secondary"],
118
- whiteSpace: "nowrap",
119
- overflow: "hidden",
120
- textOverflow: "ellipsis",
121
- }}
122
- >
123
- ${logHeader?.eval?.task || file.task}
124
- </div>
125
- <small class="mb-1" style=${{ fontSize: FontSize.small }}>
126
- ${timeStr}
127
- </small>
128
-
129
- ${model
130
- ? html` <div>
131
- <small
132
- class="mb-1"
133
- style=${{ fontSize: FontSize.small }}
134
- >${model}</small
135
- >
136
- </div>`
137
- : ""}
138
- </div>
139
- <${EvalStatus} logHeader=${logHeader} />
140
- </div>
141
- <div
142
- style=${{
143
- marginTop: "1em",
144
- ...ApplicationStyles.threeLineClamp,
145
- }}
146
- >
147
- <small class="mb-1">
148
- ${hyperparameters
149
- ? Object.keys(hyperparameters)
150
- .map((key) => {
151
- const val = hyperparameters[key];
152
- if (Array.isArray(val) || typeof val === "object") {
153
- return `${key}: ${JSON.stringify(val)}`;
154
- } else {
155
- return `${key}: ${val}`;
156
- }
157
- })
158
- .join(", ")
159
- : ""}
160
- </small>
161
- </div>
162
- ${(dataset || scorer) && logHeader?.status === "success"
163
- ? html`<div
164
- style=${{
165
- display: "flex",
166
- justifyContent: "space-between",
167
- marginTop: "0em",
168
- fontSize: FontSize.small,
169
- }}
170
- >
171
- <span>dataset: ${dataset.name || "(samples)"}</span
172
- ><span>${scorerLabel}: ${scorer}</span>
173
- </div>`
174
- : ""}
175
- </li>
176
- `;
177
- })}
178
- </ul>
179
- </div>
180
- `;
181
- };
182
-
183
- const prettyDir = (path) => {
184
- try {
185
- // Try to create a new URL object
186
- let url = new URL(path);
187
-
188
- if (url.protocol === "file:") {
189
- return url.pathname;
190
- } else {
191
- return path;
192
- }
193
- } catch {
194
- return path;
195
- }
196
- };
197
-
198
- const EvalStatus = ({ logHeader }) => {
199
- switch (logHeader?.status) {
200
- case "error":
201
- return html`<${StatusError} message="Error" />`;
202
-
203
- case "cancelled":
204
- return html`<${StatusCancelled} message="Cancelled" />`;
205
-
206
- case "started":
207
- return html`<${StatusRunning} message="Running" />`;
208
-
209
- default:
210
- if (logHeader?.results?.scores && logHeader.results?.scores.length > 0) {
211
- if (logHeader.results.scores.length === 1) {
212
- return html`<${SidebarScore}
213
- scorer=${logHeader.results.scores[0]}
214
- />`;
215
- } else {
216
- return html`<${SidebarScores} scores=${logHeader.results.scores} />`;
217
- }
218
- } else {
219
- return "";
220
- }
221
- }
222
- };
223
-
224
- const SidebarScore = ({ scorer }) => {
225
- return html`<div
226
- style=${{
227
- display: "flex",
228
- flexDirection: "row",
229
- flexWrap: "wrap",
230
- justifyContent: "flex-end",
231
- }}
232
- >
233
- ${Object.keys(scorer.metrics).map((metric) => {
234
- return html`
235
- <div
236
- style=${{
237
- display: "flex",
238
- flexDirection: "column",
239
- alignItems: "flex-end",
240
- marginLeft: "1em",
241
- marginBottom: "0.4em",
242
- marginTop: "0.5rem",
243
- }}
244
- >
245
- <div
246
- style=${{
247
- marginBottom: "-0.3em",
248
- fontSize: FontSize.small,
249
- ...TextStyle.label,
250
- ...TextStyle.secondary,
251
- }}
252
- >
253
- ${scorer.metrics[metric].name}
254
- </div>
255
- ${scorer.reducer
256
- ? html`<div
257
- style=${{
258
- fontSize: FontSize.small,
259
- marginBottom: "-0.2rem",
260
- }}
261
- >
262
- ${scorer.reducer}
263
- </div>`
264
- : ""}
265
- <div style=${{ fontSize: FontSize["title-secondary"] }}>
266
- ${formatPrettyDecimal(scorer.metrics[metric].value)}
267
- </div>
268
- </div>
269
- `;
270
- })}
271
- </div>`;
272
- };
273
-
274
- const SidebarScores = ({ scores }) => {
275
- return html`<div
276
- style=${{
277
- display: "flex",
278
- flexDirection: "row",
279
- flexWrap: "wrap",
280
- justifyContent: "flex-end",
281
- rowGap: "1em",
282
- }}
283
- >
284
- ${scores.map((score) => {
285
- const name = score.name;
286
- const reducer = score.reducer;
287
- return html`
288
- <div
289
- style=${{
290
- display: "flex",
291
- flexDirection: "column",
292
- alignItems: "center",
293
- marginLeft: "1em",
294
- }}
295
- >
296
- <div
297
- style=${{
298
- fontSize: FontSize.base,
299
- width: "100%",
300
- fontWeight: 300,
301
- borderBottom: "solid var(--bs-border-color) 1px",
302
- ...TextStyle.label,
303
- ...TextStyle.secondary,
304
- }}
305
- >
306
- ${name}
307
- </div>
308
- ${reducer
309
- ? html` <div
310
- style=${{
311
- fontSize: FontSize.smaller,
312
- width: "100%",
313
- fontWeight: 300,
314
- }}
315
- >
316
- ${reducer}
317
- </div>`
318
- : ""}
319
- <div
320
- style=${{
321
- fontSize: FontSize.smaller,
322
- display: "grid",
323
- gridTemplateColumns: "max-content max-content",
324
- gridGap: "0 0.3rem",
325
- }}
326
- >
327
- ${Object.keys(score.metrics).map((key) => {
328
- const metric = score.metrics[key];
329
- return html` <div
330
- style=${{ ...TextStyle.label, ...TextStyle.secondary }}
331
- >
332
- ${metric.name}
333
- </div>
334
- <div style=${{ fontWeight: "600" }}>
335
- ${formatPrettyDecimal(metric.value)}
336
- </div>`;
337
- })}
338
- </div>
339
- </div>
340
- `;
341
- })}
342
- </div>`;
343
- };
344
-
345
- const StatusCancelled = ({ message }) => {
346
- return html`<div
347
- style=${{
348
- marginTop: "0.2em",
349
- fontSize: FontSize.small,
350
- ...TextStyle.label,
351
- ...TextStyle.secondary,
352
- }}
353
- >
354
- ${message}
355
- </div>`;
356
- };
357
-
358
- const StatusRunning = ({ message }) => {
359
- return html` <div
360
- style=${{
361
- display: "grid",
362
- gridTemplateColumns: "max-content max-content",
363
- columnGap: "0.5em",
364
- marginTop: "0.3em",
365
- fontSize: FontSize.small,
366
- ...TextStyle.secondary,
367
- ...TextStyle.label,
368
- }}
369
- >
370
- <div>${message}</div>
371
- </div>`;
372
- };
373
-
374
- const StatusError = ({ message }) => {
375
- return html`<div
376
- style=${{
377
- color: "var(--bs-danger)",
378
- marginTop: "0.2em",
379
- fontSize: FontSize.small,
380
- ...TextStyle.label,
381
- }}
382
- >
383
- ${message}
384
- </div>`;
385
- };
386
-
387
- const LogDirectoryTitle = ({ log_dir, offcanvas }) => {
388
- if (log_dir) {
389
- const displayDir = prettyDir(log_dir);
390
- return html`<div style=${{ display: "flex", flexDirection: "column" }}>
391
- <span
392
- style=${{
393
- fontSize: FontSize.smaller,
394
- ...TextStyle.label,
395
- ...TextStyle.secondary,
396
- }}
397
- >Log Directory</span
398
- >
399
- <span
400
- title=${displayDir}
401
- style=${{
402
- fontSize: FontSize.base,
403
- overflow: "hidden",
404
- whiteSpace: "nowrap",
405
- textOverflow: "ellipsis",
406
- }}
407
- >${offcanvas ? displayDir : ""}</span
408
- >
409
- </div>`;
410
- } else {
411
- return html`<span
412
- style=${{
413
- fontSize: FontSize.title,
414
- }}
415
- >${offcanvas ? "Log History" : ""}
416
- </span>`;
417
- }
418
- };
@@ -1,72 +0,0 @@
1
- import { html } from "htm/preact";
2
- import { FontSize, TextStyle } from "../appearance/Fonts.mjs";
3
- import { ModelUsagePanel } from "./UsageCard.mjs";
4
-
5
- export const ModelTokenTable = ({ model_usage, style }) => {
6
- return html`
7
- <${TokenTable} style=${style}>
8
- <${TokenHeader}/>
9
- <tbody>
10
- ${Object.keys(model_usage).map((key) => {
11
- return html`<${TokenRow} model=${key} usage=${model_usage[key]} />`;
12
- })}
13
- </tbody>
14
- </${TokenTable}>
15
- `;
16
- };
17
-
18
- const TokenTable = ({ style, children }) => {
19
- return html`<table
20
- class="table table-sm"
21
- style=${{
22
- width: "100%",
23
- fontSize: FontSize.smaller,
24
- marginTop: "0.7rem",
25
- ...style,
26
- }}
27
- >
28
- ${children}
29
- </table>`;
30
- };
31
-
32
- const thStyle = {
33
- padding: 0,
34
- fontWeight: 300,
35
- fontSize: FontSize.small,
36
- ...TextStyle.label,
37
- ...TextStyle.secondary,
38
- };
39
-
40
- const TokenHeader = () => {
41
- return html`<thead>
42
- <tr>
43
- <td></td>
44
- <td
45
- colspan="3"
46
- align="center"
47
- class="card-subheading"
48
- style=${{
49
- paddingBottom: "0.7rem",
50
- fontSize: FontSize.small,
51
- ...TextStyle.label,
52
- ...TextStyle.secondary,
53
- }}
54
- >
55
- Tokens
56
- </td>
57
- </tr>
58
- <tr>
59
- <th style=${thStyle}>Model</th>
60
- <th style=${thStyle}>Usage</th>
61
- </tr>
62
- </thead>`;
63
- };
64
-
65
- const TokenRow = ({ model, usage }) => {
66
- return html`<tr>
67
- <td>${model}</td>
68
- <td>
69
- <${ModelUsagePanel} usage=${usage} />
70
- </td>
71
- </tr>`;
72
- };
@@ -1,159 +0,0 @@
1
- //@ts-check
2
- import { html } from "htm/preact";
3
-
4
- import { ApplicationIcons } from "../appearance/Icons.mjs";
5
- import { FontSize, TextStyle } from "../appearance/Fonts.mjs";
6
- import { formatDuration, formatNumber } from "../utils/Format.mjs";
7
- import { Card, CardHeader, CardBody } from "../components/Card.mjs";
8
- import { MetaDataView } from "../components/MetaDataView.mjs";
9
- import { ModelTokenTable } from "./ModelTokenTable.mjs";
10
-
11
- const kUsageCardBodyId = "usage-card-body";
12
-
13
- /**
14
- * Renders the UsageCard component.
15
- *
16
- * @param {Object} props - The parameters for the component.
17
- * @param {import("../types/log").EvalStats} props.stats - The identifier for this view
18
- * @returns {import("preact").JSX.Element | string} The UsageCard component.
19
- */
20
- export const UsageCard = ({ stats }) => {
21
- if (!stats) {
22
- return "";
23
- }
24
-
25
- const totalDuration = formatDuration(
26
- new Date(stats.started_at),
27
- new Date(stats.completed_at),
28
- );
29
- const usageMetadataStyle = {
30
- fontSize: FontSize.smaller,
31
- };
32
-
33
- return html`
34
-
35
- <${Card}>
36
- <${CardHeader} icon=${ApplicationIcons.usage} label="Usage"/>
37
- <${CardBody} id=${kUsageCardBodyId} style=${{
38
- paddingTop: "0",
39
- paddingBottom: "0",
40
- borderTop: "solid var(--bs-border-color) 1px",
41
- }}>
42
- <div style=${{
43
- paddingTop: "0",
44
- paddingBottom: "1em",
45
- marginLeft: "0",
46
- display: "flex",
47
- }}>
48
-
49
- <div style=${{ flex: "1 1 40%", marginRight: "1em" }}>
50
- <div style=${{ marginTop: "1em", fontSize: FontSize.smaller, ...TextStyle.label, ...TextStyle.secondary }}>Duration</div>
51
- <${MetaDataView}
52
- entries="${{
53
- ["Start"]: new Date(stats.started_at).toLocaleString(),
54
- ["End"]: new Date(stats.completed_at).toLocaleString(),
55
- ["Duration"]: totalDuration,
56
- }}"
57
- tableOptions="borderless,sm"
58
- style=${usageMetadataStyle}
59
- />
60
- </div>
61
-
62
- <div style=${{ flex: "1 1 60%" }}>
63
- <${ModelTokenTable} model_usage=${stats.model_usage}/>
64
- </div>
65
- </div>
66
- </${CardBody}>
67
- </${Card}>
68
- `;
69
- };
70
-
71
- /**
72
- * Renders the ModelUsagePanel component.
73
- *
74
- * @param {Object} props - The parameters for the component.
75
- * @param {import("../types/log").ModelUsage1} props.usage - The identifier for this view
76
- * @returns {import("preact").JSX.Element | string} The ModelUsagePanel component.
77
- */
78
- export const ModelUsagePanel = ({ usage }) => {
79
- if (!usage) {
80
- return "";
81
- }
82
-
83
- const rows = [
84
- {
85
- label: "input",
86
- value: usage.input_tokens,
87
- secondary: false,
88
- },
89
- ];
90
-
91
- if (usage.input_tokens_cache_read) {
92
- rows.push({
93
- label: "cache_read",
94
- value: usage.input_tokens_cache_read,
95
- secondary: true,
96
- });
97
- }
98
-
99
- if (usage.input_tokens_cache_write) {
100
- rows.push({
101
- label: "cache_write",
102
- value: usage.input_tokens_cache_write,
103
- secondary: true,
104
- });
105
- }
106
-
107
- rows.push({
108
- label: "Output",
109
- value: usage.output_tokens,
110
- secondary: false,
111
- bordered: true,
112
- });
113
-
114
- rows.push({
115
- label: "---",
116
- value: undefined,
117
- secondary: false,
118
- });
119
-
120
- rows.push({
121
- label: "Total",
122
- value: usage.total_tokens,
123
- secondary: false,
124
- });
125
-
126
- return html` <div
127
- style=${{
128
- display: "grid",
129
- gridTemplateColumns: "0 auto auto",
130
- columnGap: "0.5em",
131
- fontSize: FontSize.small,
132
- }}
133
- >
134
- ${rows.map((row) => {
135
- if (row.label === "---") {
136
- return html`<div
137
- style=${{
138
- gridColumn: "-1/1",
139
- height: "1px",
140
- backgroundColor: "var(--bs-light-border-subtle)",
141
- }}
142
- ></div>`;
143
- } else {
144
- return html`
145
- <div
146
- style=${{
147
- ...TextStyle.label,
148
- ...TextStyle.secondary,
149
- gridColumn: row.secondary ? "2" : "1/3",
150
- }}
151
- >
152
- ${row.label}
153
- </div>
154
- <div style=${{ gridColumn: "3" }}>${formatNumber(row.value)}</div>
155
- `;
156
- }
157
- })}
158
- </div>`;
159
- };