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
@@ -1,427 +0,0 @@
1
- import { html } from "htm/preact";
2
- import { useCallback, useMemo, useState } from "preact/hooks";
3
- import { useEffect, useRef } from "preact/hooks";
4
-
5
- import { ApplicationStyles } from "../appearance/Styles.mjs";
6
- import { FontSize } from "../appearance/Fonts.mjs";
7
- import { TextStyle } from "../appearance/Fonts.mjs";
8
- import { MarkdownDiv } from "../components/MarkdownDiv.mjs";
9
- import { SampleError } from "./SampleError.mjs";
10
-
11
- import { arrayToString, formatNoDecimal } from "../utils/Format.mjs";
12
- import { EmptyPanel } from "../components/EmptyPanel.mjs";
13
- import { VirtualList } from "../components/VirtualList.mjs";
14
- import { MessageBand } from "../components/MessageBand.mjs";
15
- import { inputString } from "../utils/Format.mjs";
16
-
17
- const kSampleHeight = 88;
18
- const kSeparatorHeight = 24;
19
-
20
- /**
21
- * Convert samples to a datastructure which contemplates grouping, etc...
22
- *
23
- * @param {Object} props - The parameters for the component.
24
- * @param {Object} props.listRef - The ref for the list.
25
- * @param {import("./SamplesTab.mjs").ListItem[]} props.items - The samples.
26
- * @param {import("../samples/SamplesDescriptor.mjs").SamplesDescriptor} props.sampleDescriptor - The sample descriptor.
27
- * @param {Object} props.style - The style for the element
28
- * @param {number} props.selectedIndex - The index of the selected sample.
29
- * @param {(index: number) => void} props.setSelectedIndex - The function to set the selected sample index.
30
- * @param {import("../Types.mjs").ScoreLabel} props.selectedScore - The function to get the selected score.
31
- * @param {() => void} props.nextSample - The function to move to the next sample.
32
- * @param {() => void} props.prevSample - The function to move to the previous sample.
33
- * @param {(index: number) => void} props.showSample - The function to show the sample.
34
- * @returns {import("preact").JSX.Element} The SampleList component.
35
- */
36
- export const SampleList = (props) => {
37
- const {
38
- listRef,
39
- items,
40
- sampleDescriptor,
41
- style,
42
- selectedIndex,
43
- setSelectedIndex,
44
- selectedScore,
45
- nextSample,
46
- prevSample,
47
- showSample,
48
- } = props;
49
- // If there are no samples, just display an empty state
50
- if (items.length === 0) {
51
- return html`<${EmptyPanel}>No Samples</${EmptyPanel}>`;
52
- }
53
-
54
- const [hidden, setHidden] = useState(false);
55
- useEffect(() => {
56
- setHidden(false);
57
- }, [items]);
58
-
59
- // Keep a mapping of the indexes to items (skipping separators)
60
- const itemRowMapping = useMemo(() => {
61
- const rowIndexes = [];
62
- items.forEach((item, index) => {
63
- if (item.type === "sample") {
64
- rowIndexes.push(index);
65
- }
66
- });
67
- return rowIndexes;
68
- }, [items]);
69
-
70
- const prevSelectedIndexRef = useRef(null);
71
- useEffect(() => {
72
- const listEl = listRef.current;
73
- if (listEl) {
74
- const actualRowIndex = itemRowMapping[selectedIndex];
75
- const direction =
76
- actualRowIndex > prevSelectedIndexRef.current ? "down" : "up";
77
- listRef.current?.scrollToIndex(actualRowIndex, direction);
78
- prevSelectedIndexRef.current = actualRowIndex;
79
- }
80
- }, [selectedIndex, listRef, itemRowMapping]);
81
-
82
- /** @param {import("./SamplesTab.mjs").ListItem} item */
83
- const renderRow = (item) => {
84
- if (item.type === "sample") {
85
- return html`
86
- <${SampleRow}
87
- id=${item.number}
88
- index=${item.index}
89
- sample=${item.data}
90
- height=${kSampleHeight}
91
- sampleDescriptor=${sampleDescriptor}
92
- selected=${selectedIndex === item.index}
93
- setSelected=${setSelectedIndex}
94
- selectedScore=${selectedScore}
95
- showSample=${showSample}
96
- />
97
- `;
98
- } else if (item.type === "separator") {
99
- return html`
100
- <${SeparatorRow}
101
- id=${`sample-group${item.number}`}
102
- title=${item.data}
103
- height=${kSeparatorHeight}
104
- />
105
- `;
106
- } else {
107
- return "";
108
- }
109
- };
110
-
111
- const onkeydown = useCallback(
112
- (e) => {
113
- switch (e.key) {
114
- case "ArrowUp":
115
- prevSample();
116
- e.preventDefault();
117
- e.stopPropagation();
118
- return false;
119
- case "ArrowDown":
120
- nextSample();
121
- e.preventDefault();
122
- e.stopPropagation();
123
- return false;
124
- case "Enter":
125
- showSample(selectedIndex);
126
- e.preventDefault();
127
- e.stopPropagation();
128
- return false;
129
- }
130
- },
131
- [selectedIndex],
132
- );
133
-
134
- const listStyle = { ...style, flex: "1", overflowY: "auto", outline: "none" };
135
- const { input, limit, answer, target } = gridColumns(sampleDescriptor);
136
-
137
- const headerRow = html`<div
138
- style=${{
139
- display: "grid",
140
- ...gridColumnStyles(sampleDescriptor),
141
- fontSize: FontSize.smaller,
142
- ...TextStyle.label,
143
- ...TextStyle.secondary,
144
- paddingBottom: "0.3em",
145
- paddingTop: "0.3em",
146
- borderBottom: "solid var(--bs-light-border-subtle) 1px",
147
- }}
148
- >
149
- <div>Id</div>
150
- <div>${input !== "0" ? "Input" : ""}</div>
151
- <div>${target !== "0" ? "Target" : ""}</div>
152
- <div>${answer !== "0" ? "Answer" : ""}</div>
153
- <div>${limit !== "0" ? "Limit" : ""}</div>
154
- <div style=${{ justifySelf: "center" }}>Score</div>
155
- </div>`;
156
-
157
- const sampleCount = items?.reduce((prev, current) => {
158
- if (current.type === "sample") {
159
- return prev + 1;
160
- } else {
161
- return prev;
162
- }
163
- }, 0);
164
- const footerRow = html` <div
165
- style=${{
166
- borderTop: "solid var(--bs-light-border-subtle) 1px",
167
- background: "var(--bs-light-bg-subtle)",
168
- fontSize: FontSize.smaller,
169
- display: "grid",
170
- gridTemplateColumns: "max-content",
171
- justifyContent: "end",
172
- alignContent: "end",
173
- padding: "0.2em 1em",
174
- }}
175
- >
176
- <div>${sampleCount} Samples</div>
177
- </div>`;
178
-
179
- // Count any sample errors and display a bad alerting the user
180
- // to any errors
181
- const errorCount = items?.reduce((previous, item) => {
182
- // @ts-expect-error
183
- if (item.data.error) {
184
- return previous + 1;
185
- } else {
186
- return previous;
187
- }
188
- }, 0);
189
-
190
- // Count limits
191
- const limitCount = items?.reduce((previous, item) => {
192
- // @ts-expect-error
193
- if (item.data.limit) {
194
- return previous + 1;
195
- } else {
196
- return previous;
197
- }
198
- }, 0);
199
-
200
- const percentError = (errorCount / sampleCount) * 100;
201
- const percentLimit = (limitCount / sampleCount) * 100;
202
- const warningMessage =
203
- errorCount > 0
204
- ? `INFO: ${errorCount} of ${sampleCount} samples (${formatNoDecimal(percentError)}%) had errors and were not scored.`
205
- : limitCount
206
- ? `INFO: ${limitCount} of ${sampleCount} samples (${formatNoDecimal(percentLimit)}%) completed due to exceeding a limit.`
207
- : undefined;
208
-
209
- const warningRow = warningMessage
210
- ? html`<${MessageBand}
211
- message=${warningMessage}
212
- hidden=${hidden}
213
- setHidden=${setHidden}
214
- type="info"
215
- />`
216
- : "";
217
-
218
- return html` <div
219
- style=${{ display: "flex", flexDirection: "column", width: "100%" }}
220
- >
221
- ${warningRow} ${headerRow}
222
- <${VirtualList}
223
- ref=${listRef}
224
- data=${items}
225
- tabIndex="0"
226
- renderRow=${renderRow}
227
- onkeydown=${onkeydown}
228
- style=${listStyle}
229
- />
230
- ${footerRow}
231
- </div>`;
232
- };
233
-
234
- const SeparatorRow = ({ id, title, height }) => {
235
- return html`<div
236
- id=${id}
237
- style=${{
238
- padding: ".25em 1em .25em 1em",
239
- textTransform: "uppercase",
240
- ...TextStyle.secondary,
241
- fontSize: FontSize.smaller,
242
- fontWeight: 600,
243
- borderBottom: "solid 1px var(--bs-border-color)",
244
- height: `${height}px`,
245
- }}
246
- >
247
- <div>${title}</div>
248
- </div>`;
249
- };
250
-
251
- /**
252
- * @param {Object} props - The parameters for the component.
253
- * @param {string} props.id - The unique identifier for the sample.
254
- * @param {number} props.index - The index of the sample.
255
- * @param {import("../api/Types.ts").SampleSummary} props.sample - The sample.
256
- * @param {import("../samples/SamplesDescriptor.mjs").SamplesDescriptor} props.sampleDescriptor - The sample descriptor.
257
- * @param {number} props.height - The height of the sample row.
258
- * @param {boolean} props.selected - Whether the sample is selected.
259
- * @param {(index: number) => void} props.showSample - The function to show the sample.
260
- * @returns {import("preact").JSX.Element} The SampleRow component.
261
- */
262
- const SampleRow = ({
263
- id,
264
- index,
265
- sample,
266
- sampleDescriptor,
267
- height,
268
- selected,
269
- showSample,
270
- }) => {
271
- const selectedStyle = selected
272
- ? {
273
- boxShadow: "inset 0 0 0px 2px var(--bs-focus-ring-color)",
274
- }
275
- : {};
276
-
277
- const cellStyle = {
278
- paddingLeft: "0em",
279
- paddingRight: "0em",
280
- };
281
-
282
- return html`
283
- <div
284
- id=${`sample-${id}`}
285
- onclick=${() => {
286
- showSample(index);
287
- }}
288
- style=${{
289
- height: `${height}px`,
290
- display: "grid",
291
- ...gridColumnStyles(sampleDescriptor),
292
- paddingTop: "1em",
293
- paddingBottom: "1em",
294
- gridTemplateRows: `${height - 28}px`,
295
- fontSize: FontSize.base,
296
- borderBottom: "solid var(--bs-border-color) 1px",
297
- cursor: "pointer",
298
- ...selectedStyle,
299
- overflowY: "hidden",
300
- }}
301
- >
302
- <div
303
- class="sample-id"
304
- style=${{ ...cellStyle, ...ApplicationStyles.threeLineClamp }}
305
- >
306
- ${sample.id}
307
- </div>
308
- <div
309
- class="sample-input"
310
- style=${{
311
- ...ApplicationStyles.threeLineClamp,
312
- wordWrap: "anywhere",
313
- ...cellStyle,
314
- }}
315
- >
316
- ${inputString(sample.input).join(" ")}
317
- </div>
318
- <div
319
- class="sample-target"
320
- style=${{
321
- ...ApplicationStyles.threeLineClamp,
322
- ...cellStyle,
323
- }}
324
- >
325
- <${MarkdownDiv}
326
- markdown=${arrayToString(sample?.target)}
327
- style=${{ paddingLeft: "0" }}
328
- class="no-last-para-padding"
329
- />
330
- </div>
331
- <div
332
- class="sample-answer"
333
- style=${{
334
- ...ApplicationStyles.threeLineClamp,
335
- ...cellStyle,
336
- }}
337
- >
338
- ${sample
339
- ? html`
340
- <${MarkdownDiv}
341
- markdown=${sampleDescriptor
342
- ?.selectedScorerDescriptor(sample)
343
- .answer()}
344
- style=${{ paddingLeft: "0" }}
345
- class="no-last-para-padding"
346
- />
347
- `
348
- : ""}
349
- </div>
350
- <div
351
- class="sample-limit"
352
- style=${{
353
- fontSize: FontSize.small,
354
- ...ApplicationStyles.threeLineClamp,
355
- ...cellStyle,
356
- }}
357
- >
358
- ${sample.limit}
359
- </div>
360
-
361
- <div
362
- style=${{
363
- fontSize: FontSize.small,
364
- ...cellStyle,
365
- display: "flex",
366
- justifySelf: "center",
367
- }}
368
- >
369
- ${sample.error
370
- ? html`<${SampleError} message=${sample.error} />`
371
- : sampleDescriptor?.selectedScore(sample).render()}
372
- </div>
373
- </div>
374
- `;
375
- };
376
-
377
- const gridColumnStyles = (sampleDescriptor) => {
378
- const { input, target, answer, limit, id, score } =
379
- gridColumns(sampleDescriptor);
380
- return {
381
- gridGap: "10px",
382
- gridTemplateColumns: `${id} ${input} ${target} ${answer} ${limit} ${score}`,
383
- paddingLeft: "1rem",
384
- paddingRight: "1rem",
385
- };
386
- };
387
-
388
- const gridColumns = (sampleDescriptor) => {
389
- const input =
390
- sampleDescriptor?.messageShape.normalized.input > 0
391
- ? Math.max(0.15, sampleDescriptor.messageShape.normalized.input)
392
- : 0;
393
- const target =
394
- sampleDescriptor?.messageShape.normalized.target > 0
395
- ? Math.max(0.15, sampleDescriptor.messageShape.normalized.target)
396
- : 0;
397
- const answer =
398
- sampleDescriptor?.messageShape.normalized.answer > 0
399
- ? Math.max(0.15, sampleDescriptor.messageShape.normalized.answer)
400
- : 0;
401
- const limit =
402
- sampleDescriptor?.messageShape.normalized.limit > 0
403
- ? Math.max(0.15, sampleDescriptor.messageShape.normalized.limit)
404
- : 0;
405
- const id = Math.max(2, Math.min(10, sampleDescriptor?.messageShape.raw.id));
406
- const score = Math.max(
407
- 3,
408
- Math.min(10, sampleDescriptor?.messageShape.raw.score),
409
- );
410
-
411
- const frSize = (val) => {
412
- if (val === 0) {
413
- return "0";
414
- } else {
415
- return `${val}fr`;
416
- }
417
- };
418
-
419
- return {
420
- input: frSize(input),
421
- target: frSize(target),
422
- answer: frSize(answer),
423
- limit: frSize(limit),
424
- id: `${id}rem`,
425
- score: `${score}rem`,
426
- };
427
- };
@@ -1,172 +0,0 @@
1
- import { html } from "htm/preact";
2
- import { arrayToString, inputString } from "../utils/Format.mjs";
3
- import { MarkdownDiv } from "../components/MarkdownDiv.mjs";
4
- import { SampleScores } from "./SampleScores.mjs";
5
- import { FontSize, TextStyle } from "../appearance/Fonts.mjs";
6
- import { MetaDataGrid } from "../components/MetaDataGrid.mjs";
7
- import { Card, CardHeader, CardBody } from "../components/Card.mjs";
8
-
9
- const labelStyle = {
10
- paddingRight: "2em",
11
- paddingLeft: "0",
12
- paddingBottom: "0",
13
- ...TextStyle.label,
14
- ...TextStyle.secondary,
15
- };
16
-
17
- /**
18
- * @param {Object} props - The component props.
19
- * @param {import("../types/log").EvalSample} props.sample - The sample.
20
- * @param {import("../samples/SamplesDescriptor.mjs").SamplesDescriptor} props.sampleDescriptor - The sample descriptor.
21
- * @param {Object} props.style - The style for the element.
22
- * @param {string} props.scorer - The scorer.
23
- * @returns {import("preact").JSX.Element} The SampleScoreView component.
24
- */
25
- export const SampleScoreView = ({
26
- sample,
27
- sampleDescriptor,
28
- style,
29
- scorer,
30
- }) => {
31
- if (!sampleDescriptor) {
32
- return html``;
33
- }
34
-
35
- const scoreInput = inputString(sample.input);
36
- if (sample.choices && sample.choices.length > 0) {
37
- scoreInput.push("");
38
- scoreInput.push(
39
- ...sample.choices.map((choice, index) => {
40
- return `${String.fromCharCode(65 + index)}) ${choice}`;
41
- }),
42
- );
43
- }
44
-
45
- const scorerDescriptor = sampleDescriptor.evalDescriptor.scorerDescriptor(
46
- sample,
47
- { scorer, name: scorer },
48
- );
49
- const explanation = scorerDescriptor.explanation() || "(No Explanation)";
50
- const answer = scorerDescriptor.answer();
51
- const metadata = scorerDescriptor.metadata();
52
-
53
- return html`
54
- <div
55
- class="container-fluid"
56
- style=${{
57
- marginTop: "0.5em",
58
- paddingLeft: "0",
59
- fontSize: FontSize.base,
60
- ...style,
61
- }}
62
- >
63
- <${Card}>
64
- <${CardHeader} label="Score"/>
65
- <${CardBody}>
66
- <div>
67
- <div style=${{ ...labelStyle }}>Input</div>
68
- <div>
69
- <${MarkdownDiv}
70
- markdown=${scoreInput.join("\n")}
71
- style=${{ wordBreak: "break-all" }}
72
- />
73
- </div>
74
- </div>
75
-
76
- <table
77
- class="table"
78
- style=${{ width: "100%", marginBottom: "1em" }}
79
- >
80
- <thead style=${{ borderBottomColor: "#00000000" }}>
81
- <tr>
82
- <th style=${{ ...labelStyle, fontWeight: "400" }}>Target</th>
83
- <th
84
- style=${{ ...labelStyle, paddingBottom: "0", fontWeight: "400" }}
85
- >
86
- Answer
87
- </th>
88
- <th
89
- style=${{
90
- ...labelStyle,
91
- paddingLeft: "2em",
92
- paddingBottom: "0",
93
- fontWeight: "400",
94
- }}
95
- >
96
- Score
97
- </th>
98
- </tr>
99
- </thead>
100
- <tbody style=${{ borderBottomColor: "#00000000" }}>
101
- <tr>
102
- <td
103
- style=${{
104
- paddingRight: "2em",
105
- paddingLeft: "0",
106
- paddingTop: "0",
107
- }}
108
- >
109
- <${MarkdownDiv}
110
- markdown=${arrayToString(
111
- arrayToString(sample?.target || "none"),
112
- )}
113
- style=${{ paddingLeft: "0" }}
114
- class="no-last-para-padding"
115
- />
116
- </td>
117
- <td style=${{ paddingTop: "0", paddingLeft: "0" }}>
118
- <${MarkdownDiv}
119
- class="no-last-para-padding"
120
- markdown=${answer}
121
- style=${{ paddingLeft: "0" }}
122
- />
123
- </td>
124
- <td style=${{ paddingLeft: "2em", paddingTop: "0" }}>
125
- <${SampleScores}
126
- sample=${sample}
127
- sampleDescriptor=${sampleDescriptor}
128
- scorer=${scorer}
129
- />
130
- </td>
131
- </tr>
132
- </tbody>
133
- </table>
134
- </${CardBody}>
135
- </${Card}>
136
-
137
- ${
138
- explanation && explanation !== answer
139
- ? html`
140
- <${Card}>
141
- <${CardHeader} label="Explanation"/>
142
- <${CardBody}>
143
- <${MarkdownDiv}
144
- markdown=${arrayToString(explanation)}
145
- style=${{ paddingLeft: "0" }}
146
- class="no-last-para-padding"
147
- />
148
-
149
- </${CardBody}>
150
- </${Card}>`
151
- : ""
152
- }
153
-
154
- ${
155
- metadata && Object.keys(metadata).length > 0
156
- ? html`
157
- <${Card}>
158
- <${CardHeader} label="Metadata"/>
159
- <${CardBody}>
160
- <${MetaDataGrid}
161
- id="task-sample-score-metadata"
162
- classes="tab-pane"
163
- entries="${metadata}"
164
- style=${{ marginTop: "0" }}
165
- />
166
- </${CardBody}>
167
- </${Card}>`
168
- : ""
169
- }
170
- </div>
171
- `;
172
- };
@@ -1,34 +0,0 @@
1
- import { html } from "htm/preact";
2
-
3
- /**
4
- * @param {Object} props
5
- * @param {import("../api/Types.ts").SampleSummary} props.sample
6
- * @param {import("../samples/SamplesDescriptor.mjs").SamplesDescriptor} props.sampleDescriptor
7
- * @param {string} props.scorer
8
- * @returns {import("preact").JSX.Element}
9
- */
10
- export const SampleScores = ({ sample, sampleDescriptor, scorer }) => {
11
- const scores = scorer
12
- ? sampleDescriptor.evalDescriptor
13
- .scorerDescriptor(sample, { scorer, name: scorer })
14
- .scores()
15
- : sampleDescriptor.selectedScorerDescriptor(sample).scores();
16
-
17
- if (scores.length === 1) {
18
- return scores[0].rendered();
19
- } else {
20
- const rows = scores.map((score) => {
21
- return html` <div style=${{ opacity: "0.7" }}>${score.name}</div>
22
- <div>${score.rendered()}</div>`;
23
- });
24
- return html`<div
25
- style=${{
26
- display: "grid",
27
- gridTemplateColumns: "max-content max-content",
28
- columnGap: "1em",
29
- }}
30
- >
31
- ${rows}
32
- </div>`;
33
- }
34
- };
@@ -1,20 +0,0 @@
1
- // @ts-check
2
- import { html } from "htm/preact";
3
- import { TranscriptVirtualList } from "./transcript/TranscriptView.mjs";
4
-
5
- /**
6
- * Renders the SampleTranscript component.
7
- *
8
- * @param {Object} props - The parameters for the component.
9
- * @param {string} props.id - The id of this component
10
- * @param {import("../types/log").Events} props.evalEvents - The transcript to display.
11
- * @param {import("htm/preact").MutableRef<HTMLElement>} props.scrollRef - The scrollable parent element
12
- * @returns {import("preact").JSX.Element} The SampleTranscript component.
13
- */
14
- export const SampleTranscript = ({ id, evalEvents, scrollRef }) => {
15
- return html`<${TranscriptVirtualList}
16
- id=${id}
17
- events=${evalEvents}
18
- scrollRef=${scrollRef}
19
- />`;
20
- };