inspect-ai 0.3.62__py3-none-any.whl → 0.3.63__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 (415) hide show
  1. inspect_ai/_cli/main.py +1 -1
  2. inspect_ai/_cli/trace.py +8 -0
  3. inspect_ai/_display/core/active.py +2 -3
  4. inspect_ai/_eval/eval.py +4 -4
  5. inspect_ai/_eval/evalset.py +6 -6
  6. inspect_ai/_eval/task/run.py +3 -0
  7. inspect_ai/_util/hash.py +1 -1
  8. inspect_ai/_view/www/.vscode/extensions.json +3 -0
  9. inspect_ai/_view/www/.vscode/settings.json +8 -0
  10. inspect_ai/_view/www/App.css +92 -29
  11. inspect_ai/_view/www/dist/assets/index.css +16637 -14676
  12. inspect_ai/_view/www/dist/assets/index.js +58897 -51440
  13. inspect_ai/_view/www/dist/index.html +1 -1
  14. inspect_ai/_view/www/index.html +2 -2
  15. inspect_ai/_view/www/log-schema.json +1 -0
  16. inspect_ai/_view/www/package.json +22 -4
  17. inspect_ai/_view/www/postcss.config.cjs +8 -9
  18. inspect_ai/_view/www/src/{App.mjs → App.tsx} +355 -365
  19. inspect_ai/_view/www/src/AppErrorBoundary.tsx +47 -0
  20. inspect_ai/_view/www/src/api/api-browser.ts +2 -2
  21. inspect_ai/_view/www/src/api/api-http.ts +3 -5
  22. inspect_ai/_view/www/src/api/api-vscode.ts +6 -6
  23. inspect_ai/_view/www/src/api/client-api.ts +4 -4
  24. inspect_ai/_view/www/src/api/index.ts +4 -4
  25. inspect_ai/_view/www/src/api/{Types.ts → types.ts} +25 -9
  26. inspect_ai/_view/www/src/appearance/colors.ts +9 -0
  27. inspect_ai/_view/www/src/appearance/fonts.ts +39 -0
  28. inspect_ai/_view/www/src/appearance/icons.ts +100 -0
  29. inspect_ai/_view/www/src/appearance/{Styles.mjs → styles.ts} +2 -32
  30. inspect_ai/_view/www/src/components/AnsiDisplay.tsx +198 -0
  31. inspect_ai/_view/www/src/components/AsciinemaPlayer.tsx +86 -0
  32. inspect_ai/_view/www/src/components/Card.css +60 -0
  33. inspect_ai/_view/www/src/components/Card.tsx +109 -0
  34. inspect_ai/_view/www/src/components/CopyButton.module.css +11 -0
  35. inspect_ai/_view/www/src/components/CopyButton.tsx +58 -0
  36. inspect_ai/_view/www/src/components/DownloadButton.css +4 -0
  37. inspect_ai/_view/www/src/components/DownloadButton.tsx +25 -0
  38. inspect_ai/_view/www/src/components/DownloadPanel.css +10 -0
  39. inspect_ai/_view/www/src/components/DownloadPanel.tsx +30 -0
  40. inspect_ai/_view/www/src/components/EmptyPanel.css +12 -0
  41. inspect_ai/_view/www/src/components/EmptyPanel.tsx +15 -0
  42. inspect_ai/_view/www/src/components/ErrorPanel.css +37 -0
  43. inspect_ai/_view/www/src/components/ErrorPanel.tsx +39 -0
  44. inspect_ai/_view/www/src/components/ExpandablePanel.css +40 -0
  45. inspect_ai/_view/www/src/components/ExpandablePanel.tsx +115 -0
  46. inspect_ai/_view/www/src/components/FindBand.css +49 -0
  47. inspect_ai/_view/www/src/components/FindBand.tsx +130 -0
  48. inspect_ai/_view/www/src/components/HumanBaselineView.css +41 -0
  49. inspect_ai/_view/www/src/components/HumanBaselineView.tsx +162 -0
  50. inspect_ai/_view/www/src/components/JsonPanel.css +20 -0
  51. inspect_ai/_view/www/src/components/JsonPanel.tsx +82 -0
  52. inspect_ai/_view/www/src/components/LabeledValue.css +20 -0
  53. inspect_ai/_view/www/src/components/LabeledValue.tsx +41 -0
  54. inspect_ai/_view/www/src/components/LargeModal.module.css +54 -0
  55. inspect_ai/_view/www/src/components/LargeModal.tsx +199 -0
  56. inspect_ai/_view/www/src/components/LightboxCarousel.css +95 -0
  57. inspect_ai/_view/www/src/components/LightboxCarousel.tsx +132 -0
  58. inspect_ai/_view/www/src/components/MarkdownDiv.css +3 -0
  59. inspect_ai/_view/www/src/components/MarkdownDiv.tsx +133 -0
  60. inspect_ai/_view/www/src/components/MessageBand.css +43 -0
  61. inspect_ai/_view/www/src/components/MessageBand.tsx +39 -0
  62. inspect_ai/_view/www/src/components/MorePopOver.tsx +67 -0
  63. inspect_ai/_view/www/src/components/NavPills.module.css +18 -0
  64. inspect_ai/_view/www/src/components/NavPills.tsx +99 -0
  65. inspect_ai/_view/www/src/components/ProgressBar.module.css +37 -0
  66. inspect_ai/_view/www/src/components/ProgressBar.tsx +22 -0
  67. inspect_ai/_view/www/src/components/TabSet.module.css +40 -0
  68. inspect_ai/_view/www/src/components/TabSet.tsx +200 -0
  69. inspect_ai/_view/www/src/components/ToolButton.css +3 -0
  70. inspect_ai/_view/www/src/components/ToolButton.tsx +27 -0
  71. inspect_ai/_view/www/src/components/VirtualList.module.css +19 -0
  72. inspect_ai/_view/www/src/components/VirtualList.tsx +292 -0
  73. inspect_ai/_view/www/src/{index.js → index.tsx} +45 -19
  74. inspect_ai/_view/www/src/{log → logfile}/remoteLogFile.ts +3 -7
  75. inspect_ai/_view/www/src/{utils/remoteZipFile.mjs → logfile/remoteZipFile.ts} +86 -80
  76. inspect_ai/_view/www/src/metadata/MetaDataGrid.tsx +83 -0
  77. inspect_ai/_view/www/src/metadata/MetaDataView.module.css +35 -0
  78. inspect_ai/_view/www/src/metadata/MetaDataView.tsx +95 -0
  79. inspect_ai/_view/www/src/metadata/MetadataGrid.module.css +15 -0
  80. inspect_ai/_view/www/src/metadata/RenderedContent.module.css +12 -0
  81. inspect_ai/_view/www/src/{components/RenderedContent/RenderedContent.mjs → metadata/RenderedContent.tsx} +92 -73
  82. inspect_ai/_view/www/src/metadata/types.ts +18 -0
  83. inspect_ai/_view/www/src/plan/DatasetDetailView.module.css +3 -0
  84. inspect_ai/_view/www/src/plan/DatasetDetailView.tsx +37 -0
  85. inspect_ai/_view/www/src/plan/DetailStep.module.css +9 -0
  86. inspect_ai/_view/www/src/plan/DetailStep.tsx +31 -0
  87. inspect_ai/_view/www/src/plan/PlanCard.tsx +28 -0
  88. inspect_ai/_view/www/src/plan/PlanDetailView.module.css +48 -0
  89. inspect_ai/_view/www/src/plan/PlanDetailView.tsx +309 -0
  90. inspect_ai/_view/www/src/plan/ScorerDetailView.module.css +3 -0
  91. inspect_ai/_view/www/src/plan/ScorerDetailView.tsx +30 -0
  92. inspect_ai/_view/www/src/plan/SolverDetailView.module.css +15 -0
  93. inspect_ai/_view/www/src/plan/SolverDetailView.tsx +32 -0
  94. inspect_ai/_view/www/src/samples/InlineSampleDisplay.module.css +8 -0
  95. inspect_ai/_view/www/src/samples/InlineSampleDisplay.tsx +53 -0
  96. inspect_ai/_view/www/src/samples/SampleDialog.tsx +122 -0
  97. inspect_ai/_view/www/src/samples/SampleDisplay.module.css +29 -0
  98. inspect_ai/_view/www/src/samples/SampleDisplay.tsx +326 -0
  99. inspect_ai/_view/www/src/samples/SampleSummaryView.module.css +24 -0
  100. inspect_ai/_view/www/src/samples/SampleSummaryView.tsx +175 -0
  101. inspect_ai/_view/www/src/samples/SamplesTools.tsx +60 -0
  102. inspect_ai/_view/www/src/samples/chat/ChatMessage.module.css +29 -0
  103. inspect_ai/_view/www/src/samples/chat/ChatMessage.tsx +76 -0
  104. inspect_ai/_view/www/src/samples/chat/ChatMessageRenderer.tsx +60 -0
  105. inspect_ai/_view/www/src/samples/chat/ChatMessageRow.module.css +9 -0
  106. inspect_ai/_view/www/src/samples/chat/ChatMessageRow.tsx +57 -0
  107. inspect_ai/_view/www/src/samples/chat/ChatView.tsx +46 -0
  108. inspect_ai/_view/www/src/samples/chat/ChatViewVirtualList.module.css +4 -0
  109. inspect_ai/_view/www/src/samples/chat/ChatViewVirtualList.tsx +58 -0
  110. inspect_ai/_view/www/src/samples/chat/MessageContent.module.css +4 -0
  111. inspect_ai/_view/www/src/samples/chat/MessageContent.tsx +143 -0
  112. inspect_ai/_view/www/src/samples/chat/MessageContents.module.css +3 -0
  113. inspect_ai/_view/www/src/samples/chat/MessageContents.tsx +131 -0
  114. inspect_ai/_view/www/src/samples/chat/messages.ts +112 -0
  115. inspect_ai/_view/www/src/samples/chat/tools/ToolCallView.tsx +145 -0
  116. inspect_ai/_view/www/src/samples/chat/tools/ToolInput.module.css +14 -0
  117. inspect_ai/_view/www/src/samples/chat/tools/ToolInput.tsx +86 -0
  118. inspect_ai/_view/www/src/samples/chat/tools/ToolOutput.module.css +19 -0
  119. inspect_ai/_view/www/src/samples/chat/tools/ToolOutput.tsx +53 -0
  120. inspect_ai/_view/www/src/samples/chat/tools/ToolTitle.module.css +4 -0
  121. inspect_ai/_view/www/src/samples/chat/tools/ToolTitle.tsx +18 -0
  122. inspect_ai/_view/www/src/samples/chat/tools/tool.ts +107 -0
  123. inspect_ai/_view/www/src/samples/descriptor/samplesDescriptor.tsx +363 -0
  124. inspect_ai/_view/www/src/samples/descriptor/score/BooleanScoreDescriptor.module.css +22 -0
  125. inspect_ai/_view/www/src/samples/descriptor/score/BooleanScoreDescriptor.tsx +26 -0
  126. inspect_ai/_view/www/src/samples/descriptor/score/CategoricalScoreDescriptor.tsx +18 -0
  127. inspect_ai/_view/www/src/samples/descriptor/score/NumericScoreDescriptor.tsx +27 -0
  128. inspect_ai/_view/www/src/samples/descriptor/score/ObjectScoreDescriptor.module.css +18 -0
  129. inspect_ai/_view/www/src/samples/descriptor/score/ObjectScoreDescriptor.tsx +71 -0
  130. inspect_ai/_view/www/src/samples/descriptor/score/OtherScoreDescriptor.tsx +20 -0
  131. inspect_ai/_view/www/src/samples/descriptor/score/PassFailScoreDescriptor.module.css +28 -0
  132. inspect_ai/_view/www/src/samples/descriptor/score/PassFailScoreDescriptor.tsx +81 -0
  133. inspect_ai/_view/www/src/samples/descriptor/score/ScoreDescriptor.tsx +99 -0
  134. inspect_ai/_view/www/src/samples/descriptor/types.ts +55 -0
  135. inspect_ai/_view/www/src/samples/error/FlatSampleErrorView.module.css +19 -0
  136. inspect_ai/_view/www/src/samples/error/FlatSampleErrorView.tsx +22 -0
  137. inspect_ai/_view/www/src/samples/error/SampleErrorView.module.css +17 -0
  138. inspect_ai/_view/www/src/samples/error/SampleErrorView.tsx +31 -0
  139. inspect_ai/_view/www/src/samples/error/error.ts +15 -0
  140. inspect_ai/_view/www/src/samples/list/SampleFooter.module.css +9 -0
  141. inspect_ai/_view/www/src/samples/list/SampleFooter.tsx +14 -0
  142. inspect_ai/_view/www/src/samples/list/SampleHeader.module.css +13 -0
  143. inspect_ai/_view/www/src/samples/list/SampleHeader.tsx +36 -0
  144. inspect_ai/_view/www/src/samples/list/SampleList.module.css +11 -0
  145. inspect_ai/_view/www/src/samples/list/SampleList.tsx +247 -0
  146. inspect_ai/_view/www/src/samples/list/SampleRow.module.css +33 -0
  147. inspect_ai/_view/www/src/samples/list/SampleRow.tsx +98 -0
  148. inspect_ai/_view/www/src/samples/list/SampleSeparator.module.css +6 -0
  149. inspect_ai/_view/www/src/samples/list/SampleSeparator.tsx +24 -0
  150. inspect_ai/_view/www/src/samples/sample-tools/EpochFilter.module.css +9 -0
  151. inspect_ai/_view/www/src/samples/sample-tools/EpochFilter.tsx +51 -0
  152. inspect_ai/_view/www/src/samples/sample-tools/SelectScorer.module.css +16 -0
  153. inspect_ai/_view/www/src/samples/sample-tools/SelectScorer.tsx +173 -0
  154. inspect_ai/_view/www/src/samples/sample-tools/SortFilter.module.css +9 -0
  155. inspect_ai/_view/www/src/samples/sample-tools/SortFilter.tsx +182 -0
  156. inspect_ai/_view/www/src/samples/{tools/filters.mjs → sample-tools/filters.ts} +86 -81
  157. inspect_ai/_view/www/src/samples/sample-tools/sample-filter/SampleFilter.module.css +16 -0
  158. inspect_ai/_view/www/src/samples/sample-tools/sample-filter/SampleFilter.tsx +288 -0
  159. inspect_ai/_view/www/src/samples/sample-tools/sample-filter/completions.ts +346 -0
  160. inspect_ai/_view/www/src/samples/sample-tools/sample-filter/language.ts +19 -0
  161. inspect_ai/_view/www/src/samples/sample-tools/sample-filter/tokenize.ts +97 -0
  162. inspect_ai/_view/www/src/samples/{SampleLimit.mjs → sampleLimit.ts} +3 -6
  163. inspect_ai/_view/www/src/samples/scores/SampleScoreView.module.css +53 -0
  164. inspect_ai/_view/www/src/samples/scores/SampleScoreView.tsx +168 -0
  165. inspect_ai/_view/www/src/samples/scores/SampleScores.module.css +5 -0
  166. inspect_ai/_view/www/src/samples/scores/SampleScores.tsx +37 -0
  167. inspect_ai/_view/www/src/samples/transcript/ApprovalEventView.tsx +66 -0
  168. inspect_ai/_view/www/src/samples/transcript/ErrorEventView.tsx +51 -0
  169. inspect_ai/_view/www/src/samples/transcript/InfoEventView.module.css +3 -0
  170. inspect_ai/_view/www/src/samples/transcript/InfoEventView.tsx +54 -0
  171. inspect_ai/_view/www/src/samples/transcript/InputEventView.tsx +48 -0
  172. inspect_ai/_view/www/src/samples/transcript/LoggerEventView.module.css +6 -0
  173. inspect_ai/_view/www/src/samples/transcript/LoggerEventView.tsx +36 -0
  174. inspect_ai/_view/www/src/samples/transcript/ModelEventView.module.css +43 -0
  175. inspect_ai/_view/www/src/samples/transcript/ModelEventView.tsx +223 -0
  176. inspect_ai/_view/www/src/samples/transcript/SampleInitEventView.module.css +23 -0
  177. inspect_ai/_view/www/src/samples/transcript/SampleInitEventView.tsx +108 -0
  178. inspect_ai/_view/www/src/samples/transcript/SampleLimitEventView.tsx +75 -0
  179. inspect_ai/_view/www/src/samples/transcript/SampleTranscript.tsx +22 -0
  180. inspect_ai/_view/www/src/samples/transcript/ScoreEventView.module.css +15 -0
  181. inspect_ai/_view/www/src/samples/transcript/ScoreEventView.tsx +100 -0
  182. inspect_ai/_view/www/src/samples/transcript/StepEventView.tsx +171 -0
  183. inspect_ai/_view/www/src/samples/transcript/SubtaskEventView.module.css +19 -0
  184. inspect_ai/_view/www/src/samples/transcript/SubtaskEventView.tsx +133 -0
  185. inspect_ai/_view/www/src/samples/transcript/ToolEventView.module.css +10 -0
  186. inspect_ai/_view/www/src/samples/transcript/ToolEventView.tsx +91 -0
  187. inspect_ai/_view/www/src/samples/transcript/TranscriptView.module.css +49 -0
  188. inspect_ai/_view/www/src/samples/transcript/TranscriptView.tsx +449 -0
  189. inspect_ai/_view/www/src/samples/transcript/event/EventNav.module.css +5 -0
  190. inspect_ai/_view/www/src/samples/transcript/event/EventNav.tsx +43 -0
  191. inspect_ai/_view/www/src/samples/transcript/event/EventNavs.module.css +3 -0
  192. inspect_ai/_view/www/src/samples/transcript/event/EventNavs.tsx +38 -0
  193. inspect_ai/_view/www/src/samples/transcript/event/EventPanel.module.css +25 -0
  194. inspect_ai/_view/www/src/samples/transcript/event/EventPanel.tsx +190 -0
  195. inspect_ai/_view/www/src/samples/transcript/event/EventRow.module.css +13 -0
  196. inspect_ai/_view/www/src/samples/transcript/event/EventRow.tsx +32 -0
  197. inspect_ai/_view/www/src/samples/transcript/event/EventSection.module.css +8 -0
  198. inspect_ai/_view/www/src/samples/transcript/event/EventSection.tsx +29 -0
  199. inspect_ai/_view/www/src/samples/transcript/state/StateDiffView.tsx +67 -0
  200. inspect_ai/_view/www/src/samples/transcript/state/StateEventRenderers.tsx +274 -0
  201. inspect_ai/_view/www/src/samples/transcript/state/StateEventRenders.module.css +10 -0
  202. inspect_ai/_view/www/src/samples/transcript/state/StateEventView.module.css +9 -0
  203. inspect_ai/_view/www/src/samples/transcript/state/{StateEventView.mjs → StateEventView.tsx} +148 -110
  204. inspect_ai/_view/www/src/samples/transcript/types.ts +58 -0
  205. inspect_ai/_view/www/src/types/log.d.ts +1 -0
  206. inspect_ai/_view/www/src/types/prism.d.ts +11 -0
  207. inspect_ai/_view/www/src/types.ts +71 -0
  208. inspect_ai/_view/www/src/usage/ModelTokenTable.tsx +22 -0
  209. inspect_ai/_view/www/src/usage/ModelUsagePanel.module.css +24 -0
  210. inspect_ai/_view/www/src/usage/ModelUsagePanel.tsx +95 -0
  211. inspect_ai/_view/www/src/usage/TokenTable.module.css +17 -0
  212. inspect_ai/_view/www/src/usage/TokenTable.tsx +91 -0
  213. inspect_ai/_view/www/src/usage/UsageCard.module.css +15 -0
  214. inspect_ai/_view/www/src/usage/UsageCard.tsx +67 -0
  215. inspect_ai/_view/www/src/utils/attachments.ts +42 -0
  216. inspect_ai/_view/www/src/utils/{Base64.mjs → base64.ts} +1 -6
  217. inspect_ai/_view/www/src/{components/Browser.mjs → utils/browser.ts} +0 -1
  218. inspect_ai/_view/www/src/utils/debugging.ts +28 -0
  219. inspect_ai/_view/www/src/utils/dom.ts +30 -0
  220. inspect_ai/_view/www/src/utils/format.ts +194 -0
  221. inspect_ai/_view/www/src/utils/git.ts +7 -0
  222. inspect_ai/_view/www/src/utils/html.ts +6 -0
  223. inspect_ai/_view/www/src/utils/http.ts +14 -0
  224. inspect_ai/_view/www/src/utils/{Path.mjs → path.ts} +2 -9
  225. inspect_ai/_view/www/src/utils/{Print.mjs → print.ts} +34 -26
  226. inspect_ai/_view/www/src/utils/queue.ts +51 -0
  227. inspect_ai/_view/www/src/utils/sync.ts +114 -0
  228. inspect_ai/_view/www/src/utils/{Type.mjs → type.ts} +3 -6
  229. inspect_ai/_view/www/src/utils/vscode.ts +13 -0
  230. inspect_ai/_view/www/src/workspace/WorkSpace.tsx +324 -0
  231. inspect_ai/_view/www/src/workspace/WorkSpaceView.module.css +33 -0
  232. inspect_ai/_view/www/src/workspace/WorkSpaceView.tsx +160 -0
  233. inspect_ai/_view/www/src/workspace/error/TaskErrorPanel.module.css +3 -0
  234. inspect_ai/_view/www/src/workspace/error/TaskErrorPanel.tsx +28 -0
  235. inspect_ai/_view/www/src/workspace/navbar/Navbar.module.css +54 -0
  236. inspect_ai/_view/www/src/workspace/navbar/Navbar.tsx +68 -0
  237. inspect_ai/_view/www/src/workspace/navbar/PrimaryBar.module.css +52 -0
  238. inspect_ai/_view/www/src/workspace/navbar/PrimaryBar.tsx +113 -0
  239. inspect_ai/_view/www/src/workspace/navbar/ResultsPanel.module.css +67 -0
  240. inspect_ai/_view/www/src/workspace/navbar/ResultsPanel.tsx +156 -0
  241. inspect_ai/_view/www/src/workspace/navbar/SecondaryBar.module.css +28 -0
  242. inspect_ai/_view/www/src/workspace/navbar/SecondaryBar.tsx +222 -0
  243. inspect_ai/_view/www/src/workspace/navbar/StatusPanel.module.css +14 -0
  244. inspect_ai/_view/www/src/workspace/navbar/StatusPanel.tsx +61 -0
  245. inspect_ai/_view/www/src/workspace/sidebar/EvalStatus.module.css +15 -0
  246. inspect_ai/_view/www/src/workspace/sidebar/EvalStatus.tsx +71 -0
  247. inspect_ai/_view/www/src/workspace/sidebar/LogDirectoryTitleView.module.css +5 -0
  248. inspect_ai/_view/www/src/workspace/sidebar/LogDirectoryTitleView.tsx +56 -0
  249. inspect_ai/_view/www/src/workspace/sidebar/Sidebar.module.css +68 -0
  250. inspect_ai/_view/www/src/workspace/sidebar/Sidebar.tsx +85 -0
  251. inspect_ai/_view/www/src/workspace/sidebar/SidebarLogEntry.module.css +29 -0
  252. inspect_ai/_view/www/src/workspace/sidebar/SidebarLogEntry.tsx +95 -0
  253. inspect_ai/_view/www/src/workspace/sidebar/SidebarScoreView.module.css +23 -0
  254. inspect_ai/_view/www/src/workspace/sidebar/SidebarScoreView.tsx +41 -0
  255. inspect_ai/_view/www/src/workspace/sidebar/SidebarScoresView.module.css +35 -0
  256. inspect_ai/_view/www/src/workspace/sidebar/SidebarScoresView.tsx +61 -0
  257. inspect_ai/_view/www/src/workspace/tabs/InfoTab.tsx +80 -0
  258. inspect_ai/_view/www/src/workspace/tabs/JsonTab.module.css +5 -0
  259. inspect_ai/_view/www/src/workspace/tabs/JsonTab.tsx +46 -0
  260. inspect_ai/_view/www/src/workspace/tabs/SamplesTab.tsx +204 -0
  261. inspect_ai/_view/www/src/workspace/tabs/grouping.ts +195 -0
  262. inspect_ai/_view/www/src/workspace/tabs/types.ts +19 -0
  263. inspect_ai/_view/www/src/workspace/types.ts +10 -0
  264. inspect_ai/_view/www/tsconfig.json +23 -9
  265. inspect_ai/_view/www/vite.config.js +8 -17
  266. inspect_ai/_view/www/yarn.lock +627 -556
  267. inspect_ai/dataset/_dataset.py +36 -0
  268. inspect_ai/dataset/_sources/csv.py +8 -0
  269. inspect_ai/dataset/_sources/file.py +4 -0
  270. inspect_ai/dataset/_sources/hf.py +11 -1
  271. inspect_ai/dataset/_sources/json.py +8 -0
  272. inspect_ai/log/_log.py +3 -6
  273. inspect_ai/log/_message.py +1 -1
  274. inspect_ai/log/_recorders/json.py +5 -7
  275. inspect_ai/model/_call_tools.py +2 -1
  276. inspect_ai/model/_providers/anthropic.py +3 -3
  277. inspect_ai/model/_providers/openai_o1.py +3 -5
  278. inspect_ai/model/_providers/openrouter.py +86 -0
  279. inspect_ai/model/_providers/providers.py +11 -0
  280. inspect_ai/scorer/_answer.py +7 -7
  281. inspect_ai/scorer/_classification.py +34 -18
  282. inspect_ai/scorer/_common.py +2 -8
  283. inspect_ai/solver/_multiple_choice.py +24 -9
  284. inspect_ai/tool/__init__.py +2 -0
  285. inspect_ai/tool/{beta → _tools}/_computer/_computer.py +2 -5
  286. inspect_ai/tool/_tools/_computer/_resources/tool/__init__.py +0 -0
  287. inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_x11_client.py +1 -1
  288. inspect_ai/tool/_tools/_computer/_resources/tool/requirements.txt +0 -0
  289. inspect_ai/tool/_tools/_execute.py +8 -2
  290. inspect_ai/tool/beta.py +3 -0
  291. inspect_ai/util/_sandbox/docker/docker.py +32 -85
  292. inspect_ai/util/_sandbox/self_check.py +124 -16
  293. {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.63.dist-info}/METADATA +2 -1
  294. inspect_ai-0.3.63.dist-info/RECORD +618 -0
  295. inspect_ai/_view/www/src/Register.mjs +0 -3
  296. inspect_ai/_view/www/src/Types.mjs +0 -38
  297. inspect_ai/_view/www/src/appearance/Colors.mjs +0 -27
  298. inspect_ai/_view/www/src/appearance/Fonts.mjs +0 -66
  299. inspect_ai/_view/www/src/appearance/Icons.mjs +0 -240
  300. inspect_ai/_view/www/src/components/AnsiDisplay.mjs +0 -184
  301. inspect_ai/_view/www/src/components/AppErrorBoundary.mjs +0 -34
  302. inspect_ai/_view/www/src/components/AsciiCinemaPlayer.mjs +0 -74
  303. inspect_ai/_view/www/src/components/Card.mjs +0 -126
  304. inspect_ai/_view/www/src/components/ChatView.mjs +0 -441
  305. inspect_ai/_view/www/src/components/CopyButton.mjs +0 -48
  306. inspect_ai/_view/www/src/components/Dialog.mjs +0 -61
  307. inspect_ai/_view/www/src/components/DownloadButton.mjs +0 -15
  308. inspect_ai/_view/www/src/components/DownloadPanel.mjs +0 -29
  309. inspect_ai/_view/www/src/components/EmptyPanel.mjs +0 -23
  310. inspect_ai/_view/www/src/components/ErrorPanel.mjs +0 -66
  311. inspect_ai/_view/www/src/components/ExpandablePanel.mjs +0 -136
  312. inspect_ai/_view/www/src/components/FindBand.mjs +0 -157
  313. inspect_ai/_view/www/src/components/HumanBaselineView.mjs +0 -168
  314. inspect_ai/_view/www/src/components/JsonPanel.mjs +0 -61
  315. inspect_ai/_view/www/src/components/LabeledValue.mjs +0 -32
  316. inspect_ai/_view/www/src/components/LargeModal.mjs +0 -190
  317. inspect_ai/_view/www/src/components/LightboxCarousel.mjs +0 -217
  318. inspect_ai/_view/www/src/components/MarkdownDiv.mjs +0 -118
  319. inspect_ai/_view/www/src/components/MessageBand.mjs +0 -48
  320. inspect_ai/_view/www/src/components/MessageContent.mjs +0 -111
  321. inspect_ai/_view/www/src/components/MetaDataGrid.mjs +0 -92
  322. inspect_ai/_view/www/src/components/MetaDataView.mjs +0 -109
  323. inspect_ai/_view/www/src/components/MorePopOver.mjs +0 -50
  324. inspect_ai/_view/www/src/components/NavPills.mjs +0 -63
  325. inspect_ai/_view/www/src/components/ProgressBar.mjs +0 -51
  326. inspect_ai/_view/www/src/components/RenderedContent/ChatMessageRenderer.mjs +0 -54
  327. inspect_ai/_view/www/src/components/RenderedContent/Types.mjs +0 -19
  328. inspect_ai/_view/www/src/components/TabSet.mjs +0 -184
  329. inspect_ai/_view/www/src/components/ToolButton.mjs +0 -16
  330. inspect_ai/_view/www/src/components/Tools.mjs +0 -376
  331. inspect_ai/_view/www/src/components/VirtualList.mjs +0 -280
  332. inspect_ai/_view/www/src/components/ansi-output.js +0 -932
  333. inspect_ai/_view/www/src/json/JsonTab.mjs +0 -48
  334. inspect_ai/_view/www/src/log-reader/Log-Reader.mjs +0 -25
  335. inspect_ai/_view/www/src/log-reader/Native-Log-Reader.mjs +0 -13
  336. inspect_ai/_view/www/src/log-reader/Open-AI-Log-Reader.mjs +0 -263
  337. inspect_ai/_view/www/src/navbar/Navbar.mjs +0 -418
  338. inspect_ai/_view/www/src/navbar/SecondaryBar.mjs +0 -175
  339. inspect_ai/_view/www/src/plan/PlanCard.mjs +0 -418
  340. inspect_ai/_view/www/src/samples/SampleDialog.mjs +0 -123
  341. inspect_ai/_view/www/src/samples/SampleDisplay.mjs +0 -516
  342. inspect_ai/_view/www/src/samples/SampleError.mjs +0 -99
  343. inspect_ai/_view/www/src/samples/SampleList.mjs +0 -427
  344. inspect_ai/_view/www/src/samples/SampleScoreView.mjs +0 -172
  345. inspect_ai/_view/www/src/samples/SampleScores.mjs +0 -34
  346. inspect_ai/_view/www/src/samples/SampleTranscript.mjs +0 -20
  347. inspect_ai/_view/www/src/samples/SamplesDescriptor.mjs +0 -771
  348. inspect_ai/_view/www/src/samples/SamplesTab.mjs +0 -399
  349. inspect_ai/_view/www/src/samples/SamplesTools.mjs +0 -64
  350. inspect_ai/_view/www/src/samples/tools/EpochFilter.mjs +0 -38
  351. inspect_ai/_view/www/src/samples/tools/SampleFilter.mjs +0 -756
  352. inspect_ai/_view/www/src/samples/tools/SelectScorer.mjs +0 -141
  353. inspect_ai/_view/www/src/samples/tools/SortFilter.mjs +0 -151
  354. inspect_ai/_view/www/src/samples/transcript/ApprovalEventView.mjs +0 -71
  355. inspect_ai/_view/www/src/samples/transcript/ErrorEventView.mjs +0 -44
  356. inspect_ai/_view/www/src/samples/transcript/EventPanel.mjs +0 -271
  357. inspect_ai/_view/www/src/samples/transcript/EventRow.mjs +0 -46
  358. inspect_ai/_view/www/src/samples/transcript/EventSection.mjs +0 -33
  359. inspect_ai/_view/www/src/samples/transcript/InfoEventView.mjs +0 -59
  360. inspect_ai/_view/www/src/samples/transcript/InputEventView.mjs +0 -44
  361. inspect_ai/_view/www/src/samples/transcript/LoggerEventView.mjs +0 -32
  362. inspect_ai/_view/www/src/samples/transcript/ModelEventView.mjs +0 -216
  363. inspect_ai/_view/www/src/samples/transcript/SampleInitEventView.mjs +0 -107
  364. inspect_ai/_view/www/src/samples/transcript/SampleLimitEventView.mjs +0 -74
  365. inspect_ai/_view/www/src/samples/transcript/ScoreEventView.mjs +0 -100
  366. inspect_ai/_view/www/src/samples/transcript/StepEventView.mjs +0 -187
  367. inspect_ai/_view/www/src/samples/transcript/SubtaskEventView.mjs +0 -133
  368. inspect_ai/_view/www/src/samples/transcript/ToolEventView.mjs +0 -88
  369. inspect_ai/_view/www/src/samples/transcript/TranscriptView.mjs +0 -459
  370. inspect_ai/_view/www/src/samples/transcript/Types.mjs +0 -44
  371. inspect_ai/_view/www/src/samples/transcript/state/StateDiffView.mjs +0 -53
  372. inspect_ai/_view/www/src/samples/transcript/state/StateEventRenderers.mjs +0 -254
  373. inspect_ai/_view/www/src/sidebar/Sidebar.mjs +0 -418
  374. inspect_ai/_view/www/src/usage/ModelTokenTable.mjs +0 -72
  375. inspect_ai/_view/www/src/usage/UsageCard.mjs +0 -159
  376. inspect_ai/_view/www/src/utils/Format.mjs +0 -260
  377. inspect_ai/_view/www/src/utils/Git.mjs +0 -12
  378. inspect_ai/_view/www/src/utils/Html.mjs +0 -21
  379. inspect_ai/_view/www/src/utils/attachments.mjs +0 -31
  380. inspect_ai/_view/www/src/utils/debugging.mjs +0 -23
  381. inspect_ai/_view/www/src/utils/http.mjs +0 -18
  382. inspect_ai/_view/www/src/utils/queue.mjs +0 -67
  383. inspect_ai/_view/www/src/utils/sync.mjs +0 -101
  384. inspect_ai/_view/www/src/workspace/TaskErrorPanel.mjs +0 -17
  385. inspect_ai/_view/www/src/workspace/WorkSpace.mjs +0 -516
  386. inspect_ai/tool/beta/__init__.py +0 -5
  387. inspect_ai-0.3.62.dist-info/RECORD +0 -481
  388. /inspect_ai/{tool/beta/_computer/_resources/tool/__init__.py → _view/www/src/components/MorePopOver.css} +0 -0
  389. /inspect_ai/_view/www/src/{constants.mjs → constants.ts} +0 -0
  390. /inspect_ai/{tool/beta/_computer/_resources/tool/requirements.txt → _view/www/src/workspace/tabs/InfoTab.module.css} +0 -0
  391. /inspect_ai/tool/{beta → _tools}/_computer/__init__.py +0 -0
  392. /inspect_ai/tool/{beta → _tools}/_computer/_common.py +0 -0
  393. /inspect_ai/tool/{beta → _tools}/_computer/_computer_split.py +0 -0
  394. /inspect_ai/tool/{beta → _tools}/_computer/_resources/Dockerfile +0 -0
  395. /inspect_ai/tool/{beta → _tools}/_computer/_resources/README.md +0 -0
  396. /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/entrypoint.sh +0 -0
  397. /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/novnc_startup.sh +0 -0
  398. /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/x11vnc_startup.sh +0 -0
  399. /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/xfce_startup.sh +0 -0
  400. /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/xvfb_startup.sh +0 -0
  401. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/Code/User/globalStorage/state.vscdb +0 -0
  402. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/Code/User/settings.json +0 -0
  403. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/xfce4/xfconf/xfce-perchannel-xml/xfce4-panel.xml +0 -0
  404. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/xfce4/xfconf/xfce-perchannel-xml/xfce4-screensaver.xml +0 -0
  405. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/Desktop/Firefox Web Browser.desktop +0 -0
  406. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/Desktop/Terminal.desktop +0 -0
  407. /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/Desktop/Visual Studio Code.desktop +0 -0
  408. /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_logger.py +0 -0
  409. /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_run.py +0 -0
  410. /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_tool_result.py +0 -0
  411. /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/computer_tool.py +0 -0
  412. {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.63.dist-info}/LICENSE +0 -0
  413. {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.63.dist-info}/WHEEL +0 -0
  414. {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.63.dist-info}/entry_points.txt +0 -0
  415. {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.63.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,160 @@
1
+ import clsx from "clsx";
2
+ import { Fragment, MouseEvent, RefObject, useCallback, useMemo } from "react";
3
+ import { SampleSummary } from "../api/types";
4
+ import { EmptyPanel } from "../components/EmptyPanel";
5
+ import { TabPanel, TabSet } from "../components/TabSet";
6
+ import { EvalDescriptor } from "../samples/descriptor/types";
7
+ import {
8
+ EvalPlan,
9
+ EvalResults,
10
+ EvalSpec,
11
+ EvalStats,
12
+ Status,
13
+ } from "../types/log";
14
+ import { debounce } from "../utils/sync";
15
+ import { Navbar } from "./navbar/Navbar";
16
+ import { TabDescriptor } from "./types";
17
+
18
+ import styles from "./WorkSpaceView.module.css";
19
+
20
+ interface WorkSpaceViewProps {
21
+ logFileName?: string;
22
+ evalSpec: EvalSpec;
23
+ evalPlan?: EvalPlan;
24
+ evalResults?: EvalResults;
25
+ evalStats?: EvalStats;
26
+ samples?: SampleSummary[];
27
+ evalDescriptor?: EvalDescriptor;
28
+ status?: Status;
29
+ showToggle: boolean;
30
+ tabs: Record<string, TabDescriptor>;
31
+ selectedTab: string;
32
+ setSelectedTab: (tab: string) => void;
33
+ divRef: RefObject<HTMLDivElement | null>;
34
+ offcanvas: boolean;
35
+ setOffcanvas: (offcanvas: boolean) => void;
36
+ workspaceTabScrollPositionRef: RefObject<Record<string, number>>;
37
+ setWorkspaceTabScrollPosition: (tab: string, pos: number) => void;
38
+ }
39
+
40
+ export const WorkSpaceView: React.FC<WorkSpaceViewProps> = ({
41
+ logFileName,
42
+ evalSpec,
43
+ evalPlan,
44
+ evalResults,
45
+ evalStats,
46
+ samples,
47
+ evalDescriptor,
48
+ status,
49
+ showToggle,
50
+ selectedTab,
51
+ tabs,
52
+ setSelectedTab,
53
+ divRef,
54
+ offcanvas,
55
+ setOffcanvas,
56
+ workspaceTabScrollPositionRef,
57
+ setWorkspaceTabScrollPosition,
58
+ }) => {
59
+ const debouncedScroll = useMemo(() => {
60
+ return debounce((id, position) => {
61
+ setWorkspaceTabScrollPosition(id, position);
62
+ }, 100);
63
+ }, [setWorkspaceTabScrollPosition]);
64
+
65
+ const onScroll = useCallback(
66
+ (id: string, position: number) => {
67
+ debouncedScroll(id, position);
68
+ },
69
+ [debouncedScroll],
70
+ );
71
+
72
+ const onSelected = useCallback(
73
+ (e: MouseEvent<HTMLElement>) => {
74
+ const id = e.currentTarget?.id;
75
+ if (id) {
76
+ setSelectedTab(id);
77
+ }
78
+ },
79
+ [setSelectedTab],
80
+ );
81
+
82
+ // Compute tab panels anytime the tabs change
83
+ const tabPanels = useMemo(() => {
84
+ return Object.keys(tabs).map((key) => {
85
+ const tab = tabs[key];
86
+ return (
87
+ <TabPanel
88
+ id={tab.id}
89
+ title={tab.label}
90
+ onSelected={onSelected}
91
+ selected={selectedTab === tab.id}
92
+ scrollable={!!tab.scrollable}
93
+ scrollRef={tab.scrollRef}
94
+ scrollPosition={workspaceTabScrollPositionRef.current?.[tab.id]}
95
+ setScrollPosition={useCallback(
96
+ (position: number) => {
97
+ onScroll(tab.id, position);
98
+ },
99
+ [onScroll],
100
+ )}
101
+ >
102
+ {tab.content()}
103
+ </TabPanel>
104
+ );
105
+ });
106
+ }, [tabs, selectedTab]);
107
+
108
+ if (evalSpec === undefined) {
109
+ return <EmptyPanel />;
110
+ } else {
111
+ const tabTools = Object.keys(tabs)
112
+ .map((key) => {
113
+ const tab = tabs[key];
114
+ return tab;
115
+ })
116
+ .filter((tab) => {
117
+ return tab.id === selectedTab;
118
+ })
119
+ .map((tab) => {
120
+ if (tab.tools) {
121
+ const tools = tab.tools();
122
+ return tools;
123
+ } else {
124
+ return null;
125
+ }
126
+ });
127
+
128
+ return (
129
+ <Fragment>
130
+ <Navbar
131
+ evalSpec={evalSpec}
132
+ evalPlan={evalPlan}
133
+ evalResults={evalResults}
134
+ evalStats={evalStats}
135
+ samples={samples}
136
+ evalDescriptor={evalDescriptor}
137
+ status={status}
138
+ file={logFileName}
139
+ showToggle={showToggle}
140
+ offcanvas={offcanvas}
141
+ setOffcanvas={setOffcanvas}
142
+ />
143
+ <div ref={divRef} className={clsx("workspace", styles.workspace)}>
144
+ <div className={clsx("log-detail", styles.tabContainer)}>
145
+ <TabSet
146
+ id="log-details"
147
+ tools={tabTools}
148
+ type="pills"
149
+ className={clsx(styles.tabSet, "text-size-smaller")}
150
+ tabControlsClassName={clsx(styles.tabs, "text-size-smaller")}
151
+ tabPanelsClassName={clsx(styles.tabPanels)}
152
+ >
153
+ {tabPanels}
154
+ </TabSet>
155
+ </div>
156
+ </div>
157
+ </Fragment>
158
+ );
159
+ }
160
+ };
@@ -0,0 +1,3 @@
1
+ .task-error-display {
2
+ font-size: clamp(0.2rem, calc(0.2em + 0.93vw), 0.9rem);
3
+ }
@@ -0,0 +1,28 @@
1
+ import { ApplicationIcons } from "../../appearance/icons";
2
+
3
+ import { ANSIDisplay } from "../../components/AnsiDisplay";
4
+ import { Card, CardBody, CardHeader } from "../../components/Card";
5
+ import { EvalError } from "../../types/log";
6
+
7
+ import styles from "./TaskErrorPanel.module.css";
8
+
9
+ interface TaskErrorProps {
10
+ error: EvalError;
11
+ }
12
+
13
+ export const TaskErrorCard: React.FC<TaskErrorProps> = ({ error }) => {
14
+ return (
15
+ <Card>
16
+ <CardHeader
17
+ icon={ApplicationIcons.error}
18
+ label="Task Failed: ${error.message}"
19
+ ></CardHeader>
20
+ <CardBody>
21
+ <ANSIDisplay
22
+ output={error.traceback_ansi}
23
+ className={styles["task-error-display"]}
24
+ />
25
+ </CardBody>
26
+ </Card>
27
+ );
28
+ };
@@ -0,0 +1,54 @@
1
+ .navbarContainer {
2
+ display: flex;
3
+ padding-top: 0;
4
+ margin-left: 0.5rem;
5
+ min-width: 250px;
6
+ }
7
+
8
+ .navbarToggle {
9
+ padding: 0rem 0.1rem 0.1rem 0rem;
10
+ display: flex;
11
+ }
12
+
13
+ .navbarBody {
14
+ display: flex;
15
+ flex-direction: column;
16
+ margin-left: 0.2rem;
17
+ }
18
+
19
+ .navbarBodyContainer {
20
+ margin-top: 0.1rem;
21
+ display: grid;
22
+ grid-template-columns: minmax(30px, max-content) minmax(100px, max-content);
23
+ }
24
+
25
+ .navbarTaskTitle {
26
+ font-weight: 600;
27
+ margin-right: 0.3rem;
28
+ }
29
+
30
+ .navbarTaskModel {
31
+ padding-top: 0.4rem;
32
+ }
33
+
34
+ .navbarSecondaryContainer {
35
+ opacity: 0.7;
36
+ margin-top: 0.1rem;
37
+ padding-bottom: 0;
38
+ display: grid;
39
+ grid-template-columns: minmax(0, max-content) max-content;
40
+ }
41
+
42
+ .navbarStatus {
43
+ justify-content: end;
44
+ margin-right: 1em;
45
+ margin-bottom: 0;
46
+ }
47
+
48
+ .navbarWrapper {
49
+ width: 100%;
50
+ }
51
+ .navbarInnerWrapper {
52
+ display: grid;
53
+ grid-template-columns: 1fr auto;
54
+ }
@@ -0,0 +1,68 @@
1
+ import clsx from "clsx";
2
+ import { SampleSummary } from "../../api/types";
3
+ import { EvalDescriptor } from "../../samples/descriptor/types";
4
+ import {
5
+ EvalPlan,
6
+ EvalResults,
7
+ EvalSpec,
8
+ EvalStats,
9
+ Status,
10
+ } from "../../types/log";
11
+ import styles from "./Navbar.module.css";
12
+ import { PrimaryBar } from "./PrimaryBar";
13
+ import { SecondaryBar } from "./SecondaryBar";
14
+
15
+ interface NavBarProps {
16
+ file?: string;
17
+ evalSpec?: EvalSpec;
18
+ evalResults?: EvalResults;
19
+ evalPlan?: EvalPlan;
20
+ evalStats?: EvalStats;
21
+ evalDescriptor?: EvalDescriptor;
22
+ samples?: SampleSummary[];
23
+ status?: Status;
24
+ offcanvas: boolean;
25
+ setOffcanvas: (offcanvas: boolean) => void;
26
+ showToggle: boolean;
27
+ }
28
+
29
+ /**
30
+ * Renders the Navbar
31
+ */
32
+ export const Navbar: React.FC<NavBarProps> = ({
33
+ file,
34
+ evalSpec,
35
+ evalPlan,
36
+ evalResults,
37
+ evalStats,
38
+ samples,
39
+ evalDescriptor,
40
+ showToggle,
41
+ offcanvas,
42
+ setOffcanvas,
43
+ status,
44
+ }) => {
45
+ return (
46
+ <nav className={clsx("navbar", "sticky-top", styles.navbarWrapper)}>
47
+ <PrimaryBar
48
+ file={file}
49
+ evalSpec={evalSpec}
50
+ evalResults={evalResults}
51
+ samples={samples}
52
+ showToggle={showToggle}
53
+ offcanvas={offcanvas}
54
+ setOffcanvas={setOffcanvas}
55
+ status={status}
56
+ />
57
+ <SecondaryBar
58
+ evalSpec={evalSpec}
59
+ evalPlan={evalPlan}
60
+ evalResults={evalResults}
61
+ evalStats={evalStats}
62
+ samples={samples}
63
+ evalDescriptor={evalDescriptor}
64
+ status={status}
65
+ />
66
+ </nav>
67
+ );
68
+ };
@@ -0,0 +1,52 @@
1
+ .container {
2
+ display: flex;
3
+ padding-top: 0;
4
+ margin-left: 0.5rem;
5
+ min-width: 250px;
6
+ }
7
+
8
+ .wrapper {
9
+ display: grid;
10
+ grid-template-columns: minmax(auto, 1fr) 1fr;
11
+ width: 100%;
12
+ }
13
+
14
+ .toggle {
15
+ padding: 0rem 0.1rem 0.1rem 0rem;
16
+ display: flex;
17
+ }
18
+
19
+ .body {
20
+ display: flex;
21
+ flex-direction: column;
22
+ margin-left: 0.2rem;
23
+ }
24
+
25
+ .bodyContainer {
26
+ margin-top: 0.1rem;
27
+ display: grid;
28
+ grid-template-columns: minmax(30px, max-content) minmax(100px, max-content);
29
+ }
30
+
31
+ .taskTitle {
32
+ font-weight: 600;
33
+ margin-right: 0.3rem;
34
+ }
35
+
36
+ .taskModel {
37
+ padding-top: 0.4rem;
38
+ }
39
+
40
+ .taskStatus {
41
+ justify-content: end;
42
+ margin-right: 1em;
43
+ margin-bottom: 0;
44
+ }
45
+
46
+ .secondaryContainer {
47
+ opacity: 0.7;
48
+ margin-top: 0.1rem;
49
+ padding-bottom: 0;
50
+ display: grid;
51
+ grid-template-columns: minmax(0, max-content) max-content;
52
+ }
@@ -0,0 +1,113 @@
1
+ import clsx from "clsx";
2
+ import { useCallback } from "react";
3
+ import { SampleSummary } from "../../api/types";
4
+ import { ApplicationIcons } from "../../appearance/icons";
5
+ import { CopyButton } from "../../components/CopyButton";
6
+ import { EvalResults, EvalSpec, Status } from "../../types/log";
7
+ import { filename } from "../../utils/path";
8
+ import styles from "./PrimaryBar.module.css";
9
+ import { ResultsPanel } from "./ResultsPanel";
10
+ import { CancelledPanel, ErroredPanel, RunningPanel } from "./StatusPanel";
11
+
12
+ interface PrimaryBarProps {
13
+ showToggle: boolean;
14
+ offcanvas: boolean;
15
+ setOffcanvas: (offcanvas: boolean) => void;
16
+ status?: Status;
17
+ evalResults?: EvalResults;
18
+ samples?: SampleSummary[];
19
+ file?: string;
20
+ evalSpec?: EvalSpec;
21
+ }
22
+
23
+ export const PrimaryBar: React.FC<PrimaryBarProps> = ({
24
+ showToggle,
25
+ offcanvas,
26
+ status,
27
+ evalResults,
28
+ samples,
29
+ file,
30
+ evalSpec,
31
+ setOffcanvas,
32
+ }) => {
33
+ let statusPanel;
34
+ if (status === "success") {
35
+ statusPanel = <ResultsPanel results={evalResults} />;
36
+ } else if (status === "cancelled") {
37
+ statusPanel = <CancelledPanel sampleCount={samples?.length || 0} />;
38
+ } else if (status === "started") {
39
+ statusPanel = <RunningPanel sampleCount={samples?.length || 0} />;
40
+ } else if (status === "error") {
41
+ statusPanel = <ErroredPanel sampleCount={samples?.length || 0} />;
42
+ }
43
+ const logFileName = file ? filename(file) : "";
44
+
45
+ const handleToggle = useCallback(() => {
46
+ setOffcanvas(!offcanvas);
47
+ }, [offcanvas]);
48
+
49
+ return (
50
+ <div className={clsx(styles.wrapper)}>
51
+ <div
52
+ className={clsx(
53
+ "navbar-brand",
54
+ "navbar-text",
55
+ "mb-0",
56
+ styles.container,
57
+ )}
58
+ >
59
+ {showToggle ? (
60
+ <button
61
+ id="sidebarToggle"
62
+ onClick={handleToggle}
63
+ className={clsx(
64
+ "btn",
65
+ offcanvas ? "d-md-none" : undefined,
66
+ styles.toggle,
67
+ )}
68
+ type="button"
69
+ >
70
+ <i className={ApplicationIcons.menu}></i>
71
+ </button>
72
+ ) : (
73
+ ""
74
+ )}
75
+ <div className={styles.body}>
76
+ <div className={styles.bodyContainer}>
77
+ <div
78
+ id="task-title"
79
+ className={clsx("task-title", "text-truncate", styles.taskTitle)}
80
+ title={evalSpec?.task}
81
+ >
82
+ {evalSpec?.task}
83
+ </div>
84
+ <div
85
+ id="task-model"
86
+ className={clsx(
87
+ "task-model",
88
+ "text-truncate",
89
+ styles.taskModel,
90
+ "text-size-base",
91
+ )}
92
+ title={evalSpec?.model}
93
+ >
94
+ {evalSpec?.model}
95
+ </div>
96
+ </div>
97
+ <div className={clsx("text-size-small", styles.secondaryContainer)}>
98
+ <div className={clsx("navbar-secondary-text", "text-truncate")}>
99
+ {logFileName}
100
+ </div>
101
+ {file ? <CopyButton value={file} /> : ""}
102
+ </div>
103
+ </div>
104
+ </div>
105
+ <div className={clsx(styles.taskStatus, "navbar-text")}>
106
+ {statusPanel}
107
+ </div>
108
+ <div id="task-created" style={{ display: "none" }}>
109
+ {evalSpec?.created}
110
+ </div>
111
+ </div>
112
+ );
113
+ };
@@ -0,0 +1,67 @@
1
+ .simpleMetricsRows {
2
+ display: flex;
3
+ flex-direction: row;
4
+ flex-wrap: wrap;
5
+ justify-content: end;
6
+ height: 100%;
7
+ align-items: center;
8
+ max-height: 15em;
9
+ overflow: scroll;
10
+ }
11
+
12
+ .multiMetricsRows {
13
+ display: flex;
14
+ flex-direction: row;
15
+ flex-wrap: wrap;
16
+ justify-content: end;
17
+ height: 100%;
18
+ align-items: center;
19
+ margin-top: 0.2rem;
20
+ padding-bottom: 0.4rem;
21
+ row-gap: 1em;
22
+ max-height: 15em;
23
+ overflow: scroll;
24
+ }
25
+
26
+ .verticalMetricReducer {
27
+ font-size: var(--inspect-font-size-smaller);
28
+ text-align: center;
29
+ padding-top: 0.3rem;
30
+ margin-bottom: -0.3rem;
31
+ }
32
+
33
+ .verticalMetricName {
34
+ font-size: var(--inspect-font-size-smaller);
35
+ text-align: center;
36
+ padding-top: 0.3rem;
37
+ margin-bottom: -0.2rem;
38
+ border-bottom: solid var(--bs-border-color) 1px;
39
+ }
40
+
41
+ .verticalMetricValue {
42
+ font-size: var(--inspect-font-size-larger);
43
+ font-weight: 500;
44
+ text-align: center;
45
+ }
46
+
47
+ .multiScorerReducer {
48
+ text-align: center;
49
+ margin-bottom: -0.3rem;
50
+ }
51
+
52
+ .multiScorerLabel {
53
+ text-align: center;
54
+ border-bottom: solid var(--bs-border-color) 1px;
55
+ margin-bottom: -0.1rem;
56
+ }
57
+
58
+ .multiScorerValue {
59
+ display: grid;
60
+ grid-template-columns: auto auto;
61
+ grid-column-gap: 0.3rem;
62
+ grid-row-gap: 0;
63
+ }
64
+
65
+ .multiScorerValueContent {
66
+ font-weight: 600;
67
+ }
@@ -0,0 +1,156 @@
1
+ import clsx from "clsx";
2
+ import { EvalMetric, EvalResults, EvalScore, Reducer } from "../../types/log";
3
+ import { formatPrettyDecimal } from "../../utils/format";
4
+ import styles from "./ResultsPanel.module.css";
5
+
6
+ interface ResultsPanelProps {
7
+ results?: EvalResults;
8
+ }
9
+
10
+ interface MetricSummary {
11
+ reducer: Reducer;
12
+ metric: EvalMetric;
13
+ }
14
+
15
+ export const ResultsPanel: React.FC<ResultsPanelProps> = ({ results }) => {
16
+ // Map the scores into a list of key/values
17
+ if (results?.scores?.length === 1) {
18
+ const scorers: Record<string, MetricSummary[]> = {};
19
+ results.scores.map((score) => {
20
+ scorers[score.name] = Object.keys(score.metrics).map((key) => {
21
+ return {
22
+ reducer: score.reducer,
23
+ metric: {
24
+ name: key,
25
+ value: score.metrics[key].value,
26
+ options: {},
27
+ metadata: {},
28
+ },
29
+ };
30
+ });
31
+ });
32
+
33
+ const metrics = Object.values(scorers)[0];
34
+ return (
35
+ <div className={styles.simpleMetricsRows}>
36
+ {metrics.map((metric, i) => {
37
+ return <VerticalMetric metricSummary={metric} isFirst={i === 0} />;
38
+ })}
39
+ </div>
40
+ );
41
+ } else {
42
+ return (
43
+ <div className={styles.multiMetricsRows}>
44
+ {results?.scores?.map((score, index) => {
45
+ return <MultiScorerMetric scorer={score} isFirst={index === 0} />;
46
+ })}
47
+ </div>
48
+ );
49
+ }
50
+ };
51
+
52
+ interface VerticalMetricProps {
53
+ metricSummary: MetricSummary;
54
+ isFirst: boolean;
55
+ }
56
+
57
+ /** Renders a Vertical Metric
58
+ */
59
+ const VerticalMetric: React.FC<VerticalMetricProps> = ({
60
+ metricSummary,
61
+ isFirst,
62
+ }) => {
63
+ const reducer_component = metricSummary.reducer ? (
64
+ <div
65
+ className={clsx(
66
+ "text-style-label",
67
+ "text-style-secondary",
68
+ styles.verticalMetricReducer,
69
+ )}
70
+ >
71
+ {metricSummary.reducer}
72
+ </div>
73
+ ) : (
74
+ ""
75
+ );
76
+
77
+ return (
78
+ <div style={{ paddingLeft: isFirst ? "0" : "1em" }}>
79
+ <div
80
+ className={clsx(
81
+ "vertical-metric-label",
82
+ "text-style-label",
83
+ "text-style-secondary",
84
+ styles.verticalMetricName,
85
+ )}
86
+ >
87
+ {metricSummary.metric.name}
88
+ </div>
89
+ {reducer_component}
90
+ <div
91
+ className={clsx("vertical-metric-value", styles.verticalMetricValue)}
92
+ >
93
+ {formatPrettyDecimal(metricSummary.metric.value)}
94
+ </div>
95
+ </div>
96
+ );
97
+ };
98
+
99
+ interface MultiScorerMetricProps {
100
+ scorer: EvalScore;
101
+ isFirst: boolean;
102
+ }
103
+
104
+ const MultiScorerMetric: React.FC<MultiScorerMetricProps> = ({
105
+ scorer,
106
+ isFirst,
107
+ }) => {
108
+ const titleFontClz = "text-size-base";
109
+ const reducerFontClz = "text-size-smaller";
110
+ const valueFontClz = "text-size-base";
111
+
112
+ const reducer_component = scorer.reducer ? (
113
+ <div
114
+ className={clsx(
115
+ reducerFontClz,
116
+ "text-style-label",
117
+ "text-style-secondary",
118
+ styles.multiScorerReducer,
119
+ )}
120
+ >
121
+ {scorer.reducer}
122
+ </div>
123
+ ) : (
124
+ ""
125
+ );
126
+
127
+ return (
128
+ <div style={{ paddingLeft: isFirst ? "0" : "1.5em" }}>
129
+ <div
130
+ className={clsx(
131
+ titleFontClz,
132
+ "text-style-label",
133
+ "text-style-secondary",
134
+ "multi-score-label",
135
+ styles.multiScorerLabel,
136
+ )}
137
+ >
138
+ {scorer.name}
139
+ </div>
140
+ {reducer_component}
141
+ <div className={clsx(valueFontClz, styles.multiScorerValue)}>
142
+ {Object.keys(scorer.metrics).map((key) => {
143
+ const metric = scorer.metrics[key];
144
+ return (
145
+ <div>
146
+ <div>{metric.name}</div>
147
+ <div className={styles.multiScorerValueContent}>
148
+ {formatPrettyDecimal(metric.value)}
149
+ </div>
150
+ </div>
151
+ );
152
+ })}
153
+ </div>
154
+ </div>
155
+ );
156
+ };