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.
- inspect_ai/_cli/cache.py +8 -7
- inspect_ai/_cli/common.py +0 -12
- inspect_ai/_cli/eval.py +32 -4
- inspect_ai/_cli/info.py +1 -0
- inspect_ai/_cli/list.py +1 -1
- inspect_ai/_cli/log.py +2 -0
- inspect_ai/_cli/main.py +1 -1
- inspect_ai/_cli/sandbox.py +4 -1
- inspect_ai/_cli/score.py +181 -32
- inspect_ai/_cli/trace.py +10 -0
- inspect_ai/_cli/view.py +4 -2
- inspect_ai/_display/core/active.py +2 -3
- inspect_ai/_display/core/config.py +7 -1
- inspect_ai/_display/textual/widgets/samples.py +4 -3
- inspect_ai/_display/textual/widgets/sandbox.py +6 -0
- inspect_ai/_eval/eval.py +104 -101
- inspect_ai/_eval/evalset.py +75 -75
- inspect_ai/_eval/loader.py +122 -12
- inspect_ai/_eval/registry.py +1 -1
- inspect_ai/_eval/run.py +14 -0
- inspect_ai/_eval/score.py +125 -36
- inspect_ai/_eval/task/log.py +105 -4
- inspect_ai/_eval/task/results.py +92 -38
- inspect_ai/_eval/task/run.py +9 -2
- inspect_ai/_eval/task/sandbox.py +35 -2
- inspect_ai/_eval/task/task.py +49 -46
- inspect_ai/_util/constants.py +1 -1
- inspect_ai/_util/content.py +8 -0
- inspect_ai/_util/error.py +2 -0
- inspect_ai/_util/file.py +15 -1
- inspect_ai/_util/hash.py +1 -1
- inspect_ai/_util/logger.py +4 -2
- inspect_ai/_util/registry.py +7 -1
- inspect_ai/_view/view.py +1 -2
- inspect_ai/_view/www/.vscode/extensions.json +3 -0
- inspect_ai/_view/www/.vscode/settings.json +8 -0
- inspect_ai/_view/www/App.css +97 -29
- inspect_ai/_view/www/README.md +1 -1
- inspect_ai/_view/www/dist/assets/index.css +16663 -14674
- inspect_ai/_view/www/dist/assets/index.js +58808 -51348
- inspect_ai/_view/www/dist/index.html +1 -1
- inspect_ai/_view/www/index.html +2 -2
- inspect_ai/_view/www/log-schema.json +87 -73
- inspect_ai/_view/www/package.json +22 -4
- inspect_ai/_view/www/postcss.config.cjs +8 -9
- inspect_ai/_view/www/src/{App.mjs → App.tsx} +356 -365
- inspect_ai/_view/www/src/AppErrorBoundary.tsx +47 -0
- inspect_ai/_view/www/src/api/api-browser.ts +2 -2
- inspect_ai/_view/www/src/api/api-http.ts +3 -5
- inspect_ai/_view/www/src/api/api-vscode.ts +6 -6
- inspect_ai/_view/www/src/api/client-api.ts +4 -4
- inspect_ai/_view/www/src/api/index.ts +4 -4
- inspect_ai/_view/www/src/api/{Types.ts → types.ts} +25 -9
- inspect_ai/_view/www/src/appearance/colors.ts +9 -0
- inspect_ai/_view/www/src/appearance/fonts.ts +39 -0
- inspect_ai/_view/www/src/appearance/icons.ts +100 -0
- inspect_ai/_view/www/src/appearance/{Styles.mjs → styles.ts} +2 -32
- inspect_ai/_view/www/src/components/AnsiDisplay.tsx +198 -0
- inspect_ai/_view/www/src/components/AsciinemaPlayer.tsx +86 -0
- inspect_ai/_view/www/src/components/Card.css +60 -0
- inspect_ai/_view/www/src/components/Card.tsx +109 -0
- inspect_ai/_view/www/src/components/CopyButton.module.css +11 -0
- inspect_ai/_view/www/src/components/CopyButton.tsx +58 -0
- inspect_ai/_view/www/src/components/DownloadButton.css +4 -0
- inspect_ai/_view/www/src/components/DownloadButton.tsx +25 -0
- inspect_ai/_view/www/src/components/DownloadPanel.css +10 -0
- inspect_ai/_view/www/src/components/DownloadPanel.tsx +30 -0
- inspect_ai/_view/www/src/components/EmptyPanel.css +12 -0
- inspect_ai/_view/www/src/components/EmptyPanel.tsx +15 -0
- inspect_ai/_view/www/src/components/ErrorPanel.css +37 -0
- inspect_ai/_view/www/src/components/ErrorPanel.tsx +39 -0
- inspect_ai/_view/www/src/components/ExpandablePanel.css +40 -0
- inspect_ai/_view/www/src/components/ExpandablePanel.tsx +115 -0
- inspect_ai/_view/www/src/components/FindBand.css +49 -0
- inspect_ai/_view/www/src/components/FindBand.tsx +130 -0
- inspect_ai/_view/www/src/components/HumanBaselineView.css +41 -0
- inspect_ai/_view/www/src/components/HumanBaselineView.tsx +162 -0
- inspect_ai/_view/www/src/components/JsonPanel.css +20 -0
- inspect_ai/_view/www/src/components/JsonPanel.tsx +82 -0
- inspect_ai/_view/www/src/components/LabeledValue.css +20 -0
- inspect_ai/_view/www/src/components/LabeledValue.tsx +41 -0
- inspect_ai/_view/www/src/components/LargeModal.module.css +54 -0
- inspect_ai/_view/www/src/components/LargeModal.tsx +189 -0
- inspect_ai/_view/www/src/components/LightboxCarousel.css +95 -0
- inspect_ai/_view/www/src/components/LightboxCarousel.tsx +132 -0
- inspect_ai/_view/www/src/components/MarkdownDiv.css +3 -0
- inspect_ai/_view/www/src/components/MarkdownDiv.tsx +133 -0
- inspect_ai/_view/www/src/components/MessageBand.css +43 -0
- inspect_ai/_view/www/src/components/MessageBand.tsx +39 -0
- inspect_ai/_view/www/src/components/MorePopOver.css +0 -0
- inspect_ai/_view/www/src/components/MorePopOver.tsx +67 -0
- inspect_ai/_view/www/src/components/NavPills.module.css +18 -0
- inspect_ai/_view/www/src/components/NavPills.tsx +101 -0
- inspect_ai/_view/www/src/components/ProgressBar.module.css +37 -0
- inspect_ai/_view/www/src/components/ProgressBar.tsx +22 -0
- inspect_ai/_view/www/src/components/TabSet.module.css +40 -0
- inspect_ai/_view/www/src/components/TabSet.tsx +215 -0
- inspect_ai/_view/www/src/components/ToolButton.css +3 -0
- inspect_ai/_view/www/src/components/ToolButton.tsx +27 -0
- inspect_ai/_view/www/src/components/VirtualList.module.css +19 -0
- inspect_ai/_view/www/src/components/VirtualList.tsx +292 -0
- inspect_ai/_view/www/src/{index.js → index.tsx} +45 -19
- inspect_ai/_view/www/src/{log → logfile}/remoteLogFile.ts +3 -8
- inspect_ai/_view/www/src/{utils/remoteZipFile.mjs → logfile/remoteZipFile.ts} +86 -80
- inspect_ai/_view/www/src/metadata/MetaDataGrid.tsx +83 -0
- inspect_ai/_view/www/src/metadata/MetaDataView.module.css +35 -0
- inspect_ai/_view/www/src/metadata/MetaDataView.tsx +95 -0
- inspect_ai/_view/www/src/metadata/MetadataGrid.module.css +15 -0
- inspect_ai/_view/www/src/metadata/RenderedContent.module.css +12 -0
- inspect_ai/_view/www/src/{components/RenderedContent/RenderedContent.mjs → metadata/RenderedContent.tsx} +92 -73
- inspect_ai/_view/www/src/metadata/types.ts +18 -0
- inspect_ai/_view/www/src/plan/DatasetDetailView.module.css +3 -0
- inspect_ai/_view/www/src/plan/DatasetDetailView.tsx +37 -0
- inspect_ai/_view/www/src/plan/DetailStep.module.css +9 -0
- inspect_ai/_view/www/src/plan/DetailStep.tsx +31 -0
- inspect_ai/_view/www/src/plan/PlanCard.tsx +28 -0
- inspect_ai/_view/www/src/plan/PlanDetailView.module.css +48 -0
- inspect_ai/_view/www/src/plan/PlanDetailView.tsx +324 -0
- inspect_ai/_view/www/src/plan/ScorerDetailView.module.css +3 -0
- inspect_ai/_view/www/src/plan/ScorerDetailView.tsx +30 -0
- inspect_ai/_view/www/src/plan/SolverDetailView.module.css +15 -0
- inspect_ai/_view/www/src/plan/SolverDetailView.tsx +32 -0
- inspect_ai/_view/www/src/samples/InlineSampleDisplay.module.css +8 -0
- inspect_ai/_view/www/src/samples/InlineSampleDisplay.tsx +53 -0
- inspect_ai/_view/www/src/samples/SampleDialog.tsx +122 -0
- inspect_ai/_view/www/src/samples/SampleDisplay.module.css +29 -0
- inspect_ai/_view/www/src/samples/SampleDisplay.tsx +331 -0
- inspect_ai/_view/www/src/samples/SampleSummaryView.module.css +24 -0
- inspect_ai/_view/www/src/samples/SampleSummaryView.tsx +177 -0
- inspect_ai/_view/www/src/samples/SamplesTools.tsx +52 -0
- inspect_ai/_view/www/src/samples/chat/ChatMessage.module.css +29 -0
- inspect_ai/_view/www/src/samples/chat/ChatMessage.tsx +76 -0
- inspect_ai/_view/www/src/samples/chat/ChatMessageRenderer.tsx +60 -0
- inspect_ai/_view/www/src/samples/chat/ChatMessageRow.module.css +9 -0
- inspect_ai/_view/www/src/samples/chat/ChatMessageRow.tsx +57 -0
- inspect_ai/_view/www/src/samples/chat/ChatView.tsx +47 -0
- inspect_ai/_view/www/src/samples/chat/ChatViewVirtualList.module.css +4 -0
- inspect_ai/_view/www/src/samples/chat/ChatViewVirtualList.tsx +58 -0
- inspect_ai/_view/www/src/samples/chat/MessageContent.module.css +4 -0
- inspect_ai/_view/www/src/samples/chat/MessageContent.tsx +157 -0
- inspect_ai/_view/www/src/samples/chat/MessageContents.module.css +3 -0
- inspect_ai/_view/www/src/samples/chat/MessageContents.tsx +133 -0
- inspect_ai/_view/www/src/samples/chat/messages.ts +112 -0
- inspect_ai/_view/www/src/samples/chat/tools/ToolCallView.tsx +147 -0
- inspect_ai/_view/www/src/samples/chat/tools/ToolInput.module.css +14 -0
- inspect_ai/_view/www/src/samples/chat/tools/ToolInput.tsx +76 -0
- inspect_ai/_view/www/src/samples/chat/tools/ToolOutput.module.css +19 -0
- inspect_ai/_view/www/src/samples/chat/tools/ToolOutput.tsx +60 -0
- inspect_ai/_view/www/src/samples/chat/tools/ToolTitle.module.css +4 -0
- inspect_ai/_view/www/src/samples/chat/tools/ToolTitle.tsx +18 -0
- inspect_ai/_view/www/src/samples/chat/tools/tool.ts +92 -0
- inspect_ai/_view/www/src/samples/descriptor/samplesDescriptor.tsx +365 -0
- inspect_ai/_view/www/src/samples/descriptor/score/BooleanScoreDescriptor.module.css +22 -0
- inspect_ai/_view/www/src/samples/descriptor/score/BooleanScoreDescriptor.tsx +26 -0
- inspect_ai/_view/www/src/samples/descriptor/score/CategoricalScoreDescriptor.tsx +18 -0
- inspect_ai/_view/www/src/samples/descriptor/score/NumericScoreDescriptor.tsx +27 -0
- inspect_ai/_view/www/src/samples/descriptor/score/ObjectScoreDescriptor.module.css +18 -0
- inspect_ai/_view/www/src/samples/descriptor/score/ObjectScoreDescriptor.tsx +71 -0
- inspect_ai/_view/www/src/samples/descriptor/score/OtherScoreDescriptor.tsx +20 -0
- inspect_ai/_view/www/src/samples/descriptor/score/PassFailScoreDescriptor.module.css +28 -0
- inspect_ai/_view/www/src/samples/descriptor/score/PassFailScoreDescriptor.tsx +81 -0
- inspect_ai/_view/www/src/samples/descriptor/score/ScoreDescriptor.tsx +99 -0
- inspect_ai/_view/www/src/samples/descriptor/types.ts +55 -0
- inspect_ai/_view/www/src/samples/error/FlatSampleErrorView.module.css +19 -0
- inspect_ai/_view/www/src/samples/error/FlatSampleErrorView.tsx +22 -0
- inspect_ai/_view/www/src/samples/error/SampleErrorView.module.css +17 -0
- inspect_ai/_view/www/src/samples/error/SampleErrorView.tsx +31 -0
- inspect_ai/_view/www/src/samples/error/error.ts +15 -0
- inspect_ai/_view/www/src/samples/list/SampleFooter.module.css +9 -0
- inspect_ai/_view/www/src/samples/list/SampleFooter.tsx +14 -0
- inspect_ai/_view/www/src/samples/list/SampleHeader.module.css +13 -0
- inspect_ai/_view/www/src/samples/list/SampleHeader.tsx +36 -0
- inspect_ai/_view/www/src/samples/list/SampleList.module.css +11 -0
- inspect_ai/_view/www/src/samples/list/SampleList.tsx +247 -0
- inspect_ai/_view/www/src/samples/list/SampleRow.module.css +33 -0
- inspect_ai/_view/www/src/samples/list/SampleRow.tsx +98 -0
- inspect_ai/_view/www/src/samples/list/SampleSeparator.module.css +6 -0
- inspect_ai/_view/www/src/samples/list/SampleSeparator.tsx +24 -0
- inspect_ai/_view/www/src/samples/sample-tools/EpochFilter.module.css +9 -0
- inspect_ai/_view/www/src/samples/sample-tools/EpochFilter.tsx +51 -0
- inspect_ai/_view/www/src/samples/sample-tools/SelectScorer.module.css +16 -0
- inspect_ai/_view/www/src/samples/sample-tools/SelectScorer.tsx +175 -0
- inspect_ai/_view/www/src/samples/sample-tools/SortFilter.module.css +9 -0
- inspect_ai/_view/www/src/samples/sample-tools/SortFilter.tsx +186 -0
- inspect_ai/_view/www/src/samples/{tools/filters.mjs → sample-tools/filters.ts} +86 -81
- inspect_ai/_view/www/src/samples/sample-tools/sample-filter/SampleFilter.module.css +16 -0
- inspect_ai/_view/www/src/samples/sample-tools/sample-filter/SampleFilter.tsx +288 -0
- inspect_ai/_view/www/src/samples/sample-tools/sample-filter/completions.ts +346 -0
- inspect_ai/_view/www/src/samples/sample-tools/sample-filter/language.ts +19 -0
- inspect_ai/_view/www/src/samples/sample-tools/sample-filter/tokenize.ts +97 -0
- inspect_ai/_view/www/src/samples/{SampleLimit.mjs → sampleLimit.ts} +3 -6
- inspect_ai/_view/www/src/samples/scores/SampleScoreView.module.css +53 -0
- inspect_ai/_view/www/src/samples/scores/SampleScoreView.tsx +168 -0
- inspect_ai/_view/www/src/samples/scores/SampleScores.module.css +5 -0
- inspect_ai/_view/www/src/samples/scores/SampleScores.tsx +37 -0
- inspect_ai/_view/www/src/samples/transcript/ApprovalEventView.tsx +66 -0
- inspect_ai/_view/www/src/samples/transcript/ErrorEventView.tsx +51 -0
- inspect_ai/_view/www/src/samples/transcript/InfoEventView.module.css +3 -0
- inspect_ai/_view/www/src/samples/transcript/InfoEventView.tsx +54 -0
- inspect_ai/_view/www/src/samples/transcript/InputEventView.tsx +48 -0
- inspect_ai/_view/www/src/samples/transcript/LoggerEventView.module.css +6 -0
- inspect_ai/_view/www/src/samples/transcript/LoggerEventView.tsx +36 -0
- inspect_ai/_view/www/src/samples/transcript/ModelEventView.module.css +43 -0
- inspect_ai/_view/www/src/samples/transcript/ModelEventView.tsx +223 -0
- inspect_ai/_view/www/src/samples/transcript/SampleInitEventView.module.css +23 -0
- inspect_ai/_view/www/src/samples/transcript/SampleInitEventView.tsx +112 -0
- inspect_ai/_view/www/src/samples/transcript/SampleLimitEventView.tsx +75 -0
- inspect_ai/_view/www/src/samples/transcript/SampleTranscript.tsx +22 -0
- inspect_ai/_view/www/src/samples/transcript/ScoreEventView.module.css +15 -0
- inspect_ai/_view/www/src/samples/transcript/ScoreEventView.tsx +100 -0
- inspect_ai/_view/www/src/samples/transcript/StepEventView.tsx +171 -0
- inspect_ai/_view/www/src/samples/transcript/SubtaskEventView.module.css +19 -0
- inspect_ai/_view/www/src/samples/transcript/SubtaskEventView.tsx +133 -0
- inspect_ai/_view/www/src/samples/transcript/ToolEventView.module.css +10 -0
- inspect_ai/_view/www/src/samples/transcript/ToolEventView.tsx +92 -0
- inspect_ai/_view/www/src/samples/transcript/TranscriptView.module.css +49 -0
- inspect_ai/_view/www/src/samples/transcript/TranscriptView.tsx +449 -0
- inspect_ai/_view/www/src/samples/transcript/event/EventNav.module.css +5 -0
- inspect_ai/_view/www/src/samples/transcript/event/EventNav.tsx +43 -0
- inspect_ai/_view/www/src/samples/transcript/event/EventNavs.module.css +3 -0
- inspect_ai/_view/www/src/samples/transcript/event/EventNavs.tsx +39 -0
- inspect_ai/_view/www/src/samples/transcript/event/EventPanel.module.css +25 -0
- inspect_ai/_view/www/src/samples/transcript/event/EventPanel.tsx +191 -0
- inspect_ai/_view/www/src/samples/transcript/event/EventRow.module.css +13 -0
- inspect_ai/_view/www/src/samples/transcript/event/EventRow.tsx +32 -0
- inspect_ai/_view/www/src/samples/transcript/event/EventSection.module.css +8 -0
- inspect_ai/_view/www/src/samples/transcript/event/EventSection.tsx +29 -0
- inspect_ai/_view/www/src/samples/transcript/state/StateDiffView.tsx +67 -0
- inspect_ai/_view/www/src/samples/transcript/state/StateEventRenderers.tsx +285 -0
- inspect_ai/_view/www/src/samples/transcript/state/StateEventRenders.module.css +10 -0
- inspect_ai/_view/www/src/samples/transcript/state/StateEventView.module.css +9 -0
- inspect_ai/_view/www/src/samples/transcript/state/StateEventView.tsx +346 -0
- inspect_ai/_view/www/src/samples/transcript/types.ts +58 -0
- inspect_ai/_view/www/src/types/log.d.ts +108 -19
- inspect_ai/_view/www/src/types/prism.d.ts +11 -0
- inspect_ai/_view/www/src/types.ts +71 -0
- inspect_ai/_view/www/src/usage/ModelTokenTable.tsx +28 -0
- inspect_ai/_view/www/src/usage/ModelUsagePanel.module.css +24 -0
- inspect_ai/_view/www/src/usage/ModelUsagePanel.tsx +97 -0
- inspect_ai/_view/www/src/usage/TokenTable.module.css +17 -0
- inspect_ai/_view/www/src/usage/TokenTable.tsx +91 -0
- inspect_ai/_view/www/src/usage/UsageCard.module.css +15 -0
- inspect_ai/_view/www/src/usage/UsageCard.tsx +67 -0
- inspect_ai/_view/www/src/utils/attachments.ts +42 -0
- inspect_ai/_view/www/src/utils/{Base64.mjs → base64.ts} +1 -6
- inspect_ai/_view/www/src/{components/Browser.mjs → utils/browser.ts} +0 -1
- inspect_ai/_view/www/src/utils/debugging.ts +28 -0
- inspect_ai/_view/www/src/utils/dom.ts +30 -0
- inspect_ai/_view/www/src/utils/format.ts +194 -0
- inspect_ai/_view/www/src/utils/git.ts +7 -0
- inspect_ai/_view/www/src/utils/html.ts +6 -0
- inspect_ai/_view/www/src/utils/http.ts +14 -0
- inspect_ai/_view/www/src/utils/{Path.mjs → path.ts} +2 -9
- inspect_ai/_view/www/src/utils/{Print.mjs → print.ts} +34 -26
- inspect_ai/_view/www/src/utils/queue.ts +51 -0
- inspect_ai/_view/www/src/utils/sync.ts +114 -0
- inspect_ai/_view/www/src/utils/{Type.mjs → type.ts} +3 -6
- inspect_ai/_view/www/src/utils/vscode.ts +13 -0
- inspect_ai/_view/www/src/workspace/WorkSpace.tsx +324 -0
- inspect_ai/_view/www/src/workspace/WorkSpaceView.module.css +33 -0
- inspect_ai/_view/www/src/workspace/WorkSpaceView.tsx +158 -0
- inspect_ai/_view/www/src/workspace/error/TaskErrorPanel.module.css +3 -0
- inspect_ai/_view/www/src/workspace/error/TaskErrorPanel.tsx +28 -0
- inspect_ai/_view/www/src/workspace/navbar/Navbar.module.css +54 -0
- inspect_ai/_view/www/src/workspace/navbar/Navbar.tsx +68 -0
- inspect_ai/_view/www/src/workspace/navbar/PrimaryBar.module.css +52 -0
- inspect_ai/_view/www/src/workspace/navbar/PrimaryBar.tsx +114 -0
- inspect_ai/_view/www/src/workspace/navbar/ResultsPanel.module.css +90 -0
- inspect_ai/_view/www/src/workspace/navbar/ResultsPanel.tsx +180 -0
- inspect_ai/_view/www/src/workspace/navbar/SecondaryBar.module.css +28 -0
- inspect_ai/_view/www/src/workspace/navbar/SecondaryBar.tsx +226 -0
- inspect_ai/_view/www/src/workspace/navbar/StatusPanel.module.css +14 -0
- inspect_ai/_view/www/src/workspace/navbar/StatusPanel.tsx +61 -0
- inspect_ai/_view/www/src/workspace/sidebar/EvalStatus.module.css +15 -0
- inspect_ai/_view/www/src/workspace/sidebar/EvalStatus.tsx +71 -0
- inspect_ai/_view/www/src/workspace/sidebar/LogDirectoryTitleView.module.css +5 -0
- inspect_ai/_view/www/src/workspace/sidebar/LogDirectoryTitleView.tsx +56 -0
- inspect_ai/_view/www/src/workspace/sidebar/Sidebar.module.css +68 -0
- inspect_ai/_view/www/src/workspace/sidebar/Sidebar.tsx +85 -0
- inspect_ai/_view/www/src/workspace/sidebar/SidebarLogEntry.module.css +29 -0
- inspect_ai/_view/www/src/workspace/sidebar/SidebarLogEntry.tsx +95 -0
- inspect_ai/_view/www/src/workspace/sidebar/SidebarScoreView.module.css +23 -0
- inspect_ai/_view/www/src/workspace/sidebar/SidebarScoreView.tsx +43 -0
- inspect_ai/_view/www/src/workspace/sidebar/SidebarScoresView.module.css +35 -0
- inspect_ai/_view/www/src/workspace/sidebar/SidebarScoresView.tsx +63 -0
- inspect_ai/_view/www/src/workspace/tabs/InfoTab.module.css +0 -0
- inspect_ai/_view/www/src/workspace/tabs/InfoTab.tsx +70 -0
- inspect_ai/_view/www/src/workspace/tabs/JsonTab.module.css +5 -0
- inspect_ai/_view/www/src/workspace/tabs/JsonTab.tsx +46 -0
- inspect_ai/_view/www/src/workspace/tabs/SamplesTab.tsx +204 -0
- inspect_ai/_view/www/src/workspace/tabs/grouping.ts +195 -0
- inspect_ai/_view/www/src/workspace/tabs/types.ts +19 -0
- inspect_ai/_view/www/src/workspace/types.ts +10 -0
- inspect_ai/_view/www/src/workspace/utils.ts +34 -0
- inspect_ai/_view/www/tsconfig.json +23 -9
- inspect_ai/_view/www/vite.config.js +8 -17
- inspect_ai/_view/www/yarn.lock +627 -556
- inspect_ai/approval/_approval.py +2 -0
- inspect_ai/approval/_approver.py +4 -4
- inspect_ai/approval/_auto.py +1 -1
- inspect_ai/approval/_human/approver.py +3 -0
- inspect_ai/approval/_policy.py +5 -0
- inspect_ai/approval/_registry.py +2 -2
- inspect_ai/dataset/_dataset.py +64 -37
- inspect_ai/dataset/_sources/__init__.py +0 -0
- inspect_ai/dataset/_sources/csv.py +20 -12
- inspect_ai/dataset/_sources/file.py +4 -0
- inspect_ai/dataset/_sources/hf.py +39 -29
- inspect_ai/dataset/_sources/json.py +17 -9
- inspect_ai/log/__init__.py +2 -0
- inspect_ai/log/_convert.py +3 -3
- inspect_ai/log/_file.py +24 -9
- inspect_ai/log/_log.py +101 -13
- inspect_ai/log/_message.py +4 -2
- inspect_ai/log/_recorders/file.py +4 -0
- inspect_ai/log/_recorders/json.py +5 -7
- inspect_ai/log/_recorders/recorder.py +3 -0
- inspect_ai/log/_transcript.py +19 -8
- inspect_ai/model/__init__.py +2 -0
- inspect_ai/model/_cache.py +39 -21
- inspect_ai/model/_call_tools.py +4 -3
- inspect_ai/model/_chat_message.py +14 -4
- inspect_ai/model/_generate_config.py +1 -1
- inspect_ai/model/_model.py +31 -24
- inspect_ai/model/_model_output.py +14 -1
- inspect_ai/model/_openai.py +10 -18
- inspect_ai/model/_providers/anthropic.py +3 -3
- inspect_ai/model/_providers/google.py +9 -5
- inspect_ai/model/_providers/openai.py +5 -9
- inspect_ai/model/_providers/openai_o1.py +3 -5
- inspect_ai/model/_providers/openrouter.py +86 -0
- inspect_ai/model/_providers/providers.py +11 -0
- inspect_ai/scorer/__init__.py +6 -1
- inspect_ai/scorer/_answer.py +7 -7
- inspect_ai/scorer/_classification.py +38 -18
- inspect_ai/scorer/_common.py +2 -8
- inspect_ai/scorer/_match.py +4 -5
- inspect_ai/scorer/_metric.py +87 -28
- inspect_ai/scorer/_metrics/__init__.py +3 -3
- inspect_ai/scorer/_metrics/accuracy.py +8 -10
- inspect_ai/scorer/_metrics/mean.py +3 -17
- inspect_ai/scorer/_metrics/std.py +111 -30
- inspect_ai/scorer/_model.py +12 -12
- inspect_ai/scorer/_pattern.py +3 -3
- inspect_ai/scorer/_reducer/reducer.py +36 -21
- inspect_ai/scorer/_reducer/registry.py +2 -2
- inspect_ai/scorer/_reducer/types.py +7 -1
- inspect_ai/scorer/_score.py +11 -1
- inspect_ai/scorer/_scorer.py +110 -16
- inspect_ai/solver/__init__.py +1 -1
- inspect_ai/solver/_basic_agent.py +19 -22
- inspect_ai/solver/_bridge/__init__.py +0 -3
- inspect_ai/solver/_bridge/bridge.py +3 -3
- inspect_ai/solver/_chain.py +1 -2
- inspect_ai/solver/_critique.py +3 -3
- inspect_ai/solver/_fork.py +2 -2
- inspect_ai/solver/_human_agent/__init__.py +0 -0
- inspect_ai/solver/_human_agent/agent.py +5 -8
- inspect_ai/solver/_human_agent/commands/clock.py +14 -10
- inspect_ai/solver/_human_agent/commands/note.py +1 -1
- inspect_ai/solver/_human_agent/commands/score.py +0 -11
- inspect_ai/solver/_multiple_choice.py +38 -26
- inspect_ai/solver/_prompt.py +7 -7
- inspect_ai/solver/_solver.py +53 -52
- inspect_ai/solver/_task_state.py +80 -69
- inspect_ai/solver/_use_tools.py +9 -9
- inspect_ai/tool/__init__.py +4 -1
- inspect_ai/tool/_tool.py +43 -14
- inspect_ai/tool/_tool_call.py +6 -2
- inspect_ai/tool/_tool_choice.py +3 -1
- inspect_ai/tool/_tool_def.py +10 -8
- inspect_ai/tool/_tool_params.py +24 -0
- inspect_ai/tool/_tool_with.py +7 -7
- inspect_ai/tool/_tools/__init__.py +0 -0
- inspect_ai/tool/{beta → _tools}/_computer/_common.py +2 -2
- inspect_ai/tool/{beta → _tools}/_computer/_computer.py +13 -5
- inspect_ai/tool/_tools/_computer/_resources/tool/__init__.py +0 -0
- inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_x11_client.py +1 -1
- inspect_ai/tool/_tools/_computer/_resources/tool/requirements.txt +0 -0
- inspect_ai/tool/_tools/_execute.py +23 -11
- inspect_ai/tool/_tools/_web_browser/_resources/README.md +2 -2
- inspect_ai/tool/_tools/_web_browser/_web_browser.py +5 -3
- inspect_ai/tool/_tools/_web_search.py +7 -5
- inspect_ai/tool/beta.py +3 -0
- inspect_ai/util/_concurrency.py +3 -3
- inspect_ai/util/_panel.py +2 -0
- inspect_ai/util/_resource.py +12 -12
- inspect_ai/util/_sandbox/docker/compose.py +23 -20
- inspect_ai/util/_sandbox/docker/config.py +2 -1
- inspect_ai/util/_sandbox/docker/docker.py +42 -86
- inspect_ai/util/_sandbox/docker/service.py +100 -0
- inspect_ai/util/_sandbox/environment.py +99 -96
- inspect_ai/util/_sandbox/self_check.py +124 -16
- inspect_ai/util/_subprocess.py +5 -3
- inspect_ai/util/_subtask.py +15 -16
- {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.64.dist-info}/LICENSE +1 -1
- {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.64.dist-info}/METADATA +11 -6
- inspect_ai-0.3.64.dist-info/RECORD +625 -0
- inspect_ai/_view/www/src/Register.mjs +0 -3
- inspect_ai/_view/www/src/Types.mjs +0 -38
- inspect_ai/_view/www/src/appearance/Colors.mjs +0 -27
- inspect_ai/_view/www/src/appearance/Fonts.mjs +0 -66
- inspect_ai/_view/www/src/appearance/Icons.mjs +0 -240
- inspect_ai/_view/www/src/components/AnsiDisplay.mjs +0 -184
- inspect_ai/_view/www/src/components/AppErrorBoundary.mjs +0 -34
- inspect_ai/_view/www/src/components/AsciiCinemaPlayer.mjs +0 -74
- inspect_ai/_view/www/src/components/Card.mjs +0 -126
- inspect_ai/_view/www/src/components/ChatView.mjs +0 -441
- inspect_ai/_view/www/src/components/CopyButton.mjs +0 -48
- inspect_ai/_view/www/src/components/Dialog.mjs +0 -61
- inspect_ai/_view/www/src/components/DownloadButton.mjs +0 -15
- inspect_ai/_view/www/src/components/DownloadPanel.mjs +0 -29
- inspect_ai/_view/www/src/components/EmptyPanel.mjs +0 -23
- inspect_ai/_view/www/src/components/ErrorPanel.mjs +0 -66
- inspect_ai/_view/www/src/components/ExpandablePanel.mjs +0 -136
- inspect_ai/_view/www/src/components/FindBand.mjs +0 -157
- inspect_ai/_view/www/src/components/HumanBaselineView.mjs +0 -168
- inspect_ai/_view/www/src/components/JsonPanel.mjs +0 -61
- inspect_ai/_view/www/src/components/LabeledValue.mjs +0 -32
- inspect_ai/_view/www/src/components/LargeModal.mjs +0 -190
- inspect_ai/_view/www/src/components/LightboxCarousel.mjs +0 -217
- inspect_ai/_view/www/src/components/MarkdownDiv.mjs +0 -118
- inspect_ai/_view/www/src/components/MessageBand.mjs +0 -48
- inspect_ai/_view/www/src/components/MessageContent.mjs +0 -111
- inspect_ai/_view/www/src/components/MetaDataGrid.mjs +0 -92
- inspect_ai/_view/www/src/components/MetaDataView.mjs +0 -109
- inspect_ai/_view/www/src/components/MorePopOver.mjs +0 -50
- inspect_ai/_view/www/src/components/NavPills.mjs +0 -63
- inspect_ai/_view/www/src/components/ProgressBar.mjs +0 -51
- inspect_ai/_view/www/src/components/RenderedContent/ChatMessageRenderer.mjs +0 -54
- inspect_ai/_view/www/src/components/RenderedContent/Types.mjs +0 -19
- inspect_ai/_view/www/src/components/TabSet.mjs +0 -184
- inspect_ai/_view/www/src/components/ToolButton.mjs +0 -16
- inspect_ai/_view/www/src/components/Tools.mjs +0 -376
- inspect_ai/_view/www/src/components/VirtualList.mjs +0 -280
- inspect_ai/_view/www/src/components/ansi-output.js +0 -932
- inspect_ai/_view/www/src/json/JsonTab.mjs +0 -48
- inspect_ai/_view/www/src/log-reader/Log-Reader.mjs +0 -25
- inspect_ai/_view/www/src/log-reader/Native-Log-Reader.mjs +0 -13
- inspect_ai/_view/www/src/log-reader/Open-AI-Log-Reader.mjs +0 -263
- inspect_ai/_view/www/src/navbar/Navbar.mjs +0 -418
- inspect_ai/_view/www/src/navbar/SecondaryBar.mjs +0 -175
- inspect_ai/_view/www/src/plan/PlanCard.mjs +0 -418
- inspect_ai/_view/www/src/samples/SampleDialog.mjs +0 -123
- inspect_ai/_view/www/src/samples/SampleDisplay.mjs +0 -516
- inspect_ai/_view/www/src/samples/SampleError.mjs +0 -99
- inspect_ai/_view/www/src/samples/SampleList.mjs +0 -427
- inspect_ai/_view/www/src/samples/SampleScoreView.mjs +0 -172
- inspect_ai/_view/www/src/samples/SampleScores.mjs +0 -34
- inspect_ai/_view/www/src/samples/SampleTranscript.mjs +0 -20
- inspect_ai/_view/www/src/samples/SamplesDescriptor.mjs +0 -771
- inspect_ai/_view/www/src/samples/SamplesTab.mjs +0 -399
- inspect_ai/_view/www/src/samples/SamplesTools.mjs +0 -64
- inspect_ai/_view/www/src/samples/tools/EpochFilter.mjs +0 -38
- inspect_ai/_view/www/src/samples/tools/SampleFilter.mjs +0 -756
- inspect_ai/_view/www/src/samples/tools/SelectScorer.mjs +0 -141
- inspect_ai/_view/www/src/samples/tools/SortFilter.mjs +0 -151
- inspect_ai/_view/www/src/samples/transcript/ApprovalEventView.mjs +0 -71
- inspect_ai/_view/www/src/samples/transcript/ErrorEventView.mjs +0 -44
- inspect_ai/_view/www/src/samples/transcript/EventPanel.mjs +0 -271
- inspect_ai/_view/www/src/samples/transcript/EventRow.mjs +0 -46
- inspect_ai/_view/www/src/samples/transcript/EventSection.mjs +0 -33
- inspect_ai/_view/www/src/samples/transcript/InfoEventView.mjs +0 -59
- inspect_ai/_view/www/src/samples/transcript/InputEventView.mjs +0 -44
- inspect_ai/_view/www/src/samples/transcript/LoggerEventView.mjs +0 -32
- inspect_ai/_view/www/src/samples/transcript/ModelEventView.mjs +0 -216
- inspect_ai/_view/www/src/samples/transcript/SampleInitEventView.mjs +0 -107
- inspect_ai/_view/www/src/samples/transcript/SampleLimitEventView.mjs +0 -74
- inspect_ai/_view/www/src/samples/transcript/ScoreEventView.mjs +0 -100
- inspect_ai/_view/www/src/samples/transcript/StepEventView.mjs +0 -187
- inspect_ai/_view/www/src/samples/transcript/SubtaskEventView.mjs +0 -133
- inspect_ai/_view/www/src/samples/transcript/ToolEventView.mjs +0 -88
- inspect_ai/_view/www/src/samples/transcript/TranscriptView.mjs +0 -459
- inspect_ai/_view/www/src/samples/transcript/Types.mjs +0 -44
- inspect_ai/_view/www/src/samples/transcript/state/StateDiffView.mjs +0 -53
- inspect_ai/_view/www/src/samples/transcript/state/StateEventRenderers.mjs +0 -254
- inspect_ai/_view/www/src/samples/transcript/state/StateEventView.mjs +0 -313
- inspect_ai/_view/www/src/sidebar/Sidebar.mjs +0 -418
- inspect_ai/_view/www/src/usage/ModelTokenTable.mjs +0 -72
- inspect_ai/_view/www/src/usage/UsageCard.mjs +0 -159
- inspect_ai/_view/www/src/utils/Format.mjs +0 -260
- inspect_ai/_view/www/src/utils/Git.mjs +0 -12
- inspect_ai/_view/www/src/utils/Html.mjs +0 -21
- inspect_ai/_view/www/src/utils/attachments.mjs +0 -31
- inspect_ai/_view/www/src/utils/debugging.mjs +0 -23
- inspect_ai/_view/www/src/utils/http.mjs +0 -18
- inspect_ai/_view/www/src/utils/queue.mjs +0 -67
- inspect_ai/_view/www/src/utils/sync.mjs +0 -101
- inspect_ai/_view/www/src/workspace/TaskErrorPanel.mjs +0 -17
- inspect_ai/_view/www/src/workspace/WorkSpace.mjs +0 -516
- inspect_ai/tool/beta/__init__.py +0 -5
- inspect_ai-0.3.62.dist-info/RECORD +0 -481
- /inspect_ai/{tool/beta/_computer/_resources/tool → _eval}/__init__.py +0 -0
- /inspect_ai/{tool/beta/_computer/_resources/tool/requirements.txt → _util/__init__.py} +0 -0
- /inspect_ai/_view/www/src/{constants.mjs → constants.ts} +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/__init__.py +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_computer_split.py +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/Dockerfile +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/README.md +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/entrypoint.sh +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/novnc_startup.sh +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/x11vnc_startup.sh +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/xfce_startup.sh +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/entrypoint/xvfb_startup.sh +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/Code/User/globalStorage/state.vscdb +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/Code/User/settings.json +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/xfce4/xfconf/xfce-perchannel-xml/xfce4-panel.xml +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/.config/xfce4/xfconf/xfce-perchannel-xml/xfce4-screensaver.xml +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/Desktop/Firefox Web Browser.desktop +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/Desktop/Terminal.desktop +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/image_home_dir/Desktop/Visual Studio Code.desktop +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_logger.py +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_run.py +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/_tool_result.py +0 -0
- /inspect_ai/tool/{beta → _tools}/_computer/_resources/tool/computer_tool.py +0 -0
- {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.64.dist-info}/WHEEL +0 -0
- {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.64.dist-info}/entry_points.txt +0 -0
- {inspect_ai-0.3.62.dist-info → inspect_ai-0.3.64.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,68 @@
|
|
1
|
+
.sidebar {
|
2
|
+
position: fixed;
|
3
|
+
left: 0;
|
4
|
+
top: 0;
|
5
|
+
width: var(--sidebar-width);
|
6
|
+
height: 100%;
|
7
|
+
background-color: #fff;
|
8
|
+
border-right: 1px solid var(--bs-light-border-subtle);
|
9
|
+
display: flex;
|
10
|
+
flex-direction: column;
|
11
|
+
z-index: 9999; /* Sit above main content */
|
12
|
+
transition: transform 0.3s ease-in-out;
|
13
|
+
}
|
14
|
+
|
15
|
+
.sidebarClosed {
|
16
|
+
transform: translateX(-100%);
|
17
|
+
}
|
18
|
+
|
19
|
+
.sidebarOpen {
|
20
|
+
transform: translateX(0);
|
21
|
+
}
|
22
|
+
|
23
|
+
.header {
|
24
|
+
display: grid;
|
25
|
+
grid-template-columns: minmax(0, 1fr) auto;
|
26
|
+
column-gap: 0.2rem;
|
27
|
+
align-items: center;
|
28
|
+
opacity: 0.7;
|
29
|
+
position: sticky;
|
30
|
+
top: 0;
|
31
|
+
width: var(--sidebar-width);
|
32
|
+
border-bottom: 1px solid var(--bs-light-border-subtle);
|
33
|
+
padding: 0.5rem 0 0.5rem 1rem;
|
34
|
+
height: 3.6em;
|
35
|
+
background-color: #fff;
|
36
|
+
z-index: 10;
|
37
|
+
}
|
38
|
+
|
39
|
+
.toggle {
|
40
|
+
padding: 0.1rem;
|
41
|
+
align-self: end;
|
42
|
+
width: 40px;
|
43
|
+
flex: 0 0 auto;
|
44
|
+
}
|
45
|
+
|
46
|
+
.progress {
|
47
|
+
z-index: 3;
|
48
|
+
}
|
49
|
+
|
50
|
+
.list {
|
51
|
+
flex-grow: 1;
|
52
|
+
overflow-y: auto;
|
53
|
+
}
|
54
|
+
|
55
|
+
.backdrop {
|
56
|
+
position: fixed;
|
57
|
+
inset: 0; /* top: 0; left: 0; right: 0; bottom: 0; */
|
58
|
+
background-color: rgba(0, 0, 0, 0.5);
|
59
|
+
z-index: 9998;
|
60
|
+
}
|
61
|
+
|
62
|
+
.active {
|
63
|
+
background-color: var(--bs-secondary-bg-subtle);
|
64
|
+
}
|
65
|
+
|
66
|
+
.item {
|
67
|
+
cursor: pointer;
|
68
|
+
}
|
@@ -0,0 +1,85 @@
|
|
1
|
+
import clsx from "clsx";
|
2
|
+
import { Fragment } from "react/jsx-runtime";
|
3
|
+
import { EvalLogHeader, LogFiles } from "../../api/types";
|
4
|
+
import { ApplicationIcons } from "../../appearance/icons";
|
5
|
+
import { ProgressBar } from "../../components/ProgressBar";
|
6
|
+
import { LogDirectoryTitleView } from "./LogDirectoryTitleView";
|
7
|
+
import styles from "./Sidebar.module.css";
|
8
|
+
import { SidebarLogEntry } from "./SidebarLogEntry";
|
9
|
+
|
10
|
+
interface SidebarProps {
|
11
|
+
logs: LogFiles;
|
12
|
+
logHeaders: Record<string, EvalLogHeader>;
|
13
|
+
offcanvas: boolean;
|
14
|
+
setOffcanvas: (offcanvas: boolean) => void;
|
15
|
+
loading: boolean;
|
16
|
+
selectedIndex: number;
|
17
|
+
onSelectedIndexChanged: (index: number) => void;
|
18
|
+
}
|
19
|
+
|
20
|
+
export const Sidebar: React.FC<SidebarProps> = ({
|
21
|
+
logs,
|
22
|
+
logHeaders,
|
23
|
+
offcanvas,
|
24
|
+
setOffcanvas,
|
25
|
+
loading,
|
26
|
+
selectedIndex,
|
27
|
+
onSelectedIndexChanged,
|
28
|
+
}) => {
|
29
|
+
const handleToggle = () => {
|
30
|
+
setOffcanvas(!offcanvas);
|
31
|
+
};
|
32
|
+
|
33
|
+
return (
|
34
|
+
<Fragment>
|
35
|
+
{/* Optional backdrop for small screens, appears only when offcanvas is open */}
|
36
|
+
{offcanvas && <div className={styles.backdrop} onClick={handleToggle} />}
|
37
|
+
|
38
|
+
<div
|
39
|
+
className={clsx(
|
40
|
+
styles.sidebar,
|
41
|
+
offcanvas ? styles.sidebarOpen : styles.sidebarClosed,
|
42
|
+
)}
|
43
|
+
>
|
44
|
+
<div className={styles.header}>
|
45
|
+
<LogDirectoryTitleView log_dir={logs.log_dir} offcanvas={offcanvas} />
|
46
|
+
<button
|
47
|
+
onClick={handleToggle}
|
48
|
+
className={clsx("btn", styles.toggle)}
|
49
|
+
type="button"
|
50
|
+
aria-label="Close sidebar"
|
51
|
+
>
|
52
|
+
<i className={ApplicationIcons.close}></i>
|
53
|
+
</button>
|
54
|
+
</div>
|
55
|
+
|
56
|
+
<div className={styles.progress}>
|
57
|
+
<ProgressBar animating={loading} />
|
58
|
+
</div>
|
59
|
+
|
60
|
+
<ul className={clsx("list-group", styles.list)}>
|
61
|
+
{logs.files.map((file, index) => {
|
62
|
+
const logHeader = logHeaders[file.name];
|
63
|
+
return (
|
64
|
+
<li
|
65
|
+
key={file.name}
|
66
|
+
className={clsx(
|
67
|
+
"list-group-item",
|
68
|
+
"list-group-item-action",
|
69
|
+
styles.item,
|
70
|
+
selectedIndex === index ? styles.active : undefined,
|
71
|
+
)}
|
72
|
+
onClick={() => onSelectedIndexChanged(index)}
|
73
|
+
>
|
74
|
+
<SidebarLogEntry
|
75
|
+
logHeader={logHeader}
|
76
|
+
task={file.task || "unknown task"}
|
77
|
+
/>
|
78
|
+
</li>
|
79
|
+
);
|
80
|
+
})}
|
81
|
+
</ul>
|
82
|
+
</div>
|
83
|
+
</Fragment>
|
84
|
+
);
|
85
|
+
};
|
@@ -0,0 +1,29 @@
|
|
1
|
+
.entry {
|
2
|
+
display: flex;
|
3
|
+
flex-direction: row;
|
4
|
+
justify-content: space-between;
|
5
|
+
}
|
6
|
+
|
7
|
+
.title {
|
8
|
+
overflow: hidden;
|
9
|
+
min-width: 33%;
|
10
|
+
}
|
11
|
+
|
12
|
+
.task {
|
13
|
+
white-space: nowrap;
|
14
|
+
overflow: hidden;
|
15
|
+
text-overflow: ellipsis;
|
16
|
+
}
|
17
|
+
|
18
|
+
.params {
|
19
|
+
margin-top: 1em;
|
20
|
+
}
|
21
|
+
|
22
|
+
.scores {
|
23
|
+
width: 100%;
|
24
|
+
display: grid;
|
25
|
+
grid-template-columns: minmax(auto, 1fr) minmax(1fr, 1fr);
|
26
|
+
column-gap: 1rem;
|
27
|
+
justify-content: space-between;
|
28
|
+
margin-top: 0em;
|
29
|
+
}
|
@@ -0,0 +1,95 @@
|
|
1
|
+
import clsx from "clsx";
|
2
|
+
import { Fragment } from "react";
|
3
|
+
import { EvalLogHeader } from "../../api/types";
|
4
|
+
import { EvalStatus } from "./EvalStatus";
|
5
|
+
import styles from "./SidebarLogEntry.module.css";
|
6
|
+
|
7
|
+
interface SidebarLogEntryProps {
|
8
|
+
logHeader?: EvalLogHeader;
|
9
|
+
task: string;
|
10
|
+
}
|
11
|
+
|
12
|
+
export const SidebarLogEntry: React.FC<SidebarLogEntryProps> = ({
|
13
|
+
logHeader,
|
14
|
+
task,
|
15
|
+
}) => {
|
16
|
+
const hyperparameters: Record<string, unknown> = {
|
17
|
+
...(logHeader?.plan?.config || {}),
|
18
|
+
...(logHeader?.eval?.task_args || {}),
|
19
|
+
};
|
20
|
+
|
21
|
+
const model = logHeader?.eval?.model;
|
22
|
+
const datasetName = logHeader?.eval?.dataset.name;
|
23
|
+
|
24
|
+
const uniqScorers = new Set();
|
25
|
+
logHeader?.results?.scores?.forEach((scorer) => {
|
26
|
+
uniqScorers.add(scorer.name);
|
27
|
+
});
|
28
|
+
const scorerNames = Array.from(uniqScorers).join(",");
|
29
|
+
|
30
|
+
const scorerLabel =
|
31
|
+
Object.keys(logHeader?.results?.scores || {}).length === 1
|
32
|
+
? "scorer"
|
33
|
+
: "scorers";
|
34
|
+
|
35
|
+
const completed = logHeader?.stats?.completed_at;
|
36
|
+
const time = completed ? new Date(completed) : undefined;
|
37
|
+
const timeStr = time
|
38
|
+
? `${time.toDateString()}
|
39
|
+
${time.toLocaleTimeString([], {
|
40
|
+
hour: "2-digit",
|
41
|
+
minute: "2-digit",
|
42
|
+
})}`
|
43
|
+
: "";
|
44
|
+
|
45
|
+
return (
|
46
|
+
<Fragment>
|
47
|
+
<div className={styles.entry}>
|
48
|
+
<div className={styles.title}>
|
49
|
+
<div className={clsx(styles.task, "text-size-title-secondary")}>
|
50
|
+
{logHeader?.eval?.task || task}
|
51
|
+
</div>
|
52
|
+
<small className={clsx("mb-1", "text-size-small")}>{timeStr}</small>
|
53
|
+
|
54
|
+
{model ? (
|
55
|
+
<div>
|
56
|
+
<small className={clsx("mb-1", "text-size-small")}>{model}</small>
|
57
|
+
</div>
|
58
|
+
) : (
|
59
|
+
""
|
60
|
+
)}
|
61
|
+
</div>
|
62
|
+
<EvalStatus logHeader={logHeader} />
|
63
|
+
</div>
|
64
|
+
<div className={clsx(styles.params, "three-line-clamp")}>
|
65
|
+
<small className={"mb-1"}>
|
66
|
+
{hyperparameters
|
67
|
+
? Object.keys(hyperparameters)
|
68
|
+
.map((key) => {
|
69
|
+
const val = hyperparameters[key];
|
70
|
+
if (Array.isArray(val) || typeof val === "object") {
|
71
|
+
return `${key}: ${JSON.stringify(val)}`;
|
72
|
+
} else {
|
73
|
+
return `${key}: ${val}`;
|
74
|
+
}
|
75
|
+
})
|
76
|
+
.join(", ")
|
77
|
+
: ""}
|
78
|
+
</small>
|
79
|
+
</div>
|
80
|
+
{(logHeader?.eval?.dataset || logHeader?.results?.scores) &&
|
81
|
+
logHeader?.status === "success" ? (
|
82
|
+
<div
|
83
|
+
className={clsx("text-truncate", "text-size-small", styles.scores)}
|
84
|
+
>
|
85
|
+
<div>dataset: {datasetName || "(samples)"}</div>
|
86
|
+
<div className={clsx("text-truncate", styles.scoreInfo)}>
|
87
|
+
{scorerLabel}: {scorerNames || "(none)"}
|
88
|
+
</div>
|
89
|
+
</div>
|
90
|
+
) : (
|
91
|
+
""
|
92
|
+
)}
|
93
|
+
</Fragment>
|
94
|
+
);
|
95
|
+
};
|
@@ -0,0 +1,23 @@
|
|
1
|
+
.container {
|
2
|
+
display: flex;
|
3
|
+
flex-direction: row;
|
4
|
+
flex-wrap: wrap;
|
5
|
+
justify-content: flex-end;
|
6
|
+
}
|
7
|
+
|
8
|
+
.metric {
|
9
|
+
display: flex;
|
10
|
+
flex-direction: column;
|
11
|
+
align-items: flex-end;
|
12
|
+
margin-left: 1em;
|
13
|
+
margin-bottom: 0.4em;
|
14
|
+
margin-top: 0.5rem;
|
15
|
+
}
|
16
|
+
|
17
|
+
.metricName {
|
18
|
+
margin-bottom: -0.3em;
|
19
|
+
}
|
20
|
+
|
21
|
+
.metricReducer {
|
22
|
+
margin-bottom: -0.2rem;
|
23
|
+
}
|
@@ -0,0 +1,43 @@
|
|
1
|
+
import clsx from "clsx";
|
2
|
+
import { EvalScore } from "../../types/log";
|
3
|
+
import { formatPrettyDecimal } from "../../utils/format";
|
4
|
+
|
5
|
+
import { metricDisplayName } from "../utils";
|
6
|
+
import styles from "./SidebarScoreView.module.css";
|
7
|
+
interface SidebarScoreProps {
|
8
|
+
scorer: EvalScore;
|
9
|
+
}
|
10
|
+
|
11
|
+
export const SidebarScoreView: React.FC<SidebarScoreProps> = ({ scorer }) => {
|
12
|
+
const showReducer = !!scorer.reducer;
|
13
|
+
return (
|
14
|
+
<div className={styles.container}>
|
15
|
+
{Object.keys(scorer.metrics).map((metric) => {
|
16
|
+
return (
|
17
|
+
<div className={styles.metric} key={metric}>
|
18
|
+
<div
|
19
|
+
className={clsx(
|
20
|
+
"text-style-secondary",
|
21
|
+
"text-style-label",
|
22
|
+
"text-size-small",
|
23
|
+
styles.metricName,
|
24
|
+
)}
|
25
|
+
>
|
26
|
+
{metricDisplayName(scorer.metrics[metric])}
|
27
|
+
</div>
|
28
|
+
{showReducer ? (
|
29
|
+
<div className={clsx("text-size-small", styles.metricReducer)}>
|
30
|
+
{scorer.reducer || "default"}
|
31
|
+
</div>
|
32
|
+
) : (
|
33
|
+
""
|
34
|
+
)}
|
35
|
+
<div className={"text-size-title-secondary"}>
|
36
|
+
{formatPrettyDecimal(scorer.metrics[metric].value)}
|
37
|
+
</div>
|
38
|
+
</div>
|
39
|
+
);
|
40
|
+
})}
|
41
|
+
</div>
|
42
|
+
);
|
43
|
+
};
|
@@ -0,0 +1,35 @@
|
|
1
|
+
.container {
|
2
|
+
display: flex;
|
3
|
+
flex-direction: row;
|
4
|
+
flex-wrap: wrap;
|
5
|
+
justify-content: flex-end;
|
6
|
+
row-gap: 1em;
|
7
|
+
}
|
8
|
+
|
9
|
+
.scoreWrapper {
|
10
|
+
display: flex;
|
11
|
+
flex-direction: column;
|
12
|
+
align-items: center;
|
13
|
+
margin-left: 1em;
|
14
|
+
}
|
15
|
+
|
16
|
+
.metricName {
|
17
|
+
width: 100%;
|
18
|
+
font-weight: 300;
|
19
|
+
border-bottom: solid var(--bs-border-color) 1px;
|
20
|
+
}
|
21
|
+
|
22
|
+
.metricReducer {
|
23
|
+
width: 100%;
|
24
|
+
font-weight: 300;
|
25
|
+
}
|
26
|
+
|
27
|
+
.metricValues {
|
28
|
+
display: grid;
|
29
|
+
grid-template-columns: max-content max-content;
|
30
|
+
grid-gap: 0 0.3rem;
|
31
|
+
}
|
32
|
+
|
33
|
+
.metricValue {
|
34
|
+
font-weight: 600;
|
35
|
+
}
|
@@ -0,0 +1,63 @@
|
|
1
|
+
import clsx from "clsx";
|
2
|
+
import { Fragment } from "react";
|
3
|
+
import { Scores } from "../../types/log";
|
4
|
+
import { formatPrettyDecimal } from "../../utils/format";
|
5
|
+
import { metricDisplayName } from "../utils";
|
6
|
+
import styles from "./SidebarScoresView.module.css";
|
7
|
+
|
8
|
+
interface SidebarScoresProps {
|
9
|
+
scores: Scores;
|
10
|
+
}
|
11
|
+
|
12
|
+
export const SidebarScoresView: React.FC<SidebarScoresProps> = ({ scores }) => {
|
13
|
+
const showReducer = scores.findIndex((score) => !!score.reducer) !== -1;
|
14
|
+
return (
|
15
|
+
<div className={styles.container}>
|
16
|
+
{scores.map((score, idx) => {
|
17
|
+
const name = score.name;
|
18
|
+
const reducer = score.reducer;
|
19
|
+
return (
|
20
|
+
<div className={styles.scoreWrapper} key={`scorer-${name}-${idx}`}>
|
21
|
+
<div
|
22
|
+
className={clsx(
|
23
|
+
"text-style-secondary",
|
24
|
+
"text-style-label",
|
25
|
+
"text-size-small",
|
26
|
+
styles.metricName,
|
27
|
+
)}
|
28
|
+
>
|
29
|
+
{name}
|
30
|
+
</div>
|
31
|
+
{showReducer ? (
|
32
|
+
<div
|
33
|
+
className={clsx(
|
34
|
+
"text-size-small",
|
35
|
+
"text-style-label",
|
36
|
+
"text-style-secondary",
|
37
|
+
styles.metricReducer,
|
38
|
+
)}
|
39
|
+
>
|
40
|
+
{reducer || "default"}
|
41
|
+
</div>
|
42
|
+
) : (
|
43
|
+
""
|
44
|
+
)}
|
45
|
+
<div className={clsx("text-size-small", styles.metricValues)}>
|
46
|
+
{Object.keys(score.metrics).map((key) => {
|
47
|
+
const metric = score.metrics[key];
|
48
|
+
return (
|
49
|
+
<Fragment key={key}>
|
50
|
+
<div className={clsx()}>{metricDisplayName(metric)}</div>
|
51
|
+
<div className={styles.metricValue}>
|
52
|
+
{formatPrettyDecimal(metric.value)}
|
53
|
+
</div>
|
54
|
+
</Fragment>
|
55
|
+
);
|
56
|
+
})}
|
57
|
+
</div>
|
58
|
+
</div>
|
59
|
+
);
|
60
|
+
})}
|
61
|
+
</div>
|
62
|
+
);
|
63
|
+
};
|
File without changes
|
@@ -0,0 +1,70 @@
|
|
1
|
+
import { useEffect, useState } from "react";
|
2
|
+
import { SampleSummary } from "../../api/types";
|
3
|
+
import { MessageBand } from "../../components/MessageBand";
|
4
|
+
import { PlanCard } from "../../plan/PlanCard";
|
5
|
+
import {
|
6
|
+
EvalError,
|
7
|
+
EvalPlan,
|
8
|
+
EvalResults,
|
9
|
+
EvalSpec,
|
10
|
+
EvalStats,
|
11
|
+
} from "../../types/log";
|
12
|
+
import { UsageCard } from "../../usage/UsageCard";
|
13
|
+
import { TaskErrorCard } from "../error/TaskErrorPanel";
|
14
|
+
|
15
|
+
interface PlanTabProps {
|
16
|
+
evalSpec?: EvalSpec;
|
17
|
+
evalPlan?: EvalPlan;
|
18
|
+
evalStats?: EvalStats;
|
19
|
+
evalResults?: EvalResults;
|
20
|
+
samples?: SampleSummary[];
|
21
|
+
evalStatus?: "started" | "error" | "cancelled" | "success";
|
22
|
+
evalError?: EvalError;
|
23
|
+
}
|
24
|
+
|
25
|
+
export const InfoTab: React.FC<PlanTabProps> = ({
|
26
|
+
evalSpec,
|
27
|
+
evalPlan,
|
28
|
+
evalResults,
|
29
|
+
evalStats,
|
30
|
+
samples,
|
31
|
+
evalStatus,
|
32
|
+
evalError,
|
33
|
+
}) => {
|
34
|
+
const [hidden, setHidden] = useState(false);
|
35
|
+
useEffect(() => {
|
36
|
+
setHidden(false);
|
37
|
+
}, [evalSpec, evalPlan, evalResults, evalStats, samples]);
|
38
|
+
|
39
|
+
const showWarning =
|
40
|
+
(!samples || samples.length === 0) &&
|
41
|
+
evalStatus === "success" &&
|
42
|
+
evalSpec?.dataset.samples &&
|
43
|
+
evalSpec.dataset.samples > 0;
|
44
|
+
|
45
|
+
return (
|
46
|
+
<div style={{ width: "100%" }}>
|
47
|
+
{showWarning ? (
|
48
|
+
<MessageBand
|
49
|
+
message="Unable to display samples (this evaluation log may be too large)."
|
50
|
+
hidden={hidden}
|
51
|
+
setHidden={setHidden}
|
52
|
+
type="warning"
|
53
|
+
/>
|
54
|
+
) : (
|
55
|
+
""
|
56
|
+
)}
|
57
|
+
<div style={{ padding: "0.5em 1em 0 1em", width: "100%" }}>
|
58
|
+
<PlanCard
|
59
|
+
evalSpec={evalSpec}
|
60
|
+
evalPlan={evalPlan}
|
61
|
+
scores={evalResults?.scores}
|
62
|
+
/>
|
63
|
+
{evalStatus !== "started" ? <UsageCard stats={evalStats} /> : undefined}
|
64
|
+
{evalStatus === "error" && evalError ? (
|
65
|
+
<TaskErrorCard error={evalError} />
|
66
|
+
) : undefined}
|
67
|
+
</div>
|
68
|
+
</div>
|
69
|
+
);
|
70
|
+
};
|
@@ -0,0 +1,46 @@
|
|
1
|
+
import { filename } from "../../utils/path";
|
2
|
+
|
3
|
+
import { Capabilities } from "../../api/types";
|
4
|
+
import { DownloadPanel } from "../../components/DownloadPanel";
|
5
|
+
import { JSONPanel } from "../../components/JsonPanel";
|
6
|
+
import styles from "./JsonTab.module.css";
|
7
|
+
|
8
|
+
const kJsonMaxSize = 10000000;
|
9
|
+
|
10
|
+
interface JsonTabProps {
|
11
|
+
logFile?: string;
|
12
|
+
capabilities: Capabilities;
|
13
|
+
selected: boolean;
|
14
|
+
json: string;
|
15
|
+
}
|
16
|
+
|
17
|
+
/**
|
18
|
+
* Renders JSON tab
|
19
|
+
*/
|
20
|
+
export const JsonTab: React.FC<JsonTabProps> = ({
|
21
|
+
logFile,
|
22
|
+
capabilities,
|
23
|
+
json,
|
24
|
+
}) => {
|
25
|
+
if (logFile && json.length > kJsonMaxSize && capabilities.downloadFiles) {
|
26
|
+
// This JSON file is so large we can't really productively render it
|
27
|
+
// we should instead just provide a DL link
|
28
|
+
const file = `${filename(logFile)}.json`;
|
29
|
+
return (
|
30
|
+
<div className={styles.jsonTab}>
|
31
|
+
<DownloadPanel
|
32
|
+
message="The JSON for this log file is too large to render."
|
33
|
+
buttonLabel="Download JSON File"
|
34
|
+
fileName={file}
|
35
|
+
fileContents={json}
|
36
|
+
/>
|
37
|
+
</div>
|
38
|
+
);
|
39
|
+
} else {
|
40
|
+
return (
|
41
|
+
<div className={styles.jsonTab}>
|
42
|
+
<JSONPanel id="task-json-contents" json={json} simple={true} />
|
43
|
+
</div>
|
44
|
+
);
|
45
|
+
}
|
46
|
+
};
|