[feature] Improve evaluation runs page(s) / table(s)#3016
Merged
ardaerzin merged 272 commits intorelease/v0.66.0from Dec 8, 2025
Merged
[feature] Improve evaluation runs page(s) / table(s)#3016ardaerzin merged 272 commits intorelease/v0.66.0from
ardaerzin merged 272 commits intorelease/v0.66.0from
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
|
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR introduces significant improvements to the evaluation runs page(s) and table(s) in the frontend, implementing a comprehensive redesign of the evaluation run details interface. The changes add new views (Overview, Scenarios, Configuration), enhanced comparison capabilities, and improved data visualization components.
Key Changes
- Added Overview view with metric comparisons, spider charts, and temporal metrics visualization
- Implemented Configuration view with detailed run metadata, evaluator settings, and variant information
- Enhanced table functionality with focus drawer for detailed scenario inspection
- Added run comparison features with support for multiple run comparisons
Reviewed Changes
Copilot reviewed 117 out of 324 changed files in this pull request and generated 5 comments.
Show a summary per file
| File | Description |
|---|---|
| OverviewPlaceholders.tsx | Loading and empty state placeholders with animated radar chart mock |
| OverviewMetricComparison.tsx | Metric comparison logic aggregating data across runs |
| MetricComparisonCard.tsx | Chart component for displaying metric distributions across runs |
| MetadataSummaryTable.tsx | Comprehensive metadata table showing run details and metrics |
| EvaluatorTemporalMetricsChart.tsx | Time-series chart for evaluator metrics with area/line visualization |
| BaseRunMetricsSection.tsx | Section displaying base run metrics with temporal and static views |
| AggregatedOverviewSection.tsx | Aggregated overview combining metadata table and spider chart |
| OverviewView.tsx | Main overview view component orchestrating run comparisons |
| ConfigurationView/utils.ts | Utility functions for parsing run configuration data |
| ConfigurationView/index.tsx | Main configuration view with synchronized scrolling columns |
| TestsetSection.tsx | Testset configuration display component |
| QuerySection.tsx | Query configuration with filters and sampling rate display |
| PromptConfigCard.tsx | Prompt configuration card with message normalization |
| InvocationSection.tsx | Invocation configuration with variant details |
| GeneralSection.tsx | General run information with editable name/description |
| EvaluatorSection.tsx | Evaluator configuration display with JSON toggle |
| Reference components | Reusable components for displaying application/variant/testset references |
| TableHeaders/StepGroupHeader.tsx | Dynamic table headers with reference resolution |
| TableCells | Cell renderers for metrics, invocations, inputs, and actions |
| FocusDrawer components | Drawer for detailed scenario inspection with navigation |
| EvaluatorMetricsSpiderChart | Spider/radar chart for multi-dimensional metric visualization |
| EvaluatorMetricsChart | Chart components for evaluator metric distributions |
| CompareRunsMenu.tsx | UI for selecting and managing run comparisons |
| Page.tsx | Main page component with tab navigation |
| Various atoms/state | State management for comparison, focus drawer, and table data |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
...components/EvalRunDetails2/components/views/OverviewView/components/OverviewPlaceholders.tsx
Outdated
Show resolved
Hide resolved
web/oss/src/components/EvalRunDetails2/components/views/ConfigurationView/utils.ts
Show resolved
Hide resolved
...omponents/EvalRunDetails2/components/views/ConfigurationView/components/PromptConfigCard.tsx
Outdated
Show resolved
Hide resolved
web/oss/src/components/EvalRunDetails2/components/TableCells/MetricCell.tsx
Outdated
Show resolved
Hide resolved
Contributor
There was a problem hiding this comment.
Pull Request Overview
Copilot reviewed 117 out of 326 changed files in this pull request and generated no new comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Contributor
There was a problem hiding this comment.
Pull Request Overview
Copilot reviewed 120 out of 336 changed files in this pull request and generated 1 comment.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
junaway
changed the title
junaway
reviewed
Nov 20, 2025
junaway
reviewed
Nov 20, 2025
junaway
reviewed
Nov 20, 2025
junaway
reviewed
Nov 20, 2025
junaway
reviewed
Nov 20, 2025
junaway
reviewed
Nov 20, 2025
junaway
reviewed
Nov 20, 2025
junaway
reviewed
Nov 20, 2025
…de-daytona-sandbox
…com/Agenta-AI/agenta into frontend-feat/new-evaluations-pages
…de-daytona-sandbox
…ogram bins, improve duration formatting - Only use invocation step (type="invocation") for shared analytics keys (duration, tokens, costs) to avoid showing evaluator execution metrics instead of LLM metrics - Add invocationStepKeys parameter to flattenRunLevelMetricData to identify correct step - Aggregate histogram bins when count exceeds MAX_DISPLAY_BINS (6) for clearer visualization - Fix duration formatting in metric popover by
…and refactor utility functions - Remove commented debug logs and unused code blocks across multiple components - Add error handling and user feedback for testset name fetching failures - Add input validation for scenario and run IDs to prevent SSRF attacks - Improve prompt key resolution with helper function in PromptConfigCard - Add clarifying comments for fallback logic and depth limits - Refactor sample rate formatting with
…-evaluations-pages
- Remove word splitting, filtering, and humanization logic from humanizeEvaluatorName - Return evaluator label unchanged instead of processing it
…com/Agenta-AI/agenta into frontend-feat/new-evaluations-pages
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
tba...