feat: add eval dataset and test runner infrastructure #43
Conversation
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
Implements #33 with comprehensive evaluation framework: ## Core Features - CLI eval runner with `pr-review-eval` script - Precision, recall, F1, confidence scoring metrics - YAML fixture format for test case definitions - Synthetic test diffs covering common issues ## Files Added - `evals/runner.py` - CLI evaluation runner - `evals/scoring.py` - Metrics calculation - `evals/cases/*.yaml` - 6 synthetic test cases - `evals/diffs/*.patch` - Sample diff files - `tests/test_evals.py` - Full test coverage ## Integration - Added `--eval` flag to main CLI - New `pr-review-eval` script entry point - Package includes evals module ## Test Cases Synthetic fixtures for: SQL injection, XSS, missing error handling, unused imports, large functions, hardcoded secrets ## Acceptance Criteria Met ✓ `uv run pr-review-eval --suite evals/cases/` produces scoring report ✓ 6+ synthetic test fixtures covering different issue types ✓ Precision/recall/F1 scoring implemented ✓ CLI integration with `--eval` flag ✓ 96.5% test coverage maintained Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
dtsong
added
evals
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Outdated suggestions cannot be applied.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.
Closes #33
Summary
Changes
evals/runner.py- CLI evaluation runnerevals/scoring.py- Metrics calculation engineevals/cases/*.yaml- 6 synthetic test case definitionsevals/diffs/*.patch- Sample diff files for testingtests/test_evals.py- Comprehensive test coveragesrc/pr_review_agent/main.py- Added--evalflagpyproject.toml- Addedpr-review-evalscriptTest Plan
uv run pr-review-eval --helpUsage Example
Test Cases Included
🤖 Generated with Claude Code