feat: Add Claude AI code review GitHub Actions workflow for automated PR reviews

[devmdave]

Summary

This PR implements an automated code review system using Claude AI (Anthropic) integrated into our GitHub Actions CI/CD pipeline.

Motivation

Manual code reviews can be time-consuming and may miss common issues. This automated review system provides immediate feedback on:

• Security vulnerabilities
• Potential bugs and logic errors
• Code quality improvements
• Best practices violations
• Documentation gaps

The AI-powered reviews complement human reviews by catching issues early and providing consistent feedback across all pull requests.

Changes

New Files

• .github/workflows/claude-code.yml - GitHub Actions workflow configuration
• scripts/claude-review.js - Core review logic using Anthropic Claude API
• scripts/format-claude-output.js - Utility for formatting review output

Modified Files

• package.json - Added @actions/core and @actions/github dependencies

Implementation Details

The workflow:

1. Triggers on pull requests and pushes to the main branch
2. Fetches full git history for comprehensive diff analysis
3. Extracts changed files and generates git diff
4. Sends the diff to Claude AI (model: claude-sonnet-4-20250514) for analysis
5. Posts formatted review results as PR comments
6. Uploads review artifacts for future reference (30-day retention)

The review includes severity levels (🔴 Critical, 🟡 Warning, 🟢 Info) for easy prioritization.

Configuration Required

Before merging, ensure the following secret is configured in the repository:

• ANTHROPIC_API_KEY - API key for Claude AI service

Testing

The workflow has been configured with continue-on-error: true to prevent blocking the CI pipeline if the review service is unavailable.

Benefits

• ✅ Immediate automated feedback on code changes
• ✅ Consistent review quality across all PRs
• ✅ Reduced reviewer burden for common issues
• ✅ Educational for team members through AI suggestions
• ✅ Non-blocking - doesn't prevent merges if service is down

Future Enhancements

Potential improvements for follow-up PRs:

• Configurable review rules and severity thresholds
• Integration with code coverage metrics
• Custom prompts for project-specific standards
• Review result caching to avoid re-analyzing unchanged code