Releases: stroupaloop/pr-vibe
v0.14.0 - Enhanced Bot Comment Detection & Human Review Support
Major Improvements
🔧 Fixed Bot Comment Detection
- FIXED: CodeRabbit review comments were being missed due to restrictive filtering
- Now processes ALL PR reviews, even those without body text but containing nested comments
- Added comprehensive error handling and debug logging
👥 Human Reviewer Support
- NEW: Automatically processes human reviewer comments alongside bot feedback
- Intelligent priority detection (critical, high, medium, low)
- Comment categorization (security, request, suggestion, blocking, informational)
- No longer requires experimental flag - human comments processed by default
📊 Enhanced Reporting
- Added Human Reviews section to markdown reports
- Better tracking of human feedback with action status
- Improved summary statistics including human reviewer metrics
🧪 Testing & Validation
- All 22 test suites passing (195 tests)
- Successfully validated on real CodeRabbit reviews
- Comprehensive error handling improvements
📝 Documentation
- Updated README with Human Reviewer Support section
- Enhanced feature descriptions and examples
- Complete changelog with technical details
This release significantly improves pr-vibe's ability to detect and process feedback from both AI bots and human reviewers, making it a more comprehensive PR review automation tool.
v0.13.0 - Enhanced Bot Comment Detection
🐛 Fixed
- Enhanced Bot Comment Detection - Fixed issue where pr-vibe would miss inline review comments from bots
- Now properly detects nested PR review comments even when parent review says "0 actionable comments"
- Fixed handling of empty/undefined comment bodies
- Added comprehensive debug logging to trace comment processing
✨ New Features
- Expanded AI Tool Support - Added detection for more AI code review tools:
- GitHub Copilot
- Codacy
- CodeGeeX
- ReviewDog
- PR Bot
- Generic bot detection for any tool with [bot] suffix
📚 Documentation
- Added "Supported Bots" section to README
- Listed all supported bot types with descriptions
- Clarified inline review comment handling
🔧 Technical Improvements
- Enhanced bot detector to handle edge cases (null/undefined bodies)
- Added comprehensive test coverage for bot comment structures
- Improved PR review comment association logic
Full Changelog
See CHANGELOG.md for complete details.
v0.12.1 - Bot Detection Fix
🐛 Bug Fixes
Fixed Bot Detection Gap
- pr-vibe can now properly detect CodeRabbit PR review comments
- Added special handling for comments attached to PR reviews
- Fixes the issue where pr-vibe couldn't review its own PRs
🚀 Dependencies Updated
- dotenv: 16.5.0 → 17.0.1
- @anthropic-ai/sdk: 0.30.1 → 0.56.0
- openai: 4.104.0 → 5.8.2
- @octokit/rest: 21.1.1 → 22.0.0
Technical Details
The issue was that CodeRabbit posts review comments attached to a PR review that says "Actionable comments posted: 0", but the actual actionable comments are in the review.comments array. pr-vibe now properly processes these nested comments.
v0.12.0 - Priority-Based Filtering
🎯 Priority-Based Filtering
Focus your reviews on what matters most with intelligent priority filtering.
New Features
- --critical-only flag - Focus on must-fix issues only (security, bugs, breaking changes)
- --priority-threshold option - Filter by priority level: must-fix, suggestion, or nitpick
- Priority breakdown in summary - Shows count of comments by priority level
- Filtered count display - Shows how many comments were hidden by priority filter
Example Usage
# Focus on critical issues only
pr-vibe pr 123 --critical-only
# Show must-fix and suggestions
pr-vibe pr 123 --priority-threshold suggestion
# Combine with auto-fix for rapid resolution
pr-vibe pr 123 --critical-only --auto-fix
Technical Improvements
- Priority levels exported from decision-engine: MUST_FIX, SUGGESTION, NITPICK
- All comments now include priority assignment based on category
- Priority filtering logic with configurable thresholds
- Validation to prevent conflicting filter options
🎵 pr-vibe continues to evolve with features that help you focus on what truly matters in PR reviews. This release brings smart filtering to help you prioritize critical issues while maintaining visibility into all feedback when needed.
v0.11.0 - Smart Watch Mode 🎯
🎉 What's New - Smart Watch Mode
pr-vibe now includes an intelligent watch mode that monitors your PRs for bot activity, making it perfect for fresh PRs where bots haven't arrived yet!
🚀 Key Features
Smart Watch Command
# Watch for bots with intelligent monitoring
pr-vibe watch 123
# Auto-process when all bots complete
pr-vibe watch 123 --auto-process
# Custom timeout (default 10 minutes)
pr-vibe watch 123 --timeout 30
Adaptive Polling Intervals
- 0-30s: Check every 5 seconds (rapid bot response period)
- 30s-2m: Check every 10 seconds (most bots have responded)
- 2-5m: Check every 20 seconds (waiting for slower bots)
- 5m+: Check every 30 seconds (long-running analysis)
Bot Completion Detection
- Recognizes completion signals: "review complete", "analysis finished", "approved", "LGTM"
- Tracks which bots typically review your PRs
- Shows real-time status of pending bots with expected completion times
- Automatically detects when all bots have finished
📊 Enhanced User Experience
-
Real-time Status Updates
- Shows which specific bots are still pending
- Displays expected completion times based on historical data
- Updates spinner with current polling interval
-
Smart Bot Tracking
- Learns which bots typically review your repository
- Tracks average response times for better predictions
- Differentiates between "should finish soon" vs "taking longer than usual"
-
Flexible Processing Options
- Manual mode: Prompts when bots complete (default)
- Auto mode: Automatically processes with
--auto-process
flag - Exit anytime: Full control over the watch process
🔧 Technical Improvements
- Bot response time tracking with configurable expectations
- Completion signal pattern matching for reliable detection
- Graceful handling of unexpected bot behavior
- Comprehensive test coverage for all watch mode features
📚 Documentation
- Updated README with Smart Watch Mode section
- New demo script:
examples/smart-watch-demo.js
- Enhanced command help with detailed usage examples
🎯 Perfect For
- Fresh PRs where you're waiting for bots to arrive
- CI/CD pipelines that need to wait for bot approvals
- Developers who want to minimize context switching
- Teams with multiple review bots
💡 Usage Example
After creating a PR:
# Create your PR
gh pr create --title "Add new feature" --body "..."
# Immediately start watching for bots
pr-vibe watch 123 --auto-process
# pr-vibe will:
# 1. Monitor for bot arrivals
# 2. Track their completion
# 3. Auto-process when all bots finish
# 4. Let you get back to coding\!
🙏 Acknowledgments
This release addresses valuable feedback from the Woodhouse project community about handling fresh PRs. Thank you for helping make pr-vibe better!
📦 Installation
npm install -g pr-vibe@latest
Or use directly:
npx pr-vibe@latest watch 123
🔗 Links
Full Changelog: v0.10.0...v0.11.0
v0.10.0 - Merge Readiness Integration
v0.9.0 - Enhanced No Issues Experience
✨ Enhanced "No Issues Found" Experience
This release significantly improves pr-vibe's output when no actionable bot comments are found, based on valuable user feedback.
What's New
🎉 Positive Messaging
- Replace warning "
⚠️ No actionable bot comments found" with celebratory "✅ All bot reviews passed!" - Show which bots reviewed the PR and their approval status
🤖 Bot Approval Detection
- Automatically detect approval signals (LGTM, approved, no issues found)
- Display issue breakdown when available (e.g., "3 suggestions, 2 nitpicks")
- Support for CodeRabbit, DeepSource, and other major bots
📊 CI Status Integration
- Show GitHub check runs with clear status: "3/5 checks passing (2 pending)"
- Gracefully handle permission issues or API errors
🔗 PR URL with Hyperlinks
- Display clickable PR URL using terminal hyperlink support
- Automatic fallback for terminals without hyperlink support
👁️ Progressive Disclosure
- New
--show-all
flag to optionally view non-critical suggestions - Keep output clean by default while allowing detailed view on demand
Example Output
Analyzing PR #123 on owner/repo...
🔗 https://github.com/owner/repo/pull/123
✅ All bot reviews passed\! No issues found.
Bot Review Summary:
- ✅ coderabbit[bot]: Approved - 0 actionable comments
- ✅ DeepSource: Not configured
- Human reviews: 0 pending
CI Status: 3/5 checks passing (2 pending)
💡 3 non-critical suggestions available (use --show-all to view)
Installation
npm install -g pr-vibe@latest
Acknowledgments
Special thanks to our users for the excellent feedback that led to these improvements!
v0.8.0 - Claude Code Integration
🤖 Claude Code Integration
pr-vibe now has full support for the Claude Code GitHub app!
What's New
- Automatic Detection: Recognizes Claude Code bot comments and reviews
- Smart Analysis: Extracts Claude's confidence levels and categories
- Efficient Processing: Skips redundant analysis when Claude has already categorized
- Seamless Integration: Maps Claude's priorities to pr-vibe's action system
How It Works
When Claude Code reviews your PR with comments like:
MUST_FIX: SQL injection vulnerability (95% confidence - FACT)
pr-vibe will:
- Recognize this as a high-confidence security issue
- Skip re-analyzing with another LLM
- Automatically mark it for fixing
- Use Claude's confidence score in reports
Get Started
npx pr-vibe@latest pr <number>
pr-vibe will now intelligently handle Claude Code comments alongside CodeRabbit, DeepSource, and other bots!
Full Changelog: v0.7.0...v0.8.0
v0.6.1: Fix False Security Categorization
🐛 Bug Fixes
This patch release fixes a critical issue where pr-vibe was incorrectly categorizing ESLint style warnings as security vulnerabilities.
What's Fixed
- ✅ Type imports (e.g., "prefer type-only import") now correctly categorized as STYLE, not SECURITY
- ✅ Empty catch blocks now correctly categorized as CODE_QUALITY, not SECURITY
- ✅ Console.log statements now correctly categorized as DEBUG, not SECURITY
- ✅ Commit messages now accurate: "style: Apply code formatting" instead of "SECURITY: Fixed vulnerability"
Technical Details
- Added context-aware categorization that checks style patterns before security patterns
- Introduced new STYLE and DEBUG categories for better classification
- Enhanced bot comment parsing to understand CodeRabbit severity indicators (
⚠️ ≠ security) - Added comprehensive test suite to prevent regression
Feedback
This fix addresses user feedback from PR lvrginc/application#9659 where style issues were causing unnecessary alarm by being flagged as security vulnerabilities.
Install/Update: npm install -g pr-vibe@latest
v0.6.0: Intelligent Nit Comment Filtering
🎉 What's New
Intelligent Nit Comment Filtering
Focus on what matters with new filtering options:
--skip-nits
flag to exclude minor style/formatting comments--nits-only
flag to review only nitpick comments- Detects common patterns: "nit:", "minor", "consider", "style", etc.
- Recognizes CodeRabbit's "review details" and "additional comments" sections
- 90%+ confidence in nit detection
- Shows [NIT] indicator in UI for nitpick comments
Enhanced Decision Engine
- New
NIT
action type with lower priority NITPICK
category for better issue classification- Appropriate suggested replies for nit comments
Improved Developer Experience
- Better error messages showing exactly what was found
- Debug mode shows detection logic and confidence scores
- Comprehensive test suite for nit detection
- Demo script to try out the filtering modes
Usage Examples
# Focus on critical issues only
pr-vibe pr 42 --skip-nits
# Review only style/formatting comments
pr-vibe pr 42 --nits-only
# Default: process all comments including nits
pr-vibe pr 42
Try It Now
npm install -g pr-vibe@latest
Built with 💜 by Claude and the vibe coding community