v2.1.0 - Critical Fixes & Accurate Documentation
·
49 commits
to main
since this release
🚨 Critical Fixes Release
🔧 Major Fixes
- Fixed Installer Scripts: New universal installers that actually work without errors
- Corrected Token Claims: Updated all documentation to reflect actual 30-40% token optimization (not 99%)
- Import Commands Fixed:
/init-importand/task-importnow properly create agent-todo folders - Parallel Agent Execution: Fixed agents working sequentially - now truly parallel
- Monitor Stability: Fixed monitor closing immediately after launch
- Global Command:
/monitornow auto-installs global command properly
📝 Documentation Updates
- Clear Installation: Step-by-step instructions that work on all platforms
- Claude Flag Requirements: Prominently documented
--dangerously-skip-permissionsrequirement - Removed Outdated Commands: No more references to
npm run devor obsolete commands - Accurate Claims: All performance claims now based on actual benchmarks
🛡️ Security Fixes
- Fixed shell command injection vulnerabilities (CWE-78, CWE-88, CWE-116)
- Replaced exec with execFile for proper input sanitization
- Added comprehensive permission checking system
📦 Installation
Quick Install (Recommended)
macOS/Linux:
curl -fsSL https://raw.githubusercontent.com/VibeCodingWithPhil/agentwise/main/installers/install.sh | bashWindows (PowerShell as Administrator):
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/VibeCodingWithPhil/agentwise/main/installers/install.ps1" -OutFile "install.ps1"
Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
.\install.ps1⚠️ IMPORTANT
Always start Claude Code with the required flag:
claude --dangerously-skip-permissionsThis flag is REQUIRED for:
- File system operations
- Monitor dashboard functionality
- Agent parallel execution
- Global command installation
🎯 What's Fixed
- ✅ Import commands create agent-todo folders properly
- ✅ Agents work in parallel as intended
- ✅ Monitor stays open and tracks progress
- ✅ Installer scripts work without errors
- ✅ Documentation reflects actual capabilities (30-40% token reduction)
- ✅ Security vulnerabilities patched
- ✅ Permission requirements clearly documented
📊 Verified Performance
- Token Optimization: 30-40% reduction (verified through benchmarking)
- Parallel Execution: True parallel agent operation
- Import Success: Projects import with proper structure
🙏 Thanks
Special thanks to users who reported these critical issues. Your feedback helps make Agentwise better!
Full Changelog: v2.0.9...v2.1.0"