- Removed lucide-react and next-themes from package dependencies
- Simplified import in workbench store for path and file-saver
- Removed unnecessary module definition in Vite config
- Implemented a new Diff View in the Workbench to visualize file changes
- Added file history tracking with detailed change information
- Enhanced FileTree and FileModifiedDropdown to show line additions and deletions
- Integrated file history saving and retrieval in ActionRunner
- Updated Workbench view types to include 'diff' option
- Added support for inline and side-by-side diff view modes
# UI V3 Changelog
Major updates and improvements in this release:
## Core Changes
- Complete NEW REWRITTEN UI system overhaul (V3) with semantic design tokens
- New settings management system with drag-and-drop capabilities
- Enhanced provider system supporting multiple AI services
- Improved theme system with better dark mode support
- New component library with consistent design patterns
## Technical Updates
- Reorganized project architecture for better maintainability
- Performance optimizations and bundle size improvements
- Enhanced security features and access controls
- Improved developer experience with better tooling
- Comprehensive testing infrastructure
## New Features
- Background rays effect for improved visual feedback
- Advanced tab management system
- Automatic and manual update support
- Enhanced error handling and visualization
- Improved accessibility across all components
For detailed information about all changes and improvements, please see the full changelog.
# Tab Management System Implementation
## What's Been Implemented
1. Complete Tab Management System with:
- Drag and drop functionality for reordering tabs
- Visual feedback during drag operations
- Smooth animations and transitions
- Dark mode support
- Search functionality for tabs
- Reset to defaults option
2. Developer Mode Features:
- Shows ALL available tabs in developer mode
- Maintains tab order across modes
- Proper visibility toggles
- Automatic inclusion of developer-specific tabs
3. User Mode Features:
- Shows only user-configured tabs
- Maintains separate tab configurations
- Proper visibility management
## Key Components
- `TabManagement.tsx`: Main management interface
- `ControlPanel.tsx`: Main panel with tab display
- Integration with tab configuration store
- Proper type definitions and interfaces
## Technical Features
- React DnD for drag and drop
- Framer Motion for animations
- TypeScript for type safety
- UnoCSS for styling
- Toast notifications for user feedback
## Next Steps
1. Testing:
- Test tab visibility in both modes
- Verify drag and drop persistence
- Check dark mode compatibility
- Verify search functionality
- Test reset functionality
2. Potential Improvements:
- Add tab grouping functionality
- Implement tab pinning
- Add keyboard shortcuts
- Improve accessibility
- Add tab descriptions
- Add tab icons customization
3. Documentation:
- Add inline code comments
- Create user documentation
- Document API interfaces
- Add setup instructions
4. Future Features:
- Tab export/import
- Custom tab creation
- Tab templates
- User preferences sync
- Tab statistics
## Known Issues to Address
1. Ensure all tabs are visible in developer mode
2. Improve drag and drop performance
3. Better state persistence
4. Enhanced error handling
5. Improved type safety
## Usage Instructions
1. Switch to developer mode to see all available tabs
2. Use drag and drop to reorder tabs
3. Toggle visibility using switches
4. Use search to filter tabs
5. Reset to defaults if needed
## Technical Debt
1. Refactor tab configuration store
2. Improve type definitions
3. Add proper error boundaries
4. Implement proper loading states
5. Add comprehensive testing
## Security Considerations
1. Validate tab configurations
2. Sanitize user input
3. Implement proper access control
4. Add audit logging
5. Secure state management
Added the new gemini-2.0-flash-thinking-exp-01-21 model to the GoogleProvider's static model configuration. This model supports a significantly increased maxTokenAllowed limit of 65,536 tokens, enabling it to handle larger context windows compared to existing Gemini models (previously capped at 8k tokens). The model is labeled as "Gemini 2.0 Flash-thinking-exp-01-21" for clear identification in the UI/dropdowns.
This PR introduces a new model, deepseek-r1-distill-llama-70b, to the staticModels array and ensures compatibility with the Groq API. The changes include:
Adding the deepseek-r1-distill-llama-70b model to the staticModels array with its relevant metadata.
Updating the Groq API call to use the new model for chat completions.
These changes enable the application to support the deepseek-r1-distill-llama-70b model, expanding the range of available models for users.
