Add metadata-first search approach followed by targeted scraping of top URLs. Includes:
- New `smartSearchRag` method in web search service
- Metadata-only search endpoint in Tauri backend
- Bulk URL scraping capability
- Payload content override in chat messages
- Added state management for web context and sources to improve debugging capabilities in chat.
- Implemented a debug view for displaying extracted context and sources used in chat responses.
- Refactored message handling to incorporate web context into user messages, enhancing response accuracy.
- Updated UI components to support new debugging features and improve user interaction.
- Integrated useRouter for navigation in chat and settings pages, improving user experience.
- Added detailed debug logging for web context generation and chat payloads to assist in troubleshooting.
- Updated settings page to include a hardware dashboard and enhanced sources configuration management.
- Implemented auto-start feature for the application and improved task management with new scheduled task options.
- Refined user interface components for better accessibility and usability across chat and settings pages.
- Added new Radix UI components including checkbox, label, popover, slider, switch, and tooltip to improve UI interactions.
- Integrated react-syntax-highlighter for better code rendering in chat messages.
- Updated package.json and pnpm-lock.yaml to include new dependencies and ensure compatibility.
- Enhanced chat input to support web search toggling, improving user experience during message composition.
- Implemented auto-saving of chat sessions and improved session management features.
- Refactored chat message rendering to clean up metadata and improve display quality.
- Added support for rendering markdown in chat messages using ReactMarkdown with custom renderers.
- Integrated a default format prompt for the chat system, improving user experience by initializing with a predefined prompt.
- Updated the prompt generator to handle model selection more robustly, including loading states and fallback options for model selection.
- Enhanced UI components for better accessibility and user feedback during prompt generation.
- Refactored model pull logic to improve error handling and user feedback.
- Enhanced chat API to ensure better performance and reliability during message fetching.
- Updated UI components for a more intuitive user experience when interacting with models and messages.
Evandro Fonseca Junior