- Removed unnecessary delay in chat redirection for immediate user feedback.
- Enhanced TitleBar component with a system health indicator, displaying RAM and CPU usage.
- Implemented optimistic UI updates for model downloads and Ollama installation, improving responsiveness.
- Introduced background health monitoring to prevent resource overload during operations.
- Added cleanup logic for child processes to ensure proper resource management during application shutdown.
- Introduced a comprehensive README.md detailing the application, its architecture, and key features.
- Implemented a local-first architecture with deep research capabilities, including query decomposition and parallel web scraping.
- Added a reactive UI built with React and Next.js, featuring Tailwind CSS for styling and Zustand for state management.
- Integrated a task scheduler for recurring tasks and system monitoring for real-time resource management.
- Enhanced settings page with debug mode options and improved hardware dashboard loading states.
- Updated chat interface to include debug data visualization and improved user experience during message streaming.
- Removed unused favicon and updated application icons for better branding.
- Improved navigation handling with non-blocking transitions and state management for setup completion.
- Added `emoji-regex` and `remove-accents` packages to improve text processing capabilities.
- Implemented automatic Ollama startup in the chat page for better user experience.
- Enhanced setup page to include GPU selection based on hardware specifications.
- Updated chat input to support real-time validation and improved user feedback.
- Refactored message handling in chat to incorporate new processing features.
- 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