- Replaced image rendering with Avatar component in PublicChatSnapshotRow, ImageModelManager, and ModelConfigManager for improved consistency.
- Adjusted DocumentsFilters to modify PopoverContent width for better layout.
- Enhanced DocumentsTableShell with new state management for member data and added bulk delete functionality.
- Added `searchSpaceSettingsDialogAtom` to manage the state of the settings dialog.
- Updated multiple components (OnboardPage, TeamManagementPage, ConnectorIndicator, DocumentUploadPopupContent, etc.) to utilize the new dialog state for navigating to settings.
- Removed unnecessary animations from ApiKeyContent and ProfileContent components for improved performance.
- Enhanced button styles for better UI consistency across settings actions.
- Refactored error handling in LLMRoleManager and ModelConfigManager to simplify the UI structure.
- Added methods to retrieve the starting page token and list changes in Google Drive, enabling delta sync capabilities.
- Updated Composio service to handle file download directory configuration.
- Modified indexing tasks to support delta sync, improving efficiency by processing only changed files.
- Adjusted date handling in connector tasks to allow optional start and end dates.
- Improved error handling and logging throughout the Composio indexing process.
- Removed unused import from model-config-manager.tsx
- Deleted useGlobalLLMConfigs hook (no longer used anywhere)
- All 5 components now using jotai + tanstack query pattern
- Full backward compatibility maintained
- Changed document links to point to the researcher page in the dashboard.
- Removed unused team and settings links from the dashboard layout.
- Redesigned settings page with a sidebar for navigation and improved layout for better user experience.
- Added delete confirmation dialog for model configurations in the settings manager.
- Updated card components for better visual consistency and responsiveness.
- Added new LLM providers including Google, Azure OpenAI, Bedrock, and others to the backend.
- Updated the model selection UI to dynamically display available models based on the selected provider.
- Enhanced the provider change handling to reset the model selection when the provider is changed.
- Improved the overall user experience by providing contextual information for model selection.
- Add support for DeepSeek, Qwen (Alibaba), Kimi (Moonshot), and GLM (Zhipu)
- Implement auto-fill API Base URL when selecting Chinese LLM providers
- Add smart validation and warnings for missing API endpoints
- Fix session state management in task logging service
- Add comprehensive Chinese setup documentation
- Add database migration for new LLM provider enums
Closes#383
- RBAC soon??
- Updated various services and routes to handle search space-specific LLM preferences.
- Modified frontend components to pass search space ID for LLM configuration management.
- Removed onboarding page and settings page as part of the refactor.
