- Modified the indexing functions for Google Calendar and Gmail to return the count of skipped messages alongside indexed messages, enhancing performance tracking.
- Updated related tests to accommodate the new return values, ensuring comprehensive coverage of the indexing process.
- Improved error handling to maintain consistency in returned values across different indexing functions.
- Updated the indexing function to return the count of skipped files alongside indexed files, improving tracking of indexing performance.
- Added logic to accumulate skipped file counts during the indexing process, providing better insights into potential issues.
- Enhanced notification updates to include skipped file counts, ensuring comprehensive progress reporting for users.
- Updated the .env.example file to include a note about disabling "Mask Connected Account Secrets" for Google indexing.
- Implemented a wait_for_connection method in ComposioService to ensure connected accounts reach ACTIVE status after authentication.
- Added logic in composio_callback and composio_reauth_callback to wait for Composio to finish processing tokens, improving reliability in token handling.
- Enhanced logging to provide clearer warnings when connection timeouts occur, ensuring better visibility into potential issues.
- Improved error handling for Google Drive indexing and listing operations to manage authentication failures more effectively.
- Added logic to mark connectors as 'auth_expired' when a 401 error or invalid credentials are detected, prompting users to re-authenticate.
- Updated error messages to provide clearer guidance on authentication issues, ensuring a better user experience.
- Added new endpoints for re-authenticating Composio connectors, allowing users to refresh their authentication when expired.
- Introduced a method in ComposioService to handle the refresh of connected accounts.
- Updated the frontend to support re-authentication flows, including success notifications and redirection after re-authentication.
- Enhanced error handling for re-authentication processes to improve user experience.
- Added re-authentication endpoints for Google Drive, Gmail, and Calendar connectors to handle expired authentication.
- Enhanced the UI to prompt users for re-authentication when their credentials are expired.
- Updated backend logic to mark connectors as 'auth_expired' and manage re-authentication requests effectively.
- Improved error handling for authentication failures across Google connectors.
- Added a mechanism to mark connectors as 'auth_expired' in the database, allowing the frontend to prompt users for re-authentication.
- Updated Linear and Notion connector routes to handle token refresh failures by invoking the new expiration flagging function.
- Enhanced UI components to display re-authentication options when a connector's authentication status is expired.
- Added re-authentication endpoints for Linear and Notion connectors to handle expired authentication.
- Enhanced error handling in issue creation, deletion, and update tools to return appropriate authentication error messages.
- Updated UI components to display authentication status and guide users on re-authentication steps.
- Improved account health checks to ensure valid tokens are used for operations.
- Added notion-markdown dependency to pyproject.toml.
- Refactored _markdown_to_blocks method to utilize notion-markdown for converting markdown content to Notion blocks.
- Updated create-notion-page component to replace Loader2Icon with Spinner for improved loading indication.
- Replaced background styles with `bg-main-panel` in various components for consistent theming.
- Enhanced the `Header`, `LayoutShell`, and `Thread` components to improve visual coherence.
- Adjusted tool management UI to reflect new design standards, ensuring a unified user experience.
Wrap synchronous embedding_model.embed() calls with asyncio.to_thread()
in both vector_search and hybrid_search methods. This prevents blocking
the asyncio event loop during embedding computation, improving server
responsiveness under concurrent load.
Fixes#794
Signed-off-by: Tim Ren <137012659+xr843@users.noreply.github.com>
- modify the `web_search` tool that integrates multiple live search connectors (Tavily, Linkup, Baidu) alongside the SearXNG platform for real-time information retrieval.
- Updated comments to reflect the separation of local knowledge base searches from web searches.
- Improved handling of connector types and search logic to ensure accurate routing of queries to the appropriate tools.
- Refactored existing code to streamline the search process and enhance performance.
- Deleted the migration script for adding web search columns to the database.
- Removed web search related fields from the SearchSpace model and schemas.
- Eliminated web search health check endpoint and associated service logic.
- Updated frontend components to remove web search settings management.
- Cleaned up references to SearXNG API in various modules, transitioning to a platform service approach.
- Consolidated volume mappings for SearXNG to use a single directory.
- Removed unnecessary port mappings and legacy data volume definitions.
- Updated web search service documentation to clarify Redis usage and circuit breaker implementation, eliminating Redis dependency for circuit breaker logic.
- Added SearXNG service configuration to Docker setup, including environment variables and health checks.
- Introduced new settings management for web search in the frontend, allowing users to enable/disable and configure search engines and language preferences.
- Updated backend to support web search functionality, including database schema changes and service integration.
- Implemented health check endpoint for the web search service and integrated it into the application.
- Removed legacy SearXNG API connector references in favor of the new platform service approach.
Add full MiniMax provider support across the entire stack:
Backend:
- Add MINIMAX to LiteLLMProvider enum in db.py
- Add MINIMAX mapping to all provider_map dicts in llm_service.py,
llm_router_service.py, and llm_config.py
- Add Alembic migration (rev 106) for PostgreSQL enum
- Add MiniMax M2.5 example in global_llm_config.example.yaml
Frontend:
- Add MiniMax to LLM_PROVIDERS enum with apiBase
- Add MiniMax-M2.5 and MiniMax-M2.5-highspeed to LLM_MODELS
- Add MINIMAX to Zod validation schema
- Add MiniMax SVG icon and wire up in provider-icons
Docs:
- Add MiniMax setup guide in chinese-llm-setup.md
MiniMax uses an OpenAI-compatible API (https://api.minimax.io/v1)
with models supporting up to 204K context window.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Added bulk delete functionality for documents in DocumentsTableShell and DocumentsSidebar.
- Enhanced search space retrieval to exclude spaces marked for deletion in read_search_spaces.
- Updated connector dialog to synchronize URL parameters when opened externally.
- Improved layout behavior to handle search space deletion and redirection more effectively.
- Added `_attach_model_profile` function to attach model context metadata to `ChatLiteLLM`.
- Updated `create_chat_litellm_from_config` and `create_chat_litellm_from_agent_config` to utilize the new profile attachment.
- Improved context profile caching in `llm_router_service.py` to include both minimum and maximum input tokens, along with token model names for better context management.
- Introduced new methods for token counting and context trimming based on model profiles.
- Added endpoint to list agent tools with metadata, excluding hidden tools.
- Updated NewChatRequest and RegenerateRequest schemas to include disabled tools.
- Integrated disabled tools management in the NewChatPage and Composer components.
- Improved tool instructions and visibility in the system prompt.
- Refactored tool registration to support hidden tools and default enabled states.
- Enhanced document chunk creation to handle strict zip behavior.
- Cleaned up imports and formatting across various files for consistency.
- Add check_permission to drive-picker-token endpoint (IDOR fix)
- Use get_composio_service singleton + asyncio.to_thread to avoid blocking the event loop
- Sanitize error detail in 500 response to prevent internal info leakage
- Dispose picker on unmount to prevent orphaned overlay
- Surface error state on Google Picker Action.ERROR instead of silently closing
