Remove all Electric SQL client code, Docker service, env vars, CI build
args, install scripts, and documentation. Feature hooks that depend on
Electric are intentionally left in place to be rewritten with Rocicorp
Zero in subsequent commits.
Deleted:
- lib/electric/ (client.ts, context.ts, auth.ts, baseline.ts)
- ElectricProvider.tsx
- docker/scripts/init-electric-user.sh
- content/docs/how-to/electric-sql.mdx
Cleaned:
- package.json (4 @electric-sql/* deps)
- app/layout.tsx, UserDropdown.tsx, LayoutDataProvider.tsx
- docker-compose.yml, docker-compose.dev.yml
- Dockerfile, docker-entrypoint.js
- .env.example (frontend, docker, backend)
- CI workflows, install scripts, docs
- Added authlib version 1.6.9 and tornado version 6.5.5 to the project dependencies.
- Updated authlib version in uv.lock to 1.6.9 with corresponding source and wheel URLs.
- Included tornado in the dependencies section of uv.lock for consistency.
- 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.
- Updated SearXNG image version to 2026.3.13-3c1f68c59 in the Docker Compose file.
- Added port mapping for SearXNG service to allow access on a configurable port.
- Enhanced the .env.example file with comments for SearXNG configuration and usage instructions.
- 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
