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 PostHog error capturing for non-authentication errors in BaseApiService.
- Refactored PostHog client initialization to ensure a single instance is used across the application.
- Added referral code tracking in PostHog initialization to capture initial and last seen referral codes.
- Wrapped PostHog capture calls in a safeCapture function to prevent app breakage due to ad-blockers.
- Introduced PostHogReferral component in PostHogProvider for improved referral tracking.
- 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.
- Increased maximum file upload limit from 10 to 50 to improve user experience.
- Implemented batch processing for document uploads to avoid proxy timeouts, splitting files into manageable chunks.
- Enhanced garbage collection in chat streaming functions to prevent memory leaks and improve performance.
- Added memory delta tracking in system snapshots for better monitoring of resource usage.
- Updated LLM router and service configurations to prevent unbounded internal accumulation and improve efficiency.
- Replaced the useDocuments hook with React Query for better caching and deduplication of document requests.
- Updated the ConnectorIndicator component to fetch document type counts using a new atom for real-time updates.
- Enhanced the useComments hook to manage batch requests more effectively, reducing race conditions and improving performance.
- Set default query options in the query client to optimize stale time and refetch behavior.
- improved search_knowledgebase_tool
- Added new endpoint to batch-fetch comments for multiple messages, reducing the number of API calls.
- Introduced CommentBatchRequest and CommentBatchResponse schemas for handling batch requests and responses.
- Updated chat_comments_service to validate message existence and permissions before fetching comments.
- Enhanced frontend with useBatchCommentsPreload hook to optimize comment loading for assistant messages.
- Replaced direct embedding calls with a utility function across various components to streamline embedding logic.
- Added enable_summary flag to several models and routes to control summary generation behavior.
- Added startTime and endTime properties to announcements for time-bound visibility.
- Introduced audience targeting to control who sees announcements (all, users, web_visitors).
- Updated related components and hooks to support new announcement features.
- Removed unused state tracking for dismissed announcements to streamline functionality.
- Changed announcement ID to a more descriptive format.
- Revised the announcement description for clarity.
- Updated the date to reflect the new announcement timing.
- Modified the link label and URL for better navigation to the announcements page.
Enables users to edit tool call arguments before execution in human-in-the-loop
workflows. Adds edit mode UI with form fields, grayscale styling, and subtle
pulse animations for pending approvals. Backend stub enhanced to verify edited
arguments are correctly passed through.
- Introduced a new endpoint for batch document status retrieval, allowing users to check the status of multiple documents in a search space.
- Enhanced the document upload process to return duplicate document IDs and improved response structure.
- Updated schemas to include new response models for document status.
- Removed unused attachment processing code from chat routes and UI components to streamline functionality.
