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>
- Introduced new enum values for Composio connectors: COMPOSIO_GOOGLE_DRIVE_CONNECTOR, COMPOSIO_GMAIL_CONNECTOR, and COMPOSIO_GOOGLE_CALENDAR_CONNECTOR.
- Updated database migration to add these new enum values to the relevant types.
- Refactored Composio integration logic to handle specific connector types, improving the management of connected accounts and indexing processes.
- Enhanced frontend components to support the new Composio connector types, including updated UI elements and connector configuration handling.
- Improved backend services to manage Composio connected accounts more effectively, including deletion and indexing tasks.
- Removed the deprecated create_connector_indexed_notification method from NotificationService.
- Introduced new notification types and schemas in notification.types.ts to standardize notification handling.
- Updated useNotifications hook to utilize the new notification type definitions.
- Updated the ConnectorIndicator component to accurately reflect active connectors and their document counts.
- Improved the display of standalone document types in the ActiveConnectorsTab, allowing users to view all documents easily.
- Enhanced the ConnectorCard to show last indexed dates and formatted document counts for better clarity.
- Adjusted tooltip and aria-labels for accessibility and consistency across attachment upload components.
- Preserved newlines in URL input for webcrawler configuration to ensure proper backend handling.
- Changed Linkup API link from linkup.ai to linkup.so in the connector popup.
- Removed unused IconSparkles and replaced it with Luma SVG in the connector icons.
- Updated image properties for Linear, GitHub, Google Calendar, Google Gmail, and Google Drive connectors to ensure consistent sizing.
- Replaced old SVG files for GitHub, Google Calendar, Google Drive, Google Gmail, and Linear with new versions for improved visuals.
- Implement CirclebackConnectForm for user input and configuration
- Update connector benefits to include Circleback features
- Add CirclebackConfig component for webhook configuration
- Integrate Circleback into connector selection and management UI
- Update connector constants and document mappings for Circleback
- Use Next.js Image component for SVG icons (20x20px)
- Replace 16 Tabler/Lucide icons with branded SVGs
- Add support for Teams, Zoom, YouTube string cases
- Clean up unused icon imports
- Maintain fallback for connectors without SVG icons
- Removed all references to the Serper API from the codebase, including related components, hooks, and schemas.
- Updated the `pyproject.toml` to reflect the new version of `chonkie` and other dependencies.
- Cleaned up the configuration and connector management to streamline the application.
- Enhanced the editor to handle new note creation directly, initializing with an empty state.
- Updated save functionality to create a note first if it's new, followed by saving the content.
- Modified breadcrumb navigation to accommodate new notes and improve user experience.
- Removed the old note creation page to streamline the editing process.
- Added error handling and dynamic title updates for better feedback during note creation.
- 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 BAIDU_SEARCH_API connector type to support Chinese web search
- Implement search_baidu() method in connector_service.py
- Add frontend configuration page for Baidu Search API
- Create Alembic migration for new enum values
- Add validation rules and agent integration
- Support configurable model, search source, and deep search options
- Update .gitignore to exclude .env.local and other env files
Addresses integration with Chinese search ecosystem for better local market support.
Baidu AI Search provides intelligent search with automatic summarization.
