- Trigger opening statement on new conversation in run/run_stream
- Fix /opening endpoint to support workflow app type
- Fix features field missing in workflow config release snapshot
- Knowledge node returns citations alongside chunks
- Aggregate citations from all knowledge nodes in result builder
- Filter citations based on features.citation.enabled switch
- Fix WorkflowConfigCreate circular import in app_schema
- Removed try-except block for importing `audit_logger` and directly imported it.
- Removed redundant checks for `audit_logger` being `None` before logging operations.
- Added a check in `MemoryPerceptualService` to return `None` if `model_config` or `llm` is `None`.
- Add memory_config_id extraction and assignment when creating new end users in public share chat
- Introduce get_or_create_end_user_with_config method to handle memory config setup in single transaction
- Add batch_update_memory_config_id_by_app method for bulk updating end user memory configs
- Rename _update_endusers_memory_config_by_workspace to _update_endusers_memory_config_by_app for correct scope
- Update app publish flow to use app_id instead of workspace_id for memory config updates
- Remove unused actual_end_user_id variable in langchain_agent
- Ensures end users are properly associated with memory configs on creation and during app updates
- Replace English validation messages with Chinese localized strings
- Update "model config" to "模型配置"
- Update "memory config" to "记忆配置"
- Enhance error message with detailed context about missing configurations
- Add BizCode.CONFIG_MISSING error code for better error handling
- Include missing_params in error context for debugging and client-side handling-
- Change extract_document_text from private to instance method in multimodal service for external access
- Optimize knowledge base search logic to improve parallel retrieval performance
- Migrate historical workflow queries from legacy ORM Query API to SQLAlchemy 2.0 select() + execute()
- Limit query fields and use pagination to reduce returned data, improving performance
- Preserve original ordering and filtering logic
- Remove unauthenticated end_user_controller and its router registration
- Move end user creation logic to authenticated memory_api_controller endpoint
- Add create_end_user method to MemoryAPIService with workspace authorization
- Fix retrieve_nodes import in read_graph to use correct function reference
- Consolidate end user management under authenticated memory API with API key scoping
