- Updated the `dashboard` function in `analyst.py` to include additional metrics for different user roles, improving data visibility for analysts, customers, advisors, and risk officers.
- Introduced a new `prepare_customer_stream` function in `customer_service.py` to facilitate streaming responses for customer interactions, enhancing the chat experience.
- Added new API endpoints in `analyst.ts` for fetching dashboard metrics and managing analyst assets, streamlining data handling and user interactions.
- Updated frontend components to support new dashboard features and asset management, ensuring a cohesive user experience across the application.
This update significantly improves the functionality and usability of the analyst and customer service features, providing users with enhanced tools for data analysis and interaction.
- Added a new visitor chat API endpoint (`/api/chat/visitor`) to allow unauthenticated users to engage in conversations without requiring customer data.
- Introduced a visitor context dependency to manage visitor interactions seamlessly.
- Enhanced the chat API to support explicit session termination and improved response handling for customer service interactions.
- Updated the database configuration to include Redis client support for caching visitor data.
- Added a new customer note repository to persist user notes independently of the L1 profile slots.
This update significantly improves the customer service experience by enabling visitor interactions and ensuring efficient data handling for both registered and unregistered users.
- Introduced a new function `_assistant_content_for_persist` to append disclaimers to assistant responses, ensuring consistency in stored content.
- Updated `chat_api` and `chat_stream_api` to utilize the new function for managing assistant replies, improving data integrity.
- Added tests to verify the correct handling of disclaimers in various scenarios, ensuring compliance with expected output.
This update enhances the chat system's reliability by ensuring that disclaimers are consistently applied to assistant responses, improving user experience and data accuracy.
- Modified `chat_stream_api` to use `new_trace()` instead of an empty string for `trace_id`, enhancing traceability.
- Added tests to verify the correct generation and propagation of `trace_id` in responses, ensuring no empty trace IDs are sent to clients.
This update improves the tracking of chat sessions and ensures compliance with traceability standards.
- Added `auth.py` for mock login and JWT issuance.
- Introduced `chat.py` for handling chat requests with role-based access control.
- Enhanced `main.py` to include new routers and middleware for tracing.
- Implemented input validation in `input_guard.py` to prevent SQL injection.
- Created repositories for managing agent sessions and audit logs.
- Added exception handling for authorization errors.
- Updated settings to include JWT configuration.
- Introduced tests for authentication and input validation.
zhanghongyu_0626