- Introduced `TemplateService` for managing SQL templates, allowing for parameterized queries based on user input.
- Added functionality to automatically reload templates upon asset creation in `analyst.py`.
- Enhanced `CacheService` to support table generation bumping, ensuring cache invalidation on data changes.
- Updated `RiskRepository` and `GatewayRepository` to trigger cache invalidation for relevant operations.
- Expanded `analyst_schemas.py` to include new fields for template tracking in response metadata.
- Created seed SQL script for populating initial templates and added unit tests for template rendering logic.
This update significantly improves the efficiency of query handling by leveraging SQL templates, reducing reliance on LLM for common queries.
- 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.
- Replaced `get_auth_context` with `get_platform_auth_context` in `analyst.py` to enhance authentication handling.
- Added a new smoke test script `smoke_analyst.py` for testing the data analysis agent with both fake and live LLM configurations.
- Updated TODO documentation to reflect the completion of Scope B smoke tests, ensuring clarity on testing status.
This update improves the authentication mechanism and introduces a comprehensive testing approach for the data analysis agent.
- Introduced `analyst_auth_adapter.py` for managing authentication context and access control for the data analysis agent.
- Added new API endpoints in `analyst.py` for chat, dashboard, asset management, and metrics, utilizing the new authentication context.
- Created Pydantic models in `analyst_schemas.py` for request and response structures, ensuring consistent data handling.
- Updated SQL guard logic in `sql_guard.py` to enforce access restrictions based on user roles and contexts.
- Implemented migration scripts for new database tables related to the data analysis agent, enhancing data management capabilities.
- Removed legacy authentication code from `auth.py`, streamlining the authentication process.
This update significantly enhances the data analysis capabilities, providing a robust framework for querying and managing data securely.
- 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.
- Updated the login endpoint to utilize shared JWT issuer/audience settings, improving consistency across modules.
- Introduced error handling for unknown accounts during token issuance, raising an UnauthorizedError when necessary.
- Enhanced traceability by adding trace and request IDs to responses, ensuring better tracking of requests.
- Refactored exception handling in middleware to properly bubble up application-specific errors, preventing them from being swallowed.
- Added new utility functions for generating trace headers to improve debugging capabilities.
This update strengthens the authentication process and enhances error visibility, contributing to a more robust and maintainable codebase.
- 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
zyi
GaoYiYuan_0626