- Added a new API endpoint to list collections in the Milvus vector database, providing metadata such as titles, descriptions, and sample data.
- Integrated the new Milvus router into the main application, ensuring it is accessible through the API.
- Updated the JSON serialization logic to handle decimal precision for financial data, maintaining accuracy in API responses.
- Enhanced the frontend with a new Knowledge Base page to display vector collections, including sample previews and collection details.
- Updated routing and menu structures to include the new Knowledge Base feature, improving navigation within the application.
- Revised README.md to clarify the roles of various documents in the defense process, emphasizing the new structure for the presentation script and demo materials.
- Added a new print-friendly README.md for the defense script, detailing the steps for printing and PDF generation.
- Introduced a new HTML file for the presentation, enhancing the visual layout and ensuring consistency with the updated content.
- Updated the content in existing documents to reflect the latest changes in the presentation flow and materials, ensuring all resources are aligned for the upcoming defense.
- Fixed three key defects in multi-turn dialogue handling: improved RAG to utilize merged messages, enhanced intent classification with recent memory, and ensured proper merging of chat and consultation memories.
- Closed five existing test bugs unrelated to the current round, including parameter adjustments and assertion corrections in various test files.
- Finalized adjustments in the F-β selection process to align race condition handling in test cases, ensuring all relevant tests pass successfully.
This update enhances the coherence of multi-turn dialogues and improves the reliability of the testing framework.
- Implemented `_merged_items` and `_merged_memory_text` functions to consolidate consult and chitchat memories, improving context awareness in intent classification and response generation.
- Updated intent prompts to include recent dialogue history, aiding in the resolution of ambiguous user queries.
- Enhanced `search_knowledge` tool to utilize context window for better query understanding, addressing issues with omitted references in user inputs.
- Fixed existing test cases to reflect changes in intent constants and ensure accurate context handling during tests.
This update significantly improves the handling of multi-turn dialogues, ensuring a more coherent and contextually aware interaction for users.
- Revised MEMORY.md to correct the status of kb_product_rules, clarifying that it has not been populated in the vector database as previously stated.
- Enhanced TODO.md with detailed descriptions of completed tasks and their corresponding documentation paths for better tracking of project deliverables.
- Added new files for daily meeting minutes, development plans, table design documents, API documentation, presentation materials, and requirements documentation, ensuring all necessary materials are indexed and easily accessible for the upcoming defense.
- Updated README files to reflect the latest changes and provide a comprehensive overview of submission materials for the defense, aligning with client requirements.
- Updated test files to import `AgentSessionLocal` from `advisor_db` instead of directly, preventing session binding to the real database during tests.
- Fixed 6 test cases to use the new login token utility, ensuring consistency across authentication methods.
- Adjusted customer risk codes in `test_convert_confirm.py` to reflect changes in customer classification (C3 to C4).
- Verified that changes resulted in zero database pollution during test runs, maintaining integrity of the testing environment.
- Documented findings and updates in the relevant test logs and memory files, ensuring clarity on the current state of tests and defects.
- Introduced `_recent_days_series_hint` to handle queries related to "最近N天" for time series data aggregation.
- Added `_cn_num_to_int` function to convert Chinese numerals to integers for better query parsing.
- Updated `_nl_sql_hints` to incorporate the new hint generation logic, ensuring accurate SQL output for recent days queries.
- Enhanced documentation to reflect these changes and improve clarity on the new functionalities.
Dev login no longer honors injected roles; self-service simulate/convert
blocks R4 disclosure grades like the UI and chat already do. Reuse of a
convert idempotency key with a different body returns 409. CT6 redeem qty
is derived from T+2 lots instead of a fixed 35000; CT7-05 and CT10-07
assertions follow. Update project memory and v1.1 post-fix test artifacts.
- Completed 203 test cases with 162 passing, 6 failing, and 2 skipped, identifying 2 critical defects (P0: authentication privilege escalation, P1: suitability disclosure not enforced).
- Enhanced test coverage by verifying front-end rendering values against back-end raw responses, addressing previous gaps in validation.
- Documented findings and defects in the new test log and README files, ensuring clarity on test outcomes and areas for improvement.
- Updated the TODO list to reflect the current state of defects and testing priorities, emphasizing the need for immediate attention to identified issues.
This round of testing significantly improves the robustness of the customer trade functionality, ensuring compliance and security standards are met.
- Introduced `pending_trade` handling in the chat API to manage trade requests more effectively.
- Updated the `submit_trade_api` to allow advisors to access customer trades based on assigned roles.
- Added new methods in `GatewayRepository` for managing core holdings during trade subscriptions and redemptions.
- Implemented context-aware trade dialogue management in the customer service layer to improve user experience during multi-turn interactions.
- Enhanced the tool service to support trade actions and suitability checks, ensuring accurate processing of user requests.
This update significantly improves the trade interaction flow, providing a more robust and user-friendly experience for customers engaging in trading activities.
- Added new entry for "STAFF-20003" role in `jwt_service.py` to support additional user permissions.
- Revised the demo SOP documentation to reflect updated processes and clarify the presentation flow, including changes to the demo script and internal guidelines.
- Enhanced the presentation materials with a new HTML slide deck for the advisor agent demo, ensuring a cohesive visual representation of the features and capabilities.
- Updated various documentation files to align with recent changes in the advisor agent functionalities and testing baselines.
This update improves the clarity and usability of the demo materials while ensuring that the documentation accurately reflects the current state of the project.
- Introduced `convert_meta_api` endpoint to fetch the latest NAV date for conversion processes, restricted to users with the "risk_officer" role.
- Updated `created_at` field in `AgentMessage` to use UTC timezone for consistency in timestamp handling.
- Added `get_max_product_nav_date` method in `CoreReadOnlyRepository` to support the new API functionality.
- Enhanced Milvus template loading in `MilvusTemplateVectorStore` to ensure collections are loaded when they exist.
This update improves the API's capability to handle conversion metadata and ensures accurate timestamp management across the application.
- Updated KYC session endpoints to remove the ApiResponse response model, simplifying the API structure.
- Enhanced clarity in the KYC session creation, retrieval, chat, and completion methods by focusing on the payload and response data directly.
- Improved code readability and maintainability by streamlining the endpoint definitions.
- Merged the `integrate/advisor-agent` branch into the `merger`, enhancing the advisor agent's capabilities with compliance, KYC, and script templates.
- Updated the testing baseline to reflect 926 passed tests, with 65 failures concentrated in the advisor agent's `test_sprint*` cases.
- Introduced new migration scripts for advisor-related database structures, ensuring smooth integration and data management.
- Enhanced documentation to include the new API structure and integration details, providing clarity for future development.
This update significantly advances the advisor agent's functionality while maintaining a structured approach to integration and testing.
- Added new modules for advisor compliance, KYC sessions, and script templates, enhancing the advisor agent's capabilities.
- Implemented a comprehensive API structure under the `/api/advisor-agent` prefix, ensuring clear organization and access to new features.
- Established database models and repositories for compliance rules and KYC sessions, facilitating robust data management.
- Integrated exception handling and response models to improve error management and user feedback.
- Updated settings to include new configurations for compliance and KYC features, ensuring flexibility and adaptability.
This update significantly expands the advisor agent's functionality, providing essential tools for compliance and customer interaction while maintaining a structured API design.
- Merged `xinghuo/advisor-agent` into the `merger` branch, establishing a new API prefix `/api/advisor-agent` to avoid conflicts with existing endpoints.
- Implemented a comprehensive implementation plan detailing the integration steps, including conflict resolution, database migrations, and service adaptations.
- Introduced new files for advisor compliance, script templates, KYC, and market alerts, ensuring a cohesive addition to the existing architecture.
- Updated documentation to reflect the new structure and integration process, enhancing clarity for future development and maintenance.
This integration significantly expands the capabilities of the merger, providing a robust framework for advisor-related functionalities while maintaining compliance and operational integrity.
- Added new endpoints to the analyst API for managing assets, including `GET /assets` to list assets and `POST /assets/{kind}/{asset_id}/publish` to publish assets.
- Introduced `DictAmbiguityCheckRequest` schema for checking metric ambiguities, enhancing the analyst's ability to clarify definitions and aliases.
- Implemented `detect_dict_ambiguity` function to analyze potential ambiguities in metrics, providing structured feedback for users.
- Updated `AnalystAgent` to support the new asset management functionalities and ambiguity detection logic, improving overall user experience.
- Enhanced existing schemas and services to accommodate new features, ensuring robust data handling and validation.
This update significantly improves the analyst API's capabilities, allowing for better asset management and clarity in metric definitions.
- Introduced a new `/analyze` endpoint in the analyst API to process analysis requests, allowing users to receive textual interpretations and chart specifications based on provided prompts.
- Enhanced `analyst_schemas.py` with `AnalyzeRequest` and `ChartSpec` models to structure analysis requests and validate chart specifications.
- Implemented chart validation logic in a new `analyst_chart.py` service, ensuring that chart types and fields are correctly specified and conform to allowed values.
- Updated `AnalystAgent` to handle analysis requests, integrating the new logic for generating responses based on user prompts and data availability.
- Added unit tests to verify the functionality of the new endpoint and validation mechanisms, ensuring robustness and reliability.
This update significantly enhances the analytical capabilities of the application, providing users with improved tools for data interpretation and visualization.
- Updated `ready.py` to include a health check for the new `products_nav_history` endpoint, ensuring system readiness.
- Enhanced the `ProductNavChartPanel` component to visualize historical NAV data with various charting options, including line and column charts.
- Introduced new utility functions for filtering and aggregating NAV data, improving data handling in the frontend.
- Updated tests to verify the inclusion of the new `products_nav_history` check in the API response.
- Improved documentation to reflect recent changes and the new testing baseline of 833 passed tests, indicating enhanced stability.
This update significantly improves the product API by providing access to historical NAV data and enhancing user insights through visualizations.
- Added `list_nav_history` method in `CoreReadOnlyRepository` to retrieve historical NAV data for products over a specified number of days.
- Introduced `get_nav_history` endpoint in `product_service` to return historical NAV sequences, improving product data accessibility.
- Updated `products.py` to include new API endpoint for fetching NAV history, ensuring compliance with access control.
- Enhanced `ready.py` to include a health check for the new functionality, ensuring system readiness.
- Updated documentation to reflect the new testing baseline of 833 passed tests, indicating improved stability and functionality across the application.
This update significantly enhances the product API by providing access to historical NAV data, improving user insights into product performance.
zhanghongyu_0626
GaoYiYuan_0626