- Removed the creation and handling of raw LLM message entries in both start and finish functions.
- Updated message entry updates to only include reasoning messages, simplifying the logic and improving clarity.
- Added imports for various dashboard, metrics, and report tools to the analyst workflow.
- Updated the `runAnalystWorkflow` function to return a comprehensive output, including tool call results, charts created, and summary statistics.
- Implemented logic to extract tool calls and segment messages by user requests, improving the overall workflow output structure.
- Upgraded '@aws-sdk/client-s3' to version 3.873.0 across multiple packages.
- Introduced caching mechanisms for metric data retrieval in the getMetricDataHandler function.
- Updated API endpoints to support report_file_id for cache lookups and data retrieval.
- Enhanced error handling and logging for cache operations.
- Refactored related components to accommodate new caching logic and parameters.
- Simplified the `GeneratingContent` component to display a static loading message.
- Updated `ReportPageController` to determine if a report is being generated based on the current message context.
- Adjusted report status handling in the delta creation process to maintain 'loading' status during streaming.
- Enhanced logic in the modify reports helper to ensure file status reflects loading during streaming and only updates to completed or failed when all edits are finalized.
- Modified database query to preserve input order for new messages during updates.
- Introduced `executeMetricQuery` utility for standardized metric SQL query execution with retry logic.
- Updated `getMetricDataHandler` and metric tool execution functions to utilize the new query utility, improving error handling and result processing.
- Added metadata generation from query results to provide detailed insights into data structure.
- Refactored SQL validation to ensure only read-only queries are executed, enhancing data integrity.
Enhance SQL permission validation to include unauthorized columns in error messages. Update permission error message creation to handle both unauthorized tables and columns. Modify SQL execution functions to validate column permissions alongside table permissions, improving feedback for users lacking access.
- Changed the wording of elapsed time in reasoning messages from "min" to "minutes" for better readability.
- Updated the final reasoning message format to specify "Reasoned for" instead of "Total workflow time," enhancing user understanding of the output.
These changes contribute to a more user-friendly experience and maintain consistency in messaging across different tools.
- Added permission checks to metric file download handler
- Added permission checks to export-metric-data trigger task
- Created comprehensive tests for access control integration
- Updated AssetType enums to include report_file
- Resolved export conflicts in server-shared package
- Fixed AI package imports for new getPermissionedDatasets API
- Introduced start time tracking for tool operations in create, modify, and report tools to improve performance monitoring.
- Updated reasoning entries to include elapsed time for completed operations, enhancing user feedback.
- Refactored tool logic to ensure consistent handling of file statuses and improved clarity in reasoning messages.
- Enhanced logging for better traceability during tool execution.
These changes improve the overall user experience and maintainability of the toolset.
- Combined asset type enums from both branches
- Merged all database query exports
- Integrated access-controls package into server-shared
- Resolved conflicts in AI package instructions
- Updated import statements for communication and database tools to improve clarity and organization.
- Introduced constants for tool names in the `execute-sql` and `sequential-thinking-tool` modules to ensure consistent usage across the codebase.
- Enhanced the `createThinkAndPrepAgent` function to utilize these constants, improving maintainability and readability.
These changes streamline the integration of tools within the Think and Prep Agent, enhancing overall code organization.
- Updated tool name constants for visualization and communication tools to improve clarity and consistency.
- Modified the AnalystAgent to utilize these constants, ensuring better context handling during tool calls.
- Enhanced the STOP_CONDITIONS to reference the DONE_TOOL_NAME constant, improving maintainability.
These changes streamline the integration of tools within the AnalystAgent, enhancing overall code organization and readability.
- Added consumption of text streams in both `runAnalystAgentStep` and `runThinkAndPrepAgentStep` to ensure continuous processing of agent responses.
- Introduced detailed logging at various stages of the agent's execution to improve traceability and debugging.
- These changes enhance the robustness of the agent workflow and provide better insights during execution.
- Added support for fetching and managing user-specific datasets in the `analystAgentTask`, enhancing the context available for processing.
- Updated the `AnalystAgent` and `ThinkAndPrepAgent` schemas to include datasets, ensuring they are passed correctly in system messages.
- Implemented error handling for dataset retrieval to prevent workflow interruptions.
- Adjusted integration tests to accommodate the new datasets structure, ensuring comprehensive coverage.
These changes improve the agents' ability to utilize relevant datasets, enhancing their functionality and user experience.
- Introduced a new streaming mechanism for generating TODO lists, allowing for real-time updates and improved user experience.
- Added context handling for datasets in both `AnalystAgent` and `ThinkAndPrepAgent`, ensuring relevant data is included in system messages.
- Implemented new helper functions for managing TODO state and reasoning messages, improving code organization and clarity.
- Updated integration tests to validate the new streaming functionality and ensure consistent message roles.
These changes significantly enhance the functionality and maintainability of the TODO creation process within the agent workflow.
- Removed unused `steps` array from `createThinkAndPrepAgent` function to simplify the code.
- Updated message role from 'assistant' to 'user' in `create-todos-step` for better context alignment.
- Adjusted `valuesMessage` role in `extract-values-search-step` to 'user' when extracted values are present, enhancing message clarity.
These changes improve code clarity and ensure consistent message roles across agent steps.
- Replaced file system reads with direct imports of prompt text files in various agent and step files to improve performance and reduce complexity.
- Updated the `runDocsAgentStep` and `runDocsAgentWorkflow` functions to return `void` instead of structured outputs, simplifying their interfaces.
- Enhanced test cases to validate prompt loading without relying on file system checks, ensuring faster and more reliable tests.
- Cleaned up unused imports and optimized code structure across multiple files.
These changes aim to enhance code clarity, maintainability, and performance in the agent workflow and related components.
- Updated type imports from `CoreMessage` to `ModelMessage` for consistency across the identify assumptions step.
- Changed argument names from `args` to `input` and `result` to `output` in the integration tests to align with the new structure.
- Removed legacy step export for `identifyAssumptionsStepLegacy` to clean up the codebase.
- Adjusted the reporting tools to import `StatusSchema` from the correct path.
- Deleted outdated test files and helper functions related to the docs agent workflow to streamline the project structure.
These changes improve code clarity and maintainability while ensuring the integration tests reflect the latest design patterns.
dal
jacob-buster