- Introduced GitHub routes for handling installation callbacks and token management.
- Implemented middleware for validating GitHub webhook requests.
- Added tests for new handlers and middleware to ensure functionality.
- Enhanced sandbox utilities to support GitHub token usage for authenticated operations.
- 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.
dal