- Implemented `withStepRetry` utility to handle retries for various steps in the analyst workflow, including creating todos, extracting values, generating chat titles, and routing analysis types.
- Enhanced error handling by logging retry attempts and errors for better debugging.
- Introduced a new utility module for step retry functionality, including options for maximum attempts and exponential backoff delays.
- Added tests for the new retry utilities to ensure correct behavior under various scenarios.
- Added .actrc to .gitignore to prevent local configuration from being tracked.
- Updated cli-release.yml to specify paths for apps and packages, enhancing workflow triggers.
- Improved permissions in cli-release.yml for better access control.
- Enhanced update-brew-tap.yml with detailed summary creation for deployment results.
- Introduced README.md for GitHub Actions, providing usage instructions and supported platforms.
- Added deploy and dry-run actions for better deployment management.
- Updated error handling in CLI commands for clearer messaging and improved user experience.
- Bumped CLI version to 0.3.0 in package.json to reflect recent changes.
Updated DEFAULT_CACHE_OPTIONS in analyst and think-and-prep agents to include gateway options. Added gateway settings in multiple steps including analysis-type-router, create-todos, extract-values, generate-chat-title, flag-chat, format-follow-up, format-initial, and identify-assumptions steps to restrict provider usage to 'anthropic'. This enhances control over the AI model interactions.
- 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.
- 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.
- Added new properties (chatId, organizationId, dataSourceId, dataSourceSyntax, userId) to the ThinkAndPrepAgentOptionsSchema for improved tracking and functionality.
- Renamed createTodos function to runCreateTodosStep for consistency across step functions.
- Updated integration tests to reflect the new function names and ensure proper functionality.
- Removed outdated test files related to the think-and-prep step, reducing clutter and focusing on relevant tests.
These changes improve the modularity and clarity of the agent's configuration while enhancing the overall maintainability of the codebase.
- Changed the declaration of AnalystAgentOptionsSchema and AnalystStreamOptionsSchema to export them for use in other modules.
- Removed the test files related to analyst-agent steps, streamlining the codebase and improving maintainability.
This update enhances the modularity of the agent's configuration schemas while cleaning up unused test files.
Wells Bunker
Nate Kelley
dal