- Added userId, chatId, organizationId, dataSourceId, and dataSourceSyntax to the integration tests for the Think and Prep Agent and Mark Message Complete Step.
- Cleaned up import statements for better organization and readability.
- Ensured that the tests reflect the latest schema changes for improved tracking and functionality.
These updates enhance the clarity and robustness of the integration tests, aligning them with recent changes in agent options.
- 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- Removed outdated test files related to the think-and-prep step, reducing clutter and focusing on relevant tests.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.
- Deleted multiple test files related to the analyst step, including tests for database save, deduplication, failed tool handling, file ID mapping, and file selection.
- This cleanup reduces clutter in the codebase and focuses on maintaining relevant tests.
These changes aim to streamline the testing process and improve overall maintainability.
- 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.
- Removed duplicate import of ModelMessage in create-dashboards-execute.ts for clarity.
- Updated createDashboardsReasoningMessage function to conditionally include version_number only if defined, improving the handling of dashboard file properties.
All changes aim to streamline the code and enhance maintainability.
Updated test expectations in list-files-tool-streaming.test.ts to match the actual structure of MessageEntry objects being passed to updateMessageEntries. The implementation passes complete objects with all properties rather than partial objects, and args are serialized as JSON strings.
Changes:
- Updated test expectations to check for complete MessageEntry objects instead of partial matches
- Fixed args field to expect JSON strings instead of objects
- Added missing properties like type, result, and started_at
- Fixed state.paths expectations for partial JSON parsing scenarios
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Introduced new file selection logic to extract and prioritize files based on their status and relationships.
- Added helper functions for failure indicator checks and file extraction from reasoning history.
- Updated the communication tools to utilize the new file selection methods, improving response message creation.
- Refactored file tools to follow a consistent factory pattern for better maintainability and clarity.
All tests updated and passing for new functionality.
- Update create-file-tool.ts to use factory function from create-files-tool.ts
- Fix docs-agent to properly use factory functions for file tools
- Remove experimental_context usage in favor of proper context passing
- Fix lint issues with type definitions in transform helper
- All tests passing for create-files-tool functionality
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added functionality to retrieve and prepend the current working directory to the repository tree output, improving context for users.
- Updated runtime context to store the modified tree structure with location information.
- Removed outdated integration tests and streamlined the test suite for better maintainability.
This update enhances the usability of the repository tree feature by providing clearer context during execution.
- Introduced an AbortController to manage idle tool execution, allowing for graceful aborting of the documentation process.
- Moved tracking variables outside the try block for better state management.
- Updated error handling to gracefully manage abort scenarios, ensuring clear logging and returning final state information.
- Adjusted integration tests to reflect changes in the docs agent workflow, improving overall robustness and reliability.
This update enhances the responsiveness of the docs agent during execution and improves error handling for better user experience.
dal