- 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.
- Introduced `createReports` and `modifyReports` tools, enabling users to create and modify reports with improved state management.
- Added new schemas for report input and output, enhancing type safety and clarity.
- Implemented helper functions for transforming report state and generating reasoning entries.
- Improved test coverage for the new reporting functionalities to ensure robust integration.
These changes streamline the reporting process and enhance overall code maintainability.
- Updated the `modifyDashboardsDelta` and `modifyDashboardsFinish` functions to streamline state handling and improve message entry updates.
- Refactored helper functions for better clarity and type safety in dashboard modifications.
- Introduced new schemas for state management, enhancing type definitions for dashboard files and their statuses.
- Improved test coverage to ensure robust functionality and integration of the modify dashboards tool.
These changes optimize the dashboard modification process and enhance code maintainability.
- Removed unused properties from the dashboard state and output schemas for clarity.
- Introduced a new state file schema to better represent dashboard files.
- Updated helper functions to streamline file transformation and reasoning message creation.
- Improved type safety by utilizing the newly defined `StatusSchema`.
These changes optimize the dashboard creation process and enhance code maintainability.
- Updated the `createDashboardsStart` function to improve message handling and reasoning entry creation.
- Refactored helper functions for better clarity and type safety in dashboard creation.
- Enhanced web search tool execution to include additional parameters for improved functionality.
- Updated tests to reflect changes in tool execution and ensure robust integration.
These changes streamline the dashboard creation process and enhance the web search tool's capabilities.
- Added `createCheckOffTodoListTool` and `createUpdateClarificationsFileTool` to enhance planning capabilities.
- Refactored existing tools to utilize the new planning tools, improving code organization and maintainability.
- Updated tests to reflect changes in tool creation and execution, ensuring robust functionality.
These changes streamline the management of todo lists and clarification questions, enhancing overall tool usability.
- Introduced the `createWebSearchTool` function to streamline web search capabilities.
- Updated various metrics tools to improve type handling and input processing.
- Refactored metrics delta and finish functions to utilize `ToolCallOptions` for better integration.
- Removed deprecated report creation and editing tools to clean up the codebase.
These changes enhance functionality and maintainability across the tools.
- Added the `GPT5` import to the analyst agent for enhanced functionality.
- Updated the `createModifyDashboardsStart` function to utilize `ToolCallOptions` for better input handling.
- Refactored dashboard and metrics tools to use helper functions for descriptions, improving maintainability.
- Ensured consistent type handling and removed redundant code in metrics delta processing.
These changes streamline the tools and improve the overall code quality.
- Disabled specific TypeScript ESLint rules to allow for more flexibility in type definitions.
- Removed unused socket query files and related types to streamline the codebase.
- Enhanced various components and layouts for better performance and readability.
These changes improve code maintainability and reduce clutter in the project.
- Introduced a section on tool calling rules to ensure proper usage of available tools.
- Added clarifications to the TODO list items regarding user requests, emphasizing the need to determine if the user is asking for a single metric, a report, or a dashboard.
These updates improve the clarity and functionality of the analyst agent's prompt, ensuring more accurate task breakdowns.
- Removed unused import for `createMetricsRawLlmMessageEntry` in visualization tools.
- Introduced Zod schemas for `Dashboard` and `DashboardConfig` to enhance type validation and structure.
- Cleaned up the interface definitions for better clarity and maintainability.
These changes improve the robustness of the dashboard configuration and streamline the codebase.
- Deleted references to the `@mastra/core` package from various configuration files.
- Removed multiple unused test files and helper functions related to visualization tools, including axis validation and version history management.
- Cleaned up import statements for better organization and readability.
These changes streamline the codebase by eliminating unnecessary dependencies and improving maintainability.
- Added a check to ensure the DataSource is available before executing SQL statements, throwing an error if not.
- Refactored test mocks to use `vi.mocked` for better clarity and consistency in handling DataSource connection errors.
- Removed unnecessary whitespace for cleaner code.
These changes enhance the robustness of SQL execution and improve the reliability of related tests.
- 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>
dal
Nate Kelley
jacob-buster
Nate Kelley