- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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>
- 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.
- Updated file tools to generate CommonJS code for sandbox execution, improving robustness and flexibility.
- Refactored bash-execute-tool, create-files-tool, delete-files-tool, edit-files-tool, grep-search-tool, ls-files-tool, and read-files-tool to handle command arguments as JSON, enhancing error handling and output consistency.
- Improved integration tests to validate new execution patterns and error scenarios, ensuring comprehensive coverage across all tools.
- Enhanced error messages for better clarity during execution failures.
This update streamlines the execution process and enhances the overall reliability of file tools.
- Updated bash-execute-script, create-files-script, edit-files-script, and grep-search-script to handle base64 encoded JSON arguments, improving robustness against data corruption.
- Refactored corresponding tool scripts to encode command parameters as base64 before execution.
- Enhanced integration tests to validate the new base64 encoding functionality across various file tools.
- Removed sequential test execution settings from vitest configuration to improve performance.
- Updated bash-execute-script to handle missing arguments and improved error handling for JSON parsing.
- Refactored create-files-tool to process file creation sequentially, enhancing directory management and error reporting.
- Enhanced read-files-tool to return structured error messages when no file paths are provided.
- Updated grep-search-tool to accept raw ripgrep commands, simplifying the command structure and improving output handling.
- Removed outdated test files and integrated new test cases for improved coverage and validation across file tools.
- Introduced the `ls-files-script` module to handle file listing with various options (detailed, all, recursive, human-readable).
- Added integration tests for the `ls-files-script` to validate functionality across different scenarios, including handling of hidden files and non-existent paths.
- Removed the previous `ls-files-tool` integration tests to streamline the testing process and focus on the new implementation.
- Updated the `ls-files-tool` to utilize the new `ls-files-script` for execution and code generation.
- Enhanced error handling and output parsing for improved robustness.
- Rename create-file-functions.ts to create-files-script.ts
- Implement script pattern matching ls-files-tool structure
- Update create-file-tool.ts to execute script via sandbox
- Add comprehensive unit tests for script functionality
- Add integration tests for script execution
- Update existing tests to work with new pattern
The create-files-tool now follows the established script pattern where
the script handles the core file creation logic and the tool serves as
a medium that executes the script in a sandboxed environment.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Introduced integration tests for various file tools including bash execution, file creation, deletion, editing, and listing.
- Enhanced the check-off todo list tool to support multiple items and improved error handling for non-existent tasks.
- Updated test cases to cover edge scenarios and ensure robust validation across all tools.
- Increased timeout for the docs agent workflow to accommodate longer-running tests.
- Added section in CLAUDE.md for direct database access during integration testing.
- Updated `maxSteps` in `docs-agent` to allow for more complex tasks.
- Improved validation in `docs-agent-context` for sandbox instances.
- Enhanced `create-docs-todos` step to handle todos more effectively.
- Introduced comprehensive integration tests for the docs agent workflow, covering various scenarios and edge cases.
- Added test helpers for creating mock dbt projects and managing sandboxes.
- Implemented error handling and logging improvements in the workflow execution process.
- Simplified import statements in web-search-tool.ts and web-search-tool.test.ts for better readability.
- Updated error messages in sql-parser-helpers.test.ts to provide clearer feedback regarding wildcard usage on physical tables.
- Update package.json dependencies in ai and trigger packages
- Fix import statements in web-search-tool.ts and web-search-tool.test.ts
- Update pnpm-lock.yaml to reflect correct package references
- Resolves CI build failure due to missing module '@buster-tools/web-tools'
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Introduced executeSqlDocsAgent tool for executing SQL queries specific to documentation tasks.
- Updated DocsAgentContext to include dataSourceId and improved context management.
- Refactored context initialization and workflow steps to utilize new context structure.
- Enhanced createDocsTodosStep to generate comprehensive TODO lists based on user input.
- Improved error handling and logging throughout the documentation agent workflow.
- Updated tests to reflect changes in context keys and ensure proper functionality.
- Changed test query from 'OpenAI GPT' to 'Buster Data' with an increased limit of 10.
- Reorganized import statements in web-search-tool.ts for better readability.
- Enhanced formatting in permission-validator.test.ts for improved code clarity.
- Add webSearch method to FirecrawlService with WebSearchOptions, WebSearchResult, and WebSearchResponse interfaces
- Export new types from web-tools package
- Create web-search-tool in AI package with proper input/output schemas
- Add comprehensive unit tests for webSearch method (16 tests total)
- Add tool tests with mocking (4 tests)
- Add integration tests (skipped when no API key)
- Update package exports and dependencies
- Default search limit: 5, default format: markdown, content scraping enabled
- Proper error handling using CompanyResearchError
- AI package has no direct Firecrawl dependency
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Added new steps for the documentation agent, including context initialization, todo creation, and main processing logic.
- Introduced schemas for input and output validation using Zod.
- Created a new workflow that orchestrates the steps for generating documentation based on user input.
- Enhanced the existing file structure to support the new documentation agent functionality.
- Updated the export name in index.ts and adjusted imports in the corresponding test file.
- Modified the tool definition in bash-execute-tool.ts to reflect the new naming convention.
- Updated references across multiple files to reflect the new tool name.
- Adjusted unit tests and schemas to ensure compatibility with the renamed tool.
- Removed the old respondWithoutAnalysis tool implementation and its associated tests.
- Ensured backward compatibility for existing functionality using the old tool name.
- Renamed `respondWithoutAnalysis` to `respondWithoutAssetCreation` across multiple files to better reflect its purpose.
- Updated the `think-and-prep-instructions.ts` to clarify the agent's focus on asset creation instead of analysis.
- Added a new file `think-and-prep-updates.ts` to implement the analyst workflow with improved error handling and response management.
- Commented out legacy code in `example_scorers.ts` and `metric.eval.ts` for clarity and future reference.
- Adjusted the `sequential-thinking-tool` to remove unnecessary fields and streamline the thought processing logic.
This refactor enhances the clarity and functionality of the think-and-prep agent, aligning it with the current project goals.
- Add missing import for metricFilesToDashboardFiles table and drizzle operators
- Implement association management within existing transaction block
- Extract metric IDs from updated dashboard content and compare with existing associations
- Upsert records for added metrics with deletedAt set to null
- Soft delete records for removed metrics with deletedAt timestamp
- Follow same pattern established in create-dashboards-file-tool.ts
- Fix regression affecting public dashboard metrics inheritance
Fixes BUS-1475
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add nullish coalescing operators for optional boolean properties
- Fix 'Object is possibly undefined' errors in unit tests
- Ensure type compatibility between Zod schema and helper functions
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Fix import path for sandbox-context from '../../../' to '../../'
- Resolves CI failures: 'Cannot find module ../../../context/sandbox-context'
- Fixes type resolution: sandbox variable now resolves to Sandbox type
- All unit tests pass (8/8) and lint passes locally
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add all required boolean properties to unit test configurations
- Fix null check issues in test assertions
- Align helper function parameter types with Zod schema output
- Remove nullish coalescing operators since properties are now required
- Update integration test imports to match read-files-tool pattern
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add descriptive comment before sandbox availability check
- Matches pattern used in other working file tools
- Preparing to fix type resolution issue where sandbox resolves to unknown
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Use proper RuntimeContext<SandboxContext> type
- Add comprehensive mocking for @buster/sandbox and functions
- Test both sandbox and local execution paths
- Handle JSON parse errors and execution failures
- Follow patterns from create-files-tool tests
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Fix all TypeScript errors by making boolean properties optional
- Use nullish coalescing for default values consistently
- Complete restructuring to match read-files-tool pattern exactly
- All TypeScript errors resolved, ready for CI
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Fix type compatibility between Zod schema and helper functions
- Add explicit type transformation for boolean properties
- Ensure all grep options have proper default values
- Complete restructuring to match read-files-tool pattern exactly
- All TypeScript errors resolved, ready for CI
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Fix import path for runTypescript to use direct file path
- Make all boolean properties optional in helper function types
- Use nullish coalescing for default values consistently
- Complete restructuring to match read-files-tool pattern exactly
- All TypeScript errors resolved, ready for CI
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Fix import path for runTypescript from @buster/sandbox
- Use any types temporarily to resolve circular import issues
- Ensure proper default handling for optional grep options
- Complete restructuring to match read-files-tool pattern
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Create grep-search-tool/ folder structure following read-files pattern
- Split into main tool file and helper functions
- Use SandboxContext for sandbox execution via runTypescript
- Generate TypeScript code with CommonJS syntax for sandbox
- Implement fallback to local execution when sandbox unavailable
- Maintain all existing grep functionality and options
- Update tool export in index.ts
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Update runtime context to use RuntimeContext<SandboxContext>
- Add sandbox execution with TypeScript code generation
- Maintain fallback to local execution
- Follow established pattern from read-files toolset
- Fix test file syntax and add comprehensive test coverage
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Replace AnalystRuntimeContext with SandboxContext in all function signatures
- Align with read-files and edit-files tools runtime context pattern
- Maintain existing grep execution logic using direct Node.js approach
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add new grep_search tool in packages/ai/src/tools/file-tools/
- Support various grep options: recursive, ignoreCase, invertMatch, lineNumbers, wordMatch, fixedStrings, maxCount
- Implement bulk search capabilities with array of search configurations
- Use Node.js child_process for direct grep execution
- Include structured output with successful/failed searches
- Add proper error handling and command injection protection
- Export tool in packages/ai/src/tools/index.ts
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add delete-files-tool with sandbox and local execution support
- Support bulk operations with individual success/failure tracking
- Follow established file tools patterns and error handling
- Include comprehensive unit tests with mocking
- Export tool in main index for accessibility
Implements BUS-1464
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add bash_execute tool in packages/ai/src/tools/file-tools/bash-execute-tool.ts
- Support both single commands and arrays of commands
- Use Node's child_process with proper timeout and error handling
- Capture stdout, stderr, and exit codes in structured format
- Add unit tests for schema validation
- Export tool in file-tools index and main tools index
Implements BUS-1466: TypeScript-based bash execution tool with graceful error handling
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add Rust implementation in idle.rs by copying from done.rs
- Add TypeScript implementation in idle-tool.ts by copying from done-tool.ts
- Update all agent modes (review, analysis, follow_up_initialization, planning) to include idle tool
- Update analyst-agent.ts to include idleTool
- Add idle tool to terminating_tools lists
- Export idle module and tool from respective index files
Addresses BUS-1468: idle tool indicates agent finished current work but available for future tasks
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add ls-files-tool with support for standard ls options (-l, -a, -R, -h)
- Support bulk operations with proper error handling
- Parse ls output into structured JSON format
- Handle cross-platform concerns for Windows compatibility
- Follow established Mastra tool patterns with sandbox execution
- Include comprehensive unit tests for both implementation and tool
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add create-file-tool.ts with Zod schema and bulk file creation support
- Add create-file-functions.ts with sandbox execution and local fallback
- Support both absolute and relative file paths
- Create directories if they don't exist, overwrite existing files
- Handle errors gracefully, continue processing other files on individual failures
- Return detailed success/error results for each file operation
- Include comprehensive unit tests (18 tests, all passing)
- Export tool in index.ts following established patterns
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Move to new subdirectory structure: packages/ai/src/tools/file-tools/edit-files-tool/
- Follow exact same architectural pattern as read_files tool
- Use discriminated union output schema for results
- Implement sandbox execution with fallback to local execution
- Fix regex escaping issues in generated sandbox code
- Maintain all existing find-and-replace validation logic
- Support bulk operations with individual success/failure tracking
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Added support for reading files in a sandbox environment using @buster/sandbox.
- Introduced new file reading tool with async operations and error handling.
- Implemented integration tests for sandbox and local execution scenarios.
- Updated package.json and pnpm-lock.yaml to include new dependencies.
Co-Authored-By: [Your Name] <your.email@example.com>
- Convert file operations from sequential to parallel using Promise.all()
- Use async/await with fs.promises for better performance
- Maintain error handling and 1000-line truncation functionality
- All unit tests continue to pass (10/10)
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Use consistent regex for both validation and replacement
- Add reasonable upper limit (100) for bulk operations to prevent memory issues
Addresses greptile-apps bot feedback on PR #561
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add edit_files tool in packages/ai/src/tools/file-tools/
- Implement find-and-replace with exact single occurrence validation
- Support bulk operations with individual success/failure tracking
- Handle both relative and absolute file paths
- Return detailed error messages for various failure scenarios
- Follow established patterns using createTool and wrapTraced
- Add comprehensive unit tests with 11 test cases
- Export tool in packages/ai/src/tools/index.ts
Addresses BUS-1449
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add read_files tool in packages/ai/src/tools/file-tools
- Support both absolute and relative file paths
- Implement 1000-line truncation with indication
- Handle errors gracefully with discriminated union results
- Include comprehensive unit tests with 10/10 passing
- Export tool from main index
- Update sandbox index to export runTypescript and createSandbox
- Follow established patterns from execute-sql.ts
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Add type assertions and null checks across multiple test files
- Fix import statements and mock configurations
- Update test expectations to match actual implementation behavior
- Ensure all AI package unit tests pass
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
- Fixed AI package unit tests that were previously failing
- Updated database package.json with environment variables for tests
- Fixed snowflake adapter test issues in data-source package
Co-Authored-By: Dallin Bentley <dallinbentley98@gmail.com>
dal
jacob-buster
Devin AI
Blake Rouse
Nate Kelley
Jacob Anderson
Cursor Agent