Integrates the OpenRouter AI provider using the Vercel AI SDK adapter (@openrouter/ai-sdk-provider). This allows users to configure and utilize models available through the OpenRouter platform.
- Added src/ai-providers/openrouter.js with standard Vercel AI SDK wrapper functions (generateText, streamText, generateObject).
- Updated ai-services-unified.js to include the OpenRouter provider in the PROVIDER_FUNCTIONS map and API key resolution logic.
- Verified config-manager.js handles OpenRouter API key checks correctly.
- Users can configure OpenRouter models via .taskmasterconfig using the task-master models command or MCP models tool. Requires OPENROUTER_API_KEY.
- Enhanced error handling in ai-services-unified.js to provide clearer messages when generateObjectService fails due to lack of underlying tool support in the selected model/provider endpoint.
Adds the ability for users to specify custom model IDs for Ollama and OpenRouter providers, bypassing the internal supported model list.
- Introduces --ollama and --openrouter flags for the 'task-master models --set-<role>' command.
- Updates the interactive 'task-master models --setup' to include options for entering custom Ollama/OpenRouter IDs.
- Implements live validation against the OpenRouter API when a custom OpenRouter ID is provided.
- Refines the model setting logic to prioritize explicit provider flags/choices.
- Adds warnings when custom models are set.
- Updates the changeset file.
Integrates the xAI provider into the unified AI service layer, allowing the use of Grok models (e.g., grok-3, grok-3-mini).
Changes include:
- Added dependency.
- Created with implementations for generateText, streamText, and generateObject (stubbed).
- Updated to include the xAI provider in the function map.
- Updated to recognize the 'xai' provider and the environment variable.
- Updated to include known Grok models and their capabilities (object generation marked as likely unsupported).
- Add OpenAI provider implementation using @ai-sdk/openai.\n- Update `models` command/tool to display API key status for configured providers.\n- Implement model-specific `maxTokens` override logic in `config-manager.js` using `supported-models.json`.\n- Improve AI error message parsing in `ai-services-unified.js` for better clarity.
The add-task command handler in commands.js was incorrectly passing null for the manualTaskData parameter to the core addTask function. This caused the core function to always fall back to the AI generation path, even when only manual flags like --title and --description were provided. This commit updates the call to pass the correctly constructed manualTaskData object, ensuring that manual task creation via the CLI works as intended without unnecessarily calling the AI service.
Refactors the `expandTask` and `expandAllTasks` features to complete subtask 61.38 and enhance functionality based on subtask 61.37's refactor.
Key Changes:
- **Additive Expansion (`expandTask`, `expandAllTasks`):**
- Modified `expandTask` default behavior to append newly generated subtasks to any existing ones.
- Added a `force` flag (passed down from CLI/MCP via `--force` option/parameter) to `expandTask` and `expandAllTasks`. When `force` is true, existing subtasks are cleared before generating new ones.
- Updated relevant CLI command (`expand`), MCP tool (`expand_task`, `expand_all`), and direct function wrappers (`expandTaskDirect`, `expandAllTasksDirect`) to handle and pass the `force` flag.
- **Complexity Report Integration (`expandTask`):**
- `expandTask` now reads `scripts/task-complexity-report.json`.
- If an analysis entry exists for the target task:
- `recommendedSubtasks` is used to determine the number of subtasks to generate (unless `--num` is explicitly provided).
- `expansionPrompt` is used as the primary prompt content for the AI.
- `reasoning` is appended to any additional context provided.
- If no report entry exists or the report is missing, it falls back to default subtask count (from config) and standard prompt generation.
- **`expandAllTasks` Orchestration:**
- Refactored `expandAllTasks` to primarily iterate through eligible tasks (pending/in-progress, considering `force` flag and existing subtasks) and call the updated `expandTask` function for each.
- Removed redundant logic (like complexity reading or explicit subtask clearing) now handled within `expandTask`.
- Ensures correct context (`session`, `mcpLog`) and flags (`useResearch`, `force`) are passed down.
- **Configuration & Cleanup:**
- Updated `.cursor/mcp.json` with new Perplexity/Anthropic API keys (old ones invalidated).
- Completed refactoring of `expandTask` started in 61.37, confirming usage of `generateTextService` and appropriate prompts.
- **Task Management:**
- Marked subtask 61.37 as complete.
- Updated `.changeset/cuddly-zebras-matter.md` to reflect user-facing changes.
These changes finalize the refactoring of the task expansion features, making them more robust, configurable via complexity analysis, and aligned with the unified AI service architecture.
This commit implements several related improvements to the models command and configuration system:
- Added MCP support for the models command:
- Created new direct function implementation in models.js
- Registered modelsDirect in task-master-core.js for proper export
- Added models tool registration in tools/index.js
- Ensured project name replacement when copying .taskmasterconfig in init.js
- Improved .taskmasterconfig copying during project initialization:
- Added copyTemplateFile() call in createProjectStructure()
- Ensured project name is properly replaced in the config
- Restructured tool registration in logical workflow groups:
- Organized registration into 6 functional categories
- Improved command ordering to follow typical workflow
- Added clear group comments for maintainability
- Enhanced documentation in cursor rules:
- Updated dev_workflow.mdc with clearer config management instructions
- Added comprehensive models command reference to taskmaster.mdc
- Clarified CLI vs MCP usage patterns and options
- Added warning against manual .taskmasterconfig editing
- Unified Service: Introduced 'scripts/modules/ai-services-unified.js' to centralize AI interactions using provider modules ('src/ai-providers/') and the Vercel AI SDK.
- Provider Modules: Implemented 'anthropic.js' and 'perplexity.js' wrappers for Vercel SDK.
- 'updateSubtaskById' Fix: Refactored the AI call within 'updateSubtaskById' to use 'generateTextService' from the unified layer, resolving runtime errors related to parameter passing and streaming. This serves as the pattern for refactoring other AI calls in 'scripts/modules/task-manager/'.
- Task Status: Marked Subtask 61.19 as 'done'.
- Rules: Added new 'ai-services.mdc' rule.
This centralizes AI logic, replacing previous direct SDK calls and custom implementations. API keys are resolved via 'resolveEnvVariable' within the service layer. The refactoring of 'updateSubtaskById' establishes the standard approach for migrating other AI-dependent functions in the task manager module to use the unified service.
Relates to Task 61.
Introduces a configurable fallback model and adds support for additional AI provider API keys in the environment setup.
- **Add Fallback Model Configuration (.taskmasterconfig):**
- Implemented a new section in .
- Configured as the default fallback model, enhancing resilience if the primary model fails.
- **Update Default Model Configuration (.taskmasterconfig):**
- Changed the default model to .
- Changed the default model to .
- **Add API Key Examples (assets/env.example):**
- Added example environment variables for:
- (for OpenAI/OpenRouter)
- (for Google Gemini)
- (for XAI Grok)
- Included format comments for clarity.
Improves the quality and relevance of research-backed AI operations:
- Tweaks Perplexity AI calls to use max input tokens (8700), temperature 0.1, high context size, and day-fresh search recency.
- Adds a system prompt to guide Perplexity research output.
Docs:
- Updates CLI examples in taskmaster.mdc to use ANSI-C quoting ($'...') for multi-line prompts, ensuring they work correctly in bash/zsh.
Change threshold parameter in analyze_project_complexity from union type to coerce.number with min/max validation. Fix Invalid type error that occurred with certain input formats. Add test implementation to avoid real API calls and proper tests for parameter validation.
Added detailed next_step guidance to the initialize-project MCP tool response,
providing clear instructions about creating a PRD file and using parse-prd
after initialization. This helps users understand the workflow better after
project initialization.
Also added comprehensive unit tests for the initialize-project MCP tool that:
- Verify tool registration with correct parameters
- Test command construction with proper argument formatting
- Check special character escaping in command arguments
- Validate success response formatting including the new next_step field
- Test error handling and fallback mechanisms
- Verify logging behavior
The tests follow the same pattern as other MCP tool tests in the codebase.
- Add support for --title/-t and --description/-d flags in add-task command
- Fix validation for manual creation mode (title + description)
- Implement proper testing for both prompt and manual creation modes
- Update testing documentation with Commander.js testing best practices
- Add guidance on handling variable hoisting and module initialization issues
Changeset: brave-doors-open.md
- Fix expand-all command bugs that caused NaN errors with --all option and JSON formatting errors with research enabled
- Improve error handling to provide clear feedback when subtask generation fails
- Include task IDs and actionable suggestions in error messages
- Add custom processTaskResponse function to get-task.js to filter response data
- Significantly reduce MCP response size by returning only the requested task
- Preserve allTasks in CLI/UI for dependency status formatting
- Update changeset with documentation of optimization
This change maintains backward compatibility while making MCP responses
more efficient, addressing potential context overflow issues in AI clients.
- Refactor for more reliable project root detection, particularly when running within integrated environments like Cursor IDE. Includes deriving root from script path and avoiding fallback to '/'.
- Enhance error handling in :
- Add detailed debug information (paths searched, CWD, etc.) to the error message when is not found in the provided project root.
- Improve clarity of error messages and potential solutions.
- Add verbose logging in to trace session object content and the finally resolved project root path, aiding in debugging path-related issues.
- Add default values for and to the example environment configuration.
Updated several Cursor rules documentation files (`mcp.mdc`, `utilities.mdc`, `architecture.mdc`, `new_features.mdc`, `commands.mdc`) to accurately reflect recent refactoring and clarify best practices.
Key documentation updates include:
- Explicitly stating the preference for using MCP tools over CLI commands in integrated environments (`commands.mdc`, `dev_workflow.mdc`).
- Describing the new standard pattern for getting the project root using `getProjectRootFromSession` within MCP tool `execute` methods (`mcp.mdc`, `utilities.mdc`, `architecture.mdc`, `new_features.mdc`).
- Clarifying the simplified role of `findTasksJsonPath` in direct functions (`mcp.mdc`, `utilities.mdc`, `architecture.mdc`, `new_features.mdc`).
- Ensuring proper interlinking between related documentation files.
- Enhance MCP server robustness and usability:
- Implement smart project root detection with hierarchical fallbacks
- Make projectRoot parameter optional across all MCP tools
- Add comprehensive PROJECT_MARKERS for reliable project detection
- Improve error messages and logging for better debugging
- Split monolithic core into focused direct-function files
- Implement full suite of MCP commands:
- Add task management: update-task, update-subtask, generate
- Add task organization: expand-task, expand-all, clear-subtasks
- Add dependency handling: add/remove/validate/fix dependencies
- Add analysis tools: analyze-complexity, complexity-report
- Rename commands for better API consistency (list-tasks → get-tasks)
- Enhance documentation and developer experience:
- Create and bundle new taskmaster.mdc as comprehensive reference
- Document all tools with natural language patterns and examples
- Clarify project root auto-detection in documentation
- Standardize naming conventions across MCP components
- Add cross-references between related tools and commands
- Improve UI and progress tracking:
- Add color-coded progress bars with status breakdown
- Implement cancelled/deferred task status handling
- Enhance status visualization and counting
- Optimize display for various terminal sizes
This major update significantly improves the robustness and usability
of the MCP server while providing comprehensive documentation for both
users and developers. The changes make Task Master more intuitive to
use programmatically while maintaining full CLI functionality.
- Update all tool definitions to use z.string().optional() for projectRoot
- Fix direct function implementations to use findTasksJsonPath(args, log) pattern
- Enables consistent project root detection without requiring explicit params
- Update changeset to document these improvements
This change ensures MCP tools work properly with the smart project root
detection system, removing the need for explicit projectRoot parameters in
client applications. Improves usability and reduces integration friction.
Overhauls the project root detection system with a hierarchical precedence mechanism that intelligently locates tasks.json and identifies project roots. This improves user experience by reducing the need for explicit path parameters and enhances cross-platform compatibility.
Key Improvements:
- Implement hierarchical precedence for project root detection:
* Environment variable override (TASK_MASTER_PROJECT_ROOT)
* Explicitly provided --project-root parameter
* Cached project root from previous successful operations
* Current directory with project markers
* Parent directory traversal to find tasks.json
* Package directory as fallback
- Create comprehensive PROJECT_MARKERS detection system with 20+ common indicators:
* Task Master specific files (tasks.json, tasks/tasks.json)
* Version control directories (.git, .svn)
* Package manifests (package.json, pyproject.toml, Gemfile, go.mod, Cargo.toml)
* IDE/editor configurations (.cursor, .vscode, .idea)
* Dependency directories (node_modules, venv, .venv)
* Configuration files (.env, tsconfig.json, webpack.config.js)
* CI/CD files (.github/workflows, .gitlab-ci.yml, .circleci/config.yml)
- DRY refactoring of path utilities:
* Centralize path-related functions in core/utils/path-utils.js
* Export PROJECT_MARKERS as a single source of truth
* Add caching via lastFoundProjectRoot for performance optimization
- Enhanced user experience:
* Improve error messages with specific troubleshooting guidance
* Add detailed logging to indicate project root detection source
* Update tool parameter descriptions for better clarity
* Add recursive parent directory searching for tasks.json
Testing:
- Verified in local dev environment
- Added unit tests for the progress bar visualization
- Updated "automatically detected" description in MCP tools
This commit addresses Task #38: Implement robust project root handling for file paths.
- Add cancelled status to UI module for marking tasks cancelled without deletion
- Improve MCP server resource documentation with implementation examples
- Update architecture.mdc with detailed resource management info
- Add comprehensive resource handling guide to mcp.mdc
- Update changeset to reflect new features and documentation
- Mark task 23.6 as cancelled (MCP SDK integration no longer needed)
- Complete task 23.12 (structured logging system)
