- Enhance E2E testing and LLM analysis report and:
- Add --analyze-log flag to run_e2e.sh to re-run LLM analysis on existing logs.
- Add test:e2e and analyze-log scripts to package.json for easier execution.
- Correct display errors and dependency validation output:
- Update chalk usage in add-task.js to use bracket notation (chalk[color]) compatible with v5, resolving 'chalk.keyword is not a function' error.
- Modify fix-dependencies command output to show red failure box with issue count instead of green success box when validation fails.
- Refactor interactive model setup:
- Verify inclusion of 'No change' option during interactive model setup flow (task-master models --setup).
- Update model definitions:
- Add max_tokens field for gpt-4o in supported-models.json.
- Remove unused scripts:
- Delete prepare-package.js and rule-transformer.test.js.
Release candidate
Implements the ability to filter subtasks displayed by the `task-master show <id>` command using the `--status` (or `-s`) flag. This is also available in the MCP context.
- Modified `commands.js` to add the `--status` option to the `show` command definition.
- Updated `utils.js` (`findTaskById`) to handle the filtering logic and return original subtask counts/arrays when filtering.
- Updated `ui.js` (`displayTaskById`) to use the filtered subtasks for the table, display a summary line when filtering, and use the original subtask list for the progress bar calculation.
- Updated MCP `get_task` tool and `showTaskDirect` function to accept and pass the `status` parameter.
- Added changeset entry.
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.
This commit completes the major refactoring initiative (Task 61) to migrate all AI-interacting task management functions to the unified service layer (`ai-services-unified.js`) and standardized configuration (`config-manager.js`).
Key Changes:
1. **Refactor `update-task-by-id` & `update-subtask-by-id`:**
* Replaced direct AI client logic and config fetching with calls to `generateTextService`.
* Preserved original prompt logic while ensuring JSON output format is requested.
* Implemented robust manual JSON parsing and Zod validation for text-based AI responses.
* Corrected logger implementation (`logFn`/`isMCP`/`report` pattern) for both CLI and MCP contexts.
* Ensured correct passing of `session` context to the unified service.
* Refactored associated direct function wrappers (`updateTaskByIdDirect`, `updateSubtaskByIdDirect`) to remove AI client initialization and call core logic appropriately.
2. **CLI Environment Loading:**
* Added `dotenv.config()` to `scripts/dev.js` to ensure consistent loading of the `.env` file for CLI operations.
3. **Obsolete Code Removal:**
* Deleted unused helper files:
* `scripts/modules/task-manager/get-subtasks-from-ai.js`
* `scripts/modules/task-manager/generate-subtask-prompt.js`
* `scripts/modules/ai-services.js`
* `scripts/modules/ai-client-factory.js`
* `mcp-server/src/core/utils/ai-client-utils.js`
* Removed corresponding imports/exports from `scripts/modules/task-manager.js` and `mcp-server/src/core/task-master-core.js`.
4. **Verification:**
* Successfully tested `update-task` and `update-subtask` via both CLI and MCP after refactoring.
5. **Task Management:**
* Marked subtasks 61.38, 61.39, 61.40, 61.41, and 61.33 as 'done'.
* Includes other task content/status updates as reflected in the diff.
This completes the migration of core AI features to the new architecture, enhancing maintainability and flexibility.
Completes the refactoring of the AI-interacting task management functions by aligning `update-tasks.js` with the unified service architecture and removing now-unused helper files.
Key Changes:
- **`update-tasks.js` Refactoring:**
- Replaced direct AI client calls and AI-specific config fetching with a call to `generateTextService` from `ai-services-unified.js`.
- Preserved the original system and user prompts requesting a JSON array output.
- Implemented manual JSON parsing (`parseUpdatedTasksFromText`) with Zod validation to handle the text response reliably.
- Updated the core function signature to accept the standard `context` object (`{ session, mcpLog }`).
- Corrected logger implementation to handle both MCP (`mcpLog`) and CLI (`consoleLog`) contexts appropriately.
- **Related Component Updates:**
- Refactored `mcp-server/src/core/direct-functions/update-tasks.js` to use the standard direct function pattern (logger wrapper, silent mode, call core function with context).
- Verified `mcp-server/src/tools/update.js` correctly passes arguments and context.
- Verified `scripts/modules/commands.js` (update command) correctly calls the refactored core function.
- **Obsolete File Cleanup:**
- Removed the now-unused `scripts/modules/task-manager/get-subtasks-from-ai.js` file and its export, as its functionality was integrated into `expand-task.js`.
- Removed the now-unused `scripts/modules/task-manager/generate-subtask-prompt.js` file and its export for the same reason.
- **Task Management:**
- Marked subtasks 61.38, 61.39, and 61.41 as complete.
This commit finalizes the alignment of `updateTasks`, `updateTaskById`, `expandTask`, `expandAllTasks`, `analyzeTaskComplexity`, `addTask`, and `parsePRD` with the unified AI service and configuration management patterns.
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.
Refactored the `expandTask` feature (`scripts/modules/task-manager/expand-task.js`) and related components (`commands.js`, `mcp-server/src/tools/expand-task.js`, `mcp-server/src/core/direct-functions/expand-task.js`) to integrate with the unified AI service layer (`ai-services-unified.js`) and configuration management (`config-manager.js`).
The refactor involved:
- Removing direct AI client calls and configuration fetching from `expand-task.js`.
- Attempting to use `generateObjectService` for structured subtask generation. This failed due to provider-specific errors (Perplexity internal errors, Anthropic schema translation issues).
- Reverting the core AI interaction to use `generateTextService`, asking the LLM to format its response as JSON containing a "subtasks" array.
- Re-implementing manual JSON parsing and Zod validation (`parseSubtasksFromText`) to handle the text response reliably.
- Updating prompt generation functions (`generateMainSystemPrompt`, `generateMainUserPrompt`, `generateResearchUserPrompt`) to request the correct JSON object structure within the text response.
- Ensuring the `expandTaskDirect` function handles pre-checks (force flag, task status) and correctly passes the `session` context and logger wrapper to the core `expandTask` function.
- Correcting duplicate imports in `commands.js`.
- Validating the refactored feature works correctly via both CLI (`task-master expand --id <id>`) and MCP (`expand_task` tool) for main and research roles.
This aligns the task expansion feature with the new architecture while using the more robust text generation approach due to current limitations with structured output services. Closes subtask 61.37.
Refactored the feature and related components (CLI command, MCP tool, direct function) to integrate with the unified AI service layer ().
Initially, was implemented to leverage structured output generation. However, this approach encountered persistent errors:
- Perplexity provider returned internal server errors.
- Anthropic provider failed with schema type and model errors.
Due to the unreliability of for this specific use case, the core AI interaction within was reverted to use . Basic manual JSON parsing and cleanup logic for the text response were reintroduced.
Key changes include:
- Removed direct AI client initialization (Anthropic, Perplexity).
- Removed direct fetching of AI model configuration parameters.
- Removed manual AI retry/fallback/streaming logic.
- Replaced direct AI calls with a call to .
- Updated wrapper to pass session context correctly.
- Updated MCP tool for correct path resolution and argument passing.
- Updated CLI command for correct path resolution.
- Preserved core functionality: task loading/filtering, report generation, CLI summary display.
Both the CLI command ([INFO] Initialized Perplexity client with OpenAI compatibility layer
[INFO] Initialized Perplexity client with OpenAI compatibility layer
Analyzing task complexity from: tasks/tasks.json
Output report will be saved to: scripts/task-complexity-report.json
Analyzing task complexity and generating expansion recommendations...
[INFO] Reading tasks from tasks/tasks.json...
[INFO] Found 62 total tasks in the task file.
[INFO] Skipping 31 tasks marked as done/cancelled/deferred. Analyzing 31 active tasks.
Skipping 31 tasks marked as done/cancelled/deferred. Analyzing 31 active tasks.
[INFO] Claude API attempt 1/2
[ERROR] Error in Claude API call: 400 {"type":"error","error":{"type":"invalid_request_error","message":"max_tokens: 100000 > 64000, which is the maximum allowed number of output tokens for claude-3-7-sonnet-20250219"}}
[ERROR] Non-overload Claude API error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"max_tokens: 100000 > 64000, which is the maximum allowed number of output tokens for claude-3-7-sonnet-20250219"}}
Claude API error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"max_tokens: 100000 > 64000, which is the maximum allowed number of output tokens for claude-3-7-sonnet-20250219"}}
[ERROR] Error during AI analysis: 400 {"type":"error","error":{"type":"invalid_request_error","message":"max_tokens: 100000 > 64000, which is the maximum allowed number of output tokens for claude-3-7-sonnet-20250219"}}
[ERROR] Error analyzing task complexity: 400 {"type":"error","error":{"type":"invalid_request_error","message":"max_tokens: 100000 > 64000, which is the maximum allowed number of output tokens for claude-3-7-sonnet-20250219"}}) and the MCP tool () have been verified to work correctly with this revised approach.
- Fixed MCP server initialization warnings by refactoring config-manager.js to handle missing project roots silently during startup
- Added project root tracking (loadedConfigRoot) to improve config caching and prevent unnecessary reloads
- Modified _loadAndValidateConfig to return defaults without warnings when no explicitRoot provided
- Improved getConfig to only update cache when loading config with a specific project root
- Ensured warning messages still appear when explicitly specified roots have missing/invalid configs
- Prevented console output during MCP startup that was causing JSON parsing errors
- Verified parse_prd and other MCP tools still work correctly with the new config loading approach.
- Replaces test perplexity api key in mcp.json and rolls it. It's invalid now.
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
Refactors parse-prd MCP tool to properly handle project root and path resolution, fixing the 'Input file not found: /scripts/prd.txt' error.
Key changes include: Made projectRoot a required parameter, prioritized args.projectRoot over session-derived paths, added validation to prevent parsing in invalid directories (/, home dir), improved error handling with detailed messages, and added creation of output directory if needed.
This resolves issues similar to those fixed in initialize-project, where the tool was incorrectly resolving paths when session context was incomplete.
Refactors the initialize_project MCP tool to call a dedicated direct function (initializeProjectDirect) instead of executing the CLI command. This improves reliability and aligns it with other MCP tools.
Key changes include: Modified initialize-project.js to call initializeProjectDirect, required projectRoot parameter, implemented handleApiResult for MCP response formatting, enhanced direct function to prioritize args.projectRoot over session-derived paths, added validation to prevent initialization in invalid directories, forces yes:true for non-interactive use, ensures process.chdir() targets validated directory, and added isSilentMode() checks to suppress console output during MCP operations.
This resolves issues where the tool previously failed due to incorrect fallback directory resolution when session context was incomplete.
- 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
- 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.
- Create direct function wrapper in add-task.js with prompt and dependency handling
- Add MCP tool integration for creating new tasks via AI
- Update task-master-core.js to expose addTaskDirect function
- Update changeset to document the new command
- Create direct function wrapper in expand-task.js with error handling
- Add MCP tool integration for breaking down tasks into subtasks
- Update task-master-core.js to expose expandTaskDirect function
- Update changeset to document the new command
- Parameter support for subtask generation options (num, research, prompt, force)
- Create direct function wrapper in next-task.js with error handling and caching
- Add MCP tool integration for finding the next task to work on
- Update task-master-core.js to expose nextTaskDirect function
- Update changeset to document the new command
- Create direct function wrapper in show-task.js with error handling and caching
- Add MCP tool integration for displaying detailed task information
- Update task-master-core.js to expose showTaskDirect function
- Update changeset to document the new command
- Follow kebab-case/camelCase/snake_case naming conventions
Split monolithic task-master-core.js into separate function files within
the mcp-server/src/core/direct-functions/ directory. This change:
- Creates individual files for each direct function implementation
- Moves findTasksJsonPath to a dedicated utils/path-utils.js file
- Converts task-master-core.js to be a simple import/export hub
- Improves maintainability and organization of the codebase
- Reduces potential merge conflicts when multiple developers contribute
- Follows standard module separation patterns
Each function is now in its own self-contained file with clear imports and
focused responsibility, while maintaining the same API endpoints.
