This commit updates all relevant documentation (READMEs, docs/*, .cursor/rules) to accurately reflect the finalized unified AI service architecture and the new configuration system (.taskmasterconfig + .env/mcp.json). It also includes the final code cleanup steps related to the refactoring.
Key Changes:
1. **Documentation Updates:**
* Revised `README.md`, `README-task-master.md`, `assets/scripts_README.md`, `docs/configuration.md`, and `docs/tutorial.md` to explain the new configuration split (.taskmasterconfig vs .env/mcp.json).
* Updated MCP configuration examples in READMEs and tutorials to only include API keys in the `env` block.
* Added/updated examples for using the `--research` flag in `docs/command-reference.md`, `docs/examples.md`, and `docs/tutorial.md`.
* Updated `.cursor/rules/ai_services.mdc`, `.cursor/rules/architecture.mdc`, `.cursor/rules/dev_workflow.mdc`, `.cursor/rules/mcp.mdc`, `.cursor/rules/taskmaster.mdc`, `.cursor/rules/utilities.mdc`, and `.cursor/rules/new_features.mdc` to align with the new architecture, removing references to old patterns/files.
* Removed internal rule links from user-facing rules (`taskmaster.mdc`, `dev_workflow.mdc`, `self_improve.mdc`).
* Deleted outdated example file `docs/ai-client-utils-example.md`.
2. **Final Code Refactor & Cleanup:**
* Corrected `update-task-by-id.js` by removing the last import from the old `ai-services.js`.
* Refactored `update-subtask-by-id.js` to correctly use the unified service and logger patterns.
* Removed the obsolete export block from `mcp-server/src/core/task-master-core.js`.
* Corrected logger implementation in `update-tasks.js` for CLI context.
* Updated API key mapping in `config-manager.js` and `ai-services-unified.js`.
3. **Configuration Files:**
* Updated API keys in `.cursor/mcp.json`, replacing `GROK_API_KEY` with `XAI_API_KEY`.
* Updated `.env.example` with current API key names.
* Added `azureOpenaiBaseUrl` to `.taskmasterconfig` example.
4. **Task Management:**
* Marked documentation subtask 61.10 as 'done'.
* Includes various other task content/status updates from the diff summary.
5. **Changeset:**
* Added `.changeset/cuddly-zebras-matter.md` for user-facing `expand`/`expand-all` improvements.
This commit concludes the major architectural refactoring (Task 61) and ensures the documentation accurately reflects the current system.
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.
Resolves persistent 404 'Not Found' errors when calling Anthropic models via the Vercel AI SDK. The primary issue was likely related to incorrect or missing API headers.
- Refactors Anthropic provider (src/ai-providers/anthropic.js) to use the standard 'anthropic-version' header instead of potentially outdated/incorrect beta headers when creating the client instance.
- Updates the default fallback model ID in .taskmasterconfig to 'claude-3-5-sonnet-20241022'.
- Fixes the interactive model setup (task-master models --setup) in scripts/modules/commands.js to correctly filter and default the main model selection.
- Improves the cost display in the 'task-master models' command output to explicitly show 'Free' for models with zero cost.
- Updates description for the 'id' parameter in the 'set_task_status' MCP tool definition for clarity.
- Updates list of models and costs
- 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.
The interactive model setup triggered by `task-master models --setup` was previously attempting to call non-existent setter functions (`setMainModel`, etc.) in `config-manager.js`, leading to errors and preventing configuration updates.
This commit refactors the `--setup` logic within the `models` command handler in `scripts/modules/commands.js`. It now correctly:
- Loads the current configuration using `getConfig()`." -m "- Updates the appropriate sections of the loaded configuration object based on user selections from `inquirer`." -m "- Saves the modified configuration using the existing `writeConfig()` function from `config-manager.js`." -m "- Handles disabling the fallback model correctly."
This commit focuses on standardizing configuration and API key access patterns across key modules as part of subtask 61.34.
Key changes include:
- Refactored `ai-services.js` to remove global AI clients and use `resolveEnvVariable` for API key checks. Client instantiation now relies on `getAnthropicClient`/`getPerplexityClient` accepting a session object.
- Refactored `task-manager.js` (`analyzeTaskComplexity` function) to use the unified `generateTextService` from `ai-services-unified.js`, removing direct AI client calls.
- Replaced direct `process.env` access for model parameters and other configurations (`PERPLEXITY_MODEL`, `CONFIG.*`) in `task-manager.js` with calls to the appropriate getters from `config-manager.js` (e.g., `getResearchModelId(session)`, `getMainMaxTokens(session)`).
- Ensured `utils.js` (`resolveEnvVariable`) correctly handles potentially undefined session objects.
- Updated function signatures where necessary to propagate the `session` object for correct context-aware configuration/key retrieval.
This moves towards the goal of using `ai-client-factory.js` and `ai-services-unified.js` as the standard pattern for AI interactions and centralizing configuration management through `config-manager.js`.
- Integrate for Grok models and for OpenRouter into the AI client factory ().
- Install necessary provider dependencies (, , and other related packages, updated core).
- Update environment variable checks () and client creation logic () for the new providers.
- Add and correct unit tests in to cover xAI and OpenRouter instantiation, error handling, and environment variable resolution.
- Corrected mock paths and names in tests to align with official package names.
- Verify all tests (28 total) pass for .
- Confirm test coverage remains high (~90%) after additions.
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.
Refactored `config-manager.js` to handle different execution contexts (CLI vs. MCP) and fixed related Jest tests.
- Modified `readConfig` and `writeConfig` to accept an optional `explicitRoot` parameter, allowing explicit path specification (e.g., from MCP) while retaining automatic project root finding for CLI usage.
- Updated getter/setter functions (`getMainProvider`, `setMainModel`, etc.) to accept and propagate the `explicitRoot`.
- Resolved Jest testing issues for dynamic imports by using `jest.unstable_mockModule` for `fs` and `chalk` dependencies *before* the dynamic `import()`.
- Corrected console error assertions in tests to match exact logged messages.
- Updated `.cursor/rules/tests.mdc` with guidelines for `jest.unstable_mockModule` and precise console assertions.
Addresses `process.stdout.clearLine is not a function` error when running AI-dependent commands non-interactively (e.g., `update-subtask`).
Adds `process.stdout.isTTY` check before attempting to use terminal-specific output manipulations.
feat: Implement initial config manager for AI models
Adds `scripts/modules/config-manager.js` to handle reading/writing model selections from/to `.taskmasterconfig`.
Implements core functions: findProjectRoot, read/writeConfig, validateModel, get/setModel.
Defines valid model lists. Completes initial work for Subtask 61.1.
The function used terminal manipulation functions
(like , ) for the CLI
streaming progress indicator. This caused errors when Task Master commands
involving AI streaming were run in non-interactive terminals (e.g., via
output redirection, some CI environments, or integrated terminals).
This commit adds a check for to the condition
that controls the display of the CLI progress indicator, ensuring these
functions are only called when standard output is a fully interactive TTY.
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.
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
- 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)
- Update subtask 23.10 with details on resource and resource template implementation
- Add resource management section to architecture.mdc with proper directory structure
- Create comprehensive resource implementation guide in mcp.mdc with examples and best practices
- Document proper integration of resources in FastMCP server initialization
