* Amp profile + tests
* generatlize to Agent instead of Claude Code to support any agent
* add changeset
* unnecessary tab formatting
* fix exports
* fix formatting
* feat: complete Groq provider integration and add Kimi K2 model
- Add missing getRequiredApiKeyName() method to GroqProvider class
- Register GroqProvider in ai-services-unified.js PROVIDERS object
- Add Groq API key handling to config-manager.js (isApiKeySet and getMcpApiKeyStatus)
- Add GROQ_API_KEY to env.example with format hint
- Add moonshotai/kimi-k2-instruct model to Groq provider ($1/$3 per 1M tokens, 16k max)
- Fix import sorting for linting compliance
- Add GroqProvider mock to ai-services-unified tests
Fixes missing implementation pieces that prevented Groq provider from working.
* chore: improve changeset
---------
Co-authored-by: Ben Vargas <ben@example.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* fix: prevent CLAUDE.md overwrite by using imports
- Copy Task Master instructions to .taskmaster/CLAUDE.md
- Add import section to user's CLAUDE.md instead of overwriting
- Preserve existing user content
- Clean removal of Task Master content on uninstall
Closes#929
* chore: add changeset for Claude import fix
* fix: resolve path resolution issues in parse-prd and analyze-complexity commands
This commit fixes critical path resolution regressions where commands were requiring files they create to already exist.
## Changes Made:
### 1. parse-prd Command (Lines 808, 828-835, 919-921)
**Problem**: Command required tasks.json to exist before it could create it (catch-22)
**Root Cause**: Default value in option definition meant options.output was always set
**Fixes**:
- Removed default value from --output option definition (line 808)
- Modified initTaskMaster to only include tasksPath when explicitly specified
- Added null handling for output path with fallback to default location
### 2. analyze-complexity Command (Lines 1637-1640, 1673-1680, 1695-1696)
**Problem**: Command required complexity report file to exist before creating it
**Root Cause**: Default value in option definition meant options.output was always set
**Fixes**:
- Removed default value from --output option definition (lines 1637-1640)
- Modified initTaskMaster to only include complexityReportPath when explicitly specified
- Added null handling for report path with fallback to default location
## Technical Details:
The core issue was that Commander.js option definitions with default values always populate the options object, making conditional checks like `if (options.output)` always true. By removing default values from option definitions, we ensure paths are only included in initTaskMaster when users explicitly provide them.
This approach is cleaner than using boolean flags (true/false) for required/optional, as it eliminates the path entirely when not needed, letting initTaskMaster use its default behavior.
## Testing:
- parse-prd now works on fresh projects without existing tasks.json
- analyze-complexity creates report file without requiring it to exist
- Commands maintain backward compatibility when paths are explicitly provided
Fixes issues reported in PATH-FIXES.md and extends the solution to other affected commands.
* fix: update expand-task test to match context gathering fix
The test was expecting gatheredContext to be a string, but the actual
implementation returns an object with a context property. Updated the
ContextGatherer mock to return the correct format and added missing
FuzzyTaskSearch mock.
---------
Co-authored-by: Ben Vargas <ben@example.com>
- Replaced local `tasksPath` variable assignments with direct calls to `taskMaster.getTasksPath()` for consistency and clarity across multiple command functions.
- This change enhances maintainability by ensuring a single source of truth for task paths, reducing redundancy in path handling logic.
- Add grok-4 to supported models with $3/$15 per 1M token pricing
- Enable main, fallback, and research roles for grok-4
- Update models.md documentation to include grok-4 in all tables
* move claude rules and commands to assets/claude
* update claude profile to copy assets/claude to .claude
* fix formatting
* feat(profiles): Implement unified profile system
- Convert Claude and Codex profiles to use createProfile() factory
- Remove simple vs complex profile distinction in rule transformer
- Unify convertAllRulesToProfileRules() to handle all profiles consistently
- Fix mcpConfigPath construction in base-profile.js for null mcpConfigName
- Update terminology from 'simpleProfiles' to 'assetOnlyProfiles' throughout
- Ensure Claude .claude directory copying works in both CLI and MCP contexts
- All profiles now follow same execution flow with proper lifecycle functions
Changes:
- src/profiles/claude.js: Convert to createProfile() factory pattern
- src/profiles/codex.js: Convert to createProfile() factory pattern
- src/utils/rule-transformer.js: Unified profile handling logic
- src/utils/profiles.js: Remove simple profile categorization
- src/profiles/base-profile.js: Fix mcpConfigPath construction
- scripts/modules/commands.js: Update variable naming
- tests/: Update all tests for unified system and terminology
Fixes Claude profile asset copying issue in MCP context.
All tests passing (617 passed, 11 skipped).
* re-checkin claude files
* fix formatting
* chore: clean up test Claude rules files
* chore: add changeset for unified profile system
* add claude files back
* add changeset
* restore proper gitignore
* remove claude agents file from root
* remove incorrect doc
* simplify profiles and update tests
* update changeset
* update changeset
* remove profile specific code
* streamline profiles with defaults and update tests
* update changeset
* add newline at end of gitignore
* restore changes
* streamline profiles with defaults; update tests and add vscode test
* update rule profile tests
* update wording for clearer profile management
* refactor and clarify terminology
* use original projectRoot var name
* revert param desc
* use updated claude assets from neno
* add "YOUR_" before api key here
* streamline codex profile
* add gemini profile
* update gemini profile
* update tests
* relocate function
* update rules interactive setup Gemini desc
* remove duplicative code
* add comma
* feat: support MCP sampling
* support provider registry
* use standard config options for MCP provider
* update fastmcp to support passing params to requestSampling
* move key name definition to base provider
* moved check for required api key to provider class
* remove unused code
* more cleanup
* more cleanup
* refactor provider
* remove not needed files
* more cleanup
* more cleanup
* more cleanup
* update docs
* fix tests
* add tests
* format fix
* clean files
* merge fixes
* format fix
* feat: add support for MCP Sampling as AI provider
* initial mcp ai sdk
* fix references to old provider
* update models
* lint
* fix gemini-cli conflicts
* ran format
* Update src/provider-registry/index.js
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* fix circular dependency
Circular Dependency Issue ✅ FIXED
Root Cause: BaseAIProvider was importing from index.js, which includes commands.js and other modules that eventually import back to AI providers
Solution: Changed imports to use direct paths to avoid circular dependencies:
Updated base-provider.js to import log directly from utils.js
Updated gemini-cli.js to import log directly from utils.js
Result: Fixed 11 failing tests in mcp-provider.test.js
* fix gemini test
* fix(claude-code): recover from CLI JSON truncation bug (#913) (#920)
Gracefully handle SyntaxError thrown by @anthropic-ai/claude-code when the CLI truncates large JSON outputs (4–16 kB cut-offs).\n\nKey points:\n• Detect JSON parse error + existing buffered text in both doGenerate() and doStream() code paths.\n• Convert the failure into a recoverable 'truncated' finish state and push a provider-warning.\n• Allows Task Master to continue parsing long PRDs / expand-task operations instead of crashing.\n\nA patch changeset (.changeset/claude-code-json-truncation.md) is included for the next release.\n\nRef: eyaltoledano/claude-task-master#913
* docs: fix gemini-cli authentication documentation (#923)
Remove erroneous 'gemini auth login' command references and replace with correct 'gemini' command authentication flow. Update documentation to reflect proper OAuth setup process via the gemini CLI interactive interface.
* fix tests
* fix: update ai-sdk-provider-gemini-cli to 0.0.4 for improved authentication (#932)
- Fixed authentication compatibility issues with Google auth
- Added support for 'api-key' auth type alongside 'gemini-api-key'
- Resolved "Unsupported authType: undefined" runtime errors
- Updated @google/gemini-cli-core dependency to 0.1.9
- Improved documentation and removed invalid auth references
- Maintained backward compatibility while enhancing type validation
* call logging directly
Need to patch upstream fastmcp to allow easier access and bootstrap the TM mcp logger to use the fastmcp logger which today is only exposed in the tools handler
* fix tests
* removing logs until we figure out how to pass mcp logger
* format
* fix tests
* format
* clean up
* cleanup
* readme fix
---------
Co-authored-by: Oren Melamed <oren.m@gloat.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
Co-authored-by: Ben Vargas <ben@vargas.com>
* feat: implement centralized path management system with initTaskMaster
This commit introduces a comprehensive refactoring of the TaskMaster CLI's path handling system, consolidating all path resolution logic into a centralized initTaskMaster function and TaskMaster class. This architectural change eliminates circular dependencies and provides consistent path management across all CLI commands.
Key changes:
• **Created new TaskMaster class and initTaskMaster factory function** in src/task-master.js
- Centralized path resolution with boolean override logic (string = explicit path, true = required search, false/undefined = optional)
- Built-in error handling with automatic process.exit() for missing required paths
- Immutable path objects with getter methods for safe access
• **Replaced findProjectRoot() calls throughout CLI** in scripts/modules/commands.js
- Updated all 25+ CLI commands to use initTaskMaster() instead of scattered path handling
- Eliminated hundreds of lines of redundant path resolution and error handling code
- Consistent project root validation and path discovery across all commands
• **Added comprehensive test suite** in tests/unit/task-master.test.js
- 22 test cases covering project root detection, path resolution, override validation, and edge cases
- Tests use temporary directories with proper cleanup and mock process.exit/console.error
- Validates both successful scenarios and error conditions with proper exit codes
* bring Usage for Parse PRD back, and revamp initTaskMaster to throw errors not error/exit.
* fix(claude-code): recover from CLI JSON truncation bug (#913) (#920)
Gracefully handle SyntaxError thrown by @anthropic-ai/claude-code when the CLI truncates large JSON outputs (4–16 kB cut-offs).\n\nKey points:\n• Detect JSON parse error + existing buffered text in both doGenerate() and doStream() code paths.\n• Convert the failure into a recoverable 'truncated' finish state and push a provider-warning.\n• Allows Task Master to continue parsing long PRDs / expand-task operations instead of crashing.\n\nA patch changeset (.changeset/claude-code-json-truncation.md) is included for the next release.\n\nRef: eyaltoledano/claude-task-master#913
* docs: fix gemini-cli authentication documentation (#923)
Remove erroneous 'gemini auth login' command references and replace with correct 'gemini' command authentication flow. Update documentation to reflect proper OAuth setup process via the gemini CLI interactive interface.
* fix: .gitignore missing trailing newline during project initialization (#855)
* Support for Additional Anthropic Models on Bedrock (#870)
* Add additional Anthropic Models for Bedrock
* Update Models Docs from `scripts/modules/supported-models.json`
* feat(models): add additional Bedrock supported models
* docs: Auto-update and format models.md
* fix: Ensure projectRoot is a string (potential WSL fix) (#892)
* ensure projectRoot is a string
* add changeset
* Fix/spelling mistakes (#876)
* docs: Auto-update and format models.md
* fix: correct typos in documentation for parse-prd and taskmaster commands
- Updated the `parse-prd` documentation to fix the spelling of "multiple."
- Clarified the description of the `id` parameter in the `taskmaster` documentation to ensure proper syntax and readability.
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* Fix `rules` command to use reliable project root detection like other commands (#908)
* update/fix projectRoot call for consistency
* internal naming consistency
* add changeset
* fix: Subtask generation fails on gemini-2.5-pro (#852)
* fix: clarify details format in task expansion prompt
* chore: add changeset
* fix: use tag-specific complexity reports (#857)
* fix(expand-task): Use tag-specific complexity reports
- Add getTagAwareFilePath utility function to resolve tag-specific file paths
- Update expandTask to use tag-aware complexity report paths
- Fix issue where expand-task always used default complexity report
- Add comprehensive tests for getTagAwareFilePath utility
- Ensure proper handling of file extensions and directory structures
Fixes#850: Expanding tasks not using tag-specific complexity reports
The expandTask function now correctly uses complexity reports specific
to the current tag context (e.g., task-complexity-report_feature-branch.json)
instead of always using the default task-complexity-report.json file.
This enables proper task expansion behavior when working with multiple
tag contexts, ensuring complexity analysis is tag-specific and accurate.
* chore: Add changeset for tag-specific complexity reports fix
* test(expand-task): Add tests for tag-specific complexity report integration
- Introduced a new test suite for verifying the integration of tag-specific complexity reports in the expandTask function.
- Added a test case to ensure the correct complexity report is used when available for a specific tag.
- Mocked file system interactions to simulate the presence of tag-specific complexity reports.
This enhances the test coverage for task expansion behavior, ensuring it accurately reflects the complexity analysis based on the current tag context.
* refactor(task-manager): unify and simplify tag-aware file path logic and tests
- Reformatted imports and cleaned up comments in test files for readability
- Centralized mocks: moved getTagAwareFilePath & slugifyTagForFilePath
mocks to setup.js for consistency and maintainability
- Simplified utils/getTagAwareFilePath: replaced manual parsing with
path.parse() & path.format(); improved extension handling
- Enhanced test mocks for path.parse, path.format & reset path.join
in beforeEach to avoid interference
- All tests now pass consistently; no change in functionality
* fix: prevent tag corruption in bulk updates (#856)
* fix(task-manager): prevent tag corruption in bulk updates and add tag preservation test
- Fix writeJSON call in scripts/modules/task-manager/update-tasks.js (line 469) to include projectRoot and tag parameters.
- Ensure tagged task lists maintain data integrity during bulk updates, preventing task disappearance in tagged contexts.
- Update MCP tools to properly pass tag context through the call chain.
- Introduce a comprehensive test case to verify that all tags are preserved when updating tasks, covering both master and feature-branch scenarios.
Addresses an issue where bulk updates could corrupt tasks.json in tagged task list structures, reinforcing task management robustness.
* style(tests): format task data in update-tasks test
* fix: Critical writeJSON Context Fixes - Prevent Tag Corruption (#910)
* feat(tasks): Fix critical tag corruption bug in task management
- Fixed missing context parameters in writeJSON calls across add-task, remove-task, and add-subtask functions
- Added projectRoot and tag parameters to prevent data corruption in multi-tag environments
- Re-enabled generateTaskFiles calls to ensure markdown files are updated after operations
- Enhanced add_subtask MCP tool with tag parameter support
- Refactored addSubtaskDirect function to properly pass context to core logic
- Streamlined codebase by removing deprecated functionality
This resolves the critical bug where task operations in one tag context would corrupt or delete tasks from other tags in tasks.json.
* feat(task-manager): Enhance addSubtask with current tag support
- Added `getCurrentTag` utility to retrieve the current tag context for task operations.
- Updated `addSubtask` to use the current tag when reading and writing tasks, ensuring proper context handling.
- Refactored tests to accommodate changes in the `addSubtask` function, ensuring accurate mock implementations and expectations.
- Cleaned up test cases for better readability and maintainability.
This improves task management by preventing tag-related data corruption and enhances the overall functionality of the task manager.
* feat(remove-task): Add tag support for task removal and enhance error handling
- Introduced `tag` parameter in `removeTaskDirect` to specify context for task operations, improving multi-tag support.
- Updated logging to include tag context in messages for better traceability.
- Refactored task removal logic to streamline the process and improve error reporting.
- Added comprehensive unit tests to validate tag handling and ensure robust error management.
This enhancement prevents task data corruption across different tags and improves the overall reliability of the task management system.
* feat(add-task): Add projectRoot and tag parameters to addTask tests
- Updated `addTask` unit tests to include `projectRoot` and `tag` parameters for better context handling.
- Enhanced test cases to ensure accurate expectations and improve overall test coverage.
This change aligns with recent enhancements in task management, ensuring consistency across task operations.
* feat(set-task-status): Add tag parameter support and enhance task status handling
- Introduced `tag` parameter in `setTaskStatusDirect` and related functions to improve context management in multi-tag environments.
- Updated `writeJSON` calls to ensure task data integrity across different tags.
- Enhanced unit tests to validate tag preservation during task status updates, ensuring robust functionality.
This change aligns with recent improvements in task management, preventing data corruption and enhancing overall reliability.
* feat(tag-management): Enhance writeJSON calls to preserve tag context
- Updated `writeJSON` calls in `createTag`, `deleteTag`, `renameTag`, `copyTag`, and `enhanceTagsWithMetadata` to include `projectRoot` for better context management and to prevent tag corruption.
- Added comprehensive unit tests for tag management functions to ensure data integrity and proper tag handling during operations.
This change improves the reliability of tag management by ensuring that operations do not corrupt existing tags and maintains the overall structure of the task data.
* feat(expand-task): Update writeJSON to include projectRoot and tag context
- Modified `writeJSON` call in `expandTaskDirect` to pass `projectRoot` and `tag` parameters, ensuring proper context management when saving tasks.json.
- This change aligns with recent enhancements in task management, preventing potential data corruption and improving overall reliability.
* feat(fix-dependencies): Add projectRoot and tag parameters for enhanced context management
- Updated `fixDependenciesDirect` and `registerFixDependenciesTool` to include `projectRoot` and `tag` parameters, improving context handling during dependency fixes.
- Introduced a new unit test for `fixDependenciesCommand` to ensure proper preservation of projectRoot and tag data in JSON outputs.
This change enhances the reliability of dependency management by ensuring that context is maintained across operations, preventing potential data issues.
* fix(context): propagate projectRoot and tag through dependency, expansion, status-update and tag-management commands to prevent cross-tag data corruption
* test(fix-dependencies): Enhance unit tests for fixDependenciesCommand
- Refactored tests to use unstable mocks for utils, ui, and task-manager modules, improving isolation and reliability.
- Added checks for process.exit to ensure proper handling of invalid data scenarios.
- Updated test cases to verify writeJSON calls with projectRoot and tag parameters, ensuring accurate context preservation during dependency fixes.
This change strengthens the test suite for dependency management, ensuring robust functionality and preventing potential data issues.
* chore(plan): remove outdated fix plan for `writeJSON` context parameters
* feat: Add gemini-cli provider integration for Task Master (#897)
* feat: Add gemini-cli provider integration for Task Master
This commit adds comprehensive support for the Gemini CLI provider, enabling users
to leverage Google's Gemini models through OAuth authentication via the gemini CLI
tool. This integration provides a seamless experience for users who prefer using
their existing Google account authentication rather than managing API keys.
## Implementation Details
### Provider Class (`src/ai-providers/gemini-cli.js`)
- Created GeminiCliProvider extending BaseAIProvider
- Implements dual authentication support:
- Primary: OAuth authentication via `gemini auth login` (authType: 'oauth-personal')
- Secondary: API key authentication for compatibility (authType: 'api-key')
- Uses the npm package `ai-sdk-provider-gemini-cli` (v0.0.3) for SDK integration
- Properly handles authentication validation without console output
### Model Configuration (`scripts/modules/supported-models.json`)
- Added two Gemini models with accurate specifications:
- gemini-2.5-pro: 72% SWE score, 65,536 max output tokens
- gemini-2.5-flash: 71% SWE score, 65,536 max output tokens
- Both models support main, fallback, and research roles
- Configured with zero cost (free tier)
### System Integration
- Registered provider in PROVIDERS map (`scripts/modules/ai-services-unified.js`)
- Added to OPTIONAL_AUTH_PROVIDERS set for flexible authentication
- Added GEMINI_CLI constant to provider constants (`src/constants/providers.js`)
- Exported GeminiCliProvider from index (`src/ai-providers/index.js`)
### Command Line Support (`scripts/modules/commands.js`)
- Added --gemini-cli flag to models command for provider hint
- Integrated into model selection logic (setModel function)
- Updated error messages to include gemini-cli in provider list
- Removed unrelated azure/vertex changes to maintain PR focus
### Documentation (`docs/providers/gemini-cli.md`)
- Comprehensive provider documentation emphasizing OAuth-first approach
- Clear explanation of why users would choose gemini-cli over standard google provider
- Detailed installation, authentication, and configuration instructions
- Troubleshooting section with common issues and solutions
### Testing (`tests/unit/ai-providers/gemini-cli.test.js`)
- Complete test suite with 12 tests covering all functionality
- Tests for both OAuth and API key authentication paths
- Error handling and edge case coverage
- Updated mocks in ai-services-unified.test.js for integration testing
## Key Design Decisions
1. **OAuth-First Design**: The provider assumes users want to leverage their existing
`gemini auth login` credentials, making this the default authentication method.
2. **Authentication Type Mapping**: Discovered through testing that the SDK expects:
- 'oauth-personal' for OAuth/CLI authentication (not 'gemini-cli' or 'oauth')
- 'api-key' for API key authentication (not 'gemini-api-key')
3. **Silent Operation**: Removed console.log statements from validateAuth to match
the pattern used by other providers like claude-code.
4. **Limited Model Support**: Only gemini-2.5-pro and gemini-2.5-flash are available
through the CLI, as confirmed by the package author.
## Usage
```bash
# Install gemini CLI globally
npm install -g @google/gemini-cli
# Authenticate with Google account
gemini auth login
# Configure Task Master to use gemini-cli
task-master models --set-main gemini-2.5-pro --gemini-cli
# Use Task Master normally
task-master new "Create a REST API endpoint"
```
## Dependencies
- Added `ai-sdk-provider-gemini-cli@^0.0.3` to package.json
- This package wraps the Google Gemini CLI Core functionality for Vercel AI SDK
## Testing
All tests pass (613 total), including the new gemini-cli provider tests.
Code has been formatted with biome to maintain consistency.
This implementation provides a clean, well-tested integration that follows Task Master's
existing patterns while offering users a convenient way to use Gemini models with their
existing Google authentication.
* feat: implement lazy loading for gemini-cli provider
- Move ai-sdk-provider-gemini-cli to optionalDependencies
- Implement dynamic import with loadGeminiCliModule() function
- Make getClient() async to support lazy loading
- Update base-provider to handle async getClient() calls
- Update tests to handle async getClient() method
This allows the application to start without the gemini-cli package
installed, only loading it when actually needed.
* feat(gemini-cli): replace regex-based JSON extraction with jsonc-parser
- Add jsonc-parser dependency for robust JSON parsing
- Replace simple regex approach with progressive parsing strategy:
1. Direct parsing after cleanup
2. Smart boundary detection with single-pass analysis
3. Limited fallback for edge cases
- Optimize performance with early termination and strategic sampling
- Add comprehensive tests for variable declarations, trailing commas,
escaped quotes, nested objects, and performance edge cases
- Improve reliability for complex JSON structures that Gemini commonly produces
- Fix code formatting with biome
This addresses JSON parsing failures in generateObject operations while
maintaining backward compatibility and significantly improving performance
for large responses.
* fix: update package-lock.json and fix formatting for CI/CD
- Add jsonc-parser to package-lock.json for proper npm ci compatibility
- Fix biome formatting issues in gemini-cli provider and tests
- Ensure all CI/CD checks pass
* feat(gemini-cli): implement comprehensive JSON output reliability system
- Add automatic JSON request detection via content analysis patterns
- Implement task-specific prompt simplification for improved AI compliance
- Add strict JSON enforcement through enhanced system prompts
- Implement response interception with intelligent JSON extraction fallback
- Add comprehensive test coverage for all new JSON handling methods
- Move debug logging to appropriate level for clean user experience
This multi-layered approach addresses gemini-cli's conversational response
tendencies, ensuring reliable structured JSON output for task expansion
operations. Achieves 100% success rate in end-to-end testing while
maintaining full backward compatibility with existing functionality.
Technical implementation includes:
• JSON detection via user message content analysis
• Expand-task prompt simplification with cleaner instructions
• System prompt enhancement with strict JSON enforcement
• Response processing with jsonc-parser-based extraction
• Comprehensive unit test coverage for edge cases
• Debug-level logging to prevent user interface clutter
Resolves: gemini-cli JSON formatting inconsistencies
Tested: All 46 test suites pass, formatting verified
* chore: add changeset for gemini-cli provider implementation
Adds minor version bump for comprehensive gemini-cli provider with:
- Lazy loading and optional dependency management
- Advanced JSON parsing with jsonc-parser
- Multi-layer reliability system for structured output
- Complete test coverage and CI/CD compliance
* refactor: consolidate optional auth provider logic
- Add gemini-cli to existing providersWithoutApiKeys array in config-manager
- Export providersWithoutApiKeys for reuse across modules
- Remove duplicate OPTIONAL_AUTH_PROVIDERS Set from ai-services-unified
- Update ai-services-unified to import and use centralized array
- Fix Jest mock to include new providersWithoutApiKeys export
This eliminates code duplication and provides a single source of truth
for which providers support optional authentication, addressing PR
reviewer feedback about existing similar functionality in src/constants.
* docs: Auto-update and format models.md
* Feat: Added automatic determination of task number based on complexity (#884)
- Added 'defaultNumTasks: 10' to default config, now used in 'parse-prd'
- Adjusted 'parse-prd' and 'expand-task' to:
- Accept a 'numTasks' value of 0
- Updated tool and command descriptions
- Updated prompts to 'an appropriate number of' when value is 0
- Updated 'README-task-master.md' and 'command-reference.md' docs
- Added more tests for: 'parse-prd', 'expand-task' and 'config-manager'
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* feat: Support custom response language (#510)
* feat: Support custom response language
* fix: Add default values for response language in config-manager.js
* chore: Update configuration file and add default response language settings
* feat: Support MCP/CLI custom response language
* chore: Update test comments to English for consistency
* docs: Auto-update and format models.md
* chore: fix format
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* Feat: Implemented advanced settings for Claude Code AI provider (#872)
* Feat: Implemented advanced settings for Claude Code AI provider
- Added new 'claudeCode' property to default config
- Added getters and validation functions to 'config-manager.js'
- Added new 'isEmpty' utility to 'utils.js'
- Added new constants file 'commands.js' for AI_COMMAND_NAMES
- Updated Claude Code AI provider to use new config functions
- Updated 'claude-code-usage.md' documentation
- Added 'config-manager.test.js' tests to cover new settings
* chore: run format
---------
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* fix: issues with release (#915)
Fix remove-task bug with mcp
Fix response-language using old config file .taskmaster
* fix(claude-code): recover from CLI JSON truncation bug (#913) (#920)
Gracefully handle SyntaxError thrown by @anthropic-ai/claude-code when the CLI truncates large JSON outputs (4–16 kB cut-offs).\n\nKey points:\n• Detect JSON parse error + existing buffered text in both doGenerate() and doStream() code paths.\n• Convert the failure into a recoverable 'truncated' finish state and push a provider-warning.\n• Allows Task Master to continue parsing long PRDs / expand-task operations instead of crashing.\n\nA patch changeset (.changeset/claude-code-json-truncation.md) is included for the next release.\n\nRef: eyaltoledano/claude-task-master#913
* docs: fix gemini-cli authentication documentation (#923)
Remove erroneous 'gemini auth login' command references and replace with correct 'gemini' command authentication flow. Update documentation to reflect proper OAuth setup process via the gemini CLI interactive interface.
* chore: run format
* fix: add initTaskMaster to new commands
Fixes CI and broken commands
* chore: format
---------
Co-authored-by: Chris Covington <chris.covington@hey.com>
Co-authored-by: Ben Vargas <ben@vargas.com>
Co-authored-by: Joe Danziger <joe@ticc.net>
Co-authored-by: Nicholas Spalding <nishedcob@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Ofer Shaal <oshaal@phase2technology.com>
Co-authored-by: Shandy Hermawan <hrm.shandy05@gmail.com>
Co-authored-by: Parthy <52548018+mm-parthy@users.noreply.github.com>
Co-authored-by: Geoff Hammond <geoff@geoffhammond.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
Co-authored-by: shenysun <40556411+shenysun@users.noreply.github.com>
* feat: Add GROQ API key support and integrate GROQ provider
* feat: Add support for Groq provider
- Added a new changeset documenting the addition of Groq provider support.
-Ran npm run format
* feat: Add support for Groq provider
- Added a new changeset documenting the addition of Groq provider support.
-Ran npm run format
Remove erroneous 'gemini auth login' command references and replace with correct 'gemini' command authentication flow. Update documentation to reflect proper OAuth setup process via the gemini CLI interactive interface.
Gracefully handle SyntaxError thrown by @anthropic-ai/claude-code when the CLI truncates large JSON outputs (4–16 kB cut-offs).\n\nKey points:\n• Detect JSON parse error + existing buffered text in both doGenerate() and doStream() code paths.\n• Convert the failure into a recoverable 'truncated' finish state and push a provider-warning.\n• Allows Task Master to continue parsing long PRDs / expand-task operations instead of crashing.\n\nA patch changeset (.changeset/claude-code-json-truncation.md) is included for the next release.\n\nRef: eyaltoledano/claude-task-master#913
* Feat: Implemented advanced settings for Claude Code AI provider
- Added new 'claudeCode' property to default config
- Added getters and validation functions to 'config-manager.js'
- Added new 'isEmpty' utility to 'utils.js'
- Added new constants file 'commands.js' for AI_COMMAND_NAMES
- Updated Claude Code AI provider to use new config functions
- Updated 'claude-code-usage.md' documentation
- Added 'config-manager.test.js' tests to cover new settings
* chore: run format
---------
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* feat: Support custom response language
* fix: Add default values for response language in config-manager.js
* chore: Update configuration file and add default response language settings
* feat: Support MCP/CLI custom response language
* chore: Update test comments to English for consistency
* docs: Auto-update and format models.md
* chore: fix format
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
- Added 'defaultNumTasks: 10' to default config, now used in 'parse-prd'
- Adjusted 'parse-prd' and 'expand-task' to:
- Accept a 'numTasks' value of 0
- Updated tool and command descriptions
- Updated prompts to 'an appropriate number of' when value is 0
- Updated 'README-task-master.md' and 'command-reference.md' docs
- Added more tests for: 'parse-prd', 'expand-task' and 'config-manager'
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* feat: Add gemini-cli provider integration for Task Master
This commit adds comprehensive support for the Gemini CLI provider, enabling users
to leverage Google's Gemini models through OAuth authentication via the gemini CLI
tool. This integration provides a seamless experience for users who prefer using
their existing Google account authentication rather than managing API keys.
## Implementation Details
### Provider Class (`src/ai-providers/gemini-cli.js`)
- Created GeminiCliProvider extending BaseAIProvider
- Implements dual authentication support:
- Primary: OAuth authentication via `gemini auth login` (authType: 'oauth-personal')
- Secondary: API key authentication for compatibility (authType: 'api-key')
- Uses the npm package `ai-sdk-provider-gemini-cli` (v0.0.3) for SDK integration
- Properly handles authentication validation without console output
### Model Configuration (`scripts/modules/supported-models.json`)
- Added two Gemini models with accurate specifications:
- gemini-2.5-pro: 72% SWE score, 65,536 max output tokens
- gemini-2.5-flash: 71% SWE score, 65,536 max output tokens
- Both models support main, fallback, and research roles
- Configured with zero cost (free tier)
### System Integration
- Registered provider in PROVIDERS map (`scripts/modules/ai-services-unified.js`)
- Added to OPTIONAL_AUTH_PROVIDERS set for flexible authentication
- Added GEMINI_CLI constant to provider constants (`src/constants/providers.js`)
- Exported GeminiCliProvider from index (`src/ai-providers/index.js`)
### Command Line Support (`scripts/modules/commands.js`)
- Added --gemini-cli flag to models command for provider hint
- Integrated into model selection logic (setModel function)
- Updated error messages to include gemini-cli in provider list
- Removed unrelated azure/vertex changes to maintain PR focus
### Documentation (`docs/providers/gemini-cli.md`)
- Comprehensive provider documentation emphasizing OAuth-first approach
- Clear explanation of why users would choose gemini-cli over standard google provider
- Detailed installation, authentication, and configuration instructions
- Troubleshooting section with common issues and solutions
### Testing (`tests/unit/ai-providers/gemini-cli.test.js`)
- Complete test suite with 12 tests covering all functionality
- Tests for both OAuth and API key authentication paths
- Error handling and edge case coverage
- Updated mocks in ai-services-unified.test.js for integration testing
## Key Design Decisions
1. **OAuth-First Design**: The provider assumes users want to leverage their existing
`gemini auth login` credentials, making this the default authentication method.
2. **Authentication Type Mapping**: Discovered through testing that the SDK expects:
- 'oauth-personal' for OAuth/CLI authentication (not 'gemini-cli' or 'oauth')
- 'api-key' for API key authentication (not 'gemini-api-key')
3. **Silent Operation**: Removed console.log statements from validateAuth to match
the pattern used by other providers like claude-code.
4. **Limited Model Support**: Only gemini-2.5-pro and gemini-2.5-flash are available
through the CLI, as confirmed by the package author.
## Usage
```bash
# Install gemini CLI globally
npm install -g @google/gemini-cli
# Authenticate with Google account
gemini auth login
# Configure Task Master to use gemini-cli
task-master models --set-main gemini-2.5-pro --gemini-cli
# Use Task Master normally
task-master new "Create a REST API endpoint"
```
## Dependencies
- Added `ai-sdk-provider-gemini-cli@^0.0.3` to package.json
- This package wraps the Google Gemini CLI Core functionality for Vercel AI SDK
## Testing
All tests pass (613 total), including the new gemini-cli provider tests.
Code has been formatted with biome to maintain consistency.
This implementation provides a clean, well-tested integration that follows Task Master's
existing patterns while offering users a convenient way to use Gemini models with their
existing Google authentication.
* feat: implement lazy loading for gemini-cli provider
- Move ai-sdk-provider-gemini-cli to optionalDependencies
- Implement dynamic import with loadGeminiCliModule() function
- Make getClient() async to support lazy loading
- Update base-provider to handle async getClient() calls
- Update tests to handle async getClient() method
This allows the application to start without the gemini-cli package
installed, only loading it when actually needed.
* feat(gemini-cli): replace regex-based JSON extraction with jsonc-parser
- Add jsonc-parser dependency for robust JSON parsing
- Replace simple regex approach with progressive parsing strategy:
1. Direct parsing after cleanup
2. Smart boundary detection with single-pass analysis
3. Limited fallback for edge cases
- Optimize performance with early termination and strategic sampling
- Add comprehensive tests for variable declarations, trailing commas,
escaped quotes, nested objects, and performance edge cases
- Improve reliability for complex JSON structures that Gemini commonly produces
- Fix code formatting with biome
This addresses JSON parsing failures in generateObject operations while
maintaining backward compatibility and significantly improving performance
for large responses.
* fix: update package-lock.json and fix formatting for CI/CD
- Add jsonc-parser to package-lock.json for proper npm ci compatibility
- Fix biome formatting issues in gemini-cli provider and tests
- Ensure all CI/CD checks pass
* feat(gemini-cli): implement comprehensive JSON output reliability system
- Add automatic JSON request detection via content analysis patterns
- Implement task-specific prompt simplification for improved AI compliance
- Add strict JSON enforcement through enhanced system prompts
- Implement response interception with intelligent JSON extraction fallback
- Add comprehensive test coverage for all new JSON handling methods
- Move debug logging to appropriate level for clean user experience
This multi-layered approach addresses gemini-cli's conversational response
tendencies, ensuring reliable structured JSON output for task expansion
operations. Achieves 100% success rate in end-to-end testing while
maintaining full backward compatibility with existing functionality.
Technical implementation includes:
• JSON detection via user message content analysis
• Expand-task prompt simplification with cleaner instructions
• System prompt enhancement with strict JSON enforcement
• Response processing with jsonc-parser-based extraction
• Comprehensive unit test coverage for edge cases
• Debug-level logging to prevent user interface clutter
Resolves: gemini-cli JSON formatting inconsistencies
Tested: All 46 test suites pass, formatting verified
* chore: add changeset for gemini-cli provider implementation
Adds minor version bump for comprehensive gemini-cli provider with:
- Lazy loading and optional dependency management
- Advanced JSON parsing with jsonc-parser
- Multi-layer reliability system for structured output
- Complete test coverage and CI/CD compliance
* refactor: consolidate optional auth provider logic
- Add gemini-cli to existing providersWithoutApiKeys array in config-manager
- Export providersWithoutApiKeys for reuse across modules
- Remove duplicate OPTIONAL_AUTH_PROVIDERS Set from ai-services-unified
- Update ai-services-unified to import and use centralized array
- Fix Jest mock to include new providersWithoutApiKeys export
This eliminates code duplication and provides a single source of truth
for which providers support optional authentication, addressing PR
reviewer feedback about existing similar functionality in src/constants.
* feat(tasks): Fix critical tag corruption bug in task management
- Fixed missing context parameters in writeJSON calls across add-task, remove-task, and add-subtask functions
- Added projectRoot and tag parameters to prevent data corruption in multi-tag environments
- Re-enabled generateTaskFiles calls to ensure markdown files are updated after operations
- Enhanced add_subtask MCP tool with tag parameter support
- Refactored addSubtaskDirect function to properly pass context to core logic
- Streamlined codebase by removing deprecated functionality
This resolves the critical bug where task operations in one tag context would corrupt or delete tasks from other tags in tasks.json.
* feat(task-manager): Enhance addSubtask with current tag support
- Added `getCurrentTag` utility to retrieve the current tag context for task operations.
- Updated `addSubtask` to use the current tag when reading and writing tasks, ensuring proper context handling.
- Refactored tests to accommodate changes in the `addSubtask` function, ensuring accurate mock implementations and expectations.
- Cleaned up test cases for better readability and maintainability.
This improves task management by preventing tag-related data corruption and enhances the overall functionality of the task manager.
* feat(remove-task): Add tag support for task removal and enhance error handling
- Introduced `tag` parameter in `removeTaskDirect` to specify context for task operations, improving multi-tag support.
- Updated logging to include tag context in messages for better traceability.
- Refactored task removal logic to streamline the process and improve error reporting.
- Added comprehensive unit tests to validate tag handling and ensure robust error management.
This enhancement prevents task data corruption across different tags and improves the overall reliability of the task management system.
* feat(add-task): Add projectRoot and tag parameters to addTask tests
- Updated `addTask` unit tests to include `projectRoot` and `tag` parameters for better context handling.
- Enhanced test cases to ensure accurate expectations and improve overall test coverage.
This change aligns with recent enhancements in task management, ensuring consistency across task operations.
* feat(set-task-status): Add tag parameter support and enhance task status handling
- Introduced `tag` parameter in `setTaskStatusDirect` and related functions to improve context management in multi-tag environments.
- Updated `writeJSON` calls to ensure task data integrity across different tags.
- Enhanced unit tests to validate tag preservation during task status updates, ensuring robust functionality.
This change aligns with recent improvements in task management, preventing data corruption and enhancing overall reliability.
* feat(tag-management): Enhance writeJSON calls to preserve tag context
- Updated `writeJSON` calls in `createTag`, `deleteTag`, `renameTag`, `copyTag`, and `enhanceTagsWithMetadata` to include `projectRoot` for better context management and to prevent tag corruption.
- Added comprehensive unit tests for tag management functions to ensure data integrity and proper tag handling during operations.
This change improves the reliability of tag management by ensuring that operations do not corrupt existing tags and maintains the overall structure of the task data.
* feat(expand-task): Update writeJSON to include projectRoot and tag context
- Modified `writeJSON` call in `expandTaskDirect` to pass `projectRoot` and `tag` parameters, ensuring proper context management when saving tasks.json.
- This change aligns with recent enhancements in task management, preventing potential data corruption and improving overall reliability.
* feat(fix-dependencies): Add projectRoot and tag parameters for enhanced context management
- Updated `fixDependenciesDirect` and `registerFixDependenciesTool` to include `projectRoot` and `tag` parameters, improving context handling during dependency fixes.
- Introduced a new unit test for `fixDependenciesCommand` to ensure proper preservation of projectRoot and tag data in JSON outputs.
This change enhances the reliability of dependency management by ensuring that context is maintained across operations, preventing potential data issues.
* fix(context): propagate projectRoot and tag through dependency, expansion, status-update and tag-management commands to prevent cross-tag data corruption
* test(fix-dependencies): Enhance unit tests for fixDependenciesCommand
- Refactored tests to use unstable mocks for utils, ui, and task-manager modules, improving isolation and reliability.
- Added checks for process.exit to ensure proper handling of invalid data scenarios.
- Updated test cases to verify writeJSON calls with projectRoot and tag parameters, ensuring accurate context preservation during dependency fixes.
This change strengthens the test suite for dependency management, ensuring robust functionality and preventing potential data issues.
* chore(plan): remove outdated fix plan for `writeJSON` context parameters
* fix(task-manager): prevent tag corruption in bulk updates and add tag preservation test
- Fix writeJSON call in scripts/modules/task-manager/update-tasks.js (line 469) to include projectRoot and tag parameters.
- Ensure tagged task lists maintain data integrity during bulk updates, preventing task disappearance in tagged contexts.
- Update MCP tools to properly pass tag context through the call chain.
- Introduce a comprehensive test case to verify that all tags are preserved when updating tasks, covering both master and feature-branch scenarios.
Addresses an issue where bulk updates could corrupt tasks.json in tagged task list structures, reinforcing task management robustness.
* style(tests): format task data in update-tasks test
* fix(expand-task): Use tag-specific complexity reports
- Add getTagAwareFilePath utility function to resolve tag-specific file paths
- Update expandTask to use tag-aware complexity report paths
- Fix issue where expand-task always used default complexity report
- Add comprehensive tests for getTagAwareFilePath utility
- Ensure proper handling of file extensions and directory structures
Fixes#850: Expanding tasks not using tag-specific complexity reports
The expandTask function now correctly uses complexity reports specific
to the current tag context (e.g., task-complexity-report_feature-branch.json)
instead of always using the default task-complexity-report.json file.
This enables proper task expansion behavior when working with multiple
tag contexts, ensuring complexity analysis is tag-specific and accurate.
* chore: Add changeset for tag-specific complexity reports fix
* test(expand-task): Add tests for tag-specific complexity report integration
- Introduced a new test suite for verifying the integration of tag-specific complexity reports in the expandTask function.
- Added a test case to ensure the correct complexity report is used when available for a specific tag.
- Mocked file system interactions to simulate the presence of tag-specific complexity reports.
This enhances the test coverage for task expansion behavior, ensuring it accurately reflects the complexity analysis based on the current tag context.
* refactor(task-manager): unify and simplify tag-aware file path logic and tests
- Reformatted imports and cleaned up comments in test files for readability
- Centralized mocks: moved getTagAwareFilePath & slugifyTagForFilePath
mocks to setup.js for consistency and maintainability
- Simplified utils/getTagAwareFilePath: replaced manual parsing with
path.parse() & path.format(); improved extension handling
- Enhanced test mocks for path.parse, path.format & reset path.join
in beforeEach to avoid interference
- All tests now pass consistently; no change in functionality
* docs: Auto-update and format models.md
* fix: correct typos in documentation for parse-prd and taskmaster commands
- Updated the `parse-prd` documentation to fix the spelling of "multiple."
- Clarified the description of the `id` parameter in the `taskmaster` documentation to ensure proper syntax and readability.
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* add compatible platform api support
* Adjust the code according to the suggestions
* Fully revised as requested: restored all required checks, improved compatibility, and converted all comments to English.
* feat: Add support for compatible API endpoints via baseURL
* chore: Add changeset for compatible API support
* chore: cleanup
* chore: improve changeset
* fix: package-lock.json
* fix: package-lock.json
---------
Co-authored-by: He-Xun <1226807142@qq.com>
This functionality was out of scope for the Claude Code provider PR.
The automatic updating of maxTokens values in config.json during
initialization is a general improvement that should be in a separate PR.
Additionally, Claude Code ignores maxTokens and temperature parameters
anyway, making this change irrelevant for the Claude Code integration.
Removed:
- scripts/modules/update-config-tokens.js
- Import and usage in scripts/init.js
This change makes the Claude Code SDK package optional, preventing installation failures for users who don't need Claude Code functionality.
Changes:
- Added @anthropic-ai/claude-code to optionalDependencies in package.json
- Implemented lazy loading in language-model.js to only import the SDK when actually used
- Updated documentation to explain the optional installation requirement
- Applied formatting fixes to ensure code consistency
Benefits:
- Users without Claude Code subscriptions don't need to install the dependency
- Reduces package size for users who don't use Claude Code
- Prevents installation failures if the package is unavailable
- Provides clear error messages when the package is needed but not installed
The implementation uses dynamic imports to load the SDK only when doGenerate() or doStream() is called, ensuring the provider can be instantiated without the package present.
Implements Claude Code as a new AI provider that uses the Claude Code CLI
without requiring API keys. This enables users to leverage Claude models
through their local Claude Code installation.
Key changes:
- Add complete AI SDK v1 implementation for Claude Code provider
- Custom SDK with streaming/non-streaming support
- Session management for conversation continuity
- JSON extraction for object generation mode
- Support for advanced settings (maxTurns, allowedTools, etc.)
- Integrate Claude Code into Task Master's provider system
- Update ai-services-unified.js to handle keyless authentication
- Add provider to supported-models.json with opus/sonnet models
- Ensure correct maxTokens values are applied (opus: 32000, sonnet: 64000)
- Fix maxTokens configuration issue
- Add max_tokens property to getAvailableModels() output
- Update setModel() to properly handle claude-code models
- Create update-config-tokens.js utility for init process
- Add comprehensive documentation
- User guide with configuration examples
- Advanced settings explanation and future integration options
The implementation maintains full backward compatibility with existing
providers while adding seamless Claude Code support to all Task Master
commands.
* feat: Add pyproject.toml as project root marker - Added 'pyproject.toml' to the project markers array in findProjectRoot() - Enables Task Master to recognize Python projects using pyproject.toml - Improves project root detection for modern Python development workflows - Maintains compatibility with existing Node.js and Git-based detection
* chore: add changeset
---------
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* fix(expand): Fix tag corruption in expand command - Fix tag parameter passing through MCP expand-task flow - Add tag parameter to direct function and tool registration - Fix contextGatherer method name from _buildDependencyContext to _buildDependencyGraphs - Add comprehensive test coverage for tag handling in expand-task - Ensures tagged task structure is preserved during expansion - Prevents corruption when tag is undefined. Fixes expand command causing tag corruption in tagged task lists. All existing tests pass and new test coverage added.
* test(e2e): Add comprehensive tag-aware expand testing to verify tag corruption fix - Add new test section for feature-expand tag creation and testing - Verify tag preservation during expand, force expand, and expand --all operations - Test that master tag remains intact and feature-expand tag receives subtasks correctly - Fix file path references to use correct .taskmaster/tasks/tasks.json location - Fix config file check to use .taskmaster/config.json instead of .taskmasterconfig - All tag corruption verification tests pass successfully in E2E test
* fix(changeset): Update E2E test improvements changeset to properly reflect tag corruption fix verification
* chore(changeset): combine duplicate changesets for expand tag corruption fix
Merge eighty-breads-wonder.md into bright-llamas-enter.md to consolidate
the expand command fix and its comprehensive E2E testing enhancements
into a single changeset entry.
* Delete .changeset/eighty-breads-wonder.md
* Version Packages
* chore: fix package.json
* fix(expand): Enhance context handling in expandAllTasks function
- Added `tag` to context destructuring for better context management.
- Updated `readJSON` call to include `contextTag` for improved data integrity.
- Ensured the correct tag is passed during task expansion to prevent tag corruption.
---------
Co-authored-by: Parththipan Thaniperumkarunai <parththipan.thaniperumkarunai@milkmonkey.de>
Co-authored-by: Parthy <52548018+mm-parthy@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix(bedrock): improve AWS credential handling and add model definitions
- Change error to warning when AWS credentials are missing in environment
- Allow fallback to system configuration (aws config files or instance profiles)
- Remove hardcoded region and profile parameters in Bedrock client
- Add Claude 3.7 Sonnet and DeepSeek R1 model definitions for Bedrock
- Update config manager to properly handle Bedrock provider
* chore: cleanup and format and small refactor
---------
Co-authored-by: Ray Krueger <raykrueger@gmail.com>
* fix: switch to ESM export to avoid mixed format
The CLI entrypoint was using `module.exports` alongside ESM `import` statements,
resulting in an invalid mixed module format. Replaced the CommonJS export with
a proper ESM `export` to maintain consistency and prevent module resolution issues.
* chore: add changeset
---------
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* chore(docs): update docs and rules related to model management.
* feat(ai): Add OpenRouter AI provider support
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.
* feat(cli): Add --status/-s filter flag to show command and get-task MCP tool
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.
* fix(tasks): Improve next task logic to be subtask-aware
* fix(tasks): Enable removing multiple tasks/subtasks via comma-separated IDs
- Refactors the core `removeTask` function (`task-manager/remove-task.js`) to accept and iterate over comma-separated task/subtask IDs.
- Updates dependency cleanup and file regeneration logic to run once after processing all specified IDs.
- Adjusts the `remove-task` CLI command (`commands.js`) description and confirmation prompt to handle multiple IDs correctly.
- Fixes a bug in the CLI confirmation prompt where task/subtask titles were not being displayed correctly.
- Updates the `remove_task` MCP tool description to reflect the new multi-ID capability.
This addresses the previously known issue where only the first ID in a comma-separated list was processed.
Closes#140
* Update README.md (#342)
* Update Discord badge (#337)
* refactor(init): Improve robustness and dependencies; Update template deps for AI SDKs; Silence npm install in MCP; Improve conditional model setup logic; Refactor init.js flags; Tweak Getting Started text; Fix MCP server launch command; Update default model in config template
* Refactor: Improve MCP logging, update E2E & tests
Refactors MCP server logging and updates testing infrastructure.
- MCP Server:
- Replaced manual logger wrappers with centralized `createLogWrapper` utility.
- Updated direct function calls to use `{ session, mcpLog }` context.
- Removed deprecated `model` parameter from analyze, expand-all, expand-task tools.
- Adjusted MCP tool import paths and parameter descriptions.
- Documentation:
- Modified `docs/configuration.md`.
- Modified `docs/tutorial.md`.
- Testing:
- E2E Script (`run_e2e.sh`):
- Removed `set -e`.
- Added LLM analysis function (`analyze_log_with_llm`) & integration.
- Adjusted test run directory creation timing.
- Added debug echo statements.
- Deleted Unit Tests: Removed `ai-client-factory.test.js`, `ai-client-utils.test.js`, `ai-services.test.js`.
- Modified Fixtures: Updated `scripts/task-complexity-report.json`.
- Dev Scripts:
- Modified `scripts/dev.js`.
* chore(tests): Passes tests for merge candidate
- Adjusted the interactive model default choice to be 'no change' instead of 'cancel setup'
- E2E script has been perfected and works as designed provided there are all provider API keys .env in the root
- Fixes the entire test suite to make sure it passes with the new architecture.
- Fixes dependency command to properly show there is a validation failure if there is one.
- Refactored config-manager.test.js mocking strategy and fixed assertions to read the real supported-models.json
- Fixed rule-transformer.test.js assertion syntax and transformation logic adjusting replacement for search which was too broad.
- Skip unstable tests in utils.test.js (log, readJSON, writeJSON error paths) due to SIGABRT crash. These tests trigger a native crash (SIGABRT), likely stemming from a conflict between internal chalk usage within the functions and Jest's test environment, possibly related to ESM module handling.
* chore(wtf): removes chai. not sure how that even made it in here. also removes duplicate test in scripts/.
* fix: ensure API key detection properly reads .env in MCP context
Problem:
- Task Master model configuration wasn't properly checking for API keys in the project's .env file when running through MCP
- The isApiKeySet function was only checking session.env and process.env but not inspecting the .env file directly
- This caused incorrect API key status reporting in MCP tools even when keys were properly set in .env
Solution:
- Modified resolveEnvVariable function in utils.js to properly read from .env file at projectRoot
- Updated isApiKeySet to correctly pass projectRoot to resolveEnvVariable
- Enhanced the key detection logic to have consistent behavior between CLI and MCP contexts
- Maintains the correct precedence: session.env → .env file → process.env
Testing:
- Verified working correctly with both MCP and CLI tools
- API keys properly detected in .env file in both contexts
- Deleted .cursor/mcp.json to confirm introspection of .env as fallback works
* fix(update): pass projectRoot through update command flow
Modified ai-services-unified.js, update.js tool, and update-tasks.js direct function to correctly pass projectRoot. This enables the .env file API key fallback mechanism for the update command when running via MCP, ensuring consistent key resolution with the CLI context.
* fix(analyze-complexity): pass projectRoot through analyze-complexity flow
Modified analyze-task-complexity.js core function, direct function, and analyze.js tool to correctly pass projectRoot. Fixed import error in tools/index.js. Added debug logging to _resolveApiKey in ai-services-unified.js. This enables the .env API key fallback for analyze_project_complexity.
* fix(add-task): pass projectRoot and fix logging/refs
Modified add-task core, direct function, and tool to pass projectRoot for .env API key fallback. Fixed logFn reference error and removed deprecated reportProgress call in core addTask function. Verified working.
* fix(parse-prd): pass projectRoot and fix schema/logging
Modified parse-prd core, direct function, and tool to pass projectRoot for .env API key fallback. Corrected Zod schema used in generateObjectService call. Fixed logFn reference error in core parsePRD. Updated unit test mock for utils.js.
* fix(update-task): pass projectRoot and adjust parsing
Modified update-task-by-id core, direct function, and tool to pass projectRoot. Reverted parsing logic in core function to prioritize `{...}` extraction, resolving parsing errors. Fixed ReferenceError by correctly destructuring projectRoot.
* fix(update-subtask): pass projectRoot and allow updating done subtasks
Modified update-subtask-by-id core, direct function, and tool to pass projectRoot for .env API key fallback. Removed check preventing appending details to completed subtasks.
* fix(mcp, expand): pass projectRoot through expand/expand-all flows
Problem: expand_task & expand_all MCP tools failed with .env keys due to missing projectRoot propagation for API key resolution. Also fixed a ReferenceError: wasSilent is not defined in expandTaskDirect.
Solution: Modified core logic, direct functions, and MCP tools for expand-task and expand-all to correctly destructure projectRoot from arguments and pass it down through the context object to the AI service call (generateTextService). Fixed wasSilent scope in expandTaskDirect.
Verification: Tested expand_task successfully in MCP using .env keys. Reviewed expand_all flow for correct projectRoot propagation.
* chore: prettier
* fix(expand-all): add projectRoot to expandAllTasksDirect invokation.
* fix(update-tasks): Improve AI response parsing for 'update' command
Refactors the JSON array parsing logic within
in .
The previous logic primarily relied on extracting content from markdown
code blocks (json or javascript), which proved brittle when the AI
response included comments or non-JSON text within the block, leading to
parsing errors for the command.
This change modifies the parsing strategy to first attempt extracting
content directly between the outermost '[' and ']' brackets. This is
more robust as it targets the expected array structure directly. If
bracket extraction fails, it falls back to looking for a strict json
code block, then prefix stripping, before attempting a raw parse.
This approach aligns with the successful parsing strategy used for
single-object responses in and resolves the
parsing errors previously observed with the command.
* refactor(mcp): introduce withNormalizedProjectRoot HOF for path normalization
Added HOF to mcp tools utils to normalize projectRoot from args/session. Refactored get-task tool to use HOF. Updated relevant documentation.
* refactor(mcp): apply withNormalizedProjectRoot HOF to update tool
Problem: The MCP tool previously handled project root acquisition and path resolution within its method, leading to potential inconsistencies and repetition.
Solution: Refactored the tool () to utilize the new Higher-Order Function (HOF) from .
Specific Changes:
- Imported HOF.
- Updated the Zod schema for the parameter to be optional, as the HOF handles deriving it from the session if not provided.
- Wrapped the entire function body with the HOF.
- Removed the manual call to from within the function body.
- Destructured the from the object received by the wrapped function, ensuring it's the normalized path provided by the HOF.
- Used the normalized variable when calling and when passing arguments to .
This change standardizes project root handling for the tool, simplifies its method, and ensures consistent path normalization. This serves as the pattern for refactoring other MCP tools.
* fix: apply to all tools withNormalizedProjectRoot to fix projectRoot issues for linux and windows
* fix: add rest of tools that need wrapper
* chore: cleanup tools to stop using rootFolder and remove unused imports
* chore: more cleanup
* refactor: Improve update-subtask, consolidate utils, update config
This commit introduces several improvements and refactorings across MCP tools, core logic, and configuration.
**Major Changes:**
1. **Refactor updateSubtaskById:**
- Switched from generateTextService to generateObjectService for structured AI responses, using a Zod schema (subtaskSchema) for validation.
- Revised prompts to have the AI generate relevant content based on user request and context (parent/sibling tasks), while explicitly preventing AI from handling timestamp/tag formatting.
- Implemented **local timestamp generation (new Date().toISOString()) and formatting** (using <info added on ...> tags) within the function *after* receiving the AI response. This ensures reliable and correctly formatted details are appended.
- Corrected logic to append only the locally formatted, AI-generated content block to the existing subtask.details.
2. **Consolidate MCP Utilities:**
- Moved/consolidated the withNormalizedProjectRoot HOF into mcp-server/src/tools/utils.js.
- Updated MCP tools (like update-subtask.js) to import withNormalizedProjectRoot from the new location.
3. **Refactor Project Initialization:**
- Deleted the redundant mcp-server/src/core/direct-functions/initialize-project-direct.js file.
- Updated mcp-server/src/core/task-master-core.js to import initializeProjectDirect from its correct location (./direct-functions/initialize-project.js).
**Other Changes:**
- Updated .taskmasterconfig fallback model to claude-3-7-sonnet-20250219.
- Clarified model cost representation in the models tool description (taskmaster.mdc and mcp-server/src/tools/models.js).
* fix: displayBanner logging when silentMode is active (#385)
* fix: improve error handling, test options, and model configuration
- Enhance error validation in parse-prd.js and update-tasks.js
- Fix bug where mcpLog was incorrectly passed as logWrapper
- Improve error messages and response formatting
- Add --skip-verification flag to E2E tests
- Update MCP server config that ships with init to match new API key structure
- Fix task force/append handling in parse-prd command
- Increase column width in update-tasks display
* chore: fixes parse prd to show loading indicator in cli.
* fix(parse-prd): suggested fix for mcpLog was incorrect. reverting to my previously working code.
* chore(init): No longer ships readme with task-master init (commented out for now). No longer looking for task-master-mcp, instead checked for task-master-ai - this should prevent the init sequence from needlessly adding another mcp server with task-master-mcp to the mpc.json which a ton of people probably ran into.
* chore: restores 3.7 sonnet as the main role.
* fix(add/remove-dependency): dependency mcp tools were failing due to hard-coded tasks path in generate task files.
* chore: removes tasks json backup that was temporarily created.
* fix(next): adjusts mcp tool response to correctly return the next task/subtask. Also adds nextSteps to the next task response.
* chore: prettier
* chore: readme typos
* fix(config): restores sonnet 3.7 as default main role.
* Version Packages
* hotfix: move production package to "dependencies" (#399)
* Version Packages
* Fix: issues with 0.13.0 not working (#402)
* Exit prerelease mode and version packages
* hotfix: move production package to "dependencies"
* Enter prerelease mode and version packages
* Enter prerelease mode and version packages
* chore: cleanup
* chore: improve pre.json and add pre-release workflow
* chore: fix package.json
* chore: cleanup
* chore: improve pre-release workflow
* chore: allow github actions to commit
* extract fileMap and conversionConfig into brand profile
* extract into brand profile
* add windsurf profile
* add remove brand rules function
* fix regex
* add rules command to add/remove rules for a specific brand
* fix post processing for roo
* allow multiples
* add cursor profile
* update test for new structure
* move rules to assets
* use assets/rules for rules files
* use standardized setupMCP function
* fix formatting
* fix formatting
* add logging
* fix escapes
* default to cursor
* allow init with certain rulesets; no more .windsurfrules
* update docs
* update log msg
* fix formatting
* keep mdc extension for cursor
* don't rewrite .mdc to .md inside the files
* fix roo init (add modes)
* fix cursor init (don't use roo transformation by default)
* use more generic function names
* update docs
* fix formatting
* update function names
* add changeset
* add rules to mcp initialize project
* register tool with mcp server
* update docs
* add integration test
* fix cursor initialization
* rule selection
* fix formatting
* fix MCP - remove yes flag
* add import
* update roo tests
* add/update tests
* remove test
* add rules command test
* update MCP responses, centralize rules profiles & helpers
* fix logging and MCP response messages
* fix formatting
* incorrect test
* fix tests
* update fileMap
* fix file extension transformations
* fix formatting
* add rules command test
* test already covered
* fix formatting
* move renaming logic into profiles
* make sure dir is deleted (DS_Store)
* add confirmation for rules removal
* add force flag for rules remove
* use force flag for test
* remove yes parameter
* fix formatting
* import brand profiles from rule-transformer.js
* update comment
* add interactive rules setup
* optimize
* only copy rules specifically listed in fileMap
* update comment
* add cline profile
* add brandDir to remove ambiguity and support Cline
* specify whether to create mcp config and filename
* add mcpConfigName value for parh
* fix formatting
* remove rules just for this repository - only include rules to be distributed
* update error message
* update "brand rules" to "rules"
* update to minor
* remove comment
* remove comments
* move to /src/utils
* optimize imports
* move rules-setup.js to /src/utils
* move rule-transformer.js to /src/utils
* move confirmation to /src/ui/confirm.js
* default to all rules
* use profile js for mcp config settings
* only run rules interactive setup if not provided via command line
* update comments
* initialize with all brands if nothing specified
* update var name
* clean up
* enumerate brands for brand rules
* update instructions
* add test to check for brand profiles
* fix quotes
* update semantics and terminology from 'brand rules' to 'rules profiles'
* fix formatting
* fix formatting
* update function name and remove copying of cursor rules, now handled by rules transformer
* update comment
* rename to mcp-config-setup.js
* use enums for rules actions
* add aggregate reporting for rules add command
* add missing log message
* use simpler path
* use base profile with modifications for each brand
* use displayName and don't select any defaults in setup
* add confirmation if removing ALL rules profiles, and add --force flag on rules remove
* Use profile-detection instead of rules-detection
* add newline at end of mcp config
* add proper formatting for mcp.json
* update rules
* update rules
* update rules
* add checks for other rules and other profile folder items before removing
* update confirmation for rules remove
* update docs
* update changeset
* fix for filepath at bottom of rule
* Update cline profile and add test; adjust other rules tests
* update changeset
* update changeset
* clarify init for all profiles if not specified
* update rule text
* revert text
* use "rule profiles" instead of "rules profiles"
* use standard tool mappings for windsurf
* add Trae support
* update changeset
* update wording
* update to 'rule profile'
* remove unneeded exports to optimize loc
* combine to /src/utils/profiles.js; add codex and claude code profiles
* rename function and add boxen
* add claude and codex integration tests
* organize tests into profiles folder
* mock fs for transformer tests
* update UI
* add cline and trae integration tests
* update test
* update function name
* update formatting
* Update change set with new profiles
* move profile integration tests to subdirectory
* properly create temp directories in /tmp folder
* fix formatting
* use taskmaster subfolder for the 2 TM rules
* update wording
* ensure subdirectory exists
* update rules from next
* update from next
* update taskmaster rule
* add details on new rules command and init
* fix mcp init
* fix MCP path to assets
* remove duplication
* remove duplication
* MCP server path fixes for rules command
* fix for CLI roo rules add/remove
* update tests
* fix formatting
* fix pattern for interactive rule profiles setup
* restore comments
* restore comments
* restore comments
* remove unused import, fix quotes
* add missing integration tests
* add VS Code profile and tests
* update docs and rules to include vscode profile
* add rules subdirectory support per-profile
* move profiles to /src
* fix formatting
* rename to remove ambiguity
* use --setup for rules interactive setup
* Fix Cursor deeplink installation with copy-paste instructions (#723)
* change roo boomerang to orchestrator; update tests that don't use modes
* fix newline
* chore: cleanup
---------
Co-authored-by: Eyal Toledano <eyal@microangel.so>
Co-authored-by: Yuval <yuvalbl@users.noreply.github.com>
Co-authored-by: Marijn van der Werf <marijn.vanderwerf@gmail.com>
Co-authored-by: Eyal Toledano <eutait@gmail.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Update SWE scores (#657)
* docs: Auto-update and format models.md
* feat: Flexible brand rules management (#460)
* chore(docs): update docs and rules related to model management.
* feat(ai): Add OpenRouter AI provider support
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.
* feat(cli): Add --status/-s filter flag to show command and get-task MCP tool
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.
* fix(tasks): Improve next task logic to be subtask-aware
* fix(tasks): Enable removing multiple tasks/subtasks via comma-separated IDs
- Refactors the core `removeTask` function (`task-manager/remove-task.js`) to accept and iterate over comma-separated task/subtask IDs.
- Updates dependency cleanup and file regeneration logic to run once after processing all specified IDs.
- Adjusts the `remove-task` CLI command (`commands.js`) description and confirmation prompt to handle multiple IDs correctly.
- Fixes a bug in the CLI confirmation prompt where task/subtask titles were not being displayed correctly.
- Updates the `remove_task` MCP tool description to reflect the new multi-ID capability.
This addresses the previously known issue where only the first ID in a comma-separated list was processed.
Closes#140
* Update README.md (#342)
* Update Discord badge (#337)
* refactor(init): Improve robustness and dependencies; Update template deps for AI SDKs; Silence npm install in MCP; Improve conditional model setup logic; Refactor init.js flags; Tweak Getting Started text; Fix MCP server launch command; Update default model in config template
* Refactor: Improve MCP logging, update E2E & tests
Refactors MCP server logging and updates testing infrastructure.
- MCP Server:
- Replaced manual logger wrappers with centralized `createLogWrapper` utility.
- Updated direct function calls to use `{ session, mcpLog }` context.
- Removed deprecated `model` parameter from analyze, expand-all, expand-task tools.
- Adjusted MCP tool import paths and parameter descriptions.
- Documentation:
- Modified `docs/configuration.md`.
- Modified `docs/tutorial.md`.
- Testing:
- E2E Script (`run_e2e.sh`):
- Removed `set -e`.
- Added LLM analysis function (`analyze_log_with_llm`) & integration.
- Adjusted test run directory creation timing.
- Added debug echo statements.
- Deleted Unit Tests: Removed `ai-client-factory.test.js`, `ai-client-utils.test.js`, `ai-services.test.js`.
- Modified Fixtures: Updated `scripts/task-complexity-report.json`.
- Dev Scripts:
- Modified `scripts/dev.js`.
* chore(tests): Passes tests for merge candidate
- Adjusted the interactive model default choice to be 'no change' instead of 'cancel setup'
- E2E script has been perfected and works as designed provided there are all provider API keys .env in the root
- Fixes the entire test suite to make sure it passes with the new architecture.
- Fixes dependency command to properly show there is a validation failure if there is one.
- Refactored config-manager.test.js mocking strategy and fixed assertions to read the real supported-models.json
- Fixed rule-transformer.test.js assertion syntax and transformation logic adjusting replacement for search which was too broad.
- Skip unstable tests in utils.test.js (log, readJSON, writeJSON error paths) due to SIGABRT crash. These tests trigger a native crash (SIGABRT), likely stemming from a conflict between internal chalk usage within the functions and Jest's test environment, possibly related to ESM module handling.
* chore(wtf): removes chai. not sure how that even made it in here. also removes duplicate test in scripts/.
* fix: ensure API key detection properly reads .env in MCP context
Problem:
- Task Master model configuration wasn't properly checking for API keys in the project's .env file when running through MCP
- The isApiKeySet function was only checking session.env and process.env but not inspecting the .env file directly
- This caused incorrect API key status reporting in MCP tools even when keys were properly set in .env
Solution:
- Modified resolveEnvVariable function in utils.js to properly read from .env file at projectRoot
- Updated isApiKeySet to correctly pass projectRoot to resolveEnvVariable
- Enhanced the key detection logic to have consistent behavior between CLI and MCP contexts
- Maintains the correct precedence: session.env → .env file → process.env
Testing:
- Verified working correctly with both MCP and CLI tools
- API keys properly detected in .env file in both contexts
- Deleted .cursor/mcp.json to confirm introspection of .env as fallback works
* fix(update): pass projectRoot through update command flow
Modified ai-services-unified.js, update.js tool, and update-tasks.js direct function to correctly pass projectRoot. This enables the .env file API key fallback mechanism for the update command when running via MCP, ensuring consistent key resolution with the CLI context.
* fix(analyze-complexity): pass projectRoot through analyze-complexity flow
Modified analyze-task-complexity.js core function, direct function, and analyze.js tool to correctly pass projectRoot. Fixed import error in tools/index.js. Added debug logging to _resolveApiKey in ai-services-unified.js. This enables the .env API key fallback for analyze_project_complexity.
* fix(add-task): pass projectRoot and fix logging/refs
Modified add-task core, direct function, and tool to pass projectRoot for .env API key fallback. Fixed logFn reference error and removed deprecated reportProgress call in core addTask function. Verified working.
* fix(parse-prd): pass projectRoot and fix schema/logging
Modified parse-prd core, direct function, and tool to pass projectRoot for .env API key fallback. Corrected Zod schema used in generateObjectService call. Fixed logFn reference error in core parsePRD. Updated unit test mock for utils.js.
* fix(update-task): pass projectRoot and adjust parsing
Modified update-task-by-id core, direct function, and tool to pass projectRoot. Reverted parsing logic in core function to prioritize `{...}` extraction, resolving parsing errors. Fixed ReferenceError by correctly destructuring projectRoot.
* fix(update-subtask): pass projectRoot and allow updating done subtasks
Modified update-subtask-by-id core, direct function, and tool to pass projectRoot for .env API key fallback. Removed check preventing appending details to completed subtasks.
* fix(mcp, expand): pass projectRoot through expand/expand-all flows
Problem: expand_task & expand_all MCP tools failed with .env keys due to missing projectRoot propagation for API key resolution. Also fixed a ReferenceError: wasSilent is not defined in expandTaskDirect.
Solution: Modified core logic, direct functions, and MCP tools for expand-task and expand-all to correctly destructure projectRoot from arguments and pass it down through the context object to the AI service call (generateTextService). Fixed wasSilent scope in expandTaskDirect.
Verification: Tested expand_task successfully in MCP using .env keys. Reviewed expand_all flow for correct projectRoot propagation.
* chore: prettier
* fix(expand-all): add projectRoot to expandAllTasksDirect invokation.
* fix(update-tasks): Improve AI response parsing for 'update' command
Refactors the JSON array parsing logic within
in .
The previous logic primarily relied on extracting content from markdown
code blocks (json or javascript), which proved brittle when the AI
response included comments or non-JSON text within the block, leading to
parsing errors for the command.
This change modifies the parsing strategy to first attempt extracting
content directly between the outermost '[' and ']' brackets. This is
more robust as it targets the expected array structure directly. If
bracket extraction fails, it falls back to looking for a strict json
code block, then prefix stripping, before attempting a raw parse.
This approach aligns with the successful parsing strategy used for
single-object responses in and resolves the
parsing errors previously observed with the command.
* refactor(mcp): introduce withNormalizedProjectRoot HOF for path normalization
Added HOF to mcp tools utils to normalize projectRoot from args/session. Refactored get-task tool to use HOF. Updated relevant documentation.
* refactor(mcp): apply withNormalizedProjectRoot HOF to update tool
Problem: The MCP tool previously handled project root acquisition and path resolution within its method, leading to potential inconsistencies and repetition.
Solution: Refactored the tool () to utilize the new Higher-Order Function (HOF) from .
Specific Changes:
- Imported HOF.
- Updated the Zod schema for the parameter to be optional, as the HOF handles deriving it from the session if not provided.
- Wrapped the entire function body with the HOF.
- Removed the manual call to from within the function body.
- Destructured the from the object received by the wrapped function, ensuring it's the normalized path provided by the HOF.
- Used the normalized variable when calling and when passing arguments to .
This change standardizes project root handling for the tool, simplifies its method, and ensures consistent path normalization. This serves as the pattern for refactoring other MCP tools.
* fix: apply to all tools withNormalizedProjectRoot to fix projectRoot issues for linux and windows
* fix: add rest of tools that need wrapper
* chore: cleanup tools to stop using rootFolder and remove unused imports
* chore: more cleanup
* refactor: Improve update-subtask, consolidate utils, update config
This commit introduces several improvements and refactorings across MCP tools, core logic, and configuration.
**Major Changes:**
1. **Refactor updateSubtaskById:**
- Switched from generateTextService to generateObjectService for structured AI responses, using a Zod schema (subtaskSchema) for validation.
- Revised prompts to have the AI generate relevant content based on user request and context (parent/sibling tasks), while explicitly preventing AI from handling timestamp/tag formatting.
- Implemented **local timestamp generation (new Date().toISOString()) and formatting** (using <info added on ...> tags) within the function *after* receiving the AI response. This ensures reliable and correctly formatted details are appended.
- Corrected logic to append only the locally formatted, AI-generated content block to the existing subtask.details.
2. **Consolidate MCP Utilities:**
- Moved/consolidated the withNormalizedProjectRoot HOF into mcp-server/src/tools/utils.js.
- Updated MCP tools (like update-subtask.js) to import withNormalizedProjectRoot from the new location.
3. **Refactor Project Initialization:**
- Deleted the redundant mcp-server/src/core/direct-functions/initialize-project-direct.js file.
- Updated mcp-server/src/core/task-master-core.js to import initializeProjectDirect from its correct location (./direct-functions/initialize-project.js).
**Other Changes:**
- Updated .taskmasterconfig fallback model to claude-3-7-sonnet-20250219.
- Clarified model cost representation in the models tool description (taskmaster.mdc and mcp-server/src/tools/models.js).
* fix: displayBanner logging when silentMode is active (#385)
* fix: improve error handling, test options, and model configuration
- Enhance error validation in parse-prd.js and update-tasks.js
- Fix bug where mcpLog was incorrectly passed as logWrapper
- Improve error messages and response formatting
- Add --skip-verification flag to E2E tests
- Update MCP server config that ships with init to match new API key structure
- Fix task force/append handling in parse-prd command
- Increase column width in update-tasks display
* chore: fixes parse prd to show loading indicator in cli.
* fix(parse-prd): suggested fix for mcpLog was incorrect. reverting to my previously working code.
* chore(init): No longer ships readme with task-master init (commented out for now). No longer looking for task-master-mcp, instead checked for task-master-ai - this should prevent the init sequence from needlessly adding another mcp server with task-master-mcp to the mpc.json which a ton of people probably ran into.
* chore: restores 3.7 sonnet as the main role.
* fix(add/remove-dependency): dependency mcp tools were failing due to hard-coded tasks path in generate task files.
* chore: removes tasks json backup that was temporarily created.
* fix(next): adjusts mcp tool response to correctly return the next task/subtask. Also adds nextSteps to the next task response.
* chore: prettier
* chore: readme typos
* fix(config): restores sonnet 3.7 as default main role.
* Version Packages
* hotfix: move production package to "dependencies" (#399)
* Version Packages
* Fix: issues with 0.13.0 not working (#402)
* Exit prerelease mode and version packages
* hotfix: move production package to "dependencies"
* Enter prerelease mode and version packages
* Enter prerelease mode and version packages
* chore: cleanup
* chore: improve pre.json and add pre-release workflow
* chore: fix package.json
* chore: cleanup
* chore: improve pre-release workflow
* chore: allow github actions to commit
* extract fileMap and conversionConfig into brand profile
* extract into brand profile
* add windsurf profile
* add remove brand rules function
* fix regex
* add rules command to add/remove rules for a specific brand
* fix post processing for roo
* allow multiples
* add cursor profile
* update test for new structure
* move rules to assets
* use assets/rules for rules files
* use standardized setupMCP function
* fix formatting
* fix formatting
* add logging
* fix escapes
* default to cursor
* allow init with certain rulesets; no more .windsurfrules
* update docs
* update log msg
* fix formatting
* keep mdc extension for cursor
* don't rewrite .mdc to .md inside the files
* fix roo init (add modes)
* fix cursor init (don't use roo transformation by default)
* use more generic function names
* update docs
* fix formatting
* update function names
* add changeset
* add rules to mcp initialize project
* register tool with mcp server
* update docs
* add integration test
* fix cursor initialization
* rule selection
* fix formatting
* fix MCP - remove yes flag
* add import
* update roo tests
* add/update tests
* remove test
* add rules command test
* update MCP responses, centralize rules profiles & helpers
* fix logging and MCP response messages
* fix formatting
* incorrect test
* fix tests
* update fileMap
* fix file extension transformations
* fix formatting
* add rules command test
* test already covered
* fix formatting
* move renaming logic into profiles
* make sure dir is deleted (DS_Store)
* add confirmation for rules removal
* add force flag for rules remove
* use force flag for test
* remove yes parameter
* fix formatting
* import brand profiles from rule-transformer.js
* update comment
* add interactive rules setup
* optimize
* only copy rules specifically listed in fileMap
* update comment
* add cline profile
* add brandDir to remove ambiguity and support Cline
* specify whether to create mcp config and filename
* add mcpConfigName value for parh
* fix formatting
* remove rules just for this repository - only include rules to be distributed
* update error message
* update "brand rules" to "rules"
* update to minor
* remove comment
* remove comments
* move to /src/utils
* optimize imports
* move rules-setup.js to /src/utils
* move rule-transformer.js to /src/utils
* move confirmation to /src/ui/confirm.js
* default to all rules
* use profile js for mcp config settings
* only run rules interactive setup if not provided via command line
* update comments
* initialize with all brands if nothing specified
* update var name
* clean up
* enumerate brands for brand rules
* update instructions
* add test to check for brand profiles
* fix quotes
* update semantics and terminology from 'brand rules' to 'rules profiles'
* fix formatting
* fix formatting
* update function name and remove copying of cursor rules, now handled by rules transformer
* update comment
* rename to mcp-config-setup.js
* use enums for rules actions
* add aggregate reporting for rules add command
* add missing log message
* use simpler path
* use base profile with modifications for each brand
* use displayName and don't select any defaults in setup
* add confirmation if removing ALL rules profiles, and add --force flag on rules remove
* Use profile-detection instead of rules-detection
* add newline at end of mcp config
* add proper formatting for mcp.json
* update rules
* update rules
* update rules
* add checks for other rules and other profile folder items before removing
* update confirmation for rules remove
* update docs
* update changeset
* fix for filepath at bottom of rule
* Update cline profile and add test; adjust other rules tests
* update changeset
* update changeset
* clarify init for all profiles if not specified
* update rule text
* revert text
* use "rule profiles" instead of "rules profiles"
* use standard tool mappings for windsurf
* add Trae support
* update changeset
* update wording
* update to 'rule profile'
* remove unneeded exports to optimize loc
* combine to /src/utils/profiles.js; add codex and claude code profiles
* rename function and add boxen
* add claude and codex integration tests
* organize tests into profiles folder
* mock fs for transformer tests
* update UI
* add cline and trae integration tests
* update test
* update function name
* update formatting
* Update change set with new profiles
* move profile integration tests to subdirectory
* properly create temp directories in /tmp folder
* fix formatting
* use taskmaster subfolder for the 2 TM rules
* update wording
* ensure subdirectory exists
* update rules from next
* update from next
* update taskmaster rule
* add details on new rules command and init
* fix mcp init
* fix MCP path to assets
* remove duplication
* remove duplication
* MCP server path fixes for rules command
* fix for CLI roo rules add/remove
* update tests
* fix formatting
* fix pattern for interactive rule profiles setup
* restore comments
* restore comments
* restore comments
* remove unused import, fix quotes
* add missing integration tests
* add VS Code profile and tests
* update docs and rules to include vscode profile
* add rules subdirectory support per-profile
* move profiles to /src
* fix formatting
* rename to remove ambiguity
* use --setup for rules interactive setup
* Fix Cursor deeplink installation with copy-paste instructions (#723)
* change roo boomerang to orchestrator; update tests that don't use modes
* fix newline
* chore: cleanup
---------
Co-authored-by: Eyal Toledano <eyal@microangel.so>
Co-authored-by: Yuval <yuvalbl@users.noreply.github.com>
Co-authored-by: Marijn van der Werf <marijn.vanderwerf@gmail.com>
Co-authored-by: Eyal Toledano <eutait@gmail.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix: providers config for azure, bedrock, and vertex (#822)
* fix: providers config for azure, bedrock, and vertex
* chore: improve changelog
* chore: fix CI
* fix: switch to ESM export to avoid mixed format (#633)
* fix: switch to ESM export to avoid mixed format
The CLI entrypoint was using `module.exports` alongside ESM `import` statements,
resulting in an invalid mixed module format. Replaced the CommonJS export with
a proper ESM `export` to maintain consistency and prevent module resolution issues.
* chore: add changeset
---------
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* fix: Fix external provider support (#726)
* fix(bedrock): improve AWS credential handling and add model definitions (#826)
* fix(bedrock): improve AWS credential handling and add model definitions
- Change error to warning when AWS credentials are missing in environment
- Allow fallback to system configuration (aws config files or instance profiles)
- Remove hardcoded region and profile parameters in Bedrock client
- Add Claude 3.7 Sonnet and DeepSeek R1 model definitions for Bedrock
- Update config manager to properly handle Bedrock provider
* chore: cleanup and format and small refactor
---------
Co-authored-by: Ray Krueger <raykrueger@gmail.com>
* docs: Auto-update and format models.md
* Version Packages
* chore: fix package.json
* Fix/expand command tag corruption (#827)
* fix(expand): Fix tag corruption in expand command - Fix tag parameter passing through MCP expand-task flow - Add tag parameter to direct function and tool registration - Fix contextGatherer method name from _buildDependencyContext to _buildDependencyGraphs - Add comprehensive test coverage for tag handling in expand-task - Ensures tagged task structure is preserved during expansion - Prevents corruption when tag is undefined. Fixes expand command causing tag corruption in tagged task lists. All existing tests pass and new test coverage added.
* test(e2e): Add comprehensive tag-aware expand testing to verify tag corruption fix - Add new test section for feature-expand tag creation and testing - Verify tag preservation during expand, force expand, and expand --all operations - Test that master tag remains intact and feature-expand tag receives subtasks correctly - Fix file path references to use correct .taskmaster/tasks/tasks.json location - Fix config file check to use .taskmaster/config.json instead of .taskmasterconfig - All tag corruption verification tests pass successfully in E2E test
* fix(changeset): Update E2E test improvements changeset to properly reflect tag corruption fix verification
* chore(changeset): combine duplicate changesets for expand tag corruption fix
Merge eighty-breads-wonder.md into bright-llamas-enter.md to consolidate
the expand command fix and its comprehensive E2E testing enhancements
into a single changeset entry.
* Delete .changeset/eighty-breads-wonder.md
* Version Packages
* chore: fix package.json
* fix(expand): Enhance context handling in expandAllTasks function
- Added `tag` to context destructuring for better context management.
- Updated `readJSON` call to include `contextTag` for improved data integrity.
- Ensured the correct tag is passed during task expansion to prevent tag corruption.
---------
Co-authored-by: Parththipan Thaniperumkarunai <parththipan.thaniperumkarunai@milkmonkey.de>
Co-authored-by: Parthy <52548018+mm-parthy@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Add pyproject.toml as project root marker (#804)
* feat: Add pyproject.toml as project root marker - Added 'pyproject.toml' to the project markers array in findProjectRoot() - Enables Task Master to recognize Python projects using pyproject.toml - Improves project root detection for modern Python development workflows - Maintains compatibility with existing Node.js and Git-based detection
* chore: add changeset
---------
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* feat: add Claude Code provider support
Implements Claude Code as a new AI provider that uses the Claude Code CLI
without requiring API keys. This enables users to leverage Claude models
through their local Claude Code installation.
Key changes:
- Add complete AI SDK v1 implementation for Claude Code provider
- Custom SDK with streaming/non-streaming support
- Session management for conversation continuity
- JSON extraction for object generation mode
- Support for advanced settings (maxTurns, allowedTools, etc.)
- Integrate Claude Code into Task Master's provider system
- Update ai-services-unified.js to handle keyless authentication
- Add provider to supported-models.json with opus/sonnet models
- Ensure correct maxTokens values are applied (opus: 32000, sonnet: 64000)
- Fix maxTokens configuration issue
- Add max_tokens property to getAvailableModels() output
- Update setModel() to properly handle claude-code models
- Create update-config-tokens.js utility for init process
- Add comprehensive documentation
- User guide with configuration examples
- Advanced settings explanation and future integration options
The implementation maintains full backward compatibility with existing
providers while adding seamless Claude Code support to all Task Master
commands.
* fix(docs): correct invalid commands in claude-code usage examples
- Remove non-existent 'do', 'estimate', and 'analyze' commands
- Replace with actual Task Master commands: next, show, set-status
- Use correct syntax for parse-prd and analyze-complexity
* feat: make @anthropic-ai/claude-code an optional dependency
This change makes the Claude Code SDK package optional, preventing installation failures for users who don't need Claude Code functionality.
Changes:
- Added @anthropic-ai/claude-code to optionalDependencies in package.json
- Implemented lazy loading in language-model.js to only import the SDK when actually used
- Updated documentation to explain the optional installation requirement
- Applied formatting fixes to ensure code consistency
Benefits:
- Users without Claude Code subscriptions don't need to install the dependency
- Reduces package size for users who don't use Claude Code
- Prevents installation failures if the package is unavailable
- Provides clear error messages when the package is needed but not installed
The implementation uses dynamic imports to load the SDK only when doGenerate() or doStream() is called, ensuring the provider can be instantiated without the package present.
* test: add comprehensive tests for ClaudeCodeProvider
Addresses code review feedback about missing automated tests for the ClaudeCodeProvider.
## Changes
- Added unit tests for ClaudeCodeProvider class covering constructor, validateAuth, and getClient methods
- Added unit tests for ClaudeCodeLanguageModel testing lazy loading behavior and error handling
- Added integration tests verifying optional dependency behavior when @anthropic-ai/claude-code is not installed
## Test Coverage
1. **Unit Tests**:
- ClaudeCodeProvider: Basic functionality, no API key requirement, client creation
- ClaudeCodeLanguageModel: Model initialization, lazy loading, error messages, warning generation
2. **Integration Tests**:
- Optional dependency behavior when package is not installed
- Clear error messages for users about missing package
- Provider instantiation works but usage fails gracefully
All tests pass and provide comprehensive coverage for the claude-code provider implementation.
* revert: remove maxTokens update functionality from init
This functionality was out of scope for the Claude Code provider PR.
The automatic updating of maxTokens values in config.json during
initialization is a general improvement that should be in a separate PR.
Additionally, Claude Code ignores maxTokens and temperature parameters
anyway, making this change irrelevant for the Claude Code integration.
Removed:
- scripts/modules/update-config-tokens.js
- Import and usage in scripts/init.js
* docs: add Claude Code support information to README
- Added Claude Code to the list of supported providers in Requirements section
- Noted that Claude Code requires no API key but needs Claude Code CLI
- Added example of configuring claude-code/sonnet model
- Created dedicated Claude Code Support section with key information
- Added link to detailed Claude Code setup documentation
This ensures users are aware of the Claude Code option as a no-API-key
alternative for using Claude models.
* style: apply biome formatting to test files
* fix(models): add missing --claude-code flag to models command
The models command was missing the --claude-code provider flag, preventing users from setting Claude Code models via CLI. While the backend already supported claude-code as a provider hint, there was no command-line flag to trigger it.
Changes:
- Added --claude-code option to models command alongside existing provider flags
- Updated provider flags validation to include claudeCode option
- Added claude-code to providerHint logic for all three model roles (main, research, fallback)
- Updated error message to include --claude-code in list of mutually exclusive flags
- Added example usage in help text
This allows users to properly set Claude Code models using commands like:
task-master models --set-main sonnet --claude-code
task-master models --set-main opus --claude-code
Without this flag, users would get "Model ID not found" errors when trying to set claude-code models, as the system couldn't determine the correct provider for generic model names like "sonnet" or "opus".
* chore: add changeset for Claude Code provider feature
* docs: Auto-update and format models.md
* readme: add troubleshooting note for MCP tools not working
* Feature/compatibleapisupport (#830)
* add compatible platform api support
* Adjust the code according to the suggestions
* Fully revised as requested: restored all required checks, improved compatibility, and converted all comments to English.
* feat: Add support for compatible API endpoints via baseURL
* chore: Add changeset for compatible API support
* chore: cleanup
* chore: improve changeset
* fix: package-lock.json
* fix: package-lock.json
---------
Co-authored-by: He-Xun <1226807142@qq.com>
* Rename Roo Code "Boomerang" role to "Orchestrator" (#831)
* feat: Enhanced project initialization with Git worktree detection (#743)
* Fix Cursor deeplink installation with copy-paste instructions (#723)
* detect git worktree
* add changeset
* add aliases and git flags
* add changeset
* rename and update test
* add store tasks in git functionality
* update changeset
* fix newline
* remove unused import
* update command wording
* update command option text
* fix: update task by id (#834)
* store tasks in git by default (#835)
* Call rules interactive setup during init (#833)
* chore: rc version bump
* feat: Claude Code slash commands for Task Master (#774)
* Fix Cursor deeplink installation with copy-paste instructions (#723)
* fix: expand-task (#755)
* docs: Update o3 model price (#751)
* docs: Auto-update and format models.md
* docs: Auto-update and format models.md
* feat: Add Claude Code task master commands
Adds Task Master slash commands for Claude Code under /project:tm/ namespace
---------
Co-authored-by: Joe Danziger <joe@ticc.net>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
Co-authored-by: Volodymyr Zahorniak <7808206+zahorniak@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: neno-is-ooo <204701868+neno-is-ooo@users.noreply.github.com>
* feat: make more compatible with "o" family models (#839)
* docs: Auto-update and format models.md
* docs: Add comprehensive Azure OpenAI configuration documentation (#837)
* docs: Add comprehensive Azure OpenAI configuration documentation
- Add detailed Azure OpenAI configuration section with prerequisites, authentication, and setup options
- Include both global and per-model baseURL configuration examples
- Add comprehensive troubleshooting guide for common Azure OpenAI issues
- Update environment variables section with Azure OpenAI examples
- Add Azure OpenAI models to all model tables (Main, Research, Fallback)
- Include prominent Azure configuration example in main documentation
- Fix azureBaseURL format to use correct Azure OpenAI endpoint structure
Addresses common Azure OpenAI setup challenges and provides clear guidance for new users.
* refactor: Move Azure models from docs/models.md to scripts/modules/supported-models.json
- Remove Azure model entries from documentation tables
- Add Azure provider section to supported-models.json with gpt-4o, gpt-4o-mini, and gpt-4-1
- Maintain consistency with existing model configuration structure
* docs: Auto-update and format models.md
* Version Packages
* chore: format fix
---------
Co-authored-by: Riccardo (Ricky) Esclapon <32306488+ries9112@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Joe Danziger <joe@ticc.net>
Co-authored-by: Eyal Toledano <eyal@microangel.so>
Co-authored-by: Yuval <yuvalbl@users.noreply.github.com>
Co-authored-by: Marijn van der Werf <marijn.vanderwerf@gmail.com>
Co-authored-by: Eyal Toledano <eutait@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Nathan Marley <nathan@glowberrylabs.com>
Co-authored-by: Ray Krueger <raykrueger@gmail.com>
Co-authored-by: Parththipan Thaniperumkarunai <parththipan.thaniperumkarunai@milkmonkey.de>
Co-authored-by: Parthy <52548018+mm-parthy@users.noreply.github.com>
Co-authored-by: ejones40 <ethan.jones@fortyau.com>
Co-authored-by: Ben Vargas <ben@vargas.com>
Co-authored-by: V4G4X <34249137+V4G4X@users.noreply.github.com>
Co-authored-by: He-Xun <1226807142@qq.com>
Co-authored-by: neno <github@meaning.systems>
Co-authored-by: Volodymyr Zahorniak <7808206+zahorniak@users.noreply.github.com>
Co-authored-by: neno-is-ooo <204701868+neno-is-ooo@users.noreply.github.com>
Co-authored-by: Jitesh Thakur <56656484+Jitha-afk@users.noreply.github.com>
* docs: Add comprehensive Azure OpenAI configuration documentation
- Add detailed Azure OpenAI configuration section with prerequisites, authentication, and setup options
- Include both global and per-model baseURL configuration examples
- Add comprehensive troubleshooting guide for common Azure OpenAI issues
- Update environment variables section with Azure OpenAI examples
- Add Azure OpenAI models to all model tables (Main, Research, Fallback)
- Include prominent Azure configuration example in main documentation
- Fix azureBaseURL format to use correct Azure OpenAI endpoint structure
Addresses common Azure OpenAI setup challenges and provides clear guidance for new users.
* refactor: Move Azure models from docs/models.md to scripts/modules/supported-models.json
- Remove Azure model entries from documentation tables
- Add Azure provider section to supported-models.json with gpt-4o, gpt-4o-mini, and gpt-4-1
- Maintain consistency with existing model configuration structure
* add compatible platform api support
* Adjust the code according to the suggestions
* Fully revised as requested: restored all required checks, improved compatibility, and converted all comments to English.
* feat: Add support for compatible API endpoints via baseURL
* chore: Add changeset for compatible API support
* chore: cleanup
* chore: improve changeset
* fix: package-lock.json
* fix: package-lock.json
---------
Co-authored-by: He-Xun <1226807142@qq.com>
The models command was missing the --claude-code provider flag, preventing users from setting Claude Code models via CLI. While the backend already supported claude-code as a provider hint, there was no command-line flag to trigger it.
Changes:
- Added --claude-code option to models command alongside existing provider flags
- Updated provider flags validation to include claudeCode option
- Added claude-code to providerHint logic for all three model roles (main, research, fallback)
- Updated error message to include --claude-code in list of mutually exclusive flags
- Added example usage in help text
This allows users to properly set Claude Code models using commands like:
task-master models --set-main sonnet --claude-code
task-master models --set-main opus --claude-code
Without this flag, users would get "Model ID not found" errors when trying to set claude-code models, as the system couldn't determine the correct provider for generic model names like "sonnet" or "opus".
- Added Claude Code to the list of supported providers in Requirements section
- Noted that Claude Code requires no API key but needs Claude Code CLI
- Added example of configuring claude-code/sonnet model
- Created dedicated Claude Code Support section with key information
- Added link to detailed Claude Code setup documentation
This ensures users are aware of the Claude Code option as a no-API-key
alternative for using Claude models.
This functionality was out of scope for the Claude Code provider PR.
The automatic updating of maxTokens values in config.json during
initialization is a general improvement that should be in a separate PR.
Additionally, Claude Code ignores maxTokens and temperature parameters
anyway, making this change irrelevant for the Claude Code integration.
Removed:
- scripts/modules/update-config-tokens.js
- Import and usage in scripts/init.js
Addresses code review feedback about missing automated tests for the ClaudeCodeProvider.
## Changes
- Added unit tests for ClaudeCodeProvider class covering constructor, validateAuth, and getClient methods
- Added unit tests for ClaudeCodeLanguageModel testing lazy loading behavior and error handling
- Added integration tests verifying optional dependency behavior when @anthropic-ai/claude-code is not installed
## Test Coverage
1. **Unit Tests**:
- ClaudeCodeProvider: Basic functionality, no API key requirement, client creation
- ClaudeCodeLanguageModel: Model initialization, lazy loading, error messages, warning generation
2. **Integration Tests**:
- Optional dependency behavior when package is not installed
- Clear error messages for users about missing package
- Provider instantiation works but usage fails gracefully
All tests pass and provide comprehensive coverage for the claude-code provider implementation.
This change makes the Claude Code SDK package optional, preventing installation failures for users who don't need Claude Code functionality.
Changes:
- Added @anthropic-ai/claude-code to optionalDependencies in package.json
- Implemented lazy loading in language-model.js to only import the SDK when actually used
- Updated documentation to explain the optional installation requirement
- Applied formatting fixes to ensure code consistency
Benefits:
- Users without Claude Code subscriptions don't need to install the dependency
- Reduces package size for users who don't use Claude Code
- Prevents installation failures if the package is unavailable
- Provides clear error messages when the package is needed but not installed
The implementation uses dynamic imports to load the SDK only when doGenerate() or doStream() is called, ensuring the provider can be instantiated without the package present.
- Remove non-existent 'do', 'estimate', and 'analyze' commands
- Replace with actual Task Master commands: next, show, set-status
- Use correct syntax for parse-prd and analyze-complexity
Implements Claude Code as a new AI provider that uses the Claude Code CLI
without requiring API keys. This enables users to leverage Claude models
through their local Claude Code installation.
Key changes:
- Add complete AI SDK v1 implementation for Claude Code provider
- Custom SDK with streaming/non-streaming support
- Session management for conversation continuity
- JSON extraction for object generation mode
- Support for advanced settings (maxTurns, allowedTools, etc.)
- Integrate Claude Code into Task Master's provider system
- Update ai-services-unified.js to handle keyless authentication
- Add provider to supported-models.json with opus/sonnet models
- Ensure correct maxTokens values are applied (opus: 32000, sonnet: 64000)
- Fix maxTokens configuration issue
- Add max_tokens property to getAvailableModels() output
- Update setModel() to properly handle claude-code models
- Create update-config-tokens.js utility for init process
- Add comprehensive documentation
- User guide with configuration examples
- Advanced settings explanation and future integration options
The implementation maintains full backward compatibility with existing
providers while adding seamless Claude Code support to all Task Master
commands.
* feat: Add pyproject.toml as project root marker - Added 'pyproject.toml' to the project markers array in findProjectRoot() - Enables Task Master to recognize Python projects using pyproject.toml - Improves project root detection for modern Python development workflows - Maintains compatibility with existing Node.js and Git-based detection
* chore: add changeset
---------
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* fix(expand): Fix tag corruption in expand command - Fix tag parameter passing through MCP expand-task flow - Add tag parameter to direct function and tool registration - Fix contextGatherer method name from _buildDependencyContext to _buildDependencyGraphs - Add comprehensive test coverage for tag handling in expand-task - Ensures tagged task structure is preserved during expansion - Prevents corruption when tag is undefined. Fixes expand command causing tag corruption in tagged task lists. All existing tests pass and new test coverage added.
* test(e2e): Add comprehensive tag-aware expand testing to verify tag corruption fix - Add new test section for feature-expand tag creation and testing - Verify tag preservation during expand, force expand, and expand --all operations - Test that master tag remains intact and feature-expand tag receives subtasks correctly - Fix file path references to use correct .taskmaster/tasks/tasks.json location - Fix config file check to use .taskmaster/config.json instead of .taskmasterconfig - All tag corruption verification tests pass successfully in E2E test
* fix(changeset): Update E2E test improvements changeset to properly reflect tag corruption fix verification
* chore(changeset): combine duplicate changesets for expand tag corruption fix
Merge eighty-breads-wonder.md into bright-llamas-enter.md to consolidate
the expand command fix and its comprehensive E2E testing enhancements
into a single changeset entry.
* Delete .changeset/eighty-breads-wonder.md
* Version Packages
* chore: fix package.json
* fix(expand): Enhance context handling in expandAllTasks function
- Added `tag` to context destructuring for better context management.
- Updated `readJSON` call to include `contextTag` for improved data integrity.
- Ensured the correct tag is passed during task expansion to prevent tag corruption.
---------
Co-authored-by: Parththipan Thaniperumkarunai <parththipan.thaniperumkarunai@milkmonkey.de>
Co-authored-by: Parthy <52548018+mm-parthy@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix(bedrock): improve AWS credential handling and add model definitions
- Change error to warning when AWS credentials are missing in environment
- Allow fallback to system configuration (aws config files or instance profiles)
- Remove hardcoded region and profile parameters in Bedrock client
- Add Claude 3.7 Sonnet and DeepSeek R1 model definitions for Bedrock
- Update config manager to properly handle Bedrock provider
* chore: cleanup and format and small refactor
---------
Co-authored-by: Ray Krueger <raykrueger@gmail.com>
* fix: switch to ESM export to avoid mixed format
The CLI entrypoint was using `module.exports` alongside ESM `import` statements,
resulting in an invalid mixed module format. Replaced the CommonJS export with
a proper ESM `export` to maintain consistency and prevent module resolution issues.
* chore: add changeset
---------
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
* chore(docs): update docs and rules related to model management.
* feat(ai): Add OpenRouter AI provider support
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.
* feat(cli): Add --status/-s filter flag to show command and get-task MCP tool
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.
* fix(tasks): Improve next task logic to be subtask-aware
* fix(tasks): Enable removing multiple tasks/subtasks via comma-separated IDs
- Refactors the core `removeTask` function (`task-manager/remove-task.js`) to accept and iterate over comma-separated task/subtask IDs.
- Updates dependency cleanup and file regeneration logic to run once after processing all specified IDs.
- Adjusts the `remove-task` CLI command (`commands.js`) description and confirmation prompt to handle multiple IDs correctly.
- Fixes a bug in the CLI confirmation prompt where task/subtask titles were not being displayed correctly.
- Updates the `remove_task` MCP tool description to reflect the new multi-ID capability.
This addresses the previously known issue where only the first ID in a comma-separated list was processed.
Closes#140
* Update README.md (#342)
* Update Discord badge (#337)
* refactor(init): Improve robustness and dependencies; Update template deps for AI SDKs; Silence npm install in MCP; Improve conditional model setup logic; Refactor init.js flags; Tweak Getting Started text; Fix MCP server launch command; Update default model in config template
* Refactor: Improve MCP logging, update E2E & tests
Refactors MCP server logging and updates testing infrastructure.
- MCP Server:
- Replaced manual logger wrappers with centralized `createLogWrapper` utility.
- Updated direct function calls to use `{ session, mcpLog }` context.
- Removed deprecated `model` parameter from analyze, expand-all, expand-task tools.
- Adjusted MCP tool import paths and parameter descriptions.
- Documentation:
- Modified `docs/configuration.md`.
- Modified `docs/tutorial.md`.
- Testing:
- E2E Script (`run_e2e.sh`):
- Removed `set -e`.
- Added LLM analysis function (`analyze_log_with_llm`) & integration.
- Adjusted test run directory creation timing.
- Added debug echo statements.
- Deleted Unit Tests: Removed `ai-client-factory.test.js`, `ai-client-utils.test.js`, `ai-services.test.js`.
- Modified Fixtures: Updated `scripts/task-complexity-report.json`.
- Dev Scripts:
- Modified `scripts/dev.js`.
* chore(tests): Passes tests for merge candidate
- Adjusted the interactive model default choice to be 'no change' instead of 'cancel setup'
- E2E script has been perfected and works as designed provided there are all provider API keys .env in the root
- Fixes the entire test suite to make sure it passes with the new architecture.
- Fixes dependency command to properly show there is a validation failure if there is one.
- Refactored config-manager.test.js mocking strategy and fixed assertions to read the real supported-models.json
- Fixed rule-transformer.test.js assertion syntax and transformation logic adjusting replacement for search which was too broad.
- Skip unstable tests in utils.test.js (log, readJSON, writeJSON error paths) due to SIGABRT crash. These tests trigger a native crash (SIGABRT), likely stemming from a conflict between internal chalk usage within the functions and Jest's test environment, possibly related to ESM module handling.
* chore(wtf): removes chai. not sure how that even made it in here. also removes duplicate test in scripts/.
* fix: ensure API key detection properly reads .env in MCP context
Problem:
- Task Master model configuration wasn't properly checking for API keys in the project's .env file when running through MCP
- The isApiKeySet function was only checking session.env and process.env but not inspecting the .env file directly
- This caused incorrect API key status reporting in MCP tools even when keys were properly set in .env
Solution:
- Modified resolveEnvVariable function in utils.js to properly read from .env file at projectRoot
- Updated isApiKeySet to correctly pass projectRoot to resolveEnvVariable
- Enhanced the key detection logic to have consistent behavior between CLI and MCP contexts
- Maintains the correct precedence: session.env → .env file → process.env
Testing:
- Verified working correctly with both MCP and CLI tools
- API keys properly detected in .env file in both contexts
- Deleted .cursor/mcp.json to confirm introspection of .env as fallback works
* fix(update): pass projectRoot through update command flow
Modified ai-services-unified.js, update.js tool, and update-tasks.js direct function to correctly pass projectRoot. This enables the .env file API key fallback mechanism for the update command when running via MCP, ensuring consistent key resolution with the CLI context.
* fix(analyze-complexity): pass projectRoot through analyze-complexity flow
Modified analyze-task-complexity.js core function, direct function, and analyze.js tool to correctly pass projectRoot. Fixed import error in tools/index.js. Added debug logging to _resolveApiKey in ai-services-unified.js. This enables the .env API key fallback for analyze_project_complexity.
* fix(add-task): pass projectRoot and fix logging/refs
Modified add-task core, direct function, and tool to pass projectRoot for .env API key fallback. Fixed logFn reference error and removed deprecated reportProgress call in core addTask function. Verified working.
* fix(parse-prd): pass projectRoot and fix schema/logging
Modified parse-prd core, direct function, and tool to pass projectRoot for .env API key fallback. Corrected Zod schema used in generateObjectService call. Fixed logFn reference error in core parsePRD. Updated unit test mock for utils.js.
* fix(update-task): pass projectRoot and adjust parsing
Modified update-task-by-id core, direct function, and tool to pass projectRoot. Reverted parsing logic in core function to prioritize `{...}` extraction, resolving parsing errors. Fixed ReferenceError by correctly destructuring projectRoot.
* fix(update-subtask): pass projectRoot and allow updating done subtasks
Modified update-subtask-by-id core, direct function, and tool to pass projectRoot for .env API key fallback. Removed check preventing appending details to completed subtasks.
* fix(mcp, expand): pass projectRoot through expand/expand-all flows
Problem: expand_task & expand_all MCP tools failed with .env keys due to missing projectRoot propagation for API key resolution. Also fixed a ReferenceError: wasSilent is not defined in expandTaskDirect.
Solution: Modified core logic, direct functions, and MCP tools for expand-task and expand-all to correctly destructure projectRoot from arguments and pass it down through the context object to the AI service call (generateTextService). Fixed wasSilent scope in expandTaskDirect.
Verification: Tested expand_task successfully in MCP using .env keys. Reviewed expand_all flow for correct projectRoot propagation.
* chore: prettier
* fix(expand-all): add projectRoot to expandAllTasksDirect invokation.
* fix(update-tasks): Improve AI response parsing for 'update' command
Refactors the JSON array parsing logic within
in .
The previous logic primarily relied on extracting content from markdown
code blocks (json or javascript), which proved brittle when the AI
response included comments or non-JSON text within the block, leading to
parsing errors for the command.
This change modifies the parsing strategy to first attempt extracting
content directly between the outermost '[' and ']' brackets. This is
more robust as it targets the expected array structure directly. If
bracket extraction fails, it falls back to looking for a strict json
code block, then prefix stripping, before attempting a raw parse.
This approach aligns with the successful parsing strategy used for
single-object responses in and resolves the
parsing errors previously observed with the command.
* refactor(mcp): introduce withNormalizedProjectRoot HOF for path normalization
Added HOF to mcp tools utils to normalize projectRoot from args/session. Refactored get-task tool to use HOF. Updated relevant documentation.
* refactor(mcp): apply withNormalizedProjectRoot HOF to update tool
Problem: The MCP tool previously handled project root acquisition and path resolution within its method, leading to potential inconsistencies and repetition.
Solution: Refactored the tool () to utilize the new Higher-Order Function (HOF) from .
Specific Changes:
- Imported HOF.
- Updated the Zod schema for the parameter to be optional, as the HOF handles deriving it from the session if not provided.
- Wrapped the entire function body with the HOF.
- Removed the manual call to from within the function body.
- Destructured the from the object received by the wrapped function, ensuring it's the normalized path provided by the HOF.
- Used the normalized variable when calling and when passing arguments to .
This change standardizes project root handling for the tool, simplifies its method, and ensures consistent path normalization. This serves as the pattern for refactoring other MCP tools.
* fix: apply to all tools withNormalizedProjectRoot to fix projectRoot issues for linux and windows
* fix: add rest of tools that need wrapper
* chore: cleanup tools to stop using rootFolder and remove unused imports
* chore: more cleanup
* refactor: Improve update-subtask, consolidate utils, update config
This commit introduces several improvements and refactorings across MCP tools, core logic, and configuration.
**Major Changes:**
1. **Refactor updateSubtaskById:**
- Switched from generateTextService to generateObjectService for structured AI responses, using a Zod schema (subtaskSchema) for validation.
- Revised prompts to have the AI generate relevant content based on user request and context (parent/sibling tasks), while explicitly preventing AI from handling timestamp/tag formatting.
- Implemented **local timestamp generation (new Date().toISOString()) and formatting** (using <info added on ...> tags) within the function *after* receiving the AI response. This ensures reliable and correctly formatted details are appended.
- Corrected logic to append only the locally formatted, AI-generated content block to the existing subtask.details.
2. **Consolidate MCP Utilities:**
- Moved/consolidated the withNormalizedProjectRoot HOF into mcp-server/src/tools/utils.js.
- Updated MCP tools (like update-subtask.js) to import withNormalizedProjectRoot from the new location.
3. **Refactor Project Initialization:**
- Deleted the redundant mcp-server/src/core/direct-functions/initialize-project-direct.js file.
- Updated mcp-server/src/core/task-master-core.js to import initializeProjectDirect from its correct location (./direct-functions/initialize-project.js).
**Other Changes:**
- Updated .taskmasterconfig fallback model to claude-3-7-sonnet-20250219.
- Clarified model cost representation in the models tool description (taskmaster.mdc and mcp-server/src/tools/models.js).
* fix: displayBanner logging when silentMode is active (#385)
* fix: improve error handling, test options, and model configuration
- Enhance error validation in parse-prd.js and update-tasks.js
- Fix bug where mcpLog was incorrectly passed as logWrapper
- Improve error messages and response formatting
- Add --skip-verification flag to E2E tests
- Update MCP server config that ships with init to match new API key structure
- Fix task force/append handling in parse-prd command
- Increase column width in update-tasks display
* chore: fixes parse prd to show loading indicator in cli.
* fix(parse-prd): suggested fix for mcpLog was incorrect. reverting to my previously working code.
* chore(init): No longer ships readme with task-master init (commented out for now). No longer looking for task-master-mcp, instead checked for task-master-ai - this should prevent the init sequence from needlessly adding another mcp server with task-master-mcp to the mpc.json which a ton of people probably ran into.
* chore: restores 3.7 sonnet as the main role.
* fix(add/remove-dependency): dependency mcp tools were failing due to hard-coded tasks path in generate task files.
* chore: removes tasks json backup that was temporarily created.
* fix(next): adjusts mcp tool response to correctly return the next task/subtask. Also adds nextSteps to the next task response.
* chore: prettier
* chore: readme typos
* fix(config): restores sonnet 3.7 as default main role.
* Version Packages
* hotfix: move production package to "dependencies" (#399)
* Version Packages
* Fix: issues with 0.13.0 not working (#402)
* Exit prerelease mode and version packages
* hotfix: move production package to "dependencies"
* Enter prerelease mode and version packages
* Enter prerelease mode and version packages
* chore: cleanup
* chore: improve pre.json and add pre-release workflow
* chore: fix package.json
* chore: cleanup
* chore: improve pre-release workflow
* chore: allow github actions to commit
* extract fileMap and conversionConfig into brand profile
* extract into brand profile
* add windsurf profile
* add remove brand rules function
* fix regex
* add rules command to add/remove rules for a specific brand
* fix post processing for roo
* allow multiples
* add cursor profile
* update test for new structure
* move rules to assets
* use assets/rules for rules files
* use standardized setupMCP function
* fix formatting
* fix formatting
* add logging
* fix escapes
* default to cursor
* allow init with certain rulesets; no more .windsurfrules
* update docs
* update log msg
* fix formatting
* keep mdc extension for cursor
* don't rewrite .mdc to .md inside the files
* fix roo init (add modes)
* fix cursor init (don't use roo transformation by default)
* use more generic function names
* update docs
* fix formatting
* update function names
* add changeset
* add rules to mcp initialize project
* register tool with mcp server
* update docs
* add integration test
* fix cursor initialization
* rule selection
* fix formatting
* fix MCP - remove yes flag
* add import
* update roo tests
* add/update tests
* remove test
* add rules command test
* update MCP responses, centralize rules profiles & helpers
* fix logging and MCP response messages
* fix formatting
* incorrect test
* fix tests
* update fileMap
* fix file extension transformations
* fix formatting
* add rules command test
* test already covered
* fix formatting
* move renaming logic into profiles
* make sure dir is deleted (DS_Store)
* add confirmation for rules removal
* add force flag for rules remove
* use force flag for test
* remove yes parameter
* fix formatting
* import brand profiles from rule-transformer.js
* update comment
* add interactive rules setup
* optimize
* only copy rules specifically listed in fileMap
* update comment
* add cline profile
* add brandDir to remove ambiguity and support Cline
* specify whether to create mcp config and filename
* add mcpConfigName value for parh
* fix formatting
* remove rules just for this repository - only include rules to be distributed
* update error message
* update "brand rules" to "rules"
* update to minor
* remove comment
* remove comments
* move to /src/utils
* optimize imports
* move rules-setup.js to /src/utils
* move rule-transformer.js to /src/utils
* move confirmation to /src/ui/confirm.js
* default to all rules
* use profile js for mcp config settings
* only run rules interactive setup if not provided via command line
* update comments
* initialize with all brands if nothing specified
* update var name
* clean up
* enumerate brands for brand rules
* update instructions
* add test to check for brand profiles
* fix quotes
* update semantics and terminology from 'brand rules' to 'rules profiles'
* fix formatting
* fix formatting
* update function name and remove copying of cursor rules, now handled by rules transformer
* update comment
* rename to mcp-config-setup.js
* use enums for rules actions
* add aggregate reporting for rules add command
* add missing log message
* use simpler path
* use base profile with modifications for each brand
* use displayName and don't select any defaults in setup
* add confirmation if removing ALL rules profiles, and add --force flag on rules remove
* Use profile-detection instead of rules-detection
* add newline at end of mcp config
* add proper formatting for mcp.json
* update rules
* update rules
* update rules
* add checks for other rules and other profile folder items before removing
* update confirmation for rules remove
* update docs
* update changeset
* fix for filepath at bottom of rule
* Update cline profile and add test; adjust other rules tests
* update changeset
* update changeset
* clarify init for all profiles if not specified
* update rule text
* revert text
* use "rule profiles" instead of "rules profiles"
* use standard tool mappings for windsurf
* add Trae support
* update changeset
* update wording
* update to 'rule profile'
* remove unneeded exports to optimize loc
* combine to /src/utils/profiles.js; add codex and claude code profiles
* rename function and add boxen
* add claude and codex integration tests
* organize tests into profiles folder
* mock fs for transformer tests
* update UI
* add cline and trae integration tests
* update test
* update function name
* update formatting
* Update change set with new profiles
* move profile integration tests to subdirectory
* properly create temp directories in /tmp folder
* fix formatting
* use taskmaster subfolder for the 2 TM rules
* update wording
* ensure subdirectory exists
* update rules from next
* update from next
* update taskmaster rule
* add details on new rules command and init
* fix mcp init
* fix MCP path to assets
* remove duplication
* remove duplication
* MCP server path fixes for rules command
* fix for CLI roo rules add/remove
* update tests
* fix formatting
* fix pattern for interactive rule profiles setup
* restore comments
* restore comments
* restore comments
* remove unused import, fix quotes
* add missing integration tests
* add VS Code profile and tests
* update docs and rules to include vscode profile
* add rules subdirectory support per-profile
* move profiles to /src
* fix formatting
* rename to remove ambiguity
* use --setup for rules interactive setup
* Fix Cursor deeplink installation with copy-paste instructions (#723)
* change roo boomerang to orchestrator; update tests that don't use modes
* fix newline
* chore: cleanup
---------
Co-authored-by: Eyal Toledano <eyal@microangel.so>
Co-authored-by: Yuval <yuvalbl@users.noreply.github.com>
Co-authored-by: Marijn van der Werf <marijn.vanderwerf@gmail.com>
Co-authored-by: Eyal Toledano <eutait@gmail.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Add comprehensive AI-powered research command with intelligent context gathering and interactive follow-ups.
The new `research` command provides AI-powered research capabilities that automatically gather relevant project context to answer your questions. The command intelligently selects context from multiple sources and supports interactive follow-up questions in CLI mode.
**Key Features:**
- **Intelligent Task Discovery**: Automatically finds relevant tasks and subtasks using fuzzy search based on your query keywords, supplementing any explicitly provided task IDs
- **Multi-Source Context**: Gathers context from tasks, files, project structure, and custom text to provide comprehensive answers
- **Interactive Follow-ups**: CLI users can ask follow-up questions that build on the conversation history while allowing fresh context discovery for each question
- **Flexible Detail Levels**: Choose from low (concise), medium (balanced), or high (comprehensive) response detail levels
- **Enhanced Display**: Syntax-highlighted code blocks and structured output with clear visual separation
**Usage Examples:**
```bash
# Basic research with auto-discovered context
task-master research "How should I implement user authentication?"
# Research with specific task context
task-master research "What's the best approach for this?" --id=15,23.2
# Research with file context and project tree
task-master research "How does the current auth system work?" --files=src/auth.js,config/auth.json --tree
# Research with custom context and low detail
task-master research "Quick implementation steps?" --context="Using JWT tokens" --detail=low
```
**Context Sources:**
- **Tasks**: Automatically discovers relevant tasks/subtasks via fuzzy search, plus any explicitly specified via `--id`
- **Files**: Include specific files via `--files` for code-aware responses
- **Project Tree**: Add `--tree` to include project structure overview
- **Custom Context**: Provide additional context via `--context` for domain-specific information
**Interactive Features (CLI only):**
- Follow-up questions that maintain conversation history
- Fresh fuzzy search for each follow-up to discover newly relevant tasks
- Cumulative context building across the conversation
- Clean visual separation between exchanges
- **Save to Tasks**: Save entire research conversations (including follow-ups) directly to task or subtask details with timestamps
- **Clean Menu Interface**: Streamlined inquirer-based menu for follow-up actions without redundant UI elements
**Save Functionality:**
The research command now supports saving complete conversation threads to tasks or subtasks:
- Save research results and follow-up conversations to any task (e.g., "15") or subtask (e.g., "15.2")
- Automatic timestamping and formatting of conversation history
- Validation of task/subtask existence before saving
- Appends to existing task details without overwriting content
- Supports both CLI interactive mode and MCP programmatic access via `--save-to` flag
**Enhanced CLI Options:**
```bash
# Auto-save research results to a task
task-master research "Implementation approach?" --save-to=15
# Combine auto-save with context gathering
task-master research "How to optimize this?" --id=23 --save-to=23.1
```
**MCP Integration:**
-`saveTo` parameter for automatic saving to specified task/subtask ID
- Structured response format with telemetry data
- Silent operation mode for programmatic usage
- Full feature parity with CLI except interactive follow-ups
The research command integrates with the existing AI service layer and supports all configured AI providers. Both CLI and MCP interfaces provide comprehensive research capabilities with intelligent context gathering and flexible output options.
Prevent CLAUDE.md overwrite by using Claude Code's import feature
- Task Master now creates its instructions in `.taskmaster/CLAUDE.md` instead of overwriting the user's `CLAUDE.md`
- Adds an import section to the user's CLAUDE.md that references the Task Master instructions
- Preserves existing user content in CLAUDE.md files
- Provides clean uninstall that only removes Task Master's additions
**Breaking Change**: Task Master instructions for Claude Code are now stored in `.taskmaster/CLAUDE.md` and imported into the main CLAUDE.md file. Users who previously had Task Master content directly in their CLAUDE.md will need to run `task-master rules remove claude` followed by `task-master rules add claude` to migrate to the new structure.
- **Fixed moving tasks to become subtasks of empty parents**: When moving a task to become a subtask of a parent that had no existing subtasks (e.g., task 89 → task 98.1), the operation would fail with validation errors.
- **Fixed moving subtasks between parents**: Subtasks can now be properly moved between different parent tasks, including to parents that previously had no subtasks.
- **Improved comma-separated batch moves**: Multiple tasks can now be moved simultaneously using comma-separated IDs (e.g., "88,90" → "92,93") with proper error handling and atomic operations.
These fixes enables proper task hierarchy reorganization for corner cases that were previously broken.
Fix: show command no longer requires complexity report file to exist
The `tm show` command was incorrectly requiring the complexity report file to exist even when not needed. Now it only validates the complexity report path when a custom report file is explicitly provided via the -r/--report option.
Enhance update-task with --append flag for timestamped task updates
Adds the `--append` flag to `update-task` command, enabling it to behave like `update-subtask` with timestamped information appending. This provides more flexible task updating options:
-`task-master update-task --id=5 --append --prompt="Progress update"` - Append timestamped info to task details
**Full MCP Integration:**
- MCP tool `update_task` now supports `append` parameter
- Seamless integration with Cursor and other MCP clients
- Consistent behavior between CLI and MCP interfaces
Instead of requiring separate subtask creation for progress tracking, you can now append timestamped information directly to parent tasks while preserving the option for comprehensive task updates.
Add --tag flag support to core commands for multi-context task management. Commands like parse-prd, analyze-complexity, and others now support targeting specific task lists, enabling rapid prototyping and parallel development workflows.
Key features:
- parse-prd --tag=feature-name: Parse PRDs into separate task contexts on the fly
Introduces Tagged Lists: AI Multi-Context Task Management System
This major feature release introduces Tagged Lists, a comprehensive system that transforms Taskmaster into a multi-context task management powerhouse. You can now organize tasks into completely isolated contexts, enabling parallel (agentic) development workflows, team collaboration, and project experimentation without conflicts.
**🏷️ Tagged Task Lists Architecture:**
The new tagged system fundamentally improves how tasks are organized:
-`task-master set-status --tag=hotfix --id=5 --status=done` - Update tasks in specific contexts
-`task-master expand --tag=research --id=3` - Break down tasks within tag contexts
This way you or your agent can store out of context tasks into the appropriate tags for later, allowing you to maintain a groomed and scoped master list. Focus on value, not chores.
**📊 Enhanced Workflow Features:**
**Smart Context Switching:**
-`use-tag` command shows immediate next task after switching
- Automatic tag creation when targeting non-existent tags
- Current tag persistence across terminal sessions
- Tagged format with complete isolation between contexts
- Rich metadata per tag (creation date, description, update tracking)
- Automatic metadata enhancement for existing tags
- Clean separation of tag data and internal state
**Performance Optimizations:**
- Dynamic task counting without stored counters
- Efficient tag resolution and caching
- Minimal file I/O with smart data loading
- Responsive table layouts adapting to terminal width
**Error Handling:**
- Comprehensive validation for tag names (alphanumeric, hyphens, underscores)
- Reserved name protection (master, main, default)
- Graceful handling of missing tags and corrupted data
- Detailed error messages with suggested corrections
This release establishes the foundation for advanced multi-context workflows while maintaining the simplicity and power that makes Task Master effective for individual developers.
Research Save-to-File Feature & Critical MCP Tag Corruption Fix
**🔬 New Research Save-to-File Functionality:**
Added comprehensive save-to-file capability to the research command, enabling users to preserve research sessions for future reference and documentation.
**CLI Integration:**
- New `--save-file` flag for `task-master research` command
- Consistent with existing `--save` and `--save-to` flags for intuitive usage
- Interactive "Save to file" option in follow-up questions menu
**MCP Integration:**
- New `saveToFile` boolean parameter for the `research` MCP tool
- Enables programmatic research saving for AI agents and integrated tools
No longer automatically creates individual task files as they are not used by the applicatoin. You can still generate them anytime using the `generate` command.
Enhanced get-task/show command to support comma-separated task IDs for efficient batch operations
**New Features:**
- **Multiple Task Retrieval**: Pass comma-separated IDs to get/show multiple tasks at once (e.g., `task-master show 1,3,5` or MCP `get_task` with `id: "1,3,5"`)
- **Smart Display Logic**: Single ID shows detailed view, multiple IDs show compact summary table with interactive options
- **Batch Action Menu**: Interactive menu for multiple tasks with copy-paste ready commands for common operations (mark as done/in-progress, expand all, view dependencies, etc.)
- **MCP Array Response**: MCP tool returns structured array of task objects for efficient AI agent context gathering
**Benefits:**
- **Faster Context Gathering**: AI agents can collect multiple tasks/subtasks in one call instead of iterating
- **Better UX**: Responsive layout adapts to terminal width, maintains consistency with existing UI patterns
- **API Efficiency**: RESTful array responses in MCP format enable more sophisticated integrations
This enhancement maintains full backward compatibility while significantly improving efficiency for both human users and AI agents working with multiple tasks.
@@ -33,6 +33,7 @@ All your standard command executions should operate on the user's current task c
For new projects or when users are getting started, operate within the `master` tag context:
- Start new projects by running `initialize_project` tool / `task-master init` or `parse_prd` / `task-master parse-prd --input='<prd-file.txt>'` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to generate initial tasks.json with tagged structure
- Configure rule sets during initialization with `--rules` flag (e.g., `task-master init --rules cursor,windsurf`) or manage them later with `task-master rules add/remove` commands
- Begin coding sessions with `get_tasks` / `task-master list` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to see current tasks, status, and IDs
- Determine the next task to work on using `next_task` / `task-master next` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc))
- Analyze task complexity with `analyze_project_complexity` / `task-master analyze-complexity --research` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) before breaking down tasks
@@ -152,7 +153,7 @@ When users initialize Taskmaster on existing projects:
5. **Master List Curation**: Keep only the most valuable initiatives in master
The parse-prd's `--append` flag enables the user to parse multple PRDs within tags or across tags. PRDs should be focused and the number of tasks they are parsed into should be strategically chosen relative to the PRD's complexity and level of detail.
The parse-prd's `--append` flag enables the user to parse multiple PRDs within tags or across tags. PRDs should be focused and the number of tasks they are parsed into should be strategically chosen relative to the PRD's complexity and level of detail.
### Workflow Transition Examples
@@ -294,6 +295,17 @@ Taskmaster configuration is managed through two main mechanisms:
**If AI commands FAIL in MCP** verify that the API key for the selected provider is present in the `env` section of `.cursor/mcp.json`.
**If AI commands FAIL in CLI** verify that the API key for the selected provider is present in the `.env` file in the root of the project.
## Rules Management
Taskmaster supports multiple AI coding assistant rule sets that can be configured during project initialization or managed afterward:
@@ -26,6 +26,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
* `--name <name>`: `Set the name for your project in Taskmaster's configuration.`
* `--description <text>`: `Provide a brief description for your project.`
* `--version <version>`: `Set the initial version for your project, e.g., '0.1.0'.`
* `--no-git`: `Skip initializing a Git repository entirely.`
* `-y, --yes`: `Initialize Taskmaster quickly using default settings without interactive prompts.`
* **Usage:** Run this once at the beginning of a new project.
* **MCP Variant Description:** `Set up the basic Taskmaster file structure and configuration in the current directory for a new project by running the 'task-master init' command.`
@@ -36,6 +37,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
* `skipInstall`: `Skip installing dependencies. Default is false.` (CLI: `--skip-install`)
* `addAliases`: `Add shell aliases tm and taskmaster. Default is false.` (CLI: `--aliases`)
* `noGit`: `Skip initializing a Git repository entirely. Default is false.` (CLI: `--no-git`)
* `yes`: `Skip prompts and use defaults/provided arguments. Default is false.` (CLI: `-y, --yes`)
* **Usage:** Run this once at the beginning of a new project, typically via an integrated tool like Cursor. Operates on the current working directory of the MCP server.
* **Important:** Once complete, you *MUST* parse a prd in order to generate tasks. There will be no tasks files until then. The next step after initializing should be to create a PRD using the example PRD in .taskmaster/templates/example_prd.txt.
@@ -270,7 +272,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
* **Description:** `Remove all subtasks from one or more specified Taskmaster parent tasks.`
* **Key Parameters/Options:**
* `id`: `The ID(s) of the Taskmaster parent task(s) whose subtasks you want to remove, e.g., '15' or '16,18'. Required unless using `all`.) (CLI: `-i, --id <ids>`)
* `id`: `The ID(s) of the Taskmaster parent task(s) whose subtasks you want to remove, e.g., '15' or '16,18'. Required unless using 'all'.` (CLI: `-i, --id <ids>`)
* `all`: `Tell Taskmaster to remove subtasks from all parent tasks.` (CLI: `--all`)
* `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
* `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
- Add TTS-specific error handling for cases where TTS is unavailable
- Create fallback behavior when TTS fails (silent failure or text output)
- Support for reading task titles, descriptions, and status updates aloud
- Add option to read entire task lists or individual task details
- Implement TTS for command confirmations and error messages
- Create TTS output formatting to make spoken text more natural (removing markdown, formatting numbers/dates appropriately)
- Add configuration option to enable/disable TTS globally
# Test Strategy:
Test TTS functionality across different operating systems (Windows, macOS, Linux). Verify that the --tts flag works with all major commands. Test voice configuration options and ensure audio output settings are properly applied. Test error handling when TTS services are unavailable. Verify that text formatting for speech is natural and understandable. Test with various task content types including special characters, code snippets, and long descriptions. Ensure TTS can be disabled and enabled through configuration.
@@ -47,8 +47,9 @@ At least one (1) of the following is required:
- Perplexity API key (for research model)
- xAI API Key (for research or main model)
- OpenRouter API Key (for research or main model)
- Claude Code (no API key required - requires Claude Code CLI)
Using the research model is optional but highly recommended. You will need at least ONE API key. Adding all API keys enables you to seamlessly switch between model providers at will.
Using the research model is optional but highly recommended. You will need at least ONE API key (unless using Claude Code). Adding all API keys enables you to seamlessly switch between model providers at will.
## Quick Start
@@ -93,6 +94,8 @@ MCP (Model Control Protocol) lets you run Task Master directly from your editor.
> 🔑 Replace `YOUR_…_KEY_HERE` with your real API keys. You can remove keys you don't use.
> **Note**: If you see `0 tools enabled` in the MCP settings, try removing the `--package=task-master-ai` flag from `args`.
###### VSCode (`servers` + `type`)
```json
@@ -131,7 +134,12 @@ In your editor's AI chat pane, say:
Change the main, research and fallback models to <model_name>, <model_name> and <model_name> respectively.
```
[Table of available models](docs/models.md)
For example, to use Claude Code (no API key required):
```txt
Change the main model to claude-code/sonnet
```
[Table of available models](docs/models.md) | [Claude Code setup](docs/examples/claude-code-usage.md)
#### 4. Initialize Task Master
@@ -189,6 +197,9 @@ task-master init
# If installed locally
npx task-master init
# Initialize project with specific rules
task-master init --rules cursor,windsurf,vscode
```
This will prompt you for project details and set up a new project with the necessary files and structure.
@@ -216,8 +227,21 @@ task-master research "What are the latest best practices for JWT authentication?
# Generate task files
task-master generate
# Add rules after initialization
task-master rules add windsurf,roo,vscode
```
## Claude Code Support
Task Master now supports Claude models through the Claude Code CLI, which requires no API key:
- **Models**: `claude-code/opus` and `claude-code/sonnet`
- **Requirements**: Claude Code CLI installed
- **Benefits**: No API key needed, uses your local Claude instance
[Learn more about Claude Code setup](docs/examples/claude-code-usage.md)
// "experimentalDecorators": true, /* Enable experimental support for legacy experimental decorators. */
// "emitDecoratorMetadata": true, /* Emit design-type metadata for decorated declarations in source files. */
// "jsxFactory": "", /* Specify the JSX factory function used when targeting React JSX emit, e.g. 'React.createElement' or 'h'. */
// "jsxFragmentFactory": "", /* Specify the JSX Fragment reference used for fragments when targeting React JSX emit e.g. 'React.Fragment' or 'Fragment'. */
// "jsxImportSource": "", /* Specify module specifier used to import the JSX factory functions when using 'jsx: react-jsx*'. */
// "reactNamespace": "", /* Specify the object invoked for 'createElement'. This only applies when targeting 'react' JSX emit. */
// "noLib": true, /* Disable including any library files, including the default lib.d.ts. */
// "useDefineForClassFields": true, /* Emit ECMAScript-standard-compliant class fields. */
// "moduleDetection": "auto", /* Control what method is used to detect module-format JS files. */
// "moduleSuffixes": [], /* List of file name suffixes to search when resolving a module. */
// "allowImportingTsExtensions": true, /* Allow imports to include TypeScript file extensions. Requires '--moduleResolution bundler' and either '--noEmit' or '--emitDeclarationOnly' to be set. */
// "rewriteRelativeImportExtensions": true, /* Rewrite '.ts', '.tsx', '.mts', and '.cts' file extensions in relative import paths to their JavaScript equivalent in output files. */
// "resolvePackageJsonExports": true, /* Use the package.json 'exports' field when resolving package imports. */
// "resolvePackageJsonImports": true, /* Use the package.json 'imports' field when resolving imports. */
// "customConditions": [], /* Conditions to set in addition to the resolver-specific defaults when resolving imports. */
// "noUncheckedSideEffectImports": true, /* Check side effect imports. */
// "maxNodeModuleJsDepth": 1, /* Specify the maximum folder depth used for checking JavaScript files from 'node_modules'. Only applicable with 'allowJs'. */
/*Emit*/
// "declaration": true, /* Generate .d.ts files from TypeScript and JavaScript files in your project. */
// "declarationMap": true, /* Create sourcemaps for d.ts files. */
// "emitDeclarationOnly": true, /* Only output d.ts files and not JavaScript files. */
// "inlineSourceMap": true, /* Include sourcemap files inside the emitted JavaScript. */
// "noEmit": true, /* Disable emitting files from a compilation. */
// "outFile": "./", /* Specify a file that bundles all outputs into one JavaScript file. If 'declaration' is true, also designates a file that bundles all .d.ts output. */
// "outDir": "./", /* Specify an output folder for all emitted files. */
// "declarationDir": "./", /* Specify the output directory for generated declaration files. */
/*InteropConstraints*/
// "isolatedModules": true, /* Ensure that each file can be safely transpiled without relying on other imports. */
// "verbatimModuleSyntax": true, /* Do not transform or elide any imports or exports not marked as type-only, ensuring they are written in the output file's format based on the 'module' setting. */
// "isolatedDeclarations": true, /* Require sufficient annotation on exports so other tools can trivially generate declaration files. */
// "erasableSyntaxOnly": true, /* Do not allow runtime constructs that are not part of ECMAScript. */
// "allowSyntheticDefaultImports": true, /* Allow 'import x from y' when a module doesn't have a default export. */
Run '/project:tm/validate-dependencies' to verify fixes
```
## Safety
- Preview mode available
- Rollback capability
- Change logging
- No data loss
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.