v.0.22.0

Minor Changes

• #1043 dc44ed9 Thanks @Crunchyman-ralph! - Prompt to generate a complexity report when it is missing

• #1032 4423119 Thanks @Crunchyman-ralph! - Add comprehensive Kiro IDE integration with autonomous task management hooks

  • Kiro Profile: Added full support for Kiro IDE with automatic installation of 7 Taskmaster agent hooks
  • Hook-Driven Workflow: Introduced natural language automation hooks that eliminate manual task status updates
  • Automatic Hook Installation: Hooks are now automatically copied to .kiro/hooks/ when running task-master rules add kiro
  • Language-Agnostic Support: All hooks support multiple programming languages (JS, Python, Go, Rust, Java, etc.)
  • Frontmatter Transformation: Kiro rules use simplified inclusion: always format instead of Cursor's complex frontmatter
  • Special Rule: Added taskmaster_hooks_workflow.md that guides AI assistants to prefer hook-driven completion

  Key hooks included:

  • Task Dependency Auto-Progression: Automatically starts tasks when dependencies complete
  • Code Change Task Tracker: Updates task progress as you save files
  • Test Success Task Completer: Marks tasks done when tests pass
  • Daily Standup Assistant: Provides personalized task status summaries
  • PR Readiness Checker: Validates task completion before creating pull requests
  • Complexity Analyzer: Auto-expands complex tasks into manageable subtasks
  • Git Commit Task Linker: Links commits to tasks for better traceability

  This creates a truly autonomous development workflow where task management happens naturally as you code!

Patch Changes

• #1033 7b90568 Thanks @ben-vargas! - Fix compatibility with @google/gemini-cli-core v0.1.12+ by updating ai-sdk-provider-gemini-cli to v0.1.1.

• #1038 77cc5e4 Thanks @Crunchyman-ralph! - Fix 'expand --all' and 'show' commands to correctly handle tag contexts for complexity reports and task display.

• #1025 8781794 Thanks @joedanz! - Clean up remaining automatic task file generation calls

• #1035 fb7d588 Thanks @Crunchyman-ralph! - Fix max_tokens limits for OpenRouter and Groq models

  • Add special handling in config-manager.js for custom OpenRouter models to use a conservative default of 32,768 max_tokens
  • Update qwen/qwen-turbo model max_tokens from 1,000,000 to 32,768 to match OpenRouter's actual limits
  • Fix moonshotai/kimi-k2-instruct max_tokens to 16,384 to match Groq's actual limit (fixes #1028)
  • This prevents "maximum context length exceeded" errors when using OpenRouter models not in our supported models list

• #1027 6ae66b2 Thanks @andreswebs! - Fix VSCode profile generation to use correct rule file names (using .instructions.md extension instead of .md) and front-matter properties (removing the unsupported alwaysApply property from instructions files' front-matter).

v0.22.0 RC.0

Minor Changes

• #1032 4423119 Thanks @Crunchyman-ralph! - Add comprehensive Kiro IDE integration with autonomous task management hooks

  • Kiro Profile: Added full support for Kiro IDE with automatic installation of 7 Taskmaster agent hooks
  • Hook-Driven Workflow: Introduced natural language automation hooks that eliminate manual task status updates
  • Automatic Hook Installation: Hooks are now automatically copied to .kiro/hooks/ when running task-master rules add kiro
  • Language-Agnostic Support: All hooks support multiple programming languages (JS, Python, Go, Rust, Java, etc.)
  • Frontmatter Transformation: Kiro rules use simplified inclusion: always format instead of Cursor's complex frontmatter
  • Special Rule: Added taskmaster_hooks_workflow.md that guides AI assistants to prefer hook-driven completion

Key hooks included:

-   Task Dependency Auto-Progression: Automatically starts tasks when dependencies complete
-   Code Change Task Tracker: Updates task progress as you save files
-   Test Success Task Completer: Marks tasks done when tests pass
-   Daily Standup Assistant: Provides personalized task status summaries
-   PR Readiness Checker: Validates task completion before creating pull requests
-   Complexity Analyzer: Auto-expands complex tasks into manageable subtasks
-   Git Commit Task Linker: Links commits to tasks for better traceability

This creates a truly autonomous development workflow where task management happens naturally as you code!

Patch Changes

• #1033 7b90568 Thanks @ben-vargas! - Fix compatibility with @google/gemini-cli-core v0.1.12+ by updating ai-sdk-provider-gemini-cli to v0.1.1.

• #1038 77cc5e4 Thanks @Crunchyman-ralph! - Fix 'expand --all' and 'show' commands to correctly handle tag contexts for complexity reports and task display.

• #1025 8781794 Thanks @joedanz! - Clean up remaining automatic task file generation calls

• #1035 fb7d588 Thanks @Crunchyman-ralph! - Fix max_tokens limits for OpenRouter and Groq models

  • Add special handling in config-manager.js for custom OpenRouter models to use a conservative default of 32,768 max_tokens
  • Update qwen/qwen-turbo model max_tokens from 1,000,000 to 32,768 to match OpenRouter's actual limits
  • Fix moonshotai/kimi-k2-instruct max_tokens to 16,384 to match Groq's actual limit (fixes #1028)
  • This prevents "maximum context length exceeded" errors when using OpenRouter models not in our supported models list

• #1027 6ae66b2 Thanks @andreswebs! - Fix VSCode profile generation to use correct rule file names (using .instructions.md extension instead of .md) and front-matter properties (removing the unsupported alwaysApply property from instructions files' front-matter).

v0.21.0

Minor Changes

• #1001 75a36ea Thanks @Crunchyman-ralph! - Add Kiro editor rule profile support

  • Add support for Kiro IDE with custom rule files and MCP configuration
  • Generate rule files in .kiro/steering/ directory with markdown format
  • Include MCP server configuration with enhanced file inclusion patterns

• #1011 3eb050a Thanks @Crunchyman-ralph! - Created a comprehensive documentation site for Task Master AI. Visit https://docs.task-master.dev to explore guides, API references, and examples.

• #978 fedfd6a Thanks @ben-vargas! - Complete Groq provider integration and add MoonshotAI Kimi K2 model support

  • Fixed Groq provider registration
  • Added Groq API key validation
  • Added GROQ_API_KEY to .env.example
  • Added moonshotai/kimi-k2-instruct model with $1/$3 per 1M token pricing and 16k max output

• #974 5b0eda0 Thanks @joedanz! - feat: Add Zed editor rule profile with agent rules and MCP config

  • Resolves #637

• #973 6d05e86 Thanks @joedanz! - Add Amp rule profile with AGENT.md and MCP config

• #1011 3eb050a Thanks @Crunchyman-ralph! - Improve project root detection

  • No longer creates an infinite loop when unable to detect your code workspace

• #970 b87499b Thanks @joedanz! - Add OpenCode profile with AGENTS.md and MCP config

  • Resolves #965

Patch Changes

• #1011 3eb050a Thanks @Crunchyman-ralph! - Make task-master update more reliable with AI responses

  The update command now handles AI responses more robustly. If the AI forgets to include certain task fields, the command will automatically fill in the missing data from your original tasks instead of failing. This means smoother bulk task updates without losing important information like IDs, dependencies, or completed subtasks.

• #1011 3eb050a Thanks @Crunchyman-ralph! - Fix subtask dependency validation when expanding tasks

  When using task-master expand to break down tasks into subtasks, dependencies between subtasks are now properly validated. Previously, subtasks with dependencies would fail validation. Now subtasks can correctly depend on their siblings within the same parent task.

• #949 f662654 Thanks @ben-vargas! - 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.

• #943 f98df5c Thanks @mm-parthy! - Implement Boundary-First Tag Resolution to ensure consistent and deterministic tag handling across CLI and MCP, resolving potential race conditions.

• #1011 3eb050a Thanks @Crunchyman-ralph! - Fix task-master lang --setup breaking when no language is defined, now defaults to English

• #979 ab2e946 Thanks @ben-vargas! - 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.

• #971 5544222 Thanks @joedanz! - Update VS Code profile with MCP config transformation

• #1002 6d0654c Thanks @Crunchyman-ralph! - Fix MCP server error when retrieving tools and resources

• #980 cc4fe20 Thanks @joedanz! - Add MCP configuration support to Claude Code rules

• #968 7b4803a Thanks @Crunchyman-ralph! - Fixed the comprehensive taskmaster system integration via custom slash commands with proper syntax

  • Provide claude clode with a complete set of of commands that can trigger task master events directly within Claude Code

• #995 b78de8d Thanks @joedanz! - Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.

• #972 1c7badf Thanks @joedanz! - Add missing API keys to .env.example and README.md

v0.20.0

Minor Changes

• #950 699e9ee Thanks @ben-vargas! - Add support for xAI Grok 4 model

  • Add grok-4 model to xAI provider with $3/$15 per 1M token pricing
  • Enable main, fallback, and research roles for grok-4
  • Max tokens set to 131,072 (matching other xAI models)

• #946 5f009a5 Thanks @Crunchyman-ralph! - Add stricter validation and clearer feedback for task priority when adding new tasks

  • if a task priority is invalid, it will default to medium
  • made taks priority case-insensitive, essentially making HIGH and high the same value

• #863 b530657 Thanks @OrenMe! - Add support for MCP Sampling as AI provider, requires no API key, uses the client LLM provider

• #930 98d1c97 Thanks @OmarElKadri! - Added Groq provider support

Patch Changes

• #958 6c88a4a Thanks @Crunchyman-ralph! - Recover from @anthropic-ai/claude-code JSON truncation bug that caused Task Master to crash when handling large (>8 kB) structured responses. The CLI/SDK still truncates, but Task Master now detects the error, preserves buffered text, and returns a usable response instead of throwing.

• #958 3334e40 Thanks @Crunchyman-ralph! - Updating dependency ai-sdk-provider-gemini-cli to 0.0.4 to address breaking change Google made to Gemini CLI and add better 'api-key' in addition to 'gemini-api-key' AI-SDK compatibility.

• #853 95c299d Thanks @joedanz! - Unify and streamline profile system architecture for improved maintainability

v0.20.0-rc.0

Minor Changes

• #950 699e9ee Thanks @ben-vargas! - Add support for xAI Grok 4 model

  • Add grok-4 model to xAI provider with $3/$15 per 1M token pricing
  • Enable main, fallback, and research roles for grok-4
  • Max tokens set to 131,072 (matching other xAI models)

• #946 5f009a5 Thanks @Crunchyman-ralph! - Add stricter validation and clearer feedback for task priority when adding new tasks

  • if a task priority is invalid, it will default to medium
  • made taks priority case-insensitive, essentially making HIGH and high the same value

• #863 b530657 Thanks @OrenMe! - Add support for MCP Sampling as AI provider, requires no API key, uses the client LLM provider

• #930 98d1c97 Thanks @OmarElKadri! - Added Groq provider support

Patch Changes

• #916 6c88a4a Thanks @Crunchyman-ralph! - Recover from @anthropic-ai/claude-code JSON truncation bug that caused Task Master to crash when handling large (>8 kB) structured responses. The CLI/SDK still truncates, but Task Master now detects the error, preserves buffered text, and returns a usable response instead of throwing.

• #916 3334e40 Thanks @Crunchyman-ralph! - Updating dependency ai-sdk-provider-gemini-cli to 0.0.4 to address breaking change Google made to Gemini CLI and add better 'api-key' in addition to 'gemini-api-key' AI-SDK compatibility.

• #853 95c299d Thanks @joedanz! - Unify and streamline profile system architecture for improved maintainability

v0.19.0

Minor Changes

• #897 dd96f51 Thanks @ben-vargas! - Adds support for gemini-cli as a provider, enabling free or subscription use through Google Accounts and paid Gemini Cloud Assist (GCA) subscriptions.

• #884 5eafc5e Thanks @geoh! - Added option for the AI to determine the number of tasks required based entirely on complexity

• #872 f7fbdd6 Thanks @geoh! - Add advanced settings for Claude Code AI Provider

• #870 6fd5e23 Thanks @nishedcob! - Include additional Anthropic models running on Bedrock in what is supported

• #510 c99df64 Thanks @shenysun! - Add support for custom response language

Patch Changes

• #892 56a415e Thanks @joedanz! - Ensure projectRoot is a string (potential WSL fix)

• #856 43e0025 Thanks @mm-parthy! - Fix bulk update tag corruption in tagged task lists

• #857 598e687 Thanks @mm-parthy! - Fix expand-task to use tag-specific complexity reports

  The expand-task 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.

• #855 e4456b1 Thanks @joedanz! - Fix .gitignore missing trailing newline during project initialization

• #846 59a4ec9 Thanks @joedanz! - Default to Cursor profile for MCP init when no rules specified

• #852 f38abd6 Thanks @hrmshandy! - fixes a critical issue where subtask generation fails on gemini-2.5-pro unless explicitly prompted to return 'details' field as a string not an object

• #908 24e9206 Thanks @joedanz! - Fix rules command to use reliable project root detection like other commands

v0.18.0

Minor Changes

• #840 b40139c Thanks @Crunchyman-ralph! - Can now configure baseURL of provider with <PROVIDER>_BASE_URL

  • For example:
    • OPENAI_BASE_URL

• #840 b40139c Thanks @Crunchyman-ralph! - Added comprehensive rule profile management:

  New Profile Support: Added comprehensive IDE profile support with eight specialized profiles: Claude Code, Cline, Codex, Cursor, Roo, Trae, VS Code, and Windsurf. Each profile is optimized for its respective IDE with appropriate mappings and configuration.
  Initialization: You can now specify which rule profiles to include at project initialization using --rules <profiles> or -r <profiles> (e.g., task-master init -r cursor,roo). Only the selected profiles and configuration are included.
  Add/Remove Commands: task-master rules add <profiles> and task-master rules remove <profiles> let you manage specific rule profiles and MCP config after initialization, supporting multiple profiles at once.
  Interactive Setup: task-master rules setup launches an interactive prompt to select which rule profiles to add to your project. This does not re-initialize your project or affect shell aliases; it only manages rules.
  Selective Removal: Rules removal intelligently preserves existing non-Task Master rules and files and only removes Task Master-specific rules. Profile directories are only removed when completely empty and all conditions are met (no existing rules, no other files/folders, MCP config completely removed).
  Safety Features: Confirmation messages clearly explain that only Task Master-specific rules and MCP configurations will be removed, while preserving existing custom rules and other files.
  Robust Validation: Includes comprehensive checks for array types in MCP config processing and error handling throughout the rules management system.

  This enables more flexible, rule-specific project setups with intelligent cleanup that preserves user customizations while safely managing Task Master components.

  • Resolves #338

• #840 b40139c Thanks @Crunchyman-ralph! - Make task-master more compatible with the "o" family models of OpenAI

  Now works well with:

  • o3
  • o3-mini
  • etc.

• #840 b40139c Thanks @Crunchyman-ralph! - Add better support for python projects by adding pyproject.toml as a projectRoot marker

• #840 b40139c Thanks @Crunchyman-ralph! - - Git Worktree Detection:

  • Now properly skips Git initialization when inside existing Git worktree
  • Prevents accidental nested repository creation
  • Flag System Overhaul:
    • --git/--no-git controls repository initialization
    • --aliases/--no-aliases consistently manages shell alias creation
    • --git-tasks/--no-git-tasks controls whether task files are stored in Git
    • --dry-run accurately previews all initialization behaviors
  • GitTasks Functionality:
    • New --git-tasks flag includes task files in Git (comments them out in .gitignore)
    • New --no-git-tasks flag excludes task files from Git (default behavior)
    • Supports both CLI and MCP interfaces with proper parameter passing

  Implementation Details:

  • Added explicit Git worktree detection before initialization
  • Refactored flag processing to ensure consistent behavior
  • Fixes #734

• #840 b40139c Thanks @Crunchyman-ralph! - Add Claude Code provider support

  Introduces a new provider that enables using Claude models (Opus and Sonnet) through the Claude Code CLI without requiring an API key.

  Key features:

  • New claude-code provider with support for opus and sonnet models
  • No API key required - uses local Claude Code CLI installation
  • Optional dependency - won't affect users who don't need Claude Code
  • Lazy loading ensures the provider only loads when requested
  • Full integration with existing Task Master commands and workflows
  • Comprehensive test coverage for reliability
  • New --claude-code flag for the models command

  Users can now configure Claude Code models with:
  task-master models --set-main sonnet --claude-code
  task-master models --set-research opus --claude-code

  The @anthropic-ai/claude-code package is optional and won't be installed unless explicitly needed.

Patch Changes

• #840 b40139c Thanks @Crunchyman-ralph! - Fix expand command preserving tagged task structure and preventing data corruption

  • Enhance E2E tests with comprehensive tag-aware expand testing to verify tag corruption fix
  • Add new test section for feature-expand tag creation and testing during expand operations
  • Verify tag preservation during expand, force expand, and expand --all operations
  • Test that master tag remains intact while feature-expand tag receives subtasks correctly
  • Fix file path references to use correct .taskmaster/config.json and .taskmaster/tasks/tasks.json locations
  • All tag corruption verification tests pass successfully, confirming the expand command tag corruption bug fix works as expected

• #840 b40139c Thanks @Crunchyman-ralph! - Fix Cursor deeplink installation by providing copy-paste instructions for GitHub compatibility

• #840 b40139c Thanks @Crunchyman-ralph! - Call rules interactive setup during init

• #840 b40139c Thanks @Crunchyman-ralph! - Update o3 model price

• #840 b40139c Thanks @Crunchyman-ralph! - Improves Amazon Bedrock support

• #840 b40139c Thanks @Crunchyman-ralph! - Fix issues with task creation/update where subtasks are being created like id: <parent_task>. instead if just id:

• #840 b40139c Thanks @Crunchyman-ralph! - Fixes issue with expand CLI command "Complexity report not found"

  • Closes #735
  • Closes #728

• #840 b40139c Thanks @Crunchyman-ralph! - Store tasks in Git by default

• #840 b40139c Thanks @Crunchyman-ralph! - Improve provider validation system with clean constants structure

  • Fixed "Invalid provider hint" errors: Resolved validation failures for Azure, Vertex, and Bedrock providers
  • Improved search UX: Integrated search for better model discovery with real-time filtering
  • Better organization: Moved custom provider options to bottom of model selection with clear section separators

  This change ensures all custom providers (Azure, Vertex, Bedrock, OpenRouter, Ollama) work correctly in task-master models --setup

• #840 b40139c Thanks @Crunchyman-ralph! - Fix weird task-master init bug when using in certain environment...

v0.18.0-rc.0

Minor Changes

• #830 e9d1bc2 Thanks @Crunchyman-ralph! - Can now configure baseURL of provider with <PROVIDER>_BASE_URL

  • For example:
    • OPENAI_BASE_URL

• #460 a09a2d0 Thanks @joedanz! - Added comprehensive rule profile management:

  New Profile Support: Added comprehensive IDE profile support with eight specialized profiles: Claude Code, Cline, Codex, Cursor, Roo, Trae, VS Code, and Windsurf. Each profile is optimized for its respective IDE with appropriate mappings and configuration.
  Initialization: You can now specify which rule profiles to include at project initialization using --rules <profiles> or -r <profiles> (e.g., task-master init -r cursor,roo). Only the selected profiles and configuration are included.
  Add/Remove Commands: task-master rules add <profiles> and task-master rules remove <profiles> let you manage specific rule profiles and MCP config after initialization, supporting multiple profiles at once.
  Interactive Setup: task-master rules setup launches an interactive prompt to select which rule profiles to add to your project. This does not re-initialize your project or affect shell aliases; it only manages rules.
  Selective Removal: Rules removal intelligently preserves existing non-Task Master rules and files and only removes Task Master-specific rules. Profile directories are only removed when completely empty and all conditions are met (no existing rules, no other files/folders, MCP config completely removed).
  Safety Features: Confirmation messages clearly explain that only Task Master-specific rules and MCP configurations will be removed, while preserving existing custom rules and other files.
  Robust Validation: Includes comprehensive checks for array types in MCP config processing and error handling throughout the rules management system.

  This enables more flexible, rule-specific project setups with intelligent cleanup that preserves user customizations while safely managing Task Master components.

  • Resolves #338

• #804 1b8c320 Thanks @ejones40! - Add better support for python projects by adding pyproject.toml as a projectRoot marker

• #743 a2a3229 Thanks @joedanz! - - Git Worktree Detection:

  • Now properly skips Git initialization when inside existing Git worktree
  • Prevents accidental nested repository creation
  • Flag System Overhaul:
    • --git/--no-git controls repository initialization
    • --aliases/--no-aliases consistently manages shell alias creation
    • --git-tasks/--no-git-tasks controls whether task files are stored in Git
    • --dry-run accurately previews all initialization behaviors
  • GitTasks Functionality:
    • New --git-tasks flag includes task files in Git (comments them out in .gitignore)
    • New --no-git-tasks flag excludes task files from Git (default behavior)
    • Supports both CLI and MCP interfaces with proper parameter passing

  Implementation Details:

  • Added explicit Git worktree detection before initialization
  • Refactored flag processing to ensure consistent behavior
  • Fixes #734

• #829 4b0c9d9 Thanks @Crunchyman-ralph! - Add Claude Code provider support

  Introduces a new provider that enables using Claude models (Opus and Sonnet) through the Claude Code CLI without requiring an API key.

  Key features:

  • New claude-code provider with support for opus and sonnet models
  • No API key required - uses local Claude Code CLI installation
  • Optional dependency - won't affect users who don't need Claude Code
  • Lazy loading ensures the provider only loads when requested
  • Full integration with existing Task Master commands and workflows
  • Comprehensive test coverage for reliability
  • New --claude-code flag for the models command

  Users can now configure Claude Code models with:
  task-master models --set-main sonnet --claude-code
  task-master models --set-research opus --claude-code

  The @anthropic-ai/claude-code package is optional and won't be installed unless explicitly needed.

Patch Changes

• #827 5da5b59 Thanks @Crunchyman-ralph! - Fix expand command preserving tagged task structure and preventing data corruption

  • Enhance E2E tests with comprehensive tag-aware expand testing to verify tag corruption fix
  • Add new test section for feature-expand tag creation and testing during expand operations
  • Verify tag preservation during expand, force expand, and expand --all operations
  • Test that master tag remains intact while feature-expand tag receives subtasks correctly
  • Fix file path references to use correct .taskmaster/config.json and .taskmaster/tasks/tasks.json locations
  • All tag corruption verification tests pass successfully, confirming the expand command tag corruption bug fix works as expected

• #833 cf2c066 Thanks @joedanz! - Call rules interactive setup during init

• #826 7811227 Thanks @Crunchyman-ralph! - Improves Amazon Bedrock support

• #834 6483537 Thanks @Crunchyman-ralph! - Fix issues with task creation/update where subtasks are being created like id: <parent_task>. instead if just id:

• #835 727f1ec Thanks @joedanz! - Store tasks in Git by default

• #822 1bd6d4f Thanks @Crunchyman-ralph! - Improve provider validation system with clean constants structure

  • Fixed "Invalid provider hint" errors: Resolved validation failures for Azure, Vertex, and Bedrock providers
  • Improved search UX: Integrated search for better model discovery with real-time filtering
  • Better organization: Moved custom provider options to bottom of model selection with clear section separators

  This change ensures all custom providers (Azure, Vertex, Bedrock, OpenRouter, Ollama) work correctly in task-master models --setup

• #633 3a2325a Thanks @nmarley! - Fix weird task-master init bug when using in certain environments

• #831 b592dff Thanks @joedanz! - Rename Roo Code Boomerang role to Orchestrator

• #830 e9d1bc2 Thanks @Crunchyman-ralph! - Improve mcp keys check in cursor

v0.17.1

Patch Changes

• #789 8cde6c2 Thanks @Crunchyman-ralph! - Fix contextGatherer bug when adding a task Cannot read properties of undefined (reading 'forEach')

v0.17.0

Minor Changes

• #779 c0b3f43 Thanks @eyaltoledano! - 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
  • Token Transparency: Displays detailed token breakdown showing context size, sources, and estimated costs
  • Enhanced Display: Syntax-highlighted code blocks and structured output with clear visual separation

  Usage Examples:

  # 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:

  # 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.

• #779 c0b3f43 Thanks @eyaltoledano! - 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:

  CLI Enhancement:

  • task-master update-task --id=5 --prompt="New info" - Full task update (existing behavior)
  • 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.

• #779 c0b3f43 Thanks @eyaltoledano! - 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
  • analyze-complexity --tag=branch: Generate tag-specific complexity reports
  • All task operations can target specific contexts while preserving other lists
  • Non-existent tags are created automatically for seamless workflow

• #779 c0b3f43 Thanks @eyaltoledano! - 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:

  • Legacy Format: { "tasks": [...] }
  • New Tagged Format: { "master": { "tasks": [...], "metadata": {...} }, "feature-xyz": { "tasks": [...], "metadata": {...} } }
  • Automatic Migration: Existing projects will seamlessly migrate to tagged format with zero user intervention
  • State Management: New .taskmaster/state.json tracks current tag, last switched time, migration status and more.
  • Configuration Integration: Enhanced .taskmaster/config.json with tag-specific settings and defaults.

  By default, your existing task list will be migrated to the master tag.

  🚀 Complete Tag Management Suite:

  Core Tag Commands:

  • task-master tags [--show-metadata] - List all tags with task counts, completion stats, and metadata
  • task-master add-tag <name> [options] - Create new tag contexts with optional task copying
  • task-master delete-tag <name> [--yes] - Delete tags (and attached tasks) with double confirmation protection
  • task-master use-tag <name> - Switch contexts and immediately see next available task
  • task-master rename-tag <old> <new> - Rename tags with automatic current tag reference updates
  • task-master copy-tag <source> <target> [options] - Duplicate tag contexts for experimentation

  🤖 Full MCP Integration for Tag Management:

  Task Master's multi-context capabilities are now fully exposed through the MCP server, enabling powerful agentic workflows:

  • list_tags: List all available tag contexts.
  • add_tag: Programmatically create new tags.
  • delete_tag: Remove tag contexts.
  • use_tag: Switch the agent's active task context.
  • rename_tag: Rename existing tags.
  • copy_tag: Duplicate entire task contexts for experimentation.

  Tag Creation Options:

  • --copy-from-current - Copy tasks from currently active tag
  • --copy-from=<tag> - Copy tasks from specific tag
  • --from-branch - Creates a new tag using the active git branch name (for add-tag only)
  • --description="<text>" - Add custom tag descriptions
  • Empty tag creation for fresh contexts

  🎯 Universal --tag Flag Support:

  Every task operation now supports tag-specific execution:

  • task-master list --tag=feature-branch - View tasks in specific context
  • task-master add-task --tag=experiment --prompt="..." - Create tasks in specific tag
  • task-master parse-prd document.txt --tag=v2-redesign - Parse PRDs into dedicated contexts
  • task-master analyze-complexity --tag=performance-work - Generate tag-specific reports
  • task-master set-status --tag=hotfix --id=5 --status=done - Update tasks in specific contexts
  • `task-...