Merge pull request #1015 from eyaltoledano/changeset-release/main

Version Packages

.changeset/claude-code-json-truncation.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-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. 

.changeset/cuddly-baboons-invent.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-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.

.changeset/grok-4-support.md

@@ -1,9 +0,0 @@
----
-"task-master-ai": minor
----
-
-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)

.changeset/quick-laws-cover.md

@@ -1,8 +0,0 @@
----
-"task-master-ai": minor
----
-
-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

.changeset/some-lies-grin.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add support for MCP Sampling as AI provider, requires no API key, uses the client LLM provider

.changeset/spicy-badgers-fail.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Unify and streamline profile system architecture for improved maintainability

.changeset/tender-ads-joke.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": minor
----
-
-Added Groq provider support

.claude/commands/tm/index.md

@@ -1,130 +0,0 @@
-# Task Master Command Reference
-
-Comprehensive command structure for Task Master integration with Claude Code.
-
-## Command Organization
-
-Commands are organized hierarchically to match Task Master's CLI structure while providing enhanced Claude Code integration.
-
-## Project Setup & Configuration
-
-### `/project:tm/init`
-- `index` - Initialize new project (handles PRD files intelligently)
-- `quick` - Quick setup with auto-confirmation (-y flag)
-
-### `/project:tm/models`
-- `index` - View current AI model configuration
-- `setup` - Interactive model configuration
-- `set-main` - Set primary generation model
-- `set-research` - Set research model
-- `set-fallback` - Set fallback model
-
-## Task Generation
-
-### `/project:tm/parse-prd`
-- `index` - Generate tasks from PRD document
-- `with-research` - Enhanced parsing with research mode
-
-### `/project:tm/generate`
-- Create individual task files from tasks.json
-
-## Task Management
-
-### `/project:tm/list`
-- `index` - Smart listing with natural language filters
-- `with-subtasks` - Include subtasks in hierarchical view
-- `by-status` - Filter by specific status
-
-### `/project:tm/set-status`
-- `to-pending` - Reset task to pending
-- `to-in-progress` - Start working on task
-- `to-done` - Mark task complete
-- `to-review` - Submit for review
-- `to-deferred` - Defer task
-- `to-cancelled` - Cancel task
-
-### `/project:tm/sync-readme`
-- Export tasks to README.md with formatting
-
-### `/project:tm/update`
-- `index` - Update tasks with natural language
-- `from-id` - Update multiple tasks from a starting point
-- `single` - Update specific task
-
-### `/project:tm/add-task`
-- `index` - Add new task with AI assistance
-
-### `/project:tm/remove-task`
-- `index` - Remove task with confirmation
-
-## Subtask Management
-
-### `/project:tm/add-subtask`
-- `index` - Add new subtask to parent
-- `from-task` - Convert existing task to subtask
-
-### `/project:tm/remove-subtask`
-- Remove subtask (with optional conversion)
-
-### `/project:tm/clear-subtasks`
-- `index` - Clear subtasks from specific task
-- `all` - Clear all subtasks globally
-
-## Task Analysis & Breakdown
-
-### `/project:tm/analyze-complexity`
-- Analyze and generate expansion recommendations
-
-### `/project:tm/complexity-report`
-- Display complexity analysis report
-
-### `/project:tm/expand`
-- `index` - Break down specific task
-- `all` - Expand all eligible tasks
-- `with-research` - Enhanced expansion
-
-## Task Navigation
-
-### `/project:tm/next`
-- Intelligent next task recommendation
-
-### `/project:tm/show`
-- Display detailed task information
-
-### `/project:tm/status`
-- Comprehensive project dashboard
-
-## Dependency Management
-
-### `/project:tm/add-dependency`
-- Add task dependency
-
-### `/project:tm/remove-dependency`
-- Remove task dependency
-
-### `/project:tm/validate-dependencies`
-- Check for dependency issues
-
-### `/project:tm/fix-dependencies`
-- Automatically fix dependency problems
-
-## Usage Patterns
-
-### Natural Language
-Most commands accept natural language arguments:
-```
-/project:tm/add-task create user authentication system
-/project:tm/update mark all API tasks as high priority
-/project:tm/list show blocked tasks
-```
-
-### ID-Based Commands
-Commands requiring IDs intelligently parse from $ARGUMENTS:
-```
-/project:tm/show 45
-/project:tm/expand 23
-/project:tm/set-status/to-done 67
-```
-
-### Smart Defaults
-Commands provide intelligent defaults and suggestions based on context.

.claude/commands/tm/tm-main.md

@@ -0,0 +1,146 @@
+# Task Master Command Reference
+
+Comprehensive command structure for Task Master integration with Claude Code.
+
+## Command Organization
+
+Commands are organized hierarchically to match Task Master's CLI structure while providing enhanced Claude Code integration.
+
+## Project Setup & Configuration
+
+### `/project:tm/init`
+- `init-project` - Initialize new project (handles PRD files intelligently)
+- `init-project-quick` - Quick setup with auto-confirmation (-y flag)
+
+### `/project:tm/models`
+- `view-models` - View current AI model configuration
+- `setup-models` - Interactive model configuration
+- `set-main` - Set primary generation model
+- `set-research` - Set research model
+- `set-fallback` - Set fallback model
+
+## Task Generation
+
+### `/project:tm/parse-prd`
+- `parse-prd` - Generate tasks from PRD document
+- `parse-prd-with-research` - Enhanced parsing with research mode
+
+### `/project:tm/generate`
+- `generate-tasks` - Create individual task files from tasks.json
+
+## Task Management
+
+### `/project:tm/list`
+- `list-tasks` - Smart listing with natural language filters
+- `list-tasks-with-subtasks` - Include subtasks in hierarchical view
+- `list-tasks-by-status` - Filter by specific status
+
+### `/project:tm/set-status`
+- `to-pending` - Reset task to pending
+- `to-in-progress` - Start working on task
+- `to-done` - Mark task complete
+- `to-review` - Submit for review
+- `to-deferred` - Defer task
+- `to-cancelled` - Cancel task
+
+### `/project:tm/sync-readme`
+- `sync-readme` - Export tasks to README.md with formatting
+
+### `/project:tm/update`
+- `update-task` - Update tasks with natural language
+- `update-tasks-from-id` - Update multiple tasks from a starting point
+- `update-single-task` - Update specific task
+
+### `/project:tm/add-task`
+- `add-task` - Add new task with AI assistance
+
+### `/project:tm/remove-task`
+- `remove-task` - Remove task with confirmation
+
+## Subtask Management
+
+### `/project:tm/add-subtask`
+- `add-subtask` - Add new subtask to parent
+- `convert-task-to-subtask` - Convert existing task to subtask
+
+### `/project:tm/remove-subtask`
+- `remove-subtask` - Remove subtask (with optional conversion)
+
+### `/project:tm/clear-subtasks`
+- `clear-subtasks` - Clear subtasks from specific task
+- `clear-all-subtasks` - Clear all subtasks globally
+
+## Task Analysis & Breakdown
+
+### `/project:tm/analyze-complexity`
+- `analyze-complexity` - Analyze and generate expansion recommendations
+
+### `/project:tm/complexity-report`
+- `complexity-report` - Display complexity analysis report
+
+### `/project:tm/expand`
+- `expand-task` - Break down specific task
+- `expand-all-tasks` - Expand all eligible tasks
+- `with-research` - Enhanced expansion
+
+## Task Navigation
+
+### `/project:tm/next`
+- `next-task` - Intelligent next task recommendation
+
+### `/project:tm/show`
+- `show-task` - Display detailed task information
+
+### `/project:tm/status`
+- `project-status` - Comprehensive project dashboard
+
+## Dependency Management
+
+### `/project:tm/add-dependency`
+- `add-dependency` - Add task dependency
+
+### `/project:tm/remove-dependency`
+- `remove-dependency` - Remove task dependency
+
+### `/project:tm/validate-dependencies`
+- `validate-dependencies` - Check for dependency issues
+
+### `/project:tm/fix-dependencies`
+- `fix-dependencies` - Automatically fix dependency problems
+
+## Workflows & Automation
+
+### `/project:tm/workflows`
+- `smart-workflow` - Context-aware intelligent workflow execution
+- `command-pipeline` - Chain multiple commands together
+- `auto-implement-tasks` - Advanced auto-implementation with code generation
+
+## Utilities
+
+### `/project:tm/utils`
+- `analyze-project` - Deep project analysis and insights
+
+### `/project:tm/setup`
+- `install-taskmaster` - Comprehensive installation guide
+- `quick-install-taskmaster` - One-line global installation
+
+## Usage Patterns
+
+### Natural Language
+Most commands accept natural language arguments:
+```
+/project:tm/add-task create user authentication system
+/project:tm/update mark all API tasks as high priority
+/project:tm/list show blocked tasks
+```
+
+### ID-Based Commands
+Commands requiring IDs intelligently parse from $ARGUMENTS:
+```
+/project:tm/show 45
+/project:tm/expand 23
+/project:tm/set-status/to-done 67
+```
+
+### Smart Defaults
+Commands provide intelligent defaults and suggestions based on context.

.coderabbit.yaml

@@ -0,0 +1,10 @@
+reviews:
+  profile: assertive
+  poem: false
+  auto_review:
+    base_branches:
+      - rc
+      - beta
+      - alpha
+      - production
+      - next

.env.example

@@ -8,6 +8,7 @@ GROQ_API_KEY=YOUR_GROQ_KEY_HERE
 OPENROUTER_API_KEY=YOUR_OPENROUTER_KEY_HERE
 XAI_API_KEY=YOUR_XAI_KEY_HERE
 AZURE_OPENAI_API_KEY=YOUR_AZURE_KEY_HERE
+OLLAMA_API_KEY=YOUR_OLLAMA_API_KEY_HERE
 
 # Google Vertex AI Configuration
 VERTEX_PROJECT_ID=your-gcp-project-id

.taskmaster/config.json

@@ -1,21 +1,21 @@
 {
 	"models": {
 		"main": {
-			"provider": "groq",
-			"modelId": "llama-3.1-8b-instant",
-			"maxTokens": 131072,
+			"provider": "anthropic",
+			"modelId": "claude-3-7-sonnet-20250219",
+			"maxTokens": 120000,
 			"temperature": 0.2
 		},
 		"research": {
-			"provider": "groq",
-			"modelId": "llama-3.3-70b-versatile",
-			"maxTokens": 32768,
+			"provider": "perplexity",
+			"modelId": "sonar",
+			"maxTokens": 8700,
 			"temperature": 0.1
 		},
 		"fallback": {
 			"provider": "anthropic",
-			"modelId": "claude-3-7-sonnet-20250219",
-			"maxTokens": 128000,
+			"modelId": "claude-3-5-sonnet-20241022",
+			"maxTokens": 8192,
 			"temperature": 0.2
 		}
 	},

.taskmaster/tasks/task_001_test-tag.txt

@@ -1,23 +0,0 @@
-# Task ID: 1
-# Title: Implement TTS Flag for Taskmaster Commands
-# Status: pending
-# Dependencies: 16 (Not found)
-# Priority: medium
-# Description: Add text-to-speech functionality to taskmaster commands with configurable voice options and audio output settings.
-# Details:
-Implement TTS functionality including:
-- Add --tts flag to all relevant taskmaster commands (list, show, generate, etc.)
-- Integrate with system TTS engines (Windows SAPI, macOS say command, Linux espeak/festival)
-- Create TTS configuration options in the configuration management system
-- Add voice selection options (male/female, different languages if available)
-- Implement audio output settings (volume, speed, pitch)
-- 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.

CHANGELOG.md

@@ -1,5 +1,189 @@
 # task-master-ai
 
+## 0.21.0
+
+### Minor Changes
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`9c58a92`](https://github.com/eyaltoledano/claude-task-master/commit/9c58a922436c0c5e7ff1b20ed2edbc269990c772) Thanks [@Crunchyman-ralph](https://github.com/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
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Created a comprehensive documentation site for Task Master AI. Visit https://docs.task-master.dev to explore guides, API references, and examples.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`58a301c`](https://github.com/eyaltoledano/claude-task-master/commit/58a301c380d18a9d9509137f3e989d24200a5faa) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - 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
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`b0e09c7`](https://github.com/eyaltoledano/claude-task-master/commit/b0e09c76ed73b00434ac95606679f570f1015a3d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - feat: Add Zed editor rule profile with agent rules and MCP config
+  - Resolves #637
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`6c5e0f9`](https://github.com/eyaltoledano/claude-task-master/commit/6c5e0f97f8403c4da85c1abba31cb8b1789511a7) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Amp rule profile with AGENT.md and MCP config
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve project root detection
+  - No longer creates an infinite loop when unable to detect your code workspace
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`36c4a7a`](https://github.com/eyaltoledano/claude-task-master/commit/36c4a7a86924c927ad7f86a4f891f66ad55eb4d2) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add OpenCode profile with AGENTS.md and MCP config
+  - Resolves #965
+
+### Patch Changes
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/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.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/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.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`6d69d02`](https://github.com/eyaltoledano/claude-task-master/commit/6d69d02fe03edcc785380415995d5cfcdd97acbb) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - 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.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`fd005c4`](https://github.com/eyaltoledano/claude-task-master/commit/fd005c4c5481ffac58b11f01a448fa5b29056b8d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Implement Boundary-First Tag Resolution to ensure consistent and deterministic tag handling across CLI and MCP, resolving potential race conditions.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix `task-master lang --setup` breaking when no language is defined, now defaults to English
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`624922c`](https://github.com/eyaltoledano/claude-task-master/commit/624922ca598c4ce8afe9a5646ebb375d4616db63) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - 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.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`858d4a1`](https://github.com/eyaltoledano/claude-task-master/commit/858d4a1c5486d20e7e3a8e37e3329d7fb8200310) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Update VS Code profile with MCP config transformation
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0451ebc`](https://github.com/eyaltoledano/claude-task-master/commit/0451ebcc32cd7e9d395b015aaa8602c4734157e1) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP server error when retrieving tools and resources
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0a70ab6`](https://github.com/eyaltoledano/claude-task-master/commit/0a70ab6179cb2b5b4b2d9dc256a7a3b69a0e5dd6) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add MCP configuration support to Claude Code rules
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`4629128`](https://github.com/eyaltoledano/claude-task-master/commit/4629128943f6283385f4762c09cf2752f855cc33) Thanks [@Crunchyman-ralph](https://github.com/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
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0886c83`](https://github.com/eyaltoledano/claude-task-master/commit/0886c83d0c678417c0313256a6dd96f7ee2c9ac6) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`88c434a`](https://github.com/eyaltoledano/claude-task-master/commit/88c434a9393e429d9277f59b3e20f1005076bbe0) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add missing API keys to .env.example and README.md
+
+## 0.21.0-rc.0
+
+### Minor Changes
+
+- [#1001](https://github.com/eyaltoledano/claude-task-master/pull/1001) [`75a36ea`](https://github.com/eyaltoledano/claude-task-master/commit/75a36ea99a1c738a555bdd4fe7c763d0c5925e37) Thanks [@Crunchyman-ralph](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/978) [`fedfd6a`](https://github.com/eyaltoledano/claude-task-master/commit/fedfd6a0f41a78094f7ee7f69be689b699475a79) Thanks [@ben-vargas](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/974) [`5b0eda0`](https://github.com/eyaltoledano/claude-task-master/commit/5b0eda07f20a365aa2ec1736eed102bca81763a9) Thanks [@joedanz](https://github.com/joedanz)! - feat: Add Zed editor rule profile with agent rules and MCP config
+  - Resolves #637
+
+- [#973](https://github.com/eyaltoledano/claude-task-master/pull/973) [`6d05e86`](https://github.com/eyaltoledano/claude-task-master/commit/6d05e8622c1d761acef10414940ff9a766b3b57d) Thanks [@joedanz](https://github.com/joedanz)! - Add Amp rule profile with AGENT.md and MCP config
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve project root detection
+  - No longer creates an infinite loop when unable to detect your code workspace
+
+- [#970](https://github.com/eyaltoledano/claude-task-master/pull/970) [`b87499b`](https://github.com/eyaltoledano/claude-task-master/commit/b87499b56e626001371a87ed56ffc72675d829f3) Thanks [@joedanz](https://github.com/joedanz)! - Add OpenCode profile with AGENTS.md and MCP config
+  - Resolves #965
+
+### Patch Changes
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/949) [`f662654`](https://github.com/eyaltoledano/claude-task-master/commit/f662654afb8e7a230448655265d6f41adf6df62c) Thanks [@ben-vargas](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/943) [`f98df5c`](https://github.com/eyaltoledano/claude-task-master/commit/f98df5c0fdb253b2b55d4278c11d626529c4dba4) Thanks [@mm-parthy](https://github.com/mm-parthy)! - Implement Boundary-First Tag Resolution to ensure consistent and deterministic tag handling across CLI and MCP, resolving potential race conditions.
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix `task-master lang --setup` breaking when no language is defined, now defaults to English
+
+- [#979](https://github.com/eyaltoledano/claude-task-master/pull/979) [`ab2e946`](https://github.com/eyaltoledano/claude-task-master/commit/ab2e94608749a2f148118daa0443bd32bca6e7a1) Thanks [@ben-vargas](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/971) [`5544222`](https://github.com/eyaltoledano/claude-task-master/commit/55442226d0aa4870470d2a9897f5538d6a0e329e) Thanks [@joedanz](https://github.com/joedanz)! - Update VS Code profile with MCP config transformation
+
+- [#1002](https://github.com/eyaltoledano/claude-task-master/pull/1002) [`6d0654c`](https://github.com/eyaltoledano/claude-task-master/commit/6d0654cb4191cee794e1c8cbf2b92dc33d4fb410) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP server error when retrieving tools and resources
+
+- [#980](https://github.com/eyaltoledano/claude-task-master/pull/980) [`cc4fe20`](https://github.com/eyaltoledano/claude-task-master/commit/cc4fe205fb468e7144c650acc92486df30731560) Thanks [@joedanz](https://github.com/joedanz)! - Add MCP configuration support to Claude Code rules
+
+- [#968](https://github.com/eyaltoledano/claude-task-master/pull/968) [`7b4803a`](https://github.com/eyaltoledano/claude-task-master/commit/7b4803a479105691c7ed032fd878fe3d48d82724) Thanks [@Crunchyman-ralph](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/995) [`b78de8d`](https://github.com/eyaltoledano/claude-task-master/commit/b78de8dbb4d6dc93b48e2f81c32960ef069736ed) Thanks [@joedanz](https://github.com/joedanz)! - Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.
+
+- [#972](https://github.com/eyaltoledano/claude-task-master/pull/972) [`1c7badf`](https://github.com/eyaltoledano/claude-task-master/commit/1c7badff2f5c548bfa90a3b2634e63087a382a84) Thanks [@joedanz](https://github.com/joedanz)! - Add missing API keys to .env.example and README.md
+
+## 0.20.0
+
+### Minor Changes
+
+- [#950](https://github.com/eyaltoledano/claude-task-master/pull/950) [`699e9ee`](https://github.com/eyaltoledano/claude-task-master/commit/699e9eefb5d687b256e9402d686bdd5e3a358b4a) Thanks [@ben-vargas](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/946) [`5f009a5`](https://github.com/eyaltoledano/claude-task-master/commit/5f009a5e1fc10e37be26f5135df4b7f44a9c5320) Thanks [@Crunchyman-ralph](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/863) [`b530657`](https://github.com/eyaltoledano/claude-task-master/commit/b53065713c8da0ae6f18eb2655397aa975004923) Thanks [@OrenMe](https://github.com/OrenMe)! - Add support for MCP Sampling as AI provider, requires no API key, uses the client LLM provider
+
+- [#930](https://github.com/eyaltoledano/claude-task-master/pull/930) [`98d1c97`](https://github.com/eyaltoledano/claude-task-master/commit/98d1c974361a56ddbeb772b1272986b9d3913459) Thanks [@OmarElKadri](https://github.com/OmarElKadri)! - Added Groq provider support
+
+### Patch Changes
+
+- [#958](https://github.com/eyaltoledano/claude-task-master/pull/958) [`6c88a4a`](https://github.com/eyaltoledano/claude-task-master/commit/6c88a4a749083e3bd2d073a9240799771774495a) Thanks [@Crunchyman-ralph](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/958) [`3334e40`](https://github.com/eyaltoledano/claude-task-master/commit/3334e409ae659d5223bb136ae23fd22c5e219073) Thanks [@Crunchyman-ralph](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/853) [`95c299d`](https://github.com/eyaltoledano/claude-task-master/commit/95c299df642bd8e6d75f8fa5110ac705bcc72edf) Thanks [@joedanz](https://github.com/joedanz)! - Unify and streamline profile system architecture for improved maintainability
+
+## 0.20.0-rc.0
+
+### Minor Changes
+
+- [#950](https://github.com/eyaltoledano/claude-task-master/pull/950) [`699e9ee`](https://github.com/eyaltoledano/claude-task-master/commit/699e9eefb5d687b256e9402d686bdd5e3a358b4a) Thanks [@ben-vargas](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/946) [`5f009a5`](https://github.com/eyaltoledano/claude-task-master/commit/5f009a5e1fc10e37be26f5135df4b7f44a9c5320) Thanks [@Crunchyman-ralph](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/863) [`b530657`](https://github.com/eyaltoledano/claude-task-master/commit/b53065713c8da0ae6f18eb2655397aa975004923) Thanks [@OrenMe](https://github.com/OrenMe)! - Add support for MCP Sampling as AI provider, requires no API key, uses the client LLM provider
+
+- [#930](https://github.com/eyaltoledano/claude-task-master/pull/930) [`98d1c97`](https://github.com/eyaltoledano/claude-task-master/commit/98d1c974361a56ddbeb772b1272986b9d3913459) Thanks [@OmarElKadri](https://github.com/OmarElKadri)! - Added Groq provider support
+
+### Patch Changes
+
+- [#916](https://github.com/eyaltoledano/claude-task-master/pull/916) [`6c88a4a`](https://github.com/eyaltoledano/claude-task-master/commit/6c88a4a749083e3bd2d073a9240799771774495a) Thanks [@Crunchyman-ralph](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/916) [`3334e40`](https://github.com/eyaltoledano/claude-task-master/commit/3334e409ae659d5223bb136ae23fd22c5e219073) Thanks [@Crunchyman-ralph](https://github.com/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](https://github.com/eyaltoledano/claude-task-master/pull/853) [`95c299d`](https://github.com/eyaltoledano/claude-task-master/commit/95c299df642bd8e6d75f8fa5110ac705bcc72edf) Thanks [@joedanz](https://github.com/joedanz)! - Unify and streamline profile system architecture for improved maintainability
+
 ## 0.19.0
 
 ### Minor Changes

README.md

@@ -14,7 +14,13 @@ A task management system for AI-driven development with Claude, designed to work
 
 ## Documentation
 
-For more detailed information, check out the documentation in the `docs` directory:
+📚 **[View Full Documentation](https://docs.task-master.dev)**
+
+For detailed guides, API references, and comprehensive examples, visit our documentation site.
+
+### Quick Reference
+
+The following documentation is also available in the `docs` directory:
 
 - [Configuration Guide](docs/configuration.md) - Set up environment variables and customize Task Master
 - [Tutorial](docs/tutorial.md) - Step-by-step guide to getting started with Task Master
@@ -25,11 +31,7 @@ For more detailed information, check out the documentation in the `docs` directo
 
 #### Quick Install for Cursor 1.0+ (One-Click)
 
-📋 Click the copy button (top-right of code block) then paste into your browser:
-
-```text
-cursor://anysphere.cursor-deeplink/mcp/install?name=taskmaster-ai&config=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
-```
+[![Add task-master-ai MCP server to Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/install-mcp?name=task-master-ai&config=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%3D%3D)
 
 > **Note:** After clicking the link, you'll still need to add your API keys to the configuration. The link installs the MCP server with placeholder keys that you'll need to replace with your actual API keys.
 
@@ -73,7 +75,7 @@ MCP (Model Control Protocol) lets you run Task Master directly from your editor.
 ```json
 {
   "mcpServers": {
-    "taskmaster-ai": {
+    "task-master-ai": {
       "command": "npx",
       "args": ["-y", "--package=task-master-ai", "task-master-ai"],
       "env": {
@@ -82,6 +84,7 @@ MCP (Model Control Protocol) lets you run Task Master directly from your editor.
         "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
         "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
         "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
+        "GROQ_API_KEY": "YOUR_GROQ_KEY_HERE",
         "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
         "XAI_API_KEY": "YOUR_XAI_KEY_HERE",
         "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE",
@@ -101,7 +104,7 @@ MCP (Model Control Protocol) lets you run Task Master directly from your editor.
 ```json
 {
   "servers": {
-    "taskmaster-ai": {
+    "task-master-ai": {
       "command": "npx",
       "args": ["-y", "--package=task-master-ai", "task-master-ai"],
       "env": {
@@ -110,9 +113,11 @@ MCP (Model Control Protocol) lets you run Task Master directly from your editor.
         "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
         "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
         "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
+        "GROQ_API_KEY": "YOUR_GROQ_KEY_HERE",
         "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
         "XAI_API_KEY": "YOUR_XAI_KEY_HERE",
-        "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE"
+        "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE",
+        "OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
       },
       "type": "stdio"
     }

apps/extension/package.json

@@ -0,0 +1,16 @@
+{
+	"name": "extension",
+	"private": true,
+	"version": "0.20.0",
+	"main": "index.js",
+	"scripts": {
+		"test": "echo \"Error: no test specified\" && exit 1"
+	},
+	"keywords": [],
+	"author": "",
+	"license": "ISC",
+	"description": "",
+	"devDependencies": {
+		"typescript": "^5.8.3"
+	}
+}

apps/extension/src/index.ts

@@ -0,0 +1 @@
+console.log('hello world');

apps/extension/tsconfig.json

@@ -0,0 +1,113 @@
+{
+	"compilerOptions": {
+		/* Visit https://aka.ms/tsconfig to read more about this file */
+
+		/* Projects */
+		// "incremental": true,                              /* Save .tsbuildinfo files to allow for incremental compilation of projects. */
+		// "composite": true,                                /* Enable constraints that allow a TypeScript project to be used with project references. */
+		// "tsBuildInfoFile": "./.tsbuildinfo",              /* Specify the path to .tsbuildinfo incremental compilation file. */
+		// "disableSourceOfProjectReferenceRedirect": true,  /* Disable preferring source files instead of declaration files when referencing composite projects. */
+		// "disableSolutionSearching": true,                 /* Opt a project out of multi-project reference checking when editing. */
+		// "disableReferencedProjectLoad": true,             /* Reduce the number of projects loaded automatically by TypeScript. */
+
+		/* Language and Environment */
+		"target": "es2016" /* Set the JavaScript language version for emitted JavaScript and include compatible library declarations. */,
+		// "lib": [],                                        /* Specify a set of bundled library declaration files that describe the target runtime environment. */
+		// "jsx": "preserve",                                /* Specify what JSX code is generated. */
+		// "libReplacement": true,                           /* Enable lib replacement. */
+		// "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. */
+
+		/* Modules */
+		"module": "commonjs" /* Specify what module code is generated. */,
+		// "rootDir": "./",                                  /* Specify the root folder within your source files. */
+		// "moduleResolution": "node10",                     /* Specify how TypeScript looks up a file from a given module specifier. */
+		// "baseUrl": "./",                                  /* Specify the base directory to resolve non-relative module names. */
+		// "paths": {},                                      /* Specify a set of entries that re-map imports to additional lookup locations. */
+		// "rootDirs": [],                                   /* Allow multiple folders to be treated as one when resolving modules. */
+		// "typeRoots": [],                                  /* Specify multiple folders that act like './node_modules/@types'. */
+		// "types": [],                                      /* Specify type package names to be included without being referenced in a source file. */
+		// "allowUmdGlobalAccess": true,                     /* Allow accessing UMD globals from modules. */
+		// "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. */
+		// "resolveJsonModule": true,                        /* Enable importing .json files. */
+		// "allowArbitraryExtensions": true,                 /* Enable importing files with any extension, provided a declaration file is present. */
+		// "noResolve": true,                                /* Disallow 'import's, 'require's or '<reference>'s from expanding the number of files TypeScript should add to a project. */
+
+		/* JavaScript Support */
+		// "allowJs": true,                                  /* Allow JavaScript files to be a part of your program. Use the 'checkJS' option to get errors from these files. */
+		// "checkJs": true,                                  /* Enable error reporting in type-checked JavaScript files. */
+		// "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. */
+		// "sourceMap": true,                                /* Create source map files for emitted 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. */
+		// "removeComments": true,                           /* Disable emitting comments. */
+		// "importHelpers": true,                            /* Allow importing helper functions from tslib once per project, instead of including them per-file. */
+		// "downlevelIteration": true,                       /* Emit more compliant, but verbose and less performant JavaScript for iteration. */
+		// "sourceRoot": "",                                 /* Specify the root path for debuggers to find the reference source code. */
+		// "mapRoot": "",                                    /* Specify the location where debugger should locate map files instead of generated locations. */
+		// "inlineSources": true,                            /* Include source code in the sourcemaps inside the emitted JavaScript. */
+		// "emitBOM": true,                                  /* Emit a UTF-8 Byte Order Mark (BOM) in the beginning of output files. */
+		// "newLine": "crlf",                                /* Set the newline character for emitting files. */
+		// "stripInternal": true,                            /* Disable emitting declarations that have '@internal' in their JSDoc comments. */
+		// "noEmitHelpers": true,                            /* Disable generating custom helper functions like '__extends' in compiled output. */
+		// "noEmitOnError": true,                            /* Disable emitting files if any type checking errors are reported. */
+		// "preserveConstEnums": true,                       /* Disable erasing 'const enum' declarations in generated code. */
+		// "declarationDir": "./",                           /* Specify the output directory for generated declaration files. */
+
+		/* Interop Constraints */
+		// "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. */
+		"esModuleInterop": true /* Emit additional JavaScript to ease support for importing CommonJS modules. This enables 'allowSyntheticDefaultImports' for type compatibility. */,
+		// "preserveSymlinks": true,                         /* Disable resolving symlinks to their realpath. This correlates to the same flag in node. */
+		"forceConsistentCasingInFileNames": true /* Ensure that casing is correct in imports. */,
+
+		/* Type Checking */
+		"strict": true /* Enable all strict type-checking options. */,
+		// "noImplicitAny": true,                            /* Enable error reporting for expressions and declarations with an implied 'any' type. */
+		// "strictNullChecks": true,                         /* When type checking, take into account 'null' and 'undefined'. */
+		// "strictFunctionTypes": true,                      /* When assigning functions, check to ensure parameters and the return values are subtype-compatible. */
+		// "strictBindCallApply": true,                      /* Check that the arguments for 'bind', 'call', and 'apply' methods match the original function. */
+		// "strictPropertyInitialization": true,             /* Check for class properties that are declared but not set in the constructor. */
+		// "strictBuiltinIteratorReturn": true,              /* Built-in iterators are instantiated with a 'TReturn' type of 'undefined' instead of 'any'. */
+		// "noImplicitThis": true,                           /* Enable error reporting when 'this' is given the type 'any'. */
+		// "useUnknownInCatchVariables": true,               /* Default catch clause variables as 'unknown' instead of 'any'. */
+		// "alwaysStrict": true,                             /* Ensure 'use strict' is always emitted. */
+		// "noUnusedLocals": true,                           /* Enable error reporting when local variables aren't read. */
+		// "noUnusedParameters": true,                       /* Raise an error when a function parameter isn't read. */
+		// "exactOptionalPropertyTypes": true,               /* Interpret optional property types as written, rather than adding 'undefined'. */
+		// "noImplicitReturns": true,                        /* Enable error reporting for codepaths that do not explicitly return in a function. */
+		// "noFallthroughCasesInSwitch": true,               /* Enable error reporting for fallthrough cases in switch statements. */
+		// "noUncheckedIndexedAccess": true,                 /* Add 'undefined' to a type when accessed using an index. */
+		// "noImplicitOverride": true,                       /* Ensure overriding members in derived classes are marked with an override modifier. */
+		// "noPropertyAccessFromIndexSignature": true,       /* Enforces using indexed accessors for keys declared using an indexed type. */
+		// "allowUnusedLabels": true,                        /* Disable error reporting for unused labels. */
+		// "allowUnreachableCode": true,                     /* Disable error reporting for unreachable code. */
+
+		/* Completeness */
+		// "skipDefaultLibCheck": true,                      /* Skip type checking .d.ts files that are included with TypeScript. */
+		"skipLibCheck": true /* Skip type checking all .d.ts files. */
+	}
+}

assets/AGENTS.md

@@ -1,4 +1,4 @@
-# Task Master AI - Claude Code Integration Guide
+# Task Master AI - Agent Integration Guide
 
 ## Essential Commands
 

assets/env.example

@@ -1,10 +1,12 @@
 # API Keys (Required to enable respective provider)
 ANTHROPIC_API_KEY="your_anthropic_api_key_here"       # Required: Format: sk-ant-api03-...
 PERPLEXITY_API_KEY="your_perplexity_api_key_here"     # Optional: Format: pplx-...
-OPENAI_API_KEY="your_openai_api_key_here"             # Optional, for OpenAI/OpenRouter models. Format: sk-proj-...
+OPENAI_API_KEY="your_openai_api_key_here"             # Optional, for OpenAI models. Format: sk-proj-...
 GOOGLE_API_KEY="your_google_api_key_here"             # Optional, for Google Gemini models.
 MISTRAL_API_KEY="your_mistral_key_here"               # Optional, for Mistral AI models.
 XAI_API_KEY="YOUR_XAI_KEY_HERE"                       # Optional, for xAI AI models.
+GROQ_API_KEY="YOUR_GROQ_KEY_HERE"                     # Optional, for Groq models.
+OPENROUTER_API_KEY="YOUR_OPENROUTER_KEY_HERE"         # Optional, for OpenRouter models.
 AZURE_OPENAI_API_KEY="your_azure_key_here"            # Optional, for Azure OpenAI models (requires endpoint in .taskmaster/config.json).
 OLLAMA_API_KEY="your_ollama_api_key_here"             # Optional: For remote Ollama servers that require authentication.
 GITHUB_API_KEY="your_github_api_key_here"             # Optional: For GitHub import/export features. Format: ghp_... or github_pat_...

docs/configuration.md

@@ -4,30 +4,7 @@ Taskmaster uses two primary methods for configuration:
 
 1.  **`.taskmaster/config.json` File (Recommended - New Structure)**
 
-    - This JSON file stores most configuration settings, including A5. **Usage Requirements**:
-   8. **Troubleshooting**:
-   - "MCP provider requires session context" → Ensure running in MCP environment
-   - See the [MCP Provider Guide](./mcp-provider-guide.md) for detailed troubleshootingust be running in an MCP context (session must be available)
-   - Session must provide `clientCapabilities.sampling` capability
-
-6. **Best Practices**:
-   - Always configure a non-MCP fallback provider
-   - Use `mcp` for main/research roles when in MCP environments
-   - Test sampling capability before production use
-
-7. **Setup Commands**:
-   ```bash
-   # Set MCP provider for main role
-   task-master models set-main --provider mcp --model claude-3-5-sonnet-20241022
-   
-   # Set MCP provider for research role  
-   task-master models set-research --provider mcp --model claude-3-opus-20240229
-   
-   # Verify configuration
-   task-master models list
-   ```
-
-8. **Troubleshooting**:lections, parameters, logging levels, and project defaults.
+    - This JSON file stores most configuration settings, including AI model selections, parameters, logging levels, and project defaults.
     - **Location:** This file is created in the `.taskmaster/` directory when you run the `task-master models --setup` interactive setup or initialize a new project with `task-master init`.
     - **Migration:** Existing projects with `.taskmasterconfig` in the root will continue to work, but should be migrated to the new structure using `task-master migrate`.
     - **Management:** Use the `task-master models --setup` command (or `models` MCP tool) to interactively create and manage this file. You can also set specific models directly using `task-master models --set-<role>=<model_id>`, adding `--ollama` or `--openrouter` flags for custom models. Manual editing is possible but not recommended unless you understand the structure.
@@ -68,11 +45,12 @@ Taskmaster uses two primary methods for configuration:
           "azureBaseURL": "https://your-endpoint.azure.com/openai/deployments",
           "vertexProjectId": "your-gcp-project-id",
           "vertexLocation": "us-central1",
-		      "responseLanguage": "English"
+	      "responseLanguage": "English"
         }
       }
       ```
 
+> For MCP-specific setup and troubleshooting, see [Provider-Specific Configuration](#provider-specific-configuration).
 
 2.  **Legacy `.taskmasterconfig` File (Backward Compatibility)**
 
@@ -198,8 +176,6 @@ node scripts/init.js
 
 ### MCP (Model Context Protocol) Provider
 
-The MCP provider enables Task Master to use MCP servers as AI providers. This is particularly useful when running Task Master within MCP-compatible development environments like Claude Desktop or Cursor.
-
 1. **Prerequisites**:
    - An active MCP session with sampling capability
    - MCP client with sampling support (e.g. VS Code)
@@ -238,12 +214,24 @@ The MCP provider enables Task Master to use MCP servers as AI providers. This is
    - Must be running in an MCP context (session must be available)
    - Session must provide `clientCapabilities.sampling` capability
 
-5. **Best Practices**:
+6. **Best Practices**:
    - Always configure a non-MCP fallback provider
    - Use `mcp` for main/research roles when in MCP environments
    - Test sampling capability before production use
 
-6. **Troubleshooting**:
+7. **Setup Commands**:
+   ```bash
+   # Set MCP provider for main role
+   task-master models set-main --provider mcp --model claude-3-5-sonnet-20241022
+   
+   # Set MCP provider for research role  
+   task-master models set-research --provider mcp --model claude-3-opus-20240229
+   
+   # Verify configuration
+   task-master models list
+   ```
+
+8. **Troubleshooting**:
    - "MCP provider requires session context" → Ensure running in MCP environment
    - See the [MCP Provider Guide](./mcp-provider-guide.md) for detailed troubleshooting
 

docs/models.md

@@ -1,4 +1,4 @@
-# Available Models as of July 10, 2025
+# Available Models as of July 19, 2025
 
 ## Main Models
 
@@ -32,6 +32,7 @@
 | xai         | grok-3                                         | —         | 3          | 15          |
 | xai         | grok-3-fast                                    | —         | 5          | 25          |
 | xai         | grok-4                                         | —         | 3          | 15          |
+| groq        | moonshotai/kimi-k2-instruct                    | 0.66      | 1          | 3           |
 | groq        | llama-3.3-70b-versatile                        | 0.55      | 0.59       | 0.79        |
 | groq        | llama-3.1-8b-instant                           | 0.32      | 0.05       | 0.08        |
 | groq        | llama-4-scout                                  | 0.45      | 0.11       | 0.34        |
@@ -144,6 +145,7 @@
 | xai         | grok-3                                         | —         | 3          | 15          |
 | xai         | grok-3-fast                                    | —         | 5          | 25          |
 | xai         | grok-4                                         | —         | 3          | 15          |
+| groq        | moonshotai/kimi-k2-instruct                    | 0.66      | 1          | 3           |
 | groq        | llama-3.3-70b-versatile                        | 0.55      | 0.59       | 0.79        |
 | groq        | llama-3.1-8b-instant                           | 0.32      | 0.05       | 0.08        |
 | groq        | llama-4-scout                                  | 0.45      | 0.11       | 0.34        |

mcp-server/src/core/direct-functions/add-dependency.js

@@ -16,12 +16,14 @@ import {
  * @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
  * @param {string|number} args.id - Task ID to add dependency to
  * @param {string|number} args.dependsOn - Task ID that will become a dependency
+ * @param {string} args.tag - Tag for the task (optional)
+ * @param {string} args.projectRoot - Project root path (for MCP/env fallback)
  * @param {Object} log - Logger object
  * @returns {Promise<Object>} - Result object with success status and data/error information
  */
 export async function addDependencyDirect(args, log) {
 	// Destructure expected args
-	const { tasksJsonPath, id, dependsOn } = args;
+	const { tasksJsonPath, id, dependsOn, tag, projectRoot } = args;
 	try {
 		log.info(`Adding dependency with args: ${JSON.stringify(args)}`);
 
@@ -76,8 +78,11 @@ export async function addDependencyDirect(args, log) {
 		// Enable silent mode to prevent console logs from interfering with JSON response
 		enableSilentMode();
 
+		// Create context object
+		const context = { projectRoot, tag };
+
 		// Call the core function using the provided path
-		await addDependency(tasksPath, taskId, dependencyId);
+		await addDependency(tasksPath, taskId, dependencyId, context);
 
 		// Restore normal logging
 		disableSilentMode();

mcp-server/src/core/direct-functions/add-task.js

@@ -24,6 +24,7 @@ import { createLogWrapper } from '../../tools/utils.js';
  * @param {string} [args.tasksJsonPath] - Path to the tasks.json file (resolved by tool)
  * @param {boolean} [args.research=false] - Whether to use research capabilities for task creation
  * @param {string} [args.projectRoot] - Project root path
+ * @param {string} [args.tag] - Tag for the task (optional)
  * @param {Object} log - Logger object
  * @param {Object} context - Additional context (session)
  * @returns {Promise<Object>} - Result object { success: boolean, data?: any, error?: { code: string, message: string } }
@@ -36,7 +37,8 @@ export async function addTaskDirect(args, log, context = {}) {
 		dependencies,
 		priority,
 		research,
-		projectRoot
+		projectRoot,
+		tag
 	} = args;
 	const { session } = context; // Destructure session from context
 
@@ -121,12 +123,12 @@ export async function addTaskDirect(args, log, context = {}) {
 					mcpLog,
 					projectRoot,
 					commandName: 'add-task',
-					outputType: 'mcp'
+					outputType: 'mcp',
+					tag
 				},
 				'json', // outputFormat
 				manualTaskData, // Pass the manual task data
-				false, // research flag is false for manual creation
-				projectRoot // Pass projectRoot
+				false // research flag is false for manual creation
 			);
 			newTaskId = result.newTaskId;
 			telemetryData = result.telemetryData;
@@ -148,7 +150,8 @@ export async function addTaskDirect(args, log, context = {}) {
 					mcpLog,
 					projectRoot,
 					commandName: 'add-task',
-					outputType: 'mcp'
+					outputType: 'mcp',
+					tag
 				},
 				'json', // outputFormat
 				null, // manualTaskData is null for AI creation

mcp-server/src/core/direct-functions/analyze-task-complexity.js

@@ -22,6 +22,7 @@ import { createLogWrapper } from '../../tools/utils.js'; // Import the new utili
  * @param {number} [args.from] - Starting task ID in a range to analyze
  * @param {number} [args.to] - Ending task ID in a range to analyze
  * @param {string} [args.projectRoot] - Project root path.
+ * @param {string} [args.tag] - Tag for the task (optional)
  * @param {Object} log - Logger object
  * @param {Object} [context={}] - Context object containing session data
  * @param {Object} [context.session] - MCP session object
@@ -37,7 +38,8 @@ export async function analyzeTaskComplexityDirect(args, log, context = {}) {
 		projectRoot,
 		ids,
 		from,
-		to
+		to,
+		tag
 	} = args;
 
 	const logWrapper = createLogWrapper(log);
@@ -91,7 +93,8 @@ export async function analyzeTaskComplexityDirect(args, log, context = {}) {
 			projectRoot: projectRoot, // Pass projectRoot here
 			id: ids, // Pass the ids parameter to the core function as 'id'
 			from: from, // Pass from parameter
-			to: to // Pass to parameter
+			to: to, // Pass to parameter
+			tag // forward tag
 		};
 		// --- End Initial Checks ---
 
@@ -112,7 +115,9 @@ export async function analyzeTaskComplexityDirect(args, log, context = {}) {
 				session,
 				mcpLog: logWrapper,
 				commandName: 'analyze-complexity',
-				outputType: 'mcp'
+				outputType: 'mcp',
+				projectRoot,
+				tag
 			});
 			report = coreResult.report;
 		} catch (error) {

mcp-server/src/core/direct-functions/clear-subtasks.js

@@ -18,6 +18,7 @@ import path from 'path';
  * @param {string} [args.id] - Task IDs (comma-separated) to clear subtasks from
  * @param {boolean} [args.all] - Clear subtasks from all tasks
  * @param {string} [args.tag] - Tag context to operate on (defaults to current active tag)
+ * @param {string} [args.projectRoot] - Project root path (for MCP/env fallback)
  * @param {Object} log - Logger object
  * @returns {Promise<{success: boolean, data?: Object, error?: {code: string, message: string}}>}
  */
@@ -80,7 +81,7 @@ export async function clearSubtasksDirect(args, log) {
 			};
 		}
 
-		const currentTag = data.tag || 'master';
+		const currentTag = data.tag || tag;
 		const tasks = data.tasks;
 
 		// If all is specified, get all task IDs

mcp-server/src/core/direct-functions/expand-all-tasks.js

@@ -18,6 +18,7 @@ import { createLogWrapper } from '../../tools/utils.js';
  * @param {string} [args.prompt] - Additional context to guide subtask generation
  * @param {boolean} [args.force] - Force regeneration of subtasks for tasks that already have them
  * @param {string} [args.projectRoot] - Project root path.
+ * @param {string} [args.tag] - Tag for the task (optional)
  * @param {Object} log - Logger object from FastMCP
  * @param {Object} context - Context object containing session
  * @returns {Promise<{success: boolean, data?: Object, error?: {code: string, message: string}}>}
@@ -25,7 +26,8 @@ import { createLogWrapper } from '../../tools/utils.js';
 export async function expandAllTasksDirect(args, log, context = {}) {
 	const { session } = context; // Extract session
 	// Destructure expected args, including projectRoot
-	const { tasksJsonPath, num, research, prompt, force, projectRoot } = args;
+	const { tasksJsonPath, num, research, prompt, force, projectRoot, tag } =
+		args;
 
 	// Create logger wrapper using the utility
 	const mcpLog = createLogWrapper(log);
@@ -44,7 +46,7 @@ export async function expandAllTasksDirect(args, log, context = {}) {
 	enableSilentMode(); // Enable silent mode for the core function call
 	try {
 		log.info(
-			`Calling core expandAllTasks with args: ${JSON.stringify({ num, research, prompt, force, projectRoot })}`
+			`Calling core expandAllTasks with args: ${JSON.stringify({ num, research, prompt, force, projectRoot, tag })}`
 		);
 
 		// Parse parameters (ensure correct types)
@@ -60,7 +62,7 @@ export async function expandAllTasksDirect(args, log, context = {}) {
 			useResearch,
 			additionalContext,
 			forceFlag,
-			{ session, mcpLog, projectRoot },
+			{ session, mcpLog, projectRoot, tag },
 			'json'
 		);
 

mcp-server/src/core/direct-functions/expand-task.js

@@ -35,8 +35,17 @@ import { createLogWrapper } from '../../tools/utils.js';
 export async function expandTaskDirect(args, log, context = {}) {
 	const { session } = context; // Extract session
 	// Destructure expected args, including projectRoot
-	const { tasksJsonPath, id, num, research, prompt, force, projectRoot, tag } =
-		args;
+	const {
+		tasksJsonPath,
+		id,
+		num,
+		research,
+		prompt,
+		force,
+		projectRoot,
+		tag,
+		complexityReportPath
+	} = args;
 
 	// Log session root data for debugging
 	log.info(
@@ -192,6 +201,7 @@ export async function expandTaskDirect(args, log, context = {}) {
 				useResearch,
 				additionalContext,
 				{
+					complexityReportPath,
 					mcpLog,
 					session,
 					projectRoot,

mcp-server/src/core/direct-functions/fix-dependencies.js

@@ -53,10 +53,9 @@ export async function fixDependenciesDirect(args, log) {
 		// Enable silent mode to prevent console logs from interfering with JSON response
 		enableSilentMode();
 
+		const options = { projectRoot, tag };
 		// Call the original command function using the provided path and proper context
-		await fixDependenciesCommand(tasksPath, {
-			context: { projectRoot, tag }
-		});
+		await fixDependenciesCommand(tasksPath, options);
 
 		// Restore normal logging
 		disableSilentMode();

mcp-server/src/core/direct-functions/generate-task-files.js

@@ -13,12 +13,16 @@ import {
  * Direct function wrapper for generateTaskFiles with error handling.
  *
  * @param {Object} args - Command arguments containing tasksJsonPath and outputDir.
+ * @param {string} args.tasksJsonPath - Path to the tasks.json file.
+ * @param {string} args.outputDir - Path to the output directory.
+ * @param {string} args.projectRoot - Project root path (for MCP/env fallback)
+ * @param {string} args.tag - Tag for the task (optional)
  * @param {Object} log - Logger object.
  * @returns {Promise<Object>} - Result object with success status and data/error information.
  */
 export async function generateTaskFilesDirect(args, log) {
 	// Destructure expected args
-	const { tasksJsonPath, outputDir } = args;
+	const { tasksJsonPath, outputDir, projectRoot, tag } = args;
 	try {
 		log.info(`Generating task files with args: ${JSON.stringify(args)}`);
 
@@ -51,8 +55,12 @@ export async function generateTaskFilesDirect(args, log) {
 			// Enable silent mode to prevent logs from being written to stdout
 			enableSilentMode();
 
-			// The function is synchronous despite being awaited elsewhere
-			generateTaskFiles(tasksPath, resolvedOutputDir);
+			// Pass projectRoot and tag so the core respects context
+			generateTaskFiles(tasksPath, resolvedOutputDir, {
+				projectRoot,
+				tag,
+				mcpLog: log
+			});
 
 			// Restore normal logging after task generation
 			disableSilentMode();

mcp-server/src/core/direct-functions/list-tasks.js

@@ -13,12 +13,19 @@ import {
  * Direct function wrapper for listTasks with error handling and caching.
  *
  * @param {Object} args - Command arguments (now expecting tasksJsonPath explicitly).
+ * @param {string} args.tasksJsonPath - Path to the tasks.json file.
+ * @param {string} args.reportPath - Path to the report file.
+ * @param {string} args.status - Status of the task.
+ * @param {boolean} args.withSubtasks - Whether to include subtasks.
+ * @param {string} args.projectRoot - Project root path (for MCP/env fallback)
+ * @param {string} args.tag - Tag for the task (optional)
  * @param {Object} log - Logger object.
  * @returns {Promise<Object>} - Task list result { success: boolean, data?: any, error?: { code: string, message: string } }.
  */
 export async function listTasksDirect(args, log, context = {}) {
 	// Destructure the explicit tasksJsonPath from args
-	const { tasksJsonPath, reportPath, status, withSubtasks, projectRoot } = args;
+	const { tasksJsonPath, reportPath, status, withSubtasks, projectRoot, tag } =
+		args;
 	const { session } = context;
 
 	if (!tasksJsonPath) {
@@ -52,8 +59,7 @@ export async function listTasksDirect(args, log, context = {}) {
 				reportPath,
 				withSubtasksFilter,
 				'json',
-				null, // tag
-				{ projectRoot, session } // context
+				{ projectRoot, session, tag }
 			);
 
 			if (!resultData || !resultData.tasks) {

mcp-server/src/core/direct-functions/move-task.js

@@ -17,12 +17,14 @@ import {
  * @param {string} args.destinationId - ID of the destination (e.g., '7' or '7.3' or '7,8,9')
  * @param {string} args.file - Alternative path to the tasks.json file
  * @param {string} args.projectRoot - Project root directory
+ * @param {string} args.tag - Tag for the task (optional)
  * @param {boolean} args.generateFiles - Whether to regenerate task files after moving (default: true)
  * @param {Object} log - Logger object
  * @returns {Promise<{success: boolean, data?: Object, error?: Object}>}
  */
 export async function moveTaskDirect(args, log, context = {}) {
 	const { session } = context;
+	const { projectRoot, tag } = args;
 
 	// Validate required parameters
 	if (!args.sourceId) {
@@ -73,8 +75,8 @@ export async function moveTaskDirect(args, log, context = {}) {
 			args.destinationId,
 			generateFiles,
 			{
-				projectRoot: args.projectRoot,
-				tag: args.tag
+				projectRoot,
+				tag
 			}
 		);
 

mcp-server/src/core/direct-functions/next-task.js

@@ -18,12 +18,15 @@ import {
  *
  * @param {Object} args - Command arguments
  * @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
+ * @param {string} args.reportPath - Path to the report file.
+ * @param {string} args.projectRoot - Project root path (for MCP/env fallback)
+ * @param {string} args.tag - Tag for the task (optional)
  * @param {Object} log - Logger object
  * @returns {Promise<Object>} - Next task result { success: boolean, data?: any, error?: { code: string, message: string } }
  */
 export async function nextTaskDirect(args, log, context = {}) {
 	// Destructure expected args
-	const { tasksJsonPath, reportPath, projectRoot } = args;
+	const { tasksJsonPath, reportPath, projectRoot, tag } = args;
 	const { session } = context;
 
 	if (!tasksJsonPath) {
@@ -46,7 +49,7 @@ export async function nextTaskDirect(args, log, context = {}) {
 			log.info(`Finding next task from ${tasksJsonPath}`);
 
 			// Read tasks data using the provided path
-			const data = readJSON(tasksJsonPath, projectRoot);
+			const data = readJSON(tasksJsonPath, projectRoot, tag);
 			if (!data || !data.tasks) {
 				disableSilentMode(); // Disable before return
 				return {

mcp-server/src/core/direct-functions/parse-prd.js

@@ -20,6 +20,13 @@ import { TASKMASTER_TASKS_FILE } from '../../../../src/constants/paths.js';
  * Direct function wrapper for parsing PRD documents and generating tasks.
  *
  * @param {Object} args - Command arguments containing projectRoot, input, output, numTasks options.
+ * @param {string} args.input - Path to the input PRD file.
+ * @param {string} args.output - Path to the output directory.
+ * @param {string} args.numTasks - Number of tasks to generate.
+ * @param {boolean} args.force - Whether to force parsing.
+ * @param {boolean} args.append - Whether to append to the output file.
+ * @param {boolean} args.research - Whether to use research mode.
+ * @param {string} args.tag - Tag context for organizing tasks into separate task lists.
  * @param {Object} log - Logger object.
  * @param {Object} context - Context object containing session data.
  * @returns {Promise<Object>} - Result object with success status and data/error information.
@@ -34,7 +41,8 @@ export async function parsePRDDirect(args, log, context = {}) {
 		force,
 		append,
 		research,
-		projectRoot
+		projectRoot,
+		tag
 	} = args;
 
 	// Create the standard logger wrapper
@@ -152,6 +160,7 @@ export async function parsePRDDirect(args, log, context = {}) {
 				session,
 				mcpLog: logWrapper,
 				projectRoot,
+				tag,
 				force,
 				append,
 				research,

mcp-server/src/core/direct-functions/remove-dependency.js

@@ -14,12 +14,14 @@ import {
  * @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
  * @param {string|number} args.id - Task ID to remove dependency from
  * @param {string|number} args.dependsOn - Task ID to remove as a dependency
+ * @param {string} args.projectRoot - Project root path (for MCP/env fallback)
+ * @param {string} args.tag - Tag for the task (optional)
  * @param {Object} log - Logger object
  * @returns {Promise<{success: boolean, data?: Object, error?: {code: string, message: string}}>}
  */
 export async function removeDependencyDirect(args, log) {
 	// Destructure expected args
-	const { tasksJsonPath, id, dependsOn } = args;
+	const { tasksJsonPath, id, dependsOn, projectRoot, tag } = args;
 	try {
 		log.info(`Removing dependency with args: ${JSON.stringify(args)}`);
 
@@ -75,7 +77,10 @@ export async function removeDependencyDirect(args, log) {
 		enableSilentMode();
 
 		// Call the core function using the provided tasksPath
-		await removeDependency(tasksPath, taskId, dependencyId);
+		await removeDependency(tasksPath, taskId, dependencyId, {
+			projectRoot,
+			tag
+		});
 
 		// Restore normal logging
 		disableSilentMode();

mcp-server/src/core/direct-functions/remove-subtask.js

@@ -15,12 +15,14 @@ import {
  * @param {string} args.id - Subtask ID in format "parentId.subtaskId" (required)
  * @param {boolean} [args.convert] - Whether to convert the subtask to a standalone task
  * @param {boolean} [args.skipGenerate] - Skip regenerating task files
+ * @param {string} args.projectRoot - Project root path (for MCP/env fallback)
+ * @param {string} args.tag - Tag for the task (optional)
  * @param {Object} log - Logger object
  * @returns {Promise<{success: boolean, data?: Object, error?: {code: string, message: string}}>}
  */
 export async function removeSubtaskDirect(args, log) {
 	// Destructure expected args
-	const { tasksJsonPath, id, convert, skipGenerate } = args;
+	const { tasksJsonPath, id, convert, skipGenerate, projectRoot, tag } = args;
 	try {
 		// Enable silent mode to prevent console logs from interfering with JSON response
 		enableSilentMode();
@@ -82,7 +84,11 @@ export async function removeSubtaskDirect(args, log) {
 			tasksPath,
 			id,
 			convertToTask,
-			generateFiles
+			generateFiles,
+			{
+				projectRoot,
+				tag
+			}
 		);
 
 		// Restore normal logging

mcp-server/src/core/direct-functions/remove-task.js

@@ -20,7 +20,8 @@ import {
  * @param {Object} args - Command arguments
  * @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
  * @param {string} args.id - The ID(s) of the task(s) or subtask(s) to remove (comma-separated for multiple).
- * @param {string} [args.tag] - Tag context to operate on (defaults to current active tag).
+ * @param {string} args.projectRoot - Project root path (for MCP/env fallback)
+ * @param {string} args.tag - Tag for the task (optional)
  * @param {Object} log - Logger object
  * @returns {Promise<Object>} - Remove task result { success: boolean, data?: any, error?: { code: string, message: string } }
  */
@@ -117,7 +118,7 @@ export async function removeTaskDirect(args, log, context = {}) {
 					removedTasks: result.removedTasks,
 					message: result.message,
 					tasksPath: tasksJsonPath,
-					tag: data.tag || tag || 'master'
+					tag
 				}
 			};
 		} finally {

mcp-server/src/core/direct-functions/research.js

@@ -24,6 +24,7 @@ import { createLogWrapper } from '../../tools/utils.js';
  * @param {string} [args.saveTo] - Automatically save to task/subtask ID (e.g., "15" or "15.2")
  * @param {boolean} [args.saveToFile=false] - Save research results to .taskmaster/docs/research/ directory
  * @param {string} [args.projectRoot] - Project root path
+ * @param {string} [args.tag] - Tag for the task (optional)
  * @param {Object} log - Logger object
  * @param {Object} context - Additional context (session)
  * @returns {Promise<Object>} - Result object { success: boolean, data?: any, error?: { code: string, message: string } }
@@ -39,7 +40,8 @@ export async function researchDirect(args, log, context = {}) {
 		detailLevel = 'medium',
 		saveTo,
 		saveToFile = false,
-		projectRoot
+		projectRoot,
+		tag
 	} = args;
 	const { session } = context; // Destructure session from context
 
@@ -111,6 +113,7 @@ export async function researchDirect(args, log, context = {}) {
 			includeProjectTree,
 			detailLevel,
 			projectRoot,
+			tag,
 			saveToFile
 		};
 
@@ -169,7 +172,8 @@ ${result.result}`;
 							mcpLog,
 							commandName: 'research-save',
 							outputType: 'mcp',
-							projectRoot
+							projectRoot,
+							tag
 						},
 						'json'
 					);
@@ -200,7 +204,8 @@ ${result.result}`;
 							mcpLog,
 							commandName: 'research-save',
 							outputType: 'mcp',
-							projectRoot
+							projectRoot,
+							tag
 						},
 						'json',
 						true // appendMode = true

mcp-server/src/core/direct-functions/set-task-status.js

@@ -14,6 +14,11 @@ import { nextTaskDirect } from './next-task.js';
  * Direct function wrapper for setTaskStatus with error handling.
  *
  * @param {Object} args - Command arguments containing id, status, tasksJsonPath, and projectRoot.
+ * @param {string} args.id - The ID of the task to update.
+ * @param {string} args.status - The new status to set for the task.
+ * @param {string} args.tasksJsonPath - Path to the tasks.json file.
+ * @param {string} args.projectRoot - Project root path (for MCP/env fallback)
+ * @param {string} args.tag - Tag for the task (optional)
  * @param {Object} log - Logger object.
  * @param {Object} context - Additional context (session)
  * @returns {Promise<Object>} - Result object with success status and data/error information.
@@ -70,17 +75,12 @@ export async function setTaskStatusDirect(args, log, context = {}) {
 		enableSilentMode(); // Enable silent mode before calling core function
 		try {
 			// Call the core function
-			await setTaskStatus(
-				tasksPath,
-				taskId,
-				newStatus,
-				{
-					mcpLog: log,
-					projectRoot,
-					session
-				},
+			await setTaskStatus(tasksPath, taskId, newStatus, {
+				mcpLog: log,
+				projectRoot,
+				session,
 				tag
-			);
+			});
 
 			log.info(`Successfully set task ${taskId} status to ${newStatus}`);
 
@@ -103,7 +103,8 @@ export async function setTaskStatusDirect(args, log, context = {}) {
 						{
 							tasksJsonPath: tasksJsonPath,
 							reportPath: complexityReportPath,
-							projectRoot: projectRoot
+							projectRoot: projectRoot,
+							tag
 						},
 						log,
 						{ session }

mcp-server/src/core/direct-functions/show-task.js

@@ -19,6 +19,7 @@ import { findTasksPath } from '../utils/path-utils.js';
  * @param {string} args.reportPath - Explicit path to the complexity report file.
  * @param {string} [args.status] - Optional status to filter subtasks by.
  * @param {string} args.projectRoot - Absolute path to the project root directory (already normalized by tool).
+ * @param {string} [args.tag] - Tag for the task
  * @param {Object} log - Logger object.
  * @param {Object} context - Context object containing session data.
  * @returns {Promise<Object>} - Result object with success status and data/error information.
@@ -26,7 +27,7 @@ import { findTasksPath } from '../utils/path-utils.js';
 export async function showTaskDirect(args, log) {
 	// This function doesn't need session context since it only reads data
 	// Destructure projectRoot and other args. projectRoot is assumed normalized.
-	const { id, file, reportPath, status, projectRoot } = args;
+	const { id, file, reportPath, status, projectRoot, tag } = args;
 
 	log.info(
 		`Showing task direct function. ID: ${id}, File: ${file}, Status Filter: ${status}, ProjectRoot: ${projectRoot}`
@@ -55,7 +56,7 @@ export async function showTaskDirect(args, log) {
 
 	// --- Rest of the function remains the same, using tasksJsonPath ---
 	try {
-		const tasksData = readJSON(tasksJsonPath, projectRoot);
+		const tasksData = readJSON(tasksJsonPath, projectRoot, tag);
 		if (!tasksData || !tasksData.tasks) {
 			return {
 				success: false,

mcp-server/src/core/direct-functions/update-subtask-by-id.js

@@ -20,6 +20,7 @@ import { createLogWrapper } from '../../tools/utils.js';
  * @param {string} args.prompt - Information to append to the subtask.
  * @param {boolean} [args.research] - Whether to use research role.
  * @param {string} [args.projectRoot] - Project root path.
+ * @param {string} [args.tag] - Tag for the task (optional)
  * @param {Object} log - Logger object.
  * @param {Object} context - Context object containing session data.
  * @returns {Promise<Object>} - Result object with success status and data/error information.
@@ -27,7 +28,7 @@ import { createLogWrapper } from '../../tools/utils.js';
 export async function updateSubtaskByIdDirect(args, log, context = {}) {
 	const { session } = context;
 	// Destructure expected args, including projectRoot
-	const { tasksJsonPath, id, prompt, research, projectRoot } = args;
+	const { tasksJsonPath, id, prompt, research, projectRoot, tag } = args;
 
 	const logWrapper = createLogWrapper(log);
 
@@ -112,6 +113,7 @@ export async function updateSubtaskByIdDirect(args, log, context = {}) {
 					mcpLog: logWrapper,
 					session,
 					projectRoot,
+					tag,
 					commandName: 'update-subtask',
 					outputType: 'mcp'
 				},

mcp-server/src/core/direct-functions/update-task-by-id.js

@@ -21,6 +21,7 @@ import { createLogWrapper } from '../../tools/utils.js';
  * @param {boolean} [args.research] - Whether to use research role.
  * @param {boolean} [args.append] - Whether to append timestamped information instead of full update.
  * @param {string} [args.projectRoot] - Project root path.
+ * @param {string} [args.tag] - Tag for the task (optional)
  * @param {Object} log - Logger object.
  * @param {Object} context - Context object containing session data.
  * @returns {Promise<Object>} - Result object with success status and data/error information.
@@ -28,7 +29,8 @@ import { createLogWrapper } from '../../tools/utils.js';
 export async function updateTaskByIdDirect(args, log, context = {}) {
 	const { session } = context;
 	// Destructure expected args, including projectRoot
-	const { tasksJsonPath, id, prompt, research, append, projectRoot } = args;
+	const { tasksJsonPath, id, prompt, research, append, projectRoot, tag } =
+		args;
 
 	const logWrapper = createLogWrapper(log);
 
@@ -116,6 +118,7 @@ export async function updateTaskByIdDirect(args, log, context = {}) {
 					mcpLog: logWrapper,
 					session,
 					projectRoot,
+					tag,
 					commandName: 'update-task',
 					outputType: 'mcp'
 				},

mcp-server/src/core/direct-functions/update-tasks.js

@@ -15,6 +15,12 @@ import {
  * Direct function wrapper for updating tasks based on new context.
  *
  * @param {Object} args - Command arguments containing projectRoot, from, prompt, research options.
+ * @param {string} args.from - The ID of the task to update.
+ * @param {string} args.prompt - The prompt to update the task with.
+ * @param {boolean} args.research - Whether to use research mode.
+ * @param {string} args.tasksJsonPath - Path to the tasks.json file.
+ * @param {string} args.projectRoot - Project root path (for MCP/env fallback)
+ * @param {string} args.tag - Tag for the task (optional)
  * @param {Object} log - Logger object.
  * @param {Object} context - Context object containing session data.
  * @returns {Promise<Object>} - Result object with success status and data/error information.

mcp-server/src/core/direct-functions/validate-dependencies.js

@@ -13,12 +13,14 @@ import fs from 'fs';
  * Validate dependencies in tasks.json
  * @param {Object} args - Function arguments
  * @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
+ * @param {string} args.projectRoot - Project root path (for MCP/env fallback)
+ * @param {string} args.tag - Tag for the task (optional)
  * @param {Object} log - Logger object
  * @returns {Promise<{success: boolean, data?: Object, error?: {code: string, message: string}}>}
  */
 export async function validateDependenciesDirect(args, log) {
 	// Destructure the explicit tasksJsonPath
-	const { tasksJsonPath } = args;
+	const { tasksJsonPath, projectRoot, tag } = args;
 
 	if (!tasksJsonPath) {
 		log.error('validateDependenciesDirect called without tasksJsonPath');
@@ -51,8 +53,9 @@ export async function validateDependenciesDirect(args, log) {
 		// Enable silent mode to prevent console logs from interfering with JSON response
 		enableSilentMode();
 
+		const options = { projectRoot, tag };
 		// Call the original command function using the provided tasksPath
-		await validateDependenciesCommand(tasksPath);
+		await validateDependenciesCommand(tasksPath, options);
 
 		// Restore normal logging
 		disableSilentMode();

mcp-server/src/core/utils/path-utils.js

@@ -121,6 +121,7 @@ export function resolveComplexityReportPath(args, log = silentLogger) {
 	// Get explicit path from args.complexityReport if provided
 	const explicitPath = args?.complexityReport;
 	const rawProjectRoot = args?.projectRoot;
+	const tag = args?.tag;
 
 	// If explicit path is provided and absolute, use it directly
 	if (explicitPath && path.isAbsolute(explicitPath)) {
@@ -139,7 +140,11 @@ export function resolveComplexityReportPath(args, log = silentLogger) {
 
 	// Use core findComplexityReportPath with explicit path and normalized projectRoot context
 	if (projectRoot) {
-		return coreFindComplexityReportPath(explicitPath, { projectRoot }, log);
+		return coreFindComplexityReportPath(
+			explicitPath,
+			{ projectRoot, tag },
+			log
+		);
 	}
 
 	// Fallback to core function without projectRoot context

mcp-server/src/index.js

@@ -32,10 +32,6 @@ class TaskMasterMCPServer {
 		this.server = new FastMCP(this.options);
 		this.initialized = false;
 
-		this.server.addResource({});
-
-		this.server.addResourceTemplate({});
-
 		// Bind methods
 		this.init = this.init.bind(this);
 		this.start = this.start.bind(this);

mcp-server/src/tools/add-dependency.js

@@ -11,6 +11,7 @@ import {
 } from './utils.js';
 import { addDependencyDirect } from '../core/task-master-core.js';
 import { findTasksPath } from '../core/utils/path-utils.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 
 /**
  * Register the addDependency tool with the MCP server
@@ -33,14 +34,18 @@ export function registerAddDependencyTool(server) {
 				),
 			projectRoot: z
 				.string()
-				.describe('The directory of the project. Must be an absolute path.')
+				.describe('The directory of the project. Must be an absolute path.'),
+			tag: z.string().optional().describe('Tag context to operate on')
 		}),
 		execute: withNormalizedProjectRoot(async (args, { log, session }) => {
 			try {
 				log.info(
 					`Adding dependency for task ${args.id} to depend on ${args.dependsOn}`
 				);
-
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
 				let tasksJsonPath;
 				try {
 					tasksJsonPath = findTasksPath(
@@ -61,7 +66,9 @@ export function registerAddDependencyTool(server) {
 						tasksJsonPath: tasksJsonPath,
 						// Pass other relevant args
 						id: args.id,
-						dependsOn: args.dependsOn
+						dependsOn: args.dependsOn,
+						projectRoot: args.projectRoot,
+						tag: resolvedTag
 					},
 					log
 					// Remove context object

mcp-server/src/tools/add-subtask.js

@@ -11,6 +11,7 @@ import {
 } from './utils.js';
 import { addSubtaskDirect } from '../core/task-master-core.js';
 import { findTasksPath } from '../core/utils/path-utils.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 
 /**
  * Register the addSubtask tool with the MCP server
@@ -52,17 +53,21 @@ export function registerAddSubtaskTool(server) {
 				.describe(
 					'Absolute path to the tasks file (default: tasks/tasks.json)'
 				),
-			tag: z.string().optional().describe('Tag context to operate on'),
 			skipGenerate: z
 				.boolean()
 				.optional()
 				.describe('Skip regenerating task files'),
 			projectRoot: z
 				.string()
-				.describe('The directory of the project. Must be an absolute path.')
+				.describe('The directory of the project. Must be an absolute path.'),
+			tag: z.string().optional().describe('Tag context to operate on')
 		}),
 		execute: withNormalizedProjectRoot(async (args, { log, session }) => {
 			try {
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
 				log.info(`Adding subtask with args: ${JSON.stringify(args)}`);
 
 				// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
@@ -91,7 +96,7 @@ export function registerAddSubtaskTool(server) {
 						dependencies: args.dependencies,
 						skipGenerate: args.skipGenerate,
 						projectRoot: args.projectRoot,
-						tag: args.tag
+						tag: resolvedTag
 					},
 					log,
 					{ session }

mcp-server/src/tools/add-task.js

@@ -11,6 +11,7 @@ import {
 } from './utils.js';
 import { addTaskDirect } from '../core/task-master-core.js';
 import { findTasksPath } from '../core/utils/path-utils.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 
 /**
  * Register the addTask tool with the MCP server
@@ -58,6 +59,7 @@ export function registerAddTaskTool(server) {
 			projectRoot: z
 				.string()
 				.describe('The directory of the project. Must be an absolute path.'),
+			tag: z.string().optional().describe('Tag context to operate on'),
 			research: z
 				.boolean()
 				.optional()
@@ -67,6 +69,11 @@ export function registerAddTaskTool(server) {
 			try {
 				log.info(`Starting add-task with args: ${JSON.stringify(args)}`);
 
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
+
 				// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
 				let tasksJsonPath;
 				try {
@@ -93,7 +100,8 @@ export function registerAddTaskTool(server) {
 						dependencies: args.dependencies,
 						priority: args.priority,
 						research: args.research,
-						projectRoot: args.projectRoot
+						projectRoot: args.projectRoot,
+						tag: resolvedTag
 					},
 					log,
 					{ session }

mcp-server/src/tools/analyze.js

@@ -13,7 +13,9 @@ import {
 } from './utils.js';
 import { analyzeTaskComplexityDirect } from '../core/task-master-core.js'; // Assuming core functions are exported via task-master-core.js
 import { findTasksPath } from '../core/utils/path-utils.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 import { COMPLEXITY_REPORT_FILE } from '../../../src/constants/paths.js';
+import { resolveComplexityReportOutputPath } from '../../../src/utils/path-utils.js';
 
 /**
  * Register the analyze_project_complexity tool
@@ -70,15 +72,22 @@ export function registerAnalyzeProjectComplexityTool(server) {
 				.describe('Ending task ID in a range to analyze.'),
 			projectRoot: z
 				.string()
-				.describe('The directory of the project. Must be an absolute path.')
+				.describe('The directory of the project. Must be an absolute path.'),
+			tag: z.string().optional().describe('Tag context to operate on')
 		}),
 		execute: withNormalizedProjectRoot(async (args, { log, session }) => {
 			const toolName = 'analyze_project_complexity'; // Define tool name for logging
+
 			try {
 				log.info(
 					`Executing ${toolName} tool with args: ${JSON.stringify(args)}`
 				);
 
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
+
 				let tasksJsonPath;
 				try {
 					tasksJsonPath = findTasksPath(
@@ -93,9 +102,14 @@ export function registerAnalyzeProjectComplexityTool(server) {
 					);
 				}
 
-				const outputPath = args.output
-					? path.resolve(args.projectRoot, args.output)
-					: path.resolve(args.projectRoot, COMPLEXITY_REPORT_FILE);
+				const outputPath = resolveComplexityReportOutputPath(
+					args.output,
+					{
+						projectRoot: args.projectRoot,
+						tag: resolvedTag
+					},
+					log
+				);
 
 				log.info(`${toolName}: Report output path: ${outputPath}`);
 
@@ -123,6 +137,7 @@ export function registerAnalyzeProjectComplexityTool(server) {
 						threshold: args.threshold,
 						research: args.research,
 						projectRoot: args.projectRoot,
+						tag: resolvedTag,
 						ids: args.ids,
 						from: args.from,
 						to: args.to

mcp-server/src/tools/clear-subtasks.js

@@ -11,6 +11,7 @@ import {
 } from './utils.js';
 import { clearSubtasksDirect } from '../core/task-master-core.js';
 import { findTasksPath } from '../core/utils/path-utils.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 
 /**
  * Register the clearSubtasks tool with the MCP server
@@ -46,6 +47,11 @@ export function registerClearSubtasksTool(server) {
 			try {
 				log.info(`Clearing subtasks with args: ${JSON.stringify(args)}`);
 
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
+
 				// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
 				let tasksJsonPath;
 				try {
@@ -65,8 +71,9 @@ export function registerClearSubtasksTool(server) {
 						tasksJsonPath: tasksJsonPath,
 						id: args.id,
 						all: args.all,
+
 						projectRoot: args.projectRoot,
-						tag: args.tag || 'master'
+						tag: resolvedTag
 					},
 					log,
 					{ session }

mcp-server/src/tools/complexity-report.js

@@ -12,6 +12,7 @@ import {
 import { complexityReportDirect } from '../core/task-master-core.js';
 import { COMPLEXITY_REPORT_FILE } from '../../../src/constants/paths.js';
 import { findComplexityReportPath } from '../core/utils/path-utils.js';
+import { getCurrentTag } from '../../../scripts/modules/utils.js';
 
 /**
  * Register the complexityReport tool with the MCP server
@@ -38,12 +39,16 @@ export function registerComplexityReportTool(server) {
 					`Getting complexity report with args: ${JSON.stringify(args)}`
 				);
 
+				const resolvedTag = getCurrentTag(args.projectRoot);
+
 				const pathArgs = {
 					projectRoot: args.projectRoot,
-					complexityReport: args.file
+					complexityReport: args.file,
+					tag: resolvedTag
 				};
 
 				const reportPath = findComplexityReportPath(pathArgs, log);
+				log.info('Reading complexity report from path: ', reportPath);
 
 				if (!reportPath) {
 					return createErrorResponse(

mcp-server/src/tools/expand-all.js

@@ -11,6 +11,7 @@ import {
 } from './utils.js';
 import { expandAllTasksDirect } from '../core/task-master-core.js';
 import { findTasksPath } from '../core/utils/path-utils.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 
 /**
  * Register the expandAll tool with the MCP server
@@ -57,7 +58,8 @@ export function registerExpandAllTool(server) {
 				.optional()
 				.describe(
 					'Absolute path to the project root directory (derived from session if possible)'
-				)
+				),
+			tag: z.string().optional().describe('Tag context to operate on')
 		}),
 		execute: withNormalizedProjectRoot(async (args, { log, session }) => {
 			try {
@@ -65,6 +67,10 @@ export function registerExpandAllTool(server) {
 					`Tool expand_all execution started with args: ${JSON.stringify(args)}`
 				);
 
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
 				let tasksJsonPath;
 				try {
 					tasksJsonPath = findTasksPath(
@@ -86,7 +92,8 @@ export function registerExpandAllTool(server) {
 						research: args.research,
 						prompt: args.prompt,
 						force: args.force,
-						projectRoot: args.projectRoot
+						projectRoot: args.projectRoot,
+						tag: resolvedTag
 					},
 					log,
 					{ session }

mcp-server/src/tools/expand-task.js

@@ -10,7 +10,11 @@ import {
 	withNormalizedProjectRoot
 } from './utils.js';
 import { expandTaskDirect } from '../core/task-master-core.js';
-import { findTasksPath } from '../core/utils/path-utils.js';
+import {
+	findTasksPath,
+	findComplexityReportPath
+} from '../core/utils/path-utils.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 
 /**
  * Register the expand-task tool with the MCP server
@@ -51,7 +55,10 @@ export function registerExpandTaskTool(server) {
 		execute: withNormalizedProjectRoot(async (args, { log, session }) => {
 			try {
 				log.info(`Starting expand-task with args: ${JSON.stringify(args)}`);
-
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
 				// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
 				let tasksJsonPath;
 				try {
@@ -66,6 +73,11 @@ export function registerExpandTaskTool(server) {
 					);
 				}
 
+				const complexityReportPath = findComplexityReportPath(
+					{ ...args, tag: resolvedTag },
+					log
+				);
+
 				const result = await expandTaskDirect(
 					{
 						tasksJsonPath: tasksJsonPath,
@@ -74,8 +86,9 @@ export function registerExpandTaskTool(server) {
 						research: args.research,
 						prompt: args.prompt,
 						force: args.force,
+						complexityReportPath,
 						projectRoot: args.projectRoot,
-						tag: args.tag || 'master'
+						tag: resolvedTag
 					},
 					log,
 					{ session }

mcp-server/src/tools/fix-dependencies.js

@@ -11,7 +11,7 @@ import {
 } from './utils.js';
 import { fixDependenciesDirect } from '../core/task-master-core.js';
 import { findTasksPath } from '../core/utils/path-utils.js';
-
+import { resolveTag } from '../../../scripts/modules/utils.js';
 /**
  * Register the fixDependencies tool with the MCP server
  * @param {Object} server - FastMCP server instance
@@ -31,6 +31,11 @@ export function registerFixDependenciesTool(server) {
 			try {
 				log.info(`Fixing dependencies with args: ${JSON.stringify(args)}`);
 
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
+
 				// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
 				let tasksJsonPath;
 				try {
@@ -49,7 +54,7 @@ export function registerFixDependenciesTool(server) {
 					{
 						tasksJsonPath: tasksJsonPath,
 						projectRoot: args.projectRoot,
-						tag: args.tag
+						tag: resolvedTag
 					},
 					log
 				);

mcp-server/src/tools/generate.js

@@ -11,6 +11,7 @@ import {
 } from './utils.js';
 import { generateTaskFilesDirect } from '../core/task-master-core.js';
 import { findTasksPath } from '../core/utils/path-utils.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 import path from 'path';
 
 /**
@@ -30,12 +31,17 @@ export function registerGenerateTool(server) {
 				.describe('Output directory (default: same directory as tasks file)'),
 			projectRoot: z
 				.string()
-				.describe('The directory of the project. Must be an absolute path.')
+				.describe('The directory of the project. Must be an absolute path.'),
+			tag: z.string().optional().describe('Tag context to operate on')
 		}),
 		execute: withNormalizedProjectRoot(async (args, { log, session }) => {
 			try {
 				log.info(`Generating task files with args: ${JSON.stringify(args)}`);
 
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
 				// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
 				let tasksJsonPath;
 				try {
@@ -58,7 +64,8 @@ export function registerGenerateTool(server) {
 					{
 						tasksJsonPath: tasksJsonPath,
 						outputDir: outputDir,
-						projectRoot: args.projectRoot
+						projectRoot: args.projectRoot,
+						tag: resolvedTag
 					},
 					log,
 					{ session }

mcp-server/src/tools/get-task.js

@@ -14,6 +14,7 @@ import {
 	findTasksPath,
 	findComplexityReportPath
 } from '../core/utils/path-utils.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 
 /**
  * Custom processor function that removes allTasks from the response
@@ -67,7 +68,8 @@ export function registerShowTaskTool(server) {
 				.string()
 				.describe(
 					'Absolute path to the project root directory (Optional, usually from session)'
-				)
+				),
+			tag: z.string().optional().describe('Tag context to operate on')
 		}),
 		execute: withNormalizedProjectRoot(async (args, { log, session }) => {
 			const { id, file, status, projectRoot } = args;
@@ -76,6 +78,10 @@ export function registerShowTaskTool(server) {
 				log.info(
 					`Getting task details for ID: ${id}${status ? ` (filtering subtasks by status: ${status})` : ''} in root: ${projectRoot}`
 				);
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
 
 				// Resolve the path to tasks.json using the NORMALIZED projectRoot from args
 				let tasksJsonPath;
@@ -99,7 +105,8 @@ export function registerShowTaskTool(server) {
 					complexityReportPath = findComplexityReportPath(
 						{
 							projectRoot: projectRoot,
-							complexityReport: args.complexityReport
+							complexityReport: args.complexityReport,
+							tag: resolvedTag
 						},
 						log
 					);
@@ -113,7 +120,8 @@ export function registerShowTaskTool(server) {
 						// Pass other relevant args
 						id: id,
 						status: status,
-						projectRoot: projectRoot
+						projectRoot: projectRoot,
+						tag: resolvedTag
 					},
 					log,
 					{ session }

mcp-server/src/tools/get-tasks.js

@@ -15,6 +15,8 @@ import {
 	resolveComplexityReportPath
 } from '../core/utils/path-utils.js';
 
+import { resolveTag } from '../../../scripts/modules/utils.js';
+
 /**
  * Register the getTasks tool with the MCP server
  * @param {Object} server - FastMCP server instance
@@ -51,12 +53,17 @@ export function registerListTasksTool(server) {
 				),
 			projectRoot: z
 				.string()
-				.describe('The directory of the project. Must be an absolute path.')
+				.describe('The directory of the project. Must be an absolute path.'),
+			tag: z.string().optional().describe('Tag context to operate on')
 		}),
 		execute: withNormalizedProjectRoot(async (args, { log, session }) => {
 			try {
 				log.info(`Getting tasks with filters: ${JSON.stringify(args)}`);
 
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
 				// Resolve the path to tasks.json using new path utilities
 				let tasksJsonPath;
 				try {
@@ -71,7 +78,10 @@ export function registerListTasksTool(server) {
 				// Resolve the path to complexity report
 				let complexityReportPath;
 				try {
-					complexityReportPath = resolveComplexityReportPath(args, session);
+					complexityReportPath = resolveComplexityReportPath(
+						{ ...args, tag: resolvedTag },
+						session
+					);
 				} catch (error) {
 					log.error(`Error finding complexity report: ${error.message}`);
 					// This is optional, so we don't fail the operation
@@ -84,7 +94,8 @@ export function registerListTasksTool(server) {
 						status: args.status,
 						withSubtasks: args.withSubtasks,
 						reportPath: complexityReportPath,
-						projectRoot: args.projectRoot
+						projectRoot: args.projectRoot,
+						tag: resolvedTag
 					},
 					log,
 					{ session }

mcp-server/src/tools/move-task.js

@@ -11,6 +11,7 @@ import {
 } from './utils.js';
 import { moveTaskDirect } from '../core/task-master-core.js';
 import { findTasksPath } from '../core/utils/path-utils.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 
 /**
  * Register the moveTask tool with the MCP server
@@ -36,10 +37,15 @@ export function registerMoveTaskTool(server) {
 				.string()
 				.describe(
 					'Root directory of the project (typically derived from session)'
-				)
+				),
+			tag: z.string().optional().describe('Tag context to operate on')
 		}),
 		execute: withNormalizedProjectRoot(async (args, { log, session }) => {
 			try {
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
 				// Find tasks.json path if not provided
 				let tasksJsonPath = args.file;
 
@@ -79,7 +85,8 @@ export function registerMoveTaskTool(server) {
 								sourceId: fromId,
 								destinationId: toId,
 								tasksJsonPath,
-								projectRoot: args.projectRoot
+								projectRoot: args.projectRoot,
+								tag: resolvedTag
 							},
 							log,
 							{ session }
@@ -115,7 +122,8 @@ export function registerMoveTaskTool(server) {
 								sourceId: args.from,
 								destinationId: args.to,
 								tasksJsonPath,
-								projectRoot: args.projectRoot
+								projectRoot: args.projectRoot,
+								tag: resolvedTag
 							},
 							log,
 							{ session }

mcp-server/src/tools/next-task.js

@@ -14,6 +14,7 @@ import {
 	resolveTasksPath,
 	resolveComplexityReportPath
 } from '../core/utils/path-utils.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 
 /**
  * Register the nextTask tool with the MCP server
@@ -34,11 +35,16 @@ export function registerNextTaskTool(server) {
 				),
 			projectRoot: z
 				.string()
-				.describe('The directory of the project. Must be an absolute path.')
+				.describe('The directory of the project. Must be an absolute path.'),
+			tag: z.string().optional().describe('Tag context to operate on')
 		}),
 		execute: withNormalizedProjectRoot(async (args, { log, session }) => {
 			try {
 				log.info(`Finding next task with args: ${JSON.stringify(args)}`);
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
 
 				// Resolve the path to tasks.json using new path utilities
 				let tasksJsonPath;
@@ -54,7 +60,10 @@ export function registerNextTaskTool(server) {
 				// Resolve the path to complexity report (optional)
 				let complexityReportPath;
 				try {
-					complexityReportPath = resolveComplexityReportPath(args, session);
+					complexityReportPath = resolveComplexityReportPath(
+						{ ...args, tag: resolvedTag },
+						session
+					);
 				} catch (error) {
 					log.error(`Error finding complexity report: ${error.message}`);
 					// This is optional, so we don't fail the operation
@@ -65,7 +74,8 @@ export function registerNextTaskTool(server) {
 					{
 						tasksJsonPath: tasksJsonPath,
 						reportPath: complexityReportPath,
-						projectRoot: args.projectRoot
+						projectRoot: args.projectRoot,
+						tag: resolvedTag
 					},
 					log,
 					{ session }

mcp-server/src/tools/parse-prd.js

@@ -15,6 +15,7 @@ import {
 	TASKMASTER_DOCS_DIR,
 	TASKMASTER_TASKS_FILE
 } from '../../../src/constants/paths.js';
+import { resolveTag } from '../../../scripts/modules/utils.js';
 
 /**
  * Register the parse_prd tool
@@ -24,6 +25,7 @@ export function registerParsePRDTool(server) {
 	server.addTool({
 		name: 'parse_prd',
 		description: `Parse a Product Requirements Document (PRD) text file to automatically generate initial tasks. Reinitializing the project is not necessary to run this tool. It is recommended to run parse-prd after initializing the project and creating/importing a prd.txt file in the project root's ${TASKMASTER_DOCS_DIR} directory.`,
+
 		parameters: z.object({
 			input: z
 				.string()
@@ -33,6 +35,7 @@ export function registerParsePRDTool(server) {
 			projectRoot: z
 				.string()
 				.describe('The directory of the project. Must be an absolute path.'),
+			tag: z.string().optional().describe('Tag context to operate on'),
 			output: z
 				.string()
 				.optional()
@@ -63,7 +66,18 @@ export function registerParsePRDTool(server) {
 		}),
 		execute: withNormalizedProjectRoot(async (args, { log, session }) => {
 			try {
-				const result = await parsePRDDirect(args, log, { session });
+				const resolvedTag = resolveTag({
+					projectRoot: args.projectRoot,
+					tag: args.tag
+				});
+				const result = await parsePRDDirect(
+					{
+						...args,
+						tag: resolvedTag
+					},
+					log,
+					{ session }
+				);
 				return handleApiResult(
 					result,
 					log,