fix: update task by id

* add compatible platform api support

* Adjust the code according to the suggestions

* Fully revised as requested: restored all required checks, improved compatibility, and converted all comments to English.

* feat: Add support for compatible API endpoints via baseURL

* chore: Add changeset for compatible API support

* chore: cleanup

* chore: improve changeset

* fix: package-lock.json

* fix: package-lock.json

---------

Co-authored-by: He-Xun <1226807142@qq.com>

.changeset/bright-llamas-enter.md

@@ -0,0 +1,12 @@
+---
+"task-master-ai": patch
+---
+
+Fix expand command preserving tagged task structure and preventing data corruption
+
+- Enhance E2E tests with comprehensive tag-aware expand testing to verify tag corruption fix
+- Add new test section for feature-expand tag creation and testing during expand operations
+- Verify tag preservation during expand, force expand, and expand --all operations
+- Test that master tag remains intact while feature-expand tag receives subtasks correctly
+- Fix file path references to use correct .taskmaster/config.json and .taskmaster/tasks/tasks.json locations
+- All tag corruption verification tests pass successfully, confirming the expand command tag corruption bug fix works as expected

.changeset/huge-moose-prove.md

@@ -0,0 +1,8 @@
+---
+"task-master-ai": minor
+---
+
+Can now configure baseURL of provider with `<PROVIDER>_BASE_URL`
+
+- For example:
+  - `OPENAI_BASE_URL`

.changeset/lemon-deer-hide.md

@@ -0,0 +1,17 @@
+---
+'task-master-ai': minor
+---
+
+Added comprehensive rule profile management:
+
+**New Profile Support**: Added comprehensive IDE profile support with eight specialized profiles: Claude Code, Cline, Codex, Cursor, Roo, Trae, VS Code, and Windsurf. Each profile is optimized for its respective IDE with appropriate mappings and configuration.
+**Initialization**: You can now specify which rule profiles to include at project initialization using `--rules <profiles>` or `-r <profiles>` (e.g., `task-master init -r cursor,roo`). Only the selected profiles and configuration are included.
+**Add/Remove Commands**: `task-master rules add <profiles>` and `task-master rules remove <profiles>` let you manage specific rule profiles and MCP config after initialization, supporting multiple profiles at once.
+**Interactive Setup**: `task-master rules setup` launches an interactive prompt to select which rule profiles to add to your project. This does **not** re-initialize your project or affect shell aliases; it only manages rules.
+**Selective Removal**: Rules removal intelligently preserves existing non-Task Master rules and files and only removes Task Master-specific rules. Profile directories are only removed when completely empty and all conditions are met (no existing rules, no other files/folders, MCP config completely removed).
+**Safety Features**: Confirmation messages clearly explain that only Task Master-specific rules and MCP configurations will be removed, while preserving existing custom rules and other files.
+**Robust Validation**: Includes comprehensive checks for array types in MCP config processing and error handling throughout the rules management system.
+
+This enables more flexible, rule-specific project setups with intelligent cleanup that preserves user customizations while safely managing Task Master components.
+
+- Resolves #338

.changeset/modern-cats-pick.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Improves Amazon Bedrock support

.changeset/nasty-berries-tan.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Fix issues with task creation/update where subtasks are being created like id: <parent_task>.<subtask> instead if just id: <subtask>

.changeset/shy-groups-fly.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": minor
+---
+
+Add better support for python projects by adding `pyproject.toml` as a projectRoot marker

.changeset/spicy-teams-travel.md

@@ -0,0 +1,11 @@
+---
+"task-master-ai": patch
+---
+
+Improve provider validation system with clean constants structure
+
+- **Fixed "Invalid provider hint" errors**: Resolved validation failures for Azure, Vertex, and Bedrock providers
+- **Improved search UX**: Integrated search for better model discovery with real-time filtering
+- **Better organization**: Moved custom provider options to bottom of model selection with clear section separators
+
+This change ensures all custom providers (Azure, Vertex, Bedrock, OpenRouter, Ollama) work correctly in `task-master models --setup`

.changeset/stale-cameras-sin.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Fix weird `task-master init` bug when using in certain environments

.changeset/swift-squids-sip.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Rename Roo Code Boomerang role to Orchestrator

.changeset/tiny-dogs-change.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Improve mcp keys check in cursor

.changeset/wet-berries-dress.md

@@ -0,0 +1,22 @@
+---
+"task-master-ai": minor
+---
+
+Add Claude Code provider support
+
+Introduces a new provider that enables using Claude models (Opus and Sonnet) through the Claude Code CLI without requiring an API key. 
+
+Key features:
+- New claude-code provider with support for opus and sonnet models
+- No API key required - uses local Claude Code CLI installation
+- Optional dependency - won't affect users who don't need Claude Code
+- Lazy loading ensures the provider only loads when requested
+- Full integration with existing Task Master commands and workflows
+- Comprehensive test coverage for reliability
+- New --claude-code flag for the models command
+
+Users can now configure Claude Code models with:
+  task-master models --set-main sonnet --claude-code
+  task-master models --set-research opus --claude-code
+
+The @anthropic-ai/claude-code package is optional and won't be installed unless explicitly needed.

.cursor/mcp.json

@@ -12,7 +12,8 @@
 				"OPENROUTER_API_KEY": "OPENROUTER_API_KEY_HERE",
 				"MISTRAL_API_KEY": "MISTRAL_API_KEY_HERE",
 				"AZURE_OPENAI_API_KEY": "AZURE_OPENAI_API_KEY_HERE",
-				"OLLAMA_API_KEY": "OLLAMA_API_KEY_HERE"
+				"OLLAMA_API_KEY": "OLLAMA_API_KEY_HERE",
+				"GITHUB_API_KEY": "GITHUB_API_KEY_HERE"
 			}
 		}
 	}

.cursor/rules/architecture.mdc

@@ -20,19 +20,21 @@ alwaysApply: false
   - **[`task-manager.js`](mdc:scripts/modules/task-manager.js) & `task-manager/` directory: Task Data & Core Logic**
     - **Purpose**: Contains core functions for task data manipulation (CRUD), AI interactions, and related logic.
     - **Responsibilities**:
-      - Reading/writing `tasks.json`.
+      - Reading/writing `tasks.json` with tagged task lists support.
       - Implementing functions for task CRUD, parsing PRDs, expanding tasks, updating status, etc.
+      - **Tagged Task Lists**: Handles task organization across multiple contexts (tags) like "master", branch names, or project phases.
+      - **Tag Resolution**: Provides backward compatibility by resolving tagged format to legacy format transparently.
       - **Delegating AI interactions** to the `ai-services-unified.js` layer.
       - Accessing non-AI configuration via `config-manager.js` getters.
     - **Key Files**: Individual files within `scripts/modules/task-manager/` handle specific actions (e.g., `add-task.js`, `expand-task.js`).
 
   - **[`dependency-manager.js`](mdc:scripts/modules/dependency-manager.js): Dependency Management**
     - **Purpose**: Manages task dependencies.
-    - **Responsibilities**: Add/remove/validate/fix dependencies.
+    - **Responsibilities**: Add/remove/validate/fix dependencies across tagged task contexts.
 
   - **[`ui.js`](mdc:scripts/modules/ui.js): User Interface Components**
     - **Purpose**: Handles CLI output formatting (tables, colors, boxes, spinners).
-    - **Responsibilities**: Displaying tasks, reports, progress, suggestions.
+    - **Responsibilities**: Displaying tasks, reports, progress, suggestions, and migration notices for tagged systems.
 
   - **[`ai-services-unified.js`](mdc:scripts/modules/ai-services-unified.js): Unified AI Service Layer**
     - **Purpose**: Centralized interface for all LLM interactions using Vercel AI SDK.
@@ -53,6 +55,7 @@ alwaysApply: false
     - **Responsibilities** (See also: [`utilities.mdc`](mdc:.cursor/rules/utilities.mdc)):
       - Reads and merges `.taskmasterconfig` with defaults.
       - Provides getters (e.g., `getMainProvider`, `getLogLevel`, `getDefaultSubtasks`) for accessing settings.
+      - **Tag Configuration**: Manages `global.defaultTag` and `tags` section for tag system settings.
       - **Note**: Does **not** store or directly handle API keys (keys are in `.env` or MCP `session.env`).
 
   - **[`utils.js`](mdc:scripts/modules/utils.js): Core Utility Functions**
@@ -62,6 +65,8 @@ alwaysApply: false
       - Task utils (`findTaskById`), Dependency utils (`findCycles`).
       - API Key Resolution (`resolveEnvVariable`).
       - Silent Mode Control (`enableSilentMode`, `disableSilentMode`).
+      - **Tagged Task Lists**: Silent migration system, tag resolution, current tag management.
+      - **Migration System**: `performCompleteTagMigration`, `migrateConfigJson`, `createStateJson`.
 
   - **[`mcp-server/`](mdc:mcp-server/): MCP Server Integration**
     - **Purpose**: Provides MCP interface using FastMCP.
@@ -71,16 +76,42 @@ alwaysApply: false
       - Tool `execute` methods call **direct function wrappers** (`mcp-server/src/core/direct-functions/*.js`), passing the normalized `projectRoot` and other args.
       - Direct functions use path utilities (`mcp-server/src/core/utils/`) to resolve paths based on `projectRoot` from session.
       - Direct functions implement silent mode, logger wrappers, and call core logic functions from `scripts/modules/`.
+      - **Tagged Task Lists**: MCP tools fully support the tagged format with complete tag management capabilities.
       - Manages MCP caching and response formatting.
 
   - **[`init.js`](mdc:scripts/init.js): Project Initialization Logic**
     - **Purpose**: Sets up new Task Master project structure.
-    - **Responsibilities**: Creates directories, copies templates, manages `package.json`, sets up `.cursor/mcp.json`.
+    - **Responsibilities**: Creates directories, copies templates, manages `package.json`, sets up `.cursor/mcp.json`, initializes state.json for tagged system.
+
+## Tagged Task Lists System Architecture
+
+**Data Structure**: Task Master now uses a tagged task lists system where the `tasks.json` file contains multiple named task lists as top-level keys:
+
+```json
+{
+  "master": {
+    "tasks": [/* standard task objects */]
+  },
+  "feature-branch": {
+    "tasks": [/* separate task context */]
+  }
+}
+```
+
+**Key Components:**
+
+- **Silent Migration**: Automatically transforms legacy `{"tasks": [...]}` format to tagged format `{"master": {"tasks": [...]}}` on first read
+- **Tag Resolution Layer**: Provides 100% backward compatibility by intercepting tagged format and returning legacy format to existing code
+- **Configuration Integration**: `global.defaultTag` and `tags` section in config.json manage tag system settings
+- **State Management**: `.taskmaster/state.json` tracks current tag, migration status, and tag-branch mappings
+- **Migration Notice**: User-friendly notification system for seamless migration experience
+
+**Backward Compatibility**: All existing CLI commands and MCP tools continue to work unchanged. The tag resolution layer ensures that existing code receives the expected legacy format while the underlying storage uses the new tagged structure.
 
 - **Data Flow and Module Dependencies (Updated)**:
 
-  - **CLI**: `bin/task-master.js` -> `scripts/dev.js` (loads `.env`) -> `scripts/modules/commands.js` -> Core Logic (`scripts/modules/*`) -> Unified AI Service (`ai-services-unified.js`) -> Provider Adapters -> LLM API.
+  - **CLI**: `bin/task-master.js` -> `scripts/dev.js` (loads `.env`) -> `scripts/modules/commands.js` -> Core Logic (`scripts/modules/*`) -> **Tag Resolution Layer** -> Unified AI Service (`ai-services-unified.js`) -> Provider Adapters -> LLM API.
-  - **MCP**: External Tool -> `mcp-server/server.js` -> Tool (`mcp-server/src/tools/*`) -> Direct Function (`mcp-server/src/core/direct-functions/*`) -> Core Logic (`scripts/modules/*`) -> Unified AI Service (`ai-services-unified.js`) -> Provider Adapters -> LLM API.
+  - **MCP**: External Tool -> `mcp-server/server.js` -> Tool (`mcp-server/src/tools/*`) -> Direct Function (`mcp-server/src/core/direct-functions/*`) -> Core Logic (`scripts/modules/*`) -> **Tag Resolution Layer** -> Unified AI Service (`ai-services-unified.js`) -> Provider Adapters -> LLM API.
   - **Configuration**: Core logic needing non-AI settings calls `config-manager.js` getters (passing `session.env` via `explicitRoot` if from MCP). Unified AI Service internally calls `config-manager.js` getters (using `role`) for AI params and `utils.js` (`resolveEnvVariable` with `session.env`) for API keys.
 
 ## Silent Mode Implementation Pattern in MCP Direct Functions
@@ -197,6 +228,7 @@ By following these patterns consistently, direct functions will properly manage
     - **Integration Tests**: Located in `tests/integration/`, test interactions between modules
     - **End-to-End Tests**: Located in `tests/e2e/`, test complete workflows from a user perspective
     - **Test Fixtures**: Located in `tests/fixtures/`, provide reusable test data
+    - **Tagged System Tests**: Test migration, tag resolution, and multi-context functionality
 
   - **Module Design for Testability**:
     - **Explicit Dependencies**: Functions accept their dependencies as parameters rather than using globals
@@ -205,12 +237,14 @@ By following these patterns consistently, direct functions will properly manage
     - **Clear Module Interfaces**: Each module has well-defined exports that can be mocked in tests
     - **Callback Isolation**: Callbacks are defined as separate functions for easier testing
     - **Stateless Design**: Modules avoid maintaining internal state where possible
+    - **Tag Resolution Testing**: Test both tagged and legacy format handling
 
   - **Mock Integration Patterns**:
     - **External Libraries**: Libraries like `fs`, `commander`, and `@anthropic-ai/sdk` are mocked at module level
     - **Internal Modules**: Application modules are mocked with appropriate spy functions
     - **Testing Function Callbacks**: Callbacks are extracted from mock call arguments and tested in isolation
     - **UI Elements**: Output functions from `ui.js` are mocked to verify display calls
+    - **Tagged Data Mocking**: Test both legacy and tagged task data structures
 
   - **Testing Flow**:
     - Module dependencies are mocked (following Jest's hoisting behavior)
@@ -218,6 +252,7 @@ By following these patterns consistently, direct functions will properly manage
     - Spy functions are set up on module methods
     - Tests call the functions under test and verify behavior
     - Mocks are reset between test cases to maintain isolation
+    - Tagged system behavior is tested for both migration and normal operation
 
 - **Benefits of this Architecture**:
 
@@ -226,8 +261,11 @@ By following these patterns consistently, direct functions will properly manage
     - **Mocking Support**: The clear dependency boundaries make mocking straightforward
     - **Test Isolation**: Each component can be tested without affecting others
     - **Callback Testing**: Function callbacks can be extracted and tested independently
+    - **Multi-Context Testing**: Tagged system enables testing different task contexts independently
   - **Reusability**: Utility functions and UI components can be reused across different parts of the application.
   - **Scalability**:  New features can be added as new modules or by extending existing ones without significantly impacting other parts of the application.
+  - **Multi-Context Support**: Tagged task lists enable working across different contexts (branches, environments, phases) without conflicts.
+  - **Backward Compatibility**: Seamless migration and tag resolution ensure existing workflows continue unchanged.
   - **Clarity**: The modular structure provides a clear separation of concerns, making the codebase easier to navigate and understand for developers.
 
 This architectural overview should help AI models understand the structure and organization of the Task Master CLI codebase, enabling them to more effectively assist with code generation, modification, and understanding.
@@ -249,6 +287,7 @@ Follow these steps to add MCP support for an existing Task Master command (see [
         - Call core logic.
         - Return `{ success: true/false, data/error, fromCache: boolean }`.
     - Export the wrapper function.
+    - **Note**: Tag-aware MCP tools are fully implemented with complete tag management support.
 
 3.  **Update `task-master-core.js` with Import/Export**: Add imports/exports for the new `*Direct` function.
 
@@ -275,12 +314,8 @@ The `initialize_project` command provides a way to set up a new Task Master proj
 - **MCP Tool**: `initialize_project`
 - **Functionality**:
   - Creates necessary directories and files for a new project
-  - Sets up `tasks.json` and initial task files
+  - Sets up `tasks.json` with tagged structure and initial task files
-  - Configures project metadata (name, description, version)
-  - Handles shell alias creation if requested
-  - Works in both interactive and non-interactive modes
-  - Creates necessary directories and files for a new project
-  - Sets up `tasks.json` and initial task files
   - Configures project metadata (name, description, version)
+  - Initializes state.json for tag system
   - Handles shell alias creation if requested
   - Works in both interactive and non-interactive modes

.cursor/rules/commands.mdc

@@ -329,6 +329,60 @@ When implementing commands that delete or remove data (like `remove-task` or `re
   };
   ```
 
+## Context-Aware Command Pattern
+
+For AI-powered commands that benefit from project context, follow the research command pattern:
+
+- **Context Integration**:
+  - ✅ DO: Use `ContextGatherer` utility for multi-source context extraction
+  - ✅ DO: Support task IDs, file paths, custom context, and project tree
+  - ✅ DO: Implement fuzzy search for automatic task discovery
+  - ✅ DO: Display detailed token breakdown for transparency
+
+  ```javascript
+  // ✅ DO: Follow this pattern for context-aware commands
+  programInstance
+    .command('research')
+    .description('Perform AI-powered research queries with project context')
+    .argument('<prompt>', 'Research prompt to investigate')
+    .option('-i, --id <ids>', 'Comma-separated task/subtask IDs to include as context')
+    .option('-f, --files <paths>', 'Comma-separated file paths to include as context')
+    .option('-c, --context <text>', 'Additional custom context')
+    .option('--tree', 'Include project file tree structure')
+    .option('-d, --detail <level>', 'Output detail level: low, medium, high', 'medium')
+    .action(async (prompt, options) => {
+      // 1. Parameter validation and parsing
+      const taskIds = options.id ? parseTaskIds(options.id) : [];
+      const filePaths = options.files ? parseFilePaths(options.files) : [];
+      
+      // 2. Initialize context gatherer
+      const projectRoot = findProjectRoot() || '.';
+      const gatherer = new ContextGatherer(projectRoot, tasksPath);
+      
+      // 3. Auto-discover relevant tasks if none specified
+      if (taskIds.length === 0) {
+        const fuzzySearch = new FuzzyTaskSearch(tasksData.tasks, 'research');
+        const discoveredIds = fuzzySearch.getTaskIds(
+          fuzzySearch.findRelevantTasks(prompt)
+        );
+        taskIds.push(...discoveredIds);
+      }
+      
+      // 4. Gather context with token breakdown
+      const contextResult = await gatherer.gather({
+        tasks: taskIds,
+        files: filePaths,
+        customContext: options.context,
+        includeProjectTree: options.projectTree,
+        format: 'research',
+        includeTokenCounts: true
+      });
+      
+      // 5. Display token breakdown and execute AI call
+      // Implementation continues...
+    });
+  ```
+
 ## Error Handling
 
 - **Exception Management**:

.cursor/rules/context_gathering.mdc

@@ -0,0 +1,268 @@
+---
+description: Standardized patterns for gathering and processing context from multiple sources in Task Master commands, particularly for AI-powered features.
+globs: 
+alwaysApply: false
+---
+# Context Gathering Patterns and Utilities
+
+This document outlines the standardized patterns for gathering and processing context from multiple sources in Task Master commands, particularly for AI-powered features.
+
+## Core Context Gathering Utility
+
+The `ContextGatherer` class (`scripts/modules/utils/contextGatherer.js`) provides a centralized, reusable utility for extracting context from multiple sources:
+
+### **Key Features**
+- **Multi-source Context**: Tasks, files, custom text, project file tree
+- **Token Counting**: Detailed breakdown using `gpt-tokens` library
+- **Format Support**: Different output formats (research, chat, system-prompt)
+- **Error Handling**: Graceful handling of missing files, invalid task IDs
+- **Performance**: File size limits, depth limits for tree generation
+
+### **Usage Pattern**
+```javascript
+import { ContextGatherer } from '../utils/contextGatherer.js';
+
+// Initialize with project paths
+const gatherer = new ContextGatherer(projectRoot, tasksPath);
+
+// Gather context with detailed token breakdown
+const result = await gatherer.gather({
+    tasks: ['15', '16.2'],           // Task and subtask IDs
+    files: ['src/api.js', 'README.md'], // File paths
+    customContext: 'Additional context text',
+    includeProjectTree: true,        // Include file tree
+    format: 'research',              // Output format
+    includeTokenCounts: true         // Get detailed token breakdown
+});
+
+// Access results
+const contextString = result.context;
+const tokenBreakdown = result.tokenBreakdown;
+```
+
+### **Token Breakdown Structure**
+```javascript
+{
+    customContext: { tokens: 150, characters: 800 },
+    tasks: [
+        { id: '15', type: 'task', title: 'Task Title', tokens: 245, characters: 1200 },
+        { id: '16.2', type: 'subtask', title: 'Subtask Title', tokens: 180, characters: 900 }
+    ],
+    files: [
+        { path: 'src/api.js', tokens: 890, characters: 4500, size: '4.5 KB' }
+    ],
+    projectTree: { tokens: 320, characters: 1600 },
+    total: { tokens: 1785, characters: 8000 }
+}
+```
+
+## Fuzzy Search Integration
+
+The `FuzzyTaskSearch` class (`scripts/modules/utils/fuzzyTaskSearch.js`) provides intelligent task discovery:
+
+### **Key Features**
+- **Semantic Matching**: Uses Fuse.js for similarity scoring
+- **Purpose Categories**: Pattern-based task categorization
+- **Relevance Scoring**: High/medium/low relevance thresholds
+- **Context-Aware**: Different search configurations for different use cases
+
+### **Usage Pattern**
+```javascript
+import { FuzzyTaskSearch } from '../utils/fuzzyTaskSearch.js';
+
+// Initialize with tasks data and context
+const fuzzySearch = new FuzzyTaskSearch(tasksData.tasks, 'research');
+
+// Find relevant tasks
+const searchResults = fuzzySearch.findRelevantTasks(query, {
+    maxResults: 8,
+    includeRecent: true,
+    includeCategoryMatches: true
+});
+
+// Get task IDs for context gathering
+const taskIds = fuzzySearch.getTaskIds(searchResults);
+```
+
+## Implementation Patterns for Commands
+
+### **1. Context-Aware Command Structure**
+```javascript
+// In command action handler
+async function commandAction(prompt, options) {
+    // 1. Parameter validation and parsing
+    const taskIds = options.id ? parseTaskIds(options.id) : [];
+    const filePaths = options.files ? parseFilePaths(options.files) : [];
+    
+    // 2. Initialize context gatherer
+    const projectRoot = findProjectRoot() || '.';
+    const tasksPath = path.join(projectRoot, 'tasks', 'tasks.json');
+    const gatherer = new ContextGatherer(projectRoot, tasksPath);
+    
+    // 3. Auto-discover relevant tasks if none specified
+    if (taskIds.length === 0) {
+        const fuzzySearch = new FuzzyTaskSearch(tasksData.tasks, 'research');
+        const discoveredIds = fuzzySearch.getTaskIds(
+            fuzzySearch.findRelevantTasks(prompt)
+        );
+        taskIds.push(...discoveredIds);
+    }
+    
+    // 4. Gather context with token breakdown
+    const contextResult = await gatherer.gather({
+        tasks: taskIds,
+        files: filePaths,
+        customContext: options.context,
+        includeProjectTree: options.projectTree,
+        format: 'research',
+        includeTokenCounts: true
+    });
+    
+    // 5. Display token breakdown (for CLI)
+    if (outputFormat === 'text') {
+        displayDetailedTokenBreakdown(contextResult.tokenBreakdown);
+    }
+    
+    // 6. Use context in AI call
+    const aiResult = await generateTextService(role, session, systemPrompt, userPrompt);
+    
+    // 7. Display results with enhanced formatting
+    displayResults(aiResult, contextResult.tokenBreakdown);
+}
+```
+
+### **2. Token Display Pattern**
+```javascript
+function displayDetailedTokenBreakdown(tokenBreakdown, systemTokens, userTokens) {
+    const sections = [];
+    
+    // Build context breakdown
+    if (tokenBreakdown.tasks?.length > 0) {
+        const taskDetails = tokenBreakdown.tasks.map(task => 
+            `${task.type === 'subtask' ? '  ' : ''}${task.id}: ${task.tokens.toLocaleString()}`
+        ).join('\n');
+        sections.push(`Tasks (${tokenBreakdown.tasks.reduce((sum, t) => sum + t.tokens, 0).toLocaleString()}):\n${taskDetails}`);
+    }
+    
+    if (tokenBreakdown.files?.length > 0) {
+        const fileDetails = tokenBreakdown.files.map(file =>
+            `  ${file.path}: ${file.tokens.toLocaleString()} (${file.size})`
+        ).join('\n');
+        sections.push(`Files (${tokenBreakdown.files.reduce((sum, f) => sum + f.tokens, 0).toLocaleString()}):\n${fileDetails}`);
+    }
+    
+    // Add prompts breakdown
+    sections.push(`Prompts: system ${systemTokens.toLocaleString()}, user ${userTokens.toLocaleString()}`);
+    
+    // Display in clean box
+    const content = sections.join('\n\n');
+    console.log(boxen(content, {
+        title: chalk.cyan('Token Usage'),
+        padding: { top: 1, bottom: 1, left: 2, right: 2 },
+        borderStyle: 'round',
+        borderColor: 'cyan'
+    }));
+}
+```
+
+### **3. Enhanced Result Display Pattern**
+```javascript
+function displayResults(result, query, detailLevel, tokenBreakdown) {
+    // Header with query info
+    const header = boxen(
+        chalk.green.bold('Research Results') + '\n\n' +
+        chalk.gray('Query: ') + chalk.white(query) + '\n' +
+        chalk.gray('Detail Level: ') + chalk.cyan(detailLevel),
+        {
+            padding: { top: 1, bottom: 1, left: 2, right: 2 },
+            margin: { top: 1, bottom: 0 },
+            borderStyle: 'round',
+            borderColor: 'green'
+        }
+    );
+    console.log(header);
+    
+    // Process and highlight code blocks
+    const processedResult = processCodeBlocks(result);
+    
+    // Main content in clean box
+    const contentBox = boxen(processedResult, {
+        padding: { top: 1, bottom: 1, left: 2, right: 2 },
+        margin: { top: 0, bottom: 1 },
+        borderStyle: 'single',
+        borderColor: 'gray'
+    });
+    console.log(contentBox);
+    
+    console.log(chalk.green('✓ Research complete'));
+}
+```
+
+## Code Block Enhancement
+
+### **Syntax Highlighting Pattern**
+```javascript
+import { highlight } from 'cli-highlight';
+
+function processCodeBlocks(text) {
+    return text.replace(/```(\w+)?\n([\s\S]*?)```/g, (match, language, code) => {
+        try {
+            const highlighted = highlight(code.trim(), { 
+                language: language || 'javascript',
+                theme: 'default'
+            });
+            return `\n${highlighted}\n`;
+        } catch (error) {
+            return `\n${code.trim()}\n`;
+        }
+    });
+}
+```
+
+## Integration Guidelines
+
+### **When to Use Context Gathering**
+- ✅ **DO**: Use for AI-powered commands that benefit from project context
+- ✅ **DO**: Use when users might want to reference specific tasks or files
+- ✅ **DO**: Use for research, analysis, or generation commands
+- ❌ **DON'T**: Use for simple CRUD operations that don't need AI context
+
+### **Performance Considerations**
+- ✅ **DO**: Set reasonable file size limits (50KB default)
+- ✅ **DO**: Limit project tree depth (3-5 levels)
+- ✅ **DO**: Provide token counts to help users understand context size
+- ✅ **DO**: Allow users to control what context is included
+
+### **Error Handling**
+- ✅ **DO**: Gracefully handle missing files with warnings
+- ✅ **DO**: Validate task IDs and provide helpful error messages
+- ✅ **DO**: Continue processing even if some context sources fail
+- ✅ **DO**: Provide fallback behavior when context gathering fails
+
+### **Future Command Integration**
+Commands that should consider adopting this pattern:
+- `analyze-complexity` - Could benefit from file context
+- `expand-task` - Could use related task context
+- `update-task` - Could reference similar tasks for consistency
+- `add-task` - Could use project context for better task generation
+
+## Export Patterns
+
+### **Context Gatherer Module**
+```javascript
+export {
+    ContextGatherer,
+    createContextGatherer  // Factory function
+};
+```
+
+### **Fuzzy Search Module**
+```javascript
+export {
+    FuzzyTaskSearch,
+    PURPOSE_CATEGORIES,
+    RELEVANCE_THRESHOLDS
+};
+```
+
+This context gathering system provides a foundation for building more intelligent, context-aware commands that can leverage project knowledge to provide better AI-powered assistance.

.cursor/rules/dev_workflow.mdc

@@ -1,23 +1,205 @@
 ---
-description: Guide for using Task Master to manage task-driven development workflows
+description: Guide for using Taskmaster to manage task-driven development workflows
 globs: **/*
 alwaysApply: true
 ---
-# Task Master Development Workflow
 
-This guide outlines the typical process for using Task Master to manage software development projects.
+# Taskmaster Development Workflow
+
+This guide outlines the standard process for using Taskmaster to manage software development projects. It is written as a set of instructions for you, the AI agent.
+
+- **Your Default Stance**: For most projects, the user can work directly within the `master` task context. Your initial actions should operate on this default context unless a clear pattern for multi-context work emerges.
+- **Your Goal**: Your role is to elevate the user's workflow by intelligently introducing advanced features like **Tagged Task Lists** when you detect the appropriate context. Do not force tags on the user; suggest them as a helpful solution to a specific need.
+
+## The Basic Loop
+The fundamental development cycle you will facilitate is:
+1.  **`list`**: Show the user what needs to be done.
+2.  **`next`**: Help the user decide what to work on.
+3.  **`show <id>`**: Provide details for a specific task.
+4.  **`expand <id>`**: Break down a complex task into smaller, manageable subtasks.
+5.  **Implement**: The user writes the code and tests.
+6.  **`update-subtask`**: Log progress and findings on behalf of the user.
+7.  **`set-status`**: Mark tasks and subtasks as `done` as work is completed.
+8.  **Repeat**.
+
+All your standard command executions should operate on the user's current task context, which defaults to `master`.
+
+---
+
+## Standard Development Workflow Process
+
+### Simple Workflow (Default Starting Point)
+
+For new projects or when users are getting started, operate within the `master` tag context:
+
+-   Start new projects by running `initialize_project` tool / `task-master init` or `parse_prd` / `task-master parse-prd --input='<prd-file.txt>'` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to generate initial tasks.json with tagged structure
+-   Configure rule sets during initialization with `--rules` flag (e.g., `task-master init --rules cursor,windsurf`) or manage them later with `task-master rules add/remove` commands  
+-   Begin coding sessions with `get_tasks` / `task-master list` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to see current tasks, status, and IDs
+-   Determine the next task to work on using `next_task` / `task-master next` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc))
+-   Analyze task complexity with `analyze_project_complexity` / `task-master analyze-complexity --research` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) before breaking down tasks
+-   Review complexity report using `complexity_report` / `task-master complexity-report` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc))
+-   Select tasks based on dependencies (all marked 'done'), priority level, and ID order
+-   View specific task details using `get_task` / `task-master show <id>` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to understand implementation requirements
+-   Break down complex tasks using `expand_task` / `task-master expand --id=<id> --force --research` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) with appropriate flags like `--force` (to replace existing subtasks) and `--research`
+-   Implement code following task details, dependencies, and project standards
+-   Mark completed tasks with `set_task_status` / `task-master set-status --id=<id> --status=done` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc))
+-   Update dependent tasks when implementation differs from original plan using `update` / `task-master update --from=<id> --prompt="..."` or `update_task` / `task-master update-task --id=<id> --prompt="..."` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc))
+
+---
+
+## Leveling Up: Agent-Led Multi-Context Workflows
+
+While the basic workflow is powerful, your primary opportunity to add value is by identifying when to introduce **Tagged Task Lists**. These patterns are your tools for creating a more organized and efficient development environment for the user, especially if you detect agentic or parallel development happening across the same session.
+
+**Critical Principle**: Most users should never see a difference in their experience. Only introduce advanced workflows when you detect clear indicators that the project has evolved beyond simple task management.
+
+### When to Introduce Tags: Your Decision Patterns
+
+Here are the patterns to look for. When you detect one, you should propose the corresponding workflow to the user.
+
+#### Pattern 1: Simple Git Feature Branching
+This is the most common and direct use case for tags.
+
+- **Trigger**: The user creates a new git branch (e.g., `git checkout -b feature/user-auth`).
+- **Your Action**: Propose creating a new tag that mirrors the branch name to isolate the feature's tasks from `master`.
+- **Your Suggested Prompt**: *"I see you've created a new branch named 'feature/user-auth'. To keep all related tasks neatly organized and separate from your main list, I can create a corresponding task tag for you. This helps prevent merge conflicts in your `tasks.json` file later. Shall I create the 'feature-user-auth' tag?"*
+- **Tool to Use**: `task-master add-tag --from-branch`
+
+#### Pattern 2: Team Collaboration
+- **Trigger**: The user mentions working with teammates (e.g., "My teammate Alice is handling the database schema," or "I need to review Bob's work on the API.").
+- **Your Action**: Suggest creating a separate tag for the user's work to prevent conflicts with shared master context.
+- **Your Suggested Prompt**: *"Since you're working with Alice, I can create a separate task context for your work to avoid conflicts. This way, Alice can continue working with the master list while you have your own isolated context. When you're ready to merge your work, we can coordinate the tasks back to master. Shall I create a tag for your current work?"*
+- **Tool to Use**: `task-master add-tag my-work --copy-from-current --description="My tasks while collaborating with Alice"`
+
+#### Pattern 3: Experiments or Risky Refactors
+- **Trigger**: The user wants to try something that might not be kept (e.g., "I want to experiment with switching our state management library," or "Let's refactor the old API module, but I want to keep the current tasks as a reference.").
+- **Your Action**: Propose creating a sandboxed tag for the experimental work.
+- **Your Suggested Prompt**: *"This sounds like a great experiment. To keep these new tasks separate from our main plan, I can create a temporary 'experiment-zustand' tag for this work. If we decide not to proceed, we can simply delete the tag without affecting the main task list. Sound good?"*
+- **Tool to Use**: `task-master add-tag experiment-zustand --description="Exploring Zustand migration"`
+
+#### Pattern 4: Large Feature Initiatives (PRD-Driven)
+This is a more structured approach for significant new features or epics.
+
+- **Trigger**: The user describes a large, multi-step feature that would benefit from a formal plan.
+- **Your Action**: Propose a comprehensive, PRD-driven workflow.
+- **Your Suggested Prompt**: *"This sounds like a significant new feature. To manage this effectively, I suggest we create a dedicated task context for it. Here's the plan: I'll create a new tag called 'feature-xyz', then we can draft a Product Requirements Document (PRD) together to scope the work. Once the PRD is ready, I'll automatically generate all the necessary tasks within that new tag. How does that sound?"*
+- **Your Implementation Flow**:
+    1.  **Create an empty tag**: `task-master add-tag feature-xyz --description "Tasks for the new XYZ feature"`. You can also start by creating a git branch if applicable, and then create the tag from that branch.
+    2.  **Collaborate & Create PRD**: Work with the user to create a detailed PRD file (e.g., `.taskmaster/docs/feature-xyz-prd.txt`).
+    3.  **Parse PRD into the new tag**: `task-master parse-prd .taskmaster/docs/feature-xyz-prd.txt --tag feature-xyz`
+    4.  **Prepare the new task list**: Follow up by suggesting `analyze-complexity` and `expand-all` for the newly created tasks within the `feature-xyz` tag.
+
+#### Pattern 5: Version-Based Development
+Tailor your approach based on the project maturity indicated by tag names.
+
+- **Prototype/MVP Tags** (`prototype`, `mvp`, `poc`, `v0.x`):
+  - **Your Approach**: Focus on speed and functionality over perfection
+  - **Task Generation**: Create tasks that emphasize "get it working" over "get it perfect"
+  - **Complexity Level**: Lower complexity, fewer subtasks, more direct implementation paths
+  - **Research Prompts**: Include context like "This is a prototype - prioritize speed and basic functionality over optimization"
+  - **Example Prompt Addition**: *"Since this is for the MVP, I'll focus on tasks that get core functionality working quickly rather than over-engineering."*
+
+- **Production/Mature Tags** (`v1.0+`, `production`, `stable`):
+  - **Your Approach**: Emphasize robustness, testing, and maintainability
+  - **Task Generation**: Include comprehensive error handling, testing, documentation, and optimization
+  - **Complexity Level**: Higher complexity, more detailed subtasks, thorough implementation paths
+  - **Research Prompts**: Include context like "This is for production - prioritize reliability, performance, and maintainability"
+  - **Example Prompt Addition**: *"Since this is for production, I'll ensure tasks include proper error handling, testing, and documentation."*
+
+### Advanced Workflow (Tag-Based & PRD-Driven)
+
+**When to Transition**: Recognize when the project has evolved (or has initiated a project which existing code) beyond simple task management. Look for these indicators:
+- User mentions teammates or collaboration needs
+- Project has grown to 15+ tasks with mixed priorities
+- User creates feature branches or mentions major initiatives
+- User initializes Taskmaster on an existing, complex codebase
+- User describes large features that would benefit from dedicated planning
+
+**Your Role in Transition**: Guide the user to a more sophisticated workflow that leverages tags for organization and PRDs for comprehensive planning.
+
+#### Master List Strategy (High-Value Focus)
+Once you transition to tag-based workflows, the `master` tag should ideally contain only:
+- **High-level deliverables** that provide significant business value
+- **Major milestones** and epic-level features
+- **Critical infrastructure** work that affects the entire project
+- **Release-blocking** items
+
+**What NOT to put in master**:
+- Detailed implementation subtasks (these go in feature-specific tags' parent tasks)
+- Refactoring work (create dedicated tags like `refactor-auth`)
+- Experimental features (use `experiment-*` tags)
+- Team member-specific tasks (use person-specific tags)
+
+#### PRD-Driven Feature Development
+
+**For New Major Features**:
+1. **Identify the Initiative**: When user describes a significant feature
+2. **Create Dedicated Tag**: `add_tag feature-[name] --description="[Feature description]"`
+3. **Collaborative PRD Creation**: Work with user to create comprehensive PRD in `.taskmaster/docs/feature-[name]-prd.txt`
+4. **Parse & Prepare**: 
+   - `parse_prd .taskmaster/docs/feature-[name]-prd.txt --tag=feature-[name]`
+   - `analyze_project_complexity --tag=feature-[name] --research`
+   - `expand_all --tag=feature-[name] --research`
+5. **Add Master Reference**: Create a high-level task in `master` that references the feature tag
+
+**For Existing Codebase Analysis**:
+When users initialize Taskmaster on existing projects:
+1. **Codebase Discovery**: Use your native tools for producing deep context about the code base. You may use `research` tool with `--tree` and `--files` to collect up to date information using the existing architecture as context.
+2. **Collaborative Assessment**: Work with user to identify improvement areas, technical debt, or new features
+3. **Strategic PRD Creation**: Co-author PRDs that include:
+   - Current state analysis (based on your codebase research)
+   - Proposed improvements or new features
+   - Implementation strategy considering existing code
+4. **Tag-Based Organization**: Parse PRDs into appropriate tags (`refactor-api`, `feature-dashboard`, `tech-debt`, etc.)
+5. **Master List Curation**: Keep only the most valuable initiatives in master
+
+The parse-prd's `--append` flag enables the user to parse multple PRDs within tags or across tags. PRDs should be focused and the number of tasks they are parsed into should be strategically chosen relative to the PRD's complexity and level of detail.
+
+### Workflow Transition Examples
+
+**Example 1: Simple → Team-Based**
+```
+User: "Alice is going to help with the API work"
+Your Response: "Great! To avoid conflicts, I'll create a separate task context for your work. Alice can continue with the master list while you work in your own context. When you're ready to merge, we can coordinate the tasks back together."
+Action: add_tag my-api-work --copy-from-current --description="My API tasks while collaborating with Alice"
+```
+
+**Example 2: Simple → PRD-Driven**
+```
+User: "I want to add a complete user dashboard with analytics, user management, and reporting"
+Your Response: "This sounds like a major feature that would benefit from detailed planning. Let me create a dedicated context for this work and we can draft a PRD together to ensure we capture all requirements."
+Actions: 
+1. add_tag feature-dashboard --description="User dashboard with analytics and management"
+2. Collaborate on PRD creation
+3. parse_prd dashboard-prd.txt --tag=feature-dashboard
+4. Add high-level "User Dashboard" task to master
+```
+
+**Example 3: Existing Project → Strategic Planning**
+```
+User: "I just initialized Taskmaster on my existing React app. It's getting messy and I want to improve it."
+Your Response: "Let me research your codebase to understand the current architecture, then we can create a strategic plan for improvements."
+Actions:
+1. research "Current React app architecture and improvement opportunities" --tree --files=src/
+2. Collaborate on improvement PRD based on findings
+3. Create tags for different improvement areas (refactor-components, improve-state-management, etc.)
+4. Keep only major improvement initiatives in master
+```
+
+---
 
 ## Primary Interaction: MCP Server vs. CLI
 
-Task Master offers two primary ways to interact:
+Taskmaster offers two primary ways to interact:
 
 1.  **MCP Server (Recommended for Integrated Tools)**:
     - For AI agents and integrated development environments (like Cursor), interacting via the **MCP server is the preferred method**.
-    - The MCP server exposes Task Master functionality through a set of tools (e.g., `get_tasks`, `add_subtask`).
+    - The MCP server exposes Taskmaster functionality through a set of tools (e.g., `get_tasks`, `add_subtask`).
     - This method offers better performance, structured data exchange, and richer error handling compared to CLI parsing.
     - Refer to [`mcp.mdc`](mdc:.cursor/rules/mcp.mdc) for details on the MCP architecture and available tools.
     - A comprehensive list and description of MCP tools and their corresponding CLI commands can be found in [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc).
     - **Restart the MCP server** if core logic in `scripts/modules` or MCP tool/direct function definitions change.
+    - **Note**: MCP tools fully support tagged task lists with complete tag management capabilities.
 
 2.  **`task-master` CLI (For Users & Fallback)**:
     - The global `task-master` command provides a user-friendly interface for direct terminal interaction.
@@ -25,30 +207,17 @@ Task Master offers two primary ways to interact:
     - Install globally with `npm install -g task-master-ai` or use locally via `npx task-master-ai ...`.
     - The CLI commands often mirror the MCP tools (e.g., `task-master list` corresponds to `get_tasks`).
     - Refer to [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc) for a detailed command reference.
+    - **Tagged Task Lists**: CLI fully supports the new tagged system with seamless migration.
 
-## Standard Development Workflow Process
+## How the Tag System Works (For Your Reference)
 
--   Start new projects by running `initialize_project` tool / `task-master init` or `parse_prd` / `task-master parse-prd --input='<prd-file.txt>'` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to generate initial tasks.json
+- **Data Structure**: Tasks are organized into separate contexts (tags) like "master", "feature-branch", or "v2.0".
--   Begin coding sessions with `get_tasks` / `task-master list` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to see current tasks, status, and IDs
+- **Silent Migration**: Existing projects automatically migrate to use a "master" tag with zero disruption.
--   Determine the next task to work on using `next_task` / `task-master next` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)).
+- **Context Isolation**: Tasks in different tags are completely separate. Changes in one tag do not affect any other tag.
--   Analyze task complexity with `analyze_project_complexity` / `task-master analyze-complexity --research` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) before breaking down tasks
+- **Manual Control**: The user is always in control. There is no automatic switching. You facilitate switching by using `use-tag <name>`.
--   Review complexity report using `complexity_report` / `task-master complexity-report` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)).
+- **Full CLI & MCP Support**: All tag management commands are available through both the CLI and MCP tools for you to use. Refer to [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc) for a full command list.
--   Select tasks based on dependencies (all marked 'done'), priority level, and ID order
+
--   Clarify tasks by checking task files in tasks/ directory or asking for user input
+---
--   View specific task details using `get_task` / `task-master show <id>` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to understand implementation requirements
--   Break down complex tasks using `expand_task` / `task-master expand --id=<id> --force --research` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) with appropriate flags like `--force` (to replace existing subtasks) and `--research`.
--   Clear existing subtasks if needed using `clear_subtasks` / `task-master clear-subtasks --id=<id>` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) before regenerating
--   Implement code following task details, dependencies, and project standards
--   Verify tasks according to test strategies before marking as complete (See [`tests.mdc`](mdc:.cursor/rules/tests.mdc))
--   Mark completed tasks with `set_task_status` / `task-master set-status --id=<id> --status=done` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc))
--   Update dependent tasks when implementation differs from original plan using `update` / `task-master update --from=<id> --prompt="..."` or `update_task` / `task-master update-task --id=<id> --prompt="..."` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc))
--   Add new tasks discovered during implementation using `add_task` / `task-master add-task --prompt="..." --research` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)).
--   Add new subtasks as needed using `add_subtask` / `task-master add-subtask --parent=<id> --title="..."` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)).
--   Append notes or details to subtasks using `update_subtask` / `task-master update-subtask --id=<subtaskId> --prompt='Add implementation notes here...\nMore details...'` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)).
--   Generate task files with `generate` / `task-master generate` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) after updating tasks.json
--   Maintain valid dependency structure with `add_dependency`/`remove_dependency` tools or `task-master add-dependency`/`remove-dependency` commands, `validate_dependencies` / `task-master validate-dependencies`, and `fix_dependencies` / `task-master fix-dependencies` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) when needed
--   Respect dependency chains and task priorities when selecting work
--   Report progress regularly using `get_tasks` / `task-master list`
 
 ## Task Complexity Analysis
 
@@ -103,12 +272,13 @@ Task Master offers two primary ways to interact:
 
 Taskmaster configuration is managed through two main mechanisms:
 
-1.  **`.taskmasterconfig` File (Primary):**
+1.  **`.taskmaster/config.json` File (Primary):**
     *   Located in the project root directory.
     *   Stores most configuration settings: AI model selections (main, research, fallback), parameters (max tokens, temperature), logging level, default subtasks/priority, project name, etc.
+    *   **Tagged System Settings**: Includes `global.defaultTag` (defaults to "master") and `tags` section for tag management configuration.
     *   **Managed via `task-master models --setup` command.** Do not edit manually unless you know what you are doing.
     *   **View/Set specific models via `task-master models` command or `models` MCP tool.**
-    *   Created automatically when you run `task-master models --setup` for the first time.
+    *   Created automatically when you run `task-master models --setup` for the first time or during tagged system migration.
 
 2.  **Environment Variables (`.env` / `mcp.json`):**
     *   Used **only** for sensitive API keys and specific endpoint URLs.
@@ -116,10 +286,26 @@ Taskmaster configuration is managed through two main mechanisms:
     *   For MCP/Cursor integration, configure these keys in the `env` section of `.cursor/mcp.json`.
     *   Available keys/variables: See `assets/env.example` or the Configuration section in the command reference (previously linked to `taskmaster.mdc`).
 
+3.  **`.taskmaster/state.json` File (Tagged System State):**
+    *   Tracks current tag context and migration status.
+    *   Automatically created during tagged system migration.
+    *   Contains: `currentTag`, `lastSwitched`, `migrationNoticeShown`.
+
 **Important:** Non-API key settings (like model selections, `MAX_TOKENS`, `TASKMASTER_LOG_LEVEL`) are **no longer configured via environment variables**. Use the `task-master models` command (or `--setup` for interactive configuration) or the `models` MCP tool.
 **If AI commands FAIL in MCP** verify that the API key for the selected provider is present in the `env` section of `.cursor/mcp.json`.
 **If AI commands FAIL in CLI** verify that the API key for the selected provider is present in the `.env` file in the root of the project.
 
+## Rules Management
+
+Taskmaster supports multiple AI coding assistant rule sets that can be configured during project initialization or managed afterward:
+
+- **Available Profiles**: Claude Code, Cline, Codex, Cursor, Roo Code, Trae, Windsurf (claude, cline, codex, cursor, roo, trae, windsurf)
+- **During Initialization**: Use `task-master init --rules cursor,windsurf` to specify which rule sets to include
+- **After Initialization**: Use `task-master rules add <profiles>` or `task-master rules remove <profiles>` to manage rule sets
+- **Interactive Setup**: Use `task-master rules setup` to launch an interactive prompt for selecting rule profiles
+- **Default Behavior**: If no `--rules` flag is specified during initialization, all available rule profiles are included
+- **Rule Structure**: Each profile creates its own directory (e.g., `.cursor/rules`, `.roo/rules`) with appropriate configuration files
+
 ## Determining the Next Task
 
 - Run `next_task` / `task-master next` to show the next task to work on.
@@ -154,6 +340,25 @@ Taskmaster configuration is managed through two main mechanisms:
 - Task files are automatically regenerated after dependency changes
 - Dependencies are visualized with status indicators in task listings and files
 
+## Task Reorganization
+
+- Use `move_task` / `task-master move --from=<id> --to=<id>` to move tasks or subtasks within the hierarchy
+- This command supports several use cases:
+  - Moving a standalone task to become a subtask (e.g., `--from=5 --to=7`)
+  - Moving a subtask to become a standalone task (e.g., `--from=5.2 --to=7`) 
+  - Moving a subtask to a different parent (e.g., `--from=5.2 --to=7.3`)
+  - Reordering subtasks within the same parent (e.g., `--from=5.2 --to=5.4`)
+  - Moving a task to a new, non-existent ID position (e.g., `--from=5 --to=25`)
+  - Moving multiple tasks at once using comma-separated IDs (e.g., `--from=10,11,12 --to=16,17,18`)
+- The system includes validation to prevent data loss:
+  - Allows moving to non-existent IDs by creating placeholder tasks
+  - Prevents moving to existing task IDs that have content (to avoid overwriting)
+  - Validates source tasks exist before attempting to move them
+- The system maintains proper parent-child relationships and dependency integrity
+- Task files are automatically regenerated after the move operation
+- This provides greater flexibility in organizing and refining your task structure as project understanding evolves
+- This is especially useful when dealing with potential merge conflicts arising from teams creating tasks on separate branches. Solve these conflicts very easily by moving your tasks and keeping theirs.
+
 ## Iterative Subtask Implementation
 
 Once a task has been broken down into subtasks using `expand_task` or similar methods, follow this iterative process for implementation:

.cursor/rules/git_workflow.mdc

@@ -0,0 +1,404 @@
+---
+description: Git workflow integrated with Task Master for feature development and collaboration
+globs: "**/*"
+alwaysApply: true
+---
+# Git Workflow with Task Master Integration
+
+## **Branch Strategy**
+
+### **Main Branch Protection**
+- **main** branch contains production-ready code
+- All feature development happens on task-specific branches
+- Direct commits to main are prohibited
+- All changes merge via Pull Requests
+
+### **Task Branch Naming**
+```bash
+# ✅ DO: Use consistent task branch naming
+task-001  # For Task 1
+task-004  # For Task 4
+task-015  # For Task 15
+
+# ❌ DON'T: Use inconsistent naming
+feature/user-auth
+fix-database-issue
+random-branch-name
+```
+
+## **Tagged Task Lists Integration**
+
+Task Master's **tagged task lists system** provides significant benefits for Git workflows:
+
+### **Multi-Context Development**
+- **Branch-Specific Tasks**: Each branch can have its own task context using tags
+- **Merge Conflict Prevention**: Tasks in different tags are completely isolated
+- **Context Switching**: Seamlessly switch between different development contexts
+- **Parallel Development**: Multiple team members can work on separate task contexts
+
+### **Migration and Compatibility**
+- **Seamless Migration**: Existing projects automatically migrate to use a "master" tag
+- **Zero Disruption**: All existing Git workflows continue unchanged
+- **Backward Compatibility**: Legacy projects work exactly as before
+
+### **Manual Git Integration**
+- **Manual Tag Creation**: Use `--from-branch` option to create tags from current git branch
+- **Manual Context Switching**: Explicitly switch tag contexts as needed for different branches
+- **Simplified Integration**: Focused on manual control rather than automatic workflows
+
+## **Workflow Overview**
+
+```mermaid
+flowchart TD
+    A[Start: On main branch] --> B[Pull latest changes]
+    B --> C[Create task branch<br/>git checkout -b task-XXX]
+    C --> D[Set task status: in-progress]
+    D --> E[Get task context & expand if needed<br/>Tasks automatically use current tag]
+    E --> F[Identify next subtask]
+    
+    F --> G[Set subtask: in-progress]
+    G --> H[Research & collect context<br/>update_subtask with findings]
+    H --> I[Implement subtask]
+    I --> J[Update subtask with completion]
+    J --> K[Set subtask: done]
+    K --> L[Git commit subtask]
+    
+    L --> M{More subtasks?}
+    M -->|Yes| F
+    M -->|No| N[Run final tests]
+    
+    N --> O[Commit tests if added]
+    O --> P[Push task branch]
+    P --> Q[Create Pull Request]
+    Q --> R[Human review & merge]
+    R --> S[Switch to main & pull]
+    S --> T[Delete task branch]
+    T --> U[Ready for next task]
+    
+    style A fill:#e1f5fe
+    style C fill:#f3e5f5
+    style G fill:#fff3e0
+    style L fill:#e8f5e8
+    style Q fill:#fce4ec
+    style R fill:#f1f8e9
+    style U fill:#e1f5fe
+```
+
+## **Complete Task Development Workflow**
+
+### **Phase 1: Task Preparation**
+```bash
+# 1. Ensure you're on main branch and pull latest
+git checkout main
+git pull origin main
+
+# 2. Check current branch status
+git branch  # Verify you're on main
+
+# 3. Create task-specific branch
+git checkout -b task-004  # For Task 4
+
+# 4. Set task status in Task Master (tasks automatically use current tag context)
+# Use: set_task_status tool or `task-master set-status --id=4 --status=in-progress`
+```
+
+### **Phase 2: Task Analysis & Planning**
+```bash
+# 5. Get task context and expand if needed (uses current tag automatically)
+# Use: get_task tool or `task-master show 4`
+# Use: expand_task tool or `task-master expand --id=4 --research --force` (if complex)
+
+# 6. Identify next subtask to work on
+# Use: next_task tool or `task-master next`
+```
+
+### **Phase 3: Subtask Implementation Loop**
+For each subtask, follow this pattern:
+
+```bash
+# 7. Mark subtask as in-progress
+# Use: set_task_status tool or `task-master set-status --id=4.1 --status=in-progress`
+
+# 8. Gather context and research (if needed)
+# Use: update_subtask tool with research flag or:
+# `task-master update-subtask --id=4.1 --prompt="Research findings..." --research`
+
+# 9. Collect code context through AI exploration
+# Document findings in subtask using update_subtask
+
+# 10. Implement the subtask
+# Write code, tests, documentation
+
+# 11. Update subtask with completion details
+# Use: update_subtask tool or:
+# `task-master update-subtask --id=4.1 --prompt="Implementation complete..."`
+
+# 12. Mark subtask as done
+# Use: set_task_status tool or `task-master set-status --id=4.1 --status=done`
+
+# 13. Commit the subtask implementation
+git add .
+git commit -m "feat(task-4): Complete subtask 4.1 - [Subtask Title]
+
+- Implementation details
+- Key changes made
+- Any important notes
+
+Subtask 4.1: [Brief description of what was accomplished]
+Relates to Task 4: [Main task title]"
+```
+
+### **Phase 4: Task Completion**
+```bash
+# 14. When all subtasks are complete, run final testing
+# Create test file if needed, ensure all tests pass
+npm test  # or jest, or manual testing
+
+# 15. If tests were added/modified, commit them
+git add .
+git commit -m "test(task-4): Add comprehensive tests for Task 4
+
+- Unit tests for core functionality
+- Integration tests for API endpoints
+- All tests passing
+
+Task 4: [Main task title] - Testing complete"
+
+# 16. Push the task branch
+git push origin task-004
+
+# 17. Create Pull Request
+# Title: "Task 4: [Task Title]"
+# Description should include:
+# - Task overview
+# - Subtasks completed
+# - Testing approach
+# - Any breaking changes or considerations
+```
+
+### **Phase 5: PR Merge & Cleanup**
+```bash
+# 18. Human reviews and merges PR into main
+
+# 19. Switch back to main and pull merged changes
+git checkout main
+git pull origin main
+
+# 20. Delete the feature branch (optional cleanup)
+git branch -d task-004
+git push origin --delete task-004
+```
+
+## **Commit Message Standards**
+
+### **Subtask Commits**
+```bash
+# ✅ DO: Consistent subtask commit format
+git commit -m "feat(task-4): Complete subtask 4.1 - Initialize Express server
+
+- Set up Express.js with TypeScript configuration
+- Added CORS and body parsing middleware
+- Implemented health check endpoints
+- Basic error handling middleware
+
+Subtask 4.1: Initialize project with npm and install dependencies
+Relates to Task 4: Setup Express.js Server Project"
+
+# ❌ DON'T: Vague or inconsistent commits
+git commit -m "fixed stuff"
+git commit -m "working on task"
+```
+
+### **Test Commits**
+```bash
+# ✅ DO: Separate test commits when substantial
+git commit -m "test(task-4): Add comprehensive tests for Express server setup
+
+- Unit tests for middleware configuration
+- Integration tests for health check endpoints
+- Mock tests for database connection
+- All tests passing with 95% coverage
+
+Task 4: Setup Express.js Server Project - Testing complete"
+```
+
+### **Commit Type Prefixes**
+- `feat(task-X):` - New feature implementation
+- `fix(task-X):` - Bug fixes
+- `test(task-X):` - Test additions/modifications
+- `docs(task-X):` - Documentation updates
+- `refactor(task-X):` - Code refactoring
+- `chore(task-X):` - Build/tooling changes
+
+## **Task Master Commands Integration**
+
+### **Essential Commands for Git Workflow**
+```bash
+# Task management (uses current tag context automatically)
+task-master show <id>           # Get task/subtask details
+task-master next                # Find next task to work on
+task-master set-status --id=<id> --status=<status>
+task-master update-subtask --id=<id> --prompt="..." --research
+
+# Task expansion (for complex tasks)
+task-master expand --id=<id> --research --force
+
+# Progress tracking
+task-master list                # View all tasks and status
+task-master list --status=in-progress  # View active tasks
+```
+
+### **MCP Tool Equivalents**
+When using Cursor or other MCP-integrated tools:
+- `get_task` instead of `task-master show`
+- `next_task` instead of `task-master next`
+- `set_task_status` instead of `task-master set-status`
+- `update_subtask` instead of `task-master update-subtask`
+
+## **Branch Management Rules**
+
+### **Branch Protection**
+```bash
+# ✅ DO: Always work on task branches
+git checkout -b task-005
+# Make changes
+git commit -m "..."
+git push origin task-005
+
+# ❌ DON'T: Commit directly to main
+git checkout main
+git commit -m "..."  # NEVER do this
+```
+
+### **Keeping Branches Updated**
+```bash
+# ✅ DO: Regularly sync with main (for long-running tasks)
+git checkout task-005
+git fetch origin
+git rebase origin/main  # or merge if preferred
+
+# Resolve any conflicts and continue
+```
+
+## **Pull Request Guidelines**
+
+### **PR Title Format**
+```
+Task <ID>: <Task Title>
+
+Examples:
+Task 4: Setup Express.js Server Project
+Task 7: Implement User Authentication
+Task 12: Add Stripe Payment Integration
+```
+
+### **PR Description Template**
+```markdown
+## Task Overview
+Brief description of the main task objective.
+
+## Subtasks Completed
+- [x] 4.1: Initialize project with npm and install dependencies
+- [x] 4.2: Configure TypeScript, ESLint and Prettier  
+- [x] 4.3: Create basic Express app with middleware and health check route
+
+## Implementation Details
+- Key architectural decisions made
+- Important code changes
+- Any deviations from original plan
+
+## Testing
+- [ ] Unit tests added/updated
+- [ ] Integration tests passing
+- [ ] Manual testing completed
+
+## Breaking Changes
+List any breaking changes or migration requirements.
+
+## Related Tasks
+Mention any dependent tasks or follow-up work needed.
+```
+
+## **Conflict Resolution**
+
+### **Task Conflicts with Tagged System**
+```bash
+# With tagged task lists, merge conflicts are significantly reduced:
+# 1. Different branches can use different tag contexts
+# 2. Tasks in separate tags are completely isolated
+# 3. Use Task Master's move functionality to reorganize if needed
+
+# Manual git integration available:
+# - Use `task-master add-tag --from-branch` to create tags from current branch
+# - Manually switch contexts with `task-master use-tag <name>`
+# - Simple, predictable workflow without automatic behavior
+```
+
+### **Code Conflicts**
+```bash
+# Standard Git conflict resolution
+git fetch origin
+git rebase origin/main
+# Resolve conflicts in files
+git add .
+git rebase --continue
+```
+
+## **Emergency Procedures**
+
+### **Hotfixes**
+```bash
+# For urgent production fixes:
+git checkout main
+git pull origin main
+git checkout -b hotfix-urgent-issue
+
+# Make minimal fix
+git commit -m "hotfix: Fix critical production issue
+
+- Specific fix description
+- Minimal impact change
+- Requires immediate deployment"
+
+git push origin hotfix-urgent-issue
+# Create emergency PR for immediate review
+```
+
+### **Task Abandonment**
+```bash
+# If task needs to be abandoned or significantly changed:
+# 1. Update task status
+task-master set-status --id=<id> --status=cancelled
+
+# 2. Clean up branch
+git checkout main
+git branch -D task-<id>
+git push origin --delete task-<id>
+
+# 3. Document reasoning in task
+task-master update-task --id=<id> --prompt="Task cancelled due to..."
+```
+
+## **Tagged System Benefits for Git Workflows**
+
+### **Multi-Team Development**
+- **Isolated Contexts**: Different teams can work on separate tag contexts without conflicts
+- **Feature Branches**: Each feature branch can have its own task context
+- **Release Management**: Separate tags for different release versions or environments
+
+### **Merge Conflict Prevention**
+- **Context Separation**: Tasks in different tags don't interfere with each other
+- **Clean Merges**: Reduced likelihood of task-related merge conflicts
+- **Parallel Development**: Multiple developers can work simultaneously without task conflicts
+
+### **Manual Git Integration**
+- **Branch-Based Tag Creation**: Use `--from-branch` option to create tags from current git branch
+- **Manual Context Management**: Explicitly switch tag contexts as needed
+- **Predictable Workflow**: Simple, manual control without automatic behavior
+
+---
+
+**References:**
+- [Task Master Workflow](mdc:.cursor/rules/dev_workflow.mdc)
+- [Architecture Guidelines](mdc:.cursor/rules/architecture.mdc)
+- [Task Master Commands](mdc:.cursor/rules/taskmaster.mdc)

.cursor/rules/glossary.mdc

@@ -7,20 +7,20 @@ alwaysApply: true
 
 This file provides a quick reference to the purpose of each rule file located in the `.cursor/rules` directory.
 
-- **[`architecture.mdc`](mdc:.cursor/rules/architecture.mdc)**: Describes the high-level architecture of the Task Master CLI application.
+- **[`architecture.mdc`](mdc:.cursor/rules/architecture.mdc)**: Describes the high-level architecture of the Task Master CLI application, including the new tagged task lists system.
 - **[`changeset.mdc`](mdc:.cursor/rules/changeset.mdc)**: Guidelines for using Changesets (npm run changeset) to manage versioning and changelogs.
 - **[`commands.mdc`](mdc:.cursor/rules/commands.mdc)**: Guidelines for implementing CLI commands using Commander.js.
 - **[`cursor_rules.mdc`](mdc:.cursor/rules/cursor_rules.mdc)**: Guidelines for creating and maintaining Cursor rules to ensure consistency and effectiveness.
-- **[`dependencies.mdc`](mdc:.cursor/rules/dependencies.mdc)**: Guidelines for managing task dependencies and relationships.
+- **[`dependencies.mdc`](mdc:.cursor/rules/dependencies.mdc)**: Guidelines for managing task dependencies and relationships across tagged task contexts.
-- **[`dev_workflow.mdc`](mdc:.cursor/rules/dev_workflow.mdc)**: Guide for using Task Master to manage task-driven development workflows.
+- **[`dev_workflow.mdc`](mdc:.cursor/rules/dev_workflow.mdc)**: Guide for using Task Master to manage task-driven development workflows with tagged task lists support.
 - **[`glossary.mdc`](mdc:.cursor/rules/glossary.mdc)**: This file; provides a glossary of other Cursor rules.
 - **[`mcp.mdc`](mdc:.cursor/rules/mcp.mdc)**: Guidelines for implementing and interacting with the Task Master MCP Server.
-- **[`new_features.mdc`](mdc:.cursor/rules/new_features.mdc)**: Guidelines for integrating new features into the Task Master CLI.
+- **[`new_features.mdc`](mdc:.cursor/rules/new_features.mdc)**: Guidelines for integrating new features into the Task Master CLI with tagged system considerations.
 - **[`self_improve.mdc`](mdc:.cursor/rules/self_improve.mdc)**: Guidelines for continuously improving Cursor rules based on emerging code patterns and best practices.
-- **[`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)**: Comprehensive reference for Taskmaster MCP tools and CLI commands.
+- **[`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)**: Comprehensive reference for Taskmaster MCP tools and CLI commands with tagged task lists information.
-- **[`tasks.mdc`](mdc:.cursor/rules/tasks.mdc)**: Guidelines for implementing task management operations.
+- **[`tasks.mdc`](mdc:.cursor/rules/tasks.mdc)**: Guidelines for implementing task management operations with tagged task lists system support.
 - **[`tests.mdc`](mdc:.cursor/rules/tests.mdc)**: Guidelines for implementing and maintaining tests for Task Master CLI.
 - **[`ui.mdc`](mdc:.cursor/rules/ui.mdc)**: Guidelines for implementing and maintaining user interface components.
-- **[`utilities.mdc`](mdc:.cursor/rules/utilities.mdc)**: Guidelines for implementing utility functions.
+- **[`utilities.mdc`](mdc:.cursor/rules/utilities.mdc)**: Guidelines for implementing utility functions including tagged task lists utilities.
 - **[`telemetry.mdc`](mdc:.cursor/rules/telemetry.mdc)**: Guidelines for integrating AI usage telemetry across Task Master.
 

.cursor/rules/new_features.mdc

@@ -24,17 +24,22 @@ alwaysApply: false
 The standard pattern for adding a feature follows this workflow:
 
 1. **Core Logic**: Implement the business logic in the appropriate module (e.g., [`task-manager.js`](mdc:scripts/modules/task-manager.js)).
-2. **AI Integration (If Applicable)**: 
+2. **Context Gathering (If Applicable)**: 
+   - For AI-powered commands that benefit from project context, use the standardized context gathering patterns from [`context_gathering.mdc`](mdc:.cursor/rules/context_gathering.mdc).
+   - Import `ContextGatherer` and `FuzzyTaskSearch` utilities for reusable context extraction.
+   - Support multiple context types: tasks, files, custom text, project tree.
+   - Implement detailed token breakdown display for transparency.
+3. **AI Integration (If Applicable)**: 
    - Import necessary service functions (e.g., `generateTextService`, `streamTextService`) from [`ai-services-unified.js`](mdc:scripts/modules/ai-services-unified.js).
    - Prepare parameters (`role`, `session`, `systemPrompt`, `prompt`).
    - Call the service function.
    - Handle the response (direct text or stream object).
    - **Important**: Prefer `generateTextService` for calls sending large context (like stringified JSON) where incremental display is not needed. See [`ai_services.mdc`](mdc:.cursor/rules/ai_services.mdc) for detailed usage patterns and cautions.
-3. **UI Components**: Add any display functions to [`ui.js`](mdc:scripts/modules/ui.js) following [`ui.mdc`](mdc:.cursor/rules/ui.mdc).
+4. **UI Components**: Add any display functions to [`ui.js`](mdc:scripts/modules/ui.js) following [`ui.mdc`](mdc:.cursor/rules/ui.mdc). Consider enhanced formatting with syntax highlighting for code blocks.
-4. **Command Integration**: Add the CLI command to [`commands.js`](mdc:scripts/modules/commands.js) following [`commands.mdc`](mdc:.cursor/rules/commands.mdc).
+5. **Command Integration**: Add the CLI command to [`commands.js`](mdc:scripts/modules/commands.js) following [`commands.mdc`](mdc:.cursor/rules/commands.mdc).
-5. **Testing**: Write tests for all components of the feature (following [`tests.mdc`](mdc:.cursor/rules/tests.mdc))
+6. **Testing**: Write tests for all components of the feature (following [`tests.mdc`](mdc:.cursor/rules/tests.mdc))
-6. **Configuration**: Update configuration settings or add new ones in [`config-manager.js`](mdc:scripts/modules/config-manager.js) and ensure getters/setters are appropriate. Update documentation in [`utilities.mdc`](mdc:.cursor/rules/utilities.mdc) and [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc). Update the `.taskmasterconfig` structure if needed.
+7. **Configuration**: Update configuration settings or add new ones in [`config-manager.js`](mdc:scripts/modules/config-manager.js) and ensure getters/setters are appropriate. Update documentation in [`utilities.mdc`](mdc:.cursor/rules/utilities.mdc) and [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc). Update the `.taskmasterconfig` structure if needed.
-7. **Documentation**: Update help text and documentation in [`dev_workflow.mdc`](mdc:.cursor/rules/dev_workflow.mdc) and [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc).
+8. **Documentation**: Update help text and documentation in [`dev_workflow.mdc`](mdc:.cursor/rules/dev_workflow.mdc) and [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc).
 
 ## Critical Checklist for New Features
 
@@ -629,3 +634,287 @@ When implementing project initialization commands:
      });
    }
    ```
+
+## Feature Planning
+
+- **Core Logic First**:
+  - ✅ DO: Implement core logic in `scripts/modules/` before CLI or MCP interfaces
+  - ✅ DO: Consider tagged task lists system compatibility from the start
+  - ✅ DO: Design functions to work with both legacy and tagged data formats
+  - ✅ DO: Use tag resolution functions (`getTasksForTag`, `setTasksForTag`) for task data access
+  - ❌ DON'T: Directly manipulate tagged data structure in new features
+
+  ```javascript
+  // ✅ DO: Design tagged-aware core functions
+  async function newFeatureCore(tasksPath, featureParams, options = {}) {
+    const tasksData = readJSON(tasksPath);
+    const currentTag = getCurrentTag() || 'master';
+    const tasks = getTasksForTag(tasksData, currentTag);
+    
+    // Perform feature logic on tasks array
+    const result = performFeatureLogic(tasks, featureParams);
+    
+    // Save back using tag resolution
+    setTasksForTag(tasksData, currentTag, tasks);
+    writeJSON(tasksPath, tasksData);
+    
+    return result;
+  }
+  ```
+
+- **Backward Compatibility**:
+  - ✅ DO: Ensure new features work with existing projects seamlessly
+  - ✅ DO: Test with both legacy and tagged task data formats
+  - ✅ DO: Support silent migration during feature usage
+  - ❌ DON'T: Break existing workflows when adding tagged system features
+
+## CLI Command Implementation
+
+- **Command Structure**:
+  - ✅ DO: Follow the established pattern in [`commands.js`](mdc:scripts/modules/commands.js)
+  - ✅ DO: Use Commander.js for argument parsing
+  - ✅ DO: Include comprehensive help text and examples
+  - ✅ DO: Support tagged task context awareness
+
+  ```javascript
+  // ✅ DO: Implement CLI commands with tagged system awareness
+  program
+    .command('new-feature')
+    .description('Description of the new feature with tagged task lists support')
+    .option('-t, --tag <tag>', 'Specify tag context (defaults to current tag)')
+    .option('-p, --param <value>', 'Feature-specific parameter')
+    .option('--force', 'Force operation without confirmation')
+    .action(async (options) => {
+      try {
+        const projectRoot = findProjectRoot();
+        if (!projectRoot) {
+          console.error('Not in a Task Master project directory');
+          process.exit(1);
+        }
+        
+        // Use specified tag or current tag
+        const targetTag = options.tag || getCurrentTag() || 'master';
+        
+        const result = await newFeatureCore(
+          path.join(projectRoot, '.taskmaster', 'tasks', 'tasks.json'),
+          { param: options.param },
+          { 
+            force: options.force,
+            targetTag: targetTag,
+            outputFormat: 'text'
+          }
+        );
+        
+        console.log('Feature executed successfully');
+      } catch (error) {
+        console.error(`Error: ${error.message}`);
+        process.exit(1);
+      }
+    });
+  ```
+
+- **Error Handling**:
+  - ✅ DO: Provide clear error messages for common failures
+  - ✅ DO: Handle tagged system migration errors gracefully
+  - ✅ DO: Include suggestion for resolution when possible
+  - ✅ DO: Exit with appropriate codes for scripting
+
+## MCP Tool Implementation
+
+- **Direct Function Pattern**:
+  - ✅ DO: Create direct function wrappers in `mcp-server/src/core/direct-functions/`
+  - ✅ DO: Follow silent mode patterns to prevent console output interference
+  - ✅ DO: Use `findTasksJsonPath` for consistent path resolution
+  - ✅ DO: Ensure tagged system compatibility
+
+  ```javascript
+  // ✅ DO: Implement MCP direct functions with tagged awareness
+  export async function newFeatureDirect(args, log, context = {}) {
+    try {
+      const tasksPath = findTasksJsonPath(args, log);
+      
+      // Enable silent mode for clean MCP responses
+      enableSilentMode();
+      
+      try {
+        const result = await newFeatureCore(
+          tasksPath,
+          { param: args.param },
+          { 
+            force: args.force,
+            targetTag: args.tag || 'master', // Support tag specification
+            mcpLog: log,
+            session: context.session,
+            outputFormat: 'json'
+          }
+        );
+        
+        return {
+          success: true,
+          data: result,
+          fromCache: false
+        };
+      } finally {
+        disableSilentMode();
+      }
+    } catch (error) {
+      log.error(`Error in newFeatureDirect: ${error.message}`);
+      return {
+        success: false,
+        error: { code: 'FEATURE_ERROR', message: error.message },
+        fromCache: false
+      };
+    }
+  }
+  ```
+
+- **Tool Registration**:
+  - ✅ DO: Create tool definitions in `mcp-server/src/tools/`
+  - ✅ DO: Use Zod for parameter validation
+  - ✅ DO: Include optional tag parameter for multi-context support
+  - ✅ DO: Follow established naming conventions
+
+  ```javascript
+  // ✅ DO: Register MCP tools with tagged system support
+  export function registerNewFeatureTool(server) {
+    server.addTool({
+      name: "new_feature",
+      description: "Description of the new feature with tagged task lists support",
+      inputSchema: z.object({
+        param: z.string().describe("Feature-specific parameter"),
+        tag: z.string().optional().describe("Target tag context (defaults to current tag)"),
+        force: z.boolean().optional().describe("Force operation without confirmation"),
+        projectRoot: z.string().optional().describe("Project root directory")
+      }),
+      execute: withNormalizedProjectRoot(async (args, { log, session }) => {
+        try {
+          const result = await newFeatureDirect(
+            { ...args, projectRoot: args.projectRoot },
+            log,
+            { session }
+          );
+          return handleApiResult(result, log);
+        } catch (error) {
+          return handleApiResult({
+            success: false,
+            error: { code: 'EXECUTION_ERROR', message: error.message }
+          }, log);
+        }
+      })
+    });
+  }
+  ```
+
+## Testing Strategy
+
+- **Unit Tests**:
+  - ✅ DO: Test core logic independently with both data formats
+  - ✅ DO: Mock file system operations appropriately
+  - ✅ DO: Test tag resolution behavior
+  - ✅ DO: Verify migration compatibility
+
+  ```javascript
+  // ✅ DO: Test new features with tagged system awareness
+  describe('newFeature', () => {
+    beforeEach(() => {
+      jest.clearAllMocks();
+    });
+    
+    it('should work with legacy task format', async () => {
+      const legacyData = { tasks: [/* test data */] };
+      fs.readFileSync.mockReturnValue(JSON.stringify(legacyData));
+      
+      const result = await newFeatureCore('/test/tasks.json', { param: 'test' });
+      
+      expect(result).toBeDefined();
+      // Test legacy format handling
+    });
+    
+    it('should work with tagged task format', async () => {
+      const taggedData = { 
+        master: { tasks: [/* test data */] },
+        feature: { tasks: [/* test data */] }
+      };
+      fs.readFileSync.mockReturnValue(JSON.stringify(taggedData));
+      
+      const result = await newFeatureCore('/test/tasks.json', { param: 'test' });
+      
+      expect(result).toBeDefined();
+      // Test tagged format handling
+    });
+    
+    it('should handle tag migration during feature usage', async () => {
+      const legacyData = { tasks: [/* test data */] };
+      fs.readFileSync.mockReturnValue(JSON.stringify(legacyData));
+      
+      await newFeatureCore('/test/tasks.json', { param: 'test' });
+      
+      // Verify migration occurred
+      expect(fs.writeFileSync).toHaveBeenCalledWith(
+        '/test/tasks.json',
+        expect.stringContaining('"master"')
+      );
+    });
+  });
+  ```
+
+- **Integration Tests**:
+  - ✅ DO: Test CLI and MCP interfaces with real task data
+  - ✅ DO: Verify end-to-end workflows across tag contexts
+  - ✅ DO: Test error scenarios and recovery
+
+## Documentation Updates
+
+- **Rule Updates**:
+  - ✅ DO: Update relevant `.cursor/rules/*.mdc` files
+  - ✅ DO: Include tagged system considerations in architecture docs
+  - ✅ DO: Add examples showing multi-context usage
+  - ✅ DO: Update workflow documentation as needed
+
+- **User Documentation**:
+  - ✅ DO: Add feature documentation to `/docs` folder
+  - ✅ DO: Include tagged system usage examples
+  - ✅ DO: Update command reference documentation
+  - ✅ DO: Provide migration notes if relevant
+
+## Migration Considerations
+
+- **Silent Migration Support**:
+  - ✅ DO: Ensure new features trigger migration when needed
+  - ✅ DO: Handle migration errors gracefully in feature code
+  - ✅ DO: Test feature behavior with pre-migration projects
+  - ❌ DON'T: Assume projects are already migrated
+
+- **Tag Context Handling**:
+  - ✅ DO: Default to current tag when not specified
+  - ✅ DO: Support explicit tag selection in advanced features
+  - ✅ DO: Validate tag existence before operations
+  - ✅ DO: Provide clear messaging about tag context
+
+## Performance Considerations
+
+- **Efficient Tag Operations**:
+  - ✅ DO: Minimize file I/O operations per feature execution
+  - ✅ DO: Cache tag resolution results when appropriate
+  - ✅ DO: Use streaming for large task datasets
+  - ❌ DON'T: Load all tags when only one is needed
+
+- **Memory Management**:
+  - ✅ DO: Process large task lists efficiently
+  - ✅ DO: Clean up temporary data structures
+  - ✅ DO: Avoid keeping all tag data in memory simultaneously
+
+## Deployment and Versioning
+
+- **Changesets**:
+  - ✅ DO: Create appropriate changesets for new features
+  - ✅ DO: Use semantic versioning (minor for new features)
+  - ✅ DO: Include tagged system information in release notes
+  - ✅ DO: Document breaking changes if any
+
+- **Feature Flags**:
+  - ✅ DO: Consider feature flags for experimental functionality
+  - ✅ DO: Ensure tagged system features work with flags
+  - ✅ DO: Provide clear documentation about flag usage
+
+By following these guidelines, new features will integrate smoothly with the Task Master ecosystem while supporting the enhanced tagged task lists system for multi-context development workflows.

.cursor/rules/tags.mdc

@@ -0,0 +1,229 @@
+---
+description: 
+globs: scripts/modules/*
+alwaysApply: false
+---
+# Tagged Task Lists Command Patterns
+
+This document outlines the standardized patterns that **ALL** Task Master commands must follow to properly support the tagged task lists system.
+
+## Core Principles
+
+- **Every command** that reads or writes tasks.json must be tag-aware
+- **Consistent tag resolution** across all commands using `getCurrentTag(projectRoot)`
+- **Proper context passing** to core functions with `{ projectRoot, tag }`
+- **Standardized CLI options** with `--tag <tag>` flag
+
+## Required Imports
+
+All command files must import `getCurrentTag`:
+
+```javascript
+// ✅ DO: Import getCurrentTag in commands.js
+import { 
+  log, 
+  readJSON, 
+  writeJSON, 
+  findProjectRoot, 
+  getCurrentTag 
+} from './utils.js';
+
+// ✅ DO: Import getCurrentTag in task-manager files
+import { 
+  readJSON, 
+  writeJSON, 
+  getCurrentTag 
+} from '../utils.js';
+```
+
+## CLI Command Pattern
+
+Every CLI command that operates on tasks must follow this exact pattern:
+
+```javascript
+// ✅ DO: Standard tag-aware CLI command pattern
+programInstance
+  .command('command-name')
+  .description('Command description')
+  .option('-f, --file <file>', 'Path to the tasks file', TASKMASTER_TASKS_FILE)
+  .option('--tag <tag>', 'Specify tag context for task operations') // REQUIRED
+  .action(async (options) => {
+    // 1. Find project root
+    const projectRoot = findProjectRoot();
+    if (!projectRoot) {
+      console.error(chalk.red('Error: Could not find project root.'));
+      process.exit(1);
+    }
+
+    // 2. Resolve tag using standard pattern
+    const tag = options.tag || getCurrentTag(projectRoot) || 'master';
+
+    // 3. Call core function with proper context
+    await coreFunction(
+      tasksPath,
+      // ... other parameters ...
+      { projectRoot, tag } // REQUIRED context object
+    );
+  });
+```
+
+## Core Function Pattern
+
+All core functions in `scripts/modules/task-manager/` must follow this pattern:
+
+```javascript
+// ✅ DO: Standard tag-aware core function pattern
+async function coreFunction(
+  tasksPath,
+  // ... other parameters ...
+  context = {} // REQUIRED context parameter
+) {
+  const { projectRoot, tag } = context;
+  
+  // Use tag-aware readJSON/writeJSON
+  const data = readJSON(tasksPath, projectRoot, tag);
+  
+  // ... function logic ...
+  
+  writeJSON(tasksPath, data, projectRoot, tag);
+}
+```
+
+## Tag Resolution Priority
+
+The tag resolution follows this exact priority order:
+
+1. **Explicit `--tag` flag**: `options.tag`
+2. **Current active tag**: `getCurrentTag(projectRoot)`  
+3. **Default fallback**: `'master'`
+
+```javascript
+// ✅ DO: Standard tag resolution pattern
+const tag = options.tag || getCurrentTag(projectRoot) || 'master';
+```
+
+## Commands Requiring Updates
+
+### High Priority (Core Task Operations)
+- [x] `add-task` - ✅ Fixed
+- [x] `list` - ✅ Fixed  
+- [x] `update-task` - ✅ Fixed
+- [x] `update-subtask` - ✅ Fixed
+- [x] `set-status` - ✅ Already correct
+- [x] `remove-task` - ✅ Already correct
+- [x] `remove-subtask` - ✅ Fixed
+- [x] `add-subtask` - ✅ Already correct
+- [x] `clear-subtasks` - ✅ Fixed
+- [x] `move-task` - ✅ Already correct
+
+### Medium Priority (Analysis & Expansion)
+- [x] `expand` - ✅ Fixed
+- [ ] `next` - ✅ Fixed
+- [ ] `show` (get-task) - Needs checking
+- [ ] `analyze-complexity` - Needs checking
+- [ ] `generate` - ✅ Fixed
+
+### Lower Priority (Utilities)
+- [ ] `research` - Needs checking
+- [ ] `complexity-report` - Needs checking
+- [ ] `validate-dependencies` - ✅ Fixed
+- [ ] `fix-dependencies` - ✅ Fixed
+- [ ] `add-dependency` - ✅ Fixed
+- [ ] `remove-dependency` - ✅ Fixed
+
+## MCP Integration Pattern
+
+MCP direct functions must also follow the tag-aware pattern:
+
+```javascript
+// ✅ DO: Tag-aware MCP direct function
+export async function coreActionDirect(args, log, context = {}) {
+  const { session } = context;
+  const { projectRoot, tag } = args; // MCP passes these in args
+  
+  try {
+    const result = await coreAction(
+      tasksPath,
+      // ... other parameters ...
+      { projectRoot, tag, session, mcpLog: logWrapper }
+    );
+    
+    return { success: true, data: result };
+  } catch (error) {
+    return { success: false, error: { code: 'ERROR_CODE', message: error.message } };
+  }
+}
+```
+
+## File Generation Tag-Aware Naming
+
+The `generate` command must use tag-aware file naming:
+
+```javascript
+// ✅ DO: Tag-aware file naming
+const taskFileName = targetTag === 'master' 
+  ? `task_${task.id.toString().padStart(3, '0')}.txt`
+  : `task_${task.id.toString().padStart(3, '0')}_${targetTag}.txt`;
+```
+
+**Examples:**
+- Master tag: `task_001.txt`, `task_002.txt`
+- Other tags: `task_001_feature.txt`, `task_002_feature.txt`
+
+## Common Anti-Patterns
+
+```javascript
+// ❌ DON'T: Missing getCurrentTag import
+import { readJSON, writeJSON } from '../utils.js'; // Missing getCurrentTag
+
+// ❌ DON'T: Hard-coded tag resolution
+const tag = options.tag || 'master'; // Missing getCurrentTag
+
+// ❌ DON'T: Missing --tag option
+.option('-f, --file <file>', 'Path to tasks file') // Missing --tag option
+
+// ❌ DON'T: Missing context parameter
+await coreFunction(tasksPath, param1, param2); // Missing { projectRoot, tag }
+
+// ❌ DON'T: Incorrect readJSON/writeJSON calls
+const data = readJSON(tasksPath); // Missing projectRoot and tag
+writeJSON(tasksPath, data); // Missing projectRoot and tag
+```
+
+## Validation Checklist
+
+For each command, verify:
+
+- [ ] Imports `getCurrentTag` from utils.js
+- [ ] Has `--tag <tag>` CLI option
+- [ ] Uses standard tag resolution: `options.tag || getCurrentTag(projectRoot) || 'master'`
+- [ ] Finds `projectRoot` with error handling
+- [ ] Passes `{ projectRoot, tag }` context to core functions
+- [ ] Core functions accept and use context parameter
+- [ ] Uses `readJSON(tasksPath, projectRoot, tag)` and `writeJSON(tasksPath, data, projectRoot, tag)`
+
+## Testing Tag Resolution
+
+Test each command with:
+
+```bash
+# Test with explicit tag
+node bin/task-master command-name --tag test-tag
+
+# Test with active tag (should use current active tag)
+node bin/task-master use-tag test-tag
+node bin/task-master command-name
+
+# Test with master tag (default)
+node bin/task-master use-tag master  
+node bin/task-master command-name
+```
+
+## Migration Strategy
+
+1. **Audit Phase**: Systematically check each command against the checklist
+2. **Fix Phase**: Apply the standard patterns to non-compliant commands
+3. **Test Phase**: Verify tag resolution works correctly
+4. **Document Phase**: Update command documentation with tag support
+
+This ensures consistent, predictable behavior across all Task Master commands and prevents tag deletion bugs.

.cursor/rules/taskmaster.mdc

@@ -11,6 +11,8 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 
 **Important:** Several MCP tools involve AI processing... The AI-powered tools include `parse_prd`, `analyze_project_complexity`, `update_subtask`, `update_task`, `update`, `expand_all`, `expand_task`, and `add_task`.
 
+**🏷️ Tagged Task Lists System:** Task Master now supports **tagged task lists** for multi-context task management. This allows you to maintain separate, isolated lists of tasks for different features, branches, or experiments. Existing projects are seamlessly migrated to use a default "master" tag. Most commands now support a `--tag <name>` flag to specify which context to operate on. If omitted, commands use the currently active tag.
+
 ---
 
 ## Initialization & Setup
@@ -36,7 +38,8 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `addAliases`: `Add shell aliases tm and taskmaster. Default is false.` (CLI: `--aliases`)
     *   `yes`: `Skip prompts and use defaults/provided arguments. Default is false.` (CLI: `-y, --yes`)
 *   **Usage:** Run this once at the beginning of a new project, typically via an integrated tool like Cursor. Operates on the current working directory of the MCP server. 
-*   **Important:** Once complete, you *MUST* parse a prd in order to generate tasks. There will be no tasks files until then. The next step after initializing should be to create a PRD using the example PRD in scripts/example_prd.txt. 
+*   **Important:** Once complete, you *MUST* parse a prd in order to generate tasks. There will be no tasks files until then. The next step after initializing should be to create a PRD using the example PRD in .taskmaster/templates/example_prd.txt. 
+*   **Tagging:** Use the `--tag` option to parse the PRD into a specific, non-default tag context. If the tag doesn't exist, it will be created automatically. Example: `task-master parse-prd spec.txt --tag=new-feature`.
 
 ### 2. Parse PRD (`parse_prd`)
 
@@ -45,12 +48,12 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Description:** `Parse a Product Requirements Document, PRD, or text file with Taskmaster to automatically generate an initial set of tasks in tasks.json.`
 *   **Key Parameters/Options:**
     *   `input`: `Path to your PRD or requirements text file that Taskmaster should parse for tasks.` (CLI: `[file]` positional or `-i, --input <file>`)
-    *   `output`: `Specify where Taskmaster should save the generated 'tasks.json' file. Defaults to 'tasks/tasks.json'.` (CLI: `-o, --output <file>`)
+    *   `output`: `Specify where Taskmaster should save the generated 'tasks.json' file. Defaults to '.taskmaster/tasks/tasks.json'.` (CLI: `-o, --output <file>`)
     *   `numTasks`: `Approximate number of top-level tasks Taskmaster should aim to generate from the document.` (CLI: `-n, --num-tasks <number>`)
     *   `force`: `Use this to allow Taskmaster to overwrite an existing 'tasks.json' without asking for confirmation.` (CLI: `-f, --force`)
 *   **Usage:** Useful for bootstrapping a project from an existing requirements document.
 *   **Notes:** Task Master will strictly adhere to any specific requirements mentioned in the PRD, such as libraries, database schemas, frameworks, tech stacks, etc., while filling in any gaps where the PRD isn't fully specified. Tasks are designed to provide the most direct implementation path while avoiding over-engineering.
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress. If the user does not have a PRD, suggest discussing their idea and then use the example PRD in `scripts/example_prd.txt` as a template for creating the PRD based on their idea, for use with `parse-prd`.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress. If the user does not have a PRD, suggest discussing their idea and then use the example PRD in `.taskmaster/templates/example_prd.txt` as a template for creating the PRD based on their idea, for use with `parse-prd`.
 
 ---
 
@@ -74,13 +77,14 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `--set-fallback <model_id>`: `Set the fallback model.`
     *   `--ollama`: `Specify that the provided model ID is for Ollama (use with --set-*).`
     *   `--openrouter`: `Specify that the provided model ID is for OpenRouter (use with --set-*). Validates against OpenRouter API.`
+    *   `--bedrock`: `Specify that the provided model ID is for AWS Bedrock (use with --set-*).`
     *   `--setup`: `Run interactive setup to configure models, including custom Ollama/OpenRouter IDs.`
 *   **Usage (MCP):** Call without set flags to get current config. Use `setMain`, `setResearch`, or `setFallback` with a valid model ID to update the configuration. Use `listAvailableModels: true` to get a list of unassigned models. To set a custom model, provide the model ID and set `ollama: true` or `openrouter: true`.
 *   **Usage (CLI):** Run without flags to view current configuration and available models. Use set flags to update specific roles. Use `--setup` for guided configuration, including custom models. To set a custom model via flags, use `--set-<role>=<model_id>` along with either `--ollama` or `--openrouter`.
-*   **Notes:** Configuration is stored in `.taskmasterconfig` in the project root. This command/tool modifies that file. Use `listAvailableModels` or `task-master models` to see internally supported models. OpenRouter custom models are validated against their live API. Ollama custom models are not validated live.
+*   **Notes:** Configuration is stored in `.taskmaster/config.json` in the project root. This command/tool modifies that file. Use `listAvailableModels` or `task-master models` to see internally supported models. OpenRouter custom models are validated against their live API. Ollama custom models are not validated live.
 *   **API note:** API keys for selected AI providers (based on their model) need to exist in the mcp.json file to be accessible in MCP context. The API keys must be present in the local .env file for the CLI to be able to read them.
 *   **Model costs:** The costs in supported models are expressed in dollars. An input/output value of 3 is $3.00. A value of 0.8 is $0.80. 
-*   **Warning:** DO NOT MANUALLY EDIT THE .taskmasterconfig FILE. Use the included commands either in the MCP or CLI format as needed. Always prioritize MCP tools when available and use the CLI as a fallback.
+*   **Warning:** DO NOT MANUALLY EDIT THE .taskmaster/config.json FILE. Use the included commands either in the MCP or CLI format as needed. Always prioritize MCP tools when available and use the CLI as a fallback.
 
 ---
 
@@ -92,8 +96,9 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **CLI Command:** `task-master list [options]`
 *   **Description:** `List your Taskmaster tasks, optionally filtering by status and showing subtasks.`
 *   **Key Parameters/Options:**
-    *   `status`: `Show only Taskmaster tasks matching this status, e.g., 'pending' or 'done'.` (CLI: `-s, --status <status>`)
+    *   `status`: `Show only Taskmaster tasks matching this status (or multiple statuses, comma-separated), e.g., 'pending' or 'done,in-progress'.` (CLI: `-s, --status <status>`)
     *   `withSubtasks`: `Include subtasks indented under their parent tasks in the list.` (CLI: `--with-subtasks`)
+    *   `tag`: `Specify which tag context to list tasks from. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Get an overview of the project status, often used at the start of a work session.
 
@@ -104,17 +109,20 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Description:** `Ask Taskmaster to show the next available task you can work on, based on status and completed dependencies.`
 *   **Key Parameters/Options:**
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+    *   `tag`: `Specify which tag context to use. Defaults to the current active tag.` (CLI: `--tag <name>`)
 *   **Usage:** Identify what to work on next according to the plan.
 
 ### 5. Get Task Details (`get_task`)
 
 *   **MCP Tool:** `get_task`
 *   **CLI Command:** `task-master show [id] [options]`
-*   **Description:** `Display detailed information for a specific Taskmaster task or subtask by its ID.`
+*   **Description:** `Display detailed information for one or more specific Taskmaster tasks or subtasks by ID.`
 *   **Key Parameters/Options:**
-    *   `id`: `Required. The ID of the Taskmaster task, e.g., '15', or subtask, e.g., '15.2', you want to view.` (CLI: `[id]` positional or `-i, --id <id>`)
+    *   `id`: `Required. The ID of the Taskmaster task (e.g., '15'), subtask (e.g., '15.2'), or a comma-separated list of IDs ('1,5,10.2') you want to view.` (CLI: `[id]` positional or `-i, --id <id>`)
+    *   `tag`: `Specify which tag context to get the task(s) from. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Understand the full details, implementation notes, and test strategy for a specific task before starting work.
+*   **Usage:** Understand the full details for a specific task. When multiple IDs are provided, a summary table is shown.
+*   **CRITICAL INFORMATION** If you need to collect information from multiple tasks, use comma-separated IDs (i.e. 1,2,3) to receive an array of tasks. Do not needlessly get tasks one at a time if you need to get many as that is wasteful.
 
 ---
 
@@ -130,6 +138,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `dependencies`: `Specify the IDs of any Taskmaster tasks that must be completed before this new one can start, e.g., '12,14'.` (CLI: `-d, --dependencies <ids>`)
     *   `priority`: `Set the priority for the new task: 'high', 'medium', or 'low'. Default is 'medium'.` (CLI: `--priority <priority>`)
     *   `research`: `Enable Taskmaster to use the research role for potentially more informed task creation.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context to add the task to. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Quickly add newly identified tasks during development.
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
@@ -148,6 +157,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `dependencies`: `Specify IDs of other tasks or subtasks, e.g., '15' or '16.1', that must be done before this new subtask.` (CLI: `--dependencies <ids>`)
     *   `status`: `Set the initial status for the new subtask. Default is 'pending'.` (CLI: `-s, --status <status>`)
     *   `skipGenerate`: `Prevent Taskmaster from automatically regenerating markdown task files after adding the subtask.` (CLI: `--skip-generate`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Break down tasks manually or reorganize existing tasks.
 
@@ -160,6 +170,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `from`: `Required. The ID of the first task Taskmaster should update. All tasks with this ID or higher that are not 'done' will be considered.` (CLI: `--from <id>`)
     *   `prompt`: `Required. Explain the change or new context for Taskmaster to apply to the tasks, e.g., "We are now using React Query instead of Redux Toolkit for data fetching".` (CLI: `-p, --prompt <text>`)
     *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Handle significant implementation changes or pivots that affect multiple future tasks. Example CLI: `task-master update --from='18' --prompt='Switching to React Query.\nNeed to refactor data fetching...'`
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
@@ -168,13 +179,15 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 
 *   **MCP Tool:** `update_task`
 *   **CLI Command:** `task-master update-task [options]`
-*   **Description:** `Modify a specific Taskmaster task or subtask by its ID, incorporating new information or changes.`
+*   **Description:** `Modify a specific Taskmaster task by ID, incorporating new information or changes. By default, this replaces the existing task details.`
 *   **Key Parameters/Options:**
-    *   `id`: `Required. The specific ID of the Taskmaster task, e.g., '15', or subtask, e.g., '15.2', you want to update.` (CLI: `-i, --id <id>`)
+    *   `id`: `Required. The specific ID of the Taskmaster task, e.g., '15', you want to update.` (CLI: `-i, --id <id>`)
     *   `prompt`: `Required. Explain the specific changes or provide the new information Taskmaster should incorporate into this task.` (CLI: `-p, --prompt <text>`)
+    *   `append`: `If true, appends the prompt content to the task's details with a timestamp, rather than replacing them. Behaves like update-subtask.` (CLI: `--append`)
     *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context the task belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Refine a specific task based on new understanding or feedback. Example CLI: `task-master update-task --id='15' --prompt='Clarification: Use PostgreSQL instead of MySQL.\nUpdate schema details...'`
+*   **Usage:** Refine a specific task based on new understanding. Use `--append` to log progress without creating subtasks.
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
 
 ### 10. Update Subtask (`update_subtask`)
@@ -183,11 +196,12 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **CLI Command:** `task-master update-subtask [options]`
 *   **Description:** `Append timestamped notes or details to a specific Taskmaster subtask without overwriting existing content. Intended for iterative implementation logging.`
 *   **Key Parameters/Options:**
-    *   `id`: `Required. The specific ID of the Taskmaster subtask, e.g., '15.2', you want to add information to.` (CLI: `-i, --id <id>`)
+    *   `id`: `Required. The ID of the Taskmaster subtask, e.g., '5.2', to update with new information.` (CLI: `-i, --id <id>`)
-    *   `prompt`: `Required. Provide the information or notes Taskmaster should append to the subtask's details. Ensure this adds *new* information not already present.` (CLI: `-p, --prompt <text>`)
+    *   `prompt`: `Required. The information, findings, or progress notes to append to the subtask's details with a timestamp.` (CLI: `-p, --prompt <text>`)
     *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context the subtask belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Add implementation notes, code snippets, or clarifications to a subtask during development. Before calling, review the subtask's current details to append only fresh insights, helping to build a detailed log of the implementation journey and avoid redundancy. Example CLI: `task-master update-subtask --id='15.2' --prompt='Discovered that the API requires header X.\nImplementation needs adjustment...'`
+*   **Usage:** Log implementation progress, findings, and discoveries during subtask development. Each update is timestamped and appended to preserve the implementation journey.
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
 
 ### 11. Set Task Status (`set_task_status`)
@@ -198,6 +212,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Key Parameters/Options:**
     *   `id`: `Required. The ID(s) of the Taskmaster task(s) or subtask(s), e.g., '15', '15.2', or '16,17.1', to update.` (CLI: `-i, --id <id>`)
     *   `status`: `Required. The new status to set, e.g., 'done', 'pending', 'in-progress', 'review', 'cancelled'.` (CLI: `-s, --status <status>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Mark progress as tasks move through the development cycle.
 
@@ -209,6 +224,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Key Parameters/Options:**
     *   `id`: `Required. The ID of the Taskmaster task, e.g., '5', or subtask, e.g., '5.2', to permanently remove.` (CLI: `-i, --id <id>`)
     *   `yes`: `Skip the confirmation prompt and immediately delete the task.` (CLI: `-y, --yes`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Permanently delete tasks or subtasks that are no longer needed in the project.
 *   **Notes:** Use with caution as this operation cannot be undone. Consider using 'blocked', 'cancelled', or 'deferred' status instead if you just want to exclude a task from active planning but keep it for reference. The command automatically cleans up dependency references in other tasks.
@@ -228,6 +244,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `research`: `Enable Taskmaster to use the research role for more informed subtask generation. Requires appropriate API key.` (CLI: `-r, --research`)
     *   `prompt`: `Optional: Provide extra context or specific instructions to Taskmaster for generating the subtasks.` (CLI: `-p, --prompt <text>`)
     *   `force`: `Optional: If true, clear existing subtasks before generating new ones. Default is false (append).` (CLI: `--force`)
+    *   `tag`: `Specify which tag context the task belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Generate a detailed implementation plan for a complex task before starting coding. Automatically uses complexity report recommendations if available and `num` is not specified.
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
@@ -242,6 +259,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `research`: `Enable research role for more informed subtask generation. Requires appropriate API key.` (CLI: `-r, --research`)
     *   `prompt`: `Optional: Provide extra context for Taskmaster to apply generally during expansion.` (CLI: `-p, --prompt <text>`)
     *   `force`: `Optional: If true, clear existing subtasks before generating new ones for each eligible task. Default is false (append).` (CLI: `--force`)
+    *   `tag`: `Specify which tag context to expand. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Useful after initial task generation or complexity analysis to break down multiple tasks at once.
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
@@ -254,6 +272,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Key Parameters/Options:**
     *   `id`: `The ID(s) of the Taskmaster parent task(s) whose subtasks you want to remove, e.g., '15' or '16,18'. Required unless using `all`.) (CLI: `-i, --id <ids>`)
     *   `all`: `Tell Taskmaster to remove subtasks from all parent tasks.` (CLI: `--all`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Used before regenerating subtasks with `expand_task` if the previous breakdown needs replacement.
 
@@ -266,14 +285,41 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `id`: `Required. The ID(s) of the Taskmaster subtask(s) to remove, e.g., '15.2' or '16.1,16.3'.` (CLI: `-i, --id <id>`)
     *   `convert`: `If used, Taskmaster will turn the subtask into a regular top-level task instead of deleting it.` (CLI: `-c, --convert`)
     *   `skipGenerate`: `Prevent Taskmaster from automatically regenerating markdown task files after removing the subtask.` (CLI: `--skip-generate`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Delete unnecessary subtasks or promote a subtask to a top-level task.
 
+### 17. Move Task (`move_task`)
+
+*   **MCP Tool:** `move_task`
+*   **CLI Command:** `task-master move [options]`
+*   **Description:** `Move a task or subtask to a new position within the task hierarchy.`
+*   **Key Parameters/Options:**
+    *   `from`: `Required. ID of the task/subtask to move (e.g., "5" or "5.2"). Can be comma-separated for multiple tasks.` (CLI: `--from <id>`)
+    *   `to`: `Required. ID of the destination (e.g., "7" or "7.3"). Must match the number of source IDs if comma-separated.` (CLI: `--to <id>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Reorganize tasks by moving them within the hierarchy. Supports various scenarios like:
+    *   Moving a task to become a subtask
+    *   Moving a subtask to become a standalone task
+    *   Moving a subtask to a different parent
+    *   Reordering subtasks within the same parent
+    *   Moving a task to a new, non-existent ID (automatically creates placeholders)
+    *   Moving multiple tasks at once with comma-separated IDs
+*   **Validation Features:**
+    *   Allows moving tasks to non-existent destination IDs (creates placeholder tasks)
+    *   Prevents moving to existing task IDs that already have content (to avoid overwriting)
+    *   Validates that source tasks exist before attempting to move them
+    *   Maintains proper parent-child relationships
+*   **Example CLI:** `task-master move --from=5.2 --to=7.3` to move subtask 5.2 to become subtask 7.3.
+*   **Example Multi-Move:** `task-master move --from=10,11,12 --to=16,17,18` to move multiple tasks to new positions.
+*   **Common Use:** Resolving merge conflicts in tasks.json when multiple team members create tasks on different branches.
+
 ---
 
 ## Dependency Management
 
-### 17. Add Dependency (`add_dependency`)
+### 18. Add Dependency (`add_dependency`)
 
 *   **MCP Tool:** `add_dependency`
 *   **CLI Command:** `task-master add-dependency [options]`
@@ -281,10 +327,11 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Key Parameters/Options:**
     *   `id`: `Required. The ID of the Taskmaster task that will depend on another.` (CLI: `-i, --id <id>`)
     *   `dependsOn`: `Required. The ID of the Taskmaster task that must be completed first, the prerequisite.` (CLI: `-d, --depends-on <id>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <path>`)
 *   **Usage:** Establish the correct order of execution between tasks.
 
-### 18. Remove Dependency (`remove_dependency`)
+### 19. Remove Dependency (`remove_dependency`)
 
 *   **MCP Tool:** `remove_dependency`
 *   **CLI Command:** `task-master remove-dependency [options]`
@@ -292,24 +339,27 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Key Parameters/Options:**
     *   `id`: `Required. The ID of the Taskmaster task you want to remove a prerequisite from.` (CLI: `-i, --id <id>`)
     *   `dependsOn`: `Required. The ID of the Taskmaster task that should no longer be a prerequisite.` (CLI: `-d, --depends-on <id>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Update task relationships when the order of execution changes.
 
-### 19. Validate Dependencies (`validate_dependencies`)
+### 20. Validate Dependencies (`validate_dependencies`)
 
 *   **MCP Tool:** `validate_dependencies`
 *   **CLI Command:** `task-master validate-dependencies [options]`
 *   **Description:** `Check your Taskmaster tasks for dependency issues (like circular references or links to non-existent tasks) without making changes.`
 *   **Key Parameters/Options:**
+    *   `tag`: `Specify which tag context to validate. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Audit the integrity of your task dependencies.
 
-### 20. Fix Dependencies (`fix_dependencies`)
+### 21. Fix Dependencies (`fix_dependencies`)
 
 *   **MCP Tool:** `fix_dependencies`
 *   **CLI Command:** `task-master fix-dependencies [options]`
 *   **Description:** `Automatically fix dependency issues (like circular references or links to non-existent tasks) in your Taskmaster tasks.`
 *   **Key Parameters/Options:**
+    *   `tag`: `Specify which tag context to fix dependencies in. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Clean up dependency errors automatically.
 
@@ -317,47 +367,172 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 
 ## Analysis & Reporting
 
-### 21. Analyze Project Complexity (`analyze_project_complexity`)
+### 22. Analyze Project Complexity (`analyze_project_complexity`)
 
 *   **MCP Tool:** `analyze_project_complexity`
 *   **CLI Command:** `task-master analyze-complexity [options]`
 *   **Description:** `Have Taskmaster analyze your tasks to determine their complexity and suggest which ones need to be broken down further.`
 *   **Key Parameters/Options:**
-    *   `output`: `Where to save the complexity analysis report (default: 'scripts/task-complexity-report.json').` (CLI: `-o, --output <file>`)
+    *   `output`: `Where to save the complexity analysis report. Default is '.taskmaster/reports/task-complexity-report.json' (or '..._tagname.json' if a tag is used).` (CLI: `-o, --output <file>`)
     *   `threshold`: `The minimum complexity score (1-10) that should trigger a recommendation to expand a task.` (CLI: `-t, --threshold <number>`)
     *   `research`: `Enable research role for more accurate complexity analysis. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context to analyze. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Used before breaking down tasks to identify which ones need the most attention.
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
 
-### 22. View Complexity Report (`complexity_report`)
+### 23. View Complexity Report (`complexity_report`)
 
 *   **MCP Tool:** `complexity_report`
 *   **CLI Command:** `task-master complexity-report [options]`
 *   **Description:** `Display the task complexity analysis report in a readable format.`
 *   **Key Parameters/Options:**
-    *   `file`: `Path to the complexity report (default: 'scripts/task-complexity-report.json').` (CLI: `-f, --file <file>`)
+    *   `tag`: `Specify which tag context to show the report for. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to the complexity report (default: '.taskmaster/reports/task-complexity-report.json').` (CLI: `-f, --file <file>`)
 *   **Usage:** Review and understand the complexity analysis results after running analyze-complexity.
 
 ---
 
 ## File Management
 
-### 23. Generate Task Files (`generate`)
+### 24. Generate Task Files (`generate`)
 
 *   **MCP Tool:** `generate`
 *   **CLI Command:** `task-master generate [options]`
 *   **Description:** `Create or update individual Markdown files for each task based on your tasks.json.`
 *   **Key Parameters/Options:**
     *   `output`: `The directory where Taskmaster should save the task files (default: in a 'tasks' directory).` (CLI: `-o, --output <directory>`)
+    *   `tag`: `Specify which tag context to generate files for. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Run this after making changes to tasks.json to keep individual task files up to date.
+*   **Usage:** Run this after making changes to tasks.json to keep individual task files up to date. This command is now manual and no longer runs automatically.
+
+---
+
+## AI-Powered Research
+
+### 25. Research (`research`)
+
+*   **MCP Tool:** `research`
+*   **CLI Command:** `task-master research [options]`
+*   **Description:** `Perform AI-powered research queries with project context to get fresh, up-to-date information beyond the AI's knowledge cutoff.`
+*   **Key Parameters/Options:**
+    *   `query`: `Required. Research query/prompt (e.g., "What are the latest best practices for React Query v5?").` (CLI: `[query]` positional or `-q, --query <text>`)
+    *   `taskIds`: `Comma-separated list of task/subtask IDs from the current tag context (e.g., "15,16.2,17").` (CLI: `-i, --id <ids>`)
+    *   `filePaths`: `Comma-separated list of file paths for context (e.g., "src/api.js,docs/readme.md").` (CLI: `-f, --files <paths>`)
+    *   `customContext`: `Additional custom context text to include in the research.` (CLI: `-c, --context <text>`)
+    *   `includeProjectTree`: `Include project file tree structure in context (default: false).` (CLI: `--tree`)
+    *   `detailLevel`: `Detail level for the research response: 'low', 'medium', 'high' (default: medium).` (CLI: `--detail <level>`)
+    *   `saveTo`: `Task or subtask ID (e.g., "15", "15.2") to automatically save the research conversation to.` (CLI: `--save-to <id>`)
+    *   `saveFile`: `If true, saves the research conversation to a markdown file in '.taskmaster/docs/research/'.` (CLI: `--save-file`)
+    *   `noFollowup`: `Disables the interactive follow-up question menu in the CLI.` (CLI: `--no-followup`)
+    *   `tag`: `Specify which tag context to use for task-based context gathering. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `projectRoot`: `The directory of the project. Must be an absolute path.` (CLI: Determined automatically)
+*   **Usage:** **This is a POWERFUL tool that agents should use FREQUENTLY** to:
+    *   Get fresh information beyond knowledge cutoff dates
+    *   Research latest best practices, library updates, security patches
+    *   Find implementation examples for specific technologies
+    *   Validate approaches against current industry standards
+    *   Get contextual advice based on project files and tasks
+*   **When to Consider Using Research:**
+    *   **Before implementing any task** - Research current best practices
+    *   **When encountering new technologies** - Get up-to-date implementation guidance (libraries, apis, etc)
+    *   **For security-related tasks** - Find latest security recommendations
+    *   **When updating dependencies** - Research breaking changes and migration guides
+    *   **For performance optimization** - Get current performance best practices
+    *   **When debugging complex issues** - Research known solutions and workarounds
+*   **Research + Action Pattern:**
+    *   Use `research` to gather fresh information
+    *   Use `update_subtask` to commit findings with timestamps
+    *   Use `update_task` to incorporate research into task details
+    *   Use `add_task` with research flag for informed task creation
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. The research provides FRESH data beyond the AI's training cutoff, making it invaluable for current best practices and recent developments.
+
+---
+
+## Tag Management
+
+This new suite of commands allows you to manage different task contexts (tags).
+
+### 26. List Tags (`tags`)
+
+*   **MCP Tool:** `list_tags`
+*   **CLI Command:** `task-master tags [options]`
+*   **Description:** `List all available tags with task counts, completion status, and other metadata.`
+*   **Key Parameters/Options:**
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+    *   `--show-metadata`: `Include detailed metadata in the output (e.g., creation date, description).` (CLI: `--show-metadata`)
+
+### 27. Add Tag (`add_tag`)
+
+*   **MCP Tool:** `add_tag`
+*   **CLI Command:** `task-master add-tag <tagName> [options]`
+*   **Description:** `Create a new, empty tag context, or copy tasks from another tag.`
+*   **Key Parameters/Options:**
+    *   `tagName`: `Name of the new tag to create (alphanumeric, hyphens, underscores).` (CLI: `<tagName>` positional)
+    *   `--from-branch`: `Creates a tag with a name derived from the current git branch, ignoring the <tagName> argument.` (CLI: `--from-branch`)
+    *   `--copy-from-current`: `Copy tasks from the currently active tag to the new tag.` (CLI: `--copy-from-current`)
+    *   `--copy-from <tag>`: `Copy tasks from a specific source tag to the new tag.` (CLI: `--copy-from <tag>`)
+    *   `--description <text>`: `Provide an optional description for the new tag.` (CLI: `-d, --description <text>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 28. Delete Tag (`delete_tag`)
+
+*   **MCP Tool:** `delete_tag`
+*   **CLI Command:** `task-master delete-tag <tagName> [options]`
+*   **Description:** `Permanently delete a tag and all of its associated tasks.`
+*   **Key Parameters/Options:**
+    *   `tagName`: `Name of the tag to delete.` (CLI: `<tagName>` positional)
+    *   `--yes`: `Skip the confirmation prompt.` (CLI: `-y, --yes`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 29. Use Tag (`use_tag`)
+
+*   **MCP Tool:** `use_tag`
+*   **CLI Command:** `task-master use-tag <tagName>`
+*   **Description:** `Switch your active task context to a different tag.`
+*   **Key Parameters/Options:**
+    *   `tagName`: `Name of the tag to switch to.` (CLI: `<tagName>` positional)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 30. Rename Tag (`rename_tag`)
+
+*   **MCP Tool:** `rename_tag`
+*   **CLI Command:** `task-master rename-tag <oldName> <newName>`
+*   **Description:** `Rename an existing tag.`
+*   **Key Parameters/Options:**
+    *   `oldName`: `The current name of the tag.` (CLI: `<oldName>` positional)
+    *   `newName`: `The new name for the tag.` (CLI: `<newName>` positional)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 31. Copy Tag (`copy_tag`)
+
+*   **MCP Tool:** `copy_tag`
+*   **CLI Command:** `task-master copy-tag <sourceName> <targetName> [options]`
+*   **Description:** `Copy an entire tag context, including all its tasks and metadata, to a new tag.`
+*   **Key Parameters/Options:**
+    *   `sourceName`: `Name of the tag to copy from.` (CLI: `<sourceName>` positional)
+    *   `targetName`: `Name of the new tag to create.` (CLI: `<targetName>` positional)
+    *   `--description <text>`: `Optional description for the new tag.` (CLI: `-d, --description <text>`)
+
+---
+
+## Miscellaneous
+
+### 32. Sync Readme (`sync-readme`) -- experimental
+
+*   **MCP Tool:** N/A
+*   **CLI Command:** `task-master sync-readme [options]`
+*   **Description:** `Exports your task list to your project's README.md file, useful for showcasing progress.`
+*   **Key Parameters/Options:**
+    *   `status`: `Filter tasks by status (e.g., 'pending', 'done').` (CLI: `-s, --status <status>`)
+    *   `withSubtasks`: `Include subtasks in the export.` (CLI: `--with-subtasks`)
+    *   `tag`: `Specify which tag context to export from. Defaults to the current active tag.` (CLI: `--tag <name>`)
 
 ---
 
 ## Environment Variables Configuration (Updated)
 
-Taskmaster primarily uses the **`.taskmasterconfig`** file (in project root) for configuration (models, parameters, logging level, etc.), managed via `task-master models --setup`.
+Taskmaster primarily uses the **`.taskmaster/config.json`** file (in project root) for configuration (models, parameters, logging level, etc.), managed via `task-master models --setup`.
 
 Environment variables are used **only** for sensitive API keys related to AI providers and specific overrides like the Ollama base URL:
 
@@ -370,13 +545,13 @@ Environment variables are used **only** for sensitive API keys related to AI pro
     *   `AZURE_OPENAI_API_KEY` (Requires `AZURE_OPENAI_ENDPOINT` too)
     *   `OPENROUTER_API_KEY`
     *   `XAI_API_KEY`
-    *   `OLLANA_API_KEY` (Requires `OLLAMA_BASE_URL` too)
+    *   `OLLAMA_API_KEY` (Requires `OLLAMA_BASE_URL` too)
-*   **Endpoints (Optional/Provider Specific inside .taskmasterconfig):**
+*   **Endpoints (Optional/Provider Specific inside .taskmaster/config.json):**
     *   `AZURE_OPENAI_ENDPOINT`
     *   `OLLAMA_BASE_URL` (Default: `http://localhost:11434/api`)
 
-**Set API keys** in your **`.env`** file in the project root (for CLI use) or within the `env` section of your **`.cursor/mcp.json`** file (for MCP/Cursor integration). All other settings (model choice, max tokens, temperature, log level, custom endpoints) are managed in `.taskmasterconfig` via `task-master models` command or `models` MCP tool.
+**Set API keys** in your **`.env`** file in the project root (for CLI use) or within the `env` section of your **`.cursor/mcp.json`** file (for MCP/Cursor integration). All other settings (model choice, max tokens, temperature, log level, custom endpoints) are managed in `.taskmaster/config.json` via `task-master models` command or `models` MCP tool.
 
 ---
 
-For details on how these commands fit into the development process, see the [Development Workflow Guide](mdc:.cursor/rules/dev_workflow.mdc).
+For details on how these commands fit into the development process, see the [Development Workflow Guide](mdc:.cursor/rules/dev_workflow.mdc).

.cursor/rules/tasks.mdc

@@ -3,9 +3,19 @@ description: Guidelines for implementing task management operations
 globs: scripts/modules/task-manager.js
 alwaysApply: false
 ---
-
 # Task Management Guidelines
 
+## Tagged Task Lists System
+
+Task Master now uses a **tagged task lists system** for multi-context task management:
+
+- **Data Structure**: Tasks are organized into separate contexts (tags) within `tasks.json`
+- **Legacy Format**: `{"tasks": [...]}`
+- **Tagged Format**: `{"master": {"tasks": [...]}, "feature-branch": {"tasks": [...]}}`
+- **Silent Migration**: Legacy format automatically converts to tagged format on first use
+- **Tag Resolution**: Core functions receive legacy format for 100% backward compatibility
+- **Default Tag**: "master" is used for all existing and new tasks unless otherwise specified
+
 ## Task Structure Standards
 
 - **Core Task Properties**:
@@ -28,6 +38,25 @@ alwaysApply: false
   };
   ```
 
+- **Tagged Data Structure**:
+  - ✅ DO: Access tasks through tag resolution layer
+  - ✅ DO: Use `getTasksForTag(data, tagName)` to retrieve tasks for a specific tag
+  - ✅ DO: Use `setTasksForTag(data, tagName, tasks)` to update tasks for a specific tag
+  - ❌ DON'T: Directly manipulate the tagged structure in core functions
+
+  ```javascript
+  // ✅ DO: Use tag resolution functions
+  const tasksData = readJSON(tasksPath);
+  const currentTag = getCurrentTag() || 'master';
+  const tasks = getTasksForTag(tasksData, currentTag);
+  
+  // Manipulate tasks as normal...
+  
+  // Save back to the tagged structure
+  setTasksForTag(tasksData, currentTag, tasks);
+  writeJSON(tasksPath, tasksData);
+  ```
+
 - **Subtask Structure**:
   - ✅ DO: Use consistent properties across subtasks
   - ✅ DO: Maintain simple numeric IDs within parent tasks
@@ -48,53 +77,56 @@ alwaysApply: false
 ## Task Creation and Parsing
 
 - **ID Management**:
-  - ✅ DO: Assign unique sequential IDs to tasks
+  - ✅ DO: Assign unique sequential IDs to tasks within each tag context
-  - ✅ DO: Calculate the next ID based on existing tasks
+  - ✅ DO: Calculate the next ID based on existing tasks in the current tag
-  - ❌ DON'T: Hardcode or reuse IDs
+  - ❌ DON'T: Hardcode or reuse IDs within the same tag
 
   ```javascript
-  // ✅ DO: Calculate the next available ID
+  // ✅ DO: Calculate the next available ID within the current tag
-  const highestId = Math.max(...data.tasks.map(t => t.id));
+  const tasksData = readJSON(tasksPath);
+  const currentTag = getCurrentTag() || 'master';
+  const tasks = getTasksForTag(tasksData, currentTag);
+  const highestId = Math.max(...tasks.map(t => t.id));
   const nextTaskId = highestId + 1;
   ```
 
 - **PRD Parsing**:
   - ✅ DO: Extract tasks from PRD documents using AI
+  - ✅ DO: Create tasks in the current tag context (defaults to "master")
   - ✅ DO: Provide clear prompts to guide AI task generation
   - ✅ DO: Validate and clean up AI-generated tasks
 
   ```javascript
-  // ✅ DO: Validate AI responses
+  // ✅ DO: Parse into current tag context
-  try {
+  const tasksData = readJSON(tasksPath) || {};
-    // Parse the JSON response
+  const currentTag = getCurrentTag() || 'master';
-    taskData = JSON.parse(jsonContent);
+  
-    
+  // Parse tasks and add to current tag
-    // Check that we have the required fields
+  const newTasks = await parseTasksFromPRD(prdContent);
-    if (!taskData.title || !taskData.description) {
+  setTasksForTag(tasksData, currentTag, newTasks);
-      throw new Error("Missing required fields in the generated task");
+  writeJSON(tasksPath, tasksData);
-    }
-  } catch (error) {
-    log('error', "Failed to parse AI's response as valid task JSON:", error);
-    process.exit(1);
-  }
   ```
 
 ## Task Updates and Modifications
 
 - **Status Management**:
-  - ✅ DO: Provide functions for updating task status
+  - ✅ DO: Provide functions for updating task status within current tag context
   - ✅ DO: Handle both individual tasks and subtasks
   - ✅ DO: Consider subtask status when updating parent tasks
 
   ```javascript
-  // ✅ DO: Handle status updates for both tasks and subtasks
+  // ✅ DO: Handle status updates within tagged context
   async function setTaskStatus(tasksPath, taskIdInput, newStatus) {
+    const tasksData = readJSON(tasksPath);
+    const currentTag = getCurrentTag() || 'master';
+    const tasks = getTasksForTag(tasksData, currentTag);
+    
     // Check if it's a subtask (e.g., "1.2")
     if (taskIdInput.includes('.')) {
       const [parentId, subtaskId] = taskIdInput.split('.').map(id => parseInt(id, 10));
       
       // Find the parent task and subtask
-      const parentTask = data.tasks.find(t => t.id === parentId);
+      const parentTask = tasks.find(t => t.id === parentId);
       const subtask = parentTask.subtasks.find(st => st.id === subtaskId);
       
       // Update subtask status
@@ -109,7 +141,7 @@ alwaysApply: false
       }
     } else {
       // Handle regular task
-      const task = data.tasks.find(t => t.id === parseInt(taskIdInput, 10));
+      const task = tasks.find(t => t.id === parseInt(taskIdInput, 10));
       task.status = newStatus;
       
       // If marking as done, also mark subtasks
@@ -119,16 +151,24 @@ alwaysApply: false
         });
       }
     }
+    
+    // Save updated tasks back to tagged structure
+    setTasksForTag(tasksData, currentTag, tasks);
+    writeJSON(tasksPath, tasksData);
   }
   ```
 
 - **Task Expansion**:
-  - ✅ DO: Use AI to generate detailed subtasks
+  - ✅ DO: Use AI to generate detailed subtasks within current tag context
   - ✅ DO: Consider complexity analysis for subtask counts
   - ✅ DO: Ensure proper IDs for newly created subtasks
 
   ```javascript
   // ✅ DO: Generate appropriate subtasks based on complexity
+  const tasksData = readJSON(tasksPath);
+  const currentTag = getCurrentTag() || 'master';
+  const tasks = getTasksForTag(tasksData, currentTag);
+  
   if (taskAnalysis) {
     log('info', `Found complexity analysis for task ${taskId}: Score ${taskAnalysis.complexityScore}/10`);
     
@@ -138,6 +178,11 @@ alwaysApply: false
       log('info', `Using recommended number of subtasks: ${numSubtasks}`);
     }
   }
+  
+  // Generate subtasks and save back
+  // ... subtask generation logic ...
+  setTasksForTag(tasksData, currentTag, tasks);
+  writeJSON(tasksPath, tasksData);
   ```
 
 ## Task File Generation
@@ -155,67 +200,65 @@ alwaysApply: false
   
   // Format dependencies with their status
   if (task.dependencies && task.dependencies.length > 0) {
-    content += `# Dependencies: ${formatDependenciesWithStatus(task.dependencies, data.tasks)}\n`;
+    content += `# Dependencies: ${formatDependenciesWithStatus(task.dependencies, tasks)}\n`;
   } else {
     content += '# Dependencies: None\n';
   }
   ```
 
-- **Subtask Inclusion**:
+- **Tagged Context Awareness**:
-  - ✅ DO: Include subtasks in parent task files
+  - ✅ DO: Generate task files from current tag context
-  - ✅ DO: Use consistent indentation for subtask sections
+  - ✅ DO: Include tag information in generated files
-  - ✅ DO: Display subtask dependencies with proper formatting
+  - ❌ DON'T: Mix tasks from different tags in file generation
 
   ```javascript
-  // ✅ DO: Format subtasks correctly in task files
+  // ✅ DO: Generate files for current tag context
-  if (task.subtasks && task.subtasks.length > 0) {
+  async function generateTaskFiles(tasksPath, outputDir) {
-    content += '\n# Subtasks:\n';
+    const tasksData = readJSON(tasksPath);
+    const currentTag = getCurrentTag() || 'master';
+    const tasks = getTasksForTag(tasksData, currentTag);
     
-    task.subtasks.forEach(subtask => {
+    // Add tag context to file header
-      content += `## ${subtask.id}. ${subtask.title} [${subtask.status || 'pending'}]\n`;
+    let content = `# Tag Context: ${currentTag}\n`;
-      
+    content += `# Task ID: ${task.id}\n`;
-      // Format subtask dependencies
+    // ... rest of file generation
-      if (subtask.dependencies && subtask.dependencies.length > 0) {
-        // Format the dependencies
-        content += `### Dependencies: ${formattedDeps}\n`;
-      } else {
-        content += '### Dependencies: None\n';
-      }
-      
-      content += `### Description: ${subtask.description || ''}\n`;
-      content += '### Details:\n';
-      content += (subtask.details || '').split('\n').map(line => line).join('\n');
-      content += '\n\n';
-    });
   }
   ```
 
 ## Task Listing and Display
 
 - **Filtering and Organization**:
-  - ✅ DO: Allow filtering tasks by status
+  - ✅ DO: Allow filtering tasks by status within current tag context
   - ✅ DO: Handle subtask display in lists
   - ✅ DO: Use consistent table formats
 
   ```javascript
-  // ✅ DO: Implement clear filtering and organization
+  // ✅ DO: Implement clear filtering within tag context
+  const tasksData = readJSON(tasksPath);
+  const currentTag = getCurrentTag() || 'master';
+  const tasks = getTasksForTag(tasksData, currentTag);
+  
   // Filter tasks by status if specified
   const filteredTasks = statusFilter 
-    ? data.tasks.filter(task => 
+    ? tasks.filter(task => 
         task.status && task.status.toLowerCase() === statusFilter.toLowerCase())
-    : data.tasks;
+    : tasks;
   ```
 
 - **Progress Tracking**:
-  - ✅ DO: Calculate and display completion statistics
+  - ✅ DO: Calculate and display completion statistics for current tag
   - ✅ DO: Track both task and subtask completion
   - ✅ DO: Use visual progress indicators
 
   ```javascript
-  // ✅ DO: Track and display progress
+  // ✅ DO: Track and display progress within tag context
+  const tasksData = readJSON(tasksPath);
+  const currentTag = getCurrentTag() || 'master';
+  const tasks = getTasksForTag(tasksData, currentTag);
+  
   // Calculate completion statistics
-  const totalTasks = data.tasks.length;
+  const totalTasks = tasks.length;
-  const completedTasks = data.tasks.filter(task => 
+  const completedTasks = tasks.filter(task => 
     task.status === 'done' || task.status === 'completed').length;
   const completionPercentage = totalTasks > 0 ? (completedTasks / totalTasks) * 100 : 0;
   
@@ -223,7 +266,7 @@ alwaysApply: false
   let totalSubtasks = 0;
   let completedSubtasks = 0;
   
-  data.tasks.forEach(task => {
+  tasks.forEach(task => {
     if (task.subtasks && task.subtasks.length > 0) {
       totalSubtasks += task.subtasks.length;
       completedSubtasks += task.subtasks.filter(st => 
@@ -232,99 +275,52 @@ alwaysApply: false
   });
   ```
 
-## Complexity Analysis
+## Migration and Compatibility
 
-- **Scoring System**:
+- **Silent Migration Handling**:
-  - ✅ DO: Use AI to analyze task complexity
+  - ✅ DO: Implement silent migration in `readJSON()` function
-  - ✅ DO: Include complexity scores (1-10)
+  - ✅ DO: Detect legacy format and convert automatically
-  - ✅ DO: Generate specific expansion recommendations
+  - ✅ DO: Preserve all existing task data during migration
 
   ```javascript
-  // ✅ DO: Handle complexity analysis properly
+  // ✅ DO: Handle silent migration (implemented in utils.js)
-  const report = {
+  function readJSON(filepath) {
-    meta: {
+    let data = JSON.parse(fs.readFileSync(filepath, 'utf8'));
-      generatedAt: new Date().toISOString(),
-      tasksAnalyzed: tasksData.tasks.length,
-      thresholdScore: thresholdScore,
-      projectName: tasksData.meta?.projectName || 'Your Project Name',
-      usedResearch: useResearch
-    },
-    complexityAnalysis: complexityAnalysis
-  };
-  ```
-
-- **Analysis-Based Workflow**:
-  - ✅ DO: Use complexity reports to guide task expansion
-  - ✅ DO: Prioritize complex tasks for more detailed breakdown
-  - ✅ DO: Use expansion prompts from complexity analysis
-
-  ```javascript
-  // ✅ DO: Apply complexity analysis to workflow
-  // Sort tasks by complexity if report exists, otherwise by ID
-  if (complexityReport && complexityReport.complexityAnalysis) {
-    log('info', 'Sorting tasks by complexity...');
     
-    // Create a map of task IDs to complexity scores
+    // Silent migration for tasks.json files
-    const complexityMap = new Map();
+    if (data.tasks && Array.isArray(data.tasks) && !data.master && isTasksFile) {
-    complexityReport.complexityAnalysis.forEach(analysis => {
+      const migratedData = {
-      complexityMap.set(analysis.taskId, analysis.complexityScore);
+        master: {
-    });
+          tasks: data.tasks
+        }
+      };
+      writeJSON(filepath, migratedData);
+      data = migratedData;
+    }
     
-    // Sort tasks by complexity score (high to low)
+    return data;
-    tasksToExpand.sort((a, b) => {
-      const scoreA = complexityMap.get(a.id) || 0;
-      const scoreB = complexityMap.get(b.id) || 0;
-      return scoreB - scoreA;
-    });
   }
   ```
 
-## Next Task Selection
+- **Tag Resolution**:
-
+  - ✅ DO: Use tag resolution functions to maintain backward compatibility
-- **Eligibility Criteria**:
+  - ✅ DO: Return legacy format to core functions
-  - ✅ DO: Consider dependencies when finding next tasks
+  - ❌ DON'T: Expose tagged structure to existing core logic
-  - ✅ DO: Prioritize by task priority and dependency count
-  - ✅ DO: Skip completed tasks
 
   ```javascript
-  // ✅ DO: Use proper task prioritization logic
+  // ✅ DO: Use tag resolution layer
-  function findNextTask(tasks) {
+  function getTasksForTag(data, tagName) {
-    // Get all completed task IDs
+    if (data.tasks && Array.isArray(data.tasks)) {
-    const completedTaskIds = new Set(
+      // Legacy format - return as-is
-      tasks
+      return data.tasks;
-        .filter(t => t.status === 'done' || t.status === 'completed')
+    }
-        .map(t => t.id)
-    );
     
-    // Filter for pending tasks whose dependencies are all satisfied
+    if (data[tagName] && data[tagName].tasks) {
-    const eligibleTasks = tasks.filter(task => 
+      // Tagged format - return tasks for specified tag
-      (task.status === 'pending' || task.status === 'in-progress') && 
+      return data[tagName].tasks;
-      task.dependencies && 
+    }
-      task.dependencies.every(depId => completedTaskIds.has(depId))
-    );
     
-    // Sort by priority, dependency count, and ID
+    return [];
-    const priorityValues = { 'high': 3, 'medium': 2, 'low': 1 };
-    
-    const nextTask = eligibleTasks.sort((a, b) => {
-      // Priority first
-      const priorityA = priorityValues[a.priority || 'medium'] || 2;
-      const priorityB = priorityValues[b.priority || 'medium'] || 2;
-      
-      if (priorityB !== priorityA) {
-        return priorityB - priorityA; // Higher priority first
-      }
-      
-      // Dependency count next
-      if (a.dependencies.length !== b.dependencies.length) {
-        return a.dependencies.length - b.dependencies.length; // Fewer dependencies first
-      }
-      
-      // ID last
-      return a.id - b.id; // Lower ID first
-    })[0];
-    
-    return nextTask;
   }
   ```
 

.cursor/rules/ui.mdc

@@ -150,4 +150,91 @@ alwaysApply: false
   ));
   ```
 
-Refer to [`ui.js`](mdc:scripts/modules/ui.js) for implementation examples and [`new_features.mdc`](mdc:.cursor/rules/new_features.mdc) for integration guidelines. 
+## Enhanced Display Patterns
+
+### **Token Breakdown Display**
+- Use detailed, granular token breakdowns for AI-powered commands
+- Display context sources with individual token counts
+- Show both token count and character count for transparency
+
+  ```javascript
+  // ✅ DO: Display detailed token breakdown
+  function displayDetailedTokenBreakdown(tokenBreakdown, systemTokens, userTokens) {
+    const sections = [];
+    
+    if (tokenBreakdown.tasks?.length > 0) {
+      const taskDetails = tokenBreakdown.tasks.map(task => 
+        `${task.type === 'subtask' ? '  ' : ''}${task.id}: ${task.tokens.toLocaleString()}`
+      ).join('\n');
+      sections.push(`Tasks (${tokenBreakdown.tasks.reduce((sum, t) => sum + t.tokens, 0).toLocaleString()}):\n${taskDetails}`);
+    }
+    
+    const content = sections.join('\n\n');
+    console.log(boxen(content, {
+      title: chalk.cyan('Token Usage'),
+      padding: { top: 1, bottom: 1, left: 2, right: 2 },
+      borderStyle: 'round',
+      borderColor: 'cyan'
+    }));
+  }
+  ```
+
+### **Code Block Syntax Highlighting**
+- Use `cli-highlight` library for syntax highlighting in terminal output
+- Process code blocks in AI responses for better readability
+
+  ```javascript
+  // ✅ DO: Enhance code blocks with syntax highlighting
+  import { highlight } from 'cli-highlight';
+  
+  function processCodeBlocks(text) {
+    return text.replace(/```(\w+)?\n([\s\S]*?)```/g, (match, language, code) => {
+      try {
+        const highlighted = highlight(code.trim(), { 
+          language: language || 'javascript',
+          theme: 'default'
+        });
+        return `\n${highlighted}\n`;
+      } catch (error) {
+        return `\n${code.trim()}\n`;
+      }
+    });
+  }
+  ```
+
+### **Multi-Section Result Display**
+- Use separate boxes for headers, content, and metadata
+- Maintain consistent styling across different result types
+
+  ```javascript
+  // ✅ DO: Use structured result display
+  function displayResults(result, query, detailLevel) {
+    // Header with query info
+    const header = boxen(
+      chalk.green.bold('Research Results') + '\n\n' +
+      chalk.gray('Query: ') + chalk.white(query) + '\n' +
+      chalk.gray('Detail Level: ') + chalk.cyan(detailLevel),
+      {
+        padding: { top: 1, bottom: 1, left: 2, right: 2 },
+        margin: { top: 1, bottom: 0 },
+        borderStyle: 'round',
+        borderColor: 'green'
+      }
+    );
+    console.log(header);
+    
+    // Process and display main content
+    const processedResult = processCodeBlocks(result);
+    const contentBox = boxen(processedResult, {
+      padding: { top: 1, bottom: 1, left: 2, right: 2 },
+      margin: { top: 0, bottom: 1 },
+      borderStyle: 'single',
+      borderColor: 'gray'
+    });
+    console.log(contentBox);
+    
+    console.log(chalk.green('✓ Operation complete'));
+  }
+  ```
+
+Refer to [`ui.js`](mdc:scripts/modules/ui.js) for implementation examples, [`context_gathering.mdc`](mdc:.cursor/rules/context_gathering.mdc) for context display patterns, and [`new_features.mdc`](mdc:.cursor/rules/new_features.mdc) for integration guidelines. 

.cursor/rules/utilities.mdc

@@ -1,6 +1,6 @@
 ---
-description: Guidelines for implementing utility functions
+description: 
-globs: scripts/modules/utils.js, mcp-server/src/**/*
+globs: 
 alwaysApply: false
 ---
 # Utility Function Guidelines
@@ -46,7 +46,7 @@ alwaysApply: false
 - **Location**:
     - **Core CLI Utilities**: Place utilities used primarily by the core `task-master` CLI logic and command modules (`scripts/modules/*`) into [`scripts/modules/utils.js`](mdc:scripts/modules/utils.js).
     - **MCP Server Utilities**: Place utilities specifically designed to support the MCP server implementation into the appropriate subdirectories within `mcp-server/src/`.
-        - Path/Core Logic Helpers: [`mcp-server/src/core/utils/`](mdc:mcp-server/src/core/utils/) (e.g., `path-utils.js`).
+        - Path/Core Logic Helpers: [`mcp-server/src/core/utils/`](mdc:mcp-server/src/core/utils) (e.g., `path-utils.js`).
         - Tool Execution/Response Helpers: [`mcp-server/src/tools/utils.js`](mdc:mcp-server/src/tools/utils.js).
 
 ## Documentation Standards
@@ -110,7 +110,7 @@ Taskmaster configuration (excluding API keys) is primarily managed through the `
   - ✅ DO: Use appropriate icons for different log levels
   - ✅ DO: Respect the configured log level
   - ❌ DON'T: Add direct console.log calls outside the logging utility
-  - **Note on Passed Loggers**: When a logger object (like the FastMCP `log` object) is passed *as a parameter* (e.g., as `mcpLog`) into core Task Master functions, the receiving function often expects specific methods (`.info`, `.warn`, `.error`, etc.) to be directly callable on that object (e.g., `mcpLog[level](...)`). If the passed logger doesn't have this exact structure, a wrapper object may be needed. See the **Handling Logging Context (`mcpLog`)** section in [`mcp.mdc`](mdc:.cursor/rules/mcp.mdc) for the standard pattern used in direct functions.
+  - **Note on Passed Loggers**: When a logger object (like the FastMCP `log` object) is passed *as a parameter* (e.g., as `mcpLog`) into core Task Master functions, the receiving function often expects specific methods (`.info`, `.warn`, `.error`, etc.) to be directly callable on that object (e.g., `mcpLog[level](mdc:...)`). If the passed logger doesn't have this exact structure, a wrapper object may be needed. See the **Handling Logging Context (`mcpLog`)** section in [`mcp.mdc`](mdc:.cursor/rules/mcp.mdc) for the standard pattern used in direct functions.
 
 - **Logger Wrapper Pattern**: 
   - ✅ DO: Use the logger wrapper pattern when passing loggers to prevent `mcpLog[level] is not a function` errors:
@@ -548,4 +548,628 @@ export {
 };
 ```
 
-Refer to [`mcp.mdc`](mdc:.cursor/rules/mcp.mdc) and [`architecture.mdc`](mdc:.cursor/rules/architecture.mdc) for more context on MCP server architecture and integration. 
+## Context Gathering Utilities
+
+### **ContextGatherer** (`scripts/modules/utils/contextGatherer.js`)
+
+- **Multi-Source Context Extraction**:
+  - ✅ DO: Use for AI-powered commands that need project context
+  - ✅ DO: Support tasks, files, custom text, and project tree context
+  - ✅ DO: Implement detailed token counting with `gpt-tokens` library
+  - ✅ DO: Provide multiple output formats (research, chat, system-prompt)
+
+  ```javascript
+  // ✅ DO: Use ContextGatherer for consistent context extraction
+  import { ContextGatherer } from '../utils/contextGatherer.js';
+  
+  const gatherer = new ContextGatherer(projectRoot, tasksPath);
+  const result = await gatherer.gather({
+    tasks: ['15', '16.2'],
+    files: ['src/api.js'],
+    customContext: 'Additional context',
+    includeProjectTree: true,
+    format: 'research',
+    includeTokenCounts: true
+  });
+  ```
+
+### **FuzzyTaskSearch** (`scripts/modules/utils/fuzzyTaskSearch.js`)
+
+- **Intelligent Task Discovery**:
+  - ✅ DO: Use for automatic task relevance detection
+  - ✅ DO: Configure search parameters based on use case context
+  - ✅ DO: Implement purpose-based categorization for better matching
+  - ✅ DO: Sort results by relevance score and task ID
+
+  ```javascript
+  // ✅ DO: Use FuzzyTaskSearch for intelligent task discovery
+  import { FuzzyTaskSearch } from '../utils/fuzzyTaskSearch.js';
+  
+  const fuzzySearch = new FuzzyTaskSearch(tasksData.tasks, 'research');
+  const searchResults = fuzzySearch.findRelevantTasks(query, {
+    maxResults: 8,
+    includeRecent: true,
+    includeCategoryMatches: true
+  });
+  const taskIds = fuzzySearch.getTaskIds(searchResults);
+  ```
+
+- **Integration Guidelines**:
+  - ✅ DO: Use fuzzy search to supplement user-provided task IDs
+  - ✅ DO: Display discovered task IDs to users for transparency
+  - ✅ DO: Sort discovered task IDs numerically for better readability
+  - ❌ DON'T: Replace explicit user task selections with fuzzy results
+
+Refer to [`context_gathering.mdc`](mdc:.cursor/rules/context_gathering.mdc) for detailed implementation patterns, [`mcp.mdc`](mdc:.cursor/rules/mcp.mdc) and [`architecture.mdc`](mdc:.cursor/rules/architecture.mdc) for more context on MCP server architecture and integration. 
+
+## File System Operations
+
+- **JSON File Handling**:
+  - ✅ DO: Use `readJSON` and `writeJSON` for all JSON operations
+  - ✅ DO: Include error handling for file operations
+  - ✅ DO: Validate JSON structure after reading
+  - ❌ DON'T: Use raw `fs.readFileSync` or `fs.writeFileSync` for JSON
+
+  ```javascript
+  // ✅ DO: Use utility functions with error handling
+  function readJSON(filepath) {
+    try {
+      if (!fs.existsSync(filepath)) {
+        return null; // or appropriate default
+      }
+      
+      let data = JSON.parse(fs.readFileSync(filepath, 'utf8'));
+      
+      // Silent migration for tasks.json files: Transform old format to tagged format
+      const isTasksFile = filepath.includes('tasks.json') || path.basename(filepath) === 'tasks.json';
+      
+      if (data && data.tasks && Array.isArray(data.tasks) && !data.master && isTasksFile) {
+        // Migrate from old format { "tasks": [...] } to new format { "master": { "tasks": [...] } }
+        const migratedData = {
+          master: {
+            tasks: data.tasks
+          }
+        };
+        
+        writeJSON(filepath, migratedData);
+        
+        // Set global flag for CLI notice and perform complete migration
+        global.taskMasterMigrationOccurred = true;
+        performCompleteTagMigration(filepath);
+        
+        data = migratedData;
+      }
+      
+      return data;
+    } catch (error) {
+      log('error', `Failed to read JSON from ${filepath}: ${error.message}`);
+      return null;
+    }
+  }
+  
+  function writeJSON(filepath, data) {
+    try {
+      const dirPath = path.dirname(filepath);
+      if (!fs.existsSync(dirPath)) {
+        fs.mkdirSync(dirPath, { recursive: true });
+      }
+      fs.writeFileSync(filepath, JSON.stringify(data, null, 2));
+    } catch (error) {
+      log('error', `Failed to write JSON to ${filepath}: ${error.message}`);
+      throw error;
+    }
+  }
+  ```
+
+- **Path Resolution**:
+  - ✅ DO: Use `path.join()` for cross-platform path construction
+  - ✅ DO: Use `path.resolve()` for absolute paths
+  - ✅ DO: Validate paths before file operations
+
+  ```javascript
+  // ✅ DO: Handle paths correctly
+  function findProjectRoot(startPath = process.cwd()) {
+    let currentPath = path.resolve(startPath);
+    const rootPath = path.parse(currentPath).root;
+    
+    while (currentPath !== rootPath) {
+      const taskMasterPath = path.join(currentPath, '.taskmaster');
+      if (fs.existsSync(taskMasterPath)) {
+        return currentPath;
+      }
+      currentPath = path.dirname(currentPath);
+    }
+    
+    return null; // Not found
+  }
+  ```
+
+## Tagged Task Lists System Utilities
+
+- **Tag Resolution Functions**:
+  - ✅ DO: Use tag resolution layer for all task data access
+  - ✅ DO: Provide backward compatibility with legacy format
+  - ✅ DO: Default to "master" tag when no tag is specified
+
+  ```javascript
+  // ✅ DO: Implement tag resolution functions
+  function getTasksForTag(data, tagName = 'master') {
+    if (!data) {
+      return [];
+    }
+    
+    // Handle legacy format - direct tasks array
+    if (data.tasks && Array.isArray(data.tasks)) {
+      return data.tasks;
+    }
+    
+    // Handle tagged format - tasks under specific tag
+    if (data[tagName] && data[tagName].tasks && Array.isArray(data[tagName].tasks)) {
+      return data[tagName].tasks;
+    }
+    
+    return [];
+  }
+  
+  function setTasksForTag(data, tagName = 'master', tasks) {
+    // Ensure data object exists
+    if (!data) {
+      data = {};
+    }
+    
+    // Create tag structure if it doesn't exist
+    if (!data[tagName]) {
+      data[tagName] = {};
+    }
+    
+    // Set tasks for the tag
+    data[tagName].tasks = tasks;
+    
+    return data;
+  }
+  
+  function getCurrentTag() {
+    // Get current tag from state.json or default to 'master'
+    try {
+      const projectRoot = findProjectRoot();
+      if (!projectRoot) return 'master';
+      
+      const statePath = path.join(projectRoot, '.taskmaster', 'state.json');
+      if (fs.existsSync(statePath)) {
+        const state = readJSON(statePath);
+        return state.currentTag || 'master';
+      }
+    } catch (error) {
+      log('debug', `Error reading current tag: ${error.message}`);
+    }
+    
+    return 'master';
+  }
+  ```
+
+- **Migration Functions**:
+  - ✅ DO: Implement complete migration for all related files
+  - ✅ DO: Handle configuration and state file creation
+  - ✅ DO: Provide migration status tracking
+
+  ```javascript
+  // ✅ DO: Implement complete migration system
+  function performCompleteTagMigration(tasksJsonPath) {
+    try {
+      // Derive project root from tasks.json path
+      const projectRoot = findProjectRoot(path.dirname(tasksJsonPath)) || path.dirname(tasksJsonPath);
+      
+      // 1. Migrate config.json - add defaultTag and tags section
+      const configPath = path.join(projectRoot, '.taskmaster', 'config.json');
+      if (fs.existsSync(configPath)) {
+        migrateConfigJson(configPath);
+      }
+      
+      // 2. Create state.json if it doesn't exist
+      const statePath = path.join(projectRoot, '.taskmaster', 'state.json');
+      if (!fs.existsSync(statePath)) {
+        createStateJson(statePath);
+      }
+      
+      if (getDebugFlag()) {
+        log('debug', 'Completed tagged task lists migration for project');
+      }
+    } catch (error) {
+      if (getDebugFlag()) {
+        log('warn', `Error during complete tag migration: ${error.message}`);
+      }
+    }
+  }
+  
+  function migrateConfigJson(configPath) {
+    try {
+      const config = readJSON(configPath);
+      if (!config) return;
+      
+      let modified = false;
+      
+      // Add global.defaultTag if missing
+      if (!config.global) {
+        config.global = {};
+      }
+      if (!config.global.defaultTag) {
+        config.global.defaultTag = 'master';
+        modified = true;
+      }
+      
+      // Add tags section if missing
+      if (!config.tags) {
+        config.tags = {
+                  // Git integration settings removed - now manual only
+        };
+        modified = true;
+      }
+      
+      if (modified) {
+        writeJSON(configPath, config);
+        if (getDebugFlag()) {
+          log('debug', 'Updated config.json with tagged task system settings');
+        }
+      }
+    } catch (error) {
+      if (getDebugFlag()) {
+        log('warn', `Error migrating config.json: ${error.message}`);
+      }
+    }
+  }
+  
+  function createStateJson(statePath) {
+    try {
+      const initialState = {
+        currentTag: 'master',
+        lastSwitched: new Date().toISOString(),
+        migrationNoticeShown: false
+      };
+      
+      writeJSON(statePath, initialState);
+      if (getDebugFlag()) {
+        log('debug', 'Created initial state.json for tagged task system');
+      }
+    } catch (error) {
+      if (getDebugFlag()) {
+        log('warn', `Error creating state.json: ${error.message}`);
+      }
+    }
+  }
+  
+  function markMigrationForNotice() {
+    try {
+      const projectRoot = findProjectRoot();
+      if (!projectRoot) return;
+      
+      const statePath = path.join(projectRoot, '.taskmaster', 'state.json');
+      const state = readJSON(statePath) || {};
+      
+      state.migrationNoticeShown = false; // Reset to show notice
+      writeJSON(statePath, state);
+    } catch (error) {
+      if (getDebugFlag()) {
+        log('warn', `Error marking migration for notice: ${error.message}`);
+      }
+    }
+  }
+  ```
+
+## Logging Functions
+
+- **Consistent Logging**:
+  - ✅ DO: Use the central `log` function for all output
+  - ✅ DO: Use appropriate log levels (info, warn, error, debug)
+  - ✅ DO: Support silent mode for programmatic usage
+
+  ```javascript
+  // ✅ DO: Implement consistent logging with silent mode
+  let silentMode = false;
+  
+  function log(level, ...messages) {
+    if (silentMode && level !== 'error') {
+      return; // Suppress non-error logs in silent mode
+    }
+    
+    const timestamp = new Date().toISOString();
+    const formattedMessage = messages.join(' ');
+    
+    switch (level) {
+      case 'error':
+        console.error(`[ERROR] ${formattedMessage}`);
+        break;
+      case 'warn':
+        console.warn(`[WARN] ${formattedMessage}`);
+        break;
+      case 'info':
+        console.log(`[INFO] ${formattedMessage}`);
+        break;
+      case 'debug':
+        if (getDebugFlag()) {
+          console.log(`[DEBUG] ${formattedMessage}`);
+        }
+        break;
+      default:
+        console.log(formattedMessage);
+    }
+  }
+  
+  function enableSilentMode() {
+    silentMode = true;
+  }
+  
+  function disableSilentMode() {
+    silentMode = false;
+  }
+  
+  function isSilentMode() {
+    return silentMode;
+  }
+  ```
+
+## Task Utilities
+
+- **Task Finding and Manipulation**:
+  - ✅ DO: Use tagged task system aware functions
+  - ✅ DO: Handle both task and subtask operations
+  - ✅ DO: Validate task IDs before operations
+
+  ```javascript
+  // ✅ DO: Implement tag-aware task utilities
+  function findTaskById(tasks, taskId) {
+    if (!Array.isArray(tasks)) {
+      return null;
+    }
+    return tasks.find(task => task.id === taskId) || null;
+  }
+  
+  function findSubtaskById(tasks, parentId, subtaskId) {
+    const parentTask = findTaskById(tasks, parentId);
+    if (!parentTask || !parentTask.subtasks) {
+      return null;
+    }
+    
+    return parentTask.subtasks.find(subtask => subtask.id === subtaskId) || null;
+  }
+  
+  function getNextTaskId(tasks) {
+    if (!Array.isArray(tasks) || tasks.length === 0) {
+      return 1;
+    }
+    
+    const maxId = Math.max(...tasks.map(task => task.id));
+    return maxId + 1;
+  }
+  
+  function getNextSubtaskId(parentTask) {
+    if (!parentTask.subtasks || parentTask.subtasks.length === 0) {
+      return 1;
+    }
+    
+    const maxId = Math.max(...parentTask.subtasks.map(subtask => subtask.id));
+    return maxId + 1;
+  }
+  ```
+
+## String Utilities
+
+- **Text Processing**:
+  - ✅ DO: Handle text truncation appropriately
+  - ✅ DO: Provide consistent formatting functions
+  - ✅ DO: Support different output formats
+
+  ```javascript
+  // ✅ DO: Implement useful string utilities
+  function truncate(str, maxLength = 50) {
+    if (!str || typeof str !== 'string') {
+      return '';
+    }
+    
+    if (str.length <= maxLength) {
+      return str;
+    }
+    
+    return str.substring(0, maxLength - 3) + '...';
+  }
+  
+  function formatDuration(ms) {
+    const seconds = Math.floor(ms / 1000);
+    const minutes = Math.floor(seconds / 60);
+    const hours = Math.floor(minutes / 60);
+    
+    if (hours > 0) {
+      return `${hours}h ${minutes % 60}m ${seconds % 60}s`;
+    } else if (minutes > 0) {
+      return `${minutes}m ${seconds % 60}s`;
+    } else {
+      return `${seconds}s`;
+    }
+  }
+  
+  function capitalizeFirst(str) {
+    if (!str || typeof str !== 'string') {
+      return '';
+    }
+    
+    return str.charAt(0).toUpperCase() + str.slice(1).toLowerCase();
+  }
+  ```
+
+## Dependency Management Utilities
+
+- **Dependency Analysis**:
+  - ✅ DO: Detect circular dependencies
+  - ✅ DO: Validate dependency references
+  - ✅ DO: Support cross-tag dependency checking (future enhancement)
+
+  ```javascript
+  // ✅ DO: Implement dependency utilities
+  function findCycles(tasks) {
+    const cycles = [];
+    const visited = new Set();
+    const recStack = new Set();
+    
+    function dfs(taskId, path = []) {
+      if (recStack.has(taskId)) {
+        // Found a cycle
+        const cycleStart = path.indexOf(taskId);
+        const cycle = path.slice(cycleStart).concat([taskId]);
+        cycles.push(cycle);
+        return;
+      }
+      
+      if (visited.has(taskId)) {
+        return;
+      }
+      
+      visited.add(taskId);
+      recStack.add(taskId);
+      
+      const task = findTaskById(tasks, taskId);
+      if (task && task.dependencies) {
+        task.dependencies.forEach(depId => {
+          dfs(depId, path.concat([taskId]));
+        });
+      }
+      
+      recStack.delete(taskId);
+    }
+    
+    tasks.forEach(task => {
+      if (!visited.has(task.id)) {
+        dfs(task.id);
+      }
+    });
+    
+    return cycles;
+  }
+  
+  function validateDependencies(tasks) {
+    const validationErrors = [];
+    const taskIds = new Set(tasks.map(task => task.id));
+    
+    tasks.forEach(task => {
+      if (task.dependencies) {
+        task.dependencies.forEach(depId => {
+          if (!taskIds.has(depId)) {
+            validationErrors.push({
+              taskId: task.id,
+              invalidDependency: depId,
+              message: `Task ${task.id} depends on non-existent task ${depId}`
+            });
+          }
+        });
+      }
+    });
+    
+    return validationErrors;
+  }
+  ```
+
+## Environment and Configuration Utilities
+
+- **Environment Variable Resolution**:
+  - ✅ DO: Support both `.env` files and MCP session environment
+  - ✅ DO: Provide fallbacks for missing values
+  - ✅ DO: Handle API key resolution correctly
+
+  ```javascript
+  // ✅ DO: Implement flexible environment resolution
+  function resolveEnvVariable(key, sessionEnv = null) {
+    // First check session environment (for MCP)
+    if (sessionEnv && sessionEnv[key]) {
+      return sessionEnv[key];
+    }
+    
+    // Then check process environment
+    if (process.env[key]) {
+      return process.env[key];
+    }
+    
+    // Finally try .env file if in project root
+    try {
+      const projectRoot = findProjectRoot();
+      if (projectRoot) {
+        const envPath = path.join(projectRoot, '.env');
+        if (fs.existsSync(envPath)) {
+          const envContent = fs.readFileSync(envPath, 'utf8');
+          const lines = envContent.split('\n');
+          
+          for (const line of lines) {
+            const [envKey, envValue] = line.split('=');
+            if (envKey && envKey.trim() === key) {
+              return envValue ? envValue.trim().replace(/^["']|["']$/g, '') : undefined;
+            }
+          }
+        }
+      }
+    } catch (error) {
+      log('debug', `Error reading .env file: ${error.message}`);
+    }
+    
+    return undefined;
+  }
+  
+  function getDebugFlag() {
+    const debugFlag = resolveEnvVariable('TASKMASTER_DEBUG') || 
+                     resolveEnvVariable('DEBUG') || 
+                     'false';
+    return debugFlag.toLowerCase() === 'true';
+  }
+  ```
+
+## Export Pattern
+
+- **Module Exports**:
+  - ✅ DO: Export all utility functions explicitly
+  - ✅ DO: Group related functions logically
+  - ✅ DO: Include new tagged system utilities
+
+  ```javascript
+  // ✅ DO: Export utilities in logical groups
+  module.exports = {
+    // File system utilities
+    readJSON,
+    writeJSON,
+    findProjectRoot,
+    
+    // Tagged task system utilities
+    getTasksForTag,
+    setTasksForTag,
+    getCurrentTag,
+    performCompleteTagMigration,
+    migrateConfigJson,
+    createStateJson,
+    markMigrationForNotice,
+    
+    // Logging utilities
+    log,
+    enableSilentMode,
+    disableSilentMode,
+    isSilentMode,
+    
+    // Task utilities
+    findTaskById,
+    findSubtaskById,
+    getNextTaskId,
+    getNextSubtaskId,
+    
+    // String utilities
+    truncate,
+    formatDuration,
+    capitalizeFirst,
+    
+    // Dependency utilities
+    findCycles,
+    validateDependencies,
+    
+    // Environment utilities
+    resolveEnvVariable,
+    getDebugFlag,
+    
+    // Legacy utilities (maintained for compatibility)
+    aggregateTelemetry
+  };
+  ```
+
+Refer to [`utils.js`](mdc:scripts/modules/utils.js) for implementation examples and [`architecture.mdc`](mdc:.cursor/rules/architecture.mdc) for integration patterns.

.env.example

@@ -7,3 +7,9 @@ MISTRAL_API_KEY=YOUR_MISTRAL_KEY_HERE
 OPENROUTER_API_KEY=YOUR_OPENROUTER_KEY_HERE
 XAI_API_KEY=YOUR_XAI_KEY_HERE
 AZURE_OPENAI_API_KEY=YOUR_AZURE_KEY_HERE
+
+# Google Vertex AI Configuration
+VERTEX_PROJECT_ID=your-gcp-project-id
+VERTEX_LOCATION=us-central1
+# Optional: Path to service account credentials JSON file (alternative to API key)
+GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account-credentials.json

.github/workflows/update-models-md.yml

@@ -0,0 +1,40 @@
+name: Update models.md from supported-models.json
+
+on:
+  push:
+    branches:
+      - main
+      - next
+    paths:
+      - 'scripts/modules/supported-models.json'
+      - 'docs/scripts/models-json-to-markdown.js'
+
+jobs:
+  update_markdown:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Run transformation script
+        run: node docs/scripts/models-json-to-markdown.js
+
+      - name: Format Markdown with Prettier
+        run: npx prettier --write docs/models.md
+
+      - name: Stage docs/models.md
+        run: git add docs/models.md
+
+      - name: Commit & Push docs/models.md
+        uses: actions-js/push@master
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          branch: ${{ github.ref_name }}
+          message: 'docs: Auto-update and format models.md'
+          author_name: 'github-actions[bot]'
+          author_email: 'github-actions[bot]@users.noreply.github.com'

.gitignore

@@ -19,13 +19,26 @@ npm-debug.log*
 yarn-debug.log*
 yarn-error.log*
 lerna-debug.log*
-tests/e2e/_runs/
-tests/e2e/log/
 
 # Coverage directory used by tools like istanbul
-coverage
+coverage/
 *.lcov
 
+# Jest cache
+.jest/
+
+# Test temporary files and directories
+tests/temp/
+tests/e2e/_runs/
+tests/e2e/log/
+tests/**/*.log
+tests/**/coverage/
+
+# Test database files (if any)
+tests/**/*.db
+tests/**/*.sqlite
+tests/**/*.sqlite3
+
 # Optional npm cache directory
 .npm
 
@@ -64,3 +77,13 @@ dev-debug.log
 
 # NPMRC
 .npmrc
+
+# Added by Task Master AI
+# Editor directories and files
+.idea
+.vscode
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?

.nvmrc

@@ -0,0 +1 @@
+22 

.prettierignore

@@ -1,7 +0,0 @@
-# Ignore artifacts:
-build
-coverage
-.changeset
-tasks
-package-lock.json
-tests/fixture/*.json

.prettierrc

@@ -1,11 +0,0 @@
-{
-	"printWidth": 80,
-	"tabWidth": 2,
-	"useTabs": true,
-	"semi": true,
-	"singleQuote": true,
-	"trailingComma": "none",
-	"bracketSpacing": true,
-	"arrowParens": "always",
-	"endOfLine": "lf"
-}

.taskmaster/config.json

@@ -1,21 +1,21 @@
 {
 	"models": {
 		"main": {
-			"provider": "anthropic",
+			"provider": "vertex",
-			"modelId": "claude-3-7-sonnet-20250219",
+			"modelId": "gemini-1.5-pro-002",
-			"maxTokens": 100000,
+			"maxTokens": 50000,
 			"temperature": 0.2
 		},
 		"research": {
 			"provider": "perplexity",
-			"modelId": "sonar-pro",
+			"modelId": "sonar",
 			"maxTokens": 8700,
 			"temperature": 0.1
 		},
 		"fallback": {
 			"provider": "anthropic",
 			"modelId": "claude-3-7-sonnet-20250219",
-			"maxTokens": 8192,
+			"maxTokens": 128000,
 			"temperature": 0.2
 		}
 	},
@@ -25,8 +25,10 @@
 		"defaultSubtasks": 5,
 		"defaultPriority": "medium",
 		"projectName": "Taskmaster",
-		"ollamaBaseUrl": "http://localhost:11434/api",
+		"ollamaBaseURL": "http://localhost:11434/api",
+		"bedrockBaseURL": "https://bedrock.us-east-1.amazonaws.com",
 		"userId": "1234567890",
-		"azureOpenaiBaseUrl": "https://your-endpoint.openai.azure.com/"
+		"azureBaseURL": "https://your-endpoint.azure.com/",
+		"defaultTag": "master"
 	}
 }

.taskmaster/docs/README.md

@@ -382,25 +382,25 @@ The output report structure is:
 
 ```json
 {
-	"meta": {
+ "meta": {
-		"generatedAt": "2023-06-15T12:34:56.789Z",
+  "generatedAt": "2023-06-15T12:34:56.789Z",
-		"tasksAnalyzed": 20,
+  "tasksAnalyzed": 20,
-		"thresholdScore": 5,
+  "thresholdScore": 5,
-		"projectName": "Your Project Name",
+  "projectName": "Your Project Name",
-		"usedResearch": true
+  "usedResearch": true
-	},
+ },
-	"complexityAnalysis": [
+ "complexityAnalysis": [
-		{
+  {
-			"taskId": 8,
+   "taskId": 8,
-			"taskTitle": "Develop Implementation Drift Handling",
+   "taskTitle": "Develop Implementation Drift Handling",
-			"complexityScore": 9.5,
+   "complexityScore": 9.5,
-			"recommendedSubtasks": 6,
+   "recommendedSubtasks": 6,
-			"expansionPrompt": "Create subtasks that handle detecting...",
+   "expansionPrompt": "Create subtasks that handle detecting...",
-			"reasoning": "This task requires sophisticated logic...",
+   "reasoning": "This task requires sophisticated logic...",
-			"expansionCommand": "node scripts/dev.js expand --id=8 --num=6 --prompt=\"Create subtasks...\" --research"
+   "expansionCommand": "node scripts/dev.js expand --id=8 --num=6 --prompt=\"Create subtasks...\" --research"
-		}
+  }
-		// More tasks sorted by complexity score (highest first)
+  // More tasks sorted by complexity score (highest first)
-	]
+ ]
 }
 ```
 

.taskmaster/docs/research/2025-06-14_how-can-i-improve-the-scope-up-and-scope-down-comm.md

@@ -0,0 +1,128 @@
+---
+title: Research Session
+query: "how can i improve the scope-up and scope-down command"
+date: 6/14/2025
+time: 4:35:03 PM
+timestamp: 2025-06-14T20:35:03.231Z
+exchanges: 2
+---
+
+# Research Session
+
+## Initial Query
+
+**Question:** how can i improve the scope-up and scope-down command
+
+**Response:**
+
+## Improving the `scope-up` and `scope-down` Commands
+
+**Clarify Command Purpose and User Experience**
+
+- Ensure the commands have clear, intuitive behavior. For example, `scope-up` should consistently broaden the context or task view, while `scope-down` should reliably narrow it.
+- Provide immediate, user-friendly feedback after each command, indicating what changed (e.g., "Now viewing parent task and all subtasks" or "Focused on subtask: X").
+- Document the commands with examples in your `docs/command-reference.md` and `docs/examples.md` to help users understand their effects and use cases.
+
+**Enhance Context Awareness**
+
+- Make the commands context-sensitive: if the user is already at the top or bottom of the scope hierarchy, return a helpful message instead of failing silently.
+- Allow optional arguments to specify the exact level or target (e.g., `scope-up 2` to move up two levels, or `scope-down <subtask-id>` to jump directly to a subtask).
+
+**Robust Error Handling and Validation**
+
+- Implement checks to prevent invalid operations, such as attempting to scope up from the root or scope down when no subtasks exist.
+- Provide clear error messages and suggestions for next steps, improving user trust and reducing confusion[1][5].
+
+**Integrate with Task and Tag Systems**
+
+- Ensure `scope-up` and `scope-down` interact smoothly with your tagging and task hierarchy features. For example, scoping up from a subtask should show the parent task and its context, while scoping down should allow selection from available subtasks or related tags.
+- Consider supporting batch operations, such as scoping down into all subtasks and displaying them in a summarized view.
+
+**Improve Performance and Synchronization**
+
+- Optimize the underlying logic to minimize delays, especially in large task trees. Use asynchronous operations where possible to keep the UI responsive.
+- If the commands trigger data loading or context switching, ensure synchronization so that subsequent commands operate on the correct, updated context[2][4].
+
+**Testing and Stakeholder Feedback**
+
+- Add or expand unit and integration tests for these commands (see `tests/unit/commands.test.js` and `integration/cli/commands.test.js`) to cover edge cases and ensure reliability.
+- Gather feedback from users and stakeholders to identify pain points and desired enhancements, then iterate on the command design and implementation[1][5].
+
+**Example Improvements Table**
+
+| Area                | Current Issue                | Suggested Improvement                        |
+|---------------------|-----------------------------|----------------------------------------------|
+| User Feedback       | Minimal or unclear output    | Add explicit, contextual messages            |
+| Error Handling      | Silent failures              | Informative errors and recovery suggestions  |
+| Flexibility         | Only single-level movement   | Support multi-level and targeted navigation  |
+| Integration         | Limited context awareness    | Sync with tags, parent/child relationships   |
+| Performance         | Slow on large hierarchies    | Optimize data access and UI updates          |
+
+By focusing on these areas, you can make `scope-up` and `scope-down` more robust, user-friendly, and aligned with best practices in scope management and command design[1][5].
+
+---
+
+## Follow-up 1
+
+**Question:** how might i do this relative to the tag system?
+
+**Response:**
+
+## Integrating Scope-Up and Scope-Down with the Tag System
+
+**Conceptual Mapping**
+
+- In your project, *scope-up* and *scope-down* commands currently operate on the task hierarchy, broadening or narrowing the context by moving between parent and child tasks.
+- The tag system provides a parallel, orthogonal way to group and filter tasks—tags can represent categories, priorities, or any custom grouping, independent of strict parent/child relationships.
+
+**How to Make Scope Commands Tag-Aware**
+
+- **Scoping by Tag**: Allow users to "scope-down" into a tag, viewing only tasks associated with that tag. Conversely, "scope-up" could move from a specific tag context back to the broader task list or to a parent tag grouping if you support tag hierarchies.
+- **Tag-Scoped Views**: When a tag is active as the current scope, all navigation and operations (listing, editing, etc.) are limited to tasks with that tag. This is similar to how some systems let you set the "Tag Scope" to filter navigation and search to only tagged items[1][5].
+- **Combining Hierarchy and Tags**: Enable compound scoping, such as "all subtasks of Task X that also have Tag Y." This can be implemented by intersecting the results of hierarchical and tag-based queries.
+
+**Implementation Strategies**
+
+- **Scope Stack or Context Object**: Maintain a stack or context object that tracks both the current task scope and any active tag filters. Each scope change (up/down or tag in/out) updates this context.
+- **Commands**:
+  - `scope-down --tag <tag>`: Narrows the view to tasks with the specified tag.
+  - `scope-up --tag`: Removes the tag filter, broadening the view.
+  - `scope-down <subtask-id> --tag <tag>`: Narrows to a specific subtask *and* applies a tag filter.
+- **Tag Hierarchies (Optional)**: If your tag system supports parent/child tags or tag groups, allow "scope-up" to move from a specific tag to its parent tag or group, and "scope-down" to move into a child tag[4][5].
+
+**Example User Flows**
+
+- *Scoping Down by Tag*:  
+  User runs `scope-down --tag urgent` → Only tasks tagged "urgent" are shown.
+- *Combining Task and Tag*:  
+  User runs `scope-down <task-id> --tag frontend` → Only subtasks of `<task-id>` that are tagged "frontend" are shown.
+- *Scoping Up from Tag*:  
+  User runs `scope-up --tag` → Removes the tag filter, returning to the previous broader context.
+
+**Technical Considerations**
+
+- **Efficient Filtering**: Use indexed queries or in-memory filtering to efficiently combine tag and hierarchy filters, especially for large task sets.
+- **Feedback and UI**: Always display the current scope context (e.g., "Viewing tasks tagged 'urgent' under 'Feature X'") so users understand what they're seeing.
+- **Extensibility**: Design the scope system so new types of scopes (e.g., by status, assignee) can be added in the future, not just tags and hierarchy.
+
+**Relevant Precedents**
+
+- Tag-based file systems and management tools often implement "scopes" as dynamic groups defined by tag criteria, allowing users to build up complex views by combining tags and other filters[5].
+- Some systems allow scoping into tag management itself, where you can create, edit, or view tags and their associated objects, which could be mirrored in your CLI or UI[4].
+
+**Summary Table**
+
+| Command Example                  | Resulting Scope                                  |
+|----------------------------------|--------------------------------------------------|
+| `scope-down --tag bug`           | All tasks tagged "bug"                           |
+| `scope-down <task-id> --tag api` | Subtasks of `<task-id>` tagged "api"             |
+| `scope-up --tag`                 | Removes tag filter, returns to previous scope    |
+| `scope-down --tag frontend`      | All tasks tagged "frontend"                      |
+
+By integrating tag-based scoping, you make your scope commands more flexible and powerful, supporting both hierarchical and ad-hoc organizational strategies[1][5].
+
+
+---
+
+*Generated by Task Master Research Command*  
+*Timestamp: 2025-06-14T20:35:03.231Z*

.taskmaster/docs/research/2025-06-14_should-i-be-using-any-specific-libraries-for-this.md

@@ -0,0 +1,158 @@
+---
+title: Research Session
+query: "should i be using any specific libraries for this?"
+date: 6/14/2025
+time: 5:20:00 PM
+timestamp: 2025-06-14T21:20:00.561Z
+exchanges: 2
+---
+
+# Research Session
+
+## Initial Query
+
+**Question:** should i be using any specific libraries for this?
+
+**Response:**
+
+HELL YEAH PARTNER
+
+For implementing a GitHub Issue export feature with bidirectional linking in your project, you absolutely should use a dedicated library for interacting with the GitHub API. This will save you a ton of time, reduce boilerplate, and help you avoid common pitfalls with authentication, pagination, and error handling.
+
+## Recommended Library: PyGithub
+
+- **PyGithub** is the most widely used and well-documented Python library for accessing the GitHub REST API v3. It allows you to manage repositories, issues, user profiles, and more, all with a clean, object-oriented interface[1][2][3][5].
+- It supports all the operations you’ll need for your export feature, including creating issues, updating them, and managing references for bidirectional linking.
+
+### Key Features
+
+- **Authentication**: Easily authenticate with a personal access token.
+- **Issue Management**: Create, update, and link issues programmatically.
+- **Repository Access**: Fetch and manipulate repository data.
+- **User/Org Support**: Works for both user and organization repos.
+- **Pagination & Rate Limiting**: Handles these for you.
+
+### Example Usage
+
+```python
+from github import Github, Auth
+
+# Authenticate with a personal access token
+auth = Auth.Token("your_github_token")
+g = Github(auth=auth)
+
+# Get the repo
+repo = g.get_repo("owner/repo_name")
+
+# Create a new issue
+issue = repo.create_issue(
+    title="Exported from Task Master",
+    body="This issue was created by Task Master. [Task ID: 123]"
+)
+
+# Add a comment or update the issue to include a backlink
+issue.create_comment("Linked to Task Master task #123")
+```
+[3][5]
+
+## Why Not Use Raw Requests?
+
+- While you *can* use the `requests` library to call the GitHub API directly[4], PyGithub abstracts away authentication, error handling, and pagination, making your code much cleaner and less error-prone[2][5].
+
+## Integration Tips
+
+- Store your GitHub token securely (e.g., in environment variables).
+- Use PyGithub’s objects to fetch, create, and update issues.
+- For bidirectional linking, store the GitHub issue URL in your task data and the Task Master task ID in the GitHub issue body or as a label/comment.
+- PyGithub is actively maintained and widely used, so you’ll find plenty of support and documentation.
+
+## Installation
+
+```bash
+pip install PyGithub
+```
+[3]
+
+## Summary Table
+
+| Library   | Language | API Coverage | Ease of Use | Maintained | Docs/Support |
+|-----------|----------|--------------|-------------|------------|--------------|
+| PyGithub  | Python   | Full         | High        | Yes        | Excellent    |
+| requests  | Python   | Full (manual)| Medium      | Yes        | Good         |
+
+**Use PyGithub for all GitHub API interactions in your export/import features.** It’s the standard for Python projects and will make your implementation faster, safer, and more maintainable[1][2][3][5].
+
+---
+
+## Follow-up 1
+
+**Question:** we don't want to use py github because we have a node project
+
+**Response:**
+
+HELL YEAH PARTNER
+
+For a Node.js project, you should use a Node-native library to interact with the GitHub API instead of PyGithub, which is Python-only. The industry standard for Node.js is **Octokit**, the official GitHub SDK for JavaScript/TypeScript[1][2].
+
+## Why Use Octokit?
+
+- **Official & Complete**: Octokit is maintained by GitHub and covers all REST and GraphQL API endpoints, including issues, repositories, users, and more[1][2].
+- **Universal**: Works in Node.js, browsers, and Deno environments[2].
+- **Typed & Tested**: Comes with TypeScript declarations and 100% test coverage[2].
+- **Authentication**: Supports personal access tokens, GitHub Apps, OAuth, and more.
+- **Pagination & Error Handling**: Handles pagination and common error scenarios out of the box.
+- **Extendable**: Supports plugins and custom hooks for advanced use cases[2].
+
+## How to Use Octokit for GitHub Issue Export
+
+Install Octokit in your Node.js project:
+
+```bash
+npm install @octokit/rest
+```
+
+Basic usage for creating and linking issues:
+
+```js
+const { Octokit } = require("@octokit/rest");
+
+// Authenticate with a personal access token
+const octokit = new Octokit({ auth: process.env.GITHUB_TOKEN });
+
+// Create a new issue
+const { data: issue } = await octokit.issues.create({
+  owner: "owner",
+  repo: "repo_name",
+  title: "Exported from Task Master",
+  body: "This issue was created by Task Master. [Task ID: 123]"
+});
+
+// Add a comment for bidirectional linking
+await octokit.issues.createComment({
+  owner: "owner",
+  repo: "repo_name",
+  issue_number: issue.number,
+  body: "Linked to Task Master task #123"
+});
+```
+
+## Alternatives
+
+- **node-github**: An older library, less maintained than Octokit, but still functional for basic API access[5].
+- **Raw HTTP Requests**: You can use `node-fetch` or `axios` to call the GitHub API directly, but you’ll need to handle authentication, pagination, and error handling yourself[3]. Octokit abstracts all of this for you.
+
+## Summary Table
+
+| Library         | Language | API Coverage | Maintained | TypeScript | Docs/Support |
+|-----------------|----------|--------------|------------|------------|--------------|
+| Octokit         | Node.js  | Full         | Yes        | Yes        | Excellent    |
+| node-github     | Node.js  | Full         | No         | No         | Limited      |
+| Raw HTTP        | Node.js  | Full (manual)| N/A        | N/A        | N/A          |
+
+**Recommendation:** Use Octokit for all GitHub API interactions in your Node.js project. It’s the official, most robust, and best-supported option for your use case[1][2].
+
+
+---
+
+*Generated by Task Master Research Command*  
+*Timestamp: 2025-06-14T21:20:00.561Z*

.taskmaster/docs/research/2025-06-14_test-save-functionality.md

@@ -0,0 +1,76 @@
+---
+title: Research Session
+query: "test save functionality"
+date: 6/14/2025
+time: 5:50:23 PM
+timestamp: 2025-06-14T21:50:23.797Z
+exchanges: 1
+---
+
+# Research Session
+
+## Initial Query
+
+**Question:** test save functionality
+
+**Response:**
+
+## Testing Save Functionality in a Task Management System
+
+**Core Steps for Testing Save Functionality**
+
+- Create or update a task in the system using the CLI or UI.
+- Trigger the save operation (e.g., by issuing a command or clicking a save button).
+- Verify that the data is correctly written to the persistent storage (e.g., `tasks.json`).
+- Reload or re-query the data to ensure the saved changes persist and are accurately reflected.
+- Validate that all required fields and relationships (such as dependencies and subtasks) are preserved and correctly structured.
+
+**Key Test Scenarios**
+
+- **Basic Save:** Add a new task and confirm it appears in `tasks.json` with all fields populated.
+- **Update Save:** Modify an existing task (e.g., change status, description, or priority) and verify the changes are saved.
+- **Subtask and Dependency Preservation:** Update a parent task and ensure that completed subtasks and dependency links remain intact, especially after using commands like `updateTask`.
+- **Batch Operations:** Perform bulk updates or additions and confirm all affected tasks are saved correctly, with no data loss or corruption.
+- **Validation:** Attempt to save invalid data and ensure the system rejects it or provides meaningful error messages, confirming validation logic is enforced.
+
+**Recommended Practices**
+
+- Use automated tests to simulate save operations for various scenarios, including edge cases (e.g., circular dependencies, missing required fields).
+- After each save, reload the data and compare it to the expected state to ensure integrity.
+- Log all save operations and errors for traceability and debugging.
+- Regularly back up the `tasks.json` file to prevent data loss during testing and development.
+
+**Relevant Features from Industry Standards**
+
+- Task management systems typically provide robust save and update mechanisms, ensuring that all task attributes (including dependencies, subtasks, and comments) are consistently maintained[1][2][5].
+- Validation and error handling are critical to prevent corrupt or incomplete saves, especially when handling complex relationships or batch operations[1][5].
+- User feedback (such as success messages or error alerts) is important for confirming save actions and guiding users in case of issues[1][2].
+
+**Example Test Case**
+
+1. Create a task with subtasks and dependencies.
+2. Mark some subtasks as complete.
+3. Use the `updateTask` command to modify the parent task.
+4. Save and reload the data.
+5. Assert that:
+   - The parent task reflects the updates.
+   - Completed subtasks remain marked as complete.
+   - Dependencies are unchanged and valid.
+
+**Summary Table: Save Functionality Test Aspects**
+
+| Aspect                | What to Test                                      | Expected Outcome                        |
+|-----------------------|---------------------------------------------------|-----------------------------------------|
+| Basic Save            | Add/update task, save, reload                     | Data persists and matches expectations  |
+| Subtask Preservation  | Update parent, check subtask status               | Completed subtasks remain complete      |
+| Dependency Handling   | Save with dependencies, reload                    | Dependencies are intact and valid       |
+| Batch Operations      | Bulk save/update, reload                          | All changes persist, no data loss       |
+| Validation            | Save invalid data                                 | Error is raised, data not corrupted     |
+
+These steps and scenarios ensure that the save functionality is robust, reliable, and meets the requirements of a modern task management system[1][2][5].
+
+
+---
+
+*Generated by Task Master Research Command*  
+*Timestamp: 2025-06-14T21:50:23.797Z*

.taskmaster/docs/research/2025-06-14_test-the-fix-for-duplicate-saves-final-test.md

@@ -0,0 +1,81 @@
+---
+title: Research Session
+query: "test the fix for duplicate saves - final test"
+date: 6/14/2025
+time: 6:10:00 PM
+timestamp: 2025-06-14T22:10:00.394Z
+exchanges: 1
+---
+
+# Research Session
+
+## Initial Query
+
+**Question:** test the fix for duplicate saves - final test
+
+**Response:**
+
+## Steps to Test the Fix for Duplicate Saves
+
+**1. Prepare a Clean Test Environment**
+- Ensure the tasks.json file and any related data stores are in a known, clean state with no pre-existing duplicate entries.
+- Back up the current tasks.json in case rollback is needed.
+
+**2. Define Test Scenarios**
+- Attempt to save a new task with unique data.
+- Attempt to save a task with the same ID or unique identifier as an existing task (simulate a duplicate).
+- Attempt to save a task with the same title or content but a different ID (to test if the fix is based on ID or content).
+- Simultaneously trigger multiple save operations (if the system supports concurrency) to test race conditions.
+
+**3. Execute Manual and Automated Tests**
+- Use the application's UI or API to create and save tasks as per the scenarios above.
+- For each save operation, check the tasks.json file or the data store to verify:
+  - No duplicate entries are created.
+  - Existing tasks are not overwritten unless intended (e.g., for updates).
+  - The system returns appropriate error messages or warnings when a duplicate save is attempted.
+
+**4. Validate System Behavior**
+- Confirm that after all test operations, each task in tasks.json is unique according to the defined criteria (ID, title, or other unique fields).
+- If the system is designed to merge duplicates, verify that merging occurs as expected.
+- If the system is designed to reject duplicates, ensure that the rejection is clear and no duplicate is present.
+
+**5. Test Edge Cases**
+- Attempt to save tasks with minor variations (e.g., whitespace differences, case sensitivity) to ensure the duplicate detection logic is robust.
+- Test with large numbers of tasks to ensure performance and correctness at scale.
+
+**6. Review Logs and Error Handling**
+- Check application logs for any errors or warnings related to duplicate saves.
+- Ensure that error handling is user-friendly and provides actionable feedback.
+
+**7. Regression Testing**
+- Run the full suite of task operations (create, update, delete) to ensure the fix for duplicate saves does not introduce new issues elsewhere in the system.
+
+## Additional Best Practices
+
+- Communicate test results with the team to confirm the fix is effective and to prevent future regressions[1][2][5].
+- Consider implementing automated duplicate detection as part of the save operation to prevent future issues[2][3].
+- Document the test cases and results for future reference and audits.
+
+## Example Test Case Table
+
+| Test Scenario                        | Expected Result                | Actual Result | Pass/Fail |
+|--------------------------------------|-------------------------------|---------------|-----------|
+| Save unique task                     | Task saved                    |               |           |
+| Save duplicate task (same ID)        | Duplicate rejected/merged     |               |           |
+| Save duplicate task (same title)     | Duplicate rejected/merged     |               |           |
+| Simultaneous saves (race condition)  | Only one unique task present  |               |           |
+| Save with minor variations           | No false positives/negatives  |               |           |
+
+Fill in the "Actual Result" and "Pass/Fail" columns during testing.
+
+## Action Items
+
+- Complete all test scenarios above.
+- Document any issues found and retest after fixes.
+- Confirm with stakeholders before closing the issue.
+
+
+---
+
+*Generated by Task Master Research Command*  
+*Timestamp: 2025-06-14T22:10:00.394Z*

.taskmaster/docs/task-template-importing-prd.txt

@@ -0,0 +1,471 @@
+# Task Template Importing System - Product Requirements Document
+
+<context>
+# Overview  
+The Task Template Importing system enables seamless integration of external task templates into the Task Master CLI through automatic file discovery. This system allows users to drop task template files into the tasks directory and immediately access them as new tag contexts without manual import commands or configuration. The solution addresses the need for multi-project task management, team collaboration through shared templates, and clean separation between permanent tasks and temporary project contexts.
+
+# Core Features  
+## Silent Task Template Discovery
+- **What it does**: Automatically scans for `tasks_*.json` files in the tasks directory during tag operations
+- **Why it's important**: Eliminates friction in adding new task contexts and enables zero-configuration workflow
+- **How it works**: File pattern matching extracts tag names from filenames and validates against internal tag keys
+
+## External Tag Resolution System
+- **What it does**: Provides fallback mechanism to external files when tags are not found in main tasks.json
+- **Why it's important**: Maintains clean separation between core tasks and project-specific templates
+- **How it works**: Tag resolution logic checks external files as secondary source while preserving main file precedence
+
+## Read-Only External Tag Access
+- **What it does**: Allows viewing and switching to external tags while preventing modifications
+- **Why it's important**: Protects template integrity and prevents accidental changes to shared templates
+- **How it works**: All task modifications route to main tasks.json regardless of current tag context
+
+## Tag Precedence Management
+- **What it does**: Ensures main tasks.json tags override external files with same tag names
+- **Why it's important**: Prevents conflicts and maintains data integrity
+- **How it works**: Priority system where main file tags take precedence over external file tags
+
+# User Experience  
+## User Personas
+- **Solo Developer**: Manages multiple projects with different task contexts
+- **Team Lead**: Shares standardized task templates across team members
+- **Project Manager**: Organizes tasks by project phases or feature branches
+
+## Key User Flows
+### Template Addition Flow
+1. User receives or creates a `tasks_projectname.json` file
+2. User drops file into `.taskmaster/tasks/` directory
+3. Tag becomes immediately available via `task-master use-tag projectname`
+4. User can list, view, and switch to external tag without configuration
+
+### Template Usage Flow
+1. User runs `task-master tags` to see available tags including external ones
+2. External tags display with `(imported)` indicator
+3. User switches to external tag with `task-master use-tag projectname`
+4. User can view tasks but modifications are routed to main tasks.json
+
+## UI/UX Considerations
+- External tags clearly marked with `(imported)` suffix in listings
+- Visual indicators distinguish between main and external tags
+- Error messages guide users when external files are malformed
+- Read-only warnings when attempting to modify external tag contexts
+</context>
+
+<PRD>
+# Technical Architecture  
+## System Components
+1. **External File Discovery Engine**
+   - File pattern scanner for `tasks_*.json` files
+   - Tag name extraction from filenames using regex
+   - Dynamic tag registry combining main and external sources
+   - Error handling for malformed external files
+
+2. **Enhanced Tag Resolution System**
+   - Fallback mechanism to external files when tags not found in main tasks.json
+   - Precedence management ensuring main file tags override external files
+   - Read-only access enforcement for external tags
+   - Tag metadata preservation during discovery operations
+
+3. **Silent Discovery Integration**
+   - Automatic scanning during tag-related operations
+   - Seamless integration with existing tag management functions
+   - Zero-configuration workflow requiring no manual import commands
+   - Dynamic tag availability without restart requirements
+
+## Data Models
+
+### External Task File Structure
+```json
+{
+  "meta": {
+    "projectName": "External Project Name",
+    "version": "1.0.0",
+    "templateSource": "external",
+    "createdAt": "ISO-8601 timestamp"
+  },
+  "tags": {
+    "projectname": {
+      "meta": {
+        "name": "Project Name",
+        "description": "Project description",
+        "createdAt": "ISO-8601 timestamp"
+      },
+      "tasks": [
+        // Array of task objects
+      ]
+    },
+    "master": {
+      // This section is ignored to prevent conflicts
+    }
+  }
+}
+```
+
+### Enhanced Tag Registry Model
+```json
+{
+  "mainTags": [
+    {
+      "name": "master",
+      "source": "main",
+      "taskCount": 150,
+      "isActive": true
+    }
+  ],
+  "externalTags": [
+    {
+      "name": "projectname",
+      "source": "external",
+      "filename": "tasks_projectname.json",
+      "taskCount": 25,
+      "isReadOnly": true
+    }
+  ]
+}
+```
+
+## APIs and Integrations
+1. **File System Discovery API**
+   - Directory scanning with pattern matching
+   - JSON file validation and parsing
+   - Error handling for corrupted or malformed files
+   - File modification time tracking for cache invalidation
+
+2. **Enhanced Tag Management API**
+   - `scanForExternalTaskFiles(projectRoot)` - Discover external template files
+   - `getExternalTagsFromFiles(projectRoot)` - Extract tag names from external files
+   - `readExternalTagData(projectRoot, tagName)` - Read specific external tag data
+   - `getAvailableTags(projectRoot)` - Combined main and external tag listing
+
+3. **Tag Resolution Enhancement**
+   - Modified `readJSON()` with external file fallback
+   - Enhanced `tags()` function with external tag display
+   - Updated `useTag()` function supporting external tag switching
+   - Read-only enforcement for external tag operations
+
+## Infrastructure Requirements
+1. **File System Access**
+   - Read permissions for tasks directory
+   - JSON parsing capabilities
+   - Pattern matching and regex support
+   - Error handling for file system operations
+
+2. **Backward Compatibility**
+   - Existing tag operations continue unchanged
+   - Main tasks.json structure preserved
+   - No breaking changes to current workflows
+   - Graceful degradation when external files unavailable
+
+# Development Roadmap  
+## Phase 1: Core External File Discovery (Foundation)
+1. **External File Scanner Implementation**
+   - Create `scanForExternalTaskFiles()` function in utils.js
+   - Implement file pattern matching for `tasks_*.json` files
+   - Add error handling for file system access issues
+   - Test with various filename patterns and edge cases
+
+2. **Tag Name Extraction System**
+   - Implement `getExternalTagsFromFiles()` function
+   - Create regex pattern for extracting tag names from filenames
+   - Add validation to ensure tag names match internal tag key format
+   - Handle special characters and invalid filename patterns
+
+3. **External Tag Data Reader**
+   - Create `readExternalTagData()` function
+   - Implement JSON parsing with error handling
+   - Add validation for required tag structure
+   - Ignore 'master' key in external files to prevent conflicts
+
+## Phase 2: Tag Resolution Enhancement (Core Integration)
+1. **Enhanced Tag Registry**
+   - Implement `getAvailableTags()` function combining main and external sources
+   - Create tag metadata structure including source information
+   - Add deduplication logic prioritizing main tags over external
+   - Implement caching mechanism for performance optimization
+
+2. **Modified readJSON Function**
+   - Add external file fallback when tag not found in main tasks.json
+   - Maintain precedence rule: main tasks.json overrides external files
+   - Preserve existing error handling and validation patterns
+   - Ensure read-only access for external tags
+
+3. **Tag Listing Enhancement**
+   - Update `tags()` function to display external tags with `(imported)` indicator
+   - Show external tag metadata and task counts
+   - Maintain current tag highlighting and sorting functionality
+   - Add visual distinction between main and external tags
+
+## Phase 3: User Interface Integration (User Experience)
+1. **Tag Switching Enhancement**
+   - Update `useTag()` function to support external tag switching
+   - Add read-only warnings when switching to external tags
+   - Update state.json with external tag context information
+   - Maintain current tag switching behavior for main tags
+
+2. **Error Handling and User Feedback**
+   - Implement comprehensive error messages for malformed external files
+   - Add user guidance for proper external file structure
+   - Create warnings for read-only operations on external tags
+   - Ensure graceful degradation when external files are corrupted
+
+3. **Documentation and Help Integration**
+   - Update command help text to include external tag information
+   - Add examples of external file structure and usage
+   - Create troubleshooting guide for common external file issues
+   - Document file naming conventions and best practices
+
+## Phase 4: Advanced Features and Optimization (Enhancement)
+1. **Performance Optimization**
+   - Implement file modification time caching
+   - Add lazy loading for external tag data
+   - Optimize file scanning for directories with many files
+   - Create efficient tag resolution caching mechanism
+
+2. **Advanced External File Features**
+   - Support for nested external file directories
+   - Batch external file validation and reporting
+   - External file metadata display and management
+   - Integration with version control ignore patterns
+
+3. **Team Collaboration Features**
+   - Shared external file validation
+   - External file conflict detection and resolution
+   - Team template sharing guidelines and documentation
+   - Integration with git workflows for template management
+
+# Logical Dependency Chain
+## Foundation Layer (Must Be Built First)
+1. **External File Scanner** 
+   - Core requirement for all other functionality
+   - Provides the discovery mechanism for external template files
+   - Must handle file system access and pattern matching reliably
+
+2. **Tag Name Extraction**
+   - Depends on file scanner functionality
+   - Required for identifying available external tags
+   - Must validate tag names against internal format requirements
+
+3. **External Tag Data Reader**
+   - Depends on tag name extraction
+   - Provides access to external tag content
+   - Must handle JSON parsing and validation safely
+
+## Integration Layer (Builds on Foundation)
+4. **Enhanced Tag Registry**
+   - Depends on all foundation components
+   - Combines main and external tag sources
+   - Required for unified tag management across the system
+
+5. **Modified readJSON Function**
+   - Depends on enhanced tag registry
+   - Provides fallback mechanism for tag resolution
+   - Critical for maintaining backward compatibility
+
+6. **Tag Listing Enhancement**
+   - Depends on enhanced tag registry
+   - Provides user visibility into external tags
+   - Required for user discovery of available templates
+
+## User Experience Layer (Completes the Feature)
+7. **Tag Switching Enhancement**
+   - Depends on modified readJSON and tag listing
+   - Enables user interaction with external tags
+   - Must enforce read-only access properly
+
+8. **Error Handling and User Feedback**
+   - Can be developed in parallel with other UX components
+   - Enhances reliability and user experience
+   - Should be integrated throughout development process
+
+9. **Documentation and Help Integration**
+   - Should be developed alongside implementation
+   - Required for user adoption and proper usage
+   - Can be completed in parallel with advanced features
+
+## Optimization Layer (Performance and Advanced Features)
+10. **Performance Optimization**
+    - Can be developed after core functionality is stable
+    - Improves user experience with large numbers of external files
+    - Not blocking for initial release
+
+11. **Advanced External File Features**
+    - Can be developed independently after core features
+    - Enhances power user workflows
+    - Optional for initial release
+
+12. **Team Collaboration Features**
+    - Depends on stable core functionality
+    - Enhances team workflows and template sharing
+    - Can be prioritized based on user feedback
+
+# Risks and Mitigations  
+## Technical Challenges
+
+### File System Performance
+**Risk**: Scanning for external files on every tag operation could impact performance with large directories.
+**Mitigation**: 
+- Implement file modification time caching to avoid unnecessary rescans
+- Use lazy loading for external tag data - only read when accessed
+- Add configurable limits on number of external files to scan
+- Optimize file pattern matching with efficient regex patterns
+
+### External File Corruption
+**Risk**: Malformed or corrupted external JSON files could break tag operations.
+**Mitigation**:
+- Implement robust JSON parsing with comprehensive error handling
+- Add file validation before attempting to parse external files
+- Gracefully skip corrupted files and continue with valid ones
+- Provide clear error messages guiding users to fix malformed files
+
+### Tag Name Conflicts
+**Risk**: External files might contain tag names that conflict with main tasks.json tags.
+**Mitigation**:
+- Implement strict precedence rule: main tasks.json always overrides external files
+- Add warnings when external tags are ignored due to conflicts
+- Document naming conventions to avoid common conflicts
+- Provide validation tools to check for potential conflicts
+
+## MVP Definition
+
+### Core Feature Scope
+**Risk**: Including too many advanced features could delay the core functionality.
+**Mitigation**:
+- Define MVP as basic external file discovery + tag switching
+- Focus on the silent discovery mechanism as the primary value proposition
+- Defer advanced features like nested directories and batch operations
+- Ensure each phase delivers complete, usable functionality
+
+### User Experience Complexity
+**Risk**: The read-only nature of external tags might confuse users.
+**Mitigation**:
+- Provide clear visual indicators for external tags in all interfaces
+- Add explicit warnings when users attempt to modify external tag contexts
+- Document the read-only behavior and its rationale clearly
+- Consider future enhancement for external tag modification workflows
+
+### Backward Compatibility
+**Risk**: Changes to tag resolution logic might break existing workflows.
+**Mitigation**:
+- Maintain existing tag operations unchanged for main tasks.json
+- Add external file support as enhancement, not replacement
+- Test thoroughly with existing task structures and workflows
+- Provide migration path if any breaking changes are necessary
+
+## Resource Constraints
+
+### Development Complexity
+**Risk**: Integration with existing tag management system could be complex.
+**Mitigation**:
+- Phase implementation to minimize risk of breaking existing functionality
+- Create comprehensive test suite covering both main and external tag scenarios
+- Use feature flags to enable/disable external file support during development
+- Implement thorough error handling to prevent system failures
+
+### File System Dependencies
+**Risk**: Different operating systems might handle file operations differently.
+**Mitigation**:
+- Use Node.js built-in file system APIs for cross-platform compatibility
+- Test on multiple operating systems (Windows, macOS, Linux)
+- Handle file path separators and naming conventions properly
+- Add fallback mechanisms for file system access issues
+
+### User Adoption
+**Risk**: Users might not understand or adopt the external file template system.
+**Mitigation**:
+- Create clear documentation with practical examples
+- Provide sample external template files for common use cases
+- Integrate help and guidance directly into the CLI interface
+- Gather user feedback early and iterate on the user experience
+
+# Appendix  
+## External File Naming Convention
+
+### Filename Pattern
+- **Format**: `tasks_[tagname].json`
+- **Examples**: `tasks_feature-auth.json`, `tasks_v2-migration.json`, `tasks_project-alpha.json`
+- **Validation**: Tag name must match internal tag key format (alphanumeric, hyphens, underscores)
+
+### File Structure Requirements
+```json
+{
+  "meta": {
+    "projectName": "Required: Human-readable project name",
+    "version": "Optional: Template version",
+    "templateSource": "Optional: Source identifier",
+    "createdAt": "Optional: ISO-8601 timestamp"
+  },
+  "tags": {
+    "[tagname]": {
+      "meta": {
+        "name": "Required: Tag display name",
+        "description": "Optional: Tag description",
+        "createdAt": "Optional: ISO-8601 timestamp"
+      },
+      "tasks": [
+        // Required: Array of task objects following standard task structure
+      ]
+    }
+  }
+}
+```
+
+## Implementation Functions Specification
+
+### Core Discovery Functions
+```javascript
+// Scan tasks directory for external template files
+function scanForExternalTaskFiles(projectRoot) {
+  // Returns: Array of external file paths
+}
+
+// Extract tag names from external filenames
+function getExternalTagsFromFiles(projectRoot) {
+  // Returns: Array of external tag names
+}
+
+// Read specific external tag data
+function readExternalTagData(projectRoot, tagName) {
+  // Returns: Tag data object or null if not found
+}
+
+// Get combined main and external tags
+function getAvailableTags(projectRoot) {
+  // Returns: Combined tag registry with metadata
+}
+```
+
+### Integration Points
+```javascript
+// Enhanced readJSON with external fallback
+function readJSON(projectRoot, tag = null) {
+  // Modified to check external files when tag not found in main
+}
+
+// Enhanced tags listing with external indicators
+function tags(projectRoot, options = {}) {
+  // Modified to display external tags with (imported) suffix
+}
+
+// Enhanced tag switching with external support
+function useTag(projectRoot, tagName) {
+  // Modified to support switching to external tags (read-only)
+}
+```
+
+## Error Handling Specifications
+
+### File System Errors
+- **ENOENT**: External file not found - gracefully skip and continue
+- **EACCES**: Permission denied - warn user and continue with available files
+- **EISDIR**: Directory instead of file - skip and continue scanning
+
+### JSON Parsing Errors
+- **SyntaxError**: Malformed JSON - skip file and log warning with filename
+- **Missing required fields**: Skip file and provide specific error message
+- **Invalid tag structure**: Skip file and guide user to correct format
+
+### Tag Conflict Resolution
+- **Duplicate tag names**: Main tasks.json takes precedence, log warning
+- **Invalid tag names**: Skip external file and provide naming guidance
+- **Master key in external**: Ignore master key, process other tags normally
+</PRD> 

.taskmaster/reports/task-complexity-report.json

@@ -0,0 +1,373 @@
+{
+	"meta": {
+		"generatedAt": "2025-05-27T16:34:53.088Z",
+		"tasksAnalyzed": 1,
+		"totalTasks": 84,
+		"analysisCount": 45,
+		"thresholdScore": 5,
+		"projectName": "Taskmaster",
+		"usedResearch": true
+	},
+	"complexityAnalysis": [
+		{
+			"taskId": 24,
+			"taskTitle": "Implement AI-Powered Test Generation Command",
+			"complexityScore": 7,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "Break down the implementation of the AI-powered test generation command into detailed subtasks covering: command structure setup, AI prompt engineering, test file generation logic, integration with Claude API, and comprehensive error handling.",
+			"reasoning": "This task involves complex integration with an AI service (Claude), requires sophisticated prompt engineering, and needs to generate structured code files. The existing 3 subtasks are a good start but could be expanded to include more detailed steps for AI integration, error handling, and test file formatting."
+		},
+		{
+			"taskId": 26,
+			"taskTitle": "Implement Context Foundation for AI Operations",
+			"complexityScore": 6,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "The current 4 subtasks for implementing the context foundation appear comprehensive. Consider if any additional subtasks are needed for testing, documentation, or integration with existing systems.",
+			"reasoning": "This task involves creating a foundation for context integration with several well-defined components. The existing 4 subtasks cover the main implementation areas (context-file flag, cursor rules integration, context extraction utility, and command handler updates). The complexity is moderate as it requires careful integration with existing systems but has clear requirements."
+		},
+		{
+			"taskId": 27,
+			"taskTitle": "Implement Context Enhancements for AI Operations",
+			"complexityScore": 7,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "The current 4 subtasks for implementing context enhancements appear well-structured. Consider if any additional subtasks are needed for testing, documentation, or performance optimization.",
+			"reasoning": "This task builds upon the foundation from Task #26 and adds more sophisticated context handling features. The 4 existing subtasks cover the main implementation areas (code context extraction, task history context, PRD context integration, and context formatting). The complexity is higher than the foundation task due to the need for intelligent context selection and optimization."
+		},
+		{
+			"taskId": 28,
+			"taskTitle": "Implement Advanced ContextManager System",
+			"complexityScore": 8,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "The current 5 subtasks for implementing the advanced ContextManager system appear comprehensive. Consider if any additional subtasks are needed for testing, documentation, or backward compatibility with previous context implementations.",
+			"reasoning": "This task represents the most complex phase of the context implementation, requiring a sophisticated class design, optimization algorithms, and integration with multiple systems. The 5 existing subtasks cover the core implementation areas, but the complexity is high due to the need for intelligent context prioritization, token management, and performance monitoring."
+		},
+		{
+			"taskId": 40,
+			"taskTitle": "Implement 'plan' Command for Task Implementation Planning",
+			"complexityScore": 5,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "The current 4 subtasks for implementing the 'plan' command appear well-structured. Consider if any additional subtasks are needed for testing, documentation, or integration with existing task management workflows.",
+			"reasoning": "This task involves creating a new command that leverages AI to generate implementation plans. The existing 4 subtasks cover the main implementation areas (retrieving task content, generating plans with AI, formatting in XML, and error handling). The complexity is moderate as it builds on existing patterns for task updates but requires careful AI integration."
+		},
+		{
+			"taskId": 41,
+			"taskTitle": "Implement Visual Task Dependency Graph in Terminal",
+			"complexityScore": 8,
+			"recommendedSubtasks": 10,
+			"expansionPrompt": "The current 10 subtasks for implementing the visual task dependency graph appear comprehensive. Consider if any additional subtasks are needed for performance optimization with large graphs or additional visualization options.",
+			"reasoning": "This task involves creating a sophisticated visualization system for terminal display, which is inherently complex due to layout algorithms, ASCII/Unicode rendering, and handling complex dependency relationships. The 10 existing subtasks cover all major aspects of implementation, from CLI interface to accessibility features."
+		},
+		{
+			"taskId": 42,
+			"taskTitle": "Implement MCP-to-MCP Communication Protocol",
+			"complexityScore": 9,
+			"recommendedSubtasks": 8,
+			"expansionPrompt": "The current 8 subtasks for implementing the MCP-to-MCP communication protocol appear well-structured. Consider if any additional subtasks are needed for security hardening, performance optimization, or comprehensive documentation.",
+			"reasoning": "This task involves designing and implementing a complex communication protocol between different MCP tools and servers. It requires sophisticated adapter patterns, client-server architecture, and handling of multiple operational modes. The complexity is very high due to the need for standardization, security, and backward compatibility."
+		},
+		{
+			"taskId": 44,
+			"taskTitle": "Implement Task Automation with Webhooks and Event Triggers",
+			"complexityScore": 8,
+			"recommendedSubtasks": 7,
+			"expansionPrompt": "The current 7 subtasks for implementing task automation with webhooks appear comprehensive. Consider if any additional subtasks are needed for security testing, rate limiting implementation, or webhook monitoring tools.",
+			"reasoning": "This task involves creating a sophisticated event system with webhooks for integration with external services. The complexity is high due to the need for secure authentication, reliable delivery mechanisms, and handling of various webhook formats and protocols. The existing subtasks cover the main implementation areas but security and monitoring could be emphasized more."
+		},
+		{
+			"taskId": 45,
+			"taskTitle": "Implement GitHub Issue Import Feature",
+			"complexityScore": 6,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "The current 5 subtasks for implementing the GitHub issue import feature appear well-structured. Consider if any additional subtasks are needed for handling GitHub API rate limiting, caching, or supporting additional issue metadata.",
+			"reasoning": "This task involves integrating with the GitHub API to import issues as tasks. The complexity is moderate as it requires API authentication, data mapping, and error handling. The existing 5 subtasks cover the main implementation areas from design to end-to-end implementation."
+		},
+		{
+			"taskId": 46,
+			"taskTitle": "Implement ICE Analysis Command for Task Prioritization",
+			"complexityScore": 7,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "The current 5 subtasks for implementing the ICE analysis command appear comprehensive. Consider if any additional subtasks are needed for visualization of ICE scores or integration with other prioritization methods.",
+			"reasoning": "This task involves creating an AI-powered analysis system for task prioritization using the ICE methodology. The complexity is high due to the need for sophisticated scoring algorithms, AI integration, and report generation. The existing subtasks cover the main implementation areas from algorithm design to integration with existing systems."
+		},
+		{
+			"taskId": 47,
+			"taskTitle": "Enhance Task Suggestion Actions Card Workflow",
+			"complexityScore": 6,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "The current 6 subtasks for enhancing the task suggestion actions card workflow appear well-structured. Consider if any additional subtasks are needed for user testing, accessibility improvements, or performance optimization.",
+			"reasoning": "This task involves redesigning the UI workflow for task expansion and management. The complexity is moderate as it requires careful UX design and state management but builds on existing components. The 6 existing subtasks cover the main implementation areas from design to testing."
+		},
+		{
+			"taskId": 48,
+			"taskTitle": "Refactor Prompts into Centralized Structure",
+			"complexityScore": 4,
+			"recommendedSubtasks": 3,
+			"expansionPrompt": "The current 3 subtasks for refactoring prompts into a centralized structure appear appropriate. Consider if any additional subtasks are needed for prompt versioning, documentation, or testing.",
+			"reasoning": "This task involves a straightforward refactoring to improve code organization. The complexity is relatively low as it primarily involves moving code rather than creating new functionality. The 3 existing subtasks cover the main implementation areas from directory structure to integration."
+		},
+		{
+			"taskId": 49,
+			"taskTitle": "Implement Code Quality Analysis Command",
+			"complexityScore": 8,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "The current 6 subtasks for implementing the code quality analysis command appear comprehensive. Consider if any additional subtasks are needed for performance optimization with large codebases or integration with existing code quality tools.",
+			"reasoning": "This task involves creating a sophisticated code analysis system with pattern recognition, best practice verification, and AI-powered recommendations. The complexity is high due to the need for code parsing, complex analysis algorithms, and integration with AI services. The existing subtasks cover the main implementation areas from algorithm design to user interface."
+		},
+		{
+			"taskId": 50,
+			"taskTitle": "Implement Test Coverage Tracking System by Task",
+			"complexityScore": 9,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "The current 5 subtasks for implementing the test coverage tracking system appear well-structured. Consider if any additional subtasks are needed for integration with CI/CD systems, performance optimization, or visualization tools.",
+			"reasoning": "This task involves creating a complex system that maps test coverage to specific tasks and subtasks. The complexity is very high due to the need for sophisticated data structures, integration with coverage tools, and AI-powered test generation. The existing subtasks are comprehensive and cover the main implementation areas from data structure design to AI integration."
+		},
+		{
+			"taskId": 51,
+			"taskTitle": "Implement Perplexity Research Command",
+			"complexityScore": 6,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "The current 5 subtasks for implementing the Perplexity research command appear comprehensive. Consider if any additional subtasks are needed for caching optimization, result formatting, or integration with other research tools.",
+			"reasoning": "This task involves creating a new command that integrates with the Perplexity AI API for research. The complexity is moderate as it requires API integration, context extraction, and result formatting. The 5 existing subtasks cover the main implementation areas from API client to caching system."
+		},
+		{
+			"taskId": 52,
+			"taskTitle": "Implement Task Suggestion Command for CLI",
+			"complexityScore": 6,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "The current 5 subtasks for implementing the task suggestion command appear well-structured. Consider if any additional subtasks are needed for suggestion quality evaluation, user feedback collection, or integration with existing task workflows.",
+			"reasoning": "This task involves creating a new CLI command that generates contextually relevant task suggestions using AI. The complexity is moderate as it requires AI integration, context collection, and interactive CLI interfaces. The existing subtasks cover the main implementation areas from data collection to user interface."
+		},
+		{
+			"taskId": 53,
+			"taskTitle": "Implement Subtask Suggestion Feature for Parent Tasks",
+			"complexityScore": 6,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "The current 6 subtasks for implementing the subtask suggestion feature appear comprehensive. Consider if any additional subtasks are needed for suggestion quality metrics, user feedback collection, or performance optimization.",
+			"reasoning": "This task involves creating a feature that suggests contextually relevant subtasks for parent tasks. The complexity is moderate as it builds on existing task management systems but requires sophisticated AI integration and context analysis. The 6 existing subtasks cover the main implementation areas from validation to testing."
+		},
+		{
+			"taskId": 55,
+			"taskTitle": "Implement Positional Arguments Support for CLI Commands",
+			"complexityScore": 5,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "The current 5 subtasks for implementing positional arguments support appear well-structured. Consider if any additional subtasks are needed for backward compatibility testing, documentation updates, or user experience improvements.",
+			"reasoning": "This task involves modifying the command parsing logic to support positional arguments alongside the existing flag-based syntax. The complexity is moderate as it requires careful handling of different argument styles and edge cases. The 5 existing subtasks cover the main implementation areas from analysis to documentation."
+		},
+		{
+			"taskId": 57,
+			"taskTitle": "Enhance Task-Master CLI User Experience and Interface",
+			"complexityScore": 7,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "The current 6 subtasks for enhancing the CLI user experience appear comprehensive. Consider if any additional subtasks are needed for accessibility testing, internationalization, or performance optimization.",
+			"reasoning": "This task involves a significant overhaul of the CLI interface to improve user experience. The complexity is high due to the breadth of changes (logging, visual elements, interactive components, etc.) and the need for consistent design across all commands. The 6 existing subtasks cover the main implementation areas from log management to help systems."
+		},
+		{
+			"taskId": 60,
+			"taskTitle": "Implement Mentor System with Round-Table Discussion Feature",
+			"complexityScore": 8,
+			"recommendedSubtasks": 7,
+			"expansionPrompt": "The current 7 subtasks for implementing the mentor system appear well-structured. Consider if any additional subtasks are needed for mentor personality consistency, discussion quality evaluation, or performance optimization with multiple mentors.",
+			"reasoning": "This task involves creating a sophisticated mentor simulation system with round-table discussions. The complexity is high due to the need for personality simulation, complex LLM integration, and structured discussion management. The 7 existing subtasks cover the main implementation areas from architecture to testing."
+		},
+		{
+			"taskId": 62,
+			"taskTitle": "Add --simple Flag to Update Commands for Direct Text Input",
+			"complexityScore": 4,
+			"recommendedSubtasks": 8,
+			"expansionPrompt": "The current 8 subtasks for implementing the --simple flag appear comprehensive. Consider if any additional subtasks are needed for user experience testing or documentation updates.",
+			"reasoning": "This task involves adding a simple flag option to bypass AI processing for updates. The complexity is relatively low as it primarily involves modifying existing command handlers and adding a flag. The 8 existing subtasks are very detailed and cover all aspects of implementation from command parsing to testing."
+		},
+		{
+			"taskId": 63,
+			"taskTitle": "Add pnpm Support for the Taskmaster Package",
+			"complexityScore": 5,
+			"recommendedSubtasks": 8,
+			"expansionPrompt": "The current 8 subtasks for adding pnpm support appear comprehensive. Consider if any additional subtasks are needed for CI/CD integration, performance comparison, or documentation updates.",
+			"reasoning": "This task involves ensuring the package works correctly with pnpm as an alternative package manager. The complexity is moderate as it requires careful testing of installation processes and scripts across different environments. The 8 existing subtasks cover all major aspects from documentation to binary verification."
+		},
+		{
+			"taskId": 64,
+			"taskTitle": "Add Yarn Support for Taskmaster Installation",
+			"complexityScore": 5,
+			"recommendedSubtasks": 9,
+			"expansionPrompt": "The current 9 subtasks for adding Yarn support appear comprehensive. Consider if any additional subtasks are needed for performance testing, CI/CD integration, or compatibility with different Yarn versions.",
+			"reasoning": "This task involves ensuring the package works correctly with Yarn as an alternative package manager. The complexity is moderate as it requires careful testing of installation processes and scripts across different environments. The 9 existing subtasks are very detailed and cover all aspects from configuration to testing."
+		},
+		{
+			"taskId": 65,
+			"taskTitle": "Add Bun Support for Taskmaster Installation",
+			"complexityScore": 6,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "The current 6 subtasks for adding Bun support appear well-structured. Consider if any additional subtasks are needed for handling Bun-specific issues, performance testing, or documentation updates.",
+			"reasoning": "This task involves adding support for the newer Bun package manager. The complexity is slightly higher than the other package manager tasks due to Bun's differences from Node.js and potential compatibility issues. The 6 existing subtasks cover the main implementation areas from research to documentation."
+		},
+		{
+			"taskId": 67,
+			"taskTitle": "Add CLI JSON output and Cursor keybindings integration",
+			"complexityScore": 5,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "The current 5 subtasks for implementing JSON output and Cursor keybindings appear well-structured. Consider if any additional subtasks are needed for testing across different operating systems, documentation updates, or user experience improvements.",
+			"reasoning": "This task involves two distinct features: adding JSON output to CLI commands and creating a keybindings installation command. The complexity is moderate as it requires careful handling of different output formats and OS-specific file paths. The 5 existing subtasks cover the main implementation areas for both features."
+		},
+		{
+			"taskId": 68,
+			"taskTitle": "Ability to create tasks without parsing PRD",
+			"complexityScore": 3,
+			"recommendedSubtasks": 2,
+			"expansionPrompt": "The current 2 subtasks for implementing task creation without PRD appear appropriate. Consider if any additional subtasks are needed for validation, error handling, or integration with existing task management workflows.",
+			"reasoning": "This task involves a relatively simple modification to allow task creation without requiring a PRD document. The complexity is low as it primarily involves creating a form interface and saving functionality. The 2 existing subtasks cover the main implementation areas of UI design and data saving."
+		},
+		{
+			"taskId": 72,
+			"taskTitle": "Implement PDF Generation for Project Progress and Dependency Overview",
+			"complexityScore": 7,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "The current 6 subtasks for implementing PDF generation appear comprehensive. Consider if any additional subtasks are needed for handling large projects, additional visualization options, or integration with existing reporting tools.",
+			"reasoning": "This task involves creating a feature to generate PDF reports of project progress and dependency visualization. The complexity is high due to the need for PDF generation, data collection, and visualization integration. The 6 existing subtasks cover the main implementation areas from library selection to export options."
+		},
+		{
+			"taskId": 75,
+			"taskTitle": "Integrate Google Search Grounding for Research Role",
+			"complexityScore": 5,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "The current 4 subtasks for integrating Google Search Grounding appear well-structured. Consider if any additional subtasks are needed for testing with different query types, error handling, or performance optimization.",
+			"reasoning": "This task involves updating the AI service layer to enable Google Search Grounding for research roles. The complexity is moderate as it requires careful integration with the existing AI service architecture and conditional logic. The 4 existing subtasks cover the main implementation areas from service layer modification to testing."
+		},
+		{
+			"taskId": 76,
+			"taskTitle": "Develop E2E Test Framework for Taskmaster MCP Server (FastMCP over stdio)",
+			"complexityScore": 8,
+			"recommendedSubtasks": 7,
+			"expansionPrompt": "The current 7 subtasks for developing the E2E test framework appear comprehensive. Consider if any additional subtasks are needed for test result reporting, CI/CD integration, or performance benchmarking.",
+			"reasoning": "This task involves creating a sophisticated end-to-end testing framework for the MCP server. The complexity is high due to the need for subprocess management, protocol handling, and robust test case definition. The 7 existing subtasks cover the main implementation areas from architecture to documentation."
+		},
+		{
+			"taskId": 77,
+			"taskTitle": "Implement AI Usage Telemetry for Taskmaster (with external analytics endpoint)",
+			"complexityScore": 7,
+			"recommendedSubtasks": 18,
+			"expansionPrompt": "The current 18 subtasks for implementing AI usage telemetry appear very comprehensive. Consider if any additional subtasks are needed for security hardening, privacy compliance, or user feedback collection.",
+			"reasoning": "This task involves creating a telemetry system to track AI usage metrics. The complexity is high due to the need for secure data transmission, comprehensive data collection, and integration across multiple commands. The 18 existing subtasks are extremely detailed and cover all aspects of implementation from core utility to provider-specific updates."
+		},
+		{
+			"taskId": 80,
+			"taskTitle": "Implement Unique User ID Generation and Storage During Installation",
+			"complexityScore": 4,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "The current 5 subtasks for implementing unique user ID generation appear well-structured. Consider if any additional subtasks are needed for privacy compliance, security auditing, or integration with the telemetry system.",
+			"reasoning": "This task involves generating and storing a unique user identifier during installation. The complexity is relatively low as it primarily involves UUID generation and configuration file management. The 5 existing subtasks cover the main implementation areas from script structure to documentation."
+		},
+		{
+			"taskId": 81,
+			"taskTitle": "Task #81: Implement Comprehensive Local Telemetry System with Future Server Integration Capability",
+			"complexityScore": 8,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "The current 6 subtasks for implementing the comprehensive local telemetry system appear well-structured. Consider if any additional subtasks are needed for data migration, storage optimization, or visualization tools.",
+			"reasoning": "This task involves expanding the telemetry system to capture additional metrics and implement local storage with future server integration capability. The complexity is high due to the breadth of data collection, storage requirements, and privacy considerations. The 6 existing subtasks cover the main implementation areas from data collection to user-facing benefits."
+		},
+		{
+			"taskId": 82,
+			"taskTitle": "Update supported-models.json with token limit fields",
+			"complexityScore": 3,
+			"recommendedSubtasks": 1,
+			"expansionPrompt": "This task appears straightforward enough to be implemented without further subtasks. Focus on researching accurate token limit values for each model and ensuring backward compatibility.",
+			"reasoning": "This task involves a simple update to the supported-models.json file to include new token limit fields. The complexity is low as it primarily involves research and data entry. No subtasks are necessary as the task is well-defined and focused."
+		},
+		{
+			"taskId": 83,
+			"taskTitle": "Update config-manager.js defaults and getters",
+			"complexityScore": 4,
+			"recommendedSubtasks": 1,
+			"expansionPrompt": "This task appears straightforward enough to be implemented without further subtasks. Focus on updating the DEFAULTS object and related getter functions while maintaining backward compatibility.",
+			"reasoning": "This task involves updating the config-manager.js module to replace maxTokens with more specific token limit fields. The complexity is relatively low as it primarily involves modifying existing code rather than creating new functionality. No subtasks are necessary as the task is well-defined and focused."
+		},
+		{
+			"taskId": 84,
+			"taskTitle": "Implement token counting utility",
+			"complexityScore": 5,
+			"recommendedSubtasks": 1,
+			"expansionPrompt": "This task appears well-defined enough to be implemented without further subtasks. Focus on implementing accurate token counting for different models and proper fallback mechanisms.",
+			"reasoning": "This task involves creating a utility function to count tokens for different AI models. The complexity is moderate as it requires integration with the tiktoken library and handling different tokenization schemes. No subtasks are necessary as the task is well-defined and focused."
+		},
+		{
+			"taskId": 69,
+			"taskTitle": "Enhance Analyze Complexity for Specific Task IDs",
+			"complexityScore": 7,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "Break down the task 'Enhance Analyze Complexity for Specific Task IDs' into 6 subtasks focusing on: 1) Core logic modification to accept ID parameters, 2) Report merging functionality, 3) CLI interface updates, 4) MCP tool integration, 5) Documentation updates, and 6) Comprehensive testing across all components.",
+			"reasoning": "This task involves modifying existing functionality across multiple components (core logic, CLI, MCP) with complex logic for filtering tasks and merging reports. The implementation requires careful handling of different parameter combinations and edge cases. The task has interdependent components that need to work together seamlessly, and the report merging functionality adds significant complexity."
+		},
+		{
+			"taskId": 70,
+			"taskTitle": "Implement 'diagram' command for Mermaid diagram generation",
+			"complexityScore": 6,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "Break down the 'diagram' command implementation into 5 subtasks: 1) Command interface and parameter handling, 2) Task data extraction and transformation to Mermaid syntax, 3) Diagram rendering with status color coding, 4) Output formatting and file export functionality, and 5) Error handling and edge case management.",
+			"reasoning": "This task requires implementing a new feature rather than modifying existing code, which reduces complexity from integration challenges. However, it involves working with visualization logic, dependency mapping, and multiple output formats. The color coding based on status and handling of dependency relationships adds moderate complexity. The task is well-defined but requires careful attention to diagram formatting and error handling."
+		},
+		{
+			"taskId": 85,
+			"taskTitle": "Update ai-services-unified.js for dynamic token limits",
+			"complexityScore": 7,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "Break down the update of ai-services-unified.js for dynamic token limits into subtasks such as: (1) Import and integrate the token counting utility, (2) Refactor _unifiedServiceRunner to calculate and enforce dynamic token limits, (3) Update error handling for token limit violations, (4) Add and verify logging for token usage, (5) Write and execute tests for various prompt and model scenarios.",
+			"reasoning": "This task involves significant code changes to a core function, integration of a new utility, dynamic logic for multiple models, and robust error handling. It also requires comprehensive testing for edge cases and integration, making it moderately complex and best managed by splitting into focused subtasks."
+		},
+		{
+			"taskId": 87,
+			"taskTitle": "Implement validation and error handling",
+			"complexityScore": 5,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Decompose this task into: (1) Add validation logic for model and config loading, (2) Implement error handling and fallback mechanisms, (3) Enhance logging and reporting for token usage, (4) Develop helper functions for configuration suggestions and improvements.",
+			"reasoning": "This task is primarily about adding validation, error handling, and logging. While important for robustness, the logic is straightforward and can be modularized into a few clear subtasks."
+		},
+		{
+			"taskId": 89,
+			"taskTitle": "Introduce Prioritize Command with Enhanced Priority Levels",
+			"complexityScore": 6,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "Expand this task into: (1) Implement the prioritize command with all required flags and shorthands, (2) Update CLI output and help documentation for new priority levels, (3) Ensure backward compatibility with existing commands, (4) Add error handling for invalid inputs, (5) Write and run tests for all command scenarios.",
+			"reasoning": "This CLI feature requires command parsing, updating internal logic for new priority levels, documentation, and robust error handling. The complexity is moderate due to the need for backward compatibility and comprehensive testing."
+		},
+		{
+			"taskId": 90,
+			"taskTitle": "Implement Subtask Progress Analyzer and Reporting System",
+			"complexityScore": 8,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "Break down the analyzer implementation into: (1) Design and implement progress tracking logic, (2) Develop status validation and issue detection, (3) Build the reporting system with multiple output formats, (4) Integrate analyzer with the existing task management system, (5) Optimize for performance and scalability, (6) Write unit, integration, and performance tests.",
+			"reasoning": "This is a complex, multi-faceted feature involving data analysis, reporting, integration, and performance optimization. It touches many parts of the system and requires careful design, making it one of the most complex tasks in the list."
+		},
+		{
+			"taskId": 91,
+			"taskTitle": "Implement Move Command for Tasks and Subtasks",
+			"complexityScore": 7,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "Expand this task into: (1) Implement move logic for tasks and subtasks, (2) Handle edge cases (invalid ids, non-existent parents, circular dependencies), (3) Update CLI to support move command with flags, (4) Ensure data integrity and update relationships, (5) Write and execute tests for various move scenarios.",
+			"reasoning": "Moving tasks and subtasks requires careful handling of hierarchical data, edge cases, and data integrity. The command must be robust and user-friendly, necessitating multiple focused subtasks for safe implementation."
+		},
+		{
+			"taskId": 92,
+			"taskTitle": "Add Global Joke Flag to All CLI Commands",
+			"complexityScore": 8,
+			"recommendedSubtasks": 7,
+			"expansionPrompt": "Break down the implementation of the global --joke flag into the following subtasks: (1) Update CLI foundation to support global flags, (2) Develop the joke-service module with joke management and category support, (3) Integrate joke output into existing output utilities, (4) Update all CLI commands for joke flag compatibility, (5) Add configuration options for joke categories and custom jokes, (6) Implement comprehensive testing (flag recognition, output, content, integration, performance, regression), (7) Update documentation and usage examples.",
+			"reasoning": "This task requires changes across the CLI foundation, output utilities, all command modules, and configuration management. It introduces a new service module, global flag handling, and output logic that must not interfere with existing features (including JSON output). The need for robust testing and backward compatibility further increases complexity. The scope spans multiple code areas and requires careful integration, justifying a high complexity score and a detailed subtask breakdown to manage risk and ensure maintainability.[2][3][5]"
+		},
+		{
+			"taskId": 94,
+			"taskTitle": "Implement Standalone 'research' CLI Command for AI-Powered Queries",
+			"complexityScore": 7,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "Break down the implementation of the 'research' CLI command into logical subtasks covering command registration, parameter handling, context gathering, AI service integration, output formatting, and documentation.",
+			"reasoning": "This task has moderate to high complexity (7/10) due to multiple interconnected components: CLI argument parsing, integration with AI services, context gathering from various sources, and output formatting with different modes. The cyclomatic complexity would be significant with multiple decision paths for handling different flags and options. The task requires understanding existing patterns and extending the codebase in a consistent manner, suggesting the need for careful decomposition into manageable subtasks."
+		},
+		{
+			"taskId": 86,
+			"taskTitle": "Implement GitHub Issue Export Feature",
+			"complexityScore": 9,
+			"recommendedSubtasks": 10,
+			"expansionPrompt": "Break down the implementation of the GitHub Issue Export Feature into detailed subtasks covering: command structure and CLI integration, GitHub API client development, authentication and error handling, task-to-issue mapping logic, content formatting and markdown conversion, bidirectional linking and metadata management, extensible architecture and adapter interfaces, configuration and settings management, documentation, and comprehensive testing (unit, integration, edge cases, performance).",
+			"reasoning": "This task involves designing and implementing a robust, extensible export system with deep integration into GitHub, including bidirectional workflows, complex data mapping, error handling, and support for future platforms. The requirements span CLI design, API integration, content transformation, metadata management, extensibility, configuration, and extensive testing. The breadth and depth of these requirements, along with the need for maintainability and future extensibility, place this task at a high complexity level. Breaking it into at least 10 subtasks will ensure each major component and concern is addressed systematically, reducing risk and improving quality."
+		}
+	]
+}

.taskmaster/reports/task-complexity-report_test-prd-tag.json

@@ -0,0 +1,53 @@
+{
+	"meta": {
+		"generatedAt": "2025-06-13T06:52:00.611Z",
+		"tasksAnalyzed": 5,
+		"totalTasks": 5,
+		"analysisCount": 5,
+		"thresholdScore": 5,
+		"projectName": "Taskmaster",
+		"usedResearch": true
+	},
+	"complexityAnalysis": [
+		{
+			"taskId": 1,
+			"taskTitle": "Setup Project Repository and Node.js Environment",
+			"complexityScore": 4,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "Break down the setup process into subtasks such as initializing npm, creating directory structure, installing dependencies, configuring package.json, adding configuration files, and setting up the main entry point.",
+			"reasoning": "This task involves several standard setup steps that are well-defined and sequential, with low algorithmic complexity but moderate procedural detail. Each step is independent and can be assigned as a subtask, making the overall complexity moderate."
+		},
+		{
+			"taskId": 2,
+			"taskTitle": "Implement Core Functionality and CLI Interface",
+			"complexityScore": 7,
+			"recommendedSubtasks": 7,
+			"expansionPrompt": "Expand into subtasks for implementing main logic, designing CLI commands, creating the CLI entry point, integrating business logic, adding error handling, formatting output, and ensuring CLI executability.",
+			"reasoning": "This task requires both application logic and user interface (CLI) development, including error handling and integration. The need to coordinate between core logic and CLI, plus ensuring usability, increases complexity and warrants detailed subtasking."
+		},
+		{
+			"taskId": 3,
+			"taskTitle": "Implement Testing Suite and Validation",
+			"complexityScore": 6,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "Divide into subtasks for configuring Jest, writing unit tests, writing integration tests, testing CLI commands, setting up coverage reporting, and preparing test fixtures/mocks.",
+			"reasoning": "Comprehensive testing involves multiple types of tests and configuration steps. While each is straightforward, the breadth of coverage and need for automation and validation increases the overall complexity."
+		},
+		{
+			"taskId": 4,
+			"taskTitle": "Setup Node.js Project with CLI Interface",
+			"complexityScore": 5,
+			"recommendedSubtasks": 7,
+			"expansionPrompt": "Break down into subtasks for npm initialization, package.json setup, directory structure creation, dependency installation, CLI entry point creation, package.json bin configuration, and CLI executability.",
+			"reasoning": "This task combines project setup with initial CLI implementation. While each step is standard, the integration of CLI elements adds a layer of complexity beyond a basic setup."
+		},
+		{
+			"taskId": 5,
+			"taskTitle": "Implement Core Functionality with Testing",
+			"complexityScore": 8,
+			"recommendedSubtasks": 8,
+			"expansionPrompt": "Expand into subtasks for implementing each feature (A, B, C), setting up the testing framework, writing tests for each feature, integrating CLI with core logic, and adding coverage reporting.",
+			"reasoning": "This task requires simultaneous development of multiple features, integration with CLI, and comprehensive testing. The coordination and depth required for both implementation and validation make it the most complex among the listed tasks."
+		}
+	]
+}

.taskmaster/state.json

@@ -0,0 +1,9 @@
+{
+	"currentTag": "master",
+	"lastSwitched": "2025-06-14T20:37:15.456Z",
+	"branchTagMapping": {
+		"v017-adds": "v017-adds",
+		"next": "next"
+	},
+	"migrationNoticeShown": true
+}

.taskmaster/tasks/task_001_test-tag.txt

@@ -0,0 +1,23 @@
+# 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 +1,804 @@
 # task-master-ai
 
+## 0.17.1
+
+### Patch Changes
+
+- [#789](https://github.com/eyaltoledano/claude-task-master/pull/789) [`8cde6c2`](https://github.com/eyaltoledano/claude-task-master/commit/8cde6c27087f401d085fe267091ae75334309d96) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix contextGatherer bug when adding a task `Cannot read properties of undefined (reading 'forEach')`
+
+## 0.17.0
+
+### Minor Changes
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add comprehensive AI-powered research command with intelligent context gathering and interactive follow-ups.
+
+  The new `research` command provides AI-powered research capabilities that automatically gather relevant project context to answer your questions. The command intelligently selects context from multiple sources and supports interactive follow-up questions in CLI mode.
+
+  **Key Features:**
+
+  - **Intelligent Task Discovery**: Automatically finds relevant tasks and subtasks using fuzzy search based on your query keywords, supplementing any explicitly provided task IDs
+  - **Multi-Source Context**: Gathers context from tasks, files, project structure, and custom text to provide comprehensive answers
+  - **Interactive Follow-ups**: CLI users can ask follow-up questions that build on the conversation history while allowing fresh context discovery for each question
+  - **Flexible Detail Levels**: Choose from low (concise), medium (balanced), or high (comprehensive) response detail levels
+  - **Token Transparency**: Displays detailed token breakdown showing context size, sources, and estimated costs
+  - **Enhanced Display**: Syntax-highlighted code blocks and structured output with clear visual separation
+
+  **Usage Examples:**
+
+  ```bash
+  # Basic research with auto-discovered context
+  task-master research "How should I implement user authentication?"
+
+  # Research with specific task context
+  task-master research "What's the best approach for this?" --id=15,23.2
+
+  # Research with file context and project tree
+  task-master research "How does the current auth system work?" --files=src/auth.js,config/auth.json --tree
+
+  # Research with custom context and low detail
+  task-master research "Quick implementation steps?" --context="Using JWT tokens" --detail=low
+  ```
+
+  **Context Sources:**
+
+  - **Tasks**: Automatically discovers relevant tasks/subtasks via fuzzy search, plus any explicitly specified via `--id`
+  - **Files**: Include specific files via `--files` for code-aware responses
+  - **Project Tree**: Add `--tree` to include project structure overview
+  - **Custom Context**: Provide additional context via `--context` for domain-specific information
+
+  **Interactive Features (CLI only):**
+
+  - Follow-up questions that maintain conversation history
+  - Fresh fuzzy search for each follow-up to discover newly relevant tasks
+  - Cumulative context building across the conversation
+  - Clean visual separation between exchanges
+  - **Save to Tasks**: Save entire research conversations (including follow-ups) directly to task or subtask details with timestamps
+  - **Clean Menu Interface**: Streamlined inquirer-based menu for follow-up actions without redundant UI elements
+
+  **Save Functionality:**
+
+  The research command now supports saving complete conversation threads to tasks or subtasks:
+
+  - Save research results and follow-up conversations to any task (e.g., "15") or subtask (e.g., "15.2")
+  - Automatic timestamping and formatting of conversation history
+  - Validation of task/subtask existence before saving
+  - Appends to existing task details without overwriting content
+  - Supports both CLI interactive mode and MCP programmatic access via `--save-to` flag
+
+  **Enhanced CLI Options:**
+
+  ```bash
+  # Auto-save research results to a task
+  task-master research "Implementation approach?" --save-to=15
+
+  # Combine auto-save with context gathering
+  task-master research "How to optimize this?" --id=23 --save-to=23.1
+  ```
+
+  **MCP Integration:**
+
+  - `saveTo` parameter for automatic saving to specified task/subtask ID
+  - Structured response format with telemetry data
+  - Silent operation mode for programmatic usage
+  - Full feature parity with CLI except interactive follow-ups
+
+  The research command integrates with the existing AI service layer and supports all configured AI providers. Both CLI and MCP interfaces provide comprehensive research capabilities with intelligent context gathering and flexible output options.
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Enhance update-task with --append flag for timestamped task updates
+
+  Adds the `--append` flag to `update-task` command, enabling it to behave like `update-subtask` with timestamped information appending. This provides more flexible task updating options:
+
+  **CLI Enhancement:**
+
+  - `task-master update-task --id=5 --prompt="New info"` - Full task update (existing behavior)
+  - `task-master update-task --id=5 --append --prompt="Progress update"` - Append timestamped info to task details
+
+  **Full MCP Integration:**
+
+  - MCP tool `update_task` now supports `append` parameter
+  - Seamless integration with Cursor and other MCP clients
+  - Consistent behavior between CLI and MCP interfaces
+
+  Instead of requiring separate subtask creation for progress tracking, you can now append timestamped information directly to parent tasks while preserving the option for comprehensive task updates.
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add --tag flag support to core commands for multi-context task management. Commands like parse-prd, analyze-complexity, and others now support targeting specific task lists, enabling rapid prototyping and parallel development workflows.
+
+  Key features:
+
+  - parse-prd --tag=feature-name: Parse PRDs into separate task contexts on the fly
+  - analyze-complexity --tag=branch: Generate tag-specific complexity reports
+  - All task operations can target specific contexts while preserving other lists
+  - Non-existent tags are created automatically for seamless workflow
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Introduces Tagged Lists: AI Multi-Context Task Management System
+
+  This major feature release introduces Tagged Lists, a comprehensive system that transforms Taskmaster into a multi-context task management powerhouse. You can now organize tasks into completely isolated contexts, enabling parallel (agentic) development workflows, team collaboration, and project experimentation without conflicts.
+
+  **🏷️ Tagged Task Lists Architecture:**
+
+  The new tagged system fundamentally improves how tasks are organized:
+
+  - **Legacy Format**: `{ "tasks": [...] }`
+  - **New Tagged Format**: `{ "master": { "tasks": [...], "metadata": {...} }, "feature-xyz": { "tasks": [...], "metadata": {...} } }`
+  - **Automatic Migration**: Existing projects will seamlessly migrate to tagged format with zero user intervention
+  - **State Management**: New `.taskmaster/state.json` tracks current tag, last switched time, migration status and more.
+  - **Configuration Integration**: Enhanced `.taskmaster/config.json` with tag-specific settings and defaults.
+
+  By default, your existing task list will be migrated to the `master` tag.
+
+  **🚀 Complete Tag Management Suite:**
+
+  **Core Tag Commands:**
+
+  - `task-master tags [--show-metadata]` - List all tags with task counts, completion stats, and metadata
+  - `task-master add-tag <name> [options]` - Create new tag contexts with optional task copying
+  - `task-master delete-tag <name> [--yes]` - Delete tags (and attached tasks) with double confirmation protection
+  - `task-master use-tag <name>` - Switch contexts and immediately see next available task
+  - `task-master rename-tag <old> <new>` - Rename tags with automatic current tag reference updates
+  - `task-master copy-tag <source> <target> [options]` - Duplicate tag contexts for experimentation
+
+  **🤖 Full MCP Integration for Tag Management:**
+
+  Task Master's multi-context capabilities are now fully exposed through the MCP server, enabling powerful agentic workflows:
+
+  - **`list_tags`**: List all available tag contexts.
+  - **`add_tag`**: Programmatically create new tags.
+  - **`delete_tag`**: Remove tag contexts.
+  - **`use_tag`**: Switch the agent's active task context.
+  - **`rename_tag`**: Rename existing tags.
+  - **`copy_tag`**: Duplicate entire task contexts for experimentation.
+
+  **Tag Creation Options:**
+
+  - `--copy-from-current` - Copy tasks from currently active tag
+  - `--copy-from=<tag>` - Copy tasks from specific tag
+  - `--from-branch` - Creates a new tag using the active git branch name (for `add-tag` only)
+  - `--description="<text>"` - Add custom tag descriptions
+  - Empty tag creation for fresh contexts
+
+  **🎯 Universal --tag Flag Support:**
+
+  Every task operation now supports tag-specific execution:
+
+  - `task-master list --tag=feature-branch` - View tasks in specific context
+  - `task-master add-task --tag=experiment --prompt="..."` - Create tasks in specific tag
+  - `task-master parse-prd document.txt --tag=v2-redesign` - Parse PRDs into dedicated contexts
+  - `task-master analyze-complexity --tag=performance-work` - Generate tag-specific reports
+  - `task-master set-status --tag=hotfix --id=5 --status=done` - Update tasks in specific contexts
+  - `task-master expand --tag=research --id=3` - Break down tasks within tag contexts
+
+  This way you or your agent can store out of context tasks into the appropriate tags for later, allowing you to maintain a groomed and scoped master list. Focus on value, not chores.
+
+  **📊 Enhanced Workflow Features:**
+
+  **Smart Context Switching:**
+
+  - `use-tag` command shows immediate next task after switching
+  - Automatic tag creation when targeting non-existent tags
+  - Current tag persistence across terminal sessions
+  - Branch-tag mapping for future Git integration
+
+  **Intelligent File Management:**
+
+  - Tag-specific complexity reports: `task-complexity-report_tagname.json`
+  - Master tag uses default filenames: `task-complexity-report.json`
+  - Automatic file isolation prevents cross-tag contamination
+
+  **Advanced Confirmation Logic:**
+
+  - Commands only prompt when target tag has existing tasks
+  - Empty tags allow immediate operations without confirmation
+  - Smart append vs overwrite detection
+
+  **🔄 Seamless Migration & Compatibility:**
+
+  **Zero-Disruption Migration:**
+
+  - Existing `tasks.json` files automatically migrate on first command
+  - Master tag receives proper metadata (creation date, description)
+  - Migration notice shown once with helpful explanation
+  - All existing commands work identically to before
+
+  **State Management:**
+
+  - `.taskmaster/state.json` tracks current tag and migration status
+  - Automatic state creation and maintenance
+  - Branch-tag mapping foundation for Git integration
+  - Migration notice tracking to avoid repeated notifications
+  - Grounds for future context additions
+
+  **Backward Compatibility:**
+
+  - All existing workflows continue unchanged
+  - Legacy commands work exactly as before
+  - Gradual adoption - users can ignore tags entirely if desired
+  - No breaking changes to existing tasks or file formats
+
+  **💡 Real-World Use Cases:**
+
+  **Team Collaboration:**
+
+  - `task-master add-tag alice --copy-from-current` - Create teammate-specific contexts
+  - `task-master add-tag bob --copy-from=master` - Onboard new team members
+  - `task-master use-tag alice` - Switch to teammate's work context
+
+  **Feature Development:**
+
+  - `task-master parse-prd feature-spec.txt --tag=user-auth` - Dedicated feature planning
+  - `task-master add-tag experiment --copy-from=user-auth` - Safe experimentation
+  - `task-master analyze-complexity --tag=user-auth` - Feature-specific analysis
+
+  **Release Management:**
+
+  - `task-master add-tag v2.0 --description="Next major release"` - Version-specific planning
+  - `task-master copy-tag master v2.1` - Release branch preparation
+  - `task-master use-tag hotfix` - Emergency fix context
+
+  **Project Phases:**
+
+  - `task-master add-tag research --description="Discovery phase"` - Research tasks
+  - `task-master add-tag implementation --copy-from=research` - Development phase
+  - `task-master add-tag testing --copy-from=implementation` - QA phase
+
+  **🛠️ Technical Implementation:**
+
+  **Data Structure:**
+
+  - Tagged format with complete isolation between contexts
+  - Rich metadata per tag (creation date, description, update tracking)
+  - Automatic metadata enhancement for existing tags
+  - Clean separation of tag data and internal state
+
+  **Performance Optimizations:**
+
+  - Dynamic task counting without stored counters
+  - Efficient tag resolution and caching
+  - Minimal file I/O with smart data loading
+  - Responsive table layouts adapting to terminal width
+
+  **Error Handling:**
+
+  - Comprehensive validation for tag names (alphanumeric, hyphens, underscores)
+  - Reserved name protection (master, main, default)
+  - Graceful handling of missing tags and corrupted data
+  - Detailed error messages with suggested corrections
+
+  This release establishes the foundation for advanced multi-context workflows while maintaining the simplicity and power that makes Task Master effective for individual developers.
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Research Save-to-File Feature & Critical MCP Tag Corruption Fix
+
+  **🔬 New Research Save-to-File Functionality:**
+
+  Added comprehensive save-to-file capability to the research command, enabling users to preserve research sessions for future reference and documentation.
+
+  **CLI Integration:**
+
+  - New `--save-file` flag for `task-master research` command
+  - Consistent with existing `--save` and `--save-to` flags for intuitive usage
+  - Interactive "Save to file" option in follow-up questions menu
+
+  **MCP Integration:**
+
+  - New `saveToFile` boolean parameter for the `research` MCP tool
+  - Enables programmatic research saving for AI agents and integrated tools
+
+  **File Management:**
+
+  - Automatically creates `.taskmaster/docs/research/` directory structure
+  - Generates timestamped, slugified filenames (e.g., `2025-01-13_what-is-typescript.md`)
+  - Comprehensive Markdown format with metadata headers including query, timestamp, and context sources
+  - Clean conversation history formatting without duplicate information
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - No longer automatically creates individual task files as they are not used by the applicatoin. You can still generate them anytime using the `generate` command.
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Enhanced get-task/show command to support comma-separated task IDs for efficient batch operations
+
+  **New Features:**
+
+  - **Multiple Task Retrieval**: Pass comma-separated IDs to get/show multiple tasks at once (e.g., `task-master show 1,3,5` or MCP `get_task` with `id: "1,3,5"`)
+  - **Smart Display Logic**: Single ID shows detailed view, multiple IDs show compact summary table with interactive options
+  - **Batch Action Menu**: Interactive menu for multiple tasks with copy-paste ready commands for common operations (mark as done/in-progress, expand all, view dependencies, etc.)
+  - **MCP Array Response**: MCP tool returns structured array of task objects for efficient AI agent context gathering
+
+  **Benefits:**
+
+  - **Faster Context Gathering**: AI agents can collect multiple tasks/subtasks in one call instead of iterating
+  - **Improved Workflow**: Interactive batch operations reduce repetitive command execution
+  - **Better UX**: Responsive layout adapts to terminal width, maintains consistency with existing UI patterns
+  - **API Efficiency**: RESTful array responses in MCP format enable more sophisticated integrations
+
+  This enhancement maintains full backward compatibility while significantly improving efficiency for both human users and AI agents working with multiple tasks.
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds support for filtering tasks by multiple statuses at once using comma-separated statuses.
+
+  Example: `cancelled,deferred`
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds tag to CLI and MCP outputs/responses so you know which tag you are performing operations on.
+
+### Patch Changes
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`5ec1f61`](https://github.com/eyaltoledano/claude-task-master/commit/5ec1f61c13f468648b7fdc8fa112e95aec25f76d) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Fix Cursor deeplink installation by providing copy-paste instructions for GitHub compatibility
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Fix critical bugs in task move functionality:
+
+  - **Fixed moving tasks to become subtasks of empty parents**: When moving a task to become a subtask of a parent that had no existing subtasks (e.g., task 89 → task 98.1), the operation would fail with validation errors.
+  - **Fixed moving subtasks between parents**: Subtasks can now be properly moved between different parent tasks, including to parents that previously had no subtasks.
+  - **Improved comma-separated batch moves**: Multiple tasks can now be moved simultaneously using comma-separated IDs (e.g., "88,90" → "92,93") with proper error handling and atomic operations.
+
+  These fixes enables proper task hierarchy reorganization for corner cases that were previously broken.
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`d76bea4`](https://github.com/eyaltoledano/claude-task-master/commit/d76bea49b381c523183f39e33c2a4269371576ed) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Update o3 model price
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`0849c0c`](https://github.com/eyaltoledano/claude-task-master/commit/0849c0c2cedb16ac44ba5cc2d109625a9b4efd67) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Fixes issue with expand CLI command "Complexity report not found"
+
+  - Closes #735
+  - Closes #728
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Fix issue with generate command which was creating tasks in the legacy tasks location.
+
+      - No longer creates individual task files automatically. You can still use `generate` if you need to create our update your task files.
+
+- [#779](https://github.com/eyaltoledano/claude-task-master/pull/779) [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Improves dependency management when moving tasks by updating subtask dependencies that reference sibling subtasks by their old parent-based ID
+
+- Updated dependencies [[`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f), [`5ec1f61`](https://github.com/eyaltoledano/claude-task-master/commit/5ec1f61c13f468648b7fdc8fa112e95aec25f76d), [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f), [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f), [`d76bea4`](https://github.com/eyaltoledano/claude-task-master/commit/d76bea49b381c523183f39e33c2a4269371576ed), [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f), [`0849c0c`](https://github.com/eyaltoledano/claude-task-master/commit/0849c0c2cedb16ac44ba5cc2d109625a9b4efd67), [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f), [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f), [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f), [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f), [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f), [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f), [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f), [`c0b3f43`](https://github.com/eyaltoledano/claude-task-master/commit/c0b3f432a60891550b00acb113dc877bd432995f)]:
+  - task-master-ai@0.17.0
+
+## 0.16.2
+
+### Patch Changes
+
+- [#695](https://github.com/eyaltoledano/claude-task-master/pull/695) [`1ece6f1`](https://github.com/eyaltoledano/claude-task-master/commit/1ece6f19048df6ae2a0b25cbfb84d2c0f430642c) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - improve findTasks algorithm for resolving tasks path
+
+- [#695](https://github.com/eyaltoledano/claude-task-master/pull/695) [`ee0be04`](https://github.com/eyaltoledano/claude-task-master/commit/ee0be04302cc602246de5cd296291db69bc8b300) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix update tool on MCP giving `No valid tasks found`
+
+- [#699](https://github.com/eyaltoledano/claude-task-master/pull/699) [`27edbd8`](https://github.com/eyaltoledano/claude-task-master/commit/27edbd8f3fe5e2ac200b80e7f27f4c0e74a074d6) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Enhanced add-task fuzzy search intelligence and improved user experience
+
+  **Smarter Task Discovery:**
+
+  - Remove hardcoded category system that always matched "Task management"
+  - Eliminate arbitrary limits on fuzzy search results (5→25 high relevance, 3→10 medium relevance, 8→20 detailed tasks)
+  - Improve semantic weighting in Fuse.js search (details=3, description=2, title=1.5) for better relevance
+  - Generate context-driven task recommendations based on true semantic similarity
+
+  **Enhanced Terminal Experience:**
+
+  - Fix duplicate banner display issue that was "eating" terminal history (closes #553)
+  - Remove console.clear() and redundant displayBanner() calls from UI functions
+  - Preserve command history for better development workflow
+  - Streamline banner display across all commands (list, next, show, set-status, clear-subtasks, dependency commands)
+
+  **Visual Improvements:**
+
+  - Replace emoji complexity indicators with clean filled circle characters (●) for professional appearance
+  - Improve consistency and readability of task complexity display
+
+  **AI Provider Compatibility:**
+
+  - Change generateObject mode from 'tool' to 'auto' for better cross-provider compatibility
+  - Add qwen3-235n-a22b:free model support (closes #687)
+  - Add smart warnings for free OpenRouter models with limitations (rate limits, restricted context, no tool_use)
+
+  **Technical Improvements:**
+
+  - Enhanced context generation in add-task to rely on semantic similarity rather than rigid pattern matching
+  - Improved dependency analysis and common pattern detection
+  - Better handling of task relationships and relevance scoring
+  - More intelligent task suggestion algorithms
+
+  The add-task system now provides truly relevant task context based on semantic understanding rather than arbitrary categories and limits, while maintaining a cleaner and more professional terminal experience.
+
+- [#655](https://github.com/eyaltoledano/claude-task-master/pull/655) [`edaa5fe`](https://github.com/eyaltoledano/claude-task-master/commit/edaa5fe0d56e0e4e7c4370670a7a388eebd922ac) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix double .taskmaster directory paths in file resolution utilities
+
+  - Closes #636
+
+- [#671](https://github.com/eyaltoledano/claude-task-master/pull/671) [`86ea6d1`](https://github.com/eyaltoledano/claude-task-master/commit/86ea6d1dbc03eeb39f524f565b50b7017b1d2c9c) Thanks [@joedanz](https://github.com/joedanz)! - Add one-click MCP server installation for Cursor
+
+- [#699](https://github.com/eyaltoledano/claude-task-master/pull/699) [`2e55757`](https://github.com/eyaltoledano/claude-task-master/commit/2e55757b2698ba20b78f09ec0286951297510b8e) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add sync-readme command for a task export to GitHub README
+
+  Introduces a new `sync-readme` command that exports your task list to your project's README.md file.
+
+  **Features:**
+
+  - **Flexible filtering**: Supports `--status` filtering (e.g., pending, done) and `--with-subtasks` flag
+  - **Smart content management**: Automatically replaces existing exports or appends to new READMEs
+  - **Metadata display**: Shows export timestamp, subtask inclusion status, and filter settings
+
+  **Usage:**
+
+  - `task-master sync-readme` - Export tasks without subtasks
+  - `task-master sync-readme --with-subtasks` - Include subtasks in export
+  - `task-master sync-readme --status=pending` - Only export pending tasks
+  - `task-master sync-readme --status=done --with-subtasks` - Export completed tasks with subtasks
+
+  Perfect for showcasing project progress on GitHub. Experimental. Open to feedback.
+
+## 0.16.2
+
+### Patch Changes
+
+- [#695](https://github.com/eyaltoledano/claude-task-master/pull/695) [`1ece6f1`](https://github.com/eyaltoledano/claude-task-master/commit/1ece6f19048df6ae2a0b25cbfb84d2c0f430642c) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - improve findTasks algorithm for resolving tasks path
+
+- [#695](https://github.com/eyaltoledano/claude-task-master/pull/695) [`ee0be04`](https://github.com/eyaltoledano/claude-task-master/commit/ee0be04302cc602246de5cd296291db69bc8b300) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix update tool on MCP giving `No valid tasks found`
+
+- [#699](https://github.com/eyaltoledano/claude-task-master/pull/699) [`27edbd8`](https://github.com/eyaltoledano/claude-task-master/commit/27edbd8f3fe5e2ac200b80e7f27f4c0e74a074d6) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Enhanced add-task fuzzy search intelligence and improved user experience
+
+  **Smarter Task Discovery:**
+
+  - Remove hardcoded category system that always matched "Task management"
+  - Eliminate arbitrary limits on fuzzy search results (5→25 high relevance, 3→10 medium relevance, 8→20 detailed tasks)
+  - Improve semantic weighting in Fuse.js search (details=3, description=2, title=1.5) for better relevance
+  - Generate context-driven task recommendations based on true semantic similarity
+
+  **Enhanced Terminal Experience:**
+
+  - Fix duplicate banner display issue that was "eating" terminal history (closes #553)
+  - Remove console.clear() and redundant displayBanner() calls from UI functions
+  - Preserve command history for better development workflow
+  - Streamline banner display across all commands (list, next, show, set-status, clear-subtasks, dependency commands)
+
+  **Visual Improvements:**
+
+  - Replace emoji complexity indicators with clean filled circle characters (●) for professional appearance
+  - Improve consistency and readability of task complexity display
+
+  **AI Provider Compatibility:**
+
+  - Change generateObject mode from 'tool' to 'auto' for better cross-provider compatibility
+  - Add qwen3-235n-a22b:free model support (closes #687)
+  - Add smart warnings for free OpenRouter models with limitations (rate limits, restricted context, no tool_use)
+
+  **Technical Improvements:**
+
+  - Enhanced context generation in add-task to rely on semantic similarity rather than rigid pattern matching
+  - Improved dependency analysis and common pattern detection
+  - Better handling of task relationships and relevance scoring
+  - More intelligent task suggestion algorithms
+
+  The add-task system now provides truly relevant task context based on semantic understanding rather than arbitrary categories and limits, while maintaining a cleaner and more professional terminal experience.
+
+- [#655](https://github.com/eyaltoledano/claude-task-master/pull/655) [`edaa5fe`](https://github.com/eyaltoledano/claude-task-master/commit/edaa5fe0d56e0e4e7c4370670a7a388eebd922ac) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix double .taskmaster directory paths in file resolution utilities
+
+  - Closes #636
+
+- [#671](https://github.com/eyaltoledano/claude-task-master/pull/671) [`86ea6d1`](https://github.com/eyaltoledano/claude-task-master/commit/86ea6d1dbc03eeb39f524f565b50b7017b1d2c9c) Thanks [@joedanz](https://github.com/joedanz)! - Add one-click MCP server installation for Cursor
+
+- [#699](https://github.com/eyaltoledano/claude-task-master/pull/699) [`2e55757`](https://github.com/eyaltoledano/claude-task-master/commit/2e55757b2698ba20b78f09ec0286951297510b8e) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add sync-readme command for a task export to GitHub README
+
+  Introduces a new `sync-readme` command that exports your task list to your project's README.md file.
+
+  **Features:**
+
+  - **Flexible filtering**: Supports `--status` filtering (e.g., pending, done) and `--with-subtasks` flag
+  - **Smart content management**: Automatically replaces existing exports or appends to new READMEs
+  - **Metadata display**: Shows export timestamp, subtask inclusion status, and filter settings
+
+  **Usage:**
+
+  - `task-master sync-readme` - Export tasks without subtasks
+  - `task-master sync-readme --with-subtasks` - Include subtasks in export
+  - `task-master sync-readme --status=pending` - Only export pending tasks
+  - `task-master sync-readme --status=done --with-subtasks` - Export completed tasks with subtasks
+
+  Perfect for showcasing project progress on GitHub. Experimental. Open to feedback.
+
+## 0.16.2-rc.0
+
+### Patch Changes
+
+- [#655](https://github.com/eyaltoledano/claude-task-master/pull/655) [`edaa5fe`](https://github.com/eyaltoledano/claude-task-master/commit/edaa5fe0d56e0e4e7c4370670a7a388eebd922ac) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix double .taskmaster directory paths in file resolution utilities
+
+  - Closes #636
+
+- [#671](https://github.com/eyaltoledano/claude-task-master/pull/671) [`86ea6d1`](https://github.com/eyaltoledano/claude-task-master/commit/86ea6d1dbc03eeb39f524f565b50b7017b1d2c9c) Thanks [@joedanz](https://github.com/joedanz)! - Add one-click MCP server installation for Cursor
+
+## 0.16.1
+
+### Patch Changes
+
+- [#641](https://github.com/eyaltoledano/claude-task-master/pull/641) [`ad61276`](https://github.com/eyaltoledano/claude-task-master/commit/ad612763ffbdd35aa1b593c9613edc1dc27a8856) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix bedrock issues
+
+- [#648](https://github.com/eyaltoledano/claude-task-master/pull/648) [`9b4168b`](https://github.com/eyaltoledano/claude-task-master/commit/9b4168bb4e4dfc2f4fb0cf6bd5f81a8565879176) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP tool calls logging errors
+
+- [#641](https://github.com/eyaltoledano/claude-task-master/pull/641) [`ad61276`](https://github.com/eyaltoledano/claude-task-master/commit/ad612763ffbdd35aa1b593c9613edc1dc27a8856) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Update rules for new directory structure
+
+- [#648](https://github.com/eyaltoledano/claude-task-master/pull/648) [`9b4168b`](https://github.com/eyaltoledano/claude-task-master/commit/9b4168bb4e4dfc2f4fb0cf6bd5f81a8565879176) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix bug in expand_all mcp tool
+
+- [#641](https://github.com/eyaltoledano/claude-task-master/pull/641) [`ad61276`](https://github.com/eyaltoledano/claude-task-master/commit/ad612763ffbdd35aa1b593c9613edc1dc27a8856) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP crashing after certain commands due to console logs
+
+## 0.16.0
+
+### Minor Changes
+
+- [#607](https://github.com/eyaltoledano/claude-task-master/pull/607) [`6a8a68e`](https://github.com/eyaltoledano/claude-task-master/commit/6a8a68e1a3f34dcdf40b355b4602a08d291f8e38) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add AWS bedrock support
+
+- [#607](https://github.com/eyaltoledano/claude-task-master/pull/607) [`6a8a68e`](https://github.com/eyaltoledano/claude-task-master/commit/6a8a68e1a3f34dcdf40b355b4602a08d291f8e38) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - # Add Google Vertex AI Provider Integration
+
+  - Implemented `VertexAIProvider` class extending BaseAIProvider
+  - Added authentication and configuration handling for Vertex AI
+  - Updated configuration manager with Vertex-specific getters
+  - Modified AI services unified system to integrate the provider
+  - Added documentation for Vertex AI setup and configuration
+  - Updated environment variable examples for Vertex AI support
+  - Implemented specialized error handling for Vertex-specific issues
+
+- [#607](https://github.com/eyaltoledano/claude-task-master/pull/607) [`6a8a68e`](https://github.com/eyaltoledano/claude-task-master/commit/6a8a68e1a3f34dcdf40b355b4602a08d291f8e38) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add support for Azure
+
+- [#612](https://github.com/eyaltoledano/claude-task-master/pull/612) [`669b744`](https://github.com/eyaltoledano/claude-task-master/commit/669b744ced454116a7b29de6c58b4b8da977186a) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Increased minimum required node version to > 18 (was > 14)
+
+- [#607](https://github.com/eyaltoledano/claude-task-master/pull/607) [`6a8a68e`](https://github.com/eyaltoledano/claude-task-master/commit/6a8a68e1a3f34dcdf40b355b4602a08d291f8e38) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Renamed baseUrl to baseURL
+
+- [#604](https://github.com/eyaltoledano/claude-task-master/pull/604) [`80735f9`](https://github.com/eyaltoledano/claude-task-master/commit/80735f9e60c7dda7207e169697f8ac07b6733634) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add TASK_MASTER_PROJECT_ROOT env variable supported in mcp.json and .env for project root resolution
+
+  - Some users were having issues where the MCP wasn't able to detect the location of their project root, you can now set the `TASK_MASTER_PROJECT_ROOT` environment variable to the root of your project.
+
+- [#619](https://github.com/eyaltoledano/claude-task-master/pull/619) [`3f64202`](https://github.com/eyaltoledano/claude-task-master/commit/3f64202c9feef83f2bf383c79e4367d337c37e20) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Consolidate Task Master files into unified .taskmaster directory structure
+
+  This release introduces a new consolidated directory structure that organizes all Task Master files under a single `.taskmaster/` directory for better project organization and cleaner workspace management.
+
+  **New Directory Structure:**
+
+  - `.taskmaster/tasks/` - Task files (previously `tasks/`)
+  - `.taskmaster/docs/` - Documentation including PRD files (previously `scripts/`)
+  - `.taskmaster/reports/` - Complexity analysis reports (previously `scripts/`)
+  - `.taskmaster/templates/` - Template files like example PRD
+  - `.taskmaster/config.json` - Configuration (previously `.taskmasterconfig`)
+
+  **Migration & Backward Compatibility:**
+
+  - Existing projects continue to work with legacy file locations
+  - New projects use the consolidated structure automatically
+  - Run `task-master migrate` to move existing projects to the new structure
+  - All CLI commands and MCP tools automatically detect and use appropriate file locations
+
+  **Benefits:**
+
+  - Cleaner project root with Task Master files organized in one location
+  - Reduced file scatter across multiple directories
+  - Improved project navigation and maintenance
+  - Consistent file organization across all Task Master projects
+
+  This change maintains full backward compatibility while providing a migration path to the improved structure.
+
+### Patch Changes
+
+- [#607](https://github.com/eyaltoledano/claude-task-master/pull/607) [`6a8a68e`](https://github.com/eyaltoledano/claude-task-master/commit/6a8a68e1a3f34dcdf40b355b4602a08d291f8e38) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix max_tokens error when trying to use claude-sonnet-4 and claude-opus-4
+
+- [#625](https://github.com/eyaltoledano/claude-task-master/pull/625) [`2d520de`](https://github.com/eyaltoledano/claude-task-master/commit/2d520de2694da3efe537b475ca52baf3c869edda) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix add-task MCP command causing an error
+
+## 0.16.0-rc.0
+
+### Minor Changes
+
+- [#607](https://github.com/eyaltoledano/claude-task-master/pull/607) [`6a8a68e`](https://github.com/eyaltoledano/claude-task-master/commit/6a8a68e1a3f34dcdf40b355b4602a08d291f8e38) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add AWS bedrock support
+
+- [#607](https://github.com/eyaltoledano/claude-task-master/pull/607) [`6a8a68e`](https://github.com/eyaltoledano/claude-task-master/commit/6a8a68e1a3f34dcdf40b355b4602a08d291f8e38) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - # Add Google Vertex AI Provider Integration
+
+  - Implemented `VertexAIProvider` class extending BaseAIProvider
+  - Added authentication and configuration handling for Vertex AI
+  - Updated configuration manager with Vertex-specific getters
+  - Modified AI services unified system to integrate the provider
+  - Added documentation for Vertex AI setup and configuration
+  - Updated environment variable examples for Vertex AI support
+  - Implemented specialized error handling for Vertex-specific issues
+
+- [#607](https://github.com/eyaltoledano/claude-task-master/pull/607) [`6a8a68e`](https://github.com/eyaltoledano/claude-task-master/commit/6a8a68e1a3f34dcdf40b355b4602a08d291f8e38) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add support for Azure
+
+- [#612](https://github.com/eyaltoledano/claude-task-master/pull/612) [`669b744`](https://github.com/eyaltoledano/claude-task-master/commit/669b744ced454116a7b29de6c58b4b8da977186a) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Increased minimum required node version to > 18 (was > 14)
+
+- [#607](https://github.com/eyaltoledano/claude-task-master/pull/607) [`6a8a68e`](https://github.com/eyaltoledano/claude-task-master/commit/6a8a68e1a3f34dcdf40b355b4602a08d291f8e38) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Renamed baseUrl to baseURL
+
+- [#604](https://github.com/eyaltoledano/claude-task-master/pull/604) [`80735f9`](https://github.com/eyaltoledano/claude-task-master/commit/80735f9e60c7dda7207e169697f8ac07b6733634) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add TASK_MASTER_PROJECT_ROOT env variable supported in mcp.json and .env for project root resolution
+
+  - Some users were having issues where the MCP wasn't able to detect the location of their project root, you can now set the `TASK_MASTER_PROJECT_ROOT` environment variable to the root of your project.
+
+- [#619](https://github.com/eyaltoledano/claude-task-master/pull/619) [`3f64202`](https://github.com/eyaltoledano/claude-task-master/commit/3f64202c9feef83f2bf383c79e4367d337c37e20) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Consolidate Task Master files into unified .taskmaster directory structure
+
+  This release introduces a new consolidated directory structure that organizes all Task Master files under a single `.taskmaster/` directory for better project organization and cleaner workspace management.
+
+  **New Directory Structure:**
+
+  - `.taskmaster/tasks/` - Task files (previously `tasks/`)
+  - `.taskmaster/docs/` - Documentation including PRD files (previously `scripts/`)
+  - `.taskmaster/reports/` - Complexity analysis reports (previously `scripts/`)
+  - `.taskmaster/templates/` - Template files like example PRD
+  - `.taskmaster/config.json` - Configuration (previously `.taskmasterconfig`)
+
+  **Migration & Backward Compatibility:**
+
+  - Existing projects continue to work with legacy file locations
+  - New projects use the consolidated structure automatically
+  - Run `task-master migrate` to move existing projects to the new structure
+  - All CLI commands and MCP tools automatically detect and use appropriate file locations
+
+  **Benefits:**
+
+  - Cleaner project root with Task Master files organized in one location
+  - Reduced file scatter across multiple directories
+  - Improved project navigation and maintenance
+  - Consistent file organization across all Task Master projects
+
+  This change maintains full backward compatibility while providing a migration path to the improved structure.
+
+### Patch Changes
+
+- [#607](https://github.com/eyaltoledano/claude-task-master/pull/607) [`6a8a68e`](https://github.com/eyaltoledano/claude-task-master/commit/6a8a68e1a3f34dcdf40b355b4602a08d291f8e38) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix max_tokens error when trying to use claude-sonnet-4 and claude-opus-4
+
+- [#597](https://github.com/eyaltoledano/claude-task-master/pull/597) [`2d520de`](https://github.com/eyaltoledano/claude-task-master/commit/2d520de2694da3efe537b475ca52baf3c869edda) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Fix add-task MCP command causing an error
+
+## 0.15.0
+
+### Minor Changes
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`09add37`](https://github.com/eyaltoledano/claude-task-master/commit/09add37423d70b809d5c28f3cde9fccd5a7e64e7) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Added comprehensive Ollama model validation and interactive setup support
+
+  - **Interactive Setup Enhancement**: Added "Custom Ollama model" option to `task-master models --setup`, matching the existing OpenRouter functionality
+  - **Live Model Validation**: When setting Ollama models, Taskmaster now validates against the local Ollama instance by querying `/api/tags` endpoint
+  - **Configurable Endpoints**: Uses the `ollamaBaseUrl` from `.taskmasterconfig` (with role-specific `baseUrl` overrides supported)
+  - **Robust Error Handling**:
+    - Detects when Ollama server is not running and provides clear error messages
+    - Validates model existence and lists available alternatives when model not found
+    - Graceful fallback behavior for connection issues
+  - **Full Platform Support**: Both MCP server tools and CLI commands support the new validation
+  - **Improved User Experience**: Clear feedback during model validation with informative success/error messages
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`4c83526`](https://github.com/eyaltoledano/claude-task-master/commit/4c835264ac6c1f74896cddabc3b3c69a5c435417) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds and updates supported AI models with costs:
+
+  - Added new OpenRouter models: GPT-4.1 series, O3, Codex Mini, Llama 4 Maverick, Llama 4 Scout, Qwen3-235b
+  - Added Mistral models: Devstral Small, Mistral Nemo
+  - Updated Ollama models with latest variants: Devstral, Qwen3, Mistral-small3.1, Llama3.3
+  - Updated Gemini model to latest 2.5 Flash preview version
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`70f4054`](https://github.com/eyaltoledano/claude-task-master/commit/70f4054f268f9f8257870e64c24070263d4e2966) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add `--research` flag to parse-prd command, enabling enhanced task generation from PRD files. When used, Taskmaster leverages the research model to:
+
+  - Research current technologies and best practices relevant to the project
+  - Identify technical challenges and security concerns not explicitly mentioned in the PRD
+  - Include specific library recommendations with version numbers
+  - Provide more detailed implementation guidance based on industry standards
+  - Create more accurate dependency relationships between tasks
+
+  This results in higher quality, more actionable tasks with minimal additional effort.
+
+  _NOTE_ That this is an experimental feature. Research models don't typically do great at structured output. You may find some failures when using research mode, so please share your feedback so we can improve this.
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`5e9bc28`](https://github.com/eyaltoledano/claude-task-master/commit/5e9bc28abea36ec7cd25489af7fcc6cbea51038b) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - This change significantly enhances the `add-task` command's intelligence. When you add a new task, Taskmaster now automatically: - Analyzes your existing tasks to find those most relevant to your new task's description. - Provides the AI with detailed context from these relevant tasks.
+
+  This results in newly created tasks being more accurately placed within your project's dependency structure, saving you time and any need to update tasks just for dependencies, all without significantly increasing AI costs. You'll get smarter, more connected tasks right from the start.
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`34c769b`](https://github.com/eyaltoledano/claude-task-master/commit/34c769bcd0faf65ddec3b95de2ba152a8be3ec5c) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Enhance analyze-complexity to support analyzing specific task IDs. - You can now analyze individual tasks or selected task groups by using the new `--id` option with comma-separated IDs, or `--from` and `--to` options to specify a range of tasks. - The feature intelligently merges analysis results with existing reports, allowing incremental analysis while preserving previous results.
+
+- [#558](https://github.com/eyaltoledano/claude-task-master/pull/558) [`86d8f00`](https://github.com/eyaltoledano/claude-task-master/commit/86d8f00af809887ee0ba0ba7157cc555e0d07c38) Thanks [@ShreyPaharia](https://github.com/ShreyPaharia)! - Add next task to set task status response
+  Status: DONE
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`04af16d`](https://github.com/eyaltoledano/claude-task-master/commit/04af16de27295452e134b17b3c7d0f44bbb84c29) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add move command to enable moving tasks and subtasks within the task hierarchy. This new command supports moving standalone tasks to become subtasks, subtasks to become standalone tasks, and moving subtasks between different parents. The implementation handles circular dependencies, validation, and proper updating of parent-child relationships.
+
+  **Usage:**
+
+  - CLI command: `task-master move --from=<id> --to=<id>`
+  - MCP tool: `move_task` with parameters:
+    - `from`: ID of task/subtask to move (e.g., "5" or "5.2")
+    - `to`: ID of destination (e.g., "7" or "7.3")
+    - `file` (optional): Custom path to tasks.json
+
+  **Example scenarios:**
+
+  - Move task to become subtask: `--from="5" --to="7"`
+  - Move subtask to standalone task: `--from="5.2" --to="7"`
+  - Move subtask to different parent: `--from="5.2" --to="7.3"`
+  - Reorder subtask within same parent: `--from="5.2" --to="5.4"`
+  - Move multiple tasks at once: `--from="10,11,12" --to="16,17,18"`
+  - Move task to new ID: `--from="5" --to="25"` (creates a new task with ID 25)
+
+  **Multiple Task Support:**
+  The command supports moving multiple tasks simultaneously by providing comma-separated lists for both `--from` and `--to` parameters. The number of source and destination IDs must match. This is particularly useful for resolving merge conflicts in task files when multiple team members have created tasks on different branches.
+
+  **Validation Features:**
+
+  - Allows moving tasks to new, non-existent IDs (automatically creates placeholders)
+  - Prevents moving to existing task IDs that already contain content (to avoid overwriting)
+  - Validates source tasks exist before attempting to move them
+  - Ensures proper parent-child relationships are maintained
+
+### Patch Changes
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`231e569`](https://github.com/eyaltoledano/claude-task-master/commit/231e569e84804a2e5ba1f9da1a985d0851b7e949) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adjusts default main model model to Claude Sonnet 4. Adjusts default fallback to Claude Sonney 3.7"
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`b371808`](https://github.com/eyaltoledano/claude-task-master/commit/b371808524f2c2986f4940d78fcef32c125d01f2) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds llms-install.md to the root to enable AI agents to programmatically install the Taskmaster MCP server. This is specifically being introduced for the Cline MCP marketplace and will be adjusted over time for other MCP clients as needed.
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`a59dd03`](https://github.com/eyaltoledano/claude-task-master/commit/a59dd037cfebb46d38bc44dd216c7c23933be641) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds AGENTS.md to power Claude Code integration more natively based on Anthropic's best practice and Claude-specific MCP client behaviours. Also adds in advanced workflows that tie Taskmaster commands together into one Claude workflow."
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`e0e1155`](https://github.com/eyaltoledano/claude-task-master/commit/e0e115526089bf41d5d60929956edf5601ff3e23) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Fixes issue with force/append flag combinations for parse-prd.
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`34df2c8`](https://github.com/eyaltoledano/claude-task-master/commit/34df2c8bbddc0e157c981d32502bbe6b9468202e) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - You can now add tasks to a newly initialized project without having to parse a prd. This will automatically create the missing tasks.json file and create the first task. Lets you vibe if you want to vibe."
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`d2e6431`](https://github.com/eyaltoledano/claude-task-master/commit/d2e64318e2f4bfc3457792e310cc4ff9210bba30) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Fixes an issue where the research fallback would attempt to make API calls without checking for a valid API key first. This ensures proper error handling when the main task generation and first fallback both fail. Closes #421 #519.
+
+## 0.15.0-rc.0
+
+### Minor Changes
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`09add37`](https://github.com/eyaltoledano/claude-task-master/commit/09add37423d70b809d5c28f3cde9fccd5a7e64e7) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Added comprehensive Ollama model validation and interactive setup support
+
+  - **Interactive Setup Enhancement**: Added "Custom Ollama model" option to `task-master models --setup`, matching the existing OpenRouter functionality
+  - **Live Model Validation**: When setting Ollama models, Taskmaster now validates against the local Ollama instance by querying `/api/tags` endpoint
+  - **Configurable Endpoints**: Uses the `ollamaBaseUrl` from `.taskmasterconfig` (with role-specific `baseUrl` overrides supported)
+  - **Robust Error Handling**:
+    - Detects when Ollama server is not running and provides clear error messages
+    - Validates model existence and lists available alternatives when model not found
+    - Graceful fallback behavior for connection issues
+  - **Full Platform Support**: Both MCP server tools and CLI commands support the new validation
+  - **Improved User Experience**: Clear feedback during model validation with informative success/error messages
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`4c83526`](https://github.com/eyaltoledano/claude-task-master/commit/4c835264ac6c1f74896cddabc3b3c69a5c435417) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds and updates supported AI models with costs:
+
+  - Added new OpenRouter models: GPT-4.1 series, O3, Codex Mini, Llama 4 Maverick, Llama 4 Scout, Qwen3-235b
+  - Added Mistral models: Devstral Small, Mistral Nemo
+  - Updated Ollama models with latest variants: Devstral, Qwen3, Mistral-small3.1, Llama3.3
+  - Updated Gemini model to latest 2.5 Flash preview version
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`70f4054`](https://github.com/eyaltoledano/claude-task-master/commit/70f4054f268f9f8257870e64c24070263d4e2966) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add `--research` flag to parse-prd command, enabling enhanced task generation from PRD files. When used, Taskmaster leverages the research model to:
+
+  - Research current technologies and best practices relevant to the project
+  - Identify technical challenges and security concerns not explicitly mentioned in the PRD
+  - Include specific library recommendations with version numbers
+  - Provide more detailed implementation guidance based on industry standards
+  - Create more accurate dependency relationships between tasks
+
+  This results in higher quality, more actionable tasks with minimal additional effort.
+
+  _NOTE_ That this is an experimental feature. Research models don't typically do great at structured output. You may find some failures when using research mode, so please share your feedback so we can improve this.
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`5e9bc28`](https://github.com/eyaltoledano/claude-task-master/commit/5e9bc28abea36ec7cd25489af7fcc6cbea51038b) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - This change significantly enhances the `add-task` command's intelligence. When you add a new task, Taskmaster now automatically: - Analyzes your existing tasks to find those most relevant to your new task's description. - Provides the AI with detailed context from these relevant tasks.
+
+  This results in newly created tasks being more accurately placed within your project's dependency structure, saving you time and any need to update tasks just for dependencies, all without significantly increasing AI costs. You'll get smarter, more connected tasks right from the start.
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`34c769b`](https://github.com/eyaltoledano/claude-task-master/commit/34c769bcd0faf65ddec3b95de2ba152a8be3ec5c) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Enhance analyze-complexity to support analyzing specific task IDs. - You can now analyze individual tasks or selected task groups by using the new `--id` option with comma-separated IDs, or `--from` and `--to` options to specify a range of tasks. - The feature intelligently merges analysis results with existing reports, allowing incremental analysis while preserving previous results.
+
+- [#558](https://github.com/eyaltoledano/claude-task-master/pull/558) [`86d8f00`](https://github.com/eyaltoledano/claude-task-master/commit/86d8f00af809887ee0ba0ba7157cc555e0d07c38) Thanks [@ShreyPaharia](https://github.com/ShreyPaharia)! - Add next task to set task status response
+  Status: DONE
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`04af16d`](https://github.com/eyaltoledano/claude-task-master/commit/04af16de27295452e134b17b3c7d0f44bbb84c29) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add move command to enable moving tasks and subtasks within the task hierarchy. This new command supports moving standalone tasks to become subtasks, subtasks to become standalone tasks, and moving subtasks between different parents. The implementation handles circular dependencies, validation, and proper updating of parent-child relationships.
+
+  **Usage:**
+
+  - CLI command: `task-master move --from=<id> --to=<id>`
+  - MCP tool: `move_task` with parameters:
+    - `from`: ID of task/subtask to move (e.g., "5" or "5.2")
+    - `to`: ID of destination (e.g., "7" or "7.3")
+    - `file` (optional): Custom path to tasks.json
+
+  **Example scenarios:**
+
+  - Move task to become subtask: `--from="5" --to="7"`
+  - Move subtask to standalone task: `--from="5.2" --to="7"`
+  - Move subtask to different parent: `--from="5.2" --to="7.3"`
+  - Reorder subtask within same parent: `--from="5.2" --to="5.4"`
+  - Move multiple tasks at once: `--from="10,11,12" --to="16,17,18"`
+  - Move task to new ID: `--from="5" --to="25"` (creates a new task with ID 25)
+
+  **Multiple Task Support:**
+  The command supports moving multiple tasks simultaneously by providing comma-separated lists for both `--from` and `--to` parameters. The number of source and destination IDs must match. This is particularly useful for resolving merge conflicts in task files when multiple team members have created tasks on different branches.
+
+  **Validation Features:**
+
+  - Allows moving tasks to new, non-existent IDs (automatically creates placeholders)
+  - Prevents moving to existing task IDs that already contain content (to avoid overwriting)
+  - Validates source tasks exist before attempting to move them
+  - Ensures proper parent-child relationships are maintained
+
+### Patch Changes
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`231e569`](https://github.com/eyaltoledano/claude-task-master/commit/231e569e84804a2e5ba1f9da1a985d0851b7e949) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adjusts default main model model to Claude Sonnet 4. Adjusts default fallback to Claude Sonney 3.7"
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`b371808`](https://github.com/eyaltoledano/claude-task-master/commit/b371808524f2c2986f4940d78fcef32c125d01f2) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds llms-install.md to the root to enable AI agents to programmatically install the Taskmaster MCP server. This is specifically being introduced for the Cline MCP marketplace and will be adjusted over time for other MCP clients as needed.
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`a59dd03`](https://github.com/eyaltoledano/claude-task-master/commit/a59dd037cfebb46d38bc44dd216c7c23933be641) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Adds AGENTS.md to power Claude Code integration more natively based on Anthropic's best practice and Claude-specific MCP client behaviours. Also adds in advanced workflows that tie Taskmaster commands together into one Claude workflow."
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`e0e1155`](https://github.com/eyaltoledano/claude-task-master/commit/e0e115526089bf41d5d60929956edf5601ff3e23) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Fixes issue with force/append flag combinations for parse-prd.
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`34df2c8`](https://github.com/eyaltoledano/claude-task-master/commit/34df2c8bbddc0e157c981d32502bbe6b9468202e) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - You can now add tasks to a newly initialized project without having to parse a prd. This will automatically create the missing tasks.json file and create the first task. Lets you vibe if you want to vibe."
+
+- [#567](https://github.com/eyaltoledano/claude-task-master/pull/567) [`d2e6431`](https://github.com/eyaltoledano/claude-task-master/commit/d2e64318e2f4bfc3457792e310cc4ff9210bba30) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Fixes an issue where the research fallback would attempt to make API calls without checking for a valid API key first. This ensures proper error handling when the main task generation and first fallback both fail. Closes #421 #519.
+
 ## 0.14.0
 
 ### Minor Changes

CONTRIBUTING.md

@@ -0,0 +1,335 @@
+# Contributing to Task Master
+
+Thank you for your interest in contributing to Task Master! We're excited to work with you and appreciate your help in making this project better. 🚀
+
+## 🤝 Our Collaborative Approach
+
+We're a **PR-friendly team** that values collaboration:
+
+- ✅ **We review PRs quickly** - Usually within hours, not days
+- ✅ **We're super reactive** - Expect fast feedback and engagement
+- ✅ **We sometimes take over PRs** - If your contribution is valuable but needs cleanup, we might jump in to help finish it
+- ✅ **We're open to all contributions** - From bug fixes to major features
+
+**We don't mind AI-generated code**, but we do expect you to:
+
+- ✅ **Review and understand** what the AI generated
+- ✅ **Test the code thoroughly** before submitting
+- ✅ **Ensure it's well-written** and follows our patterns
+- ❌ **Don't submit "AI slop"** - untested, unreviewed AI output
+
+> **Why this matters**: We spend significant time reviewing PRs. Help us help you by submitting quality contributions that save everyone time!
+
+## 🚀 Quick Start for Contributors
+
+### 1. Fork and Clone
+
+```bash
+git clone https://github.com/YOUR_USERNAME/claude-task-master.git
+cd claude-task-master
+npm install
+```
+
+### 2. Create a Feature Branch
+
+**Important**: Always target the `next` branch, not `main`:
+
+```bash
+git checkout next
+git pull origin next
+git checkout -b feature/your-feature-name
+```
+
+### 3. Make Your Changes
+
+Follow our development guidelines below.
+
+### 4. Test Everything Yourself
+
+**Before submitting your PR**, ensure:
+
+```bash
+# Run all tests
+npm test
+
+# Check formatting
+npm run format-check
+
+# Fix formatting if needed
+npm run format
+```
+
+### 5. Create a Changeset
+
+**Required for most changes**:
+
+```bash
+npm run changeset
+```
+
+See the [Changeset Guidelines](#changeset-guidelines) below for details.
+
+### 6. Submit Your PR
+
+- Target the `next` branch
+- Write a clear description
+- Reference any related issues
+
+## 📋 Development Guidelines
+
+### Branch Strategy
+
+- **`main`**: Production-ready code
+- **`next`**: Development branch - **target this for PRs**
+- **Feature branches**: `feature/description` or `fix/description`
+
+### Code Quality Standards
+
+1. **Write tests** for new functionality
+2. **Follow existing patterns** in the codebase
+3. **Add JSDoc comments** for functions
+4. **Keep functions focused** and single-purpose
+
+### Testing Requirements
+
+Your PR **must pass all CI checks**:
+
+- ✅ **Unit tests**: `npm test`
+- ✅ **Format check**: `npm run format-check`
+
+**Test your changes locally first** - this saves review time and shows you care about quality.
+
+## 📦 Changeset Guidelines
+
+We use [Changesets](https://github.com/changesets/changesets) to manage versioning and generate changelogs.
+
+### When to Create a Changeset
+
+**Always create a changeset for**:
+
+- ✅ New features
+- ✅ Bug fixes
+- ✅ Breaking changes
+- ✅ Performance improvements
+- ✅ User-facing documentation updates
+- ✅ Dependency updates that affect functionality
+
+**Skip changesets for**:
+
+- ❌ Internal documentation only
+- ❌ Test-only changes
+- ❌ Code formatting/linting
+- ❌ Development tooling that doesn't affect users
+
+### How to Create a Changeset
+
+1. **After making your changes**:
+
+   ```bash
+   npm run changeset
+   ```
+
+2. **Choose the bump type**:
+
+   - **Major**: Breaking changes
+   - **Minor**: New features
+   - **Patch**: Bug fixes, docs, performance improvements
+
+3. **Write a clear summary**:
+
+   ```
+   Add support for custom AI models in MCP configuration
+   ```
+
+4. **Commit the changeset file** with your changes:
+   ```bash
+   git add .changeset/*.md
+   git commit -m "feat: add custom AI model support"
+   ```
+
+### Changeset vs Git Commit Messages
+
+- **Changeset summary**: User-facing, goes in CHANGELOG.md
+- **Git commit**: Developer-facing, explains the technical change
+
+Example:
+
+```bash
+# Changeset summary (user-facing)
+"Add support for custom Ollama models"
+
+# Git commit message (developer-facing)
+"feat(models): implement custom Ollama model validation
+
+- Add model validation for custom Ollama endpoints
+- Update configuration schema to support custom models
+- Add tests for new validation logic"
+```
+
+## 🔧 Development Setup
+
+### Prerequisites
+
+- Node.js 18+
+- npm or yarn
+
+### Environment Setup
+
+1. **Copy environment template**:
+
+   ```bash
+   cp .env.example .env
+   ```
+
+2. **Add your API keys** (for testing AI features):
+   ```bash
+   ANTHROPIC_API_KEY=your_key_here
+   OPENAI_API_KEY=your_key_here
+   # Add others as needed
+   ```
+
+### Running Tests
+
+```bash
+# Run all tests
+npm test
+
+# Run tests in watch mode
+npm run test:watch
+
+# Run with coverage
+npm run test:coverage
+
+# Run E2E tests
+npm run test:e2e
+```
+
+### Code Formatting
+
+We use Prettier for consistent formatting:
+
+```bash
+# Check formatting
+npm run format-check
+
+# Fix formatting
+npm run format
+```
+
+## 📝 PR Guidelines
+
+### Before Submitting
+
+- [ ] **Target the `next` branch**
+- [ ] **Test everything locally**
+- [ ] **Run the full test suite**
+- [ ] **Check code formatting**
+- [ ] **Create a changeset** (if needed)
+- [ ] **Re-read your changes** - ensure they're clean and well-thought-out
+
+### PR Description Template
+
+```markdown
+## Description
+
+Brief description of what this PR does.
+
+## Type of Change
+
+- [ ] Bug fix
+- [ ] New feature
+- [ ] Breaking change
+- [ ] Documentation update
+
+## Testing
+
+- [ ] I have tested this locally
+- [ ] All existing tests pass
+- [ ] I have added tests for new functionality
+
+## Changeset
+
+- [ ] I have created a changeset (or this change doesn't need one)
+
+## Additional Notes
+
+Any additional context or notes for reviewers.
+```
+
+### What We Look For
+
+✅ **Good PRs**:
+
+- Clear, focused changes
+- Comprehensive testing
+- Good commit messages
+- Proper changeset (when needed)
+- Self-reviewed code
+
+❌ **Avoid**:
+
+- Massive PRs that change everything
+- Untested code
+- Formatting issues
+- Missing changesets for user-facing changes
+- AI-generated code that wasn't reviewed
+
+## 🏗️ Project Structure
+
+```
+claude-task-master/
+├── bin/                    # CLI executables
+├── mcp-server/            # MCP server implementation
+├── scripts/               # Core task management logic
+├── src/                   # Shared utilities and providers and well refactored code (we are slowly moving everything here)
+├── tests/                 # Test files
+├── docs/                  # Documentation
+└── .cursor/               # Cursor IDE rules and configuration
+└── assets/							   # Assets like rules and configuration for all IDEs
+```
+
+### Key Areas for Contribution
+
+- **CLI Commands**: `scripts/modules/commands.js`
+- **MCP Tools**: `mcp-server/src/tools/`
+- **Core Logic**: `scripts/modules/task-manager/`
+- **AI Providers**: `src/ai-providers/`
+- **Tests**: `tests/`
+
+## 🐛 Reporting Issues
+
+### Bug Reports
+
+Include:
+
+- Task Master version
+- Node.js version
+- Operating system
+- Steps to reproduce
+- Expected vs actual behavior
+- Error messages/logs
+
+### Feature Requests
+
+Include:
+
+- Clear description of the feature
+- Use case/motivation
+- Proposed implementation (if you have ideas)
+- Willingness to contribute
+
+## 💬 Getting Help
+
+- **Discord**: [Join our community](https://discord.gg/taskmasterai)
+- **Issues**: [GitHub Issues](https://github.com/eyaltoledano/claude-task-master/issues)
+- **Discussions**: [GitHub Discussions](https://github.com/eyaltoledano/claude-task-master/discussions)
+
+## 📄 License
+
+By contributing, you agree that your contributions will be licensed under the same license as the project (MIT with Commons Clause).
+
+---
+
+**Thank you for contributing to Task Master!** 🎉
+
+Your contributions help make AI-driven development more accessible and efficient for everyone.

README.md

@@ -2,13 +2,37 @@
 
 [![CI](https://github.com/eyaltoledano/claude-task-master/actions/workflows/ci.yml/badge.svg)](https://github.com/eyaltoledano/claude-task-master/actions/workflows/ci.yml) [![npm version](https://badge.fury.io/js/task-master-ai.svg)](https://badge.fury.io/js/task-master-ai) [![Discord](https://dcbadge.limes.pink/api/server/https://discord.gg/taskmasterai?style=flat)](https://discord.gg/taskmasterai) [![License: MIT with Commons Clause](https://img.shields.io/badge/license-MIT%20with%20Commons%20Clause-blue.svg)](LICENSE)
 
-### By [@eyaltoledano](https://x.com/eyaltoledano) & [@RalphEcom](https://x.com/RalphEcom)
+[![NPM Downloads](https://img.shields.io/npm/d18m/task-master-ai?style=flat)](https://www.npmjs.com/package/task-master-ai) [![NPM Downloads](https://img.shields.io/npm/dm/task-master-ai?style=flat)](https://www.npmjs.com/package/task-master-ai) [![NPM Downloads](https://img.shields.io/npm/dw/task-master-ai?style=flat)](https://www.npmjs.com/package/task-master-ai)
 
-[![Twitter Follow](https://img.shields.io/twitter/follow/eyaltoledano?style=flat)](https://x.com/eyaltoledano)
+## By [@eyaltoledano](https://x.com/eyaltoledano), [@RalphEcom](https://x.com/RalphEcom) & [@jasonzhou1993](https://x.com/jasonzhou1993)
-[![Twitter Follow](https://img.shields.io/twitter/follow/RalphEcom?style=flat)](https://x.com/RalphEcom)
+
+[![Twitter Follow](https://img.shields.io/twitter/follow/eyaltoledano)](https://x.com/eyaltoledano)
+[![Twitter Follow](https://img.shields.io/twitter/follow/RalphEcom)](https://x.com/RalphEcom)
+[![Twitter Follow](https://img.shields.io/twitter/follow/jasonzhou1993)](https://x.com/jasonzhou1993)
 
 A task management system for AI-driven development with Claude, designed to work seamlessly with Cursor AI.
 
+## Documentation
+
+For more detailed information, check out the documentation 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
+- [Command Reference](docs/command-reference.md) - Complete list of all available commands
+- [Task Structure](docs/task-structure.md) - Understanding the task format and features
+- [Example Interactions](docs/examples.md) - Common Cursor AI interaction examples
+- [Migration Guide](docs/migration-guide.md) - Guide to migrating to the new project structure
+
+#### 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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
+```
+
+> **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.
+
 ## Requirements
 
 Taskmaster utilizes AI across several commands, and those require a separate API key. You can use a variety of models from different AI providers provided you add your API keys. For example, if you want to use Claude 3.7, you'll need an Anthropic API key.
@@ -23,56 +47,136 @@ At least one (1) of the following is required:
 - Perplexity API key (for research model)
 - xAI API Key (for research or main model)
 - OpenRouter API Key (for research or main model)
+- Claude Code (no API key required - requires Claude Code CLI)
 
-Using the research model is optional but highly recommended. You will need at least ONE API key. Adding all API keys enables you to seamlessly switch between model providers at will.
+Using the research model is optional but highly recommended. You will need at least ONE API key (unless using Claude Code). Adding all API keys enables you to seamlessly switch between model providers at will.
 
 ## Quick Start
 
-### Option 1 | MCP (Recommended):
+### Option 1: MCP (Recommended)
 
-MCP (Model Control Protocol) provides the easiest way to get started with Task Master directly in your editor.
+MCP (Model Control Protocol) lets you run Task Master directly from your editor.
 
-1. **Add the MCP config to your editor** (Cursor recommended, but it works with other text editors):
+#### 1. Add your MCP config at the following path depending on your editor
+
+| Editor       | Scope   | Linux/macOS Path                      | Windows Path                                      | Key          |
+| ------------ | ------- | ------------------------------------- | ------------------------------------------------- | ------------ |
+| **Cursor**   | Global  | `~/.cursor/mcp.json`                  | `%USERPROFILE%\.cursor\mcp.json`                  | `mcpServers` |
+|              | Project | `<project_folder>/.cursor/mcp.json`   | `<project_folder>\.cursor\mcp.json`               | `mcpServers` |
+| **Windsurf** | Global  | `~/.codeium/windsurf/mcp_config.json` | `%USERPROFILE%\.codeium\windsurf\mcp_config.json` | `mcpServers` |
+| **VS Code**  | Project | `<project_folder>/.vscode/mcp.json`   | `<project_folder>\.vscode\mcp.json`               | `servers`    |
+
+##### Manual Configuration
+
+###### Cursor & Windsurf (`mcpServers`)
 
 ```json
 {
-	"mcpServers": {
+  "mcpServers": {
-		"taskmaster-ai": {
+    "taskmaster-ai": {
-			"command": "npx",
+      "command": "npx",
-			"args": ["-y", "--package=task-master-ai", "task-master-ai"],
+      "args": ["-y", "--package=task-master-ai", "task-master-ai"],
-			"env": {
+      "env": {
-				"ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
+        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
-				"PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
+        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
-				"OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
+        "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
-				"GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
+        "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
-				"MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
+        "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
-				"OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
+        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
-				"XAI_API_KEY": "YOUR_XAI_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"
+        "OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
-			}
+      }
-		}
+    }
-	}
+  }
 }
 ```
 
-2. **Enable the MCP** in your editor
+> 🔑 Replace `YOUR_…_KEY_HERE` with your real API keys. You can remove keys you don't use.
 
-3. **Prompt the AI** to initialize Task Master:
+> **Note**: If you see `0 tools enabled` in the MCP settings, try removing the `--package=task-master-ai` flag from `args`.
 
-```
+###### VS Code (`servers` + `type`)
-Can you please initialize taskmaster-ai into my project?
+
+```json
+{
+  "servers": {
+    "taskmaster-ai": {
+      "command": "npx",
+      "args": ["-y", "--package=task-master-ai", "task-master-ai"],
+      "env": {
+        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
+        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
+        "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
+        "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
+        "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
+        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
+        "XAI_API_KEY": "YOUR_XAI_KEY_HERE",
+        "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE"
+      },
+      "type": "stdio"
+    }
+  }
+}
 ```
 
-4. **Use common commands** directly through your AI assistant:
+> 🔑 Replace `YOUR_…_KEY_HERE` with your real API keys. You can remove keys you don't use.
+
+#### 2. (Cursor-only) Enable Taskmaster MCP
+
+Open Cursor Settings (Ctrl+Shift+J) ➡ Click on MCP tab on the left ➡ Enable task-master-ai with the toggle
+
+#### 3. (Optional) Configure the models you want to use
+
+In your editor's AI chat pane, say:
 
 ```txt
-Can you parse my PRD at scripts/prd.txt?
+Change the main, research and fallback models to <model_name>, <model_name> and <model_name> respectively.
-What's the next task I should work on?
-Can you help me implement task 3?
-Can you help me expand task 4?
 ```
 
+For example, to use Claude Code (no API key required):
+```txt
+Change the main model to claude-code/sonnet
+```
+
+[Table of available models](docs/models.md) | [Claude Code setup](docs/examples/claude-code-usage.md)
+
+#### 4. Initialize Task Master
+
+In your editor's AI chat pane, say:
+
+```txt
+Initialize taskmaster-ai in my project
+```
+
+#### 5. Make sure you have a PRD (Recommended)
+
+For **new projects**: Create your PRD at `.taskmaster/docs/prd.txt`  
+For **existing projects**: You can use `scripts/prd.txt` or migrate with `task-master migrate`
+
+An example PRD template is available after initialization in `.taskmaster/templates/example_prd.txt`.
+
+> [!NOTE]
+> While a PRD is recommended for complex projects, you can always create individual tasks by asking "Can you help me implement [description of what you want to do]?" in chat.
+
+**Always start with a detailed PRD.**
+
+The more detailed your PRD, the better the generated tasks will be.
+
+#### 6. Common Commands
+
+Use your AI assistant to:
+
+- Parse requirements: `Can you parse my PRD at scripts/prd.txt?`
+- Plan next step: `What's the next task I should work on?`
+- Implement a task: `Can you help me implement task 3?`
+- View multiple tasks: `Can you show me tasks 1, 3, and 5?`
+- Expand a task: `Can you help me expand task 4?`
+- **Research fresh information**: `Research the latest best practices for implementing JWT authentication with Node.js`
+- **Research with context**: `Research React Query v5 migration strategies for our current API implementation in src/api.js`
+
+[More examples on how to use Task Master in chat](docs/examples.md)
+
 ### Option 2: Using Command Line
 
 #### Installation
@@ -93,6 +197,9 @@ task-master init
 
 # If installed locally
 npx task-master init
+
+# Initialize project with specific rules
+task-master init --rules cursor,windsurf,vscode
 ```
 
 This will prompt you for project details and set up a new project with the necessary files and structure.
@@ -112,23 +219,32 @@ task-master list
 # Show the next task to work on
 task-master next
 
+# Show specific task(s) - supports comma-separated IDs
+task-master show 1,3,5
+
+# Research fresh information with project context
+task-master research "What are the latest best practices for JWT authentication?"
+
 # Generate task files
 task-master generate
+
+# Add rules after initialization
+task-master rules add windsurf,roo,vscode
 ```
 
-## Documentation
+## Claude Code Support
 
-For more detailed information, check out the documentation in the `docs` directory:
+Task Master now supports Claude models through the Claude Code CLI, which requires no API key:
 
-- [Configuration Guide](docs/configuration.md) - Set up environment variables and customize Task Master
+- **Models**: `claude-code/opus` and `claude-code/sonnet`
-- [Tutorial](docs/tutorial.md) - Step-by-step guide to getting started with Task Master
+- **Requirements**: Claude Code CLI installed
-- [Command Reference](docs/command-reference.md) - Complete list of all available commands
+- **Benefits**: No API key needed, uses your local Claude instance
-- [Task Structure](docs/task-structure.md) - Understanding the task format and features
+
-- [Example Interactions](docs/examples.md) - Common Cursor AI interaction examples
+[Learn more about Claude Code setup](docs/examples/claude-code-usage.md)
 
 ## Troubleshooting
 
-### If `task-master init` doesn't respond:
+### If `task-master init` doesn't respond
 
 Try running it with Node directly:
 

assets/.windsurfrules

@@ -1,18 +1,22 @@
 Below you will find a variety of important rules spanning:
+
 - the dev_workflow
 - the .windsurfrules document self-improvement workflow
 - the template to follow when modifying or adding new sections/rules to this document.
 
 ---
-DEV_WORKFLOW
+
----
+## DEV_WORKFLOW
+
 description: Guide for using meta-development script (scripts/dev.js) to manage task-driven development workflows
-globs: **/*
+globs: **/\*
-filesToApplyRule: **/*
+filesToApplyRule: **/\*
 alwaysApply: true
+
 ---
 
 - **Global CLI Commands**
+
   - Task Master now provides a global CLI through the `task-master` command
   - All functionality from `scripts/dev.js` is available through this interface
   - Install globally with `npm install -g claude-task-master` or use locally via `npx`
@@ -25,6 +29,7 @@ alwaysApply: true
   - The CLI provides additional commands like `task-master init` for project setup
 
 - **Development Workflow Process**
+
   - Start new projects by running `task-master init` or `node scripts/dev.js parse-prd --input=<prd-file.txt>` to generate initial tasks.json
   - Begin coding sessions with `task-master list` to see current tasks, status, and IDs
   - Analyze task complexity with `task-master analyze-complexity --research` before breaking down tasks
@@ -43,6 +48,7 @@ alwaysApply: true
   - Report progress regularly using the list command
 
 - **Task Complexity Analysis**
+
   - Run `node scripts/dev.js analyze-complexity --research` for comprehensive analysis
   - Review complexity report in scripts/task-complexity-report.json
   - Or use `node scripts/dev.js complexity-report` for a formatted, readable version of the report
@@ -51,6 +57,7 @@ alwaysApply: true
   - Note that reports are automatically used by the expand command
 
 - **Task Breakdown Process**
+
   - For tasks with complexity analysis, use `node scripts/dev.js expand --id=<id>`
   - Otherwise use `node scripts/dev.js expand --id=<id> --subtasks=<number>`
   - Add `--research` flag to leverage Perplexity AI for research-backed expansion
@@ -60,18 +67,21 @@ alwaysApply: true
   - If subtasks need regeneration, clear them first with `clear-subtasks` command
 
 - **Implementation Drift Handling**
+
   - When implementation differs significantly from planned approach
   - When future tasks need modification due to current implementation choices
   - When new dependencies or requirements emerge
   - Call `node scripts/dev.js update --from=<futureTaskId> --prompt="<explanation>"` to update tasks.json
 
 - **Task Status Management**
+
   - Use 'pending' for tasks ready to be worked on
   - Use 'done' for completed and verified tasks
   - Use 'deferred' for postponed tasks
   - Add custom status values as needed for project-specific workflows
 
 - **Task File Format Reference**
+
   ```
   # Task ID: <id>
   # Title: <title>
@@ -81,21 +91,23 @@ alwaysApply: true
   # Description: <brief description>
   # Details:
   <detailed implementation notes>
-  
+
   # Test Strategy:
   <verification approach>
   ```
 
 - **Command Reference: parse-prd**
+
   - Legacy Syntax: `node scripts/dev.js parse-prd --input=<prd-file.txt>`
   - CLI Syntax: `task-master parse-prd --input=<prd-file.txt>`
   - Description: Parses a PRD document and generates a tasks.json file with structured tasks
-  - Parameters: 
+  - Parameters:
     - `--input=<file>`: Path to the PRD text file (default: sample-prd.txt)
   - Example: `task-master parse-prd --input=requirements.txt`
   - Notes: Will overwrite existing tasks.json file. Use with caution.
 
 - **Command Reference: update**
+
   - Legacy Syntax: `node scripts/dev.js update --from=<id> --prompt="<prompt>"`
   - CLI Syntax: `task-master update --from=<id> --prompt="<prompt>"`
   - Description: Updates tasks with ID >= specified ID based on the provided prompt
@@ -106,16 +118,18 @@ alwaysApply: true
   - Notes: Only updates tasks not marked as 'done'. Completed tasks remain unchanged.
 
 - **Command Reference: generate**
+
   - Legacy Syntax: `node scripts/dev.js generate`
   - CLI Syntax: `task-master generate`
-  - Description: Generates individual task files in tasks/ directory based on tasks.json
+  - Description: Generates individual task files based on tasks.json
-  - Parameters: 
+  - Parameters:
-    - `--file=<path>, -f`: Use alternative tasks.json file (default: 'tasks/tasks.json')
+    - `--file=<path>, -f`: Use alternative tasks.json file (default: '.taskmaster/tasks/tasks.json')
-    - `--output=<dir>, -o`: Output directory (default: 'tasks')
+    - `--output=<dir>, -o`: Output directory (default: '.taskmaster/tasks')
   - Example: `task-master generate`
-  - Notes: Overwrites existing task files. Creates tasks/ directory if needed.
+  - Notes: Overwrites existing task files. Creates output directory if needed.
 
 - **Command Reference: set-status**
+
   - Legacy Syntax: `node scripts/dev.js set-status --id=<id> --status=<status>`
   - CLI Syntax: `task-master set-status --id=<id> --status=<status>`
   - Description: Updates the status of a specific task in tasks.json
@@ -126,10 +140,11 @@ alwaysApply: true
   - Notes: Common values are 'done', 'pending', and 'deferred', but any string is accepted.
 
 - **Command Reference: list**
+
   - Legacy Syntax: `node scripts/dev.js list`
   - CLI Syntax: `task-master list`
   - Description: Lists all tasks in tasks.json with IDs, titles, and status
-  - Parameters: 
+  - Parameters:
     - `--status=<status>, -s`: Filter by status
     - `--with-subtasks`: Show subtasks for each task
     - `--file=<path>, -f`: Use alternative tasks.json file (default: 'tasks/tasks.json')
@@ -137,6 +152,7 @@ alwaysApply: true
   - Notes: Provides quick overview of project progress. Use at start of sessions.
 
 - **Command Reference: expand**
+
   - Legacy Syntax: `node scripts/dev.js expand --id=<id> [--num=<number>] [--research] [--prompt="<context>"]`
   - CLI Syntax: `task-master expand --id=<id> [--num=<number>] [--research] [--prompt="<context>"]`
   - Description: Expands a task with subtasks for detailed implementation
@@ -151,6 +167,7 @@ alwaysApply: true
   - Notes: Uses complexity report recommendations if available.
 
 - **Command Reference: analyze-complexity**
+
   - Legacy Syntax: `node scripts/dev.js analyze-complexity [options]`
   - CLI Syntax: `task-master analyze-complexity [options]`
   - Description: Analyzes task complexity and generates expansion recommendations
@@ -164,6 +181,7 @@ alwaysApply: true
   - Notes: Report includes complexity scores, recommended subtasks, and tailored prompts.
 
 - **Command Reference: clear-subtasks**
+
   - Legacy Syntax: `node scripts/dev.js clear-subtasks --id=<id>`
   - CLI Syntax: `task-master clear-subtasks --id=<id>`
   - Description: Removes subtasks from specified tasks to allow regeneration
@@ -174,12 +192,13 @@ alwaysApply: true
     - `task-master clear-subtasks --id=3`
     - `task-master clear-subtasks --id=1,2,3`
     - `task-master clear-subtasks --all`
-  - Notes: 
+  - Notes:
     - Task files are automatically regenerated after clearing subtasks
     - Can be combined with expand command to immediately generate new subtasks
     - Works with both parent tasks and individual subtasks
 
 - **Task Structure Fields**
+
   - **id**: Unique identifier for the task (Example: `1`)
   - **title**: Brief, descriptive title (Example: `"Initialize Repo"`)
   - **description**: Concise summary of what the task involves (Example: `"Create a new repository, set up initial structure."`)
@@ -193,6 +212,7 @@ alwaysApply: true
   - **subtasks**: List of smaller, more specific tasks (Example: `[{"id": 1, "title": "Configure OAuth", ...}]`)
 
 - **Environment Variables Configuration**
+
   - **ANTHROPIC_API_KEY** (Required): Your Anthropic API key for Claude (Example: `ANTHROPIC_API_KEY=sk-ant-api03-...`)
   - **MODEL** (Default: `"claude-3-7-sonnet-20250219"`): Claude model to use (Example: `MODEL=claude-3-opus-20240229`)
   - **MAX_TOKENS** (Default: `"4000"`): Maximum tokens for responses (Example: `MAX_TOKENS=8000`)
@@ -207,6 +227,7 @@ alwaysApply: true
   - **PERPLEXITY_MODEL** (Default: `"sonar-medium-online"`): Perplexity model (Example: `PERPLEXITY_MODEL=sonar-large-online`)
 
 - **Determining the Next Task**
+
   - Run `task-master next` to show the next task to work on
   - The next command identifies tasks with all dependencies satisfied
   - Tasks are prioritized by priority level, dependency count, and ID
@@ -221,6 +242,7 @@ alwaysApply: true
   - Provides ready-to-use commands for common task actions
 
 - **Viewing Specific Task Details**
+
   - Run `task-master show <id>` or `task-master show --id=<id>` to view a specific task
   - Use dot notation for subtasks: `task-master show 1.2` (shows subtask 2 of task 1)
   - Displays comprehensive information similar to the next command, but for a specific task
@@ -230,6 +252,7 @@ alwaysApply: true
   - Useful for examining task details before implementation or checking status
 
 - **Managing Task Dependencies**
+
   - Use `task-master add-dependency --id=<id> --depends-on=<id>` to add a dependency
   - Use `task-master remove-dependency --id=<id> --depends-on=<id>` to remove a dependency
   - The system prevents circular dependencies and duplicate dependency entries
@@ -238,6 +261,7 @@ alwaysApply: true
   - Dependencies are visualized with status indicators in task listings and files
 
 - **Command Reference: add-dependency**
+
   - Legacy Syntax: `node scripts/dev.js add-dependency --id=<id> --depends-on=<id>`
   - CLI Syntax: `task-master add-dependency --id=<id> --depends-on=<id>`
   - Description: Adds a dependency relationship between two tasks
@@ -248,6 +272,7 @@ alwaysApply: true
   - Notes: Prevents circular dependencies and duplicates; updates task files automatically
 
 - **Command Reference: remove-dependency**
+
   - Legacy Syntax: `node scripts/dev.js remove-dependency --id=<id> --depends-on=<id>`
   - CLI Syntax: `task-master remove-dependency --id=<id> --depends-on=<id>`
   - Description: Removes a dependency relationship between two tasks
@@ -258,44 +283,48 @@ alwaysApply: true
   - Notes: Checks if dependency actually exists; updates task files automatically
 
 - **Command Reference: validate-dependencies**
+
   - Legacy Syntax: `node scripts/dev.js validate-dependencies [options]`
   - CLI Syntax: `task-master validate-dependencies [options]`
   - Description: Checks for and identifies invalid dependencies in tasks.json and task files
   - Parameters:
     - `--file=<path>, -f`: Use alternative tasks.json file (default: 'tasks/tasks.json')
   - Example: `task-master validate-dependencies`
-  - Notes: 
+  - Notes:
     - Reports all non-existent dependencies and self-dependencies without modifying files
     - Provides detailed statistics on task dependency state
     - Use before fix-dependencies to audit your task structure
 
 - **Command Reference: fix-dependencies**
+
   - Legacy Syntax: `node scripts/dev.js fix-dependencies [options]`
   - CLI Syntax: `task-master fix-dependencies [options]`
   - Description: Finds and fixes all invalid dependencies in tasks.json and task files
   - Parameters:
     - `--file=<path>, -f`: Use alternative tasks.json file (default: 'tasks/tasks.json')
   - Example: `task-master fix-dependencies`
-  - Notes: 
+  - Notes:
     - Removes references to non-existent tasks and subtasks
     - Eliminates self-dependencies (tasks depending on themselves)
     - Regenerates task files with corrected dependencies
     - Provides detailed report of all fixes made
 
 - **Command Reference: complexity-report**
+
   - Legacy Syntax: `node scripts/dev.js complexity-report [options]`
   - CLI Syntax: `task-master complexity-report [options]`
   - Description: Displays the task complexity analysis report in a formatted, easy-to-read way
   - Parameters:
     - `--file=<path>, -f`: Path to the complexity report file (default: 'scripts/task-complexity-report.json')
   - Example: `task-master complexity-report`
-  - Notes: 
+  - Notes:
     - Shows tasks organized by complexity score with recommended actions
     - Provides complexity distribution statistics
     - Displays ready-to-use expansion commands for complex tasks
     - If no report exists, offers to generate one interactively
 
 - **Command Reference: add-task**
+
   - CLI Syntax: `task-master add-task [options]`
   - Description: Add a new task to tasks.json using AI
   - Parameters:
@@ -307,11 +336,12 @@ alwaysApply: true
   - Notes: Uses AI to convert description into structured task with appropriate details
 
 - **Command Reference: init**
+
   - CLI Syntax: `task-master init`
   - Description: Initialize a new project with Task Master structure
   - Parameters: None
   - Example: `task-master init`
-  - Notes: 
+  - Notes:
     - Creates initial project structure with required files
     - Prompts for project settings if not provided
     - Merges with existing files when appropriate
@@ -341,15 +371,20 @@ alwaysApply: true
       - Check for any unintentional duplications or omissions
 
 ---
-WINDSURF_RULES
+
----
+## WINDSURF_RULES
+
 description: Guidelines for creating and maintaining Windsurf rules to ensure consistency and effectiveness.
 globs: .windsurfrules
 filesToApplyRule: .windsurfrules
 alwaysApply: true
+
 ---
+
 The below describes how you should be structuring new rule sections in this document.
+
 - **Required Rule Structure:**
+
   ```markdown
   ---
   description: Clear, one-line description of what the rule enforces
@@ -363,20 +398,24 @@ The below describes how you should be structuring new rule sections in this docu
   ```
 
 - **Section References:**
+
   - Use `ALL_CAPS_SECTION` to reference files
   - Example: `WINDSURF_RULES`
 
 - **Code Examples:**
+
   - Use language-specific code blocks
+
   ```typescript
   // ✅ DO: Show good examples
   const goodExample = true;
-  
+
   // ❌ DON'T: Show anti-patterns
   const badExample = false;
   ```
 
 - **Rule Content Guidelines:**
+
   - Start with high-level overview
   - Include specific, actionable requirements
   - Show examples of correct implementation
@@ -384,6 +423,7 @@ The below describes how you should be structuring new rule sections in this docu
   - Keep rules DRY by referencing other rules
 
 - **Rule Maintenance:**
+
   - Update rules when new patterns emerge
   - Add examples from actual codebase
   - Remove outdated patterns
@@ -394,18 +434,21 @@ The below describes how you should be structuring new rule sections in this docu
   - Keep descriptions concise
   - Include both DO and DON'T examples
   - Reference actual code over theoretical examples
-  - Use consistent formatting across rules 
+  - Use consistent formatting across rules
 
 ---
-SELF_IMPROVE
+
----
+## SELF_IMPROVE
+
 description: Guidelines for continuously improving this rules document based on emerging code patterns and best practices.
-globs: **/*
+globs: **/\*
-filesToApplyRule: **/*
+filesToApplyRule: **/\*
 alwaysApply: true
+
 ---
 
 - **Rule Improvement Triggers:**
+
   - New code patterns not covered by existing rules
   - Repeated similar implementations across files
   - Common error patterns that could be prevented
@@ -413,6 +456,7 @@ alwaysApply: true
   - Emerging best practices in the codebase
 
 - **Analysis Process:**
+
   - Compare new code with existing rules
   - Identify patterns that should be standardized
   - Look for references to external documentation
@@ -420,7 +464,9 @@ alwaysApply: true
   - Monitor test patterns and coverage
 
 - **Rule Updates:**
+
   - **Add New Rules When:**
+
     - A new technology/pattern is used in 3+ files
     - Common bugs could be prevented by a rule
     - Code reviews repeatedly mention the same feedback
@@ -433,13 +479,14 @@ alwaysApply: true
     - Implementation details have changed
 
 - **Example Pattern Recognition:**
+
   ```typescript
   // If you see repeated patterns like:
   const data = await prisma.user.findMany({
     select: { id: true, email: true },
-    where: { status: 'ACTIVE' }
+    where: { status: "ACTIVE" },
   });
-  
+
   // Consider adding a PRISMA section in the .windsurfrules:
   // - Standard select fields
   // - Common where conditions
@@ -447,12 +494,14 @@ alwaysApply: true
   ```
 
 - **Rule Quality Checks:**
+
   - Rules should be actionable and specific
   - Examples should come from actual code
   - References should be up to date
   - Patterns should be consistently enforced
 
 - **Continuous Improvement:**
+
   - Monitor code review comments
   - Track common development questions
   - Update rules after major refactors
@@ -460,6 +509,7 @@ alwaysApply: true
   - Cross-reference related rules
 
 - **Rule Deprecation:**
+
   - Mark outdated patterns as deprecated
   - Remove rules that no longer apply
   - Update references to deprecated rules
@@ -471,4 +521,4 @@ alwaysApply: true
   - Maintain links between related rules
   - Document breaking changes
 
-Follow WINDSURF_RULES for proper rule formatting and structure of windsurf rule sections.
+Follow WINDSURF_RULES for proper rule formatting and structure of windsurf rule sections.

assets/AGENTS.md

@@ -0,0 +1,417 @@
+# Task Master AI - Claude Code Integration Guide
+
+## Essential Commands
+
+### Core Workflow Commands
+
+```bash
+# Project Setup
+task-master init                                    # Initialize Task Master in current project
+task-master parse-prd .taskmaster/docs/prd.txt      # Generate tasks from PRD document
+task-master models --setup                        # Configure AI models interactively
+
+# Daily Development Workflow
+task-master list                                   # Show all tasks with status
+task-master next                                   # Get next available task to work on
+task-master show <id>                             # View detailed task information (e.g., task-master show 1.2)
+task-master set-status --id=<id> --status=done    # Mark task complete
+
+# Task Management
+task-master add-task --prompt="description" --research        # Add new task with AI assistance
+task-master expand --id=<id> --research --force              # Break task into subtasks
+task-master update-task --id=<id> --prompt="changes"         # Update specific task
+task-master update --from=<id> --prompt="changes"            # Update multiple tasks from ID onwards
+task-master update-subtask --id=<id> --prompt="notes"        # Add implementation notes to subtask
+
+# Analysis & Planning
+task-master analyze-complexity --research          # Analyze task complexity
+task-master complexity-report                      # View complexity analysis
+task-master expand --all --research               # Expand all eligible tasks
+
+# Dependencies & Organization
+task-master add-dependency --id=<id> --depends-on=<id>       # Add task dependency
+task-master move --from=<id> --to=<id>                       # Reorganize task hierarchy
+task-master validate-dependencies                            # Check for dependency issues
+task-master generate                                         # Update task markdown files (usually auto-called)
+```
+
+## Key Files & Project Structure
+
+### Core Files
+
+- `.taskmaster/tasks/tasks.json` - Main task data file (auto-managed)
+- `.taskmaster/config.json` - AI model configuration (use `task-master models` to modify)
+- `.taskmaster/docs/prd.txt` - Product Requirements Document for parsing
+- `.taskmaster/tasks/*.txt` - Individual task files (auto-generated from tasks.json)
+- `.env` - API keys for CLI usage
+
+### Claude Code Integration Files
+
+- `CLAUDE.md` - Auto-loaded context for Claude Code (this file)
+- `.claude/settings.json` - Claude Code tool allowlist and preferences
+- `.claude/commands/` - Custom slash commands for repeated workflows
+- `.mcp.json` - MCP server configuration (project-specific)
+
+### Directory Structure
+
+```
+project/
+├── .taskmaster/
+│   ├── tasks/              # Task files directory
+│   │   ├── tasks.json      # Main task database
+│   │   ├── task-1.md      # Individual task files
+│   │   └── task-2.md
+│   ├── docs/              # Documentation directory
+│   │   ├── prd.txt        # Product requirements
+│   ├── reports/           # Analysis reports directory
+│   │   └── task-complexity-report.json
+│   ├── templates/         # Template files
+│   │   └── example_prd.txt  # Example PRD template
+│   └── config.json        # AI models & settings
+├── .claude/
+│   ├── settings.json      # Claude Code configuration
+│   └── commands/         # Custom slash commands
+├── .env                  # API keys
+├── .mcp.json            # MCP configuration
+└── CLAUDE.md            # This file - auto-loaded by Claude Code
+```
+
+## MCP Integration
+
+Task Master provides an MCP server that Claude Code can connect to. Configure in `.mcp.json`:
+
+```json
+{
+  "mcpServers": {
+    "task-master-ai": {
+      "command": "npx",
+      "args": ["-y", "--package=task-master-ai", "task-master-ai"],
+      "env": {
+        "ANTHROPIC_API_KEY": "your_key_here",
+        "PERPLEXITY_API_KEY": "your_key_here",
+        "OPENAI_API_KEY": "OPENAI_API_KEY_HERE",
+        "GOOGLE_API_KEY": "GOOGLE_API_KEY_HERE",
+        "XAI_API_KEY": "XAI_API_KEY_HERE",
+        "OPENROUTER_API_KEY": "OPENROUTER_API_KEY_HERE",
+        "MISTRAL_API_KEY": "MISTRAL_API_KEY_HERE",
+        "AZURE_OPENAI_API_KEY": "AZURE_OPENAI_API_KEY_HERE",
+        "OLLAMA_API_KEY": "OLLAMA_API_KEY_HERE"
+      }
+    }
+  }
+}
+```
+
+### Essential MCP Tools
+
+```javascript
+help; // = shows available taskmaster commands
+// Project setup
+initialize_project; // = task-master init
+parse_prd; // = task-master parse-prd
+
+// Daily workflow
+get_tasks; // = task-master list
+next_task; // = task-master next
+get_task; // = task-master show <id>
+set_task_status; // = task-master set-status
+
+// Task management
+add_task; // = task-master add-task
+expand_task; // = task-master expand
+update_task; // = task-master update-task
+update_subtask; // = task-master update-subtask
+update; // = task-master update
+
+// Analysis
+analyze_project_complexity; // = task-master analyze-complexity
+complexity_report; // = task-master complexity-report
+```
+
+## Claude Code Workflow Integration
+
+### Standard Development Workflow
+
+#### 1. Project Initialization
+
+```bash
+# Initialize Task Master
+task-master init
+
+# Create or obtain PRD, then parse it
+task-master parse-prd .taskmaster/docs/prd.txt
+
+# Analyze complexity and expand tasks
+task-master analyze-complexity --research
+task-master expand --all --research
+```
+
+If tasks already exist, another PRD can be parsed (with new information only!) using parse-prd with --append flag. This will add the generated tasks to the existing list of tasks..
+
+#### 2. Daily Development Loop
+
+```bash
+# Start each session
+task-master next                           # Find next available task
+task-master show <id>                     # Review task details
+
+# During implementation, check in code context into the tasks and subtasks
+task-master update-subtask --id=<id> --prompt="implementation notes..."
+
+# Complete tasks
+task-master set-status --id=<id> --status=done
+```
+
+#### 3. Multi-Claude Workflows
+
+For complex projects, use multiple Claude Code sessions:
+
+```bash
+# Terminal 1: Main implementation
+cd project && claude
+
+# Terminal 2: Testing and validation
+cd project-test-worktree && claude
+
+# Terminal 3: Documentation updates
+cd project-docs-worktree && claude
+```
+
+### Custom Slash Commands
+
+Create `.claude/commands/taskmaster-next.md`:
+
+```markdown
+Find the next available Task Master task and show its details.
+
+Steps:
+
+1. Run `task-master next` to get the next task
+2. If a task is available, run `task-master show <id>` for full details
+3. Provide a summary of what needs to be implemented
+4. Suggest the first implementation step
+```
+
+Create `.claude/commands/taskmaster-complete.md`:
+
+```markdown
+Complete a Task Master task: $ARGUMENTS
+
+Steps:
+
+1. Review the current task with `task-master show $ARGUMENTS`
+2. Verify all implementation is complete
+3. Run any tests related to this task
+4. Mark as complete: `task-master set-status --id=$ARGUMENTS --status=done`
+5. Show the next available task with `task-master next`
+```
+
+## Tool Allowlist Recommendations
+
+Add to `.claude/settings.json`:
+
+```json
+{
+  "allowedTools": [
+    "Edit",
+    "Bash(task-master *)",
+    "Bash(git commit:*)",
+    "Bash(git add:*)",
+    "Bash(npm run *)",
+    "mcp__task_master_ai__*"
+  ]
+}
+```
+
+## Configuration & Setup
+
+### API Keys Required
+
+At least **one** of these API keys must be configured:
+
+- `ANTHROPIC_API_KEY` (Claude models) - **Recommended**
+- `PERPLEXITY_API_KEY` (Research features) - **Highly recommended**
+- `OPENAI_API_KEY` (GPT models)
+- `GOOGLE_API_KEY` (Gemini models)
+- `MISTRAL_API_KEY` (Mistral models)
+- `OPENROUTER_API_KEY` (Multiple models)
+- `XAI_API_KEY` (Grok models)
+
+An API key is required for any provider used across any of the 3 roles defined in the `models` command.
+
+### Model Configuration
+
+```bash
+# Interactive setup (recommended)
+task-master models --setup
+
+# Set specific models
+task-master models --set-main claude-3-5-sonnet-20241022
+task-master models --set-research perplexity-llama-3.1-sonar-large-128k-online
+task-master models --set-fallback gpt-4o-mini
+```
+
+## Task Structure & IDs
+
+### Task ID Format
+
+- Main tasks: `1`, `2`, `3`, etc.
+- Subtasks: `1.1`, `1.2`, `2.1`, etc.
+- Sub-subtasks: `1.1.1`, `1.1.2`, etc.
+
+### Task Status Values
+
+- `pending` - Ready to work on
+- `in-progress` - Currently being worked on
+- `done` - Completed and verified
+- `deferred` - Postponed
+- `cancelled` - No longer needed
+- `blocked` - Waiting on external factors
+
+### Task Fields
+
+```json
+{
+  "id": "1.2",
+  "title": "Implement user authentication",
+  "description": "Set up JWT-based auth system",
+  "status": "pending",
+  "priority": "high",
+  "dependencies": ["1.1"],
+  "details": "Use bcrypt for hashing, JWT for tokens...",
+  "testStrategy": "Unit tests for auth functions, integration tests for login flow",
+  "subtasks": []
+}
+```
+
+## Claude Code Best Practices with Task Master
+
+### Context Management
+
+- Use `/clear` between different tasks to maintain focus
+- This CLAUDE.md file is automatically loaded for context
+- Use `task-master show <id>` to pull specific task context when needed
+
+### Iterative Implementation
+
+1. `task-master show <subtask-id>` - Understand requirements
+2. Explore codebase and plan implementation
+3. `task-master update-subtask --id=<id> --prompt="detailed plan"` - Log plan
+4. `task-master set-status --id=<id> --status=in-progress` - Start work
+5. Implement code following logged plan
+6. `task-master update-subtask --id=<id> --prompt="what worked/didn't work"` - Log progress
+7. `task-master set-status --id=<id> --status=done` - Complete task
+
+### Complex Workflows with Checklists
+
+For large migrations or multi-step processes:
+
+1. Create a markdown PRD file describing the new changes: `touch task-migration-checklist.md` (prds can be .txt or .md)
+2. Use Taskmaster to parse the new prd with `task-master parse-prd --append` (also available in MCP)
+3. Use Taskmaster to expand the newly generated tasks into subtasks. Consdier using `analyze-complexity` with the correct --to and --from IDs (the new ids) to identify the ideal subtask amounts for each task. Then expand them.
+4. Work through items systematically, checking them off as completed
+5. Use `task-master update-subtask` to log progress on each task/subtask and/or updating/researching them before/during implementation if getting stuck
+
+### Git Integration
+
+Task Master works well with `gh` CLI:
+
+```bash
+# Create PR for completed task
+gh pr create --title "Complete task 1.2: User authentication" --body "Implements JWT auth system as specified in task 1.2"
+
+# Reference task in commits
+git commit -m "feat: implement JWT auth (task 1.2)"
+```
+
+### Parallel Development with Git Worktrees
+
+```bash
+# Create worktrees for parallel task development
+git worktree add ../project-auth feature/auth-system
+git worktree add ../project-api feature/api-refactor
+
+# Run Claude Code in each worktree
+cd ../project-auth && claude    # Terminal 1: Auth work
+cd ../project-api && claude     # Terminal 2: API work
+```
+
+## Troubleshooting
+
+### AI Commands Failing
+
+```bash
+# Check API keys are configured
+cat .env                           # For CLI usage
+
+# Verify model configuration
+task-master models
+
+# Test with different model
+task-master models --set-fallback gpt-4o-mini
+```
+
+### MCP Connection Issues
+
+- Check `.mcp.json` configuration
+- Verify Node.js installation
+- Use `--mcp-debug` flag when starting Claude Code
+- Use CLI as fallback if MCP unavailable
+
+### Task File Sync Issues
+
+```bash
+# Regenerate task files from tasks.json
+task-master generate
+
+# Fix dependency issues
+task-master fix-dependencies
+```
+
+DO NOT RE-INITIALIZE. That will not do anything beyond re-adding the same Taskmaster core files.
+
+## Important Notes
+
+### AI-Powered Operations
+
+These commands make AI calls and may take up to a minute:
+
+- `parse_prd` / `task-master parse-prd`
+- `analyze_project_complexity` / `task-master analyze-complexity`
+- `expand_task` / `task-master expand`
+- `expand_all` / `task-master expand --all`
+- `add_task` / `task-master add-task`
+- `update` / `task-master update`
+- `update_task` / `task-master update-task`
+- `update_subtask` / `task-master update-subtask`
+
+### File Management
+
+- Never manually edit `tasks.json` - use commands instead
+- Never manually edit `.taskmaster/config.json` - use `task-master models`
+- Task markdown files in `tasks/` are auto-generated
+- Run `task-master generate` after manual changes to tasks.json
+
+### Claude Code Session Management
+
+- Use `/clear` frequently to maintain focused context
+- Create custom slash commands for repeated Task Master workflows
+- Configure tool allowlist to streamline permissions
+- Use headless mode for automation: `claude -p "task-master next"`
+
+### Multi-Task Updates
+
+- Use `update --from=<id>` to update multiple future tasks
+- Use `update-task --id=<id>` for single task updates
+- Use `update-subtask --id=<id>` for implementation logging
+
+### Research Mode
+
+- Add `--research` flag for research-based AI enhancement
+- Requires a research model API key like Perplexity (`PERPLEXITY_API_KEY`) in environment
+- Provides more informed task creation and updates
+- Recommended for complex technical tasks
+
+---
+
+_This guide ensures Claude Code has immediate access to Task Master's essential functionality for agentic development workflows._

assets/config.json

@@ -25,7 +25,9 @@
 		"defaultSubtasks": 5,
 		"defaultPriority": "medium",
 		"projectName": "Taskmaster",
-		"ollamaBaseUrl": "http://localhost:11434/api",
+		"defaultTag": "master",
-		"azureOpenaiBaseUrl": "https://your-endpoint.openai.azure.com/"
+		"ollamaBaseURL": "http://localhost:11434/api",
+		"azureOpenaiBaseURL": "https://your-endpoint.openai.azure.com/",
+		"bedrockBaseURL": "https://bedrock.us-east-1.amazonaws.com"
 	}
 }

assets/env.example

@@ -5,5 +5,6 @@ OPENAI_API_KEY="your_openai_api_key_here"             # Optional, for OpenAI/Ope
 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.
-AZURE_OPENAI_API_KEY="your_azure_key_here"            # Optional, for Azure OpenAI models (requires endpoint in .taskmasterconfig).
+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.
+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_...

assets/gitignore

@@ -22,8 +22,4 @@ node_modules/
 *.sw?
 
 # OS specific
-.DS_Store
+.DS_Store
-
-# Task files
-tasks.json
-tasks/ 

assets/roocode/.roo/rules-architect/architect-rules

@@ -9,32 +9,32 @@
 
 **Architectural Design & Planning Role (Delegated Tasks):**
 
-Your primary role when activated via `new_task` by the Boomerang orchestrator is to perform specific architectural, design, or planning tasks, focusing on the instructions provided in the delegation message and referencing the relevant `taskmaster-ai` task ID.
+Your primary role when activated via `new_task` by the Orchestrator is to perform specific architectural, design, or planning tasks, focusing on the instructions provided in the delegation message and referencing the relevant `taskmaster-ai` task ID.
 
-1.  **Analyze Delegated Task:** Carefully examine the `message` provided by Boomerang. This message contains the specific task scope, context (including the `taskmaster-ai` task ID), and constraints.
+1.  **Analyze Delegated Task:** Carefully examine the `message` provided by Orchestrator. This message contains the specific task scope, context (including the `taskmaster-ai` task ID), and constraints.
 2.  **Information Gathering (As Needed):** Use analysis tools to fulfill the task:
     *   `list_files`: Understand project structure.
     *   `read_file`: Examine specific code, configuration, or documentation files relevant to the architectural task.
     *   `list_code_definition_names`: Analyze code structure and relationships.
-    *   `use_mcp_tool` (taskmaster-ai): Use `get_task` or `analyze_project_complexity` *only if explicitly instructed* by Boomerang in the delegation message to gather further context beyond what was provided.
+    *   `use_mcp_tool` (taskmaster-ai): Use `get_task` or `analyze_project_complexity` *only if explicitly instructed* by Orchestrator in the delegation message to gather further context beyond what was provided.
 3.  **Task Execution (Design & Planning):** Focus *exclusively* on the delegated architectural task, which may involve:
     *   Designing system architecture, component interactions, or data models.
     *   Planning implementation steps or identifying necessary subtasks (to be reported back).
     *   Analyzing technical feasibility, complexity, or potential risks.
     *   Defining interfaces, APIs, or data contracts.
     *   Reviewing existing code/architecture against requirements or best practices.
-4.  **Reporting Completion:** Signal completion using `attempt_completion`. Provide a concise yet thorough summary of the outcome in the `result` parameter. This summary is **crucial** for Boomerang to update `taskmaster-ai`. Include:
+4.  **Reporting Completion:** Signal completion using `attempt_completion`. Provide a concise yet thorough summary of the outcome in the `result` parameter. This summary is **crucial** for Orchestrator to update `taskmaster-ai`. Include:
     *   Summary of design decisions, plans created, analysis performed, or subtasks identified.
     *   Any relevant artifacts produced (e.g., diagrams described, markdown files written - if applicable and instructed).
     *   Completion status (success, failure, needs review).
     *   Any significant findings, potential issues, or context gathered relevant to the next steps.
 5.  **Handling Issues:**
-    *   **Complexity/Review:** If you encounter significant complexity, uncertainty, or issues requiring further review (e.g., needing testing input, deeper debugging analysis), set the status to 'review' within your `attempt_completion` result and clearly state the reason. **Do not delegate directly.** Report back to Boomerang.
+    *   **Complexity/Review:** If you encounter significant complexity, uncertainty, or issues requiring further review (e.g., needing testing input, deeper debugging analysis), set the status to 'review' within your `attempt_completion` result and clearly state the reason. **Do not delegate directly.** Report back to Orchestrator.
     *   **Failure:** If the task fails (e.g., requirements are contradictory, necessary information unavailable), clearly report the failure and the reason in the `attempt_completion` result.
 6.  **Taskmaster Interaction:**
-    *   **Primary Responsibility:** Boomerang is primarily responsible for updating Taskmaster (`set_task_status`, `update_task`, `update_subtask`) after receiving your `attempt_completion` result.
+    *   **Primary Responsibility:** Orchestrator is primarily responsible for updating Taskmaster (`set_task_status`, `update_task`, `update_subtask`) after receiving your `attempt_completion` result.
-    *   **Direct Updates (Rare):** Only update Taskmaster directly if operating autonomously (not under Boomerang's delegation) or if *explicitly* instructed by Boomerang within the `new_task` message.
+    *   **Direct Updates (Rare):** Only update Taskmaster directly if operating autonomously (not under Orchestrator's delegation) or if *explicitly* instructed by Orchestrator within the `new_task` message.
-7.  **Autonomous Operation (Exceptional):** If operating outside of Boomerang's delegation (e.g., direct user request), ensure Taskmaster is initialized before attempting Taskmaster operations (see Taskmaster-AI Strategy below).
+7.  **Autonomous Operation (Exceptional):** If operating outside of Orchestrator's delegation (e.g., direct user request), ensure Taskmaster is initialized before attempting Taskmaster operations (see Taskmaster-AI Strategy below).
 
 **Context Reporting Strategy:**
 
@@ -42,17 +42,17 @@ context_reporting: |
       <thinking>
       Strategy:
       - Focus on providing comprehensive information within the `attempt_completion` `result` parameter.
-      - Boomerang will use this information to update Taskmaster's `description`, `details`, or log via `update_task`/`update_subtask`.
+      - Orchestrator will use this information to update Taskmaster's `description`, `details`, or log via `update_task`/`update_subtask`.
       - My role is to *report* accurately, not *log* directly to Taskmaster unless explicitly instructed or operating autonomously.
       </thinking>
-      - **Goal:** Ensure the `result` parameter in `attempt_completion` contains all necessary information for Boomerang to understand the outcome and update Taskmaster effectively.
+      - **Goal:** Ensure the `result` parameter in `attempt_completion` contains all necessary information for Orchestrator to understand the outcome and update Taskmaster effectively.
       - **Content:** Include summaries of architectural decisions, plans, analysis, identified subtasks, errors encountered, or new context discovered. Structure the `result` clearly.
       - **Trigger:** Always provide a detailed `result` upon using `attempt_completion`.
-      - **Mechanism:** Boomerang receives the `result` and performs the necessary Taskmaster updates.
+      - **Mechanism:** Orchestrator receives the `result` and performs the necessary Taskmaster updates.
 
 **Taskmaster-AI Strategy (for Autonomous Operation):**
 
-# Only relevant if operating autonomously (not delegated by Boomerang).
+# Only relevant if operating autonomously (not delegated by Orchestrator).
 taskmaster_strategy:
   status_prefix: "Begin autonomous responses with either '[TASKMASTER: ON]' or '[TASKMASTER: OFF]'."
   initialization: |
@@ -64,7 +64,7 @@ taskmaster_strategy:
       *Execute the plan described above only if autonomous Taskmaster interaction is required.*
   if_uninitialized: |
       1. **Inform:** "Task Master is not initialized. Autonomous Taskmaster operations cannot proceed."
-      2. **Suggest:** "Consider switching to Boomerang mode to initialize and manage the project workflow."
+      2. **Suggest:** "Consider switching to Orchestrator mode to initialize and manage the project workflow."
   if_ready: |
       1. **Verify & Load:** Optionally fetch tasks using `taskmaster-ai`'s `get_tasks` tool if needed for autonomous context.
       2. **Set Status:** Set status to '[TASKMASTER: ON]'.
@@ -73,21 +73,21 @@ taskmaster_strategy:
 **Mode Collaboration & Triggers (Architect Perspective):**
 
 mode_collaboration: |
-    # Architect Mode Collaboration (Focus on receiving from Boomerang and reporting back)
+    # Architect Mode Collaboration (Focus on receiving from Orchestrator and reporting back)
-    - Delegated Task Reception (FROM Boomerang via `new_task`):
+    - Delegated Task Reception (FROM Orchestrator via `new_task`):
       * Receive specific architectural/planning task instructions referencing a `taskmaster-ai` ID.
-      * Analyze requirements, scope, and constraints provided by Boomerang.
+      * Analyze requirements, scope, and constraints provided by Orchestrator.
-    - Completion Reporting (TO Boomerang via `attempt_completion`):
+    - Completion Reporting (TO Orchestrator via `attempt_completion`):
       * Report design decisions, plans, analysis results, or identified subtasks in the `result`.
-      * Include completion status (success, failure, review) and context for Boomerang.
+      * Include completion status (success, failure, review) and context for Orchestrator.
       * Signal completion of the *specific delegated architectural task*.
 
 mode_triggers:
-  # Conditions that might trigger a switch TO Architect mode (typically orchestrated BY Boomerang based on needs identified by other modes or the user)
+  # Conditions that might trigger a switch TO Architect mode (typically orchestrated BY Orchestrator based on needs identified by other modes or the user)
   architect:
     - condition: needs_architectural_design # e.g., New feature requires system design
     - condition: needs_refactoring_plan # e.g., Code mode identifies complex refactoring needed
     - condition: needs_complexity_analysis # e.g., Before breaking down a large feature
     - condition: design_clarification_needed # e.g., Implementation details unclear
     - condition: pattern_violation_found # e.g., Code deviates significantly from established patterns
-    - condition: review_architectural_decision # e.g., Boomerang requests review based on 'review' status from another mode
+    - condition: review_architectural_decision # e.g., Orchestrator requests review based on 'review' status from another mode

assets/roocode/.roo/rules-ask/ask-rules

@@ -9,16 +9,16 @@
 
 **Information Retrieval & Explanation Role (Delegated Tasks):**
 
-Your primary role when activated via `new_task` by the Boomerang (orchestrator) mode is to act as a specialized technical assistant. Focus *exclusively* on fulfilling the specific instructions provided in the `new_task` message, referencing the relevant `taskmaster-ai` task ID.
+Your primary role when activated via `new_task` by the Orchestrator (orchestrator) mode is to act as a specialized technical assistant. Focus *exclusively* on fulfilling the specific instructions provided in the `new_task` message, referencing the relevant `taskmaster-ai` task ID.
 
 1.  **Understand the Request:** Carefully analyze the `message` provided in the `new_task` delegation. This message will contain the specific question, information request, or analysis needed, referencing the `taskmaster-ai` task ID for context.
 2.  **Information Gathering:** Utilize appropriate tools to gather the necessary information based *only* on the delegation instructions:
     *   `read_file`: To examine specific file contents.
     *   `search_files`: To find patterns or specific text across the project.
     *   `list_code_definition_names`: To understand code structure in relevant directories.
-    *   `use_mcp_tool` (with `taskmaster-ai`): *Only if explicitly instructed* by the Boomerang delegation message to retrieve specific task details (e.g., using `get_task`).
+    *   `use_mcp_tool` (with `taskmaster-ai`): *Only if explicitly instructed* by the Orchestrator delegation message to retrieve specific task details (e.g., using `get_task`).
 3.  **Formulate Response:** Synthesize the gathered information into a clear, concise, and accurate answer or explanation addressing the specific request from the delegation message.
-4.  **Reporting Completion:** Signal completion using `attempt_completion`. Provide a concise yet thorough summary of the outcome in the `result` parameter. This summary is **crucial** for Boomerang to process and potentially update `taskmaster-ai`. Include:
+4.  **Reporting Completion:** Signal completion using `attempt_completion`. Provide a concise yet thorough summary of the outcome in the `result` parameter. This summary is **crucial** for Orchestrator to process and potentially update `taskmaster-ai`. Include:
     *   The complete answer, explanation, or analysis formulated in the previous step.
     *   Completion status (success, failure - e.g., if information could not be found).
     *   Any significant findings or context gathered relevant to the question.
@@ -31,22 +31,22 @@ context_reporting: |
       <thinking>
       Strategy:
       - Focus on providing comprehensive information (the answer/analysis) within the `attempt_completion` `result` parameter.
-      - Boomerang will use this information to potentially update Taskmaster's `description`, `details`, or log via `update_task`/`update_subtask`.
+      - Orchestrator will use this information to potentially update Taskmaster's `description`, `details`, or log via `update_task`/`update_subtask`.
       - My role is to *report* accurately, not *log* directly to Taskmaster.
       </thinking>
-      - **Goal:** Ensure the `result` parameter in `attempt_completion` contains the complete and accurate answer/analysis requested by Boomerang.
+      - **Goal:** Ensure the `result` parameter in `attempt_completion` contains the complete and accurate answer/analysis requested by Orchestrator.
       - **Content:** Include the full answer, explanation, or analysis results. Cite sources if applicable. Structure the `result` clearly.
       - **Trigger:** Always provide a detailed `result` upon using `attempt_completion`.
-      - **Mechanism:** Boomerang receives the `result` and performs any necessary Taskmaster updates or decides the next workflow step.
+      - **Mechanism:** Orchestrator receives the `result` and performs any necessary Taskmaster updates or decides the next workflow step.
 
 **Taskmaster Interaction:**
 
-*   **Primary Responsibility:** Boomerang is primarily responsible for updating Taskmaster (`set_task_status`, `update_task`, `update_subtask`) after receiving your `attempt_completion` result.
+*   **Primary Responsibility:** Orchestrator is primarily responsible for updating Taskmaster (`set_task_status`, `update_task`, `update_subtask`) after receiving your `attempt_completion` result.
-*   **Direct Use (Rare & Specific):** Only use Taskmaster tools (`use_mcp_tool` with `taskmaster-ai`) if *explicitly instructed* by Boomerang within the `new_task` message, and *only* for retrieving information (e.g., `get_task`). Do not update Taskmaster status or content directly.
+*   **Direct Use (Rare & Specific):** Only use Taskmaster tools (`use_mcp_tool` with `taskmaster-ai`) if *explicitly instructed* by Orchestrator within the `new_task` message, and *only* for retrieving information (e.g., `get_task`). Do not update Taskmaster status or content directly.
 
 **Taskmaster-AI Strategy (for Autonomous Operation):**
 
-# Only relevant if operating autonomously (not delegated by Boomerang), which is highly exceptional for Ask mode.
+# Only relevant if operating autonomously (not delegated by Orchestrator), which is highly exceptional for Ask mode.
 taskmaster_strategy:
   status_prefix: "Begin autonomous responses with either '[TASKMASTER: ON]' or '[TASKMASTER: OFF]'."
   initialization: |
@@ -58,7 +58,7 @@ taskmaster_strategy:
       *Execute the plan described above only if autonomous Taskmaster interaction is required.*
   if_uninitialized: |
       1. **Inform:** "Task Master is not initialized. Autonomous Taskmaster operations cannot proceed."
-      2. **Suggest:** "Consider switching to Boomerang mode to initialize and manage the project workflow."
+      2. **Suggest:** "Consider switching to Orchestrator mode to initialize and manage the project workflow."
   if_ready: |
       1. **Verify & Load:** Optionally fetch tasks using `taskmaster-ai`'s `get_tasks` tool if needed for autonomous context (again, very rare for Ask).
       2. **Set Status:** Set status to '[TASKMASTER: ON]'.
@@ -67,13 +67,13 @@ taskmaster_strategy:
 **Mode Collaboration & Triggers:**
 
 mode_collaboration: |
-    # Ask Mode Collaboration: Focuses on receiving tasks from Boomerang and reporting back findings.
+    # Ask Mode Collaboration: Focuses on receiving tasks from Orchestrator and reporting back findings.
-    - Delegated Task Reception (FROM Boomerang via `new_task`):
+    - Delegated Task Reception (FROM Orchestrator via `new_task`):
-      * Understand question/analysis request from Boomerang (referencing taskmaster-ai task ID).
+      * Understand question/analysis request from Orchestrator (referencing taskmaster-ai task ID).
       * Research information or analyze provided context using appropriate tools (`read_file`, `search_files`, etc.) as instructed.
       * Formulate answers/explanations strictly within the subtask scope.
       * Use `taskmaster-ai` tools *only* if explicitly instructed in the delegation message for information retrieval.
-    - Completion Reporting (TO Boomerang via `attempt_completion`):
+    - Completion Reporting (TO Orchestrator via `attempt_completion`):
       * Provide the complete answer, explanation, or analysis results in the `result` parameter.
       * Report completion status (success/failure) of the information-gathering subtask.
       * Cite sources or relevant context found.

assets/roocode/.roo/rules-code/code-rules

@@ -9,22 +9,22 @@
 
 **Execution Role (Delegated Tasks):**
 
-Your primary role is to **execute** tasks delegated to you by the Boomerang orchestrator mode. Focus on fulfilling the specific instructions provided in the `new_task` message, referencing the relevant `taskmaster-ai` task ID.
+Your primary role is to **execute** tasks delegated to you by the Orchestrator mode. Focus on fulfilling the specific instructions provided in the `new_task` message, referencing the relevant `taskmaster-ai` task ID.
 
 1.  **Task Execution:** Implement the requested code changes, run commands, use tools, or perform system operations as specified in the delegated task instructions.
-2.  **Reporting Completion:** Signal completion using `attempt_completion`. Provide a concise yet thorough summary of the outcome in the `result` parameter. This summary is **crucial** for Boomerang to update `taskmaster-ai`. Include:
+2.  **Reporting Completion:** Signal completion using `attempt_completion`. Provide a concise yet thorough summary of the outcome in the `result` parameter. This summary is **crucial** for Orchestrator to update `taskmaster-ai`. Include:
     *   Outcome of commands/tool usage.
     *   Summary of code changes made or system operations performed.
     *   Completion status (success, failure, needs review).
     *   Any significant findings, errors encountered, or context gathered.
     *   Links to commits or relevant code sections if applicable.
 3.  **Handling Issues:**
-    *   **Complexity/Review:** If you encounter significant complexity, uncertainty, or issues requiring review (architectural, testing, debugging), set the status to 'review' within your `attempt_completion` result and clearly state the reason. **Do not delegate directly.** Report back to Boomerang.
+    *   **Complexity/Review:** If you encounter significant complexity, uncertainty, or issues requiring review (architectural, testing, debugging), set the status to 'review' within your `attempt_completion` result and clearly state the reason. **Do not delegate directly.** Report back to Orchestrator.
     *   **Failure:** If the task fails, clearly report the failure and any relevant error information in the `attempt_completion` result.
 4.  **Taskmaster Interaction:**
-    *   **Primary Responsibility:** Boomerang is primarily responsible for updating Taskmaster (`set_task_status`, `update_task`, `update_subtask`) after receiving your `attempt_completion` result.
+    *   **Primary Responsibility:** Orchestrator is primarily responsible for updating Taskmaster (`set_task_status`, `update_task`, `update_subtask`) after receiving your `attempt_completion` result.
-    *   **Direct Updates (Rare):** Only update Taskmaster directly if operating autonomously (not under Boomerang's delegation) or if *explicitly* instructed by Boomerang within the `new_task` message.
+    *   **Direct Updates (Rare):** Only update Taskmaster directly if operating autonomously (not under Orchestrator's delegation) or if *explicitly* instructed by Orchestrator within the `new_task` message.
-5.  **Autonomous Operation (Exceptional):** If operating outside of Boomerang's delegation (e.g., direct user request), ensure Taskmaster is initialized before attempting Taskmaster operations (see Taskmaster-AI Strategy below).
+5.  **Autonomous Operation (Exceptional):** If operating outside of Orchestrator's delegation (e.g., direct user request), ensure Taskmaster is initialized before attempting Taskmaster operations (see Taskmaster-AI Strategy below).
 
 **Context Reporting Strategy:**
 
@@ -32,17 +32,17 @@ context_reporting: |
       <thinking>
       Strategy:
       - Focus on providing comprehensive information within the `attempt_completion` `result` parameter.
-      - Boomerang will use this information to update Taskmaster's `description`, `details`, or log via `update_task`/`update_subtask`.
+      - Orchestrator will use this information to update Taskmaster's `description`, `details`, or log via `update_task`/`update_subtask`.
       - My role is to *report* accurately, not *log* directly to Taskmaster unless explicitly instructed or operating autonomously.
       </thinking>
-      - **Goal:** Ensure the `result` parameter in `attempt_completion` contains all necessary information for Boomerang to understand the outcome and update Taskmaster effectively.
+      - **Goal:** Ensure the `result` parameter in `attempt_completion` contains all necessary information for Orchestrator to understand the outcome and update Taskmaster effectively.
       - **Content:** Include summaries of actions taken, results achieved, errors encountered, decisions made during execution (if relevant to the outcome), and any new context discovered. Structure the `result` clearly.
       - **Trigger:** Always provide a detailed `result` upon using `attempt_completion`.
-      - **Mechanism:** Boomerang receives the `result` and performs the necessary Taskmaster updates.
+      - **Mechanism:** Orchestrator receives the `result` and performs the necessary Taskmaster updates.
 
 **Taskmaster-AI Strategy (for Autonomous Operation):**
 
-# Only relevant if operating autonomously (not delegated by Boomerang).
+# Only relevant if operating autonomously (not delegated by Orchestrator).
 taskmaster_strategy:
   status_prefix: "Begin autonomous responses with either '[TASKMASTER: ON]' or '[TASKMASTER: OFF]'."
   initialization: |
@@ -54,7 +54,7 @@ taskmaster_strategy:
       *Execute the plan described above only if autonomous Taskmaster interaction is required.*
   if_uninitialized: |
       1. **Inform:** "Task Master is not initialized. Autonomous Taskmaster operations cannot proceed."
-      2. **Suggest:** "Consider switching to Boomerang mode to initialize and manage the project workflow."
+      2. **Suggest:** "Consider switching to Orchestrator mode to initialize and manage the project workflow."
   if_ready: |
       1. **Verify & Load:** Optionally fetch tasks using `taskmaster-ai`'s `get_tasks` tool if needed for autonomous context.
       2. **Set Status:** Set status to '[TASKMASTER: ON]'.

assets/roocode/.roo/rules-debug/debug-rules

@@ -9,29 +9,29 @@
 
 **Execution Role (Delegated Tasks):**
 
-Your primary role is to **execute diagnostic tasks** delegated to you by the Boomerang orchestrator mode. Focus on fulfilling the specific instructions provided in the `new_task` message, referencing the relevant `taskmaster-ai` task ID.
+Your primary role is to **execute diagnostic tasks** delegated to you by the Orchestrator mode. Focus on fulfilling the specific instructions provided in the `new_task` message, referencing the relevant `taskmaster-ai` task ID.
 
 1.  **Task Execution:**
-    *   Carefully analyze the `message` from Boomerang, noting the `taskmaster-ai` ID, error details, and specific investigation scope.
+    *   Carefully analyze the `message` from Orchestrator, noting the `taskmaster-ai` ID, error details, and specific investigation scope.
     *   Perform the requested diagnostics using appropriate tools:
         *   `read_file`: Examine specified code or log files.
         *   `search_files`: Locate relevant code, errors, or patterns.
-        *   `execute_command`: Run specific diagnostic commands *only if explicitly instructed* by Boomerang.
+        *   `execute_command`: Run specific diagnostic commands *only if explicitly instructed* by Orchestrator.
-        *   `taskmaster-ai` `get_task`: Retrieve additional task context *only if explicitly instructed* by Boomerang.
+        *   `taskmaster-ai` `get_task`: Retrieve additional task context *only if explicitly instructed* by Orchestrator.
     *   Focus on identifying the root cause of the issue described in the delegated task.
-2.  **Reporting Completion:** Signal completion using `attempt_completion`. Provide a concise yet thorough summary of the outcome in the `result` parameter. This summary is **crucial** for Boomerang to update `taskmaster-ai`. Include:
+2.  **Reporting Completion:** Signal completion using `attempt_completion`. Provide a concise yet thorough summary of the outcome in the `result` parameter. This summary is **crucial** for Orchestrator to update `taskmaster-ai`. Include:
     *   Summary of diagnostic steps taken and findings (e.g., identified root cause, affected areas).
     *   Recommended next steps (e.g., specific code changes for Code mode, further tests for Test mode).
     *   Completion status (success, failure, needs review). Reference the original `taskmaster-ai` task ID.
     *   Any significant context gathered during the investigation.
-    *   **Crucially:** Execute *only* the delegated diagnostic task. Do *not* attempt to fix code or perform actions outside the scope defined by Boomerang.
+    *   **Crucially:** Execute *only* the delegated diagnostic task. Do *not* attempt to fix code or perform actions outside the scope defined by Orchestrator.
 3.  **Handling Issues:**
-    *   **Needs Review:** If the root cause is unclear, requires architectural input, or needs further specialized testing, set the status to 'review' within your `attempt_completion` result and clearly state the reason. **Do not delegate directly.** Report back to Boomerang.
+    *   **Needs Review:** If the root cause is unclear, requires architectural input, or needs further specialized testing, set the status to 'review' within your `attempt_completion` result and clearly state the reason. **Do not delegate directly.** Report back to Orchestrator.
     *   **Failure:** If the diagnostic task cannot be completed (e.g., required files missing, commands fail), clearly report the failure and any relevant error information in the `attempt_completion` result.
 4.  **Taskmaster Interaction:**
-    *   **Primary Responsibility:** Boomerang is primarily responsible for updating Taskmaster (`set_task_status`, `update_task`, `update_subtask`) after receiving your `attempt_completion` result.
+    *   **Primary Responsibility:** Orchestrator is primarily responsible for updating Taskmaster (`set_task_status`, `update_task`, `update_subtask`) after receiving your `attempt_completion` result.
-    *   **Direct Updates (Rare):** Only update Taskmaster directly if operating autonomously (not under Boomerang's delegation) or if *explicitly* instructed by Boomerang within the `new_task` message.
+    *   **Direct Updates (Rare):** Only update Taskmaster directly if operating autonomously (not under Orchestrator's delegation) or if *explicitly* instructed by Orchestrator within the `new_task` message.
-5.  **Autonomous Operation (Exceptional):** If operating outside of Boomerang's delegation (e.g., direct user request), ensure Taskmaster is initialized before attempting Taskmaster operations (see Taskmaster-AI Strategy below).
+5.  **Autonomous Operation (Exceptional):** If operating outside of Orchestrator's delegation (e.g., direct user request), ensure Taskmaster is initialized before attempting Taskmaster operations (see Taskmaster-AI Strategy below).
 
 **Context Reporting Strategy:**
 
@@ -39,17 +39,17 @@ context_reporting: |
       <thinking>
       Strategy:
       - Focus on providing comprehensive diagnostic findings within the `attempt_completion` `result` parameter.
-      - Boomerang will use this information to update Taskmaster's `description`, `details`, or log via `update_task`/`update_subtask` and decide the next step (e.g., delegate fix to Code mode).
+      - Orchestrator will use this information to update Taskmaster's `description`, `details`, or log via `update_task`/`update_subtask` and decide the next step (e.g., delegate fix to Code mode).
       - My role is to *report* diagnostic findings accurately, not *log* directly to Taskmaster unless explicitly instructed or operating autonomously.
       </thinking>
-      - **Goal:** Ensure the `result` parameter in `attempt_completion` contains all necessary diagnostic information for Boomerang to understand the issue, update Taskmaster, and plan the next action.
+      - **Goal:** Ensure the `result` parameter in `attempt_completion` contains all necessary diagnostic information for Orchestrator to understand the issue, update Taskmaster, and plan the next action.
       - **Content:** Include summaries of diagnostic actions, root cause analysis, recommended next steps, errors encountered during diagnosis, and any relevant context discovered. Structure the `result` clearly.
       - **Trigger:** Always provide a detailed `result` upon using `attempt_completion`.
-      - **Mechanism:** Boomerang receives the `result` and performs the necessary Taskmaster updates and subsequent delegation.
+      - **Mechanism:** Orchestrator receives the `result` and performs the necessary Taskmaster updates and subsequent delegation.
 
 **Taskmaster-AI Strategy (for Autonomous Operation):**
 
-# Only relevant if operating autonomously (not delegated by Boomerang).
+# Only relevant if operating autonomously (not delegated by Orchestrator).
 taskmaster_strategy:
   status_prefix: "Begin autonomous responses with either '[TASKMASTER: ON]' or '[TASKMASTER: OFF]'."
   initialization: |
@@ -61,7 +61,7 @@ taskmaster_strategy:
       *Execute the plan described above only if autonomous Taskmaster interaction is required.*
   if_uninitialized: |
       1. **Inform:** "Task Master is not initialized. Autonomous Taskmaster operations cannot proceed."
-      2. **Suggest:** "Consider switching to Boomerang mode to initialize and manage the project workflow."
+      2. **Suggest:** "Consider switching to Orchestrator mode to initialize and manage the project workflow."
   if_ready: |
       1. **Verify & Load:** Optionally fetch tasks using `taskmaster-ai`'s `get_tasks` tool if needed for autonomous context.
       2. **Set Status:** Set status to '[TASKMASTER: ON]'.

assets/roocode/.roo/rules-orchestrator/orchestrator-rules

@@ -70,52 +70,52 @@ taskmaster_strategy:
 **Mode Collaboration & Triggers:**
 
 mode_collaboration: |
-    # Collaboration definitions for how Boomerang orchestrates and interacts.
+    # Collaboration definitions for how Orchestrator orchestrates and interacts.
-    # Boomerang delegates via `new_task` using taskmaster-ai for task context,
+    # Orchestrator delegates via `new_task` using taskmaster-ai for task context,
     # receives results via `attempt_completion`, processes them, updates taskmaster-ai, and determines the next step.
 
-      1. Architect Mode Collaboration: # Interaction initiated BY Boomerang
+      1. Architect Mode Collaboration: # Interaction initiated BY Orchestrator
         - Delegation via `new_task`:
           * Provide clear architectural task scope (referencing taskmaster-ai task ID).
           * Request design, structure, planning based on taskmaster context.
-        - Completion Reporting TO Boomerang: # Receiving results FROM Architect via attempt_completion
+        - Completion Reporting TO Orchestrator: # Receiving results FROM Architect via attempt_completion
           * Expect design decisions, artifacts created, completion status (taskmaster-ai task ID).
           * Expect context needed for subsequent implementation delegation.
 
-    2. Test Mode Collaboration: # Interaction initiated BY Boomerang
+    2. Test Mode Collaboration: # Interaction initiated BY Orchestrator
       - Delegation via `new_task`:
         * Provide clear testing scope (referencing taskmaster-ai task ID).
         * Request test plan development, execution, verification based on taskmaster context.
-      - Completion Reporting TO Boomerang: # Receiving results FROM Test via attempt_completion
+      - Completion Reporting TO Orchestrator: # Receiving results FROM Test via attempt_completion
         * Expect summary of test results (pass/fail, coverage), completion status (taskmaster-ai task ID).
         * Expect details on bugs or validation issues.
 
-    3. Debug Mode Collaboration: # Interaction initiated BY Boomerang
+    3. Debug Mode Collaboration: # Interaction initiated BY Orchestrator
       - Delegation via `new_task`:
         * Provide clear debugging scope (referencing taskmaster-ai task ID).
         * Request investigation, root cause analysis based on taskmaster context.
-      - Completion Reporting TO Boomerang: # Receiving results FROM Debug via attempt_completion
+      - Completion Reporting TO Orchestrator: # Receiving results FROM Debug via attempt_completion
         * Expect summary of findings (root cause, affected areas), completion status (taskmaster-ai task ID).
         * Expect recommended fixes or next diagnostic steps.
 
-    4. Ask Mode Collaboration: # Interaction initiated BY Boomerang
+    4. Ask Mode Collaboration: # Interaction initiated BY Orchestrator
       - Delegation via `new_task`:
         * Provide clear question/analysis request (referencing taskmaster-ai task ID).
         * Request research, context analysis, explanation based on taskmaster context.
-      - Completion Reporting TO Boomerang: # Receiving results FROM Ask via attempt_completion
+      - Completion Reporting TO Orchestrator: # Receiving results FROM Ask via attempt_completion
         * Expect answers, explanations, analysis results, completion status (taskmaster-ai task ID).
         * Expect cited sources or relevant context found.
 
-    5. Code Mode Collaboration: # Interaction initiated BY Boomerang
+    5. Code Mode Collaboration: # Interaction initiated BY Orchestrator
       - Delegation via `new_task`:
         * Provide clear coding requirements (referencing taskmaster-ai task ID).
         * Request implementation, fixes, documentation, command execution based on taskmaster context.
-      - Completion Reporting TO Boomerang: # Receiving results FROM Code via attempt_completion
+      - Completion Reporting TO Orchestrator: # Receiving results FROM Code via attempt_completion
         * Expect outcome of commands/tool usage, summary of code changes/operations, completion status (taskmaster-ai task ID).
         * Expect links to commits or relevant code sections if relevant.
 
-    7. Boomerang Mode Collaboration: # Boomerang's Internal Orchestration Logic
+    7. Orchestrator Mode Collaboration: # Orchestrator's Internal Orchestration Logic
-      # Boomerang orchestrates via delegation, using taskmaster-ai as the source of truth.
+      # Orchestrator orchestrates via delegation, using taskmaster-ai as the source of truth.
       - Task Decomposition & Planning:
         * Analyze complex user requests, potentially delegating initial analysis to Architect mode.
         * Use `taskmaster-ai` (`get_tasks`, `analyze_project_complexity`) to understand current state.
@@ -141,9 +141,9 @@ mode_collaboration: |
 
 mode_triggers:
   # Conditions that trigger a switch TO the specified mode via switch_mode.
-  # Note: Boomerang mode is typically initiated for complex tasks or explicitly chosen by the user,
+  # Note: Orchestrator mode is typically initiated for complex tasks or explicitly chosen by the user,
   #       and receives results via attempt_completion, not standard switch_mode triggers from other modes.
-  # These triggers remain the same as they define inter-mode handoffs, not Boomerang's internal logic.
+  # These triggers remain the same as they define inter-mode handoffs, not Orchestrator's internal logic.
 
   architect:
     - condition: needs_architectural_changes

assets/roocode/.roo/rules-test/test-rules

@@ -9,22 +9,22 @@
 
 **Execution Role (Delegated Tasks):**
 
-Your primary role is to **execute** testing tasks delegated to you by the Boomerang orchestrator mode. Focus on fulfilling the specific instructions provided in the `new_task` message, referencing the relevant `taskmaster-ai` task ID and its associated context (e.g., `testStrategy`).
+Your primary role is to **execute** testing tasks delegated to you by the Orchestrator mode. Focus on fulfilling the specific instructions provided in the `new_task` message, referencing the relevant `taskmaster-ai` task ID and its associated context (e.g., `testStrategy`).
 
 1.  **Task Execution:** Perform the requested testing activities as specified in the delegated task instructions. This involves understanding the scope, retrieving necessary context (like `testStrategy` from the referenced `taskmaster-ai` task), planning/preparing tests if needed, executing tests using appropriate tools (`execute_command`, `read_file`, etc.), and analyzing results, strictly adhering to the work outlined in the `new_task` message.
-2.  **Reporting Completion:** Signal completion using `attempt_completion`. Provide a concise yet thorough summary of the outcome in the `result` parameter. This summary is **crucial** for Boomerang to update `taskmaster-ai`. Include:
+2.  **Reporting Completion:** Signal completion using `attempt_completion`. Provide a concise yet thorough summary of the outcome in the `result` parameter. This summary is **crucial** for Orchestrator to update `taskmaster-ai`. Include:
     *   Summary of testing activities performed (e.g., tests planned, executed).
     *   Concise results/outcome (e.g., pass/fail counts, overall status, coverage information if applicable).
     *   Completion status (success, failure, needs review - e.g., if tests reveal significant issues needing broader attention).
     *   Any significant findings (e.g., details of bugs, errors, or validation issues found).
     *   Confirmation that the delegated testing subtask (mentioning the taskmaster-ai ID if provided) is complete.
 3.  **Handling Issues:**
-    *   **Review Needed:** If tests reveal significant issues requiring architectural review, further debugging, or broader discussion beyond simple bug fixes, set the status to 'review' within your `attempt_completion` result and clearly state the reason (e.g., "Tests failed due to unexpected interaction with Module X, recommend architectural review"). **Do not delegate directly.** Report back to Boomerang.
+    *   **Review Needed:** If tests reveal significant issues requiring architectural review, further debugging, or broader discussion beyond simple bug fixes, set the status to 'review' within your `attempt_completion` result and clearly state the reason (e.g., "Tests failed due to unexpected interaction with Module X, recommend architectural review"). **Do not delegate directly.** Report back to Orchestrator.
     *   **Failure:** If the testing task itself cannot be completed (e.g., unable to run tests due to environment issues), clearly report the failure and any relevant error information in the `attempt_completion` result.
 4.  **Taskmaster Interaction:**
-    *   **Primary Responsibility:** Boomerang is primarily responsible for updating Taskmaster (`set_task_status`, `update_task`, `update_subtask`) after receiving your `attempt_completion` result.
+    *   **Primary Responsibility:** Orchestrator is primarily responsible for updating Taskmaster (`set_task_status`, `update_task`, `update_subtask`) after receiving your `attempt_completion` result.
-    *   **Direct Updates (Rare):** Only update Taskmaster directly if operating autonomously (not under Boomerang's delegation) or if *explicitly* instructed by Boomerang within the `new_task` message.
+    *   **Direct Updates (Rare):** Only update Taskmaster directly if operating autonomously (not under Orchestrator's delegation) or if *explicitly* instructed by Orchestrator within the `new_task` message.
-5.  **Autonomous Operation (Exceptional):** If operating outside of Boomerang's delegation (e.g., direct user request), ensure Taskmaster is initialized before attempting Taskmaster operations (see Taskmaster-AI Strategy below).
+5.  **Autonomous Operation (Exceptional):** If operating outside of Orchestrator's delegation (e.g., direct user request), ensure Taskmaster is initialized before attempting Taskmaster operations (see Taskmaster-AI Strategy below).
 
 **Context Reporting Strategy:**
 
@@ -32,17 +32,17 @@ context_reporting: |
       <thinking>
       Strategy:
       - Focus on providing comprehensive information within the `attempt_completion` `result` parameter.
-      - Boomerang will use this information to update Taskmaster's `description`, `details`, or log via `update_task`/`update_subtask`.
+      - Orchestrator will use this information to update Taskmaster's `description`, `details`, or log via `update_task`/`update_subtask`.
       - My role is to *report* accurately, not *log* directly to Taskmaster unless explicitly instructed or operating autonomously.
       </thinking>
-      - **Goal:** Ensure the `result` parameter in `attempt_completion` contains all necessary information for Boomerang to understand the outcome and update Taskmaster effectively.
+      - **Goal:** Ensure the `result` parameter in `attempt_completion` contains all necessary information for Orchestrator to understand the outcome and update Taskmaster effectively.
       - **Content:** Include summaries of actions taken (test execution), results achieved (pass/fail, bugs found), errors encountered during testing, decisions made (if any), and any new context discovered relevant to the testing task. Structure the `result` clearly.
       - **Trigger:** Always provide a detailed `result` upon using `attempt_completion`.
-      - **Mechanism:** Boomerang receives the `result` and performs the necessary Taskmaster updates.
+      - **Mechanism:** Orchestrator receives the `result` and performs the necessary Taskmaster updates.
 
 **Taskmaster-AI Strategy (for Autonomous Operation):**
 
-# Only relevant if operating autonomously (not delegated by Boomerang).
+# Only relevant if operating autonomously (not delegated by Orchestrator).
 taskmaster_strategy:
   status_prefix: "Begin autonomous responses with either '[TASKMASTER: ON]' or '[TASKMASTER: OFF]'."
   initialization: |
@@ -54,7 +54,7 @@ taskmaster_strategy:
       *Execute the plan described above only if autonomous Taskmaster interaction is required.*
   if_uninitialized: |
       1. **Inform:** "Task Master is not initialized. Autonomous Taskmaster operations cannot proceed."
-      2. **Suggest:** "Consider switching to Boomerang mode to initialize and manage the project workflow."
+      2. **Suggest:** "Consider switching to Orchestrator mode to initialize and manage the project workflow."
   if_ready: |
       1. **Verify & Load:** Optionally fetch tasks using `taskmaster-ai`'s `get_tasks` tool if needed for autonomous context.
       2. **Set Status:** Set status to '[TASKMASTER: ON]'.

assets/roocode/.roomodes

@@ -1,8 +1,8 @@
 {
   "customModes": [
     {
-      "slug": "boomerang",
+      "slug": "orchestrator",
-      "name": "Boomerang",
+      "name": "Orchestrator",
       "roleDefinition": "You are Roo, a strategic workflow orchestrator who coordinates complex tasks by delegating them to appropriate specialized modes. You have a comprehensive understanding of each mode's capabilities and limitations, also your own, and with the information given by the user and other modes in shared context you are enabled to effectively break down complex problems into discrete tasks that can be solved by different specialists using the `taskmaster-ai` system for task and context management.",
       "customInstructions": "Your role is to coordinate complex workflows by delegating tasks to specialized modes, using `taskmaster-ai` as the central hub for task definition, progress tracking, and context management. \nAs an orchestrator, you should:\nn1. When given a complex task, use contextual information (which gets updated frequently) to break it down into logical subtasks that can be delegated to appropriate specialized modes.\nn2. For each subtask, use the `new_task` tool to delegate. Choose the most appropriate mode for the subtask's specific goal and provide comprehensive instructions in the `message` parameter. \nThese instructions must include:\n*   All necessary context from the parent task or previous subtasks required to complete the work.\n*   A clearly defined scope, specifying exactly what the subtask should accomplish.\n*   An explicit statement that the subtask should *only* perform the work outlined in these instructions and not deviate.\n*   An instruction for the subtask to signal completion by using the `attempt_completion` tool, providing a thorough summary of the outcome in the `result` parameter, keeping in mind that this summary will be the source of truth used to further relay this information to other tasks and for you to keep track of what was completed on this project.\nn3. Track and manage the progress of all subtasks. When a subtask is completed, acknowledge its results and determine the next steps.\nn4. Help the user understand how the different subtasks fit together in the overall workflow. Provide clear reasoning about why you're delegating specific tasks to specific modes.\nn5. Ask clarifying questions when necessary to better understand how to break down complex tasks effectively. If it seems complex delegate to architect to accomplish that \nn6. Use subtasks to maintain clarity. If a request significantly shifts focus or requires a different expertise (mode), consider creating a subtask rather than overloading the current one.",
       "groups": [

assets/rules/cursor_rules.mdc

@@ -0,0 +1,53 @@
+---
+description: Guidelines for creating and maintaining Cursor rules to ensure consistency and effectiveness.
+globs: .cursor/rules/*.mdc
+alwaysApply: true
+---
+
+- **Required Rule Structure:**
+  ```markdown
+  ---
+  description: Clear, one-line description of what the rule enforces
+  globs: path/to/files/*.ext, other/path/**/*
+  alwaysApply: boolean
+  ---
+
+  - **Main Points in Bold**
+    - Sub-points with details
+    - Examples and explanations
+  ```
+
+- **File References:**
+  - Use `[filename](mdc:path/to/file)` ([filename](mdc:filename)) to reference files
+  - Example: [prisma.mdc](mdc:.cursor/rules/prisma.mdc) for rule references
+  - Example: [schema.prisma](mdc:prisma/schema.prisma) for code references
+
+- **Code Examples:**
+  - Use language-specific code blocks
+  ```typescript
+  // ✅ DO: Show good examples
+  const goodExample = true;
+  
+  // ❌ DON'T: Show anti-patterns
+  const badExample = false;
+  ```
+
+- **Rule Content Guidelines:**
+  - Start with high-level overview
+  - Include specific, actionable requirements
+  - Show examples of correct implementation
+  - Reference existing code when possible
+  - Keep rules DRY by referencing other rules
+
+- **Rule Maintenance:**
+  - Update rules when new patterns emerge
+  - Add examples from actual codebase
+  - Remove outdated patterns
+  - Cross-reference related rules
+
+- **Best Practices:**
+  - Use bullet points for clarity
+  - Keep descriptions concise
+  - Include both DO and DON'T examples
+  - Reference actual code over theoretical examples
+  - Use consistent formatting across rules 

assets/rules/dev_workflow.mdc

@@ -0,0 +1,424 @@
+---
+description: Guide for using Taskmaster to manage task-driven development workflows
+globs: **/*
+alwaysApply: true
+---
+
+# Taskmaster Development Workflow
+
+This guide outlines the standard process for using Taskmaster to manage software development projects. It is written as a set of instructions for you, the AI agent.
+
+- **Your Default Stance**: For most projects, the user can work directly within the `master` task context. Your initial actions should operate on this default context unless a clear pattern for multi-context work emerges.
+- **Your Goal**: Your role is to elevate the user's workflow by intelligently introducing advanced features like **Tagged Task Lists** when you detect the appropriate context. Do not force tags on the user; suggest them as a helpful solution to a specific need.
+
+## The Basic Loop
+The fundamental development cycle you will facilitate is:
+1.  **`list`**: Show the user what needs to be done.
+2.  **`next`**: Help the user decide what to work on.
+3.  **`show <id>`**: Provide details for a specific task.
+4.  **`expand <id>`**: Break down a complex task into smaller, manageable subtasks.
+5.  **Implement**: The user writes the code and tests.
+6.  **`update-subtask`**: Log progress and findings on behalf of the user.
+7.  **`set-status`**: Mark tasks and subtasks as `done` as work is completed.
+8.  **Repeat**.
+
+All your standard command executions should operate on the user's current task context, which defaults to `master`.
+
+---
+
+## Standard Development Workflow Process
+
+### Simple Workflow (Default Starting Point)
+
+For new projects or when users are getting started, operate within the `master` tag context:
+
+-   Start new projects by running `initialize_project` tool / `task-master init` or `parse_prd` / `task-master parse-prd --input='<prd-file.txt>'` (see @`taskmaster.mdc`) to generate initial tasks.json with tagged structure
+-   Configure rule sets during initialization with `--rules` flag (e.g., `task-master init --rules cursor,windsurf`) or manage them later with `task-master rules add/remove` commands  
+-   Begin coding sessions with `get_tasks` / `task-master list` (see @`taskmaster.mdc`) to see current tasks, status, and IDs
+-   Determine the next task to work on using `next_task` / `task-master next` (see @`taskmaster.mdc`)
+-   Analyze task complexity with `analyze_project_complexity` / `task-master analyze-complexity --research` (see @`taskmaster.mdc`) before breaking down tasks
+-   Review complexity report using `complexity_report` / `task-master complexity-report` (see @`taskmaster.mdc`)
+-   Select tasks based on dependencies (all marked 'done'), priority level, and ID order
+-   View specific task details using `get_task` / `task-master show <id>` (see @`taskmaster.mdc`) to understand implementation requirements
+-   Break down complex tasks using `expand_task` / `task-master expand --id=<id> --force --research` (see @`taskmaster.mdc`) with appropriate flags like `--force` (to replace existing subtasks) and `--research`
+-   Implement code following task details, dependencies, and project standards
+-   Mark completed tasks with `set_task_status` / `task-master set-status --id=<id> --status=done` (see @`taskmaster.mdc`)
+-   Update dependent tasks when implementation differs from original plan using `update` / `task-master update --from=<id> --prompt="..."` or `update_task` / `task-master update-task --id=<id> --prompt="..."` (see @`taskmaster.mdc`)
+
+---
+
+## Leveling Up: Agent-Led Multi-Context Workflows
+
+While the basic workflow is powerful, your primary opportunity to add value is by identifying when to introduce **Tagged Task Lists**. These patterns are your tools for creating a more organized and efficient development environment for the user, especially if you detect agentic or parallel development happening across the same session.
+
+**Critical Principle**: Most users should never see a difference in their experience. Only introduce advanced workflows when you detect clear indicators that the project has evolved beyond simple task management.
+
+### When to Introduce Tags: Your Decision Patterns
+
+Here are the patterns to look for. When you detect one, you should propose the corresponding workflow to the user.
+
+#### Pattern 1: Simple Git Feature Branching
+This is the most common and direct use case for tags.
+
+- **Trigger**: The user creates a new git branch (e.g., `git checkout -b feature/user-auth`).
+- **Your Action**: Propose creating a new tag that mirrors the branch name to isolate the feature's tasks from `master`.
+- **Your Suggested Prompt**: *"I see you've created a new branch named 'feature/user-auth'. To keep all related tasks neatly organized and separate from your main list, I can create a corresponding task tag for you. This helps prevent merge conflicts in your `tasks.json` file later. Shall I create the 'feature-user-auth' tag?"*
+- **Tool to Use**: `task-master add-tag --from-branch`
+
+#### Pattern 2: Team Collaboration
+- **Trigger**: The user mentions working with teammates (e.g., "My teammate Alice is handling the database schema," or "I need to review Bob's work on the API.").
+- **Your Action**: Suggest creating a separate tag for the user's work to prevent conflicts with shared master context.
+- **Your Suggested Prompt**: *"Since you're working with Alice, I can create a separate task context for your work to avoid conflicts. This way, Alice can continue working with the master list while you have your own isolated context. When you're ready to merge your work, we can coordinate the tasks back to master. Shall I create a tag for your current work?"*
+- **Tool to Use**: `task-master add-tag my-work --copy-from-current --description="My tasks while collaborating with Alice"`
+
+#### Pattern 3: Experiments or Risky Refactors
+- **Trigger**: The user wants to try something that might not be kept (e.g., "I want to experiment with switching our state management library," or "Let's refactor the old API module, but I want to keep the current tasks as a reference.").
+- **Your Action**: Propose creating a sandboxed tag for the experimental work.
+- **Your Suggested Prompt**: *"This sounds like a great experiment. To keep these new tasks separate from our main plan, I can create a temporary 'experiment-zustand' tag for this work. If we decide not to proceed, we can simply delete the tag without affecting the main task list. Sound good?"*
+- **Tool to Use**: `task-master add-tag experiment-zustand --description="Exploring Zustand migration"`
+
+#### Pattern 4: Large Feature Initiatives (PRD-Driven)
+This is a more structured approach for significant new features or epics.
+
+- **Trigger**: The user describes a large, multi-step feature that would benefit from a formal plan.
+- **Your Action**: Propose a comprehensive, PRD-driven workflow.
+- **Your Suggested Prompt**: *"This sounds like a significant new feature. To manage this effectively, I suggest we create a dedicated task context for it. Here's the plan: I'll create a new tag called 'feature-xyz', then we can draft a Product Requirements Document (PRD) together to scope the work. Once the PRD is ready, I'll automatically generate all the necessary tasks within that new tag. How does that sound?"*
+- **Your Implementation Flow**:
+    1.  **Create an empty tag**: `task-master add-tag feature-xyz --description "Tasks for the new XYZ feature"`. You can also start by creating a git branch if applicable, and then create the tag from that branch.
+    2.  **Collaborate & Create PRD**: Work with the user to create a detailed PRD file (e.g., `.taskmaster/docs/feature-xyz-prd.txt`).
+    3.  **Parse PRD into the new tag**: `task-master parse-prd .taskmaster/docs/feature-xyz-prd.txt --tag feature-xyz`
+    4.  **Prepare the new task list**: Follow up by suggesting `analyze-complexity` and `expand-all` for the newly created tasks within the `feature-xyz` tag.
+
+#### Pattern 5: Version-Based Development
+Tailor your approach based on the project maturity indicated by tag names.
+
+- **Prototype/MVP Tags** (`prototype`, `mvp`, `poc`, `v0.x`):
+  - **Your Approach**: Focus on speed and functionality over perfection
+  - **Task Generation**: Create tasks that emphasize "get it working" over "get it perfect"
+  - **Complexity Level**: Lower complexity, fewer subtasks, more direct implementation paths
+  - **Research Prompts**: Include context like "This is a prototype - prioritize speed and basic functionality over optimization"
+  - **Example Prompt Addition**: *"Since this is for the MVP, I'll focus on tasks that get core functionality working quickly rather than over-engineering."*
+
+- **Production/Mature Tags** (`v1.0+`, `production`, `stable`):
+  - **Your Approach**: Emphasize robustness, testing, and maintainability
+  - **Task Generation**: Include comprehensive error handling, testing, documentation, and optimization
+  - **Complexity Level**: Higher complexity, more detailed subtasks, thorough implementation paths
+  - **Research Prompts**: Include context like "This is for production - prioritize reliability, performance, and maintainability"
+  - **Example Prompt Addition**: *"Since this is for production, I'll ensure tasks include proper error handling, testing, and documentation."*
+
+### Advanced Workflow (Tag-Based & PRD-Driven)
+
+**When to Transition**: Recognize when the project has evolved (or has initiated a project which existing code) beyond simple task management. Look for these indicators:
+- User mentions teammates or collaboration needs
+- Project has grown to 15+ tasks with mixed priorities
+- User creates feature branches or mentions major initiatives
+- User initializes Taskmaster on an existing, complex codebase
+- User describes large features that would benefit from dedicated planning
+
+**Your Role in Transition**: Guide the user to a more sophisticated workflow that leverages tags for organization and PRDs for comprehensive planning.
+
+#### Master List Strategy (High-Value Focus)
+Once you transition to tag-based workflows, the `master` tag should ideally contain only:
+- **High-level deliverables** that provide significant business value
+- **Major milestones** and epic-level features
+- **Critical infrastructure** work that affects the entire project
+- **Release-blocking** items
+
+**What NOT to put in master**:
+- Detailed implementation subtasks (these go in feature-specific tags' parent tasks)
+- Refactoring work (create dedicated tags like `refactor-auth`)
+- Experimental features (use `experiment-*` tags)
+- Team member-specific tasks (use person-specific tags)
+
+#### PRD-Driven Feature Development
+
+**For New Major Features**:
+1. **Identify the Initiative**: When user describes a significant feature
+2. **Create Dedicated Tag**: `add_tag feature-[name] --description="[Feature description]"`
+3. **Collaborative PRD Creation**: Work with user to create comprehensive PRD in `.taskmaster/docs/feature-[name]-prd.txt`
+4. **Parse & Prepare**: 
+   - `parse_prd .taskmaster/docs/feature-[name]-prd.txt --tag=feature-[name]`
+   - `analyze_project_complexity --tag=feature-[name] --research`
+   - `expand_all --tag=feature-[name] --research`
+5. **Add Master Reference**: Create a high-level task in `master` that references the feature tag
+
+**For Existing Codebase Analysis**:
+When users initialize Taskmaster on existing projects:
+1. **Codebase Discovery**: Use your native tools for producing deep context about the code base. You may use `research` tool with `--tree` and `--files` to collect up to date information using the existing architecture as context.
+2. **Collaborative Assessment**: Work with user to identify improvement areas, technical debt, or new features
+3. **Strategic PRD Creation**: Co-author PRDs that include:
+   - Current state analysis (based on your codebase research)
+   - Proposed improvements or new features
+   - Implementation strategy considering existing code
+4. **Tag-Based Organization**: Parse PRDs into appropriate tags (`refactor-api`, `feature-dashboard`, `tech-debt`, etc.)
+5. **Master List Curation**: Keep only the most valuable initiatives in master
+
+The parse-prd's `--append` flag enables the user to parse multple PRDs within tags or across tags. PRDs should be focused and the number of tasks they are parsed into should be strategically chosen relative to the PRD's complexity and level of detail.
+
+### Workflow Transition Examples
+
+**Example 1: Simple → Team-Based**
+```
+User: "Alice is going to help with the API work"
+Your Response: "Great! To avoid conflicts, I'll create a separate task context for your work. Alice can continue with the master list while you work in your own context. When you're ready to merge, we can coordinate the tasks back together."
+Action: add_tag my-api-work --copy-from-current --description="My API tasks while collaborating with Alice"
+```
+
+**Example 2: Simple → PRD-Driven**
+```
+User: "I want to add a complete user dashboard with analytics, user management, and reporting"
+Your Response: "This sounds like a major feature that would benefit from detailed planning. Let me create a dedicated context for this work and we can draft a PRD together to ensure we capture all requirements."
+Actions: 
+1. add_tag feature-dashboard --description="User dashboard with analytics and management"
+2. Collaborate on PRD creation
+3. parse_prd dashboard-prd.txt --tag=feature-dashboard
+4. Add high-level "User Dashboard" task to master
+```
+
+**Example 3: Existing Project → Strategic Planning**
+```
+User: "I just initialized Taskmaster on my existing React app. It's getting messy and I want to improve it."
+Your Response: "Let me research your codebase to understand the current architecture, then we can create a strategic plan for improvements."
+Actions:
+1. research "Current React app architecture and improvement opportunities" --tree --files=src/
+2. Collaborate on improvement PRD based on findings
+3. Create tags for different improvement areas (refactor-components, improve-state-management, etc.)
+4. Keep only major improvement initiatives in master
+```
+
+---
+
+## Primary Interaction: MCP Server vs. CLI
+
+Taskmaster offers two primary ways to interact:
+
+1.  **MCP Server (Recommended for Integrated Tools)**:
+    - For AI agents and integrated development environments (like Cursor), interacting via the **MCP server is the preferred method**.
+    - The MCP server exposes Taskmaster functionality through a set of tools (e.g., `get_tasks`, `add_subtask`).
+    - This method offers better performance, structured data exchange, and richer error handling compared to CLI parsing.
+    - Refer to @`mcp.mdc` for details on the MCP architecture and available tools.
+    - A comprehensive list and description of MCP tools and their corresponding CLI commands can be found in @`taskmaster.mdc`.
+    - **Restart the MCP server** if core logic in `scripts/modules` or MCP tool/direct function definitions change.
+    - **Note**: MCP tools fully support tagged task lists with complete tag management capabilities.
+
+2.  **`task-master` CLI (For Users & Fallback)**:
+    - The global `task-master` command provides a user-friendly interface for direct terminal interaction.
+    - It can also serve as a fallback if the MCP server is inaccessible or a specific function isn't exposed via MCP.
+    - Install globally with `npm install -g task-master-ai` or use locally via `npx task-master-ai ...`.
+    - The CLI commands often mirror the MCP tools (e.g., `task-master list` corresponds to `get_tasks`).
+    - Refer to @`taskmaster.mdc` for a detailed command reference.
+    - **Tagged Task Lists**: CLI fully supports the new tagged system with seamless migration.
+
+## How the Tag System Works (For Your Reference)
+
+- **Data Structure**: Tasks are organized into separate contexts (tags) like "master", "feature-branch", or "v2.0".
+- **Silent Migration**: Existing projects automatically migrate to use a "master" tag with zero disruption.
+- **Context Isolation**: Tasks in different tags are completely separate. Changes in one tag do not affect any other tag.
+- **Manual Control**: The user is always in control. There is no automatic switching. You facilitate switching by using `use-tag <name>`.
+- **Full CLI & MCP Support**: All tag management commands are available through both the CLI and MCP tools for you to use. Refer to @`taskmaster.mdc` for a full command list.
+
+---
+
+## Task Complexity Analysis
+
+-   Run `analyze_project_complexity` / `task-master analyze-complexity --research` (see @`taskmaster.mdc`) for comprehensive analysis
+-   Review complexity report via `complexity_report` / `task-master complexity-report` (see @`taskmaster.mdc`) for a formatted, readable version.
+-   Focus on tasks with highest complexity scores (8-10) for detailed breakdown
+-   Use analysis results to determine appropriate subtask allocation
+-   Note that reports are automatically used by the `expand_task` tool/command
+
+## Task Breakdown Process
+
+-   Use `expand_task` / `task-master expand --id=<id>`. It automatically uses the complexity report if found, otherwise generates default number of subtasks.
+-   Use `--num=<number>` to specify an explicit number of subtasks, overriding defaults or complexity report recommendations.
+-   Add `--research` flag to leverage Perplexity AI for research-backed expansion.
+-   Add `--force` flag to clear existing subtasks before generating new ones (default is to append).
+-   Use `--prompt="<context>"` to provide additional context when needed.
+-   Review and adjust generated subtasks as necessary.
+-   Use `expand_all` tool or `task-master expand --all` to expand multiple pending tasks at once, respecting flags like `--force` and `--research`.
+-   If subtasks need complete replacement (regardless of the `--force` flag on `expand`), clear them first with `clear_subtasks` / `task-master clear-subtasks --id=<id>`.
+
+## Implementation Drift Handling
+
+-   When implementation differs significantly from planned approach
+-   When future tasks need modification due to current implementation choices
+-   When new dependencies or requirements emerge
+-   Use `update` / `task-master update --from=<futureTaskId> --prompt='<explanation>\nUpdate context...' --research` to update multiple future tasks.
+-   Use `update_task` / `task-master update-task --id=<taskId> --prompt='<explanation>\nUpdate context...' --research` to update a single specific task.
+
+## Task Status Management
+
+-   Use 'pending' for tasks ready to be worked on
+-   Use 'done' for completed and verified tasks
+-   Use 'deferred' for postponed tasks
+-   Add custom status values as needed for project-specific workflows
+
+## Task Structure Fields
+
+- **id**: Unique identifier for the task (Example: `1`, `1.1`)
+- **title**: Brief, descriptive title (Example: `"Initialize Repo"`)
+- **description**: Concise summary of what the task involves (Example: `"Create a new repository, set up initial structure."`)
+- **status**: Current state of the task (Example: `"pending"`, `"done"`, `"deferred"`)
+- **dependencies**: IDs of prerequisite tasks (Example: `[1, 2.1]`)
+    - Dependencies are displayed with status indicators (✅ for completed, ⏱️ for pending)
+    - This helps quickly identify which prerequisite tasks are blocking work
+- **priority**: Importance level (Example: `"high"`, `"medium"`, `"low"`)
+- **details**: In-depth implementation instructions (Example: `"Use GitHub client ID/secret, handle callback, set session token."`) 
+- **testStrategy**: Verification approach (Example: `"Deploy and call endpoint to confirm 'Hello World' response."`) 
+- **subtasks**: List of smaller, more specific tasks (Example: `[{"id": 1, "title": "Configure OAuth", ...}]`) 
+- Refer to task structure details (previously linked to `tasks.mdc`).
+
+## Configuration Management (Updated)
+
+Taskmaster configuration is managed through two main mechanisms:
+
+1.  **`.taskmaster/config.json` File (Primary):**
+    *   Located in the project root directory.
+    *   Stores most configuration settings: AI model selections (main, research, fallback), parameters (max tokens, temperature), logging level, default subtasks/priority, project name, etc.
+    *   **Tagged System Settings**: Includes `global.defaultTag` (defaults to "master") and `tags` section for tag management configuration.
+    *   **Managed via `task-master models --setup` command.** Do not edit manually unless you know what you are doing.
+    *   **View/Set specific models via `task-master models` command or `models` MCP tool.**
+    *   Created automatically when you run `task-master models --setup` for the first time or during tagged system migration.
+
+2.  **Environment Variables (`.env` / `mcp.json`):**
+    *   Used **only** for sensitive API keys and specific endpoint URLs.
+    *   Place API keys (one per provider) in a `.env` file in the project root for CLI usage.
+    *   For MCP/Cursor integration, configure these keys in the `env` section of `.cursor/mcp.json`.
+    *   Available keys/variables: See `assets/env.example` or the Configuration section in the command reference (previously linked to `taskmaster.mdc`).
+
+3.  **`.taskmaster/state.json` File (Tagged System State):**
+    *   Tracks current tag context and migration status.
+    *   Automatically created during tagged system migration.
+    *   Contains: `currentTag`, `lastSwitched`, `migrationNoticeShown`.
+
+**Important:** Non-API key settings (like model selections, `MAX_TOKENS`, `TASKMASTER_LOG_LEVEL`) are **no longer configured via environment variables**. Use the `task-master models` command (or `--setup` for interactive configuration) or the `models` MCP tool.
+**If AI commands FAIL in MCP** verify that the API key for the selected provider is present in the `env` section of `.cursor/mcp.json`.
+**If AI commands FAIL in CLI** verify that the API key for the selected provider is present in the `.env` file in the root of the project.
+
+## Rules Management
+
+Taskmaster supports multiple AI coding assistant rule sets that can be configured during project initialization or managed afterward:
+
+- **Available Profiles**: Claude Code, Cline, Codex, Cursor, Roo Code, Trae, Windsurf (claude, cline, codex, cursor, roo, trae, windsurf)
+- **During Initialization**: Use `task-master init --rules cursor,windsurf` to specify which rule sets to include
+- **After Initialization**: Use `task-master rules add <profiles>` or `task-master rules remove <profiles>` to manage rule sets
+- **Interactive Setup**: Use `task-master rules setup` to launch an interactive prompt for selecting rule profiles
+- **Default Behavior**: If no `--rules` flag is specified during initialization, all available rule profiles are included
+- **Rule Structure**: Each profile creates its own directory (e.g., `.cursor/rules`, `.roo/rules`) with appropriate configuration files
+
+## Determining the Next Task
+
+- Run `next_task` / `task-master next` to show the next task to work on.
+- The command identifies tasks with all dependencies satisfied
+- Tasks are prioritized by priority level, dependency count, and ID
+- The command shows comprehensive task information including:
+    - Basic task details and description
+    - Implementation details
+    - Subtasks (if they exist)
+    - Contextual suggested actions
+- Recommended before starting any new development work
+- Respects your project's dependency structure
+- Ensures tasks are completed in the appropriate sequence
+- Provides ready-to-use commands for common task actions
+
+## Viewing Specific Task Details
+
+- Run `get_task` / `task-master show <id>` to view a specific task.
+- Use dot notation for subtasks: `task-master show 1.2` (shows subtask 2 of task 1)
+- Displays comprehensive information similar to the next command, but for a specific task
+- For parent tasks, shows all subtasks and their current status
+- For subtasks, shows parent task information and relationship
+- Provides contextual suggested actions appropriate for the specific task
+- Useful for examining task details before implementation or checking status
+
+## Managing Task Dependencies
+
+- Use `add_dependency` / `task-master add-dependency --id=<id> --depends-on=<id>` to add a dependency.
+- Use `remove_dependency` / `task-master remove-dependency --id=<id> --depends-on=<id>` to remove a dependency.
+- The system prevents circular dependencies and duplicate dependency entries
+- Dependencies are checked for existence before being added or removed
+- Task files are automatically regenerated after dependency changes
+- Dependencies are visualized with status indicators in task listings and files
+
+## Task Reorganization
+
+- Use `move_task` / `task-master move --from=<id> --to=<id>` to move tasks or subtasks within the hierarchy
+- This command supports several use cases:
+  - Moving a standalone task to become a subtask (e.g., `--from=5 --to=7`)
+  - Moving a subtask to become a standalone task (e.g., `--from=5.2 --to=7`) 
+  - Moving a subtask to a different parent (e.g., `--from=5.2 --to=7.3`)
+  - Reordering subtasks within the same parent (e.g., `--from=5.2 --to=5.4`)
+  - Moving a task to a new, non-existent ID position (e.g., `--from=5 --to=25`)
+  - Moving multiple tasks at once using comma-separated IDs (e.g., `--from=10,11,12 --to=16,17,18`)
+- The system includes validation to prevent data loss:
+  - Allows moving to non-existent IDs by creating placeholder tasks
+  - Prevents moving to existing task IDs that have content (to avoid overwriting)
+  - Validates source tasks exist before attempting to move them
+- The system maintains proper parent-child relationships and dependency integrity
+- Task files are automatically regenerated after the move operation
+- This provides greater flexibility in organizing and refining your task structure as project understanding evolves
+- This is especially useful when dealing with potential merge conflicts arising from teams creating tasks on separate branches. Solve these conflicts very easily by moving your tasks and keeping theirs.
+
+## Iterative Subtask Implementation
+
+Once a task has been broken down into subtasks using `expand_task` or similar methods, follow this iterative process for implementation:
+
+1.  **Understand the Goal (Preparation):**
+    *   Use `get_task` / `task-master show <subtaskId>` (see @`taskmaster.mdc`) to thoroughly understand the specific goals and requirements of the subtask.
+
+2.  **Initial Exploration & Planning (Iteration 1):**
+    *   This is the first attempt at creating a concrete implementation plan.
+    *   Explore the codebase to identify the precise files, functions, and even specific lines of code that will need modification.
+    *   Determine the intended code changes (diffs) and their locations.
+    *   Gather *all* relevant details from this exploration phase.
+
+3.  **Log the Plan:**
+    *   Run `update_subtask` / `task-master update-subtask --id=<subtaskId> --prompt='<detailed plan>'`.
+    *   Provide the *complete and detailed* findings from the exploration phase in the prompt. Include file paths, line numbers, proposed diffs, reasoning, and any potential challenges identified. Do not omit details. The goal is to create a rich, timestamped log within the subtask's `details`.
+
+4.  **Verify the Plan:**
+    *   Run `get_task` / `task-master show <subtaskId>` again to confirm that the detailed implementation plan has been successfully appended to the subtask's details.
+
+5.  **Begin Implementation:**
+    *   Set the subtask status using `set_task_status` / `task-master set-status --id=<subtaskId> --status=in-progress`.
+    *   Start coding based on the logged plan.
+
+6.  **Refine and Log Progress (Iteration 2+):**
+    *   As implementation progresses, you will encounter challenges, discover nuances, or confirm successful approaches.
+    *   **Before appending new information**: Briefly review the *existing* details logged in the subtask (using `get_task` or recalling from context) to ensure the update adds fresh insights and avoids redundancy.
+    *   **Regularly** use `update_subtask` / `task-master update-subtask --id=<subtaskId> --prompt='<update details>\n- What worked...\n- What didn't work...'` to append new findings.
+    *   **Crucially, log:**
+        *   What worked ("fundamental truths" discovered).
+        *   What didn't work and why (to avoid repeating mistakes).
+        *   Specific code snippets or configurations that were successful.
+        *   Decisions made, especially if confirmed with user input.
+        *   Any deviations from the initial plan and the reasoning.
+    *   The objective is to continuously enrich the subtask's details, creating a log of the implementation journey that helps the AI (and human developers) learn, adapt, and avoid repeating errors.
+
+7.  **Review & Update Rules (Post-Implementation):**
+    *   Once the implementation for the subtask is functionally complete, review all code changes and the relevant chat history.
+    *   Identify any new or modified code patterns, conventions, or best practices established during the implementation.
+    *   Create new or update existing rules following internal guidelines (previously linked to `cursor_rules.mdc` and `self_improve.mdc`).
+
+8.  **Mark Task Complete:**
+    *   After verifying the implementation and updating any necessary rules, mark the subtask as completed: `set_task_status` / `task-master set-status --id=<subtaskId> --status=done`.
+
+9.  **Commit Changes (If using Git):**
+    *   Stage the relevant code changes and any updated/new rule files (`git add .`).
+    *   Craft a comprehensive Git commit message summarizing the work done for the subtask, including both code implementation and any rule adjustments.
+    *   Execute the commit command directly in the terminal (e.g., `git commit -m 'feat(module): Implement feature X for subtask <subtaskId>\n\n- Details about changes...\n- Updated rule Y for pattern Z'`).
+    *   Consider if a Changeset is needed according to internal versioning guidelines (previously linked to `changeset.mdc`). If so, run `npm run changeset`, stage the generated file, and amend the commit or create a new one.
+
+10. **Proceed to Next Subtask:**
+    *   Identify the next subtask (e.g., using `next_task` / `task-master next`).
+
+## Code Analysis & Refactoring Techniques
+
+- **Top-Level Function Search**:
+    - Useful for understanding module structure or planning refactors.
+    - Use grep/ripgrep to find exported functions/constants:
+      `rg "export (async function|function|const) \w+"` or similar patterns.
+    - Can help compare functions between files during migrations or identify potential naming conflicts.
+
+---
+*This workflow provides a general guideline. Adapt it based on your specific project needs and team practices.*

assets/rules/self_improve.mdc

@@ -0,0 +1,72 @@
+---
+description: Guidelines for continuously improving Cursor rules based on emerging code patterns and best practices.
+globs: **/*
+alwaysApply: true
+---
+
+- **Rule Improvement Triggers:**
+  - New code patterns not covered by existing rules
+  - Repeated similar implementations across files
+  - Common error patterns that could be prevented
+  - New libraries or tools being used consistently
+  - Emerging best practices in the codebase
+
+- **Analysis Process:**
+  - Compare new code with existing rules
+  - Identify patterns that should be standardized
+  - Look for references to external documentation
+  - Check for consistent error handling patterns
+  - Monitor test patterns and coverage
+
+- **Rule Updates:**
+  - **Add New Rules When:**
+    - A new technology/pattern is used in 3+ files
+    - Common bugs could be prevented by a rule
+    - Code reviews repeatedly mention the same feedback
+    - New security or performance patterns emerge
+
+  - **Modify Existing Rules When:**
+    - Better examples exist in the codebase
+    - Additional edge cases are discovered
+    - Related rules have been updated
+    - Implementation details have changed
+
+- **Example Pattern Recognition:**
+  ```typescript
+  // If you see repeated patterns like:
+  const data = await prisma.user.findMany({
+    select: { id: true, email: true },
+    where: { status: 'ACTIVE' }
+  });
+  
+  // Consider adding to [prisma.mdc](mdc:.cursor/rules/prisma.mdc):
+  // - Standard select fields
+  // - Common where conditions
+  // - Performance optimization patterns
+  ```
+
+- **Rule Quality Checks:**
+  - Rules should be actionable and specific
+  - Examples should come from actual code
+  - References should be up to date
+  - Patterns should be consistently enforced
+
+- **Continuous Improvement:**
+  - Monitor code review comments
+  - Track common development questions
+  - Update rules after major refactors
+  - Add links to relevant documentation
+  - Cross-reference related rules
+
+- **Rule Deprecation:**
+  - Mark outdated patterns as deprecated
+  - Remove rules that no longer apply
+  - Update references to deprecated rules
+  - Document migration paths for old patterns
+
+- **Documentation Updates:**
+  - Keep examples synchronized with code
+  - Update references to external docs
+  - Maintain links between related rules
+  - Document breaking changes
+Follow [cursor_rules.mdc](mdc:.cursor/rules/cursor_rules.mdc) for proper rule formatting and structure.

assets/rules/taskmaster.mdc

@@ -0,0 +1,558 @@
+---
+description: Comprehensive reference for Taskmaster MCP tools and CLI commands.
+globs: **/*
+alwaysApply: true
+---
+
+# Taskmaster Tool & Command Reference
+
+This document provides a detailed reference for interacting with Taskmaster, covering both the recommended MCP tools, suitable for integrations like Cursor, and the corresponding `task-master` CLI commands, designed for direct user interaction or fallback.
+
+**Note:** For interacting with Taskmaster programmatically or via integrated tools, using the **MCP tools is strongly recommended** due to better performance, structured data, and error handling. The CLI commands serve as a user-friendly alternative and fallback. 
+
+**Important:** Several MCP tools involve AI processing... The AI-powered tools include `parse_prd`, `analyze_project_complexity`, `update_subtask`, `update_task`, `update`, `expand_all`, `expand_task`, and `add_task`.
+
+**🏷️ Tagged Task Lists System:** Task Master now supports **tagged task lists** for multi-context task management. This allows you to maintain separate, isolated lists of tasks for different features, branches, or experiments. Existing projects are seamlessly migrated to use a default "master" tag. Most commands now support a `--tag <name>` flag to specify which context to operate on. If omitted, commands use the currently active tag.
+
+---
+
+## Initialization & Setup
+
+### 1. Initialize Project (`init`)
+
+*   **MCP Tool:** `initialize_project`
+*   **CLI Command:** `task-master init [options]`
+*   **Description:** `Set up the basic Taskmaster file structure and configuration in the current directory for a new project.`
+*   **Key CLI Options:**
+    *   `--name <name>`: `Set the name for your project in Taskmaster's configuration.`
+    *   `--description <text>`: `Provide a brief description for your project.`
+    *   `--version <version>`: `Set the initial version for your project, e.g., '0.1.0'.`
+    *   `-y, --yes`: `Initialize Taskmaster quickly using default settings without interactive prompts.`
+*   **Usage:** Run this once at the beginning of a new project.
+*   **MCP Variant Description:** `Set up the basic Taskmaster file structure and configuration in the current directory for a new project by running the 'task-master init' command.`
+*   **Key MCP Parameters/Options:**
+    *   `projectName`: `Set the name for your project.` (CLI: `--name <name>`)
+    *   `projectDescription`: `Provide a brief description for your project.` (CLI: `--description <text>`)
+    *   `projectVersion`: `Set the initial version for your project, e.g., '0.1.0'.` (CLI: `--version <version>`)
+    *   `authorName`: `Author name.` (CLI: `--author <author>`)
+    *   `skipInstall`: `Skip installing dependencies. Default is false.` (CLI: `--skip-install`)
+    *   `addAliases`: `Add shell aliases tm and taskmaster. Default is false.` (CLI: `--aliases`)
+    *   `yes`: `Skip prompts and use defaults/provided arguments. Default is false.` (CLI: `-y, --yes`)
+*   **Usage:** Run this once at the beginning of a new project, typically via an integrated tool like Cursor. Operates on the current working directory of the MCP server. 
+*   **Important:** Once complete, you *MUST* parse a prd in order to generate tasks. There will be no tasks files until then. The next step after initializing should be to create a PRD using the example PRD in .taskmaster/templates/example_prd.txt. 
+*   **Tagging:** Use the `--tag` option to parse the PRD into a specific, non-default tag context. If the tag doesn't exist, it will be created automatically. Example: `task-master parse-prd spec.txt --tag=new-feature`.
+
+### 2. Parse PRD (`parse_prd`)
+
+*   **MCP Tool:** `parse_prd`
+*   **CLI Command:** `task-master parse-prd [file] [options]`
+*   **Description:** `Parse a Product Requirements Document, PRD, or text file with Taskmaster to automatically generate an initial set of tasks in tasks.json.`
+*   **Key Parameters/Options:**
+    *   `input`: `Path to your PRD or requirements text file that Taskmaster should parse for tasks.` (CLI: `[file]` positional or `-i, --input <file>`)
+    *   `output`: `Specify where Taskmaster should save the generated 'tasks.json' file. Defaults to '.taskmaster/tasks/tasks.json'.` (CLI: `-o, --output <file>`)
+    *   `numTasks`: `Approximate number of top-level tasks Taskmaster should aim to generate from the document.` (CLI: `-n, --num-tasks <number>`)
+    *   `force`: `Use this to allow Taskmaster to overwrite an existing 'tasks.json' without asking for confirmation.` (CLI: `-f, --force`)
+*   **Usage:** Useful for bootstrapping a project from an existing requirements document.
+*   **Notes:** Task Master will strictly adhere to any specific requirements mentioned in the PRD, such as libraries, database schemas, frameworks, tech stacks, etc., while filling in any gaps where the PRD isn't fully specified. Tasks are designed to provide the most direct implementation path while avoiding over-engineering.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress. If the user does not have a PRD, suggest discussing their idea and then use the example PRD in `.taskmaster/templates/example_prd.txt` as a template for creating the PRD based on their idea, for use with `parse-prd`.
+
+---
+
+## AI Model Configuration
+
+### 2. Manage Models (`models`)
+*   **MCP Tool:** `models`
+*   **CLI Command:** `task-master models [options]`
+*   **Description:** `View the current AI model configuration or set specific models for different roles (main, research, fallback). Allows setting custom model IDs for Ollama and OpenRouter.`
+*   **Key MCP Parameters/Options:**
+    *   `setMain <model_id>`: `Set the primary model ID for task generation/updates.` (CLI: `--set-main <model_id>`)
+    *   `setResearch <model_id>`: `Set the model ID for research-backed operations.` (CLI: `--set-research <model_id>`)
+    *   `setFallback <model_id>`: `Set the model ID to use if the primary fails.` (CLI: `--set-fallback <model_id>`)
+    *   `ollama <boolean>`: `Indicates the set model ID is a custom Ollama model.` (CLI: `--ollama`)
+    *   `openrouter <boolean>`: `Indicates the set model ID is a custom OpenRouter model.` (CLI: `--openrouter`)
+    *   `listAvailableModels <boolean>`: `If true, lists available models not currently assigned to a role.` (CLI: No direct equivalent; CLI lists available automatically)
+    *   `projectRoot <string>`: `Optional. Absolute path to the project root directory.` (CLI: Determined automatically)
+*   **Key CLI Options:**
+    *   `--set-main <model_id>`: `Set the primary model.`
+    *   `--set-research <model_id>`: `Set the research model.`
+    *   `--set-fallback <model_id>`: `Set the fallback model.`
+    *   `--ollama`: `Specify that the provided model ID is for Ollama (use with --set-*).`
+    *   `--openrouter`: `Specify that the provided model ID is for OpenRouter (use with --set-*). Validates against OpenRouter API.`
+    *   `--bedrock`: `Specify that the provided model ID is for AWS Bedrock (use with --set-*).`
+    *   `--setup`: `Run interactive setup to configure models, including custom Ollama/OpenRouter IDs.`
+*   **Usage (MCP):** Call without set flags to get current config. Use `setMain`, `setResearch`, or `setFallback` with a valid model ID to update the configuration. Use `listAvailableModels: true` to get a list of unassigned models. To set a custom model, provide the model ID and set `ollama: true` or `openrouter: true`.
+*   **Usage (CLI):** Run without flags to view current configuration and available models. Use set flags to update specific roles. Use `--setup` for guided configuration, including custom models. To set a custom model via flags, use `--set-<role>=<model_id>` along with either `--ollama` or `--openrouter`.
+*   **Notes:** Configuration is stored in `.taskmaster/config.json` in the project root. This command/tool modifies that file. Use `listAvailableModels` or `task-master models` to see internally supported models. OpenRouter custom models are validated against their live API. Ollama custom models are not validated live.
+*   **API note:** API keys for selected AI providers (based on their model) need to exist in the mcp.json file to be accessible in MCP context. The API keys must be present in the local .env file for the CLI to be able to read them.
+*   **Model costs:** The costs in supported models are expressed in dollars. An input/output value of 3 is $3.00. A value of 0.8 is $0.80. 
+*   **Warning:** DO NOT MANUALLY EDIT THE .taskmaster/config.json FILE. Use the included commands either in the MCP or CLI format as needed. Always prioritize MCP tools when available and use the CLI as a fallback.
+
+---
+
+## Task Listing & Viewing
+
+### 3. Get Tasks (`get_tasks`)
+
+*   **MCP Tool:** `get_tasks`
+*   **CLI Command:** `task-master list [options]`
+*   **Description:** `List your Taskmaster tasks, optionally filtering by status and showing subtasks.`
+*   **Key Parameters/Options:**
+    *   `status`: `Show only Taskmaster tasks matching this status (or multiple statuses, comma-separated), e.g., 'pending' or 'done,in-progress'.` (CLI: `-s, --status <status>`)
+    *   `withSubtasks`: `Include subtasks indented under their parent tasks in the list.` (CLI: `--with-subtasks`)
+    *   `tag`: `Specify which tag context to list tasks from. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Get an overview of the project status, often used at the start of a work session.
+
+### 4. Get Next Task (`next_task`)
+
+*   **MCP Tool:** `next_task`
+*   **CLI Command:** `task-master next [options]`
+*   **Description:** `Ask Taskmaster to show the next available task you can work on, based on status and completed dependencies.`
+*   **Key Parameters/Options:**
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+    *   `tag`: `Specify which tag context to use. Defaults to the current active tag.` (CLI: `--tag <name>`)
+*   **Usage:** Identify what to work on next according to the plan.
+
+### 5. Get Task Details (`get_task`)
+
+*   **MCP Tool:** `get_task`
+*   **CLI Command:** `task-master show [id] [options]`
+*   **Description:** `Display detailed information for one or more specific Taskmaster tasks or subtasks by ID.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID of the Taskmaster task (e.g., '15'), subtask (e.g., '15.2'), or a comma-separated list of IDs ('1,5,10.2') you want to view.` (CLI: `[id]` positional or `-i, --id <id>`)
+    *   `tag`: `Specify which tag context to get the task(s) from. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Understand the full details for a specific task. When multiple IDs are provided, a summary table is shown.
+*   **CRITICAL INFORMATION** If you need to collect information from multiple tasks, use comma-separated IDs (i.e. 1,2,3) to receive an array of tasks. Do not needlessly get tasks one at a time if you need to get many as that is wasteful.
+
+---
+
+## Task Creation & Modification
+
+### 6. Add Task (`add_task`)
+
+*   **MCP Tool:** `add_task`
+*   **CLI Command:** `task-master add-task [options]`
+*   **Description:** `Add a new task to Taskmaster by describing it; AI will structure it.`
+*   **Key Parameters/Options:**
+    *   `prompt`: `Required. Describe the new task you want Taskmaster to create, e.g., "Implement user authentication using JWT".` (CLI: `-p, --prompt <text>`)
+    *   `dependencies`: `Specify the IDs of any Taskmaster tasks that must be completed before this new one can start, e.g., '12,14'.` (CLI: `-d, --dependencies <ids>`)
+    *   `priority`: `Set the priority for the new task: 'high', 'medium', or 'low'. Default is 'medium'.` (CLI: `--priority <priority>`)
+    *   `research`: `Enable Taskmaster to use the research role for potentially more informed task creation.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context to add the task to. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Quickly add newly identified tasks during development.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 7. Add Subtask (`add_subtask`)
+
+*   **MCP Tool:** `add_subtask`
+*   **CLI Command:** `task-master add-subtask [options]`
+*   **Description:** `Add a new subtask to a Taskmaster parent task, or convert an existing task into a subtask.`
+*   **Key Parameters/Options:**
+    *   `id` / `parent`: `Required. The ID of the Taskmaster task that will be the parent.` (MCP: `id`, CLI: `-p, --parent <id>`)
+    *   `taskId`: `Use this if you want to convert an existing top-level Taskmaster task into a subtask of the specified parent.` (CLI: `-i, --task-id <id>`)
+    *   `title`: `Required if not using taskId. The title for the new subtask Taskmaster should create.` (CLI: `-t, --title <title>`)
+    *   `description`: `A brief description for the new subtask.` (CLI: `-d, --description <text>`)
+    *   `details`: `Provide implementation notes or details for the new subtask.` (CLI: `--details <text>`)
+    *   `dependencies`: `Specify IDs of other tasks or subtasks, e.g., '15' or '16.1', that must be done before this new subtask.` (CLI: `--dependencies <ids>`)
+    *   `status`: `Set the initial status for the new subtask. Default is 'pending'.` (CLI: `-s, --status <status>`)
+    *   `skipGenerate`: `Prevent Taskmaster from automatically regenerating markdown task files after adding the subtask.` (CLI: `--skip-generate`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Break down tasks manually or reorganize existing tasks.
+
+### 8. Update Tasks (`update`)
+
+*   **MCP Tool:** `update`
+*   **CLI Command:** `task-master update [options]`
+*   **Description:** `Update multiple upcoming tasks in Taskmaster based on new context or changes, starting from a specific task ID.`
+*   **Key Parameters/Options:**
+    *   `from`: `Required. The ID of the first task Taskmaster should update. All tasks with this ID or higher that are not 'done' will be considered.` (CLI: `--from <id>`)
+    *   `prompt`: `Required. Explain the change or new context for Taskmaster to apply to the tasks, e.g., "We are now using React Query instead of Redux Toolkit for data fetching".` (CLI: `-p, --prompt <text>`)
+    *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Handle significant implementation changes or pivots that affect multiple future tasks. Example CLI: `task-master update --from='18' --prompt='Switching to React Query.\nNeed to refactor data fetching...'`
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 9. Update Task (`update_task`)
+
+*   **MCP Tool:** `update_task`
+*   **CLI Command:** `task-master update-task [options]`
+*   **Description:** `Modify a specific Taskmaster task by ID, incorporating new information or changes. By default, this replaces the existing task details.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The specific ID of the Taskmaster task, e.g., '15', you want to update.` (CLI: `-i, --id <id>`)
+    *   `prompt`: `Required. Explain the specific changes or provide the new information Taskmaster should incorporate into this task.` (CLI: `-p, --prompt <text>`)
+    *   `append`: `If true, appends the prompt content to the task's details with a timestamp, rather than replacing them. Behaves like update-subtask.` (CLI: `--append`)
+    *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context the task belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Refine a specific task based on new understanding. Use `--append` to log progress without creating subtasks.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 10. Update Subtask (`update_subtask`)
+
+*   **MCP Tool:** `update_subtask`
+*   **CLI Command:** `task-master update-subtask [options]`
+*   **Description:** `Append timestamped notes or details to a specific Taskmaster subtask without overwriting existing content. Intended for iterative implementation logging.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID of the Taskmaster subtask, e.g., '5.2', to update with new information.` (CLI: `-i, --id <id>`)
+    *   `prompt`: `Required. The information, findings, or progress notes to append to the subtask's details with a timestamp.` (CLI: `-p, --prompt <text>`)
+    *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context the subtask belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Log implementation progress, findings, and discoveries during subtask development. Each update is timestamped and appended to preserve the implementation journey.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 11. Set Task Status (`set_task_status`)
+
+*   **MCP Tool:** `set_task_status`
+*   **CLI Command:** `task-master set-status [options]`
+*   **Description:** `Update the status of one or more Taskmaster tasks or subtasks, e.g., 'pending', 'in-progress', 'done'.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID(s) of the Taskmaster task(s) or subtask(s), e.g., '15', '15.2', or '16,17.1', to update.` (CLI: `-i, --id <id>`)
+    *   `status`: `Required. The new status to set, e.g., 'done', 'pending', 'in-progress', 'review', 'cancelled'.` (CLI: `-s, --status <status>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Mark progress as tasks move through the development cycle.
+
+### 12. Remove Task (`remove_task`)
+
+*   **MCP Tool:** `remove_task`
+*   **CLI Command:** `task-master remove-task [options]`
+*   **Description:** `Permanently remove a task or subtask from the Taskmaster tasks list.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID of the Taskmaster task, e.g., '5', or subtask, e.g., '5.2', to permanently remove.` (CLI: `-i, --id <id>`)
+    *   `yes`: `Skip the confirmation prompt and immediately delete the task.` (CLI: `-y, --yes`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Permanently delete tasks or subtasks that are no longer needed in the project.
+*   **Notes:** Use with caution as this operation cannot be undone. Consider using 'blocked', 'cancelled', or 'deferred' status instead if you just want to exclude a task from active planning but keep it for reference. The command automatically cleans up dependency references in other tasks.
+
+---
+
+## Task Structure & Breakdown
+
+### 13. Expand Task (`expand_task`)
+
+*   **MCP Tool:** `expand_task`
+*   **CLI Command:** `task-master expand [options]`
+*   **Description:** `Use Taskmaster's AI to break down a complex task into smaller, manageable subtasks. Appends subtasks by default.`
+*   **Key Parameters/Options:**
+    *   `id`: `The ID of the specific Taskmaster task you want to break down into subtasks.` (CLI: `-i, --id <id>`)
+    *   `num`: `Optional: Suggests how many subtasks Taskmaster should aim to create. Uses complexity analysis/defaults otherwise.` (CLI: `-n, --num <number>`)
+    *   `research`: `Enable Taskmaster to use the research role for more informed subtask generation. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `prompt`: `Optional: Provide extra context or specific instructions to Taskmaster for generating the subtasks.` (CLI: `-p, --prompt <text>`)
+    *   `force`: `Optional: If true, clear existing subtasks before generating new ones. Default is false (append).` (CLI: `--force`)
+    *   `tag`: `Specify which tag context the task belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Generate a detailed implementation plan for a complex task before starting coding. Automatically uses complexity report recommendations if available and `num` is not specified.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 14. Expand All Tasks (`expand_all`)
+
+*   **MCP Tool:** `expand_all`
+*   **CLI Command:** `task-master expand --all [options]` (Note: CLI uses the `expand` command with the `--all` flag)
+*   **Description:** `Tell Taskmaster to automatically expand all eligible pending/in-progress tasks based on complexity analysis or defaults. Appends subtasks by default.`
+*   **Key Parameters/Options:**
+    *   `num`: `Optional: Suggests how many subtasks Taskmaster should aim to create per task.` (CLI: `-n, --num <number>`)
+    *   `research`: `Enable research role for more informed subtask generation. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `prompt`: `Optional: Provide extra context for Taskmaster to apply generally during expansion.` (CLI: `-p, --prompt <text>`)
+    *   `force`: `Optional: If true, clear existing subtasks before generating new ones for each eligible task. Default is false (append).` (CLI: `--force`)
+    *   `tag`: `Specify which tag context to expand. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Useful after initial task generation or complexity analysis to break down multiple tasks at once.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 15. Clear Subtasks (`clear_subtasks`)
+
+*   **MCP Tool:** `clear_subtasks`
+*   **CLI Command:** `task-master clear-subtasks [options]`
+*   **Description:** `Remove all subtasks from one or more specified Taskmaster parent tasks.`
+*   **Key Parameters/Options:**
+    *   `id`: `The ID(s) of the Taskmaster parent task(s) whose subtasks you want to remove, e.g., '15' or '16,18'. Required unless using `all`.) (CLI: `-i, --id <ids>`)
+    *   `all`: `Tell Taskmaster to remove subtasks from all parent tasks.` (CLI: `--all`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Used before regenerating subtasks with `expand_task` if the previous breakdown needs replacement.
+
+### 16. Remove Subtask (`remove_subtask`)
+
+*   **MCP Tool:** `remove_subtask`
+*   **CLI Command:** `task-master remove-subtask [options]`
+*   **Description:** `Remove a subtask from its Taskmaster parent, optionally converting it into a standalone task.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID(s) of the Taskmaster subtask(s) to remove, e.g., '15.2' or '16.1,16.3'.` (CLI: `-i, --id <id>`)
+    *   `convert`: `If used, Taskmaster will turn the subtask into a regular top-level task instead of deleting it.` (CLI: `-c, --convert`)
+    *   `skipGenerate`: `Prevent Taskmaster from automatically regenerating markdown task files after removing the subtask.` (CLI: `--skip-generate`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Delete unnecessary subtasks or promote a subtask to a top-level task.
+
+### 17. Move Task (`move_task`)
+
+*   **MCP Tool:** `move_task`
+*   **CLI Command:** `task-master move [options]`
+*   **Description:** `Move a task or subtask to a new position within the task hierarchy.`
+*   **Key Parameters/Options:**
+    *   `from`: `Required. ID of the task/subtask to move (e.g., "5" or "5.2"). Can be comma-separated for multiple tasks.` (CLI: `--from <id>`)
+    *   `to`: `Required. ID of the destination (e.g., "7" or "7.3"). Must match the number of source IDs if comma-separated.` (CLI: `--to <id>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Reorganize tasks by moving them within the hierarchy. Supports various scenarios like:
+    *   Moving a task to become a subtask
+    *   Moving a subtask to become a standalone task
+    *   Moving a subtask to a different parent
+    *   Reordering subtasks within the same parent
+    *   Moving a task to a new, non-existent ID (automatically creates placeholders)
+    *   Moving multiple tasks at once with comma-separated IDs
+*   **Validation Features:**
+    *   Allows moving tasks to non-existent destination IDs (creates placeholder tasks)
+    *   Prevents moving to existing task IDs that already have content (to avoid overwriting)
+    *   Validates that source tasks exist before attempting to move them
+    *   Maintains proper parent-child relationships
+*   **Example CLI:** `task-master move --from=5.2 --to=7.3` to move subtask 5.2 to become subtask 7.3.
+*   **Example Multi-Move:** `task-master move --from=10,11,12 --to=16,17,18` to move multiple tasks to new positions.
+*   **Common Use:** Resolving merge conflicts in tasks.json when multiple team members create tasks on different branches.
+
+---
+
+## Dependency Management
+
+### 18. Add Dependency (`add_dependency`)
+
+*   **MCP Tool:** `add_dependency`
+*   **CLI Command:** `task-master add-dependency [options]`
+*   **Description:** `Define a dependency in Taskmaster, making one task a prerequisite for another.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID of the Taskmaster task that will depend on another.` (CLI: `-i, --id <id>`)
+    *   `dependsOn`: `Required. The ID of the Taskmaster task that must be completed first, the prerequisite.` (CLI: `-d, --depends-on <id>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <path>`)
+*   **Usage:** Establish the correct order of execution between tasks.
+
+### 19. Remove Dependency (`remove_dependency`)
+
+*   **MCP Tool:** `remove_dependency`
+*   **CLI Command:** `task-master remove-dependency [options]`
+*   **Description:** `Remove a dependency relationship between two Taskmaster tasks.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID of the Taskmaster task you want to remove a prerequisite from.` (CLI: `-i, --id <id>`)
+    *   `dependsOn`: `Required. The ID of the Taskmaster task that should no longer be a prerequisite.` (CLI: `-d, --depends-on <id>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Update task relationships when the order of execution changes.
+
+### 20. Validate Dependencies (`validate_dependencies`)
+
+*   **MCP Tool:** `validate_dependencies`
+*   **CLI Command:** `task-master validate-dependencies [options]`
+*   **Description:** `Check your Taskmaster tasks for dependency issues (like circular references or links to non-existent tasks) without making changes.`
+*   **Key Parameters/Options:**
+    *   `tag`: `Specify which tag context to validate. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Audit the integrity of your task dependencies.
+
+### 21. Fix Dependencies (`fix_dependencies`)
+
+*   **MCP Tool:** `fix_dependencies`
+*   **CLI Command:** `task-master fix-dependencies [options]`
+*   **Description:** `Automatically fix dependency issues (like circular references or links to non-existent tasks) in your Taskmaster tasks.`
+*   **Key Parameters/Options:**
+    *   `tag`: `Specify which tag context to fix dependencies in. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Clean up dependency errors automatically.
+
+---
+
+## Analysis & Reporting
+
+### 22. Analyze Project Complexity (`analyze_project_complexity`)
+
+*   **MCP Tool:** `analyze_project_complexity`
+*   **CLI Command:** `task-master analyze-complexity [options]`
+*   **Description:** `Have Taskmaster analyze your tasks to determine their complexity and suggest which ones need to be broken down further.`
+*   **Key Parameters/Options:**
+    *   `output`: `Where to save the complexity analysis report. Default is '.taskmaster/reports/task-complexity-report.json' (or '..._tagname.json' if a tag is used).` (CLI: `-o, --output <file>`)
+    *   `threshold`: `The minimum complexity score (1-10) that should trigger a recommendation to expand a task.` (CLI: `-t, --threshold <number>`)
+    *   `research`: `Enable research role for more accurate complexity analysis. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context to analyze. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Used before breaking down tasks to identify which ones need the most attention.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 23. View Complexity Report (`complexity_report`)
+
+*   **MCP Tool:** `complexity_report`
+*   **CLI Command:** `task-master complexity-report [options]`
+*   **Description:** `Display the task complexity analysis report in a readable format.`
+*   **Key Parameters/Options:**
+    *   `tag`: `Specify which tag context to show the report for. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to the complexity report (default: '.taskmaster/reports/task-complexity-report.json').` (CLI: `-f, --file <file>`)
+*   **Usage:** Review and understand the complexity analysis results after running analyze-complexity.
+
+---
+
+## File Management
+
+### 24. Generate Task Files (`generate`)
+
+*   **MCP Tool:** `generate`
+*   **CLI Command:** `task-master generate [options]`
+*   **Description:** `Create or update individual Markdown files for each task based on your tasks.json.`
+*   **Key Parameters/Options:**
+    *   `output`: `The directory where Taskmaster should save the task files (default: in a 'tasks' directory).` (CLI: `-o, --output <directory>`)
+    *   `tag`: `Specify which tag context to generate files for. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Run this after making changes to tasks.json to keep individual task files up to date. This command is now manual and no longer runs automatically.
+
+---
+
+## AI-Powered Research
+
+### 25. Research (`research`)
+
+*   **MCP Tool:** `research`
+*   **CLI Command:** `task-master research [options]`
+*   **Description:** `Perform AI-powered research queries with project context to get fresh, up-to-date information beyond the AI's knowledge cutoff.`
+*   **Key Parameters/Options:**
+    *   `query`: `Required. Research query/prompt (e.g., "What are the latest best practices for React Query v5?").` (CLI: `[query]` positional or `-q, --query <text>`)
+    *   `taskIds`: `Comma-separated list of task/subtask IDs from the current tag context (e.g., "15,16.2,17").` (CLI: `-i, --id <ids>`)
+    *   `filePaths`: `Comma-separated list of file paths for context (e.g., "src/api.js,docs/readme.md").` (CLI: `-f, --files <paths>`)
+    *   `customContext`: `Additional custom context text to include in the research.` (CLI: `-c, --context <text>`)
+    *   `includeProjectTree`: `Include project file tree structure in context (default: false).` (CLI: `--tree`)
+    *   `detailLevel`: `Detail level for the research response: 'low', 'medium', 'high' (default: medium).` (CLI: `--detail <level>`)
+    *   `saveTo`: `Task or subtask ID (e.g., "15", "15.2") to automatically save the research conversation to.` (CLI: `--save-to <id>`)
+    *   `saveFile`: `If true, saves the research conversation to a markdown file in '.taskmaster/docs/research/'.` (CLI: `--save-file`)
+    *   `noFollowup`: `Disables the interactive follow-up question menu in the CLI.` (CLI: `--no-followup`)
+    *   `tag`: `Specify which tag context to use for task-based context gathering. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `projectRoot`: `The directory of the project. Must be an absolute path.` (CLI: Determined automatically)
+*   **Usage:** **This is a POWERFUL tool that agents should use FREQUENTLY** to:
+    *   Get fresh information beyond knowledge cutoff dates
+    *   Research latest best practices, library updates, security patches
+    *   Find implementation examples for specific technologies
+    *   Validate approaches against current industry standards
+    *   Get contextual advice based on project files and tasks
+*   **When to Consider Using Research:**
+    *   **Before implementing any task** - Research current best practices
+    *   **When encountering new technologies** - Get up-to-date implementation guidance (libraries, apis, etc)
+    *   **For security-related tasks** - Find latest security recommendations
+    *   **When updating dependencies** - Research breaking changes and migration guides
+    *   **For performance optimization** - Get current performance best practices
+    *   **When debugging complex issues** - Research known solutions and workarounds
+*   **Research + Action Pattern:**
+    *   Use `research` to gather fresh information
+    *   Use `update_subtask` to commit findings with timestamps
+    *   Use `update_task` to incorporate research into task details
+    *   Use `add_task` with research flag for informed task creation
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. The research provides FRESH data beyond the AI's training cutoff, making it invaluable for current best practices and recent developments.
+
+---
+
+## Tag Management
+
+This new suite of commands allows you to manage different task contexts (tags).
+
+### 26. List Tags (`tags`)
+
+*   **MCP Tool:** `list_tags`
+*   **CLI Command:** `task-master tags [options]`
+*   **Description:** `List all available tags with task counts, completion status, and other metadata.`
+*   **Key Parameters/Options:**
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+    *   `--show-metadata`: `Include detailed metadata in the output (e.g., creation date, description).` (CLI: `--show-metadata`)
+
+### 27. Add Tag (`add_tag`)
+
+*   **MCP Tool:** `add_tag`
+*   **CLI Command:** `task-master add-tag <tagName> [options]`
+*   **Description:** `Create a new, empty tag context, or copy tasks from another tag.`
+*   **Key Parameters/Options:**
+    *   `tagName`: `Name of the new tag to create (alphanumeric, hyphens, underscores).` (CLI: `<tagName>` positional)
+    *   `--from-branch`: `Creates a tag with a name derived from the current git branch, ignoring the <tagName> argument.` (CLI: `--from-branch`)
+    *   `--copy-from-current`: `Copy tasks from the currently active tag to the new tag.` (CLI: `--copy-from-current`)
+    *   `--copy-from <tag>`: `Copy tasks from a specific source tag to the new tag.` (CLI: `--copy-from <tag>`)
+    *   `--description <text>`: `Provide an optional description for the new tag.` (CLI: `-d, --description <text>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 28. Delete Tag (`delete_tag`)
+
+*   **MCP Tool:** `delete_tag`
+*   **CLI Command:** `task-master delete-tag <tagName> [options]`
+*   **Description:** `Permanently delete a tag and all of its associated tasks.`
+*   **Key Parameters/Options:**
+    *   `tagName`: `Name of the tag to delete.` (CLI: `<tagName>` positional)
+    *   `--yes`: `Skip the confirmation prompt.` (CLI: `-y, --yes`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 29. Use Tag (`use_tag`)
+
+*   **MCP Tool:** `use_tag`
+*   **CLI Command:** `task-master use-tag <tagName>`
+*   **Description:** `Switch your active task context to a different tag.`
+*   **Key Parameters/Options:**
+    *   `tagName`: `Name of the tag to switch to.` (CLI: `<tagName>` positional)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 30. Rename Tag (`rename_tag`)
+
+*   **MCP Tool:** `rename_tag`
+*   **CLI Command:** `task-master rename-tag <oldName> <newName>`
+*   **Description:** `Rename an existing tag.`
+*   **Key Parameters/Options:**
+    *   `oldName`: `The current name of the tag.` (CLI: `<oldName>` positional)
+    *   `newName`: `The new name for the tag.` (CLI: `<newName>` positional)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 31. Copy Tag (`copy_tag`)
+
+*   **MCP Tool:** `copy_tag`
+*   **CLI Command:** `task-master copy-tag <sourceName> <targetName> [options]`
+*   **Description:** `Copy an entire tag context, including all its tasks and metadata, to a new tag.`
+*   **Key Parameters/Options:**
+    *   `sourceName`: `Name of the tag to copy from.` (CLI: `<sourceName>` positional)
+    *   `targetName`: `Name of the new tag to create.` (CLI: `<targetName>` positional)
+    *   `--description <text>`: `Optional description for the new tag.` (CLI: `-d, --description <text>`)
+
+---
+
+## Miscellaneous
+
+### 32. Sync Readme (`sync-readme`) -- experimental
+
+*   **MCP Tool:** N/A
+*   **CLI Command:** `task-master sync-readme [options]`
+*   **Description:** `Exports your task list to your project's README.md file, useful for showcasing progress.`
+*   **Key Parameters/Options:**
+    *   `status`: `Filter tasks by status (e.g., 'pending', 'done').` (CLI: `-s, --status <status>`)
+    *   `withSubtasks`: `Include subtasks in the export.` (CLI: `--with-subtasks`)
+    *   `tag`: `Specify which tag context to export from. Defaults to the current active tag.` (CLI: `--tag <name>`)
+
+---
+
+## Environment Variables Configuration (Updated)
+
+Taskmaster primarily uses the **`.taskmaster/config.json`** file (in project root) for configuration (models, parameters, logging level, etc.), managed via `task-master models --setup`.
+
+Environment variables are used **only** for sensitive API keys related to AI providers and specific overrides like the Ollama base URL:
+
+*   **API Keys (Required for corresponding provider):**
+    *   `ANTHROPIC_API_KEY`
+    *   `PERPLEXITY_API_KEY`
+    *   `OPENAI_API_KEY`
+    *   `GOOGLE_API_KEY`
+    *   `MISTRAL_API_KEY`
+    *   `AZURE_OPENAI_API_KEY` (Requires `AZURE_OPENAI_ENDPOINT` too)
+    *   `OPENROUTER_API_KEY`
+    *   `XAI_API_KEY`
+    *   `OLLAMA_API_KEY` (Requires `OLLAMA_BASE_URL` too)
+*   **Endpoints (Optional/Provider Specific inside .taskmaster/config.json):**
+    *   `AZURE_OPENAI_ENDPOINT`
+    *   `OLLAMA_BASE_URL` (Default: `http://localhost:11434/api`)
+
+**Set API keys** in your **`.env`** file in the project root (for CLI use) or within the `env` section of your **`.cursor/mcp.json`** file (for MCP/Cursor integration). All other settings (model choice, max tokens, temperature, log level, custom endpoints) are managed in `.taskmaster/config.json` via `task-master models` command or `models` MCP tool.
+
+---
+
+For details on how these commands fit into the development process, see the [Development Workflow Guide](mdc:.cursor/rules/dev_workflow.mdc).

assets/scripts_README.md

@@ -20,7 +20,7 @@ In an AI-driven development process—particularly with tools like [Cursor](http
 
 Task Master configuration is now managed through two primary methods:
 
-1.  **`.taskmasterconfig` File (Project Root - Primary)**
+1.  **`.taskmaster/config.json` File (Project Root - Primary)**
 
     - Stores AI model selections (`main`, `research`, `fallback`), model parameters (`maxTokens`, `temperature`), `logLevel`, `defaultSubtasks`, `defaultPriority`, `projectName`, etc.
     - Managed using the `task-master models --setup` command or the `models` MCP tool.
@@ -192,7 +192,7 @@ Notes:
 ## AI Integration (Updated)
 
 - The script now uses a unified AI service layer (`ai-services-unified.js`).
-- Model selection (e.g., Claude vs. Perplexity for `--research`) is determined by the configuration in `.taskmasterconfig` based on the requested `role` (`main` or `research`).
+- Model selection (e.g., Claude vs. Perplexity for `--research`) is determined by the configuration in `.taskmaster/config.json` based on the requested `role` (`main` or `research`).
 - API keys are automatically resolved from your `.env` file (for CLI) or MCP session environment.
 - To use the research capabilities (e.g., `expand --research`), ensure you have:
   1.  Configured a model for the `research` role using `task-master models --setup` (Perplexity models are recommended).
@@ -357,25 +357,25 @@ The output report structure is:
 
 ```json
 {
-	"meta": {
+  "meta": {
-		"generatedAt": "2023-06-15T12:34:56.789Z",
+    "generatedAt": "2023-06-15T12:34:56.789Z",
-		"tasksAnalyzed": 20,
+    "tasksAnalyzed": 20,
-		"thresholdScore": 5,
+    "thresholdScore": 5,
-		"projectName": "Your Project Name",
+    "projectName": "Your Project Name",
-		"usedResearch": true
+    "usedResearch": true
-	},
+  },
-	"complexityAnalysis": [
+  "complexityAnalysis": [
-		{
+    {
-			"taskId": 8,
+      "taskId": 8,
-			"taskTitle": "Develop Implementation Drift Handling",
+      "taskTitle": "Develop Implementation Drift Handling",
-			"complexityScore": 9.5,
+      "complexityScore": 9.5,
-			"recommendedSubtasks": 6,
+      "recommendedSubtasks": 6,
-			"expansionPrompt": "Create subtasks that handle detecting...",
+      "expansionPrompt": "Create subtasks that handle detecting...",
-			"reasoning": "This task requires sophisticated logic...",
+      "reasoning": "This task requires sophisticated logic...",
-			"expansionCommand": "task-master expand --id=8 --num=6 --prompt=\"Create subtasks...\" --research"
+      "expansionCommand": "task-master expand --id=8 --num=6 --prompt=\"Create subtasks...\" --research"
-		}
+    }
-		// More tasks sorted by complexity score (highest first)
+    // More tasks sorted by complexity score (highest first)
-	]
+  ]
 }
 ```
 

bin/task-master.js

@@ -373,8 +373,4 @@ if (process.argv.length <= 2) {
 }
 
 // Add exports at the end of the file
-if (typeof module !== 'undefined') {
+export { detectCamelCaseFlags };
-	module.exports = {
-		detectCamelCaseFlags
-	};
-}

biome.json

@@ -0,0 +1,50 @@
+{
+	"files": {
+		"ignore": [
+			"build",
+			"coverage",
+			".changeset",
+			"tasks",
+			"package-lock.json",
+			"tests/fixture/*.json"
+		]
+	},
+	"formatter": {
+		"bracketSpacing": true,
+		"enabled": true,
+		"indentStyle": "tab",
+		"lineWidth": 80
+	},
+	"javascript": {
+		"formatter": {
+			"arrowParentheses": "always",
+			"quoteStyle": "single",
+			"trailingCommas": "none"
+		}
+	},
+	"linter": {
+		"rules": {
+			"complexity": {
+				"noForEach": "off",
+				"useOptionalChain": "off",
+				"useArrowFunction": "off"
+			},
+			"correctness": {
+				"noConstantCondition": "off",
+				"noUnreachable": "off"
+			},
+			"suspicious": {
+				"noDuplicateTestHooks": "off",
+				"noPrototypeBuiltins": "off"
+			},
+			"style": {
+				"noUselessElse": "off",
+				"useNodejsImportProtocol": "off",
+				"useNumberNamespace": "off",
+				"noParameterAssign": "off",
+				"useTemplate": "off",
+				"noUnusedTemplateLiteral": "off"
+			}
+		}
+	}
+}

docs/README.md

@@ -9,7 +9,7 @@ Welcome to the Task Master documentation. Use the links below to navigate to the
 
 ## Reference
 
-- [Command Reference](command-reference.md) - Complete list of all available commands
+- [Command Reference](command-reference.md) - Complete list of all available commands (including research and multi-task viewing)
 - [Task Structure](task-structure.md) - Understanding the task format and features
 
 ## Examples & Licensing

docs/command-reference.md

@@ -43,10 +43,28 @@ task-master show <id>
 # or
 task-master show --id=<id>
 
+# View multiple tasks with comma-separated IDs
+task-master show 1,3,5
+task-master show 44,55
+
 # View a specific subtask (e.g., subtask 2 of task 1)
 task-master show 1.2
+
+# Mix parent tasks and subtasks
+task-master show 44,44.1,55,55.2
 ```
 
+**Multiple Task Display:**
+
+- **Single ID**: Shows detailed task view with full implementation details
+- **Multiple IDs**: Shows compact summary table with interactive action menu
+- **Action Menu**: Provides copy-paste ready commands for batch operations:
+  - Mark all as in-progress/done
+  - Show next available task
+  - Expand all tasks (generate subtasks)
+  - View dependency relationships
+  - Generate task files
+
 ## Update Tasks
 
 ```bash
@@ -187,6 +205,32 @@ task-master validate-dependencies
 task-master fix-dependencies
 ```
 
+## Move Tasks
+
+```bash
+# Move a task or subtask to a new position
+task-master move --from=<id> --to=<id>
+
+# Examples:
+# Move task to become a subtask
+task-master move --from=5 --to=7
+
+# Move subtask to become a standalone task
+task-master move --from=5.2 --to=7
+
+# Move subtask to a different parent
+task-master move --from=5.2 --to=7.3
+
+# Reorder subtasks within the same parent
+task-master move --from=5.2 --to=5.4
+
+# Move a task to a new ID position (creates placeholder if doesn't exist)
+task-master move --from=5 --to=25
+
+# Move multiple tasks at once (must have the same number of IDs)
+task-master move --from=10,11,12 --to=16,17,18
+```
+
 ## Add a New Task
 
 ```bash
@@ -203,13 +247,115 @@ task-master add-task --prompt="Description" --dependencies=1,2,3
 task-master add-task --prompt="Description" --priority=high
 ```
 
+## Tag Management
+
+Task Master supports tagged task lists for multi-context task management. Each tag represents a separate, isolated context for tasks.
+
+```bash
+# List all available tags with task counts and status
+task-master tags
+
+# List tags with detailed metadata
+task-master tags --show-metadata
+
+# Create a new empty tag
+task-master add-tag <tag-name>
+
+# Create a new tag with a description
+task-master add-tag <tag-name> --description="Feature development tasks"
+
+# Create a tag based on current git branch name
+task-master add-tag --from-branch
+
+# Create a new tag by copying tasks from the current tag
+task-master add-tag <new-tag> --copy-from-current
+
+# Create a new tag by copying from a specific tag
+task-master add-tag <new-tag> --copy-from=<source-tag>
+
+# Switch to a different tag context
+task-master use-tag <tag-name>
+
+# Rename an existing tag
+task-master rename-tag <old-name> <new-name>
+
+# Copy an entire tag to create a new one
+task-master copy-tag <source-tag> <target-tag>
+
+# Copy a tag with a description
+task-master copy-tag <source-tag> <target-tag> --description="Copied for testing"
+
+# Delete a tag and all its tasks (with confirmation)
+task-master delete-tag <tag-name>
+
+# Delete a tag without confirmation prompt
+task-master delete-tag <tag-name> --yes
+```
+
+**Tag Context:**
+- All task operations (list, show, add, update, etc.) work within the currently active tag
+- Use `--tag=<name>` flag with most commands to operate on a specific tag context
+- Tags provide complete isolation - tasks in different tags don't interfere with each other
+
 ## Initialize a Project
 
 ```bash
 # Initialize a new project with Task Master structure
 task-master init
+
+# Initialize a new project applying specific rules
+task-master init --rules cursor,windsurf,vscode
 ```
 
+- The `--rules` flag allows you to specify one or more rule profiles (e.g., `cursor`, `roo`, `windsurf`, `cline`) to apply during initialization.
+- If omitted, all available rule profiles are installed by default (claude, cline, codex, cursor, roo, trae, vscode, windsurf).
+- You can use multiple comma-separated profiles in a single command.
+
+## Manage Rules
+
+```bash
+# Add rule profiles to your project
+# (e.g., .roo/rules, .windsurf/rules)
+task-master rules add <profile1,profile2,...>
+
+# Remove rule sets from your project
+task-master rules remove <profile1,profile2,...>
+
+# Remove rule sets bypassing safety check (dangerous)
+task-master rules remove <profile1,profile2,...> --force
+
+# Launch interactive rules setup to select rules
+# (does not re-initialize project or ask about shell aliases)
+task-master rules setup
+```
+
+- Adding rules creates the profile and rules directory (e.g., `.roo/rules`) and copies/initializes the rules.
+- Removing rules deletes the profile and rules directory and associated MCP config.
+- **Safety Check**: Attempting to remove rule profiles will trigger a critical warning requiring confirmation. Use `--force` to bypass.
+- You can use multiple comma-separated rules in a single command.
+- The `setup` action launches an interactive prompt to select which rules to apply. The list of rules is always current with the available profiles, and no manual updates are needed. This command does **not** re-initialize your project or affect shell aliases; it only manages rules interactively.
+
+**Examples:**
+
+```bash
+task-master rules add windsurf,roo,vscode
+task-master rules remove windsurf
+task-master rules setup
+```
+
+### Interactive Rules Setup
+
+You can launch the interactive rules setup at any time with:
+
+```bash
+task-master rules setup
+```
+
+This command opens a prompt where you can select which rule profiles (e.g., Cursor, Roo, Windsurf) you want to add to your project. This does **not** re-initialize your project or ask about shell aliases; it only manages rules.
+
+- Use this command to add rule profiles interactively after project creation.
+- The same interactive prompt is also used during `init` if you don't specify rules with `--rules`.
+
 ## Configure AI Models
 
 ```bash
@@ -235,4 +381,70 @@ task-master models --set-research=google/gemini-pro --openrouter
 task-master models --setup
 ```
 
-Configuration is stored in `.taskmasterconfig` in your project root. API keys are still managed via `.env` or MCP configuration. Use `task-master models` without flags to see available built-in models. Use `--setup` for a guided experience.
+Configuration is stored in `.taskmaster/config.json` in your project root (legacy `.taskmasterconfig` files are automatically migrated). API keys are still managed via `.env` or MCP configuration. Use `task-master models` without flags to see available built-in models. Use `--setup` for a guided experience.
+
+State is stored in `.taskmaster/state.json` in your project root. It maintains important information like the current tag. Do not manually edit this file.
+
+## Research Fresh Information
+
+```bash
+# Perform AI-powered research with fresh, up-to-date information
+task-master research "What are the latest best practices for JWT authentication in Node.js?"
+
+# Research with specific task context
+task-master research "How to implement OAuth 2.0?" --id=15,16
+
+# Research with file context for code-aware suggestions
+task-master research "How can I optimize this API implementation?" --files=src/api.js,src/auth.js
+
+# Research with custom context and project tree
+task-master research "Best practices for error handling" --context="We're using Express.js" --tree
+
+# Research with different detail levels
+task-master research "React Query v5 migration guide" --detail=high
+
+# Disable interactive follow-up questions (useful for scripting, is the default for MCP)
+# Use a custom tasks file location
+task-master research "How to implement this feature?" --file=custom-tasks.json
+
+# Research within a specific tag context
+task-master research "Database optimization strategies" --tag=feature-branch
+
+# Save research conversation to .taskmaster/docs/research/ directory (for later reference)
+task-master research "Database optimization techniques" --save-file
+
+# Save key findings directly to a task or subtask (recommended for actionable insights)
+task-master research "How to implement OAuth?" --save-to=15
+task-master research "API optimization strategies" --save-to=15.2
+
+# Combine context gathering with automatic saving of findings
+task-master research "Best practices for this implementation" --id=15,16 --files=src/auth.js --save-to=15.3
+```
+
+**The research command is a powerful exploration tool that provides:**
+
+- **Fresh information beyond AI knowledge cutoffs**
+- **Project-aware context** from your tasks and files
+- **Automatic task discovery** using fuzzy search
+- **Multiple detail levels** (low, medium, high)
+- **Token counting and cost tracking**
+- **Interactive follow-up questions** for deep exploration
+- **Flexible save options** (commit findings to tasks or preserve conversations)
+- **Iterative discovery** through continuous questioning and refinement
+
+**Use research frequently to:**
+
+- Get current best practices before implementing features
+- Research new technologies and libraries
+- Find solutions to complex problems
+- Validate your implementation approaches
+- Stay updated with latest security recommendations
+
+**Interactive Features (CLI):**
+
+- **Follow-up questions** that maintain conversation context and allow deep exploration
+- **Save menu** during or after research with flexible options:
+  - **Save to task/subtask**: Commit key findings and actionable insights (recommended)
+  - **Save to file**: Preserve entire conversation for later reference if needed
+  - **Continue exploring**: Ask more follow-up questions to dig deeper
+- **Automatic file naming** with timestamps and query-based slugs when saving conversations

docs/configuration.md

@@ -2,73 +2,129 @@
 
 Taskmaster uses two primary methods for configuration:
 
-1.  **`.taskmasterconfig` File (Project Root - Recommended for most settings)**
+1.  **`.taskmaster/config.json` File (Recommended - New Structure)**
 
     - This JSON file stores most configuration settings, including AI model selections, parameters, logging levels, and project defaults.
-    - **Location:** This file is created in the root directory of your project when you run the `task-master models --setup` interactive setup. You typically do this during the initialization sequence. Do not manually edit this file beyond adjusting Temperature and Max Tokens depending on your model.
+    - **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.
     - **Example Structure:**
       ```json
       {
-      	"models": {
+        "models": {
-      		"main": {
+          "main": {
-      			"provider": "anthropic",
+            "provider": "anthropic",
-      			"modelId": "claude-3-7-sonnet-20250219",
+            "modelId": "claude-3-7-sonnet-20250219",
-      			"maxTokens": 64000,
+            "maxTokens": 64000,
-      			"temperature": 0.2,
+            "temperature": 0.2,
-      			"baseUrl": "https://api.anthropic.com/v1"
+            "baseURL": "https://api.anthropic.com/v1"
-      		},
+          },
-      		"research": {
+          "research": {
-      			"provider": "perplexity",
+            "provider": "perplexity",
-      			"modelId": "sonar-pro",
+            "modelId": "sonar-pro",
-      			"maxTokens": 8700,
+            "maxTokens": 8700,
-      			"temperature": 0.1,
+            "temperature": 0.1,
-      			"baseUrl": "https://api.perplexity.ai/v1"
+            "baseURL": "https://api.perplexity.ai/v1"
-      		},
+          },
-      		"fallback": {
+          "fallback": {
-      			"provider": "anthropic",
+            "provider": "anthropic",
-      			"modelId": "claude-3-5-sonnet",
+            "modelId": "claude-3-5-sonnet",
-      			"maxTokens": 64000,
+            "maxTokens": 64000,
-      			"temperature": 0.2
+            "temperature": 0.2
-      		}
+          }
-      	},
+        },
-      	"global": {
+        "global": {
-      		"logLevel": "info",
+          "logLevel": "info",
-      		"debug": false,
+          "debug": false,
-      		"defaultSubtasks": 5,
+          "defaultSubtasks": 5,
-      		"defaultPriority": "medium",
+          "defaultPriority": "medium",
-      		"projectName": "Your Project Name",
+          "defaultTag": "master",
-      		"ollamaBaseUrl": "http://localhost:11434/api",
+          "projectName": "Your Project Name",
-      		"azureOpenaiBaseUrl": "https://your-endpoint.openai.azure.com/"
+          "ollamaBaseURL": "http://localhost:11434/api",
-      	}
+          "azureBaseURL": "https://your-endpoint.azure.com/",
+          "vertexProjectId": "your-gcp-project-id",
+          "vertexLocation": "us-central1"
+        }
       }
       ```
 
-2.  **Environment Variables (`.env` file or MCP `env` block - For API Keys Only)**
+2.  **Legacy `.taskmasterconfig` File (Backward Compatibility)**
-    - Used **exclusively** for sensitive API keys and specific endpoint URLs.
-    - **Location:**
-      - For CLI usage: Create a `.env` file in your project root.
-      - For MCP/Cursor usage: Configure keys in the `env` section of your `.cursor/mcp.json` file.
-    - **Required API Keys (Depending on configured providers):**
-      - `ANTHROPIC_API_KEY`: Your Anthropic API key.
-      - `PERPLEXITY_API_KEY`: Your Perplexity API key.
-      - `OPENAI_API_KEY`: Your OpenAI API key.
-      - `GOOGLE_API_KEY`: Your Google API key.
-      - `MISTRAL_API_KEY`: Your Mistral API key.
-      - `AZURE_OPENAI_API_KEY`: Your Azure OpenAI API key (also requires `AZURE_OPENAI_ENDPOINT`).
-      - `OPENROUTER_API_KEY`: Your OpenRouter API key.
-      - `XAI_API_KEY`: Your X-AI API key.
-    - **Optional Endpoint Overrides:**
-      - **Per-role `baseUrl` in `.taskmasterconfig`:** You can add a `baseUrl` property to any model role (`main`, `research`, `fallback`) to override the default API endpoint for that provider. If omitted, the provider's standard endpoint is used.
-      - `AZURE_OPENAI_ENDPOINT`: Required if using Azure OpenAI key (can also be set as `baseUrl` for the Azure model role).
-      - `OLLAMA_BASE_URL`: Override the default Ollama API URL (Default: `http://localhost:11434/api`).
 
-**Important:** Settings like model ID selections (`main`, `research`, `fallback`), `maxTokens`, `temperature`, `logLevel`, `defaultSubtasks`, `defaultPriority`, and `projectName` are **managed in `.taskmasterconfig`**, not environment variables.
+    - For projects that haven't migrated to the new structure yet.
+    - **Location:** Project root directory.
+    - **Migration:** Use `task-master migrate` to move this to `.taskmaster/config.json`.
+    - **Deprecation:** While still supported, you'll see warnings encouraging migration to the new structure.
+
+## Environment Variables (`.env` file or MCP `env` block - For API Keys Only)
+
+- Used **exclusively** for sensitive API keys and specific endpoint URLs.
+- **Location:**
+  - For CLI usage: Create a `.env` file in your project root.
+  - For MCP/Cursor usage: Configure keys in the `env` section of your `.cursor/mcp.json` file.
+- **Required API Keys (Depending on configured providers):**
+  - `ANTHROPIC_API_KEY`: Your Anthropic API key.
+  - `PERPLEXITY_API_KEY`: Your Perplexity API key.
+  - `OPENAI_API_KEY`: Your OpenAI API key.
+  - `GOOGLE_API_KEY`: Your Google API key (also used for Vertex AI provider).
+  - `MISTRAL_API_KEY`: Your Mistral API key.
+  - `AZURE_OPENAI_API_KEY`: Your Azure OpenAI API key (also requires `AZURE_OPENAI_ENDPOINT`).
+  - `OPENROUTER_API_KEY`: Your OpenRouter API key.
+  - `XAI_API_KEY`: Your X-AI API key.
+- **Optional Endpoint Overrides:**
+  - **Per-role `baseURL` in `.taskmasterconfig`:** You can add a `baseURL` property to any model role (`main`, `research`, `fallback`) to override the default API endpoint for that provider. If omitted, the provider's standard endpoint is used.
+  - **Environment Variable Overrides (`<PROVIDER>_BASE_URL`):** For greater flexibility, especially with third-party services, you can set an environment variable like `OPENAI_BASE_URL` or `MISTRAL_BASE_URL`. This will override any `baseURL` set in the configuration file for that provider. This is the recommended way to connect to OpenAI-compatible APIs.
+  - `AZURE_OPENAI_ENDPOINT`: Required if using Azure OpenAI key (can also be set as `baseURL` for the Azure model role).
+  - `OLLAMA_BASE_URL`: Override the default Ollama API URL (Default: `http://localhost:11434/api`).
+  - `VERTEX_PROJECT_ID`: Your Google Cloud project ID for Vertex AI. Required when using the 'vertex' provider.
+  - `VERTEX_LOCATION`: Google Cloud region for Vertex AI (e.g., 'us-central1'). Default is 'us-central1'.
+  - `GOOGLE_APPLICATION_CREDENTIALS`: Path to service account credentials JSON file for Google Cloud auth (alternative to API key for Vertex AI).
+
+**Important:** Settings like model ID selections (`main`, `research`, `fallback`), `maxTokens`, `temperature`, `logLevel`, `defaultSubtasks`, `defaultPriority`, and `projectName` are **managed in `.taskmaster/config.json`** (or `.taskmasterconfig` for unmigrated projects), not environment variables.
+
+## Tagged Task Lists Configuration (v0.17+)
+
+Taskmaster includes a tagged task lists system for multi-context task management.
+
+### Global Tag Settings
+
+```json
+"global": {
+  "defaultTag": "master"
+}
+```
+
+- **`defaultTag`** (string): Default tag context for new operations (default: "master")
+
+### Git Integration
+
+Task Master provides manual git integration through the `--from-branch` option:
+
+- **Manual Tag Creation**: Use `task-master add-tag --from-branch` to create a tag based on your current git branch name
+- **User Control**: No automatic tag switching - you control when and how tags are created
+- **Flexible Workflow**: Supports any git workflow without imposing rigid branch-tag mappings
+
+## State Management File
+
+Taskmaster uses `.taskmaster/state.json` to track tagged system runtime information:
+
+```json
+{
+  "currentTag": "master",
+  "lastSwitched": "2025-06-11T20:26:12.598Z",
+  "migrationNoticeShown": true
+}
+```
+
+- **`currentTag`**: Currently active tag context
+- **`lastSwitched`**: Timestamp of last tag switch
+- **`migrationNoticeShown`**: Whether migration notice has been displayed
+
+This file is automatically created during tagged system migration and should not be manually edited.
 
 ## Example `.env` File (for API Keys)
 
 ```
-# Required API keys for providers configured in .taskmasterconfig
+# Required API keys for providers configured in .taskmaster/config.json
 ANTHROPIC_API_KEY=sk-ant-api03-your-key-here
 PERPLEXITY_API_KEY=pplx-your-key-here
 # OPENAI_API_KEY=sk-your-key-here
@@ -76,16 +132,23 @@ PERPLEXITY_API_KEY=pplx-your-key-here
 # etc.
 
 # Optional Endpoint Overrides
+# Use a specific provider's base URL, e.g., for an OpenAI-compatible API
+# OPENAI_BASE_URL=https://api.third-party.com/v1
+#
 # AZURE_OPENAI_ENDPOINT=https://your-azure-endpoint.openai.azure.com/
 # OLLAMA_BASE_URL=http://custom-ollama-host:11434/api
+
+# Google Vertex AI Configuration (Required if using 'vertex' provider)
+# VERTEX_PROJECT_ID=your-gcp-project-id
 ```
 
 ## Troubleshooting
 
 ### Configuration Errors
 
-- If Task Master reports errors about missing configuration or cannot find `.taskmasterconfig`, run `task-master models --setup` in your project root to create or repair the file.
+- If Task Master reports errors about missing configuration or cannot find the config file, run `task-master models --setup` in your project root to create or repair the file.
-- Ensure API keys are correctly placed in your `.env` file (for CLI) or `.cursor/mcp.json` (for MCP) and are valid for the providers selected in `.taskmasterconfig`.
+- For new projects, config will be created at `.taskmaster/config.json`. For legacy projects, you may want to use `task-master migrate` to move to the new structure.
+- Ensure API keys are correctly placed in your `.env` file (for CLI) or `.cursor/mcp.json` (for MCP) and are valid for the providers selected in your config file.
 
 ### If `task-master init` doesn't respond:
 
@@ -102,3 +165,45 @@ git clone https://github.com/eyaltoledano/claude-task-master.git
 cd claude-task-master
 node scripts/init.js
 ```
+
+## Provider-Specific Configuration
+
+### Google Vertex AI Configuration
+
+Google Vertex AI is Google Cloud's enterprise AI platform and requires specific configuration:
+
+1. **Prerequisites**:
+   - A Google Cloud account with Vertex AI API enabled
+   - Either a Google API key with Vertex AI permissions OR a service account with appropriate roles
+   - A Google Cloud project ID
+2. **Authentication Options**:
+   - **API Key**: Set the `GOOGLE_API_KEY` environment variable
+   - **Service Account**: Set `GOOGLE_APPLICATION_CREDENTIALS` to point to your service account JSON file
+3. **Required Configuration**:
+   - Set `VERTEX_PROJECT_ID` to your Google Cloud project ID
+   - Set `VERTEX_LOCATION` to your preferred Google Cloud region (default: us-central1)
+4. **Example Setup**:
+
+   ```bash
+   # In .env file
+   GOOGLE_API_KEY=AIzaSyXXXXXXXXXXXXXXXXXXXXXXXXX
+   VERTEX_PROJECT_ID=my-gcp-project-123
+   VERTEX_LOCATION=us-central1
+   ```
+
+   Or using service account:
+
+   ```bash
+   # In .env file
+   GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json
+   VERTEX_PROJECT_ID=my-gcp-project-123
+   VERTEX_LOCATION=us-central1
+   ```
+
+5. **In .taskmaster/config.json**:
+   ```json
+   "global": {
+     "vertexProjectId": "my-gcp-project-123",
+     "vertexLocation": "us-central1"
+   }
+   ```

docs/contributor-docs/testing-roo-integration.md

@@ -64,7 +64,7 @@ To manually verify that the Roo files are properly included in the package:
    ls -la .roo/rules
    ls -la .roo/rules-architect
    ls -la .roo/rules-ask
-   ls -la .roo/rules-boomerang
+   ls -la .roo/rules-orchestrator
    ls -la .roo/rules-code
    ls -la .roo/rules-debug
    ls -la .roo/rules-test

docs/examples.md

@@ -5,7 +5,7 @@ Here are some common interactions with Cursor AI when using Task Master:
 ## Starting a new project
 
 ```
-I've just initialized a new project with Claude Task Master. I have a PRD at scripts/prd.txt.
+I've just initialized a new project with Claude Task Master. I have a PRD at .taskmaster/docs/prd.txt.
 Can you help me parse it and set up the initial tasks?
 ```
 
@@ -21,6 +21,20 @@ What's the next task I should work on? Please consider dependencies and prioriti
 I'd like to implement task 4. Can you help me understand what needs to be done and how to approach it?
 ```
 
+## Viewing multiple tasks
+
+```
+Can you show me tasks 1, 3, and 5 so I can understand their relationship?
+```
+
+```
+I need to see the status of tasks 44, 55, and their subtasks. Can you show me those?
+```
+
+```
+Show me tasks 10, 12, and 15 and give me some batch actions I can perform on them.
+```
+
 ## Managing subtasks
 
 ```
@@ -30,7 +44,7 @@ I need to regenerate the subtasks for task 3 with a different approach. Can you
 ## Handling changes
 
 ```
-We've decided to use MongoDB instead of PostgreSQL. Can you update all future tasks to reflect this change?
+I've decided to use MongoDB instead of PostgreSQL. Can you update all future tasks to reflect this change?
 ```
 
 ## Completing work
@@ -40,6 +54,34 @@ I've finished implementing the authentication system described in task 2. All te
 Please mark it as complete and tell me what I should work on next.
 ```
 
+## Reorganizing tasks
+
+```
+I think subtask 5.2 would fit better as part of task 7. Can you move it there?
+```
+
+(Agent runs: `task-master move --from=5.2 --to=7.3`)
+
+```
+Task 8 should actually be a subtask of task 4. Can you reorganize this?
+```
+
+(Agent runs: `task-master move --from=8 --to=4.1`)
+
+```
+I just merged the main branch and there's a conflict in tasks.json. My teammates created tasks 10-15 on their branch while I created tasks 10-12 on my branch. Can you help me resolve this by moving my tasks?
+```
+
+(Agent runs:
+
+```bash
+task-master move --from=10 --to=16
+task-master move --from=11 --to=17
+task-master move --from=12 --to=18
+```
+
+)
+
 ## Analyzing complexity
 
 ```
@@ -81,3 +123,136 @@ Please add a new task to implement user profile image uploads using Cloudinary,
 ```
 
 (Agent runs: `task-master add-task --prompt="Implement user profile image uploads using Cloudinary" --research`)
+
+## Research-Driven Development
+
+### Getting Fresh Information
+
+```
+Research the latest best practices for implementing JWT authentication in Node.js applications.
+```
+
+(Agent runs: `task-master research "Latest best practices for JWT authentication in Node.js"`)
+
+### Research with Project Context
+
+```
+I'm working on task 15 which involves API optimization. Can you research current best practices for our specific implementation?
+```
+
+(Agent runs: `task-master research "API optimization best practices" --id=15 --files=src/api.js`)
+
+### Research Before Implementation
+
+```
+Before I implement task 8 (React Query integration), can you research the latest React Query v5 patterns and any breaking changes?
+```
+
+(Agent runs: `task-master research "React Query v5 patterns and breaking changes" --id=8`)
+
+### Research and Update Pattern
+
+```
+Research the latest security recommendations for Express.js applications and update our authentication task with the findings.
+```
+
+(Agent runs:
+
+1. `task-master research "Latest Express.js security recommendations" --id=12`
+2. `task-master update-subtask --id=12.3 --prompt="Updated with latest security findings: [research results]"`)
+
+### Research for Debugging
+
+```
+I'm having issues with our WebSocket implementation in task 20. Can you research common WebSocket problems and solutions?
+```
+
+(Agent runs: `task-master research "Common WebSocket implementation problems and solutions" --id=20 --files=src/websocket.js`)
+
+### Research Technology Comparisons
+
+```
+We need to choose between Redis and Memcached for caching. Can you research the current recommendations for our use case?
+```
+
+(Agent runs: `task-master research "Redis vs Memcached 2024 comparison for session caching" --tree`)
+
+## Git Integration and Tag Management
+
+### Creating Tags for Feature Branches
+
+```
+I'm starting work on a new feature branch for user authentication. Can you create a matching task tag?
+```
+
+(Agent runs: `task-master add-tag --from-branch`)
+
+### Creating Named Tags
+
+```
+Create a new tag called 'api-v2' for our API redesign work.
+```
+
+(Agent runs: `task-master add-tag api-v2 --description="API v2 redesign tasks"`)
+
+### Switching Tag Contexts
+
+```
+Switch to the 'testing' tag so I can work on QA tasks.
+```
+
+(Agent runs: `task-master use-tag testing`)
+
+### Copying Tasks Between Tags
+
+```
+I need to copy the current tasks to a new 'hotfix' tag for urgent fixes.
+```
+
+(Agent runs: `task-master add-tag hotfix --copy-from-current --description="Urgent hotfix tasks"`)
+
+### Managing Multiple Contexts
+
+```
+Show me all available tags and their current status.
+```
+
+(Agent runs: `task-master tags --show-metadata`)
+
+### Tag Cleanup
+
+```
+I've finished the 'user-auth' feature and merged the branch. Can you clean up the tag?
+```
+
+(Agent runs: `task-master delete-tag user-auth`)
+
+### Working with Tag-Specific Tasks
+
+```
+List all tasks in the 'api-v2' tag context.
+```
+
+(Agent runs: `task-master use-tag api-v2` then `task-master list`)
+
+### Branch-Based Development Workflow
+
+```
+I'm switching to work on the 'feature/payments' branch. Can you set up the task context for this?
+```
+
+(Agent runs:
+1. `git checkout feature/payments`
+2. `task-master add-tag --from-branch --description="Payment system implementation"`
+3. `task-master list` to show tasks in the new context)
+
+### Parallel Feature Development
+
+```
+I need to work on both authentication and payment features simultaneously. How should I organize the tasks?
+```
+
+(Agent suggests and runs:
+1. `task-master add-tag auth --description="Authentication feature tasks"`
+2. `task-master add-tag payments --description="Payment system tasks"`
+3. `task-master use-tag auth` to start with authentication work)

docs/examples/claude-code-usage.md

@@ -0,0 +1,169 @@
+# Claude Code Provider Usage Example
+
+The Claude Code provider allows you to use Claude models through the Claude Code CLI without requiring an API key.
+
+## Configuration
+
+To use the Claude Code provider, update your `.taskmaster/config.json`:
+
+```json
+{
+  "models": {
+    "main": {
+      "provider": "claude-code",
+      "modelId": "sonnet",
+      "maxTokens": 64000,
+      "temperature": 0.2
+    },
+    "research": {
+      "provider": "claude-code",
+      "modelId": "opus",
+      "maxTokens": 32000,
+      "temperature": 0.1
+    },
+    "fallback": {
+      "provider": "claude-code",
+      "modelId": "sonnet",
+      "maxTokens": 64000,
+      "temperature": 0.2
+    }
+  }
+}
+```
+
+## Available Models
+
+- `opus` - Claude Opus model (SWE score: 0.725)
+- `sonnet` - Claude Sonnet model (SWE score: 0.727)
+
+## Usage
+
+Once configured, you can use Claude Code with all Task Master commands:
+
+```bash
+# Generate tasks from a PRD
+task-master parse-prd --input=prd.txt
+
+# Analyze project complexity
+task-master analyze-complexity
+
+# Show the next task to work on
+task-master next
+
+# View a specific task
+task-master show task-001
+
+# Update task status
+task-master set-status --id=task-001 --status=in-progress
+```
+
+## Requirements
+
+1. Claude Code CLI must be installed and authenticated on your system
+2. Install the optional `@anthropic-ai/claude-code` package if you enable this provider:
+   ```bash
+   npm install @anthropic-ai/claude-code
+   ```
+3. No API key is required in your environment variables or MCP configuration
+
+## Advanced Settings
+
+The Claude Code SDK supports additional settings that provide fine-grained control over Claude's behavior. While these settings are implemented in the underlying SDK (`src/ai-providers/custom-sdk/claude-code/`), they are not currently exposed through Task Master's standard API due to architectural constraints.
+
+### Supported Settings
+
+```javascript
+const settings = {
+  // Maximum conversation turns Claude can make in a single request
+  maxTurns: 5,
+  
+  // Custom system prompt to override Claude Code's default behavior
+  customSystemPrompt: "You are a helpful assistant focused on code quality",
+  
+  // Permission mode for file system operations
+  permissionMode: 'default', // Options: 'default', 'restricted', 'permissive'
+  
+  // Explicitly allow only certain tools
+  allowedTools: ['Read', 'LS'], // Claude can only read files and list directories
+  
+  // Explicitly disallow certain tools
+  disallowedTools: ['Write', 'Edit'], // Prevent Claude from modifying files
+  
+  // MCP servers for additional tool integrations
+  mcpServers: []
+};
+```
+
+### Current Limitations
+
+Task Master uses a standardized `BaseAIProvider` interface that only passes through common parameters (modelId, messages, maxTokens, temperature) to maintain consistency across all providers. The Claude Code advanced settings are implemented in the SDK but not accessible through Task Master's high-level commands.
+
+### Future Integration Options
+
+For developers who need to use these advanced settings, there are three potential approaches:
+
+#### Option 1: Extend BaseAIProvider
+Modify the core Task Master architecture to support provider-specific settings:
+
+```javascript
+// In BaseAIProvider
+const result = await generateText({
+  model: client(params.modelId),
+  messages: params.messages,
+  maxTokens: params.maxTokens,
+  temperature: params.temperature,
+  ...params.providerSettings // New: pass through provider-specific settings
+});
+```
+
+#### Option 2: Override Methods in ClaudeCodeProvider
+Create custom implementations that extract and use Claude-specific settings:
+
+```javascript
+// In ClaudeCodeProvider
+async generateText(params) {
+  const { maxTurns, allowedTools, disallowedTools, ...baseParams } = params;
+  
+  const client = this.getClient({
+    ...baseParams,
+    settings: { maxTurns, allowedTools, disallowedTools }
+  });
+  
+  // Continue with generation...
+}
+```
+
+#### Option 3: Direct SDK Usage
+For immediate access to advanced features, developers can use the Claude Code SDK directly:
+
+```javascript
+import { createClaudeCode } from 'task-master-ai/ai-providers/custom-sdk/claude-code';
+
+const claude = createClaudeCode({
+  defaultSettings: {
+    maxTurns: 5,
+    allowedTools: ['Read', 'LS'],
+    disallowedTools: ['Write', 'Edit']
+  }
+});
+
+const model = claude('sonnet');
+const result = await generateText({
+  model,
+  messages: [{ role: 'user', content: 'Analyze this code...' }]
+});
+```
+
+### Why These Settings Matter
+
+- **maxTurns**: Useful for complex refactoring tasks that require multiple iterations
+- **customSystemPrompt**: Allows specializing Claude for specific domains or coding standards
+- **permissionMode**: Critical for security in production environments
+- **allowedTools/disallowedTools**: Enable read-only analysis modes or restrict access to sensitive operations
+- **mcpServers**: Future extensibility for custom tool integrations
+
+## Notes
+
+- The Claude Code provider doesn't track usage costs (shown as 0 in telemetry)
+- Session management is handled automatically for conversation continuity
+- Some AI SDK parameters (temperature, maxTokens) are not supported by Claude Code CLI and will be ignored

docs/migration-guide.md

@@ -0,0 +1,235 @@
+# Migration Guide: New .taskmaster Directory Structure
+
+## Overview
+
+Task Master v0.16.0 introduces a new `.taskmaster/` directory structure to keep your project directories clean and organized. This guide explains the benefits of the new structure and how to migrate existing projects.
+
+## What's New
+
+### Before (Legacy Structure)
+
+```
+your-project/
+├── tasks/                    # Task files
+│   ├── tasks.json
+│   ├── task-1.txt
+│   └── task-2.txt
+├── scripts/                  # PRD and reports
+│   ├── prd.txt
+│   ├── example_prd.txt
+│   └── task-complexity-report.json
+├── .taskmasterconfig         # Configuration
+└── ... (your project files)
+```
+
+### After (New Structure)
+
+```
+your-project/
+├── .taskmaster/              # Consolidated Task Master files
+│   ├── config.json          # Configuration (was .taskmasterconfig)
+│   ├── tasks/               # Task files
+│   │   ├── tasks.json
+│   │   ├── task-1.txt
+│   │   └── task-2.txt
+│   ├── docs/                # Project documentation
+│   │   └── prd.txt
+│   ├── reports/             # Generated reports
+│   │   └── task-complexity-report.json
+│   └── templates/           # Example/template files
+│       └── example_prd.txt
+└── ... (your project files)
+```
+
+## Benefits of the New Structure
+
+✅ **Cleaner Project Root**: No more scattered Task Master files  
+✅ **Better Organization**: Logical separation of tasks, docs, reports, and templates  
+✅ **Hidden by Default**: `.taskmaster/` directory is hidden from most file browsers  
+✅ **Future-Proof**: Centralized location for Task Master extensions  
+✅ **Backward Compatible**: Existing projects continue to work until migrated
+
+## Migration Options
+
+### Option 1: Automatic Migration (Recommended)
+
+Task Master provides a built-in migration command that handles everything automatically:
+
+#### CLI Migration
+
+```bash
+# Dry run to see what would be migrated
+task-master migrate --dry-run
+
+# Perform the migration with backup
+task-master migrate --backup
+
+# Force migration (overwrites existing files)
+task-master migrate --force
+
+# Clean up legacy files after migration
+task-master migrate --cleanup
+```
+
+#### MCP Migration (Cursor/AI Editors)
+
+Ask your AI assistant:
+
+```
+Please migrate my Task Master project to the new .taskmaster directory structure
+```
+
+### Option 2: Manual Migration
+
+If you prefer to migrate manually:
+
+1. **Create the new directory structure:**
+
+   ```bash
+   mkdir -p .taskmaster/{tasks,docs,reports,templates}
+   ```
+
+2. **Move your files:**
+
+   ```bash
+   # Move tasks
+   mv tasks/* .taskmaster/tasks/
+
+   # Move configuration
+   mv .taskmasterconfig .taskmaster/config.json
+
+   # Move PRD and documentation
+   mv scripts/prd.txt .taskmaster/docs/
+   mv scripts/example_prd.txt .taskmaster/templates/
+
+   # Move reports (if they exist)
+   mv scripts/task-complexity-report.json .taskmaster/reports/ 2>/dev/null || true
+   ```
+
+3. **Clean up empty directories:**
+   ```bash
+   rmdir tasks scripts 2>/dev/null || true
+   ```
+
+## What Gets Migrated
+
+The migration process handles these file types:
+
+### Tasks Directory → `.taskmaster/tasks/`
+
+- `tasks.json`
+- Individual task text files (`.txt`)
+
+### Scripts Directory → Multiple Destinations
+
+- **PRD files** → `.taskmaster/docs/`
+  - `prd.txt`, `requirements.txt`, etc.
+- **Example/Template files** → `.taskmaster/templates/`
+  - `example_prd.txt`, template files
+- **Reports** → `.taskmaster/reports/`
+  - `task-complexity-report.json`
+
+### Configuration
+
+- `.taskmasterconfig` → `.taskmaster/config.json`
+
+## After Migration
+
+Once migrated, Task Master will:
+
+✅ **Automatically use** the new directory structure  
+✅ **Show deprecation warnings** when legacy files are detected  
+✅ **Create new files** in the proper locations  
+✅ **Fall back gracefully** to legacy locations if new ones don't exist
+
+### Verification
+
+After migration, verify everything works:
+
+1. **List your tasks:**
+
+   ```bash
+   task-master list
+   ```
+
+2. **Check your configuration:**
+
+   ```bash
+   task-master models
+   ```
+
+3. **Generate new task files:**
+   ```bash
+   task-master generate
+   ```
+
+## Troubleshooting
+
+### Migration Issues
+
+**Q: Migration says "no files to migrate"**  
+A: Your project may already be using the new structure or have no Task Master files to migrate.
+
+**Q: Migration fails with permission errors**  
+A: Ensure you have write permissions in your project directory.
+
+**Q: Some files weren't migrated**  
+A: Check the migration output - some files may not match the expected patterns. You can migrate these manually.
+
+### Working with Legacy Projects
+
+If you're working with an older project that hasn't been migrated:
+
+- Task Master will continue to work with the old structure
+- You'll see deprecation warnings in the output
+- New files will still be created in legacy locations
+- Use the migration command when ready to upgrade
+
+### New Project Initialization
+
+New projects automatically use the new structure:
+
+```bash
+task-master init  # Creates .taskmaster/ structure
+```
+
+## Path Changes for Developers
+
+If you're developing tools or scripts that interact with Task Master files:
+
+### Configuration File
+
+- **Old:** `.taskmasterconfig`
+- **New:** `.taskmaster/config.json`
+- **Fallback:** Task Master checks both locations
+
+### Tasks File
+
+- **Old:** `tasks/tasks.json`
+- **New:** `.taskmaster/tasks/tasks.json`
+- **Fallback:** Task Master checks both locations
+
+### Reports
+
+- **Old:** `scripts/task-complexity-report.json`
+- **New:** `.taskmaster/reports/task-complexity-report.json`
+- **Fallback:** Task Master checks both locations
+
+### PRD Files
+
+- **Old:** `scripts/prd.txt`
+- **New:** `.taskmaster/docs/prd.txt`
+- **Fallback:** Task Master checks both locations
+
+## Need Help?
+
+If you encounter issues during migration:
+
+1. **Check the logs:** Add `--debug` flag for detailed output
+2. **Backup first:** Always use `--backup` option for safety
+3. **Test with dry-run:** Use `--dry-run` to preview changes
+4. **Ask for help:** Use our Discord community or GitHub issues
+
+---
+
+_This migration guide applies to Task Master v0.15.x and later. For older versions, please upgrade to the latest version first._

docs/models.md

@@ -0,0 +1,137 @@
+# Available Models as of June 20, 2025
+
+## Main Models
+
+| Provider    | Model Name                                     | SWE Score | Input Cost | Output Cost |
+| ----------- | ---------------------------------------------- | --------- | ---------- | ----------- |
+| bedrock     | us.anthropic.claude-3-7-sonnet-20250219-v1:0   | 0.623     | 3          | 15          |
+| anthropic   | claude-sonnet-4-20250514                       | 0.727     | 3          | 15          |
+| anthropic   | claude-opus-4-20250514                         | 0.725     | 15         | 75          |
+| anthropic   | claude-3-7-sonnet-20250219                     | 0.623     | 3          | 15          |
+| anthropic   | claude-3-5-sonnet-20241022                     | 0.49      | 3          | 15          |
+| openai      | gpt-4o                                         | 0.332     | 2.5        | 10          |
+| openai      | o1                                             | 0.489     | 15         | 60          |
+| openai      | o3                                             | 0.5       | 2          | 8           |
+| openai      | o3-mini                                        | 0.493     | 1.1        | 4.4         |
+| openai      | o4-mini                                        | 0.45      | 1.1        | 4.4         |
+| openai      | o1-mini                                        | 0.4       | 1.1        | 4.4         |
+| openai      | o1-pro                                         | —         | 150        | 600         |
+| openai      | gpt-4-5-preview                                | 0.38      | 75         | 150         |
+| openai      | gpt-4-1-mini                                   | —         | 0.4        | 1.6         |
+| openai      | gpt-4-1-nano                                   | —         | 0.1        | 0.4         |
+| openai      | gpt-4o-mini                                    | 0.3       | 0.15       | 0.6         |
+| google      | gemini-2.5-pro-preview-05-06                   | 0.638     | —          | —           |
+| google      | gemini-2.5-pro-preview-03-25                   | 0.638     | —          | —           |
+| google      | gemini-2.5-flash-preview-04-17                 | 0.604     | —          | —           |
+| google      | gemini-2.0-flash                               | 0.518     | 0.15       | 0.6         |
+| google      | gemini-2.0-flash-lite                          | —         | —          | —           |
+| perplexity  | sonar-pro                                      | —         | 3          | 15          |
+| perplexity  | sonar-reasoning-pro                            | 0.211     | 2          | 8           |
+| perplexity  | sonar-reasoning                                | 0.211     | 1          | 5           |
+| xai         | grok-3                                         | —         | 3          | 15          |
+| xai         | grok-3-fast                                    | —         | 5          | 25          |
+| ollama      | devstral:latest                                | —         | 0          | 0           |
+| ollama      | qwen3:latest                                   | —         | 0          | 0           |
+| ollama      | qwen3:14b                                      | —         | 0          | 0           |
+| ollama      | qwen3:32b                                      | —         | 0          | 0           |
+| ollama      | mistral-small3.1:latest                        | —         | 0          | 0           |
+| ollama      | llama3.3:latest                                | —         | 0          | 0           |
+| ollama      | phi4:latest                                    | —         | 0          | 0           |
+| openrouter  | google/gemini-2.5-flash-preview-05-20          | —         | 0.15       | 0.6         |
+| openrouter  | google/gemini-2.5-flash-preview-05-20:thinking | —         | 0.15       | 3.5         |
+| openrouter  | google/gemini-2.5-pro-exp-03-25                | —         | 0          | 0           |
+| openrouter  | deepseek/deepseek-chat-v3-0324:free            | —         | 0          | 0           |
+| openrouter  | deepseek/deepseek-chat-v3-0324                 | —         | 0.27       | 1.1         |
+| openrouter  | openai/gpt-4.1                                 | —         | 2          | 8           |
+| openrouter  | openai/gpt-4.1-mini                            | —         | 0.4        | 1.6         |
+| openrouter  | openai/gpt-4.1-nano                            | —         | 0.1        | 0.4         |
+| openrouter  | openai/o3                                      | —         | 10         | 40          |
+| openrouter  | openai/codex-mini                              | —         | 1.5        | 6           |
+| openrouter  | openai/gpt-4o-mini                             | —         | 0.15       | 0.6         |
+| openrouter  | openai/o4-mini                                 | 0.45      | 1.1        | 4.4         |
+| openrouter  | openai/o4-mini-high                            | —         | 1.1        | 4.4         |
+| openrouter  | openai/o1-pro                                  | —         | 150        | 600         |
+| openrouter  | meta-llama/llama-3.3-70b-instruct              | —         | 120        | 600         |
+| openrouter  | meta-llama/llama-4-maverick                    | —         | 0.18       | 0.6         |
+| openrouter  | meta-llama/llama-4-scout                       | —         | 0.08       | 0.3         |
+| openrouter  | qwen/qwen-max                                  | —         | 1.6        | 6.4         |
+| openrouter  | qwen/qwen-turbo                                | —         | 0.05       | 0.2         |
+| openrouter  | qwen/qwen3-235b-a22b                           | —         | 0.14       | 2           |
+| openrouter  | mistralai/mistral-small-3.1-24b-instruct:free  | —         | 0          | 0           |
+| openrouter  | mistralai/mistral-small-3.1-24b-instruct       | —         | 0.1        | 0.3         |
+| openrouter  | mistralai/devstral-small                       | —         | 0.1        | 0.3         |
+| openrouter  | mistralai/mistral-nemo                         | —         | 0.03       | 0.07        |
+| openrouter  | thudm/glm-4-32b:free                           | —         | 0          | 0           |
+| claude-code | opus                                           | 0.725     | 0          | 0           |
+| claude-code | sonnet                                         | 0.727     | 0          | 0           |
+
+## Research Models
+
+| Provider    | Model Name                 | SWE Score | Input Cost | Output Cost |
+| ----------- | -------------------------- | --------- | ---------- | ----------- |
+| bedrock     | us.deepseek.r1-v1:0        | —         | 1.35       | 5.4         |
+| openai      | gpt-4o-search-preview      | 0.33      | 2.5        | 10          |
+| openai      | gpt-4o-mini-search-preview | 0.3       | 0.15       | 0.6         |
+| perplexity  | sonar-pro                  | —         | 3          | 15          |
+| perplexity  | sonar                      | —         | 1          | 1           |
+| perplexity  | deep-research              | 0.211     | 2          | 8           |
+| perplexity  | sonar-reasoning-pro        | 0.211     | 2          | 8           |
+| perplexity  | sonar-reasoning            | 0.211     | 1          | 5           |
+| xai         | grok-3                     | —         | 3          | 15          |
+| xai         | grok-3-fast                | —         | 5          | 25          |
+| claude-code | opus                       | 0.725     | 0          | 0           |
+| claude-code | sonnet                     | 0.727     | 0          | 0           |
+
+## Fallback Models
+
+| Provider    | Model Name                                     | SWE Score | Input Cost | Output Cost |
+| ----------- | ---------------------------------------------- | --------- | ---------- | ----------- |
+| bedrock     | us.anthropic.claude-3-7-sonnet-20250219-v1:0   | 0.623     | 3          | 15          |
+| anthropic   | claude-sonnet-4-20250514                       | 0.727     | 3          | 15          |
+| anthropic   | claude-opus-4-20250514                         | 0.725     | 15         | 75          |
+| anthropic   | claude-3-7-sonnet-20250219                     | 0.623     | 3          | 15          |
+| anthropic   | claude-3-5-sonnet-20241022                     | 0.49      | 3          | 15          |
+| openai      | gpt-4o                                         | 0.332     | 2.5        | 10          |
+| openai      | o3                                             | 0.5       | 2          | 8           |
+| openai      | o4-mini                                        | 0.45      | 1.1        | 4.4         |
+| google      | gemini-2.5-pro-preview-05-06                   | 0.638     | —          | —           |
+| google      | gemini-2.5-pro-preview-03-25                   | 0.638     | —          | —           |
+| google      | gemini-2.5-flash-preview-04-17                 | 0.604     | —          | —           |
+| google      | gemini-2.0-flash                               | 0.518     | 0.15       | 0.6         |
+| google      | gemini-2.0-flash-lite                          | —         | —          | —           |
+| perplexity  | sonar-reasoning-pro                            | 0.211     | 2          | 8           |
+| perplexity  | sonar-reasoning                                | 0.211     | 1          | 5           |
+| xai         | grok-3                                         | —         | 3          | 15          |
+| xai         | grok-3-fast                                    | —         | 5          | 25          |
+| ollama      | devstral:latest                                | —         | 0          | 0           |
+| ollama      | qwen3:latest                                   | —         | 0          | 0           |
+| ollama      | qwen3:14b                                      | —         | 0          | 0           |
+| ollama      | qwen3:32b                                      | —         | 0          | 0           |
+| ollama      | mistral-small3.1:latest                        | —         | 0          | 0           |
+| ollama      | llama3.3:latest                                | —         | 0          | 0           |
+| ollama      | phi4:latest                                    | —         | 0          | 0           |
+| openrouter  | google/gemini-2.5-flash-preview-05-20          | —         | 0.15       | 0.6         |
+| openrouter  | google/gemini-2.5-flash-preview-05-20:thinking | —         | 0.15       | 3.5         |
+| openrouter  | google/gemini-2.5-pro-exp-03-25                | —         | 0          | 0           |
+| openrouter  | deepseek/deepseek-chat-v3-0324:free            | —         | 0          | 0           |
+| openrouter  | openai/gpt-4.1                                 | —         | 2          | 8           |
+| openrouter  | openai/gpt-4.1-mini                            | —         | 0.4        | 1.6         |
+| openrouter  | openai/gpt-4.1-nano                            | —         | 0.1        | 0.4         |
+| openrouter  | openai/o3                                      | —         | 10         | 40          |
+| openrouter  | openai/codex-mini                              | —         | 1.5        | 6           |
+| openrouter  | openai/gpt-4o-mini                             | —         | 0.15       | 0.6         |
+| openrouter  | openai/o4-mini                                 | 0.45      | 1.1        | 4.4         |
+| openrouter  | openai/o4-mini-high                            | —         | 1.1        | 4.4         |
+| openrouter  | openai/o1-pro                                  | —         | 150        | 600         |
+| openrouter  | meta-llama/llama-3.3-70b-instruct              | —         | 120        | 600         |
+| openrouter  | meta-llama/llama-4-maverick                    | —         | 0.18       | 0.6         |
+| openrouter  | meta-llama/llama-4-scout                       | —         | 0.08       | 0.3         |
+| openrouter  | qwen/qwen-max                                  | —         | 1.6        | 6.4         |
+| openrouter  | qwen/qwen-turbo                                | —         | 0.05       | 0.2         |
+| openrouter  | qwen/qwen3-235b-a22b                           | —         | 0.14       | 2           |
+| openrouter  | mistralai/mistral-small-3.1-24b-instruct:free  | —         | 0          | 0           |
+| openrouter  | mistralai/mistral-small-3.1-24b-instruct       | —         | 0.1        | 0.3         |
+| openrouter  | mistralai/mistral-nemo                         | —         | 0.03       | 0.07        |
+| openrouter  | thudm/glm-4-32b:free                           | —         | 0          | 0           |
+| claude-code | opus                                           | 0.725     | 0          | 0           |
+| claude-code | sonnet                                         | 0.727     | 0          | 0           |

docs/scripts/models-json-to-markdown.js

@@ -0,0 +1,131 @@
+import fs from 'fs';
+import path from 'path';
+import { fileURLToPath } from 'url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = path.dirname(__filename);
+
+const supportedModelsPath = path.join(
+	__dirname,
+	'..',
+	'modules',
+	'supported-models.json'
+);
+const outputMarkdownPath = path.join(
+	__dirname,
+	'..',
+	'..',
+	'docs',
+	'models.md'
+);
+
+function formatCost(cost) {
+	if (cost === null || cost === undefined) {
+		return '—';
+	}
+	return cost;
+}
+
+function formatSweScore(score) {
+	if (score === null || score === undefined || score === 0) {
+		return '—';
+	}
+	return score.toString();
+}
+
+function generateMarkdownTable(title, models) {
+	if (!models || models.length === 0) {
+		return `## ${title}\n\nNo models in this category.\n\n`;
+	}
+	let table = `## ${title}\n\n`;
+	table += '| Provider | Model Name | SWE Score | Input Cost | Output Cost |\n';
+	table += '|---|---|---|---|---|\n';
+	models.forEach((model) => {
+		table += `| ${model.provider} | ${model.modelName} | ${formatSweScore(model.sweScore)} | ${formatCost(model.inputCost)} | ${formatCost(model.outputCost)} |\n`;
+	});
+	table += '\n';
+	return table;
+}
+
+function main() {
+	try {
+		const correctSupportedModelsPath = path.join(
+			__dirname,
+			'..',
+			'..',
+			'scripts',
+			'modules',
+			'supported-models.json'
+		);
+		const correctOutputMarkdownPath = path.join(__dirname, '..', 'models.md');
+
+		const supportedModelsContent = fs.readFileSync(
+			correctSupportedModelsPath,
+			'utf8'
+		);
+		const supportedModels = JSON.parse(supportedModelsContent);
+
+		const mainModels = [];
+		const researchModels = [];
+		const fallbackModels = [];
+
+		for (const provider in supportedModels) {
+			if (Object.hasOwnProperty.call(supportedModels, provider)) {
+				const models = supportedModels[provider];
+				models.forEach((model) => {
+					const modelEntry = {
+						provider: provider,
+						modelName: model.id,
+						sweScore: model.swe_score,
+						inputCost: model.cost_per_1m_tokens
+							? model.cost_per_1m_tokens.input
+							: null,
+						outputCost: model.cost_per_1m_tokens
+							? model.cost_per_1m_tokens.output
+							: null
+					};
+
+					if (model.allowed_roles.includes('main')) {
+						mainModels.push(modelEntry);
+					}
+					if (model.allowed_roles.includes('research')) {
+						researchModels.push(modelEntry);
+					}
+					if (model.allowed_roles.includes('fallback')) {
+						fallbackModels.push(modelEntry);
+					}
+				});
+			}
+		}
+
+		const date = new Date();
+		const monthNames = [
+			'January',
+			'February',
+			'March',
+			'April',
+			'May',
+			'June',
+			'July',
+			'August',
+			'September',
+			'October',
+			'November',
+			'December'
+		];
+		const formattedDate = `${monthNames[date.getMonth()]} ${date.getDate()}, ${date.getFullYear()}`;
+
+		let markdownContent = `# Available Models as of ${formattedDate}\n\n`;
+		markdownContent += generateMarkdownTable('Main Models', mainModels);
+		markdownContent += generateMarkdownTable('Research Models', researchModels);
+		markdownContent += generateMarkdownTable('Fallback Models', fallbackModels);
+
+		fs.writeFileSync(correctOutputMarkdownPath, markdownContent, 'utf8');
+		console.log(`Successfully updated ${correctOutputMarkdownPath}`);
+	} catch (error) {
+		console.error('Error transforming models.json to models.md:', error);
+		process.exit(1);
+	}
+}
+
+main();

docs/task-structure.md

@@ -137,3 +137,290 @@ The `show` command:
 8. **Communicate context to the agent**: When asking the Cursor agent to help with a task, provide context about what you're trying to achieve.
 
 9. **Validate dependencies**: Periodically run the validate-dependencies command to check for invalid or circular dependencies.
+
+# Task Structure Documentation
+
+Task Master uses a structured JSON format to organize and manage tasks. As of version 0.16.2, Task Master introduces **Tagged Task Lists** for multi-context task management while maintaining full backward compatibility.
+
+## Tagged Task Lists System
+
+Task Master now organizes tasks into separate contexts called **tags**. This enables working across multiple contexts such as different branches, environments, or project phases without conflicts.
+
+### Data Structure Overview
+
+**Tagged Format (Current)**:
+
+```json
+{
+  "master": {
+    "tasks": [
+      { "id": 1, "title": "Setup API", "status": "pending", ... }
+    ]
+  },
+  "feature-branch": {
+    "tasks": [
+      { "id": 1, "title": "New Feature", "status": "pending", ... }
+    ]
+  }
+}
+```
+
+**Legacy Format (Automatically Migrated)**:
+
+```json
+{
+  "tasks": [
+    { "id": 1, "title": "Setup API", "status": "pending", ... }
+  ]
+}
+```
+
+### Tag-based Task Lists (v0.17+) and Compatibility
+
+- **Seamless Migration**: Existing `tasks.json` files are automatically migrated to use a "master" tag
+- **Zero Disruption**: All existing commands continue to work exactly as before
+- **Backward Compatibility**: Existing workflows remain unchanged
+- **Silent Process**: Migration happens transparently on first use with a friendly notification
+
+## Core Task Properties
+
+Each task within a tag context contains the following properties:
+
+### Required Properties
+
+- **`id`** (number): Unique identifier within the tag context
+
+  ```json
+  "id": 1
+  ```
+
+- **`title`** (string): Brief, descriptive title
+
+  ```json
+  "title": "Implement user authentication"
+  ```
+
+- **`description`** (string): Concise summary of what the task involves
+
+  ```json
+  "description": "Create a secure authentication system using JWT tokens"
+  ```
+
+- **`status`** (string): Current state of the task
+  - Valid values: `"pending"`, `"in-progress"`, `"done"`, `"review"`, `"deferred"`, `"cancelled"`
+  ```json
+  "status": "pending"
+  ```
+
+### Optional Properties
+
+- **`dependencies`** (array): IDs of prerequisite tasks that must be completed first
+
+  ```json
+  "dependencies": [2, 3]
+  ```
+
+- **`priority`** (string): Importance level
+
+  - Valid values: `"high"`, `"medium"`, `"low"`
+  - Default: `"medium"`
+
+  ```json
+  "priority": "high"
+  ```
+
+- **`details`** (string): In-depth implementation instructions
+
+  ```json
+  "details": "Use GitHub OAuth client ID/secret, handle callback, set session token"
+  ```
+
+- **`testStrategy`** (string): Verification approach
+
+  ```json
+  "testStrategy": "Deploy and call endpoint to confirm authentication flow"
+  ```
+
+- **`subtasks`** (array): List of smaller, more specific tasks
+  ```json
+  "subtasks": [
+    {
+      "id": 1,
+      "title": "Configure OAuth",
+      "description": "Set up OAuth configuration",
+      "status": "pending",
+      "dependencies": [],
+      "details": "Configure GitHub OAuth app and store credentials"
+    }
+  ]
+  ```
+
+## Subtask Structure
+
+Subtasks follow a similar structure to main tasks but with some differences:
+
+### Subtask Properties
+
+- **`id`** (number): Unique identifier within the parent task
+- **`title`** (string): Brief, descriptive title
+- **`description`** (string): Concise summary of the subtask
+- **`status`** (string): Current state (same values as main tasks)
+- **`dependencies`** (array): Can reference other subtasks or main task IDs
+- **`details`** (string): Implementation instructions and notes
+
+### Subtask Example
+
+```json
+{
+  "id": 2,
+  "title": "Handle OAuth callback",
+  "description": "Process the OAuth callback and extract user data",
+  "status": "pending",
+  "dependencies": [1],
+  "details": "Parse callback parameters, exchange code for token, fetch user profile"
+}
+```
+
+## Complete Example
+
+Here's a complete example showing the tagged task structure:
+
+```json
+{
+  "master": {
+    "tasks": [
+      {
+        "id": 1,
+        "title": "Setup Express Server",
+        "description": "Initialize and configure Express.js server with middleware",
+        "status": "done",
+        "dependencies": [],
+        "priority": "high",
+        "details": "Create Express app with CORS, body parser, and error handling",
+        "testStrategy": "Start server and verify health check endpoint responds",
+        "subtasks": [
+          {
+            "id": 1,
+            "title": "Initialize npm project",
+            "description": "Set up package.json and install dependencies",
+            "status": "done",
+            "dependencies": [],
+            "details": "Run npm init, install express, cors, body-parser"
+          },
+          {
+            "id": 2,
+            "title": "Configure middleware",
+            "description": "Set up CORS and body parsing middleware",
+            "status": "done",
+            "dependencies": [1],
+            "details": "Add app.use() calls for cors() and express.json()"
+          }
+        ]
+      },
+      {
+        "id": 2,
+        "title": "Implement user authentication",
+        "description": "Create secure authentication system",
+        "status": "pending",
+        "dependencies": [1],
+        "priority": "high",
+        "details": "Use JWT tokens for session management",
+        "testStrategy": "Test login/logout flow with valid and invalid credentials",
+        "subtasks": []
+      }
+    ]
+  },
+  "feature-auth": {
+    "tasks": [
+      {
+        "id": 1,
+        "title": "OAuth Integration",
+        "description": "Add OAuth authentication support",
+        "status": "pending",
+        "dependencies": [],
+        "priority": "medium",
+        "details": "Integrate with GitHub OAuth for user authentication",
+        "testStrategy": "Test OAuth flow with GitHub account",
+        "subtasks": []
+      }
+    ]
+  }
+}
+```
+
+## Tag Context Management
+
+### Current Tag Resolution
+
+Task Master automatically determines the current tag context based on:
+
+1. **State Configuration**: Current tag stored in `.taskmaster/state.json`
+2. **Default Fallback**: "master" tag when no context is specified
+3. **Future Enhancement**: Git branch-based tag switching (Part 2)
+
+### Tag Isolation
+
+- **Context Separation**: Tasks in different tags are completely isolated
+- **Independent Numbering**: Each tag has its own task ID sequence starting from 1
+- **Parallel Development**: Multiple team members can work on separate tags without conflicts
+
+## Data Validation
+
+Task Master validates the following aspects of task data:
+
+### Required Validations
+
+- **Unique IDs**: Task IDs must be unique within each tag context
+- **Valid Status**: Status values must be from the allowed set
+- **Dependency References**: Dependencies must reference existing task IDs within the same tag
+- **Subtask IDs**: Subtask IDs must be unique within their parent task
+
+### Optional Validations
+
+- **Circular Dependencies**: System detects and prevents circular dependency chains
+- **Priority Values**: Priority must be one of the allowed values if specified
+- **Data Types**: All properties must match their expected data types
+
+## File Generation
+
+Task Master can generate individual markdown files for each task based on the JSON structure. These files include:
+
+- **Task Overview**: ID, title, status, dependencies
+- **Tag Context**: Which tag the task belongs to
+- **Implementation Details**: Full task details and test strategy
+- **Subtask Breakdown**: All subtasks with their current status
+- **Dependency Status**: Visual indicators showing which dependencies are complete
+
+## Migration Process
+
+When Task Master encounters a legacy format `tasks.json` file:
+
+1. **Detection**: Automatically detects `{"tasks": [...]}` format
+2. **Transformation**: Converts to `{"master": {"tasks": [...]}}` format
+3. **Configuration**: Updates `.taskmaster/config.json` with tagged system settings
+4. **State Creation**: Creates `.taskmaster/state.json` for tag management
+5. **Notification**: Shows one-time friendly notice about the new system
+6. **Preservation**: All existing task data is preserved exactly as-is
+
+## Best Practices
+
+### Task Organization
+
+- **Logical Grouping**: Use tags to group related tasks (e.g., by feature, branch, or milestone)
+- **Clear Titles**: Use descriptive titles that explain the task's purpose
+- **Proper Dependencies**: Define dependencies to ensure correct execution order
+- **Detailed Instructions**: Include sufficient detail in the `details` field for implementation
+
+### Tag Management
+
+- **Meaningful Names**: Use descriptive tag names that reflect their purpose
+- **Consistent Naming**: Establish naming conventions for tags (e.g., branch names, feature names)
+- **Context Switching**: Be aware of which tag context you're working in
+- **Isolation Benefits**: Leverage tag isolation to prevent merge conflicts
+
+### Subtask Design
+
+- **Granular Tasks**: Break down complex tasks into manageable subtasks
+- **Clear Dependencies**: Define subtask dependencies to show implementation order
+- **Implementation Notes**: Use subtask details to track progress and decisions
+- **Status Tracking**: Keep subtask status updated as work progresses

docs/tutorial.md

@@ -20,22 +20,22 @@ npm i -g task-master-ai
 
 ```json
 {
-	"mcpServers": {
+  "mcpServers": {
-		"taskmaster-ai": {
+    "taskmaster-ai": {
-			"command": "npx",
+      "command": "npx",
-			"args": ["-y", "--package=task-master-ai", "task-master-ai"],
+      "args": ["-y", "--package=task-master-ai", "task-master-ai"],
-			"env": {
+      "env": {
-				"ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
+        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
-				"PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
+        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
-				"OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
+        "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
-				"GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
+        "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
-				"MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
+        "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
-				"OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
+        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
-				"XAI_API_KEY": "YOUR_XAI_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"
-			}
+      }
-		}
+    }
-	}
+  }
 }
 ```
 
@@ -60,12 +60,12 @@ The AI will:
 - Set up initial configuration files
 - Guide you through the rest of the process
 
-5. Place your PRD document in the `scripts/` directory (e.g., `scripts/prd.txt`)
+5. Place your PRD document in the `.taskmaster/docs/` directory (e.g., `.taskmaster/docs/prd.txt`)
 
 6. **Use natural language commands** to interact with Task Master:
 
 ```
-Can you parse my PRD at scripts/prd.txt?
+Can you parse my PRD at .taskmaster/docs/prd.txt?
 What's the next task I should work on?
 Can you help me implement task 3?
 ```
@@ -132,7 +132,7 @@ If you're not using MCP, you can still set up Cursor integration:
 
 1. After initializing your project, open it in Cursor
 2. The `.cursor/rules/dev_workflow.mdc` file is automatically loaded by Cursor, providing the AI with knowledge about the task management system
-3. Place your PRD document in the `scripts/` directory (e.g., `scripts/prd.txt`)
+3. Place your PRD document in the `.taskmaster/docs/` directory (e.g., `.taskmaster/docs/prd.txt`)
 4. Open Cursor's AI chat and switch to Agent mode
 
 ### Alternative MCP Setup in Cursor
@@ -155,13 +155,13 @@ Once configured, you can interact with Task Master's task management commands di
 In Cursor's AI chat, instruct the agent to generate tasks from your PRD:
 
 ```
-Please use the task-master parse-prd command to generate tasks from my PRD. The PRD is located at scripts/prd.txt.
+Please use the task-master parse-prd command to generate tasks from my PRD. The PRD is located at .taskmaster/docs/prd.txt.
 ```
 
 The agent will execute:
 
 ```bash
-task-master parse-prd scripts/prd.txt
+task-master parse-prd .taskmaster/docs/prd.txt
 ```
 
 This will:
@@ -198,10 +198,15 @@ Ask the agent to list available tasks:
 What tasks are available to work on next?
 ```
 
+```
+Can you show me tasks 1, 3, and 5 to understand their current status?
+```
+
 The agent will:
 
 - Run `task-master list` to see all tasks
 - Run `task-master next` to determine the next task to work on
+- Run `task-master show 1,3,5` to display multiple tasks with interactive options
 - Analyze dependencies to determine which tasks are ready to be worked on
 - Prioritize tasks based on priority level and ID order
 - Suggest the next task(s) to implement
@@ -221,6 +226,21 @@ You can ask:
 Let's implement task 3. What does it involve?
 ```
 
+### 2.1. Viewing Multiple Tasks
+
+For efficient context gathering and batch operations:
+
+```
+Show me tasks 5, 7, and 9 so I can plan my implementation approach.
+```
+
+The agent will:
+
+- Run `task-master show 5,7,9` to display a compact summary table
+- Show task status, priority, and progress indicators
+- Provide an interactive action menu with batch operations
+- Allow you to perform group actions like marking multiple tasks as in-progress
+
 ### 3. Task Verification
 
 Before marking a task as complete, verify it according to:
@@ -268,7 +288,61 @@ task-master update --from=4 --prompt="Update to use MongoDB, researching best pr
 
 This will rewrite or re-scope subsequent tasks in tasks.json while preserving completed work.
 
-### 6. Breaking Down Complex Tasks
+### 6. Reorganizing Tasks
+
+If you need to reorganize your task structure:
+
+```
+I think subtask 5.2 would fit better as part of task 7 instead. Can you move it there?
+```
+
+The agent will execute:
+
+```bash
+task-master move --from=5.2 --to=7.3
+```
+
+You can reorganize tasks in various ways:
+
+- Moving a standalone task to become a subtask: `--from=5 --to=7`
+- Moving a subtask to become a standalone task: `--from=5.2 --to=7`
+- Moving a subtask to a different parent: `--from=5.2 --to=7.3`
+- Reordering subtasks within the same parent: `--from=5.2 --to=5.4`
+- Moving a task to a new ID position: `--from=5 --to=25` (even if task 25 doesn't exist yet)
+- Moving multiple tasks at once: `--from=10,11,12 --to=16,17,18` (must have same number of IDs, Taskmaster will look through each position)
+
+When moving tasks to new IDs:
+
+- The system automatically creates placeholder tasks for non-existent destination IDs
+- This prevents accidental data loss during reorganization
+- Any tasks that depend on moved tasks will have their dependencies updated
+- When moving a parent task, all its subtasks are automatically moved with it and renumbered
+
+This is particularly useful as your project understanding evolves and you need to refine your task structure.
+
+### 7. Resolving Merge Conflicts with Tasks
+
+When working with a team, you might encounter merge conflicts in your tasks.json file if multiple team members create tasks on different branches. The move command makes resolving these conflicts straightforward:
+
+```
+I just merged the main branch and there's a conflict with tasks.json. My teammates created tasks 10-15 while I created tasks 10-12 on my branch. Can you help me resolve this?
+```
+
+The agent will help you:
+
+1. Keep your teammates' tasks (10-15)
+2. Move your tasks to new positions to avoid conflicts:
+
+```bash
+# Move your tasks to new positions (e.g., 16-18)
+task-master move --from=10 --to=16
+task-master move --from=11 --to=17
+task-master move --from=12 --to=18
+```
+
+This approach preserves everyone's work while maintaining a clean task structure, making it much easier to handle task conflicts than trying to manually merge JSON files.
+
+### 8. Breaking Down Complex Tasks
 
 For complex tasks that need more granularity:
 
@@ -323,7 +397,7 @@ task-master expand --id=5 --research
 ### Starting a new project
 
 ```
-I've just initialized a new project with Claude Task Master. I have a PRD at scripts/prd.txt.
+I've just initialized a new project with Claude Task Master. I have a PRD at .taskmaster/docs/prd.txt.
 Can you help me parse it and set up the initial tasks?
 ```
 
@@ -369,3 +443,148 @@ Can you analyze the complexity of our tasks to help me understand which ones nee
 ```
 Can you show me the complexity report in a more readable format?
 ```
+
+### Research-Driven Development
+
+Task Master includes a powerful research tool that provides fresh, up-to-date information beyond the AI's knowledge cutoff. This is particularly valuable for:
+
+#### Getting Current Best Practices
+
+```
+Before implementing task 5 (authentication), research the latest JWT security recommendations.
+```
+
+The agent will execute:
+
+```bash
+task-master research "Latest JWT security recommendations 2024" --id=5
+```
+
+#### Research with Project Context
+
+```
+Research React Query v5 migration strategies for our current API implementation.
+```
+
+The agent will execute:
+
+```bash
+task-master research "React Query v5 migration strategies" --files=src/api.js,src/hooks.js
+```
+
+#### Research and Update Pattern
+
+A powerful workflow is to research first, then update tasks with findings:
+
+```
+Research the latest Node.js performance optimization techniques and update task 12 with the findings.
+```
+
+The agent will:
+
+1. Run research: `task-master research "Node.js performance optimization 2024" --id=12`
+2. Update the task: `task-master update-subtask --id=12.2 --prompt="Updated with latest performance findings: [research results]"`
+
+#### When to Use Research
+
+- **Before implementing any new technology**
+- **When encountering security-related tasks**
+- **For performance optimization tasks**
+- **When debugging complex issues**
+- **Before making architectural decisions**
+- **When updating dependencies**
+
+The research tool automatically includes relevant project context and provides fresh information that can significantly improve implementation quality.
+
+## Git Integration and Tag Management
+
+Task Master supports tagged task lists for multi-context development, which is particularly useful when working with git branches or different project phases.
+
+### Working with Tags
+
+Tags provide isolated task contexts, allowing you to maintain separate task lists for different features, branches, or experiments:
+
+```
+I'm starting work on a new feature branch. Can you create a new tag for this work?
+```
+
+The agent will execute:
+
+```bash
+# Create a tag based on your current git branch
+task-master add-tag --from-branch
+```
+
+Or you can create a tag with a specific name:
+
+```
+Create a new tag called 'user-auth' for authentication-related tasks.
+```
+
+The agent will execute:
+
+```bash
+task-master add-tag user-auth --description="User authentication feature tasks"
+```
+
+### Switching Between Contexts
+
+When working on different features or branches:
+
+```
+Switch to the 'user-auth' tag context so I can work on authentication tasks.
+```
+
+The agent will execute:
+
+```bash
+task-master use-tag user-auth
+```
+
+### Copying Tasks Between Tags
+
+When you need to duplicate work across contexts:
+
+```
+Copy all tasks from the current tag to a new 'testing' tag for QA work.
+```
+
+The agent will execute:
+
+```bash
+task-master add-tag testing --copy-from-current --description="QA and testing tasks"
+```
+
+### Tag Management
+
+View and manage your tag contexts:
+
+```
+Show me all available tags and their current status.
+```
+
+The agent will execute:
+
+```bash
+task-master tags --show-metadata
+```
+
+### Benefits of Tagged Task Lists
+
+- **Branch Isolation**: Each git branch can have its own task context
+- **Merge Conflict Prevention**: Tasks in different tags don't interfere with each other
+- **Parallel Development**: Multiple team members can work on separate contexts
+- **Context Switching**: Easily switch between different project phases or features
+- **Experimentation**: Create experimental task lists without affecting main work
+
+### Git Workflow Integration
+
+A typical git workflow with Task Master tags:
+
+1. **Create feature branch**: `git checkout -b feature/user-auth`
+2. **Create matching tag**: Ask agent to run `task-master add-tag --from-branch`
+3. **Work in isolated context**: All task operations work within the new tag
+4. **Switch contexts as needed**: Use `task-master use-tag <name>` to switch between different work streams
+5. **Merge and cleanup**: After merging the branch, optionally delete the tag with `task-master delete-tag <name>`
+
+This workflow ensures your task management stays organized and conflicts are minimized when working with teams or multiple features simultaneously.

llms-install.md

@@ -0,0 +1,131 @@
+# Taskmaster AI Installation Guide
+
+This guide helps AI assistants install and configure Taskmaster for users in their development projects.
+
+## What is Taskmaster?
+
+Taskmaster is an AI-driven task management system designed for development workflows. It helps break down projects into manageable tasks, track dependencies, and maintain development momentum through structured, AI-enhanced planning.
+
+## Installation Steps
+
+### Step 1: Add MCP Configuration
+
+Add the following configuration to the user's MCP settings file (`.cursor/mcp.json` for Cursor, or equivalent for other editors):
+
+```json
+{
+	"mcpServers": {
+		"taskmaster-ai": {
+			"command": "npx",
+			"args": ["-y", "--package=task-master-ai", "task-master-ai"],
+			"env": {
+				"ANTHROPIC_API_KEY": "user_will_add_their_key_here",
+				"PERPLEXITY_API_KEY": "user_will_add_their_key_here",
+				"OPENAI_API_KEY": "user_will_add_their_key_here",
+				"GOOGLE_API_KEY": "user_will_add_their_key_here",
+				"MISTRAL_API_KEY": "user_will_add_their_key_here",
+				"OPENROUTER_API_KEY": "user_will_add_their_key_here",
+				"XAI_API_KEY": "user_will_add_their_key_here"
+			}
+		}
+	}
+}
+```
+
+### Step 2: API Key Requirements
+
+Inform the user they need **at least one** API key from the following providers:
+
+- **Anthropic** (for Claude models) - Recommended
+- **OpenAI** (for GPT models)
+- **Google** (for Gemini models)
+- **Perplexity** (for research features) - Highly recommended
+- **Mistral** (for Mistral models)
+- **OpenRouter** (access to multiple models)
+- **xAI** (for Grok models)
+
+The user will be able to define 3 separate roles (can be the same provider or separate providers) for main AI operations, research operations (research providers/models only), and a fallback model in case of errors.
+
+### Step 3: Initialize Project
+
+Once the MCP server is configured and API keys are added, initialize Taskmaster in the user's project:
+
+> Can you initialize Task Master in my project?
+
+This will run the `initialize_project` tool to set up the basic file structure.
+
+### Step 4: Create Initial Tasks
+
+Users have two options for creating initial tasks:
+
+**Option A: Parse a PRD (Recommended)**
+If they have a Product Requirements Document:
+
+> Can you parse my PRD file at [path/to/prd.txt] to generate initial tasks?
+
+If the user does not have a PRD, the AI agent can help them create one and store it in scripts/prd.txt for parsing.
+
+**Option B: Start from scratch**
+
+> Can you help me add my first task: [describe the task]
+
+## Common Usage Patterns
+
+### Daily Workflow
+
+> What's the next task I should work on?
+> Can you show me the details for task [ID]?
+> Can you mark task [ID] as done?
+
+### Task Management
+
+> Can you break down task [ID] into subtasks?
+> Can you add a new task: [description]
+> Can you analyze the complexity of my tasks?
+
+### Project Organization
+
+> Can you show me all my pending tasks?
+> Can you move task [ID] to become a subtask of [parent ID]?
+> Can you update task [ID] with this new information: [details]
+
+## Verification Steps
+
+After installation, verify everything is working:
+
+1. **Check MCP Connection**: The AI should be able to access Task Master tools
+2. **Test Basic Commands**: Try `get_tasks` to list current tasks
+3. **Verify API Keys**: Ensure AI-powered commands work (like `add_task`)
+
+Note: An API key fallback exists that allows the MCP server to read API keys from `.env` instead of the MCP JSON config. It is recommended to have keys in both places in case the MCP server is unable to read keys from its environment for whatever reason.
+
+When adding keys to `.env` only, the `models` tool will explain that the keys are not OK for MCP. Despite this, the fallback should kick in and the API keys will be read from the `.env` file.
+
+## Troubleshooting
+
+**If MCP server doesn't start:**
+
+- Verify the JSON configuration is valid
+- Check that Node.js is installed
+- Ensure API keys are properly formatted
+
+**If AI commands fail:**
+
+- Verify at least one API key is configured
+- Check API key permissions and quotas
+- Try using a different model via the `models` tool
+
+## CLI Fallback
+
+Taskmaster is also available via CLI commands, by installing with `npm install task-master-ai@latest` in a terminal. Running `task-master help` will show all available commands, which offer a 1:1 experience with the MCP server. As the AI agent, you should refer to the system prompts and rules provided to you to identify Taskmaster-specific rules that help you understand how and when to use it.
+
+## Next Steps
+
+Once installed, users can:
+
+- Create new tasks with `add-task` or parse a PRD (scripts/prd.txt) into tasks with `parse-prd`
+- Set up model preferences with `models` tool
+- Expand tasks into subtasks with `expand-all` and `expand-task`
+- Explore advanced features like research mode and complexity analysis
+
+For detailed documentation, refer to the Task Master docs directory.``

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

@@ -0,0 +1,198 @@
+/**
+ * add-tag.js
+ * Direct function implementation for creating a new tag
+ */
+
+import {
+	createTag,
+	createTagFromBranch
+} from '../../../../scripts/modules/task-manager/tag-management.js';
+import {
+	enableSilentMode,
+	disableSilentMode
+} from '../../../../scripts/modules/utils.js';
+import { createLogWrapper } from '../../tools/utils.js';
+
+/**
+ * Direct function wrapper for creating a new tag with error handling.
+ *
+ * @param {Object} args - Command arguments
+ * @param {string} args.name - Name of the new tag to create
+ * @param {boolean} [args.copyFromCurrent=false] - Whether to copy tasks from current tag
+ * @param {string} [args.copyFromTag] - Specific tag to copy tasks from
+ * @param {boolean} [args.fromBranch=false] - Create tag name from current git branch
+ * @param {string} [args.description] - Optional description for the tag
+ * @param {string} [args.tasksJsonPath] - Path to the tasks.json file (resolved by tool)
+ * @param {string} [args.projectRoot] - Project root path
+ * @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 } }
+ */
+export async function addTagDirect(args, log, context = {}) {
+	// Destructure expected args
+	const {
+		tasksJsonPath,
+		name,
+		copyFromCurrent = false,
+		copyFromTag,
+		fromBranch = false,
+		description,
+		projectRoot
+	} = args;
+	const { session } = context;
+
+	// Enable silent mode to prevent console logs from interfering with JSON response
+	enableSilentMode();
+
+	// Create logger wrapper using the utility
+	const mcpLog = createLogWrapper(log);
+
+	try {
+		// Check if tasksJsonPath was provided
+		if (!tasksJsonPath) {
+			log.error('addTagDirect called without tasksJsonPath');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_ARGUMENT',
+					message: 'tasksJsonPath is required'
+				}
+			};
+		}
+
+		// Handle --from-branch option
+		if (fromBranch) {
+			log.info('Creating tag from current git branch');
+
+			// Import git utilities
+			const gitUtils = await import(
+				'../../../../scripts/modules/utils/git-utils.js'
+			);
+
+			// Check if we're in a git repository
+			if (!(await gitUtils.isGitRepository(projectRoot))) {
+				log.error('Not in a git repository');
+				disableSilentMode();
+				return {
+					success: false,
+					error: {
+						code: 'NOT_GIT_REPO',
+						message: 'Not in a git repository. Cannot use fromBranch option.'
+					}
+				};
+			}
+
+			// Get current git branch
+			const currentBranch = await gitUtils.getCurrentBranch(projectRoot);
+			if (!currentBranch) {
+				log.error('Could not determine current git branch');
+				disableSilentMode();
+				return {
+					success: false,
+					error: {
+						code: 'NO_CURRENT_BRANCH',
+						message: 'Could not determine current git branch.'
+					}
+				};
+			}
+
+			// Prepare options for branch-based tag creation
+			const branchOptions = {
+				copyFromCurrent,
+				copyFromTag,
+				description:
+					description || `Tag created from git branch "${currentBranch}"`
+			};
+
+			// Call the createTagFromBranch function
+			const result = await createTagFromBranch(
+				tasksJsonPath,
+				currentBranch,
+				branchOptions,
+				{
+					session,
+					mcpLog,
+					projectRoot
+				},
+				'json' // outputFormat - use 'json' to suppress CLI UI
+			);
+
+			// Restore normal logging
+			disableSilentMode();
+
+			return {
+				success: true,
+				data: {
+					branchName: result.branchName,
+					tagName: result.tagName,
+					created: result.created,
+					mappingUpdated: result.mappingUpdated,
+					message: `Successfully created tag "${result.tagName}" from git branch "${result.branchName}"`
+				}
+			};
+		} else {
+			// Check required parameters for regular tag creation
+			if (!name || typeof name !== 'string') {
+				log.error('Missing required parameter: name');
+				disableSilentMode();
+				return {
+					success: false,
+					error: {
+						code: 'MISSING_PARAMETER',
+						message: 'Tag name is required and must be a string'
+					}
+				};
+			}
+
+			log.info(`Creating new tag: ${name}`);
+
+			// Prepare options
+			const options = {
+				copyFromCurrent,
+				copyFromTag,
+				description
+			};
+
+			// Call the createTag function
+			const result = await createTag(
+				tasksJsonPath,
+				name,
+				options,
+				{
+					session,
+					mcpLog,
+					projectRoot
+				},
+				'json' // outputFormat - use 'json' to suppress CLI UI
+			);
+
+			// Restore normal logging
+			disableSilentMode();
+
+			return {
+				success: true,
+				data: {
+					tagName: result.tagName,
+					created: result.created,
+					tasksCopied: result.tasksCopied,
+					sourceTag: result.sourceTag,
+					description: result.description,
+					message: `Successfully created tag "${result.tagName}"`
+				}
+			};
+		}
+	} catch (error) {
+		// Make sure to restore normal logging even if there's an error
+		disableSilentMode();
+
+		log.error(`Error in addTagDirect: ${error.message}`);
+		return {
+			success: false,
+			error: {
+				code: error.code || 'ADD_TAG_ERROR',
+				message: error.message
+			}
+		};
+	}
+}

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

@@ -95,6 +95,7 @@ export async function addTaskDirect(args, log, context = {}) {
 		let manualTaskData = null;
 		let newTaskId;
 		let telemetryData;
+		let tagInfo;
 
 		if (isManualCreation) {
 			// Create manual task data object
@@ -129,6 +130,7 @@ export async function addTaskDirect(args, log, context = {}) {
 			);
 			newTaskId = result.newTaskId;
 			telemetryData = result.telemetryData;
+			tagInfo = result.tagInfo;
 		} else {
 			// AI-driven task creation
 			log.info(
@@ -154,6 +156,7 @@ export async function addTaskDirect(args, log, context = {}) {
 			);
 			newTaskId = result.newTaskId;
 			telemetryData = result.telemetryData;
+			tagInfo = result.tagInfo;
 		}
 
 		// Restore normal logging
@@ -164,7 +167,8 @@ export async function addTaskDirect(args, log, context = {}) {
 			data: {
 				taskId: newTaskId,
 				message: `Successfully added new task #${newTaskId}`,
-				telemetryData: telemetryData
+				telemetryData: telemetryData,
+				tagInfo: tagInfo
 			}
 		};
 	} catch (error) {

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

@@ -18,6 +18,9 @@ import { createLogWrapper } from '../../tools/utils.js'; // Import the new utili
  * @param {string} args.outputPath - Explicit absolute path to save the report.
  * @param {string|number} [args.threshold] - Minimum complexity score to recommend expansion (1-10)
  * @param {boolean} [args.research] - Use Perplexity AI for research-backed complexity analysis
+ * @param {string} [args.ids] - Comma-separated list of task IDs to analyze
+ * @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 {Object} log - Logger object
  * @param {Object} [context={}] - Context object containing session data
@@ -26,7 +29,16 @@ import { createLogWrapper } from '../../tools/utils.js'; // Import the new utili
  */
 export async function analyzeTaskComplexityDirect(args, log, context = {}) {
 	const { session } = context;
-	const { tasksJsonPath, outputPath, threshold, research, projectRoot } = args;
+	const {
+		tasksJsonPath,
+		outputPath,
+		threshold,
+		research,
+		projectRoot,
+		ids,
+		from,
+		to
+	} = args;
 
 	const logWrapper = createLogWrapper(log);
 
@@ -58,6 +70,14 @@ export async function analyzeTaskComplexityDirect(args, log, context = {}) {
 		log.info(`Analyzing task complexity from: ${tasksPath}`);
 		log.info(`Output report will be saved to: ${resolvedOutputPath}`);
 
+		if (ids) {
+			log.info(`Analyzing specific task IDs: ${ids}`);
+		} else if (from || to) {
+			const fromStr = from !== undefined ? from : 'first';
+			const toStr = to !== undefined ? to : 'last';
+			log.info(`Analyzing tasks in range: ${fromStr} to ${toStr}`);
+		}
+
 		if (research) {
 			log.info('Using research role for complexity analysis');
 		}
@@ -68,7 +88,10 @@ export async function analyzeTaskComplexityDirect(args, log, context = {}) {
 			output: outputPath,
 			threshold: threshold,
 			research: research === true, // Ensure boolean
-			projectRoot: projectRoot // Pass projectRoot here
+			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
 		};
 		// --- End Initial Checks ---
 
@@ -173,7 +196,8 @@ export async function analyzeTaskComplexityDirect(args, log, context = {}) {
 						lowComplexityTasks
 					},
 					fullReport: coreResult.report,
-					telemetryData: coreResult.telemetryData
+					telemetryData: coreResult.telemetryData,
+					tagInfo: coreResult.tagInfo
 				}
 			};
 		} catch (parseError) {

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

@@ -5,9 +5,11 @@
 import { clearSubtasks } from '../../../../scripts/modules/task-manager.js';
 import {
 	enableSilentMode,
-	disableSilentMode
+	disableSilentMode,
+	readJSON
 } from '../../../../scripts/modules/utils.js';
 import fs from 'fs';
+import path from 'path';
 
 /**
  * Clear subtasks from specified tasks
@@ -15,12 +17,13 @@ import fs from 'fs';
  * @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
  * @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 {Object} log - Logger object
  * @returns {Promise<{success: boolean, data?: Object, error?: {code: string, message: string}}>}
  */
 export async function clearSubtasksDirect(args, log) {
 	// Destructure expected args
-	const { tasksJsonPath, id, all } = args;
+	const { tasksJsonPath, id, all, tag, projectRoot } = args;
 	try {
 		log.info(`Clearing subtasks with args: ${JSON.stringify(args)}`);
 
@@ -64,52 +67,70 @@ export async function clearSubtasksDirect(args, log) {
 
 		let taskIds;
 
+		// Use readJSON which handles silent migration and tag resolution
+		const data = readJSON(tasksPath, projectRoot, tag);
+
+		if (!data || !data.tasks) {
+			return {
+				success: false,
+				error: {
+					code: 'INPUT_VALIDATION_ERROR',
+					message: `No tasks found in tasks file: ${tasksPath}`
+				}
+			};
+		}
+
+		const currentTag = data.tag || 'master';
+		const tasks = data.tasks;
+
 		// If all is specified, get all task IDs
 		if (all) {
-			log.info('Clearing subtasks from all tasks');
+			log.info(`Clearing subtasks from all tasks in tag '${currentTag}'`);
-			const data = JSON.parse(fs.readFileSync(tasksPath, 'utf8'));
+			if (tasks.length === 0) {
-			if (!data || !data.tasks || data.tasks.length === 0) {
 				return {
 					success: false,
 					error: {
 						code: 'INPUT_VALIDATION_ERROR',
-						message: 'No valid tasks found in the tasks file'
+						message: `No tasks found in tag context '${currentTag}'`
 					}
 				};
 			}
-			taskIds = data.tasks.map((t) => t.id).join(',');
+			taskIds = tasks.map((t) => t.id).join(',');
 		} else {
 			// Use the provided task IDs
 			taskIds = id;
 		}
 
-		log.info(`Clearing subtasks from tasks: ${taskIds}`);
+		log.info(`Clearing subtasks from tasks: ${taskIds} in tag '${currentTag}'`);
 
 		// Enable silent mode to prevent console logs from interfering with JSON response
 		enableSilentMode();
 
 		// Call the core function
-		clearSubtasks(tasksPath, taskIds);
+		clearSubtasks(tasksPath, taskIds, { projectRoot, tag: currentTag });
 
 		// Restore normal logging
 		disableSilentMode();
 
 		// Read the updated data to provide a summary
-		const updatedData = JSON.parse(fs.readFileSync(tasksPath, 'utf8'));
+		const updatedData = readJSON(tasksPath, projectRoot, currentTag);
 		const taskIdArray = taskIds.split(',').map((id) => parseInt(id.trim(), 10));
 
 		// Build a summary of what was done
 		const clearedTasksCount = taskIdArray.length;
+		const updatedTasks = updatedData.tasks || [];
+
 		const taskSummary = taskIdArray.map((id) => {
-			const task = updatedData.tasks.find((t) => t.id === id);
+			const task = updatedTasks.find((t) => t.id === id);
 			return task ? { id, title: task.title } : { id, title: 'Task not found' };
 		});
 
 		return {
 			success: true,
 			data: {
-				message: `Successfully cleared subtasks from ${clearedTasksCount} task(s)`,
+				message: `Successfully cleared subtasks from ${clearedTasksCount} task(s) in tag '${currentTag}'`,
-				tasksCleared: taskSummary
+				tasksCleared: taskSummary,
+				tag: currentTag
 			}
 		};
 	} catch (error) {

mcp-server/src/core/direct-functions/complexity-report.js

@@ -28,8 +28,7 @@ export async function complexityReportDirect(args, log) {
 			log.error('complexityReportDirect called without reportPath');
 			return {
 				success: false,
-				error: { code: 'MISSING_ARGUMENT', message: 'reportPath is required' },
+				error: { code: 'MISSING_ARGUMENT', message: 'reportPath is required' }
-				fromCache: false
 			};
 		}
 
@@ -111,8 +110,7 @@ export async function complexityReportDirect(args, log) {
 			error: {
 				code: 'UNEXPECTED_ERROR',
 				message: error.message
-			},
+			}
-			fromCache: false
 		};
 	}
 }

mcp-server/src/core/direct-functions/copy-tag.js

@@ -0,0 +1,125 @@
+/**
+ * copy-tag.js
+ * Direct function implementation for copying a tag
+ */
+
+import { copyTag } from '../../../../scripts/modules/task-manager/tag-management.js';
+import {
+	enableSilentMode,
+	disableSilentMode
+} from '../../../../scripts/modules/utils.js';
+import { createLogWrapper } from '../../tools/utils.js';
+
+/**
+ * Direct function wrapper for copying a tag with error handling.
+ *
+ * @param {Object} args - Command arguments
+ * @param {string} args.sourceName - Name of the source tag to copy from
+ * @param {string} args.targetName - Name of the new tag to create
+ * @param {string} [args.description] - Optional description for the new tag
+ * @param {string} [args.tasksJsonPath] - Path to the tasks.json file (resolved by tool)
+ * @param {string} [args.projectRoot] - Project root path
+ * @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 } }
+ */
+export async function copyTagDirect(args, log, context = {}) {
+	// Destructure expected args
+	const { tasksJsonPath, sourceName, targetName, description, projectRoot } =
+		args;
+	const { session } = context;
+
+	// Enable silent mode to prevent console logs from interfering with JSON response
+	enableSilentMode();
+
+	// Create logger wrapper using the utility
+	const mcpLog = createLogWrapper(log);
+
+	try {
+		// Check if tasksJsonPath was provided
+		if (!tasksJsonPath) {
+			log.error('copyTagDirect called without tasksJsonPath');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_ARGUMENT',
+					message: 'tasksJsonPath is required'
+				}
+			};
+		}
+
+		// Check required parameters
+		if (!sourceName || typeof sourceName !== 'string') {
+			log.error('Missing required parameter: sourceName');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_PARAMETER',
+					message: 'Source tag name is required and must be a string'
+				}
+			};
+		}
+
+		if (!targetName || typeof targetName !== 'string') {
+			log.error('Missing required parameter: targetName');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_PARAMETER',
+					message: 'Target tag name is required and must be a string'
+				}
+			};
+		}
+
+		log.info(`Copying tag from "${sourceName}" to "${targetName}"`);
+
+		// Prepare options
+		const options = {
+			description
+		};
+
+		// Call the copyTag function
+		const result = await copyTag(
+			tasksJsonPath,
+			sourceName,
+			targetName,
+			options,
+			{
+				session,
+				mcpLog,
+				projectRoot
+			},
+			'json' // outputFormat - use 'json' to suppress CLI UI
+		);
+
+		// Restore normal logging
+		disableSilentMode();
+
+		return {
+			success: true,
+			data: {
+				sourceName: result.sourceName,
+				targetName: result.targetName,
+				copied: result.copied,
+				tasksCopied: result.tasksCopied,
+				description: result.description,
+				message: `Successfully copied tag from "${result.sourceName}" to "${result.targetName}"`
+			}
+		};
+	} catch (error) {
+		// Make sure to restore normal logging even if there's an error
+		disableSilentMode();
+
+		log.error(`Error in copyTagDirect: ${error.message}`);
+		return {
+			success: false,
+			error: {
+				code: error.code || 'COPY_TAG_ERROR',
+				message: error.message
+			}
+		};
+	}
+}

mcp-server/src/core/direct-functions/create-tag-from-branch.js

@@ -0,0 +1,159 @@
+/**
+ * create-tag-from-branch.js
+ * Direct function implementation for creating tags from git branches
+ */
+
+import { createTagFromBranch } from '../../../../scripts/modules/task-manager/tag-management.js';
+import {
+	getCurrentBranch,
+	isGitRepository
+} from '../../../../scripts/modules/utils/git-utils.js';
+import {
+	enableSilentMode,
+	disableSilentMode
+} from '../../../../scripts/modules/utils.js';
+import { createLogWrapper } from '../../tools/utils.js';
+
+/**
+ * Direct function wrapper for creating tags from git branches with error handling.
+ *
+ * @param {Object} args - Command arguments
+ * @param {string} args.tasksJsonPath - Path to the tasks.json file (resolved by tool)
+ * @param {string} [args.branchName] - Git branch name (optional, uses current branch if not provided)
+ * @param {boolean} [args.copyFromCurrent] - Copy tasks from current tag
+ * @param {string} [args.copyFromTag] - Copy tasks from specific tag
+ * @param {string} [args.description] - Custom description for the tag
+ * @param {boolean} [args.autoSwitch] - Automatically switch to the new tag
+ * @param {string} [args.projectRoot] - Project root path
+ * @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 } }
+ */
+export async function createTagFromBranchDirect(args, log, context = {}) {
+	// Destructure expected args
+	const {
+		tasksJsonPath,
+		branchName,
+		copyFromCurrent,
+		copyFromTag,
+		description,
+		autoSwitch,
+		projectRoot
+	} = args;
+	const { session } = context;
+
+	// Enable silent mode to prevent console logs from interfering with JSON response
+	enableSilentMode();
+
+	// Create logger wrapper using the utility
+	const mcpLog = createLogWrapper(log);
+
+	try {
+		// Check if tasksJsonPath was provided
+		if (!tasksJsonPath) {
+			log.error('createTagFromBranchDirect called without tasksJsonPath');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_ARGUMENT',
+					message: 'tasksJsonPath is required'
+				}
+			};
+		}
+
+		// Check if projectRoot was provided
+		if (!projectRoot) {
+			log.error('createTagFromBranchDirect called without projectRoot');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_ARGUMENT',
+					message: 'projectRoot is required'
+				}
+			};
+		}
+
+		// Check if we're in a git repository
+		if (!(await isGitRepository(projectRoot))) {
+			log.error('Not in a git repository');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'NOT_GIT_REPOSITORY',
+					message: 'Not in a git repository. Cannot create tag from branch.'
+				}
+			};
+		}
+
+		// Determine branch name
+		let targetBranch = branchName;
+		if (!targetBranch) {
+			targetBranch = await getCurrentBranch(projectRoot);
+			if (!targetBranch) {
+				log.error('Could not determine current git branch');
+				disableSilentMode();
+				return {
+					success: false,
+					error: {
+						code: 'NO_CURRENT_BRANCH',
+						message: 'Could not determine current git branch'
+					}
+				};
+			}
+		}
+
+		log.info(`Creating tag from git branch: ${targetBranch}`);
+
+		// Prepare options
+		const options = {
+			copyFromCurrent: copyFromCurrent || false,
+			copyFromTag,
+			description:
+				description || `Tag created from git branch "${targetBranch}"`,
+			autoSwitch: autoSwitch || false
+		};
+
+		// Call the createTagFromBranch function
+		const result = await createTagFromBranch(
+			tasksJsonPath,
+			targetBranch,
+			options,
+			{
+				session,
+				mcpLog,
+				projectRoot
+			},
+			'json' // outputFormat - use 'json' to suppress CLI UI
+		);
+
+		// Restore normal logging
+		disableSilentMode();
+
+		return {
+			success: true,
+			data: {
+				branchName: result.branchName,
+				tagName: result.tagName,
+				created: result.created,
+				mappingUpdated: result.mappingUpdated,
+				autoSwitched: result.autoSwitched,
+				message: `Successfully created tag "${result.tagName}" from branch "${result.branchName}"`
+			}
+		};
+	} catch (error) {
+		// Make sure to restore normal logging even if there's an error
+		disableSilentMode();
+
+		log.error(`Error in createTagFromBranchDirect: ${error.message}`);
+		return {
+			success: false,
+			error: {
+				code: error.code || 'CREATE_TAG_FROM_BRANCH_ERROR',
+				message: error.message
+			}
+		};
+	}
+}

mcp-server/src/core/direct-functions/delete-tag.js

@@ -0,0 +1,110 @@
+/**
+ * delete-tag.js
+ * Direct function implementation for deleting a tag
+ */
+
+import { deleteTag } from '../../../../scripts/modules/task-manager/tag-management.js';
+import {
+	enableSilentMode,
+	disableSilentMode
+} from '../../../../scripts/modules/utils.js';
+import { createLogWrapper } from '../../tools/utils.js';
+
+/**
+ * Direct function wrapper for deleting a tag with error handling.
+ *
+ * @param {Object} args - Command arguments
+ * @param {string} args.name - Name of the tag to delete
+ * @param {boolean} [args.yes=false] - Skip confirmation prompts
+ * @param {string} [args.tasksJsonPath] - Path to the tasks.json file (resolved by tool)
+ * @param {string} [args.projectRoot] - Project root path
+ * @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 } }
+ */
+export async function deleteTagDirect(args, log, context = {}) {
+	// Destructure expected args
+	const { tasksJsonPath, name, yes = false, projectRoot } = args;
+	const { session } = context;
+
+	// Enable silent mode to prevent console logs from interfering with JSON response
+	enableSilentMode();
+
+	// Create logger wrapper using the utility
+	const mcpLog = createLogWrapper(log);
+
+	try {
+		// Check if tasksJsonPath was provided
+		if (!tasksJsonPath) {
+			log.error('deleteTagDirect called without tasksJsonPath');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_ARGUMENT',
+					message: 'tasksJsonPath is required'
+				}
+			};
+		}
+
+		// Check required parameters
+		if (!name || typeof name !== 'string') {
+			log.error('Missing required parameter: name');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_PARAMETER',
+					message: 'Tag name is required and must be a string'
+				}
+			};
+		}
+
+		log.info(`Deleting tag: ${name}`);
+
+		// Prepare options
+		const options = {
+			yes // For MCP, we always skip confirmation prompts
+		};
+
+		// Call the deleteTag function
+		const result = await deleteTag(
+			tasksJsonPath,
+			name,
+			options,
+			{
+				session,
+				mcpLog,
+				projectRoot
+			},
+			'json' // outputFormat - use 'json' to suppress CLI UI
+		);
+
+		// Restore normal logging
+		disableSilentMode();
+
+		return {
+			success: true,
+			data: {
+				tagName: result.tagName,
+				deleted: result.deleted,
+				tasksDeleted: result.tasksDeleted,
+				wasCurrentTag: result.wasCurrentTag,
+				switchedToMaster: result.switchedToMaster,
+				message: `Successfully deleted tag "${result.tagName}"`
+			}
+		};
+	} catch (error) {
+		// Make sure to restore normal logging even if there's an error
+		disableSilentMode();
+
+		log.error(`Error in deleteTagDirect: ${error.message}`);
+		return {
+			success: false,
+			error: {
+				code: error.code || 'DELETE_TAG_ERROR',
+				message: error.message
+			}
+		};
+	}
+}

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

@@ -60,7 +60,8 @@ export async function expandAllTasksDirect(args, log, context = {}) {
 			useResearch,
 			additionalContext,
 			forceFlag,
-			{ session, mcpLog, projectRoot }
+			{ session, mcpLog, projectRoot },
+			'json'
 		);
 
 		// Core function now returns a summary object including the *aggregated* telemetryData

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

@@ -26,15 +26,17 @@ import { createLogWrapper } from '../../tools/utils.js';
  * @param {string} [args.prompt] - Additional context to guide subtask generation.
  * @param {boolean} [args.force] - Force expansion even if subtasks exist.
  * @param {string} [args.projectRoot] - Project root directory.
+ * @param {string} [args.tag] - Tag for the task
  * @param {Object} log - Logger object
  * @param {Object} context - Context object containing session
  * @param {Object} [context.session] - MCP Session object
- * @returns {Promise<Object>} - Task expansion result { success: boolean, data?: any, error?: { code: string, message: string }, fromCache: boolean }
+ * @returns {Promise<Object>} - Task expansion result { success: boolean, data?: any, error?: { code: string, message: string } }
  */
 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 } = args;
+	const { tasksJsonPath, id, num, research, prompt, force, projectRoot, tag } =
+		args;
 
 	// Log session root data for debugging
 	log.info(
@@ -54,8 +56,7 @@ export async function expandTaskDirect(args, log, context = {}) {
 			error: {
 				code: 'MISSING_ARGUMENT',
 				message: 'tasksJsonPath is required'
-			},
+			}
-			fromCache: false
 		};
 	}
 
@@ -73,8 +74,7 @@ export async function expandTaskDirect(args, log, context = {}) {
 			error: {
 				code: 'INPUT_VALIDATION_ERROR',
 				message: 'Task ID is required'
-			},
+			}
-			fromCache: false
 		};
 	}
 
@@ -91,7 +91,7 @@ export async function expandTaskDirect(args, log, context = {}) {
 
 		// Read tasks data
 		log.info(`[expandTaskDirect] Attempting to read JSON from: ${tasksPath}`);
-		const data = readJSON(tasksPath);
+		const data = readJSON(tasksPath, projectRoot);
 		log.info(
 			`[expandTaskDirect] Result of readJSON: ${data ? 'Data read successfully' : 'readJSON returned null or undefined'}`
 		);
@@ -105,8 +105,7 @@ export async function expandTaskDirect(args, log, context = {}) {
 				error: {
 					code: 'INVALID_TASKS_FILE',
 					message: `No valid tasks found in ${tasksPath}. readJSON returned: ${JSON.stringify(data)}`
-				},
+				}
-				fromCache: false
 			};
 		}
 
@@ -121,8 +120,7 @@ export async function expandTaskDirect(args, log, context = {}) {
 				error: {
 					code: 'TASK_NOT_FOUND',
 					message: `Task with ID ${taskId} not found`
-				},
+				}
-				fromCache: false
 			};
 		}
 
@@ -133,8 +131,7 @@ export async function expandTaskDirect(args, log, context = {}) {
 				error: {
 					code: 'TASK_COMPLETED',
 					message: `Task ${taskId} is already marked as ${task.status} and cannot be expanded`
-				},
+				}
-				fromCache: false
 			};
 		}
 
@@ -151,8 +148,7 @@ export async function expandTaskDirect(args, log, context = {}) {
 					task,
 					subtasksAdded: 0,
 					hasExistingSubtasks
-				},
+				}
-				fromCache: false
 			};
 		}
 
@@ -170,10 +166,6 @@ export async function expandTaskDirect(args, log, context = {}) {
 		// Tracking subtasks count before expansion
 		const subtasksCountBefore = task.subtasks ? task.subtasks.length : 0;
 
-		// Create a backup of the tasks.json file
-		const backupPath = path.join(path.dirname(tasksPath), 'tasks.json.bak');
-		fs.copyFileSync(tasksPath, backupPath);
-
 		// Directly modify the data instead of calling the CLI function
 		if (!task.subtasks) {
 			task.subtasks = [];
@@ -204,7 +196,8 @@ export async function expandTaskDirect(args, log, context = {}) {
 					session,
 					projectRoot,
 					commandName: 'expand-task',
-					outputType: 'mcp'
+					outputType: 'mcp',
+					tag
 				},
 				forceFlag
 			);
@@ -213,7 +206,7 @@ export async function expandTaskDirect(args, log, context = {}) {
 			if (!wasSilent && isSilentMode()) disableSilentMode();
 
 			// Read the updated data
-			const updatedData = readJSON(tasksPath);
+			const updatedData = readJSON(tasksPath, projectRoot);
 			const updatedTask = updatedData.tasks.find((t) => t.id === taskId);
 
 			// Calculate how many subtasks were added
@@ -231,9 +224,9 @@ export async function expandTaskDirect(args, log, context = {}) {
 					task: coreResult.task,
 					subtasksAdded,
 					hasExistingSubtasks,
-					telemetryData: coreResult.telemetryData
+					telemetryData: coreResult.telemetryData,
-				},
+					tagInfo: coreResult.tagInfo
-				fromCache: false
+				}
 			};
 		} catch (error) {
 			// Make sure to restore normal logging even if there's an error
@@ -245,8 +238,7 @@ export async function expandTaskDirect(args, log, context = {}) {
 				error: {
 					code: 'CORE_FUNCTION_ERROR',
 					message: error.message || 'Failed to expand task'
-				},
+				}
-				fromCache: false
 			};
 		}
 	} catch (error) {
@@ -256,8 +248,7 @@ export async function expandTaskDirect(args, log, context = {}) {
 			error: {
 				code: 'CORE_FUNCTION_ERROR',
 				message: error.message || 'Failed to expand task'
-			},
+			}
-			fromCache: false
 		};
 	}
 }

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

@@ -28,8 +28,7 @@ export async function generateTaskFilesDirect(args, log) {
 			log.error(errorMessage);
 			return {
 				success: false,
-				error: { code: 'MISSING_ARGUMENT', message: errorMessage },
+				error: { code: 'MISSING_ARGUMENT', message: errorMessage }
-				fromCache: false
 			};
 		}
 		if (!outputDir) {
@@ -37,8 +36,7 @@ export async function generateTaskFilesDirect(args, log) {
 			log.error(errorMessage);
 			return {
 				success: false,
-				error: { code: 'MISSING_ARGUMENT', message: errorMessage },
+				error: { code: 'MISSING_ARGUMENT', message: errorMessage }
-				fromCache: false
 			};
 		}
 
@@ -65,8 +63,7 @@ export async function generateTaskFilesDirect(args, log) {
 			log.error(`Error in generateTaskFiles: ${genError.message}`);
 			return {
 				success: false,
-				error: { code: 'GENERATE_FILES_ERROR', message: genError.message },
+				error: { code: 'GENERATE_FILES_ERROR', message: genError.message }
-				fromCache: false
 			};
 		}
 
@@ -79,8 +76,7 @@ export async function generateTaskFilesDirect(args, log) {
 				outputDir: resolvedOutputDir,
 				taskFiles:
 					'Individual task files have been generated in the output directory'
-			},
+			}
-			fromCache: false // This operation always modifies state and should never be cached
 		};
 	} catch (error) {
 		// Make sure to restore normal logging if an outer error occurs
@@ -92,8 +88,7 @@ export async function generateTaskFilesDirect(args, log) {
 			error: {
 				code: 'GENERATE_TASKS_ERROR',
 				message: error.message || 'Unknown error generating task files'
-			},
+			}
-			fromCache: false
 		};
 	}
 }

mcp-server/src/core/direct-functions/initialize-project.js

@@ -5,11 +5,13 @@ import {
 	// isSilentMode // Not used directly here
 } from '../../../../scripts/modules/utils.js';
 import os from 'os'; // Import os module for home directory check
+import { RULE_PROFILES } from '../../../../src/constants/profiles.js';
+import { convertAllRulesToProfileRules } from '../../../../src/utils/rule-transformer.js';
 
 /**
  * Direct function wrapper for initializing a project.
  * Derives target directory from session, sets CWD, and calls core init logic.
- * @param {object} args - Arguments containing initialization options (addAliases, skipInstall, yes, projectRoot)
+ * @param {object} args - Arguments containing initialization options (addAliases, skipInstall, yes, projectRoot, rules)
  * @param {object} log - The FastMCP logger instance.
  * @param {object} context - The context object, must contain { session }.
  * @returns {Promise<{success: boolean, data?: any, error?: {code: string, message: string}}>} - Standard result object.
@@ -41,8 +43,7 @@ export async function initializeProjectDirect(args, log, context = {}) {
 				code: 'INVALID_TARGET_DIRECTORY',
 				message: `Cannot initialize project: Invalid target directory '${targetDirectory}' received. Please ensure a valid workspace/folder is open or specified.`,
 				details: `Received args.projectRoot: ${args.projectRoot}` // Show what was received
-			},
+			}
-			fromCache: false
 		};
 	}
 
@@ -69,13 +70,24 @@ export async function initializeProjectDirect(args, log, context = {}) {
 			yes: true // Force yes mode
 		};
 
+		// Handle rules option just like CLI
+		if (Array.isArray(args.rules) && args.rules.length > 0) {
+			options.rules = args.rules;
+			log.info(`Including rules: ${args.rules.join(', ')}`);
+		} else {
+			options.rules = RULE_PROFILES;
+			log.info(
+				`No rule profiles specified, defaulting to: ${RULE_PROFILES.join(', ')}`
+			);
+		}
+
 		log.info(`Initializing project with options: ${JSON.stringify(options)}`);
 		const result = await initializeProject(options); // Call core logic
 
 		resultData = {
 			message: 'Project initialized successfully.',
 			next_step:
-				'Now that the project is initialized, the next step is to create the tasks by parsing a PRD. This will create the tasks folder and the initial task files (tasks folder will be created when parse-prd is run). The parse-prd tool will require a prd.txt file as input (typically found in the project root directory, scripts/ directory). You can create a prd.txt file by asking the user about their idea, and then using the scripts/example_prd.txt file as a template to genrate a prd.txt file in scripts/. You may skip all of this if the user already has a prd.txt file. You can THEN use the parse-prd tool to create the tasks. So: step 1 after initialization is to create a prd.txt file in scripts/prd.txt or confirm the user already has one. Step 2 is to use the parse-prd tool to create the tasks. Do not bother looking for tasks after initialization, just use the parse-prd tool to create the tasks after creating a prd.txt from which to parse the tasks. You do NOT need to reinitialize the project to parse-prd.',
+				'Now that the project is initialized, the next step is to create the tasks by parsing a PRD. This will create the tasks folder and the initial task files (tasks folder will be created when parse-prd is run). The parse-prd tool will require a prd.txt file as input (typically found in .taskmaster/docs/ directory). You can create a prd.txt file by asking the user about their idea, and then using the .taskmaster/templates/example_prd.txt file as a template to generate a prd.txt file in .taskmaster/docs/. You may skip all of this if the user already has a prd.txt file. You can THEN use the parse-prd tool to create the tasks. So: step 1 after initialization is to create a prd.txt file in .taskmaster/docs/prd.txt or confirm the user already has one. Step 2 is to use the parse-prd tool to create the tasks. Do not bother looking for tasks after initialization, just use the parse-prd tool to create the tasks after creating a prd.txt from which to parse the tasks. You do NOT need to reinitialize the project to parse-prd.',
 			...result
 		};
 		success = true;
@@ -97,8 +109,8 @@ export async function initializeProjectDirect(args, log, context = {}) {
 	}
 
 	if (success) {
-		return { success: true, data: resultData, fromCache: false };
+		return { success: true, data: resultData };
 	} else {
-		return { success: false, error: errorResult, fromCache: false };
+		return { success: false, error: errorResult };
 	}
 }

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

@@ -0,0 +1,132 @@
+/**
+ * list-tags.js
+ * Direct function implementation for listing all tags
+ */
+
+import { tags } from '../../../../scripts/modules/task-manager/tag-management.js';
+import {
+	enableSilentMode,
+	disableSilentMode
+} from '../../../../scripts/modules/utils.js';
+import { createLogWrapper } from '../../tools/utils.js';
+
+/**
+ * Direct function wrapper for listing all tags with error handling.
+ *
+ * @param {Object} args - Command arguments
+ * @param {boolean} [args.showMetadata=false] - Whether to include metadata in the output
+ * @param {string} [args.tasksJsonPath] - Path to the tasks.json file (resolved by tool)
+ * @param {string} [args.projectRoot] - Project root path
+ * @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 } }
+ */
+export async function listTagsDirect(args, log, context = {}) {
+	// Destructure expected args
+	const { tasksJsonPath, showMetadata = false, projectRoot } = args;
+	const { session } = context;
+
+	// Enable silent mode to prevent console logs from interfering with JSON response
+	enableSilentMode();
+
+	// Create logger wrapper using the utility
+	const mcpLog = createLogWrapper(log);
+
+	try {
+		// Check if tasksJsonPath was provided
+		if (!tasksJsonPath) {
+			log.error('listTagsDirect called without tasksJsonPath');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_ARGUMENT',
+					message: 'tasksJsonPath is required'
+				}
+			};
+		}
+
+		log.info('Listing all tags');
+
+		// Prepare options
+		const options = {
+			showMetadata
+		};
+
+		// Call the tags function
+		const result = await tags(
+			tasksJsonPath,
+			options,
+			{
+				session,
+				mcpLog,
+				projectRoot
+			},
+			'json' // outputFormat - use 'json' to suppress CLI UI
+		);
+
+		// Transform the result to remove full task data and provide summary info
+		const tagsSummary = result.tags.map((tag) => {
+			const tasks = tag.tasks || [];
+
+			// Calculate status breakdown
+			const statusBreakdown = tasks.reduce((acc, task) => {
+				const status = task.status || 'pending';
+				acc[status] = (acc[status] || 0) + 1;
+				return acc;
+			}, {});
+
+			// Calculate subtask counts
+			const subtaskCounts = tasks.reduce(
+				(acc, task) => {
+					if (task.subtasks && task.subtasks.length > 0) {
+						acc.totalSubtasks += task.subtasks.length;
+						task.subtasks.forEach((subtask) => {
+							const subStatus = subtask.status || 'pending';
+							acc.subtasksByStatus[subStatus] =
+								(acc.subtasksByStatus[subStatus] || 0) + 1;
+						});
+					}
+					return acc;
+				},
+				{ totalSubtasks: 0, subtasksByStatus: {} }
+			);
+
+			return {
+				name: tag.name,
+				isCurrent: tag.isCurrent,
+				taskCount: tasks.length,
+				completedTasks: tag.completedTasks,
+				statusBreakdown,
+				subtaskCounts,
+				created: tag.created,
+				description: tag.description
+			};
+		});
+
+		// Restore normal logging
+		disableSilentMode();
+
+		return {
+			success: true,
+			data: {
+				tags: tagsSummary,
+				currentTag: result.currentTag,
+				totalTags: result.totalTags,
+				message: `Found ${result.totalTags} tag(s)`
+			}
+		};
+	} catch (error) {
+		// Make sure to restore normal logging even if there's an error
+		disableSilentMode();
+
+		log.error(`Error in listTagsDirect: ${error.message}`);
+		return {
+			success: false,
+			error: {
+				code: error.code || 'LIST_TAGS_ERROR',
+				message: error.message
+			}
+		};
+	}
+}

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

@@ -14,11 +14,12 @@ import {
  *
  * @param {Object} args - Command arguments (now expecting tasksJsonPath explicitly).
  * @param {Object} log - Logger object.
- * @returns {Promise<Object>} - Task list result { success: boolean, data?: any, error?: { code: string, message: string }, fromCache: boolean }.
+ * @returns {Promise<Object>} - Task list result { success: boolean, data?: any, error?: { code: string, message: string } }.
  */
-export async function listTasksDirect(args, log) {
+export async function listTasksDirect(args, log, context = {}) {
 	// Destructure the explicit tasksJsonPath from args
-	const { tasksJsonPath, reportPath, status, withSubtasks } = args;
+	const { tasksJsonPath, reportPath, status, withSubtasks, projectRoot } = args;
+	const { session } = context;
 
 	if (!tasksJsonPath) {
 		log.error('listTasksDirect called without tasksJsonPath');
@@ -27,8 +28,7 @@ export async function listTasksDirect(args, log) {
 			error: {
 				code: 'MISSING_ARGUMENT',
 				message: 'tasksJsonPath is required'
-			},
+			}
-			fromCache: false
 		};
 	}
 
@@ -51,7 +51,9 @@ export async function listTasksDirect(args, log) {
 				statusFilter,
 				reportPath,
 				withSubtasksFilter,
-				'json'
+				'json',
+				null, // tag
+				{ projectRoot, session } // context
 			);
 
 			if (!resultData || !resultData.tasks) {

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

@@ -13,6 +13,41 @@ import {
 	disableSilentMode
 } from '../../../../scripts/modules/utils.js';
 import { createLogWrapper } from '../../tools/utils.js';
+import { CUSTOM_PROVIDERS_ARRAY } from '../../../../src/constants/providers.js';
+
+// Define supported roles for model setting
+const MODEL_ROLES = ['main', 'research', 'fallback'];
+
+/**
+ * Determine provider hint from custom provider flags
+ * @param {Object} args - Arguments containing provider flags
+ * @returns {string|undefined} Provider hint or undefined if no custom provider flag is set
+ */
+function getProviderHint(args) {
+	return CUSTOM_PROVIDERS_ARRAY.find((provider) => args[provider]);
+}
+
+/**
+ * Handle setting models for different roles
+ * @param {Object} args - Arguments containing role-specific model IDs
+ * @param {Object} context - Context object with session, mcpLog, projectRoot
+ * @returns {Object|null} Result if a model was set, null if no model setting was requested
+ */
+async function handleModelSetting(args, context) {
+	for (const role of MODEL_ROLES) {
+		const roleKey = `set${role.charAt(0).toUpperCase() + role.slice(1)}`; // setMain, setResearch, setFallback
+
+		if (args[roleKey]) {
+			const providerHint = getProviderHint(args);
+
+			return await setModel(role, args[roleKey], {
+				...context,
+				providerHint
+			});
+		}
+	}
+	return null; // No model setting was requested
+}
 
 /**
  * Get or update model configuration
@@ -31,16 +66,21 @@ export async function modelsDirect(args, log, context = {}) {
 	log.info(`Executing models_direct with args: ${JSON.stringify(args)}`);
 	log.info(`Using project root: ${projectRoot}`);
 
-	// Validate flags: cannot use both openrouter and ollama simultaneously
+	// Validate flags: only one custom provider flag can be used simultaneously
-	if (args.openrouter && args.ollama) {
+	const customProviderFlags = CUSTOM_PROVIDERS_ARRAY.filter(
+		(provider) => args[provider]
+	);
+
+	if (customProviderFlags.length > 1) {
 		log.error(
-			'Error: Cannot use both openrouter and ollama flags simultaneously.'
+			'Error: Cannot use multiple custom provider flags simultaneously.'
 		);
 		return {
 			success: false,
 			error: {
 				code: 'INVALID_ARGS',
-				message: 'Cannot use both openrouter and ollama flags simultaneously.'
+				message:
+					'Cannot use multiple custom provider flags simultaneously. Choose only one: openrouter, ollama, bedrock, azure, or vertex.'
 			}
 		};
 	}
@@ -54,55 +94,22 @@ export async function modelsDirect(args, log, context = {}) {
 				return await getAvailableModelsList({
 					session,
 					mcpLog,
-					projectRoot // Pass projectRoot to function
+					projectRoot
 				});
 			}
 
-			// Handle setting a specific model
+			// Handle setting any model role using unified function
-			if (args.setMain) {
+			const modelContext = { session, mcpLog, projectRoot };
-				return await setModel('main', args.setMain, {
+			const modelSetResult = await handleModelSetting(args, modelContext);
-					session,
+			if (modelSetResult) {
-					mcpLog,
+				return modelSetResult;
-					projectRoot, // Pass projectRoot to function
-					providerHint: args.openrouter
-						? 'openrouter'
-						: args.ollama
-							? 'ollama'
-							: undefined // Pass hint
-				});
-			}
-
-			if (args.setResearch) {
-				return await setModel('research', args.setResearch, {
-					session,
-					mcpLog,
-					projectRoot, // Pass projectRoot to function
-					providerHint: args.openrouter
-						? 'openrouter'
-						: args.ollama
-							? 'ollama'
-							: undefined // Pass hint
-				});
-			}
-
-			if (args.setFallback) {
-				return await setModel('fallback', args.setFallback, {
-					session,
-					mcpLog,
-					projectRoot, // Pass projectRoot to function
-					providerHint: args.openrouter
-						? 'openrouter'
-						: args.ollama
-							? 'ollama'
-							: undefined // Pass hint
-				});
 			}
 
 			// Default action: get current configuration
 			return await getModelConfiguration({
 				session,
 				mcpLog,
-				projectRoot // Pass projectRoot to function
+				projectRoot
 			});
 		} finally {
 			disableSilentMode();

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

@@ -0,0 +1,105 @@
+/**
+ * Direct function wrapper for moveTask
+ */
+
+import { moveTask } from '../../../../scripts/modules/task-manager.js';
+import { findTasksPath } from '../utils/path-utils.js';
+import {
+	enableSilentMode,
+	disableSilentMode
+} from '../../../../scripts/modules/utils.js';
+
+/**
+ * Move a task or subtask to a new position
+ * @param {Object} args - Function arguments
+ * @param {string} args.tasksJsonPath - Explicit path to the tasks.json file
+ * @param {string} args.sourceId - ID of the task/subtask to move (e.g., '5' or '5.2' or '5,6,7')
+ * @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 {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;
+
+	// Validate required parameters
+	if (!args.sourceId) {
+		return {
+			success: false,
+			error: {
+				message: 'Source ID is required',
+				code: 'MISSING_SOURCE_ID'
+			}
+		};
+	}
+
+	if (!args.destinationId) {
+		return {
+			success: false,
+			error: {
+				message: 'Destination ID is required',
+				code: 'MISSING_DESTINATION_ID'
+			}
+		};
+	}
+
+	try {
+		// Find tasks.json path if not provided
+		let tasksPath = args.tasksJsonPath || args.file;
+		if (!tasksPath) {
+			if (!args.projectRoot) {
+				return {
+					success: false,
+					error: {
+						message:
+							'Project root is required if tasksJsonPath is not provided',
+						code: 'MISSING_PROJECT_ROOT'
+					}
+				};
+			}
+			tasksPath = findTasksPath(args, log);
+		}
+
+		// Enable silent mode to prevent console output during MCP operation
+		enableSilentMode();
+
+		// Call the core moveTask function with file generation control
+		const generateFiles = args.generateFiles !== false; // Default to true
+		const result = await moveTask(
+			tasksPath,
+			args.sourceId,
+			args.destinationId,
+			generateFiles,
+			{
+				projectRoot: args.projectRoot,
+				tag: args.tag
+			}
+		);
+
+		// Restore console output
+		disableSilentMode();
+
+		return {
+			success: true,
+			data: {
+				...result,
+				message: `Successfully moved task/subtask ${args.sourceId} to ${args.destinationId}`
+			}
+		};
+	} catch (error) {
+		// Restore console output in case of error
+		disableSilentMode();
+
+		log.error(`Failed to move task: ${error.message}`);
+
+		return {
+			success: false,
+			error: {
+				message: error.message,
+				code: 'MOVE_TASK_ERROR'
+			}
+		};
+	}
+}

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

@@ -19,11 +19,12 @@ import {
  * @param {Object} args - Command arguments
  * @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
  * @param {Object} log - Logger object
- * @returns {Promise<Object>} - Next task result { success: boolean, data?: any, error?: { code: string, message: string }, fromCache: boolean }
+ * @returns {Promise<Object>} - Next task result { success: boolean, data?: any, error?: { code: string, message: string } }
  */
-export async function nextTaskDirect(args, log) {
+export async function nextTaskDirect(args, log, context = {}) {
 	// Destructure expected args
-	const { tasksJsonPath, reportPath } = args;
+	const { tasksJsonPath, reportPath, projectRoot } = args;
+	const { session } = context;
 
 	if (!tasksJsonPath) {
 		log.error('nextTaskDirect called without tasksJsonPath');
@@ -32,8 +33,7 @@ export async function nextTaskDirect(args, log) {
 			error: {
 				code: 'MISSING_ARGUMENT',
 				message: 'tasksJsonPath is required'
-			},
+			}
-			fromCache: false
 		};
 	}
 
@@ -46,7 +46,7 @@ export async function nextTaskDirect(args, log) {
 			log.info(`Finding next task from ${tasksJsonPath}`);
 
 			// Read tasks data using the provided path
-			const data = readJSON(tasksJsonPath);
+			const data = readJSON(tasksJsonPath, projectRoot);
 			if (!data || !data.tasks) {
 				disableSilentMode(); // Disable before return
 				return {
@@ -121,7 +121,7 @@ export async function nextTaskDirect(args, log) {
 	// Use the caching utility
 	try {
 		const result = await coreNextTaskAction();
-		log.info(`nextTaskDirect completed.`);
+		log.info('nextTaskDirect completed.');
 		return result;
 	} catch (error) {
 		log.error(`Unexpected error during nextTask: ${error.message}`);
@@ -130,8 +130,7 @@ export async function nextTaskDirect(args, log) {
 			error: {
 				code: 'UNEXPECTED_ERROR',
 				message: error.message
-			},
+			}
-			fromCache: false
 		};
 	}
 }

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

@@ -13,6 +13,8 @@ import {
 } from '../../../../scripts/modules/utils.js';
 import { createLogWrapper } from '../../tools/utils.js';
 import { getDefaultNumTasks } from '../../../../scripts/modules/config-manager.js';
+import { resolvePrdPath, resolveProjectPath } from '../utils/path-utils.js';
+import { TASKMASTER_TASKS_FILE } from '../../../../src/constants/paths.js';
 
 /**
  * Direct function wrapper for parsing PRD documents and generating tasks.
@@ -31,6 +33,7 @@ export async function parsePRDDirect(args, log, context = {}) {
 		numTasks: numTasksArg,
 		force,
 		append,
+		research,
 		projectRoot
 	} = args;
 
@@ -48,7 +51,20 @@ export async function parsePRDDirect(args, log, context = {}) {
 			}
 		};
 	}
-	if (!inputArg) {
+
+	// Resolve input path using path utilities
+	let inputPath;
+	if (inputArg) {
+		try {
+			inputPath = resolvePrdPath({ input: inputArg, projectRoot }, session);
+		} catch (error) {
+			logWrapper.error(`Error resolving PRD path: ${error.message}`);
+			return {
+				success: false,
+				error: { code: 'FILE_NOT_FOUND', message: error.message }
+			};
+		}
+	} else {
 		logWrapper.error('parsePRDDirect called without input path');
 		return {
 			success: false,
@@ -56,11 +72,13 @@ export async function parsePRDDirect(args, log, context = {}) {
 		};
 	}
 
-	// Resolve input and output paths relative to projectRoot
+	// Resolve output path - use new path utilities for default
-	const inputPath = path.resolve(projectRoot, inputArg);
 	const outputPath = outputArg
-		? path.resolve(projectRoot, outputArg)
+		? path.isAbsolute(outputArg)
-		: path.resolve(projectRoot, 'tasks', 'tasks.json'); // Default output path
+			? outputArg
+			: path.resolve(projectRoot, outputArg)
+		: resolveProjectPath(TASKMASTER_TASKS_FILE, args) ||
+			path.resolve(projectRoot, TASKMASTER_TASKS_FILE);
 
 	// Check if input file exists
 	if (!fs.existsSync(inputPath)) {
@@ -78,17 +96,12 @@ export async function parsePRDDirect(args, log, context = {}) {
 			logWrapper.info(`Creating output directory: ${outputDir}`);
 			fs.mkdirSync(outputDir, { recursive: true });
 		}
-	} catch (dirError) {
+	} catch (error) {
-		logWrapper.error(
+		const errorMsg = `Failed to create output directory ${outputDir}: ${error.message}`;
-			`Failed to create output directory ${outputDir}: ${dirError.message}`
+		logWrapper.error(errorMsg);
-		);
-		// Return an error response immediately if dir creation fails
 		return {
 			success: false,
-			error: {
+			error: { code: 'DIRECTORY_CREATE_FAILED', message: errorMsg }
-				code: 'DIRECTORY_CREATION_ERROR',
-				message: `Failed to create output directory: ${dirError.message}`
-			}
 		};
 	}
 
@@ -96,7 +109,7 @@ export async function parsePRDDirect(args, log, context = {}) {
 	if (numTasksArg) {
 		numTasks =
 			typeof numTasksArg === 'string' ? parseInt(numTasksArg, 10) : numTasksArg;
-		if (isNaN(numTasks) || numTasks <= 0) {
+		if (Number.isNaN(numTasks) || numTasks <= 0) {
 			// Ensure positive number
 			numTasks = getDefaultNumTasks(projectRoot); // Fallback to default if parsing fails or invalid
 			logWrapper.warn(
@@ -114,8 +127,14 @@ export async function parsePRDDirect(args, log, context = {}) {
 		}
 	}
 
+	if (research) {
+		logWrapper.info(
+			'Research mode enabled. Using Perplexity AI for enhanced PRD analysis.'
+		);
+	}
+
 	logWrapper.info(
-		`Parsing PRD via direct function. Input: ${inputPath}, Output: ${outputPath}, NumTasks: ${numTasks}, Force: ${force}, Append: ${append}, ProjectRoot: ${projectRoot}`
+		`Parsing PRD via direct function. Input: ${inputPath}, Output: ${outputPath}, NumTasks: ${numTasks}, Force: ${force}, Append: ${append}, Research: ${research}, ProjectRoot: ${projectRoot}`
 	);
 
 	const wasSilent = isSilentMode();
@@ -135,6 +154,7 @@ export async function parsePRDDirect(args, log, context = {}) {
 				projectRoot,
 				force,
 				append,
+				research,
 				commandName: 'parse-prd',
 				outputType: 'mcp'
 			},
@@ -150,7 +170,8 @@ export async function parsePRDDirect(args, log, context = {}) {
 				data: {
 					message: successMsg,
 					outputPath: result.tasksPath,
-					telemetryData: result.telemetryData
+					telemetryData: result.telemetryData,
+					tagInfo: result.tagInfo
 				}
 			};
 		} else {

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

@@ -21,11 +21,12 @@ import {
  * @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 {Object} log - Logger object
- * @returns {Promise<Object>} - Remove task result { success: boolean, data?: any, error?: { code: string, message: string }, fromCache: false }
+ * @returns {Promise<Object>} - Remove task result { success: boolean, data?: any, error?: { code: string, message: string } }
  */
-export async function removeTaskDirect(args, log) {
+export async function removeTaskDirect(args, log, context = {}) {
 	// Destructure expected args
-	const { tasksJsonPath, id } = args;
+	const { tasksJsonPath, id, projectRoot } = args;
+	const { session } = context;
 	try {
 		// Check if tasksJsonPath was provided
 		if (!tasksJsonPath) {
@@ -35,8 +36,7 @@ export async function removeTaskDirect(args, log) {
 				error: {
 					code: 'MISSING_ARGUMENT',
 					message: 'tasksJsonPath is required'
-				},
+				}
-				fromCache: false
 			};
 		}
 
@@ -48,8 +48,7 @@ export async function removeTaskDirect(args, log) {
 				error: {
 					code: 'INPUT_VALIDATION_ERROR',
 					message: 'Task ID is required'
-				},
+				}
-				fromCache: false
 			};
 		}
 
@@ -61,15 +60,14 @@ export async function removeTaskDirect(args, log) {
 		);
 
 		// Validate all task IDs exist before proceeding
-		const data = readJSON(tasksJsonPath);
+		const data = readJSON(tasksJsonPath, projectRoot);
 		if (!data || !data.tasks) {
 			return {
 				success: false,
 				error: {
 					code: 'INVALID_TASKS_FILE',
 					message: `No valid tasks found in ${tasksJsonPath}`
-				},
+				}
-				fromCache: false
 			};
 		}
 
@@ -83,8 +81,7 @@ export async function removeTaskDirect(args, log) {
 				error: {
 					code: 'INVALID_TASK_ID',
 					message: `The following tasks were not found: ${invalidTasks.join(', ')}`
-				},
+				}
-				fromCache: false
 			};
 		}
 
@@ -133,8 +130,7 @@ export async function removeTaskDirect(args, log) {
 					details: failedRemovals
 						.map((r) => `${r.taskId}: ${r.error}`)
 						.join('; ')
-				},
+				}
-				fromCache: false
 			};
 		}
 
@@ -147,8 +143,7 @@ export async function removeTaskDirect(args, log) {
 				failed: failedRemovals.length,
 				results: results,
 				tasksPath: tasksJsonPath
-			},
+			}
-			fromCache: false
 		};
 	} catch (error) {
 		// Ensure silent mode is disabled even if an outer error occurs
@@ -161,8 +156,7 @@ export async function removeTaskDirect(args, log) {
 			error: {
 				code: 'UNEXPECTED_ERROR',
 				message: error.message
-			},
+			}
-			fromCache: false
 		};
 	}
 }

mcp-server/src/core/direct-functions/rename-tag.js

@@ -0,0 +1,118 @@
+/**
+ * rename-tag.js
+ * Direct function implementation for renaming a tag
+ */
+
+import { renameTag } from '../../../../scripts/modules/task-manager/tag-management.js';
+import {
+	enableSilentMode,
+	disableSilentMode
+} from '../../../../scripts/modules/utils.js';
+import { createLogWrapper } from '../../tools/utils.js';
+
+/**
+ * Direct function wrapper for renaming a tag with error handling.
+ *
+ * @param {Object} args - Command arguments
+ * @param {string} args.oldName - Current name of the tag to rename
+ * @param {string} args.newName - New name for the tag
+ * @param {string} [args.tasksJsonPath] - Path to the tasks.json file (resolved by tool)
+ * @param {string} [args.projectRoot] - Project root path
+ * @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 } }
+ */
+export async function renameTagDirect(args, log, context = {}) {
+	// Destructure expected args
+	const { tasksJsonPath, oldName, newName, projectRoot } = args;
+	const { session } = context;
+
+	// Enable silent mode to prevent console logs from interfering with JSON response
+	enableSilentMode();
+
+	// Create logger wrapper using the utility
+	const mcpLog = createLogWrapper(log);
+
+	try {
+		// Check if tasksJsonPath was provided
+		if (!tasksJsonPath) {
+			log.error('renameTagDirect called without tasksJsonPath');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_ARGUMENT',
+					message: 'tasksJsonPath is required'
+				}
+			};
+		}
+
+		// Check required parameters
+		if (!oldName || typeof oldName !== 'string') {
+			log.error('Missing required parameter: oldName');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_PARAMETER',
+					message: 'Old tag name is required and must be a string'
+				}
+			};
+		}
+
+		if (!newName || typeof newName !== 'string') {
+			log.error('Missing required parameter: newName');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_PARAMETER',
+					message: 'New tag name is required and must be a string'
+				}
+			};
+		}
+
+		log.info(`Renaming tag from "${oldName}" to "${newName}"`);
+
+		// Call the renameTag function
+		const result = await renameTag(
+			tasksJsonPath,
+			oldName,
+			newName,
+			{}, // options (empty for now)
+			{
+				session,
+				mcpLog,
+				projectRoot
+			},
+			'json' // outputFormat - use 'json' to suppress CLI UI
+		);
+
+		// Restore normal logging
+		disableSilentMode();
+
+		return {
+			success: true,
+			data: {
+				oldName: result.oldName,
+				newName: result.newName,
+				renamed: result.renamed,
+				taskCount: result.taskCount,
+				wasCurrentTag: result.wasCurrentTag,
+				message: `Successfully renamed tag from "${result.oldName}" to "${result.newName}"`
+			}
+		};
+	} catch (error) {
+		// Make sure to restore normal logging even if there's an error
+		disableSilentMode();
+
+		log.error(`Error in renameTagDirect: ${error.message}`);
+		return {
+			success: false,
+			error: {
+				code: error.code || 'RENAME_TAG_ERROR',
+				message: error.message
+			}
+		};
+	}
+}

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

@@ -0,0 +1,249 @@
+/**
+ * research.js
+ * Direct function implementation for AI-powered research queries
+ */
+
+import path from 'path';
+import { performResearch } from '../../../../scripts/modules/task-manager.js';
+import {
+	enableSilentMode,
+	disableSilentMode
+} from '../../../../scripts/modules/utils.js';
+import { createLogWrapper } from '../../tools/utils.js';
+
+/**
+ * Direct function wrapper for performing AI-powered research with project context.
+ *
+ * @param {Object} args - Command arguments
+ * @param {string} args.query - Research query/prompt (required)
+ * @param {string} [args.taskIds] - Comma-separated list of task/subtask IDs for context
+ * @param {string} [args.filePaths] - Comma-separated list of file paths for context
+ * @param {string} [args.customContext] - Additional custom context text
+ * @param {boolean} [args.includeProjectTree=false] - Include project file tree in context
+ * @param {string} [args.detailLevel='medium'] - Detail level: 'low', 'medium', 'high'
+ * @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 {Object} log - Logger object
+ * @param {Object} context - Additional context (session)
+ * @returns {Promise<Object>} - Result object { success: boolean, data?: any, error?: { code: string, message: string } }
+ */
+export async function researchDirect(args, log, context = {}) {
+	// Destructure expected args
+	const {
+		query,
+		taskIds,
+		filePaths,
+		customContext,
+		includeProjectTree = false,
+		detailLevel = 'medium',
+		saveTo,
+		saveToFile = false,
+		projectRoot
+	} = args;
+	const { session } = context; // Destructure session from context
+
+	// Enable silent mode to prevent console logs from interfering with JSON response
+	enableSilentMode();
+
+	// Create logger wrapper using the utility
+	const mcpLog = createLogWrapper(log);
+
+	try {
+		// Check required parameters
+		if (!query || typeof query !== 'string' || query.trim().length === 0) {
+			log.error('Missing or invalid required parameter: query');
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'MISSING_PARAMETER',
+					message:
+						'The query parameter is required and must be a non-empty string'
+				}
+			};
+		}
+
+		// Parse comma-separated task IDs if provided
+		const parsedTaskIds = taskIds
+			? taskIds
+					.split(',')
+					.map((id) => id.trim())
+					.filter((id) => id.length > 0)
+			: [];
+
+		// Parse comma-separated file paths if provided
+		const parsedFilePaths = filePaths
+			? filePaths
+					.split(',')
+					.map((path) => path.trim())
+					.filter((path) => path.length > 0)
+			: [];
+
+		// Validate detail level
+		const validDetailLevels = ['low', 'medium', 'high'];
+		if (!validDetailLevels.includes(detailLevel)) {
+			log.error(`Invalid detail level: ${detailLevel}`);
+			disableSilentMode();
+			return {
+				success: false,
+				error: {
+					code: 'INVALID_PARAMETER',
+					message: `Detail level must be one of: ${validDetailLevels.join(', ')}`
+				}
+			};
+		}
+
+		log.info(
+			`Performing research query: "${query.substring(0, 100)}${query.length > 100 ? '...' : ''}", ` +
+				`taskIds: [${parsedTaskIds.join(', ')}], ` +
+				`filePaths: [${parsedFilePaths.join(', ')}], ` +
+				`detailLevel: ${detailLevel}, ` +
+				`includeProjectTree: ${includeProjectTree}, ` +
+				`projectRoot: ${projectRoot}`
+		);
+
+		// Prepare options for the research function
+		const researchOptions = {
+			taskIds: parsedTaskIds,
+			filePaths: parsedFilePaths,
+			customContext: customContext || '',
+			includeProjectTree,
+			detailLevel,
+			projectRoot,
+			saveToFile
+		};
+
+		// Prepare context for the research function
+		const researchContext = {
+			session,
+			mcpLog,
+			commandName: 'research',
+			outputType: 'mcp'
+		};
+
+		// Call the performResearch function
+		const result = await performResearch(
+			query.trim(),
+			researchOptions,
+			researchContext,
+			'json', // outputFormat - use 'json' to suppress CLI UI
+			false // allowFollowUp - disable for MCP calls
+		);
+
+		// Auto-save to task/subtask if requested
+		if (saveTo) {
+			try {
+				const isSubtask = saveTo.includes('.');
+
+				// Format research content for saving
+				const researchContent = `## Research Query: ${query.trim()}
+
+**Detail Level:** ${result.detailLevel}
+**Context Size:** ${result.contextSize} characters
+**Timestamp:** ${new Date().toLocaleDateString()} ${new Date().toLocaleTimeString()}
+
+### Results
+
+${result.result}`;
+
+				if (isSubtask) {
+					// Save to subtask
+					const { updateSubtaskById } = await import(
+						'../../../../scripts/modules/task-manager/update-subtask-by-id.js'
+					);
+
+					const tasksPath = path.join(
+						projectRoot,
+						'.taskmaster',
+						'tasks',
+						'tasks.json'
+					);
+					await updateSubtaskById(
+						tasksPath,
+						saveTo,
+						researchContent,
+						false, // useResearch = false for simple append
+						{
+							session,
+							mcpLog,
+							commandName: 'research-save',
+							outputType: 'mcp',
+							projectRoot
+						},
+						'json'
+					);
+
+					log.info(`Research saved to subtask ${saveTo}`);
+				} else {
+					// Save to task
+					const updateTaskById = (
+						await import(
+							'../../../../scripts/modules/task-manager/update-task-by-id.js'
+						)
+					).default;
+
+					const taskIdNum = parseInt(saveTo, 10);
+					const tasksPath = path.join(
+						projectRoot,
+						'.taskmaster',
+						'tasks',
+						'tasks.json'
+					);
+					await updateTaskById(
+						tasksPath,
+						taskIdNum,
+						researchContent,
+						false, // useResearch = false for simple append
+						{
+							session,
+							mcpLog,
+							commandName: 'research-save',
+							outputType: 'mcp',
+							projectRoot
+						},
+						'json',
+						true // appendMode = true
+					);
+
+					log.info(`Research saved to task ${saveTo}`);
+				}
+			} catch (saveError) {
+				log.warn(`Error saving research to task/subtask: ${saveError.message}`);
+			}
+		}
+
+		// Restore normal logging
+		disableSilentMode();
+
+		return {
+			success: true,
+			data: {
+				query: result.query,
+				result: result.result,
+				contextSize: result.contextSize,
+				contextTokens: result.contextTokens,
+				tokenBreakdown: result.tokenBreakdown,
+				systemPromptTokens: result.systemPromptTokens,
+				userPromptTokens: result.userPromptTokens,
+				totalInputTokens: result.totalInputTokens,
+				detailLevel: result.detailLevel,
+				telemetryData: result.telemetryData,
+				tagInfo: result.tagInfo,
+				savedFilePath: result.savedFilePath
+			}
+		};
+	} catch (error) {
+		// Make sure to restore normal logging even if there's an error
+		disableSilentMode();
+
+		log.error(`Error in researchDirect: ${error.message}`);
+		return {
+			success: false,
+			error: {
+				code: error.code || 'RESEARCH_ERROR',
+				message: error.message
+			}
+		};
+	}
+}