chore: improve pre-release CI to be able to release more than one release candidate (#1036)

* chore: improve pre-release CI to be able to release more than one release candidate

* chore: implement requested changes from coderabbit

* chore: apply requested changes

.changeset/add-kiro-profile.md

@@ -1,9 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add Kiro editor rule profile support
-
-- Add support for Kiro IDE with custom rule files and MCP configuration
-- Generate rule files in `.kiro/steering/` directory with markdown format
-- Include MCP server configuration with enhanced file inclusion patterns

.changeset/claude-import-fix-new.md

@@ -1,12 +0,0 @@
----
-"task-master-ai": patch
----
-
-Prevent CLAUDE.md overwrite by using Claude Code's import feature
-
-- Task Master now creates its instructions in `.taskmaster/CLAUDE.md` instead of overwriting the user's `CLAUDE.md`
-- Adds an import section to the user's CLAUDE.md that references the Task Master instructions
-- Preserves existing user content in CLAUDE.md files
-- Provides clean uninstall that only removes Task Master's additions
-
-**Breaking Change**: Task Master instructions for Claude Code are now stored in `.taskmaster/CLAUDE.md` and imported into the main CLAUDE.md file. Users who previously had Task Master content directly in their CLAUDE.md will need to run `task-master rules remove claude` followed by `task-master rules add claude` to migrate to the new structure.

.changeset/cool-glasses-invite.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Implement Boundary-First Tag Resolution to ensure consistent and deterministic tag handling across CLI and MCP, resolving potential race conditions.

.changeset/fix-gemini-cli-dependency.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Fix compatibility with @google/gemini-cli-core v0.1.12+ by updating ai-sdk-provider-gemini-cli to v0.1.1.

.changeset/fix-show-command-complexity.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix: show command no longer requires complexity report file to exist
-
-The `tm show` command was incorrectly requiring the complexity report file to exist even when not needed. Now it only validates the complexity report path when a custom report file is explicitly provided via the -r/--report option.

.changeset/fresh-bugs-squashed.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Fix 'expand --all' and 'show' commands to correctly handle tag contexts for complexity reports and task display.

.changeset/gentle-beds-beam.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Update VS Code profile with MCP config transformation

.changeset/groq-kimi-k2-support.md

@@ -1,10 +0,0 @@
----
-"task-master-ai": minor
----
-
-Complete Groq provider integration and add MoonshotAI Kimi K2 model support
-
-- Fixed Groq provider registration
-- Added Groq API key validation
-- Added GROQ_API_KEY to .env.example
-- Added moonshotai/kimi-k2-instruct model with $1/$3 per 1M token pricing and 16k max output

.changeset/happy-sites-stay.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Clean up remaining automatic task file generation calls

.changeset/metal-papers-stay.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": minor
----
-
-feat: Add Zed editor rule profile with agent rules and MCP config
-
-- Resolves #637

.changeset/orange-pots-add.md

@@ -0,0 +1,24 @@
+---
+"task-master-ai": minor
+---
+
+Add comprehensive Kiro IDE integration with autonomous task management hooks
+
+- **Kiro Profile**: Added full support for Kiro IDE with automatic installation of 7 Taskmaster agent hooks
+- **Hook-Driven Workflow**: Introduced natural language automation hooks that eliminate manual task status updates
+- **Automatic Hook Installation**: Hooks are now automatically copied to `.kiro/hooks/` when running `task-master rules add kiro`
+- **Language-Agnostic Support**: All hooks support multiple programming languages (JS, Python, Go, Rust, Java, etc.)
+- **Frontmatter Transformation**: Kiro rules use simplified `inclusion: always` format instead of Cursor's complex frontmatter
+- **Special Rule**: Added `taskmaster_hooks_workflow.md` that guides AI assistants to prefer hook-driven completion
+
+Key hooks included:
+
+- Task Dependency Auto-Progression: Automatically starts tasks when dependencies complete
+- Code Change Task Tracker: Updates task progress as you save files
+- Test Success Task Completer: Marks tasks done when tests pass
+- Daily Standup Assistant: Provides personalized task status summaries
+- PR Readiness Checker: Validates task completion before creating pull requests
+- Complexity Analyzer: Auto-expands complex tasks into manageable subtasks
+- Git Commit Task Linker: Links commits to tasks for better traceability
+
+This creates a truly autonomous development workflow where task management happens naturally as you code!

.changeset/public-crabs-ask.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add Amp rule profile with AGENT.md and MCP config

.changeset/puny-friends-give.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix MCP server error when retrieving tools and resources

.changeset/quiet-rabbits-bathe.md

@@ -0,0 +1,10 @@
+---
+"task-master-ai": patch
+---
+
+Fix max_tokens limits for OpenRouter and Groq models
+
+- Add special handling in config-manager.js for custom OpenRouter models to use a conservative default of 32,768 max_tokens
+- Update qwen/qwen-turbo model max_tokens from 1,000,000 to 32,768 to match OpenRouter's actual limits
+- Fix moonshotai/kimi-k2-instruct max_tokens to 16,384 to match Groq's actual limit (fixes #1028)
+- This prevents "maximum context length exceeded" errors when using OpenRouter models not in our supported models list

.changeset/swift-otters-argue.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Fix VSCode profile generation to use correct rule file names (using `.instructions.md` extension instead of `.md`) and front-matter properties (removing the unsupported `alwaysApply` property from instructions files' front-matter).

.changeset/swift-turtles-sit.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Add MCP configuration support to Claude Code rules

.changeset/ten-glasses-feel.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fixed the comprehensive taskmaster system integration via custom slash commands with proper syntax
-
-- Provide claude clode with a complete set of of commands that can trigger task master events directly within Claude Code

.changeset/update-mcp-readme.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.

.changeset/yellow-showers-heal.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add OpenCode profile with AGENTS.md and MCP config
-
-- Resolves #965

.changeset/yummy-walls-eat.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Add missing API keys to .env.example and README.md

.cursor/rules/commands.mdc

@@ -523,7 +523,7 @@ For AI-powered commands that benefit from project context, follow the research c
     .option('--details <details>', 'Implementation details for the new subtask, optional')
     .option('--dependencies <ids>', 'Comma-separated list of subtask IDs this subtask depends on')
     .option('--status <status>', 'Initial status for the subtask', 'pending')
-    .option('--skip-generate', 'Skip regenerating task files')
+    .option('--generate', 'Regenerate task files after adding subtask')
     .action(async (options) => {
       // Validate required parameters
       if (!options.parent) {
@@ -545,7 +545,7 @@ For AI-powered commands that benefit from project context, follow the research c
     .option('-f, --file <path>', 'Path to the tasks file', 'tasks/tasks.json')
     .option('-i, --id <id>', 'ID of the subtask to remove in format parentId.subtaskId, required')
     .option('-c, --convert', 'Convert the subtask to a standalone task instead of deleting')
-    .option('--skip-generate', 'Skip regenerating task files')
+    .option('--generate', 'Regenerate task files after removing subtask')
     .action(async (options) => {
       // Implementation with detailed error handling
     })
@@ -633,11 +633,11 @@ function showAddSubtaskHelp() {
     '  --dependencies <ids>      Comma-separated list of dependency IDs\n' +
     '  -s, --status <status>     Status for the new subtask (default: "pending")\n' +
     '  -f, --file <file>         Path to the tasks file (default: "tasks/tasks.json")\n' +
-    '  --skip-generate           Skip regenerating task files\n\n' +
+    '  --generate                Regenerate task files after adding subtask\n\n' +
     chalk.cyan('Examples:') + '\n' +
     '  task-master add-subtask --parent=\'5\' --task-id=\'8\'\n' +
     '  task-master add-subtask -p \'5\' -t \'Implement login UI\' -d \'Create the login form\'\n' +
-    '  task-master add-subtask -p \'5\' -t \'Handle API Errors\' --details $\'Handle 401 Unauthorized.\nHandle 500 Server Error.\'',
+    '  task-master add-subtask -p \'5\' -t \'Handle API Errors\' --details "Handle 401 Unauthorized.\\nHandle 500 Server Error." --generate',
     { padding: 1, borderColor: 'blue', borderStyle: 'round' }
   ));
 }
@@ -652,7 +652,7 @@ function showRemoveSubtaskHelp() {
     '  -i, --id <id>       Subtask ID(s) to remove in format "parentId.subtaskId" (can be comma-separated, required)\n' +
     '  -c, --convert       Convert the subtask to a standalone task instead of deleting it\n' +
     '  -f, --file <file>   Path to the tasks file (default: "tasks/tasks.json")\n' +
-    '  --skip-generate     Skip regenerating task files\n\n' +
+    '  --generate          Regenerate task files after removing subtask\n\n' +
     chalk.cyan('Examples:') + '\n' +
     '  task-master remove-subtask --id=\'5.2\'\n' +
     '  task-master remove-subtask --id=\'5.2,6.3,7.1\'\n' +

.cursor/rules/taskmaster.mdc

@@ -158,7 +158,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `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`)
+    *   `generate`: `Enable Taskmaster to regenerate markdown task files after adding the subtask.` (CLI: `--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.
@@ -286,7 +286,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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`)
+    *   `generate`: `Enable Taskmaster to regenerate markdown task files after removing the subtask.` (CLI: `--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.

.github/workflows/pre-release.yml

@@ -16,7 +16,7 @@ jobs:
       - uses: actions/setup-node@v4
         with:
           node-version: 20
-          cache: 'npm'
+          cache: "npm"
 
       - name: Cache node_modules
         uses: actions/cache@v4
@@ -32,10 +32,13 @@ jobs:
         run: npm ci
         timeout-minutes: 2
 
-      - name: Enter RC mode
+      - name: Enter RC mode (if not already in RC mode)
         run: |
-          npx changeset pre exit || true
+          # ensure we’re in the right pre-mode (tag "rc")
+          if [ ! -f .changeset/pre.json ] \
+            || [ "$(jq -r '.tag' .changeset/pre.json 2>/dev/null || echo '')" != "rc" ]; then
             npx changeset pre enter rc
+          fi
 
       - name: Version RC packages
         run: npx changeset version
@@ -51,12 +54,9 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
 
-      - name: Exit RC mode
-        run: npx changeset pre exit
-
       - name: Commit & Push changes
         uses: actions-js/push@master
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           branch: ${{ github.ref }}
-          message: 'chore: rc version bump'
+          message: "chore: rc version bump"

.gitignore

@@ -22,17 +22,11 @@ lerna-debug.log*
 
 # Coverage directory used by tools like istanbul
 coverage/
-coverage-e2e/
 *.lcov
 
 # Jest cache
 .jest/
 
-# Test results and reports
-test-results/
-jest-results.json
-junit.xml
-
 # Test temporary files and directories
 tests/temp/
 tests/e2e/_runs/
@@ -93,9 +87,3 @@ dev-debug.log
 *.njsproj
 *.sln
 *.sw?
-
-# OS specific
-
-# Task files
-# tasks.json
-# tasks/ 

.kiro/hooks/tm-code-change-task-tracker.kiro.hook

@@ -0,0 +1,23 @@
+{
+  "enabled": true,
+  "name": "[TM] Code Change Task Tracker",
+  "description": "Track implementation progress by monitoring code changes",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      "**/*.{js,ts,jsx,tsx,py,go,rs,java,cpp,c,h,hpp,cs,rb,php,swift,kt,scala,clj}",
+      "!**/node_modules/**",
+      "!**/vendor/**",
+      "!**/.git/**",
+      "!**/build/**",
+      "!**/dist/**",
+      "!**/target/**",
+      "!**/__pycache__/**"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "I just saved a source code file. Please:\n\n1. Check what task is currently 'in-progress' using 'tm list --status=in-progress'\n2. Look at the file I saved and summarize what was changed (considering the programming language and context)\n3. Update the task's notes with: 'tm update-subtask --id=<task_id> --prompt=\"Implemented: <summary_of_changes> in <file_path>\"'\n4. If the changes seem to complete the task based on its description, ask if I want to mark it as done"
+  }
+}

.kiro/hooks/tm-complexity-analyzer.kiro.hook

@@ -0,0 +1,16 @@
+{
+  "enabled": false,
+  "name": "[TM] Complexity Analyzer",
+  "description": "Analyze task complexity when new tasks are added",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      ".taskmaster/tasks/tasks.json"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "New tasks were added to tasks.json. For each new task:\n\n1. Run 'tm analyze-complexity --id=<task_id>'\n2. If complexity score is > 7, automatically expand it: 'tm expand --id=<task_id> --num=5'\n3. Show the complexity analysis results\n4. Suggest task dependencies based on the expanded subtasks"
+  }
+}

.kiro/hooks/tm-daily-standup-assistant.kiro.hook

@@ -0,0 +1,13 @@
+{
+  "enabled": true,
+  "name": "[TM] Daily Standup Assistant",
+  "description": "Morning workflow summary and task selection",
+  "version": "1",
+  "when": {
+    "type": "userTriggered"
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "Good morning! Please provide my daily standup summary:\n\n1. Run 'tm list --status=done' and show tasks completed in the last 24 hours\n2. Run 'tm list --status=in-progress' to show current work\n3. Run 'tm next' to suggest the highest priority task to start\n4. Show the dependency graph for upcoming work\n5. Ask which task I'd like to focus on today"
+  }
+}

.kiro/hooks/tm-git-commit-task-linker.kiro.hook

@@ -0,0 +1,13 @@
+{
+  "enabled": true,
+  "name": "[TM] Git Commit Task Linker",
+  "description": "Link commits to tasks for traceability",
+  "version": "1",
+  "when": {
+    "type": "manual"
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "I'm about to commit code. Please:\n\n1. Run 'git diff --staged' to see what's being committed\n2. Analyze the changes and suggest which tasks they relate to\n3. Generate a commit message in format: 'feat(task-<id>): <description>'\n4. Update the relevant tasks with a note about this commit\n5. Show the proposed commit message for approval"
+  }
+}

.kiro/hooks/tm-pr-readiness-checker.kiro.hook

@@ -0,0 +1,13 @@
+{
+  "enabled": true,
+  "name": "[TM] PR Readiness Checker",
+  "description": "Validate tasks before creating a pull request",
+  "version": "1",
+  "when": {
+    "type": "manual"
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "I'm about to create a PR. Please:\n\n1. List all tasks marked as 'done' in this branch\n2. For each done task, verify:\n   - All subtasks are also done\n   - Test files exist for new functionality\n   - No TODO comments remain related to the task\n3. Generate a PR description listing completed tasks\n4. Suggest a PR title based on the main tasks completed"
+  }
+}

.kiro/hooks/tm-task-dependency-auto-progression.kiro.hook

@@ -0,0 +1,17 @@
+{
+  "enabled": true,
+  "name": "[TM] Task Dependency Auto-Progression",
+  "description": "Automatically progress tasks when dependencies are completed",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      ".taskmaster/tasks/tasks.json",
+      ".taskmaster/tasks/*.json"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "Check the tasks.json file for any tasks that just changed status to 'done'. For each completed task:\n\n1. Find all tasks that depend on it\n2. Check if those dependent tasks now have all their dependencies satisfied\n3. If a task has all dependencies met and is still 'pending', use the command 'tm set-status --id=<task_id> --status=in-progress' to start it\n4. Show me which tasks were auto-started and why"
+  }
+}

.kiro/hooks/tm-test-success-task-completer.kiro.hook

@@ -0,0 +1,23 @@
+{
+  "enabled": true,
+  "name": "[TM] Test Success Task Completer",
+  "description": "Mark tasks as done when their tests pass",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      "**/*test*.{js,ts,jsx,tsx,py,go,java,rb,php,rs,cpp,cs}",
+      "**/*spec*.{js,ts,jsx,tsx,rb}",
+      "**/test_*.py",
+      "**/*_test.go",
+      "**/*Test.java",
+      "**/*Tests.cs",
+      "!**/node_modules/**",
+      "!**/vendor/**"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "A test file was just saved. Please:\n\n1. Identify the test framework/language and run the appropriate test command for this file (npm test, pytest, go test, cargo test, dotnet test, mvn test, etc.)\n2. If all tests pass, check which tasks mention this functionality\n3. For any matching tasks that are 'in-progress', ask if the passing tests mean the task is complete\n4. If confirmed, mark the task as done with 'tm set-status --id=<task_id> --status=done'"
+  }
+}

.kiro/settings/mcp.json

@@ -0,0 +1,19 @@
+{
+	"mcpServers": {
+		"task-master-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",
+				"XAI_API_KEY": "YOUR_XAI_KEY_HERE",
+				"OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
+				"MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
+				"AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE",
+				"OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
+			}
+		}
+	}
+}

.kiro/steering/dev_workflow.md

@@ -1,7 +1,5 @@
 ---
-description: Guide for using Taskmaster to manage task-driven development workflows
-globs: **/*
-alwaysApply: true
+inclusion: always
 ---
 
 # Taskmaster Development Workflow
@@ -32,18 +30,18 @@ All your standard command executions should operate on the user's current task c
 
 For new projects or when users are getting started, operate within the `master` tag context:
 
--   Start new projects by running `initialize_project` tool / `task-master init` or `parse_prd` / `task-master parse-prd --input='<prd-file.txt>'` (see @`taskmaster.mdc`) 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`)
+-   Start new projects by running `initialize_project` tool / `task-master init` or `parse_prd` / `task-master parse-prd --input='<prd-file.txt>'` (see @`taskmaster.md`) to generate initial tasks.json with tagged structure
+-   Configure rule sets during initialization with `--rules` flag (e.g., `task-master init --rules kiro,windsurf`) or manage them later with `task-master rules add/remove` commands  
+-   Begin coding sessions with `get_tasks` / `task-master list` (see @`taskmaster.md`) to see current tasks, status, and IDs
+-   Determine the next task to work on using `next_task` / `task-master next` (see @`taskmaster.md`)
+-   Analyze task complexity with `analyze_project_complexity` / `task-master analyze-complexity --research` (see @`taskmaster.md`) before breaking down tasks
+-   Review complexity report using `complexity_report` / `task-master complexity-report` (see @`taskmaster.md`)
 -   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`
+-   View specific task details using `get_task` / `task-master show <id>` (see @`taskmaster.md`) to understand implementation requirements
+-   Break down complex tasks using `expand_task` / `task-master expand --id=<id> --force --research` (see @`taskmaster.md`) 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`)
+-   Mark completed tasks with `set_task_status` / `task-master set-status --id=<id> --status=done` (see @`taskmaster.md`)
+-   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.md`)
 
 ---
 
@@ -193,11 +191,11 @@ Actions:
 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**.
+    - For AI agents and integrated development environments (like Kiro), 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`.
+    - Refer to @`mcp.md` 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.md`.
     - **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.
 
@@ -206,7 +204,7 @@ Taskmaster offers two primary ways to interact:
     - 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.
+    - Refer to @`taskmaster.md` 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)
@@ -215,14 +213,14 @@ Taskmaster offers two primary ways to interact:
 - **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.
+- **Full CLI & MCP Support**: All tag management commands are available through both the CLI and MCP tools for you to use. Refer to @`taskmaster.md` 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.
+-   Run `analyze_project_complexity` / `task-master analyze-complexity --research` (see @`taskmaster.md`) for comprehensive analysis
+-   Review complexity report via `complexity_report` / `task-master complexity-report` (see @`taskmaster.md`) 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
@@ -266,7 +264,7 @@ Taskmaster offers two primary ways to interact:
 - **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`).
+- Refer to task structure details (previously linked to `tasks.md`).
 
 ## Configuration Management (Updated)
 
@@ -283,8 +281,8 @@ Taskmaster configuration is managed through two main mechanisms:
 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`).
+    *   For MCP/Kiro integration, configure these keys in the `env` section of `.kiro/mcp.json`.
+    *   Available keys/variables: See `assets/env.example` or the Configuration section in the command reference (previously linked to `taskmaster.md`).
 
 3.  **`.taskmaster/state.json` File (Tagged System State):**
     *   Tracks current tag context and migration status.
@@ -292,19 +290,19 @@ Taskmaster configuration is managed through two main mechanisms:
     *   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 MCP** verify that the API key for the selected provider is present in the `env` section of `.kiro/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
+- **Available Profiles**: Claude Code, Cline, Codex, Kiro, Roo Code, Trae, Windsurf (claude, cline, codex, kiro, roo, trae, windsurf)
+- **During Initialization**: Use `task-master init --rules kiro,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
+- **Rule Structure**: Each profile creates its own directory (e.g., `.kiro/steering`, `.roo/rules`) with appropriate configuration files
 
 ## Determining the Next Task
 
@@ -364,7 +362,7 @@ Taskmaster supports multiple AI coding assistant rule sets that can be configure
 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.
+    *   Use `get_task` / `task-master show <subtaskId>` (see @`taskmaster.md`) 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.
@@ -398,7 +396,7 @@ Once a task has been broken down into subtasks using `expand_task` or similar me
 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`).
+    *   Create new or update existing rules following internal guidelines (previously linked to `cursor_rules.md` and `self_improve.md`).
 
 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`.
@@ -407,7 +405,7 @@ Once a task has been broken down into subtasks using `expand_task` or similar me
     *   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.
+    *   Consider if a Changeset is needed according to internal versioning guidelines (previously linked to `changeset.md`). 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`).

.kiro/steering/kiro_rules.md

@@ -0,0 +1,51 @@
+---
+inclusion: always
+---
+
+- **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.md](.kiro/steering/prisma.md) 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 

.kiro/steering/self_improve.md

@@ -0,0 +1,70 @@
+---
+inclusion: always
+---
+
+- **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.md](.kiro/steering/prisma.md):
+  // - 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 [kiro_rules.md](.kiro/steering/kiro_rules.md) for proper rule formatting and structure.

.kiro/steering/taskmaster.md

@@ -1,12 +1,10 @@
 ---
-description: Comprehensive reference for Taskmaster MCP tools and CLI commands.
-globs: **/*
-alwaysApply: true
+inclusion: always
 ---
 
 # 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.
+This document provides a detailed reference for interacting with Taskmaster, covering both the recommended MCP tools, suitable for integrations like Kiro, 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. 
 
@@ -38,7 +36,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `skipInstall`: `Skip installing dependencies. Default is false.` (CLI: `--skip-install`)
     *   `addAliases`: `Add shell aliases tm and taskmaster. Default is false.` (CLI: `--aliases`)
     *   `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. 
+*   **Usage:** Run this once at the beginning of a new project, typically via an integrated tool like Kiro. 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`.
 
@@ -157,7 +155,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `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`)
+    *   `generate`: `Enable Taskmaster to regenerate markdown task files after adding the subtask.` (CLI: `--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.
@@ -285,7 +283,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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`)
+    *   `generate`: `Enable Taskmaster to regenerate markdown task files after removing the subtask.` (CLI: `--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.
@@ -551,8 +549,8 @@ Environment variables are used **only** for sensitive API keys related to AI pro
     *   `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.
+**Set API keys** in your **`.env`** file in the project root (for CLI use) or within the `env` section of your **`.kiro/mcp.json`** file (for MCP/Kiro 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 [dev_workflow.mdc](mdc:.cursor/rules/taskmaster/dev_workflow.mdc).
+For details on how these commands fit into the development process, see the [dev_workflow.md](.kiro/steering/dev_workflow.md).

.kiro/steering/taskmaster_hooks_workflow.md

@@ -0,0 +1,59 @@
+---
+inclusion: always
+---
+
+# Taskmaster Hook-Driven Workflow
+
+## Core Principle: Hooks Automate Task Management
+
+When working with Taskmaster in Kiro, **avoid manually marking tasks as done**. The hook system automatically handles task completion based on:
+
+- **Test Success**: `[TM] Test Success Task Completer` detects passing tests and prompts for task completion
+- **Code Changes**: `[TM] Code Change Task Tracker` monitors implementation progress
+- **Dependency Chains**: `[TM] Task Dependency Auto-Progression` auto-starts dependent tasks
+
+## AI Assistant Workflow
+
+Follow this pattern when implementing features:
+
+1. **Implement First**: Write code, create tests, make changes
+2. **Save Frequently**: Hooks trigger on file saves to track progress automatically
+3. **Let Hooks Decide**: Allow hooks to detect completion rather than manually setting status
+4. **Respond to Prompts**: Confirm when hooks suggest task completion
+
+## Key Rules for AI Assistants
+
+- **Never use `tm set-status --status=done`** unless hooks fail to detect completion
+- **Always write tests** - they provide the most reliable completion signal
+- **Save files after implementation** - this triggers progress tracking
+- **Trust hook suggestions** - if no completion prompt appears, more work may be needed
+
+## Automatic Behaviors
+
+The hook system provides:
+
+- **Progress Logging**: Implementation details automatically added to task notes
+- **Evidence-Based Completion**: Tasks marked done only when criteria are met
+- **Dependency Management**: Next tasks auto-started when dependencies complete
+- **Natural Flow**: Focus on coding, not task management overhead
+
+## Manual Override Cases
+
+Only manually set task status for:
+
+- Documentation-only tasks
+- Tasks without testable outcomes
+- Emergency fixes without proper test coverage
+
+Use `tm set-status` sparingly - prefer hook-driven completion.
+
+## Implementation Pattern
+
+```
+1. Implement feature → Save file
+2. Write tests → Save test file
+3. Tests pass → Hook prompts completion
+4. Confirm completion → Next task auto-starts
+```
+
+This workflow ensures proper task tracking while maintaining development flow.

.mcp.json

@@ -0,0 +1,9 @@
+{
+	"mcpServers": {
+		"task-master-ai": {
+			"type": "stdio",
+			"command": "npx",
+			"args": ["-y", "task-master-ai"]
+		}
+	}
+}

.taskmaster/CLAUDE.md

@@ -0,0 +1,417 @@
+# Task Master AI - Agent 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._

.taskmaster/reports/task-complexity-report_cc-kiro-hooks.json

@@ -0,0 +1,93 @@
+{
+	"meta": {
+		"generatedAt": "2025-07-22T09:41:10.517Z",
+		"tasksAnalyzed": 10,
+		"totalTasks": 10,
+		"analysisCount": 10,
+		"thresholdScore": 5,
+		"projectName": "Taskmaster",
+		"usedResearch": false
+	},
+	"complexityAnalysis": [
+		{
+			"taskId": 1,
+			"taskTitle": "Implement Task Integration Layer (TIL) Core",
+			"complexityScore": 8,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "Break down the TIL Core implementation into distinct components: hook registration system, task lifecycle management, event coordination, state persistence layer, and configuration validation. Each subtask should focus on a specific architectural component with clear interfaces and testable boundaries.",
+			"reasoning": "This is a foundational component with multiple complex subsystems including event-driven architecture, API integration, state management, and configuration validation. The existing 5 subtasks are well-structured and appropriately sized."
+		},
+		{
+			"taskId": 2,
+			"taskTitle": "Develop Dependency Monitor with Taskmaster MCP Integration",
+			"complexityScore": 7,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Divide the dependency monitor into: dependency graph data structure implementation, circular dependency detection algorithm, Taskmaster MCP integration layer, and real-time notification system. Focus on performance optimization for large graphs and efficient caching strategies.",
+			"reasoning": "Complex graph algorithms and real-time monitoring require careful implementation. The task involves sophisticated data structures, algorithm design, and API integration with performance constraints."
+		},
+		{
+			"taskId": 3,
+			"taskTitle": "Build Execution Manager with Priority Queue and Parallel Execution",
+			"complexityScore": 8,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "Structure the execution manager into: priority queue implementation, resource conflict detection system, parallel execution coordinator, timeout and cancellation handler, and execution history persistence layer. Each component should handle specific aspects of concurrent task management.",
+			"reasoning": "Managing concurrent execution with resource conflicts, priority scheduling, and persistence is highly complex. Requires careful synchronization, error handling, and performance optimization."
+		},
+		{
+			"taskId": 4,
+			"taskTitle": "Implement Safety Manager with Configurable Constraints and Emergency Controls",
+			"complexityScore": 7,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Break down into: constraint validation engine, emergency control system (stop/pause), user approval workflow implementation, and safety monitoring/audit logging. Each subtask should address specific safety aspects with fail-safe mechanisms.",
+			"reasoning": "Safety systems require careful design with multiple fail-safes. The task involves validation logic, real-time controls, workflow management, and comprehensive logging."
+		},
+		{
+			"taskId": 5,
+			"taskTitle": "Develop Event-Based Hook Processor",
+			"complexityScore": 6,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Organize into: file system event integration, Git/VCS event listeners, build system event connectors, and event filtering/debouncing mechanism. Focus on modular event source integration with configurable processing pipelines.",
+			"reasoning": "While conceptually straightforward, integrating multiple event sources with proper filtering and performance optimization requires careful implementation. Each event source has unique characteristics."
+		},
+		{
+			"taskId": 6,
+			"taskTitle": "Implement Prompt-Based Hook Processor with AI Integration",
+			"complexityScore": 7,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Divide into: prompt interception mechanism, NLP-based task suggestion engine, context injection system, and conversation-based status updater. Each component should handle specific aspects of AI conversation integration.",
+			"reasoning": "AI integration with prompt analysis and dynamic context injection is complex. Requires understanding of conversation flow, relevance scoring, and seamless integration with existing systems."
+		},
+		{
+			"taskId": 7,
+			"taskTitle": "Create Update-Based Hook Processor for Automatic Progress Tracking",
+			"complexityScore": 6,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Structure as: code change monitor, acceptance criteria validator, dependency update propagator, and conflict detection/resolution system. Focus on accurate progress tracking and automated validation logic.",
+			"reasoning": "Automatic progress tracking requires integration with version control and intelligent analysis of code changes. Conflict detection and dependency propagation add complexity."
+		},
+		{
+			"taskId": 8,
+			"taskTitle": "Develop Real-Time Automation Dashboard and User Controls",
+			"complexityScore": 7,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "Break down into: WebSocket real-time communication layer, interactive dependency graph visualization, task queue and status displays, user control interfaces, and analytics/charting components. Each UI component should be modular and reusable.",
+			"reasoning": "Building a responsive real-time dashboard with complex visualizations and interactive controls is challenging. Requires careful state management, performance optimization, and user experience design."
+		},
+		{
+			"taskId": 9,
+			"taskTitle": "Integrate Kiro IDE and Taskmaster MCP with Core Services",
+			"complexityScore": 8,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Organize into: KiroHookAdapter implementation, TaskmasterMCPAdapter development, error handling and retry logic layer, and IDE UI component integration. Focus on robust adapter patterns and comprehensive error recovery.",
+			"reasoning": "End-to-end integration of multiple systems with different architectures is highly complex. Requires careful adapter design, extensive error handling, and thorough testing across all integration points."
+		},
+		{
+			"taskId": 10,
+			"taskTitle": "Implement Configuration Management and Safety Profiles",
+			"complexityScore": 6,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Divide into: visual configuration editor UI, JSON Schema validation engine, import/export functionality, and version control integration. Each component should provide intuitive configuration management with robust validation.",
+			"reasoning": "While technically less complex than core systems, building an intuitive configuration editor with validation, versioning, and import/export requires careful UI/UX design and robust data handling."
+		}
+	]
+}

.taskmaster/state.json

@@ -1,6 +1,6 @@
 {
 	"currentTag": "master",
-	"lastSwitched": "2025-06-14T20:37:15.456Z",
+	"lastSwitched": "2025-07-22T13:32:03.558Z",
 	"branchTagMapping": {
 		"v017-adds": "v017-adds",
 		"next": "next"

CHANGELOG.md

@@ -1,5 +1,139 @@
 # task-master-ai
 
+## 0.21.0
+
+### Minor Changes
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`9c58a92`](https://github.com/eyaltoledano/claude-task-master/commit/9c58a922436c0c5e7ff1b20ed2edbc269990c772) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Kiro editor rule profile support
+  - Add support for Kiro IDE with custom rule files and MCP configuration
+  - Generate rule files in `.kiro/steering/` directory with markdown format
+  - Include MCP server configuration with enhanced file inclusion patterns
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Created a comprehensive documentation site for Task Master AI. Visit https://docs.task-master.dev to explore guides, API references, and examples.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`58a301c`](https://github.com/eyaltoledano/claude-task-master/commit/58a301c380d18a9d9509137f3e989d24200a5faa) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Complete Groq provider integration and add MoonshotAI Kimi K2 model support
+  - Fixed Groq provider registration
+  - Added Groq API key validation
+  - Added GROQ_API_KEY to .env.example
+  - Added moonshotai/kimi-k2-instruct model with $1/$3 per 1M token pricing and 16k max output
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`b0e09c7`](https://github.com/eyaltoledano/claude-task-master/commit/b0e09c76ed73b00434ac95606679f570f1015a3d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - feat: Add Zed editor rule profile with agent rules and MCP config
+  - Resolves #637
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`6c5e0f9`](https://github.com/eyaltoledano/claude-task-master/commit/6c5e0f97f8403c4da85c1abba31cb8b1789511a7) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Amp rule profile with AGENT.md and MCP config
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve project root detection
+  - No longer creates an infinite loop when unable to detect your code workspace
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`36c4a7a`](https://github.com/eyaltoledano/claude-task-master/commit/36c4a7a86924c927ad7f86a4f891f66ad55eb4d2) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add OpenCode profile with AGENTS.md and MCP config
+  - Resolves #965
+
+### Patch Changes
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Make `task-master update` more reliable with AI responses
+
+  The `update` command now handles AI responses more robustly. If the AI forgets to include certain task fields, the command will automatically fill in the missing data from your original tasks instead of failing. This means smoother bulk task updates without losing important information like IDs, dependencies, or completed subtasks.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix subtask dependency validation when expanding tasks
+
+  When using `task-master expand` to break down tasks into subtasks, dependencies between subtasks are now properly validated. Previously, subtasks with dependencies would fail validation. Now subtasks can correctly depend on their siblings within the same parent task.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`6d69d02`](https://github.com/eyaltoledano/claude-task-master/commit/6d69d02fe03edcc785380415995d5cfcdd97acbb) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Prevent CLAUDE.md overwrite by using Claude Code's import feature
+  - Task Master now creates its instructions in `.taskmaster/CLAUDE.md` instead of overwriting the user's `CLAUDE.md`
+  - Adds an import section to the user's CLAUDE.md that references the Task Master instructions
+  - Preserves existing user content in CLAUDE.md files
+  - Provides clean uninstall that only removes Task Master's additions
+
+  **Breaking Change**: Task Master instructions for Claude Code are now stored in `.taskmaster/CLAUDE.md` and imported into the main CLAUDE.md file. Users who previously had Task Master content directly in their CLAUDE.md will need to run `task-master rules remove claude` followed by `task-master rules add claude` to migrate to the new structure.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`fd005c4`](https://github.com/eyaltoledano/claude-task-master/commit/fd005c4c5481ffac58b11f01a448fa5b29056b8d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Implement Boundary-First Tag Resolution to ensure consistent and deterministic tag handling across CLI and MCP, resolving potential race conditions.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix `task-master lang --setup` breaking when no language is defined, now defaults to English
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`624922c`](https://github.com/eyaltoledano/claude-task-master/commit/624922ca598c4ce8afe9a5646ebb375d4616db63) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix: show command no longer requires complexity report file to exist
+
+  The `tm show` command was incorrectly requiring the complexity report file to exist even when not needed. Now it only validates the complexity report path when a custom report file is explicitly provided via the -r/--report option.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`858d4a1`](https://github.com/eyaltoledano/claude-task-master/commit/858d4a1c5486d20e7e3a8e37e3329d7fb8200310) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Update VS Code profile with MCP config transformation
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0451ebc`](https://github.com/eyaltoledano/claude-task-master/commit/0451ebcc32cd7e9d395b015aaa8602c4734157e1) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP server error when retrieving tools and resources
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0a70ab6`](https://github.com/eyaltoledano/claude-task-master/commit/0a70ab6179cb2b5b4b2d9dc256a7a3b69a0e5dd6) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add MCP configuration support to Claude Code rules
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`4629128`](https://github.com/eyaltoledano/claude-task-master/commit/4629128943f6283385f4762c09cf2752f855cc33) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fixed the comprehensive taskmaster system integration via custom slash commands with proper syntax
+  - Provide claude clode with a complete set of of commands that can trigger task master events directly within Claude Code
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0886c83`](https://github.com/eyaltoledano/claude-task-master/commit/0886c83d0c678417c0313256a6dd96f7ee2c9ac6) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`88c434a`](https://github.com/eyaltoledano/claude-task-master/commit/88c434a9393e429d9277f59b3e20f1005076bbe0) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add missing API keys to .env.example and README.md
+
+## 0.21.0-rc.0
+
+### Minor Changes
+
+- [#1001](https://github.com/eyaltoledano/claude-task-master/pull/1001) [`75a36ea`](https://github.com/eyaltoledano/claude-task-master/commit/75a36ea99a1c738a555bdd4fe7c763d0c5925e37) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Kiro editor rule profile support
+  - Add support for Kiro IDE with custom rule files and MCP configuration
+  - Generate rule files in `.kiro/steering/` directory with markdown format
+  - Include MCP server configuration with enhanced file inclusion patterns
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Created a comprehensive documentation site for Task Master AI. Visit https://docs.task-master.dev to explore guides, API references, and examples.
+
+- [#978](https://github.com/eyaltoledano/claude-task-master/pull/978) [`fedfd6a`](https://github.com/eyaltoledano/claude-task-master/commit/fedfd6a0f41a78094f7ee7f69be689b699475a79) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Complete Groq provider integration and add MoonshotAI Kimi K2 model support
+  - Fixed Groq provider registration
+  - Added Groq API key validation
+  - Added GROQ_API_KEY to .env.example
+  - Added moonshotai/kimi-k2-instruct model with $1/$3 per 1M token pricing and 16k max output
+
+- [#974](https://github.com/eyaltoledano/claude-task-master/pull/974) [`5b0eda0`](https://github.com/eyaltoledano/claude-task-master/commit/5b0eda07f20a365aa2ec1736eed102bca81763a9) Thanks [@joedanz](https://github.com/joedanz)! - feat: Add Zed editor rule profile with agent rules and MCP config
+  - Resolves #637
+
+- [#973](https://github.com/eyaltoledano/claude-task-master/pull/973) [`6d05e86`](https://github.com/eyaltoledano/claude-task-master/commit/6d05e8622c1d761acef10414940ff9a766b3b57d) Thanks [@joedanz](https://github.com/joedanz)! - Add Amp rule profile with AGENT.md and MCP config
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve project root detection
+  - No longer creates an infinite loop when unable to detect your code workspace
+
+- [#970](https://github.com/eyaltoledano/claude-task-master/pull/970) [`b87499b`](https://github.com/eyaltoledano/claude-task-master/commit/b87499b56e626001371a87ed56ffc72675d829f3) Thanks [@joedanz](https://github.com/joedanz)! - Add OpenCode profile with AGENTS.md and MCP config
+  - Resolves #965
+
+### Patch Changes
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Make `task-master update` more reliable with AI responses
+
+  The `update` command now handles AI responses more robustly. If the AI forgets to include certain task fields, the command will automatically fill in the missing data from your original tasks instead of failing. This means smoother bulk task updates without losing important information like IDs, dependencies, or completed subtasks.
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix subtask dependency validation when expanding tasks
+
+  When using `task-master expand` to break down tasks into subtasks, dependencies between subtasks are now properly validated. Previously, subtasks with dependencies would fail validation. Now subtasks can correctly depend on their siblings within the same parent task.
+
+- [#949](https://github.com/eyaltoledano/claude-task-master/pull/949) [`f662654`](https://github.com/eyaltoledano/claude-task-master/commit/f662654afb8e7a230448655265d6f41adf6df62c) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Prevent CLAUDE.md overwrite by using Claude Code's import feature
+  - Task Master now creates its instructions in `.taskmaster/CLAUDE.md` instead of overwriting the user's `CLAUDE.md`
+  - Adds an import section to the user's CLAUDE.md that references the Task Master instructions
+  - Preserves existing user content in CLAUDE.md files
+  - Provides clean uninstall that only removes Task Master's additions
+
+  **Breaking Change**: Task Master instructions for Claude Code are now stored in `.taskmaster/CLAUDE.md` and imported into the main CLAUDE.md file. Users who previously had Task Master content directly in their CLAUDE.md will need to run `task-master rules remove claude` followed by `task-master rules add claude` to migrate to the new structure.
+
+- [#943](https://github.com/eyaltoledano/claude-task-master/pull/943) [`f98df5c`](https://github.com/eyaltoledano/claude-task-master/commit/f98df5c0fdb253b2b55d4278c11d626529c4dba4) Thanks [@mm-parthy](https://github.com/mm-parthy)! - Implement Boundary-First Tag Resolution to ensure consistent and deterministic tag handling across CLI and MCP, resolving potential race conditions.
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix `task-master lang --setup` breaking when no language is defined, now defaults to English
+
+- [#979](https://github.com/eyaltoledano/claude-task-master/pull/979) [`ab2e946`](https://github.com/eyaltoledano/claude-task-master/commit/ab2e94608749a2f148118daa0443bd32bca6e7a1) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Fix: show command no longer requires complexity report file to exist
+
+  The `tm show` command was incorrectly requiring the complexity report file to exist even when not needed. Now it only validates the complexity report path when a custom report file is explicitly provided via the -r/--report option.
+
+- [#971](https://github.com/eyaltoledano/claude-task-master/pull/971) [`5544222`](https://github.com/eyaltoledano/claude-task-master/commit/55442226d0aa4870470d2a9897f5538d6a0e329e) Thanks [@joedanz](https://github.com/joedanz)! - Update VS Code profile with MCP config transformation
+
+- [#1002](https://github.com/eyaltoledano/claude-task-master/pull/1002) [`6d0654c`](https://github.com/eyaltoledano/claude-task-master/commit/6d0654cb4191cee794e1c8cbf2b92dc33d4fb410) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP server error when retrieving tools and resources
+
+- [#980](https://github.com/eyaltoledano/claude-task-master/pull/980) [`cc4fe20`](https://github.com/eyaltoledano/claude-task-master/commit/cc4fe205fb468e7144c650acc92486df30731560) Thanks [@joedanz](https://github.com/joedanz)! - Add MCP configuration support to Claude Code rules
+
+- [#968](https://github.com/eyaltoledano/claude-task-master/pull/968) [`7b4803a`](https://github.com/eyaltoledano/claude-task-master/commit/7b4803a479105691c7ed032fd878fe3d48d82724) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fixed the comprehensive taskmaster system integration via custom slash commands with proper syntax
+  - Provide claude clode with a complete set of of commands that can trigger task master events directly within Claude Code
+
+- [#995](https://github.com/eyaltoledano/claude-task-master/pull/995) [`b78de8d`](https://github.com/eyaltoledano/claude-task-master/commit/b78de8dbb4d6dc93b48e2f81c32960ef069736ed) Thanks [@joedanz](https://github.com/joedanz)! - Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.
+
+- [#972](https://github.com/eyaltoledano/claude-task-master/pull/972) [`1c7badf`](https://github.com/eyaltoledano/claude-task-master/commit/1c7badff2f5c548bfa90a3b2634e63087a382a84) Thanks [@joedanz](https://github.com/joedanz)! - Add missing API keys to .env.example and README.md
+
 ## 0.20.0
 
 ### Minor Changes

CLAUDE.md

@@ -0,0 +1,5 @@
+# Claude Code Instructions
+
+## Task Master AI Instructions
+**Import Task Master's development workflow commands and guidelines, treat as if import is in the main CLAUDE.md file.**
+@./.taskmaster/CLAUDE.md

README.md

@@ -14,7 +14,13 @@ A task management system for AI-driven development with Claude, designed to work
 
 ## Documentation
 
-For more detailed information, check out the documentation in the `docs` directory:
+📚 **[View Full Documentation](https://docs.task-master.dev)**
+
+For detailed guides, API references, and comprehensive examples, visit our documentation site.
+
+### Quick Reference
+
+The following documentation is also available in the `docs` directory:
 
 - [Configuration Guide](docs/configuration.md) - Set up environment variables and customize Task Master
 - [Tutorial](docs/tutorial.md) - Step-by-step guide to getting started with Task Master

apps/extension/package.json

@@ -1,5 +1,6 @@
 {
 	"name": "extension",
+	"private": true,
 	"version": "0.20.0",
 	"main": "index.js",
 	"scripts": {

assets/kiro-hooks/tm-code-change-task-tracker.kiro.hook

@@ -0,0 +1,23 @@
+{
+  "enabled": true,
+  "name": "[TM] Code Change Task Tracker",
+  "description": "Track implementation progress by monitoring code changes",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      "**/*.{js,ts,jsx,tsx,py,go,rs,java,cpp,c,h,hpp,cs,rb,php,swift,kt,scala,clj}",
+      "!**/node_modules/**",
+      "!**/vendor/**",
+      "!**/.git/**",
+      "!**/build/**",
+      "!**/dist/**",
+      "!**/target/**",
+      "!**/__pycache__/**"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "I just saved a source code file. Please:\n\n1. Check what task is currently 'in-progress' using 'tm list --status=in-progress'\n2. Look at the file I saved and summarize what was changed (considering the programming language and context)\n3. Update the task's notes with: 'tm update-subtask --id=<task_id> --prompt=\"Implemented: <summary_of_changes> in <file_path>\"'\n4. If the changes seem to complete the task based on its description, ask if I want to mark it as done"
+  }
+}

assets/kiro-hooks/tm-complexity-analyzer.kiro.hook

@@ -0,0 +1,16 @@
+{
+  "enabled": false,
+  "name": "[TM] Complexity Analyzer",
+  "description": "Analyze task complexity when new tasks are added",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      ".taskmaster/tasks/tasks.json"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "New tasks were added to tasks.json. For each new task:\n\n1. Run 'tm analyze-complexity --id=<task_id>'\n2. If complexity score is > 7, automatically expand it: 'tm expand --id=<task_id> --num=5'\n3. Show the complexity analysis results\n4. Suggest task dependencies based on the expanded subtasks"
+  }
+}

assets/kiro-hooks/tm-daily-standup-assistant.kiro.hook

@@ -0,0 +1,13 @@
+{
+  "enabled": true,
+  "name": "[TM] Daily Standup Assistant",
+  "description": "Morning workflow summary and task selection",
+  "version": "1",
+  "when": {
+    "type": "userTriggered"
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "Good morning! Please provide my daily standup summary:\n\n1. Run 'tm list --status=done' and show tasks completed in the last 24 hours\n2. Run 'tm list --status=in-progress' to show current work\n3. Run 'tm next' to suggest the highest priority task to start\n4. Show the dependency graph for upcoming work\n5. Ask which task I'd like to focus on today"
+  }
+}

assets/kiro-hooks/tm-git-commit-task-linker.kiro.hook

@@ -0,0 +1,13 @@
+{
+  "enabled": true,
+  "name": "[TM] Git Commit Task Linker",
+  "description": "Link commits to tasks for traceability",
+  "version": "1",
+  "when": {
+    "type": "manual"
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "I'm about to commit code. Please:\n\n1. Run 'git diff --staged' to see what's being committed\n2. Analyze the changes and suggest which tasks they relate to\n3. Generate a commit message in format: 'feat(task-<id>): <description>'\n4. Update the relevant tasks with a note about this commit\n5. Show the proposed commit message for approval"
+  }
+}

assets/kiro-hooks/tm-pr-readiness-checker.kiro.hook

@@ -0,0 +1,13 @@
+{
+  "enabled": true,
+  "name": "[TM] PR Readiness Checker",
+  "description": "Validate tasks before creating a pull request",
+  "version": "1",
+  "when": {
+    "type": "manual"
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "I'm about to create a PR. Please:\n\n1. List all tasks marked as 'done' in this branch\n2. For each done task, verify:\n   - All subtasks are also done\n   - Test files exist for new functionality\n   - No TODO comments remain related to the task\n3. Generate a PR description listing completed tasks\n4. Suggest a PR title based on the main tasks completed"
+  }
+}

assets/kiro-hooks/tm-task-dependency-auto-progression.kiro.hook

@@ -0,0 +1,17 @@
+{
+  "enabled": true,
+  "name": "[TM] Task Dependency Auto-Progression",
+  "description": "Automatically progress tasks when dependencies are completed",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      ".taskmaster/tasks/tasks.json",
+      ".taskmaster/tasks/*.json"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "Check the tasks.json file for any tasks that just changed status to 'done'. For each completed task:\n\n1. Find all tasks that depend on it\n2. Check if those dependent tasks now have all their dependencies satisfied\n3. If a task has all dependencies met and is still 'pending', use the command 'tm set-status --id=<task_id> --status=in-progress' to start it\n4. Show me which tasks were auto-started and why"
+  }
+}

assets/kiro-hooks/tm-test-success-task-completer.kiro.hook

@@ -0,0 +1,23 @@
+{
+  "enabled": true,
+  "name": "[TM] Test Success Task Completer",
+  "description": "Mark tasks as done when their tests pass",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      "**/*test*.{js,ts,jsx,tsx,py,go,java,rb,php,rs,cpp,cs}",
+      "**/*spec*.{js,ts,jsx,tsx,rb}",
+      "**/test_*.py",
+      "**/*_test.go",
+      "**/*Test.java",
+      "**/*Tests.cs",
+      "!**/node_modules/**",
+      "!**/vendor/**"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "A test file was just saved. Please:\n\n1. Identify the test framework/language and run the appropriate test command for this file (npm test, pytest, go test, cargo test, dotnet test, mvn test, etc.)\n2. If all tests pass, check which tasks mention this functionality\n3. For any matching tasks that are 'in-progress', ask if the passing tests mean the task is complete\n4. If confirmed, mark the task as done with 'tm set-status --id=<task_id> --status=done'"
+  }
+}

assets/rules/taskmaster.mdc

@@ -157,7 +157,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `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`)
+    *   `generate`: `Enable Taskmaster to regenerate markdown task files after adding the subtask.` (CLI: `--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.
@@ -285,7 +285,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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`)
+    *   `generate`: `Enable Taskmaster to regenerate markdown task files after removing the subtask.` (CLI: `--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.

assets/rules/taskmaster_hooks_workflow.mdc

@@ -0,0 +1,59 @@
+---
+inclusion: always
+---
+
+# Taskmaster Hook-Driven Workflow
+
+## Core Principle: Hooks Automate Task Management
+
+When working with Taskmaster in Kiro, **avoid manually marking tasks as done**. The hook system automatically handles task completion based on:
+
+- **Test Success**: `[TM] Test Success Task Completer` detects passing tests and prompts for task completion
+- **Code Changes**: `[TM] Code Change Task Tracker` monitors implementation progress
+- **Dependency Chains**: `[TM] Task Dependency Auto-Progression` auto-starts dependent tasks
+
+## AI Assistant Workflow
+
+Follow this pattern when implementing features:
+
+1. **Implement First**: Write code, create tests, make changes
+2. **Save Frequently**: Hooks trigger on file saves to track progress automatically
+3. **Let Hooks Decide**: Allow hooks to detect completion rather than manually setting status
+4. **Respond to Prompts**: Confirm when hooks suggest task completion
+
+## Key Rules for AI Assistants
+
+- **Never use `tm set-status --status=done`** unless hooks fail to detect completion
+- **Always write tests** - they provide the most reliable completion signal
+- **Save files after implementation** - this triggers progress tracking
+- **Trust hook suggestions** - if no completion prompt appears, more work may be needed
+
+## Automatic Behaviors
+
+The hook system provides:
+
+- **Progress Logging**: Implementation details automatically added to task notes
+- **Evidence-Based Completion**: Tasks marked done only when criteria are met
+- **Dependency Management**: Next tasks auto-started when dependencies complete
+- **Natural Flow**: Focus on coding, not task management overhead
+
+## Manual Override Cases
+
+Only manually set task status for:
+
+- Documentation-only tasks
+- Tasks without testable outcomes
+- Emergency fixes without proper test coverage
+
+Use `tm set-status` sparingly - prefer hook-driven completion.
+
+## Implementation Pattern
+
+```
+1. Implement feature → Save file
+2. Write tests → Save test file
+3. Tests pass → Hook prompts completion
+4. Confirm completion → Next task auto-starts
+```
+
+This workflow ensures proper task tracking while maintaining development flow.

docs/models.md

@@ -1,4 +1,4 @@
-# Available Models as of July 16, 2025
+# Available Models as of July 23, 2025
 
 ## Main Models
 
@@ -48,7 +48,6 @@
 | 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         |
@@ -65,11 +64,9 @@
 | 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           |
 | ollama      | devstral:latest                                | —         | 0          | 0           |
 | ollama      | qwen3:latest                                   | —         | 0          | 0           |
 | ollama      | qwen3:14b                                      | —         | 0          | 0           |
@@ -158,7 +155,6 @@
 | 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         |
@@ -174,10 +170,8 @@
 | 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           |
 | ollama      | devstral:latest                                | —         | 0          | 0           |
 | ollama      | qwen3:latest                                   | —         | 0          | 0           |
 | ollama      | qwen3:14b                                      | —         | 0          | 0           |
@@ -196,3 +190,11 @@
 | bedrock     | us.anthropic.claude-3-5-haiku-20241022-v1:0    | 0.4       | 0.8        | 4           |
 | bedrock     | us.anthropic.claude-opus-4-20250514-v1:0       | 0.725     | 15         | 75          |
 | bedrock     | us.anthropic.claude-sonnet-4-20250514-v1:0     | 0.727     | 3          | 15          |
+
+## Unsupported Models
+
+| Provider   | Model Name                                    | Reason                                                                                                                                                                    |
+| ---------- | --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| openrouter | deepseek/deepseek-chat-v3-0324:free           | Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use. |
+| openrouter | mistralai/mistral-small-3.1-24b-instruct:free | Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use. |
+| openrouter | thudm/glm-4-32b:free                          | Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use. |

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

@@ -47,6 +47,20 @@ function generateMarkdownTable(title, models) {
 	return table;
 }
 
+function generateUnsupportedTable(models) {
+	if (!models || models.length === 0) {
+		return '## Unsupported Models\n\nNo unsupported models found.\n\n';
+	}
+	let table = '## Unsupported Models\n\n';
+	table += '| Provider | Model Name | Reason |\n';
+	table += '|---|---|---|\n';
+	models.forEach((model) => {
+		table += `| ${model.provider} | ${model.modelName} | ${model.reason || '—'} |\n`;
+	});
+	table += '\n';
+	return table;
+}
+
 function main() {
 	try {
 		const correctSupportedModelsPath = path.join(
@@ -68,11 +82,14 @@ function main() {
 		const mainModels = [];
 		const researchModels = [];
 		const fallbackModels = [];
+		const unsupportedModels = [];
 
 		for (const provider in supportedModels) {
 			if (Object.hasOwnProperty.call(supportedModels, provider)) {
 				const models = supportedModels[provider];
 				models.forEach((model) => {
+					const isSupported = model.supported !== false; // default to true if missing
+					if (isSupported) {
 						const modelEntry = {
 							provider: provider,
 							modelName: model.id,
@@ -84,16 +101,28 @@ function main() {
 								? model.cost_per_1m_tokens.output
 								: null
 						};
-
-					if (model.allowed_roles.includes('main')) {
+						if (model.allowed_roles && model.allowed_roles.includes('main')) {
 							mainModels.push(modelEntry);
 						}
-					if (model.allowed_roles.includes('research')) {
+						if (
+							model.allowed_roles &&
+							model.allowed_roles.includes('research')
+						) {
 							researchModels.push(modelEntry);
 						}
-					if (model.allowed_roles.includes('fallback')) {
+						if (
+							model.allowed_roles &&
+							model.allowed_roles.includes('fallback')
+						) {
 							fallbackModels.push(modelEntry);
 						}
+					} else {
+						unsupportedModels.push({
+							provider: provider,
+							modelName: model.id,
+							reason: model.reason || 'Not specified'
+						});
+					}
 				});
 			}
 		}
@@ -119,6 +148,7 @@ function main() {
 		markdownContent += generateMarkdownTable('Main Models', mainModels);
 		markdownContent += generateMarkdownTable('Research Models', researchModels);
 		markdownContent += generateMarkdownTable('Fallback Models', fallbackModels);
+		markdownContent += generateUnsupportedTable(unsupportedModels);
 
 		fs.writeFileSync(correctOutputMarkdownPath, markdownContent, 'utf8');
 		console.log(`Successfully updated ${correctOutputMarkdownPath}`);

jest.config.js

@@ -48,8 +48,5 @@ export default {
 	verbose: true,
 
 	// Setup file
-	setupFilesAfterEnv: ['<rootDir>/tests/setup.js'],
-
-	// Ignore e2e tests from default Jest runs
-	testPathIgnorePatterns: ['<rootDir>/tests/e2e/']
+	setupFilesAfterEnv: ['<rootDir>/tests/setup.js']
 };

jest.e2e.config.js

@@ -1,82 +0,0 @@
-/**
- * Jest configuration for E2E tests
- * Separate from unit tests to allow different settings
- */
-
-export default {
-	displayName: 'E2E Tests',
-	testMatch: ['<rootDir>/tests/e2e/**/*.test.js'],
-	testPathIgnorePatterns: [
-		'/node_modules/',
-		'/tests/e2e/utils/',
-		'/tests/e2e/config/',
-		'/tests/e2e/runners/',
-		'/tests/e2e/e2e_helpers.sh',
-		'/tests/e2e/test_llm_analysis.sh',
-		'/tests/e2e/run_e2e.sh',
-		'/tests/e2e/run_fallback_verification.sh'
-	],
-	testEnvironment: 'node',
-	testTimeout: 600000, // 10 minutes default (AI operations can be slow)
-	maxWorkers: 10, // Run tests in parallel workers to avoid rate limits
-	maxConcurrency: 10, // Limit concurrent test execution
-	testSequencer: '<rootDir>/tests/e2e/setup/rate-limit-sequencer.cjs', // Custom sequencer for rate limiting
-	verbose: true,
-	// Suppress console output for cleaner test results
-	silent: false,
-	setupFilesAfterEnv: ['<rootDir>/tests/e2e/setup/jest-setup.js'],
-	globalSetup: '<rootDir>/tests/e2e/setup/global-setup.js',
-	globalTeardown: '<rootDir>/tests/e2e/setup/global-teardown.js',
-	collectCoverageFrom: [
-		'src/**/*.js',
-		'!src/**/*.test.js',
-		'!src/**/__tests__/**'
-	],
-	coverageDirectory: '<rootDir>/coverage-e2e',
-	// Custom reporters for better E2E test output
-	// Transform configuration to match unit tests
-	transform: {},
-	transformIgnorePatterns: ['/node_modules/'],
-	// Module configuration
-	moduleNameMapper: {
-		'^@/(.*)$': '<rootDir>/$1'
-	},
-	moduleDirectories: ['node_modules', '<rootDir>'],
-	// Reporters configuration
-	reporters: [
-		'default',
-		'jest-junit',
-		[
-			'jest-html-reporters',
-			{
-				publicPath: './test-results',
-				filename: 'index.html',
-				pageTitle: 'Task Master E2E Test Report',
-				expand: true,
-				openReport: false,
-				hideIcon: false,
-				includeFailureMsg: true,
-				enableMergeData: true,
-				dataMergeLevel: 1,
-				inlineSource: false,
-				customInfos: [
-					{
-						title: 'Environment',
-						value: 'E2E Testing'
-					},
-					{
-						title: 'Test Type',
-						value: 'CLI Commands'
-					}
-				]
-			}
-		]
-	],
-	// Environment variables for E2E tests
-	testEnvironmentOptions: {
-		env: {
-			NODE_ENV: 'test',
-			E2E_TEST: 'true'
-		}
-	}
-};

jest.e2e.projects.config.js

@@ -1,116 +0,0 @@
-/**
- * Jest configuration using projects feature to separate AI and non-AI tests
- * This allows different concurrency settings for each type
- */
-
-const baseConfig = {
-	testEnvironment: 'node',
-	testTimeout: 600000,
-	verbose: true,
-	silent: false,
-	setupFilesAfterEnv: ['<rootDir>/tests/e2e/setup/jest-setup.js'],
-	globalSetup: '<rootDir>/tests/e2e/setup/global-setup.js',
-	globalTeardown: '<rootDir>/tests/e2e/setup/global-teardown.js',
-	transform: {},
-	transformIgnorePatterns: ['/node_modules/'],
-	moduleNameMapper: {
-		'^@/(.*)$': '<rootDir>/$1'
-	},
-	moduleDirectories: ['node_modules', '<rootDir>'],
-	reporters: [
-		'default',
-		'jest-junit',
-		[
-			'jest-html-reporters',
-			{
-				publicPath: './test-results',
-				filename: 'index.html',
-				pageTitle: 'Task Master E2E Test Report',
-				expand: true,
-				openReport: false,
-				hideIcon: false,
-				includeFailureMsg: true,
-				enableMergeData: true,
-				dataMergeLevel: 1,
-				inlineSource: false
-			}
-		]
-	]
-};
-
-export default {
-	projects: [
-		{
-			...baseConfig,
-			displayName: 'Non-AI E2E Tests',
-			testMatch: [
-				'<rootDir>/tests/e2e/**/add-dependency.test.js',
-				'<rootDir>/tests/e2e/**/remove-dependency.test.js',
-				'<rootDir>/tests/e2e/**/validate-dependencies.test.js',
-				'<rootDir>/tests/e2e/**/fix-dependencies.test.js',
-				'<rootDir>/tests/e2e/**/add-subtask.test.js',
-				'<rootDir>/tests/e2e/**/remove-subtask.test.js',
-				'<rootDir>/tests/e2e/**/clear-subtasks.test.js',
-				'<rootDir>/tests/e2e/**/set-status.test.js',
-				'<rootDir>/tests/e2e/**/show.test.js',
-				'<rootDir>/tests/e2e/**/list.test.js',
-				'<rootDir>/tests/e2e/**/next.test.js',
-				'<rootDir>/tests/e2e/**/tags.test.js',
-				'<rootDir>/tests/e2e/**/add-tag.test.js',
-				'<rootDir>/tests/e2e/**/delete-tag.test.js',
-				'<rootDir>/tests/e2e/**/rename-tag.test.js',
-				'<rootDir>/tests/e2e/**/copy-tag.test.js',
-				'<rootDir>/tests/e2e/**/use-tag.test.js',
-				'<rootDir>/tests/e2e/**/init.test.js',
-				'<rootDir>/tests/e2e/**/models.test.js',
-				'<rootDir>/tests/e2e/**/move.test.js',
-				'<rootDir>/tests/e2e/**/remove-task.test.js',
-				'<rootDir>/tests/e2e/**/sync-readme.test.js',
-				'<rootDir>/tests/e2e/**/rules.test.js',
-				'<rootDir>/tests/e2e/**/lang.test.js',
-				'<rootDir>/tests/e2e/**/migrate.test.js'
-			],
-			// Non-AI tests can run with more parallelism
-			maxWorkers: 4,
-			maxConcurrency: 5
-		},
-		{
-			...baseConfig,
-			displayName: 'Light AI E2E Tests',
-			testMatch: [
-				'<rootDir>/tests/e2e/**/add-task.test.js',
-				'<rootDir>/tests/e2e/**/update-subtask.test.js',
-				'<rootDir>/tests/e2e/**/complexity-report.test.js'
-			],
-			// Light AI tests with moderate parallelism
-			maxWorkers: 3,
-			maxConcurrency: 3
-		},
-		{
-			...baseConfig,
-			displayName: 'Heavy AI E2E Tests',
-			testMatch: [
-				'<rootDir>/tests/e2e/**/update-task.test.js',
-				'<rootDir>/tests/e2e/**/expand-task.test.js',
-				'<rootDir>/tests/e2e/**/research.test.js',
-				'<rootDir>/tests/e2e/**/research-save.test.js',
-				'<rootDir>/tests/e2e/**/parse-prd.test.js',
-				'<rootDir>/tests/e2e/**/generate.test.js',
-				'<rootDir>/tests/e2e/**/analyze-complexity.test.js',
-				'<rootDir>/tests/e2e/**/update.test.js'
-			],
-			// Heavy AI tests run sequentially to avoid rate limits
-			maxWorkers: 1,
-			maxConcurrency: 1,
-			// Even longer timeout for AI operations
-			testTimeout: 900000 // 15 minutes
-		}
-	],
-	// Global settings
-	coverageDirectory: '<rootDir>/coverage-e2e',
-	collectCoverageFrom: [
-		'src/**/*.js',
-		'!src/**/*.test.js',
-		'!src/**/__tests__/**'
-	]
-};

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "task-master-ai",
-	"version": "0.20.0",
+	"version": "0.21.0",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "task-master-ai",
-			"version": "0.20.0",
+			"version": "0.21.0",
 			"license": "MIT WITH Commons-Clause",
 			"workspaces": [
 				"apps/*",
@@ -69,9 +69,6 @@
 				"ink": "^5.0.1",
 				"jest": "^29.7.0",
 				"jest-environment-node": "^29.7.0",
-				"jest-html-reporters": "^3.1.7",
-				"jest-junit": "^16.0.0",
-				"mcp-jest": "^1.0.10",
 				"mock-fs": "^5.5.0",
 				"prettier": "^3.5.3",
 				"react": "^18.3.1",
@@ -84,7 +81,7 @@
 			"optionalDependencies": {
 				"@anthropic-ai/claude-code": "^1.0.25",
 				"@biomejs/cli-linux-x64": "^1.9.4",
-				"ai-sdk-provider-gemini-cli": "^0.0.4"
+				"ai-sdk-provider-gemini-cli": "^0.1.1"
 			}
 		},
 		"apps/extension": {
@@ -2068,12 +2065,12 @@
 			}
 		},
 		"node_modules/@google/gemini-cli-core": {
-			"version": "0.1.9",
-			"resolved": "https://registry.npmjs.org/@google/gemini-cli-core/-/gemini-cli-core-0.1.9.tgz",
-			"integrity": "sha512-NFmu0qivppBZ3JT6to0A2+tEtcvWcWuhbfyTz42Wm2AoAtl941lTbcd/TiBryK0yWz3WCkqukuDxl+L7axLpvA==",
+			"version": "0.1.13",
+			"resolved": "https://registry.npmjs.org/@google/gemini-cli-core/-/gemini-cli-core-0.1.13.tgz",
+			"integrity": "sha512-Vx3CbRpLJiGs/sj4SXlGH2ALKyON5skV/p+SCAoRuS6yRsANS1+diEeXbp6jlWT2TTiGoa8+GolqeNIU7wbN8w==",
 			"optional": true,
 			"dependencies": {
-				"@google/genai": "^1.4.0",
+				"@google/genai": "1.9.0",
 				"@modelcontextprotocol/sdk": "^1.11.0",
 				"@opentelemetry/api": "^1.9.0",
 				"@opentelemetry/exporter-logs-otlp-grpc": "^0.52.0",
@@ -2083,23 +2080,46 @@
 				"@opentelemetry/sdk-node": "^0.52.0",
 				"@types/glob": "^8.1.0",
 				"@types/html-to-text": "^9.0.4",
+				"ajv": "^8.17.1",
 				"diff": "^7.0.0",
-				"dotenv": "^16.6.1",
-				"gaxios": "^6.1.1",
+				"dotenv": "^17.1.0",
 				"glob": "^10.4.5",
 				"google-auth-library": "^9.11.0",
 				"html-to-text": "^9.0.5",
+				"https-proxy-agent": "^7.0.6",
 				"ignore": "^7.0.0",
 				"micromatch": "^4.0.8",
 				"open": "^10.1.2",
-				"shell-quote": "^1.8.2",
+				"shell-quote": "^1.8.3",
 				"simple-git": "^3.28.0",
 				"strip-ansi": "^7.1.0",
 				"undici": "^7.10.0",
 				"ws": "^8.18.0"
 			},
 			"engines": {
-				"node": ">=18"
+				"node": ">=20"
+			}
+		},
+		"node_modules/@google/gemini-cli-core/node_modules/@google/genai": {
+			"version": "1.9.0",
+			"resolved": "https://registry.npmjs.org/@google/genai/-/genai-1.9.0.tgz",
+			"integrity": "sha512-w9P93OXKPMs9H1mfAx9+p3zJqQGrWBGdvK/SVc7cLZEXNHr/3+vW2eif7ZShA6wU24rNLn9z9MK2vQFUvNRI2Q==",
+			"license": "Apache-2.0",
+			"optional": true,
+			"dependencies": {
+				"google-auth-library": "^9.14.2",
+				"ws": "^8.18.0"
+			},
+			"engines": {
+				"node": ">=20.0.0"
+			},
+			"peerDependencies": {
+				"@modelcontextprotocol/sdk": "^1.11.0"
+			},
+			"peerDependenciesMeta": {
+				"@modelcontextprotocol/sdk": {
+					"optional": true
+				}
 			}
 		},
 		"node_modules/@google/gemini-cli-core/node_modules/ansi-regex": {
@@ -2125,6 +2145,19 @@
 				"balanced-match": "^1.0.0"
 			}
 		},
+		"node_modules/@google/gemini-cli-core/node_modules/dotenv": {
+			"version": "17.2.0",
+			"resolved": "https://registry.npmjs.org/dotenv/-/dotenv-17.2.0.tgz",
+			"integrity": "sha512-Q4sgBT60gzd0BB0lSyYD3xM4YxrXA9y4uBDof1JNYGzOXrQdQ6yX+7XIAqoFOGQFOTK1D3Hts5OllpxMDZFONQ==",
+			"license": "BSD-2-Clause",
+			"optional": true,
+			"engines": {
+				"node": ">=12"
+			},
+			"funding": {
+				"url": "https://dotenvx.com"
+			}
+		},
 		"node_modules/@google/gemini-cli-core/node_modules/glob": {
 			"version": "10.4.5",
 			"resolved": "https://registry.npmjs.org/glob/-/glob-10.4.5.tgz",
@@ -2189,16 +2222,14 @@
 			}
 		},
 		"node_modules/@google/genai": {
-			"version": "1.8.0",
-			"resolved": "https://registry.npmjs.org/@google/genai/-/genai-1.8.0.tgz",
-			"integrity": "sha512-n3KiMFesQCy2R9iSdBIuJ0JWYQ1HZBJJkmt4PPZMGZKvlgHhBAGw1kUMyX+vsAIzprN3lK45DI755lm70wPOOg==",
+			"version": "1.10.0",
+			"resolved": "https://registry.npmjs.org/@google/genai/-/genai-1.10.0.tgz",
+			"integrity": "sha512-PR4tLuiIFMrpAiiCko2Z16ydikFsPF1c5TBfI64hlZcv3xBEApSCceLuDYu1pNMq2SkNh4r66J4AG+ZexBnMLw==",
 			"license": "Apache-2.0",
 			"optional": true,
 			"dependencies": {
 				"google-auth-library": "^9.14.2",
-				"ws": "^8.18.0",
-				"zod": "^3.22.4",
-				"zod-to-json-schema": "^3.22.4"
+				"ws": "^8.18.0"
 			},
 			"engines": {
 				"node": ">=20.0.0"
@@ -3460,9 +3491,9 @@
 			}
 		},
 		"node_modules/@modelcontextprotocol/sdk": {
-			"version": "1.15.1",
-			"resolved": "https://registry.npmjs.org/@modelcontextprotocol/sdk/-/sdk-1.15.1.tgz",
-			"integrity": "sha512-W/XlN9c528yYn+9MQkVjxiTPgPxoxt+oczfjHBDsJx0+59+O7B75Zhsp0B16Xbwbz8ANISDajh6+V7nIcPMc5w==",
+			"version": "1.15.0",
+			"resolved": "https://registry.npmjs.org/@modelcontextprotocol/sdk/-/sdk-1.15.0.tgz",
+			"integrity": "sha512-67hnl/ROKdb03Vuu0YOr+baKTvf1/5YBHBm9KnZdjdAh8hjt4FRCPD5ucwxGB237sBpzlqQsLy1PFu7z/ekZ9Q==",
 			"license": "MIT",
 			"dependencies": {
 				"ajv": "^6.12.6",
@@ -5426,15 +5457,15 @@
 			}
 		},
 		"node_modules/ai-sdk-provider-gemini-cli": {
-			"version": "0.0.4",
-			"resolved": "https://registry.npmjs.org/ai-sdk-provider-gemini-cli/-/ai-sdk-provider-gemini-cli-0.0.4.tgz",
-			"integrity": "sha512-rXxNM/+wVHL8Syf/SjyoVmFJgTMwLnVSPPhqkLzbP6JKBvp81qZfkBFQiI9l6VMF1ctb6L+iSdVNd0/G1pTVZg==",
+			"version": "0.1.1",
+			"resolved": "https://registry.npmjs.org/ai-sdk-provider-gemini-cli/-/ai-sdk-provider-gemini-cli-0.1.1.tgz",
+			"integrity": "sha512-fvX3n9jTt8JaTyc+qDv5Og0H4NQMpS6B1VdaTT71AN2F+3u2Bz9/OSd7ATokrV2Rmv+ZlEnUCmJnke58zHXUSQ==",
 			"license": "MIT",
 			"optional": true,
 			"dependencies": {
 				"@ai-sdk/provider": "^1.1.3",
 				"@ai-sdk/provider-utils": "^2.2.8",
-				"@google/gemini-cli-core": "^0.1.4",
+				"@google/gemini-cli-core": "^0.1.13",
 				"@google/genai": "^1.7.0",
 				"google-auth-library": "^9.0.0",
 				"zod": "^3.23.8",
@@ -9700,138 +9731,6 @@
 				"fsevents": "^2.3.2"
 			}
 		},
-		"node_modules/jest-html-reporters": {
-			"version": "3.1.7",
-			"resolved": "https://registry.npmjs.org/jest-html-reporters/-/jest-html-reporters-3.1.7.tgz",
-			"integrity": "sha512-GTmjqK6muQ0S0Mnksf9QkL9X9z2FGIpNSxC52E0PHDzjPQ1XDu2+XTI3B3FS43ZiUzD1f354/5FfwbNIBzT7ew==",
-			"dev": true,
-			"license": "MIT",
-			"dependencies": {
-				"fs-extra": "^10.0.0",
-				"open": "^8.0.3"
-			}
-		},
-		"node_modules/jest-html-reporters/node_modules/define-lazy-prop": {
-			"version": "2.0.0",
-			"resolved": "https://registry.npmjs.org/define-lazy-prop/-/define-lazy-prop-2.0.0.tgz",
-			"integrity": "sha512-Ds09qNh8yw3khSjiJjiUInaGX9xlqZDY7JVryGxdxV7NPeuqQfplOpQ66yJFZut3jLa5zOwkXw1g9EI2uKh4Og==",
-			"dev": true,
-			"license": "MIT",
-			"engines": {
-				"node": ">=8"
-			}
-		},
-		"node_modules/jest-html-reporters/node_modules/fs-extra": {
-			"version": "10.1.0",
-			"resolved": "https://registry.npmjs.org/fs-extra/-/fs-extra-10.1.0.tgz",
-			"integrity": "sha512-oRXApq54ETRj4eMiFzGnHWGy+zo5raudjuxN0b8H7s/RU2oW0Wvsx9O0ACRN/kRq9E8Vu/ReskGB5o3ji+FzHQ==",
-			"dev": true,
-			"license": "MIT",
-			"dependencies": {
-				"graceful-fs": "^4.2.0",
-				"jsonfile": "^6.0.1",
-				"universalify": "^2.0.0"
-			},
-			"engines": {
-				"node": ">=12"
-			}
-		},
-		"node_modules/jest-html-reporters/node_modules/is-docker": {
-			"version": "2.2.1",
-			"resolved": "https://registry.npmjs.org/is-docker/-/is-docker-2.2.1.tgz",
-			"integrity": "sha512-F+i2BKsFrH66iaUFc0woD8sLy8getkwTwtOBjvs56Cx4CgJDeKQeqfz8wAYiSb8JOprWhHH5p77PbmYCvvUuXQ==",
-			"dev": true,
-			"license": "MIT",
-			"bin": {
-				"is-docker": "cli.js"
-			},
-			"engines": {
-				"node": ">=8"
-			},
-			"funding": {
-				"url": "https://github.com/sponsors/sindresorhus"
-			}
-		},
-		"node_modules/jest-html-reporters/node_modules/is-wsl": {
-			"version": "2.2.0",
-			"resolved": "https://registry.npmjs.org/is-wsl/-/is-wsl-2.2.0.tgz",
-			"integrity": "sha512-fKzAra0rGJUUBwGBgNkHZuToZcn+TtXHpeCgmkMJMMYx1sQDYaCSyjJBSCa2nH1DGm7s3n1oBnohoVTBaN7Lww==",
-			"dev": true,
-			"license": "MIT",
-			"dependencies": {
-				"is-docker": "^2.0.0"
-			},
-			"engines": {
-				"node": ">=8"
-			}
-		},
-		"node_modules/jest-html-reporters/node_modules/jsonfile": {
-			"version": "6.1.0",
-			"resolved": "https://registry.npmjs.org/jsonfile/-/jsonfile-6.1.0.tgz",
-			"integrity": "sha512-5dgndWOriYSm5cnYaJNhalLNDKOqFwyDB/rr1E9ZsGciGvKPs8R2xYGCacuf3z6K1YKDz182fd+fY3cn3pMqXQ==",
-			"dev": true,
-			"license": "MIT",
-			"dependencies": {
-				"universalify": "^2.0.0"
-			},
-			"optionalDependencies": {
-				"graceful-fs": "^4.1.6"
-			}
-		},
-		"node_modules/jest-html-reporters/node_modules/open": {
-			"version": "8.4.2",
-			"resolved": "https://registry.npmjs.org/open/-/open-8.4.2.tgz",
-			"integrity": "sha512-7x81NCL719oNbsq/3mh+hVrAWmFuEYUqrq/Iw3kUzH8ReypT9QQ0BLoJS7/G9k6N81XjW4qHWtjWwe/9eLy1EQ==",
-			"dev": true,
-			"license": "MIT",
-			"dependencies": {
-				"define-lazy-prop": "^2.0.0",
-				"is-docker": "^2.1.1",
-				"is-wsl": "^2.2.0"
-			},
-			"engines": {
-				"node": ">=12"
-			},
-			"funding": {
-				"url": "https://github.com/sponsors/sindresorhus"
-			}
-		},
-		"node_modules/jest-html-reporters/node_modules/universalify": {
-			"version": "2.0.1",
-			"resolved": "https://registry.npmjs.org/universalify/-/universalify-2.0.1.tgz",
-			"integrity": "sha512-gptHNQghINnc/vTGIk0SOFGFNXw7JVrlRUtConJRlvaw6DuX0wO5Jeko9sWrMBhh+PsYAZ7oXAiOnf/UKogyiw==",
-			"dev": true,
-			"license": "MIT",
-			"engines": {
-				"node": ">= 10.0.0"
-			}
-		},
-		"node_modules/jest-junit": {
-			"version": "16.0.0",
-			"resolved": "https://registry.npmjs.org/jest-junit/-/jest-junit-16.0.0.tgz",
-			"integrity": "sha512-A94mmw6NfJab4Fg/BlvVOUXzXgF0XIH6EmTgJ5NDPp4xoKq0Kr7sErb+4Xs9nZvu58pJojz5RFGpqnZYJTrRfQ==",
-			"dev": true,
-			"license": "Apache-2.0",
-			"dependencies": {
-				"mkdirp": "^1.0.4",
-				"strip-ansi": "^6.0.1",
-				"uuid": "^8.3.2",
-				"xml": "^1.0.1"
-			},
-			"engines": {
-				"node": ">=10.12.0"
-			}
-		},
-		"node_modules/jest-junit/node_modules/uuid": {
-			"version": "8.3.2",
-			"resolved": "https://registry.npmjs.org/uuid/-/uuid-8.3.2.tgz",
-			"integrity": "sha512-+NYs2QeMWy+GWFOEm9xnn6HCDp0l7QBD7ml8zLUmJ+93Q5NF0NocErnwkTkXVFNiX3/fpC6afS8Dhb/gz7R7eg==",
-			"dev": true,
-			"license": "MIT",
-			"bin": {
-				"uuid": "dist/bin/uuid"
-			}
-		},
 		"node_modules/jest-leak-detector": {
 			"version": "29.7.0",
 			"resolved": "https://registry.npmjs.org/jest-leak-detector/-/jest-leak-detector-29.7.0.tgz",
@@ -10861,27 +10760,6 @@
 				"node": ">= 0.4"
 			}
 		},
-		"node_modules/mcp-jest": {
-			"version": "1.0.10",
-			"resolved": "https://registry.npmjs.org/mcp-jest/-/mcp-jest-1.0.10.tgz",
-			"integrity": "sha512-gmvWzgj+p789Hofeuej60qBDfHTFn98aNfpgb+Q7a69vLSLvXBXDv2pcjYOLEuBvss/AGe26xq0WHbbX01X5AA==",
-			"dev": true,
-			"license": "MIT",
-			"dependencies": {
-				"@modelcontextprotocol/sdk": "^1.12.1",
-				"zod": "^3.22.0"
-			},
-			"bin": {
-				"mcp-jest": "dist/cli.js"
-			},
-			"engines": {
-				"node": ">=18"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/josharsh"
-			}
-		},
 		"node_modules/mcp-proxy": {
 			"version": "5.3.0",
 			"resolved": "https://registry.npmjs.org/mcp-proxy/-/mcp-proxy-5.3.0.tgz",
@@ -11131,19 +11009,6 @@
 				"node": ">=16 || 14 >=14.17"
 			}
 		},
-		"node_modules/mkdirp": {
-			"version": "1.0.4",
-			"resolved": "https://registry.npmjs.org/mkdirp/-/mkdirp-1.0.4.tgz",
-			"integrity": "sha512-vVqVZQyf3WLx2Shd0qJ9xuvqgAyKPLAiqITEtqW0oIUjzo3PePDd6fW9iFz30ef7Ysp/oiWqbhszeGWW2T6Gzw==",
-			"dev": true,
-			"license": "MIT",
-			"bin": {
-				"mkdirp": "bin/cmd.js"
-			},
-			"engines": {
-				"node": ">=10"
-			}
-		},
 		"node_modules/mock-fs": {
 			"version": "5.5.0",
 			"resolved": "https://registry.npmjs.org/mock-fs/-/mock-fs-5.5.0.tgz",
@@ -11405,16 +11270,16 @@
 			}
 		},
 		"node_modules/open": {
-			"version": "10.1.2",
-			"resolved": "https://registry.npmjs.org/open/-/open-10.1.2.tgz",
-			"integrity": "sha512-cxN6aIDPz6rm8hbebcP7vrQNhvRcveZoJU72Y7vskh4oIm+BZwBECnx5nTmrlres1Qapvx27Qo1Auukpf8PKXw==",
+			"version": "10.2.0",
+			"resolved": "https://registry.npmjs.org/open/-/open-10.2.0.tgz",
+			"integrity": "sha512-YgBpdJHPyQ2UE5x+hlSXcnejzAvD0b22U2OuAP+8OnlJT+PjWPxtgmGqKKc+RgTM63U9gN0YzrYc71R2WT/hTA==",
 			"license": "MIT",
 			"optional": true,
 			"dependencies": {
 				"default-browser": "^5.2.1",
 				"define-lazy-prop": "^3.0.0",
 				"is-inside-container": "^1.0.0",
-				"is-wsl": "^3.1.0"
+				"wsl-utils": "^0.1.0"
 			},
 			"engines": {
 				"node": ">=18"
@@ -13791,12 +13656,21 @@
 				}
 			}
 		},
-		"node_modules/xml": {
-			"version": "1.0.1",
-			"resolved": "https://registry.npmjs.org/xml/-/xml-1.0.1.tgz",
-			"integrity": "sha512-huCv9IH9Tcf95zuYCsQraZtWnJvBtLVE0QHMOs8bWyZAFZNDcYjsPq1nEx8jKA9y+Beo9v+7OBPRisQTjinQMw==",
-			"dev": true,
-			"license": "MIT"
+		"node_modules/wsl-utils": {
+			"version": "0.1.0",
+			"resolved": "https://registry.npmjs.org/wsl-utils/-/wsl-utils-0.1.0.tgz",
+			"integrity": "sha512-h3Fbisa2nKGPxCpm89Hk33lBLsnaGBvctQopaBSOW/uIs6FTe1ATyAnKFJrzVs9vpGdsTe73WF3V4lIsk4Gacw==",
+			"license": "MIT",
+			"optional": true,
+			"dependencies": {
+				"is-wsl": "^3.1.0"
+			},
+			"engines": {
+				"node": ">=18"
+			},
+			"funding": {
+				"url": "https://github.com/sponsors/sindresorhus"
+			}
 		},
 		"node_modules/xsschema": {
 			"version": "0.3.0-beta.8",

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "task-master-ai",
-	"version": "0.20.0",
+	"version": "0.21.0",
 	"description": "A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.",
 	"main": "index.js",
 	"type": "module",
@@ -9,28 +9,21 @@
 		"task-master-mcp": "mcp-server/server.js",
 		"task-master-ai": "mcp-server/server.js"
 	},
-	"workspaces": [
-		"apps/*",
-		"."
-	],
+	"workspaces": ["apps/*", "."],
 	"scripts": {
 		"test": "node --experimental-vm-modules node_modules/.bin/jest",
+		"test:fails": "node --experimental-vm-modules node_modules/.bin/jest --onlyFailures",
 		"test:watch": "node --experimental-vm-modules node_modules/.bin/jest --watch",
 		"test:coverage": "node --experimental-vm-modules node_modules/.bin/jest --coverage",
-		"test:e2e:bash": "./tests/e2e/run_e2e.sh",
-		"test:e2e:bash:analyze": "./tests/e2e/run_e2e.sh --analyze-log",
-		"e2e": "node --experimental-vm-modules node_modules/.bin/jest --config jest.e2e.config.js",
-		"e2e:watch": "node --experimental-vm-modules node_modules/.bin/jest --config jest.e2e.config.js --watch",
-		"e2e:ai": "node --experimental-vm-modules node_modules/.bin/jest --config jest.e2e.projects.config.js --selectProjects='Heavy AI E2E Tests'",
-		"e2e:non-ai": "node --experimental-vm-modules node_modules/.bin/jest --config jest.e2e.projects.config.js --selectProjects='Non-AI E2E Tests'",
-		"e2e:report": "open test-results/index.html",
+		"test:e2e": "./tests/e2e/run_e2e.sh",
+		"test:e2e-report": "./tests/e2e/run_e2e.sh --analyze-log",
 		"prepare": "chmod +x bin/task-master.js mcp-server/server.js",
 		"changeset": "changeset",
 		"release": "changeset publish",
 		"inspector": "npx @modelcontextprotocol/inspector node mcp-server/server.js",
 		"mcp-server": "node mcp-server/server.js",
-		"format": "biome format . --write",
-		"format:check": "biome format ."
+		"format-check": "biome format .",
+		"format": "biome format . --write"
 	},
 	"keywords": [
 		"claude",
@@ -92,7 +85,7 @@
 	"optionalDependencies": {
 		"@anthropic-ai/claude-code": "^1.0.25",
 		"@biomejs/cli-linux-x64": "^1.9.4",
-		"ai-sdk-provider-gemini-cli": "^0.0.4"
+		"ai-sdk-provider-gemini-cli": "^0.1.1"
 	},
 	"engines": {
 		"node": ">=18.0.0"
@@ -128,9 +121,6 @@
 		"ink": "^5.0.1",
 		"jest": "^29.7.0",
 		"jest-environment-node": "^29.7.0",
-		"jest-html-reporters": "^3.1.7",
-		"jest-junit": "^16.0.0",
-		"mcp-jest": "^1.0.10",
 		"mock-fs": "^5.5.0",
 		"prettier": "^3.5.3",
 		"react": "^18.3.1",

scripts/modules/commands.js

@@ -2381,7 +2381,8 @@ ${result.result}
 		.action(async (taskId, options) => {
 			// Initialize TaskMaster
 			const initOptions = {
-				tasksPath: options.file || true
+				tasksPath: options.file || true,
+				tag: options.tag
 			};
 			// Only pass complexityReportPath if user provided a custom path
 			if (options.report && options.report !== COMPLEXITY_REPORT_FILE) {
@@ -2654,7 +2655,7 @@ ${result.result}
 			'Comma-separated list of dependency IDs for the new subtask'
 		)
 		.option('-s, --status <status>', 'Status for the new subtask', 'pending')
-		.option('--skip-generate', 'Skip regenerating task files')
+		.option('--generate', 'Regenerate task files after adding subtask')
 		.option('--tag <tag>', 'Specify tag context for task operations')
 		.action(async (options) => {
 			// Initialize TaskMaster
@@ -2665,7 +2666,7 @@ ${result.result}
 
 			const parentId = options.parent;
 			const existingTaskId = options.taskId;
-			const generateFiles = !options.skipGenerate;
+			const generateFiles = options.generate || false;
 
 			// Resolve tag using standard pattern
 			const tag = taskMaster.getCurrentTag();
@@ -2815,7 +2816,7 @@ ${result.result}
 	function showAddSubtaskHelp() {
 		console.log(
 			boxen(
-				`${chalk.white.bold('Add Subtask Command Help')}\n\n${chalk.cyan('Usage:')}\n  task-master add-subtask --parent=<id> [options]\n\n${chalk.cyan('Options:')}\n  -p, --parent <id>         Parent task ID (required)\n  -i, --task-id <id>        Existing task ID to convert to subtask\n  -t, --title <title>       Title for the new subtask\n  -d, --description <text>  Description for the new subtask\n  --details <text>          Implementation details for the new subtask\n  --dependencies <ids>      Comma-separated list of dependency IDs\n  -s, --status <status>     Status for the new subtask (default: "pending")\n  -f, --file <file>         Path to the tasks file (default: "${TASKMASTER_TASKS_FILE}")\n  --skip-generate           Skip regenerating task files\n\n${chalk.cyan('Examples:')}\n  task-master add-subtask --parent=5 --task-id=8\n  task-master add-subtask -p 5 -t "Implement login UI" -d "Create the login form"`,
+				`${chalk.white.bold('Add Subtask Command Help')}\n\n${chalk.cyan('Usage:')}\n  task-master add-subtask --parent=<id> [options]\n\n${chalk.cyan('Options:')}\n  -p, --parent <id>         Parent task ID (required)\n  -i, --task-id <id>        Existing task ID to convert to subtask\n  -t, --title <title>       Title for the new subtask\n  -d, --description <text>  Description for the new subtask\n  --details <text>          Implementation details for the new subtask\n  --dependencies <ids>      Comma-separated list of dependency IDs\n  -s, --status <status>     Status for the new subtask (default: "pending")\n  -f, --file <file>         Path to the tasks file (default: "${TASKMASTER_TASKS_FILE}")\n  --generate                Regenerate task files after adding subtask\n\n${chalk.cyan('Examples:')}\n  task-master add-subtask --parent=5 --task-id=8\n  task-master add-subtask -p 5 -t "Implement login UI" -d "Create the login form" --generate`,
 				{ padding: 1, borderColor: 'blue', borderStyle: 'round' }
 			)
 		);
@@ -2838,7 +2839,7 @@ ${result.result}
 			'-c, --convert',
 			'Convert the subtask to a standalone task instead of deleting it'
 		)
-		.option('--skip-generate', 'Skip regenerating task files')
+		.option('--generate', 'Regenerate task files after removing subtask')
 		.option('--tag <tag>', 'Specify tag context for task operations')
 		.action(async (options) => {
 			// Initialize TaskMaster
@@ -2849,7 +2850,7 @@ ${result.result}
 
 			const subtaskIds = options.id;
 			const convertToTask = options.convert || false;
-			const generateFiles = !options.skipGenerate;
+			const generateFiles = options.generate || false;
 			const tag = taskMaster.getCurrentTag();
 
 			if (!subtaskIds) {
@@ -3727,10 +3728,7 @@ Examples:
 			const taskMaster = initTaskMaster({});
 			const projectRoot = taskMaster.getProjectRoot(); // Find project root for context
 			const { response, setup } = options;
-			console.log(
-				chalk.blue('Response language set to:', JSON.stringify(options))
-			);
-			let responseLanguage = response || 'English';
+			let responseLanguage = response !== undefined ? response : 'English';
 			if (setup) {
 				console.log(
 					chalk.blue('Starting interactive response language setup...')
@@ -3772,6 +3770,7 @@ Examples:
 						`❌ Error setting response language: ${result.error.message}`
 					)
 				);
+				process.exit(1);
 			}
 		});
 
@@ -4485,11 +4484,13 @@ Examples:
 			TASKMASTER_TASKS_FILE
 		)
 		.option('--show-metadata', 'Show detailed metadata for each tag')
+		.option('--tag <tag>', 'Specify tag context for task operations')
 		.action(async (options) => {
 			try {
 				// Initialize TaskMaster
 				const taskMaster = initTaskMaster({
-					tasksPath: options.file || true
+					tasksPath: options.file || true,
+					tag: options.tag
 				});
 				const tasksPath = taskMaster.getTasksPath();
 

scripts/modules/config-manager.js

@@ -583,12 +583,23 @@ function getParametersForRole(role, explicitRoot = null) {
 					`No valid model-specific max_tokens override found for ${modelId}. Using role default: ${roleMaxTokens}`
 				);
 			}
+		} else {
+			// Special handling for custom OpenRouter models
+			if (providerName === CUSTOM_PROVIDERS.OPENROUTER) {
+				// Use a conservative default for OpenRouter models not in our list
+				const openrouterDefault = 32768;
+				effectiveMaxTokens = Math.min(roleMaxTokens, openrouterDefault);
+				log(
+					'debug',
+					`Custom OpenRouter model ${modelId} detected. Using conservative max_tokens: ${effectiveMaxTokens}`
+				);
 			} else {
 				log(
 					'debug',
 					`No model definitions found for provider ${providerName} in MODEL_MAP. Using role default maxTokens: ${roleMaxTokens}`
 				);
 			}
+		}
 	} catch (lookupError) {
 		log(
 			'warn',
@@ -772,7 +783,9 @@ function getAvailableModels() {
 	const available = [];
 	for (const [provider, models] of Object.entries(MODEL_MAP)) {
 		if (models.length > 0) {
-			models.forEach((modelObj) => {
+			models
+				.filter((modelObj) => Boolean(modelObj.supported))
+				.forEach((modelObj) => {
 					// Basic name generation - can be improved
 					const modelId = modelObj.id;
 					const sweScore = modelObj.swe_score;

scripts/modules/supported-models.json

@@ -8,7 +8,8 @@
 				"output": 15.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 64000
+			"max_tokens": 64000,
+			"supported": true
 		},
 		{
 			"id": "claude-opus-4-20250514",
@@ -18,7 +19,8 @@
 				"output": 75.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 32000
+			"max_tokens": 32000,
+			"supported": true
 		},
 		{
 			"id": "claude-3-7-sonnet-20250219",
@@ -28,7 +30,8 @@
 				"output": 15.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 120000
+			"max_tokens": 120000,
+			"supported": true
 		},
 		{
 			"id": "claude-3-5-sonnet-20241022",
@@ -38,7 +41,8 @@
 				"output": 15.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 8192
+			"max_tokens": 8192,
+			"supported": true
 		}
 	],
 	"claude-code": [
@@ -50,7 +54,8 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 32000
+			"max_tokens": 32000,
+			"supported": true
 		},
 		{
 			"id": "sonnet",
@@ -60,7 +65,8 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 64000
+			"max_tokens": 64000,
+			"supported": true
 		}
 	],
 	"mcp": [
@@ -72,7 +78,8 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 100000
+			"max_tokens": 100000,
+			"supported": true
 		}
 	],
 	"gemini-cli": [
@@ -84,7 +91,8 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 65536
+			"max_tokens": 65536,
+			"supported": true
 		},
 		{
 			"id": "gemini-2.5-flash",
@@ -94,7 +102,8 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 65536
+			"max_tokens": 65536,
+			"supported": true
 		}
 	],
 	"openai": [
@@ -106,7 +115,8 @@
 				"output": 10.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 16384
+			"max_tokens": 16384,
+			"supported": true
 		},
 		{
 			"id": "o1",
@@ -115,7 +125,8 @@
 				"input": 15.0,
 				"output": 60.0
 			},
-			"allowed_roles": ["main"]
+			"allowed_roles": ["main"],
+			"supported": true
 		},
 		{
 			"id": "o3",
@@ -125,7 +136,8 @@
 				"output": 8.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000
+			"max_tokens": 100000,
+			"supported": true
 		},
 		{
 			"id": "o3-mini",
@@ -135,7 +147,8 @@
 				"output": 4.4
 			},
 			"allowed_roles": ["main"],
-			"max_tokens": 100000
+			"max_tokens": 100000,
+			"supported": true
 		},
 		{
 			"id": "o4-mini",
@@ -144,7 +157,8 @@
 				"input": 1.1,
 				"output": 4.4
 			},
-			"allowed_roles": ["main", "fallback"]
+			"allowed_roles": ["main", "fallback"],
+			"supported": true
 		},
 		{
 			"id": "o1-mini",
@@ -153,7 +167,8 @@
 				"input": 1.1,
 				"output": 4.4
 			},
-			"allowed_roles": ["main"]
+			"allowed_roles": ["main"],
+			"supported": true
 		},
 		{
 			"id": "o1-pro",
@@ -162,7 +177,8 @@
 				"input": 150.0,
 				"output": 600.0
 			},
-			"allowed_roles": ["main"]
+			"allowed_roles": ["main"],
+			"supported": true
 		},
 		{
 			"id": "gpt-4-5-preview",
@@ -171,7 +187,8 @@
 				"input": 75.0,
 				"output": 150.0
 			},
-			"allowed_roles": ["main"]
+			"allowed_roles": ["main"],
+			"supported": true
 		},
 		{
 			"id": "gpt-4-1-mini",
@@ -180,7 +197,8 @@
 				"input": 0.4,
 				"output": 1.6
 			},
-			"allowed_roles": ["main"]
+			"allowed_roles": ["main"],
+			"supported": true
 		},
 		{
 			"id": "gpt-4-1-nano",
@@ -189,7 +207,8 @@
 				"input": 0.1,
 				"output": 0.4
 			},
-			"allowed_roles": ["main"]
+			"allowed_roles": ["main"],
+			"supported": true
 		},
 		{
 			"id": "gpt-4o-mini",
@@ -198,7 +217,8 @@
 				"input": 0.15,
 				"output": 0.6
 			},
-			"allowed_roles": ["main"]
+			"allowed_roles": ["main"],
+			"supported": true
 		},
 		{
 			"id": "gpt-4o-search-preview",
@@ -207,7 +227,8 @@
 				"input": 2.5,
 				"output": 10.0
 			},
-			"allowed_roles": ["research"]
+			"allowed_roles": ["research"],
+			"supported": true
 		},
 		{
 			"id": "gpt-4o-mini-search-preview",
@@ -216,7 +237,8 @@
 				"input": 0.15,
 				"output": 0.6
 			},
-			"allowed_roles": ["research"]
+			"allowed_roles": ["research"],
+			"supported": true
 		}
 	],
 	"google": [
@@ -225,21 +247,24 @@
 			"swe_score": 0.638,
 			"cost_per_1m_tokens": null,
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048000
+			"max_tokens": 1048000,
+			"supported": true
 		},
 		{
 			"id": "gemini-2.5-pro-preview-03-25",
 			"swe_score": 0.638,
 			"cost_per_1m_tokens": null,
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048000
+			"max_tokens": 1048000,
+			"supported": true
 		},
 		{
 			"id": "gemini-2.5-flash-preview-04-17",
 			"swe_score": 0.604,
 			"cost_per_1m_tokens": null,
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048000
+			"max_tokens": 1048000,
+			"supported": true
 		},
 		{
 			"id": "gemini-2.0-flash",
@@ -249,14 +274,16 @@
 				"output": 0.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048000
+			"max_tokens": 1048000,
+			"supported": true
 		},
 		{
 			"id": "gemini-2.0-flash-lite",
 			"swe_score": 0,
 			"cost_per_1m_tokens": null,
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048000
+			"max_tokens": 1048000,
+			"supported": true
 		}
 	],
 	"xai": [
@@ -269,7 +296,8 @@
 				"output": 15
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 131072
+			"max_tokens": 131072,
+			"supported": true
 		},
 		{
 			"id": "grok-3-fast",
@@ -280,7 +308,8 @@
 				"output": 25
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 131072
+			"max_tokens": 131072,
+			"supported": true
 		},
 		{
 			"id": "grok-4",
@@ -291,7 +320,8 @@
 				"output": 15
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 131072
+			"max_tokens": 131072,
+			"supported": true
 		}
 	],
 	"groq": [
@@ -303,7 +333,8 @@
 				"output": 3.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 16384
+			"max_tokens": 16384,
+			"supported": true
 		},
 		{
 			"id": "llama-3.3-70b-versatile",
@@ -313,7 +344,8 @@
 				"output": 0.79
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 32768
+			"max_tokens": 32768,
+			"supported": true
 		},
 		{
 			"id": "llama-3.1-8b-instant",
@@ -323,7 +355,8 @@
 				"output": 0.08
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 131072
+			"max_tokens": 131072,
+			"supported": true
 		},
 		{
 			"id": "llama-4-scout",
@@ -333,7 +366,8 @@
 				"output": 0.34
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 32768
+			"max_tokens": 32768,
+			"supported": true
 		},
 		{
 			"id": "llama-4-maverick",
@@ -343,7 +377,8 @@
 				"output": 0.77
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 32768
+			"max_tokens": 32768,
+			"supported": true
 		},
 		{
 			"id": "mixtral-8x7b-32768",
@@ -353,7 +388,8 @@
 				"output": 0.24
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 32768
+			"max_tokens": 32768,
+			"supported": true
 		},
 		{
 			"id": "qwen-qwq-32b-preview",
@@ -363,7 +399,8 @@
 				"output": 0.18
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 32768
+			"max_tokens": 32768,
+			"supported": true
 		},
 		{
 			"id": "deepseek-r1-distill-llama-70b",
@@ -373,7 +410,8 @@
 				"output": 0.99
 			},
 			"allowed_roles": ["main", "research"],
-			"max_tokens": 8192
+			"max_tokens": 8192,
+			"supported": true
 		},
 		{
 			"id": "gemma2-9b-it",
@@ -383,7 +421,8 @@
 				"output": 0.2
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 8192
+			"max_tokens": 8192,
+			"supported": true
 		},
 		{
 			"id": "whisper-large-v3",
@@ -393,7 +432,8 @@
 				"output": 0
 			},
 			"allowed_roles": ["main"],
-			"max_tokens": 0
+			"max_tokens": 0,
+			"supported": true
 		}
 	],
 	"perplexity": [
@@ -405,7 +445,8 @@
 				"output": 15
 			},
 			"allowed_roles": ["main", "research"],
-			"max_tokens": 8700
+			"max_tokens": 8700,
+			"supported": true
 		},
 		{
 			"id": "sonar",
@@ -415,7 +456,8 @@
 				"output": 1
 			},
 			"allowed_roles": ["research"],
-			"max_tokens": 8700
+			"max_tokens": 8700,
+			"supported": true
 		},
 		{
 			"id": "deep-research",
@@ -425,7 +467,8 @@
 				"output": 8
 			},
 			"allowed_roles": ["research"],
-			"max_tokens": 8700
+			"max_tokens": 8700,
+			"supported": true
 		},
 		{
 			"id": "sonar-reasoning-pro",
@@ -435,7 +478,8 @@
 				"output": 8
 			},
 			"allowed_roles": ["main", "research", "fallback"],
-			"max_tokens": 8700
+			"max_tokens": 8700,
+			"supported": true
 		},
 		{
 			"id": "sonar-reasoning",
@@ -445,7 +489,8 @@
 				"output": 5
 			},
 			"allowed_roles": ["main", "research", "fallback"],
-			"max_tokens": 8700
+			"max_tokens": 8700,
+			"supported": true
 		}
 	],
 	"openrouter": [
@@ -457,7 +502,8 @@
 				"output": 0.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048576
+			"max_tokens": 1048576,
+			"supported": true
 		},
 		{
 			"id": "google/gemini-2.5-flash-preview-05-20:thinking",
@@ -467,7 +513,8 @@
 				"output": 3.5
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048576
+			"max_tokens": 1048576,
+			"supported": true
 		},
 		{
 			"id": "google/gemini-2.5-pro-exp-03-25",
@@ -477,7 +524,8 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000
+			"max_tokens": 1000000,
+			"supported": true
 		},
 		{
 			"id": "deepseek/deepseek-chat-v3-0324:free",
@@ -487,7 +535,9 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 163840
+			"max_tokens": 163840,
+			"supported": false,
+			"reason": "Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use."
 		},
 		{
 			"id": "deepseek/deepseek-chat-v3-0324",
@@ -497,7 +547,8 @@
 				"output": 1.1
 			},
 			"allowed_roles": ["main"],
-			"max_tokens": 64000
+			"max_tokens": 64000,
+			"supported": true
 		},
 		{
 			"id": "openai/gpt-4.1",
@@ -507,7 +558,8 @@
 				"output": 8
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000
+			"max_tokens": 1000000,
+			"supported": true
 		},
 		{
 			"id": "openai/gpt-4.1-mini",
@@ -517,7 +569,8 @@
 				"output": 1.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000
+			"max_tokens": 1000000,
+			"supported": true
 		},
 		{
 			"id": "openai/gpt-4.1-nano",
@@ -527,7 +580,8 @@
 				"output": 0.4
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000
+			"max_tokens": 1000000,
+			"supported": true
 		},
 		{
 			"id": "openai/o3",
@@ -537,7 +591,8 @@
 				"output": 40
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 200000
+			"max_tokens": 200000,
+			"supported": true
 		},
 		{
 			"id": "openai/codex-mini",
@@ -547,7 +602,8 @@
 				"output": 6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000
+			"max_tokens": 100000,
+			"supported": true
 		},
 		{
 			"id": "openai/gpt-4o-mini",
@@ -557,7 +613,8 @@
 				"output": 0.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000
+			"max_tokens": 100000,
+			"supported": true
 		},
 		{
 			"id": "openai/o4-mini",
@@ -567,7 +624,8 @@
 				"output": 4.4
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000
+			"max_tokens": 100000,
+			"supported": true
 		},
 		{
 			"id": "openai/o4-mini-high",
@@ -577,7 +635,8 @@
 				"output": 4.4
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000
+			"max_tokens": 100000,
+			"supported": true
 		},
 		{
 			"id": "openai/o1-pro",
@@ -587,7 +646,8 @@
 				"output": 600
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000
+			"max_tokens": 100000,
+			"supported": true
 		},
 		{
 			"id": "meta-llama/llama-3.3-70b-instruct",
@@ -597,7 +657,8 @@
 				"output": 600
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048576
+			"max_tokens": 1048576,
+			"supported": true
 		},
 		{
 			"id": "meta-llama/llama-4-maverick",
@@ -607,7 +668,8 @@
 				"output": 0.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000
+			"max_tokens": 1000000,
+			"supported": true
 		},
 		{
 			"id": "meta-llama/llama-4-scout",
@@ -617,7 +679,8 @@
 				"output": 0.3
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000
+			"max_tokens": 1000000,
+			"supported": true
 		},
 		{
 			"id": "qwen/qwen-max",
@@ -627,7 +690,8 @@
 				"output": 6.4
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 32768
+			"max_tokens": 32768,
+			"supported": true
 		},
 		{
 			"id": "qwen/qwen-turbo",
@@ -637,7 +701,8 @@
 				"output": 0.2
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000
+			"max_tokens": 32768,
+			"supported": true
 		},
 		{
 			"id": "qwen/qwen3-235b-a22b",
@@ -647,7 +712,8 @@
 				"output": 2
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 24000
+			"max_tokens": 24000,
+			"supported": true
 		},
 		{
 			"id": "mistralai/mistral-small-3.1-24b-instruct:free",
@@ -657,7 +723,9 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 96000
+			"max_tokens": 96000,
+			"supported": false,
+			"reason": "Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use."
 		},
 		{
 			"id": "mistralai/mistral-small-3.1-24b-instruct",
@@ -667,7 +735,8 @@
 				"output": 0.3
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 128000
+			"max_tokens": 128000,
+			"supported": true
 		},
 		{
 			"id": "mistralai/devstral-small",
@@ -677,7 +746,8 @@
 				"output": 0.3
 			},
 			"allowed_roles": ["main"],
-			"max_tokens": 110000
+			"max_tokens": 110000,
+			"supported": true
 		},
 		{
 			"id": "mistralai/mistral-nemo",
@@ -687,7 +757,8 @@
 				"output": 0.07
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000
+			"max_tokens": 100000,
+			"supported": true
 		},
 		{
 			"id": "thudm/glm-4-32b:free",
@@ -697,7 +768,9 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 32768
+			"max_tokens": 32768,
+			"supported": false,
+			"reason": "Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use."
 		}
 	],
 	"ollama": [
@@ -708,7 +781,8 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"]
+			"allowed_roles": ["main", "fallback"],
+			"supported": true
 		},
 		{
 			"id": "qwen3:latest",
@@ -717,7 +791,8 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"]
+			"allowed_roles": ["main", "fallback"],
+			"supported": true
 		},
 		{
 			"id": "qwen3:14b",
@@ -726,7 +801,8 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"]
+			"allowed_roles": ["main", "fallback"],
+			"supported": true
 		},
 		{
 			"id": "qwen3:32b",
@@ -735,7 +811,8 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"]
+			"allowed_roles": ["main", "fallback"],
+			"supported": true
 		},
 		{
 			"id": "mistral-small3.1:latest",
@@ -744,7 +821,8 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"]
+			"allowed_roles": ["main", "fallback"],
+			"supported": true
 		},
 		{
 			"id": "llama3.3:latest",
@@ -753,7 +831,8 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"]
+			"allowed_roles": ["main", "fallback"],
+			"supported": true
 		},
 		{
 			"id": "phi4:latest",
@@ -762,7 +841,8 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"]
+			"allowed_roles": ["main", "fallback"],
+			"supported": true
 		}
 	],
 	"azure": [
@@ -771,10 +851,11 @@
 			"swe_score": 0.332,
 			"cost_per_1m_tokens": {
 				"input": 2.5,
-				"output": 10.0
+				"output": 10
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 16384
+			"max_tokens": 16384,
+			"supported": true
 		},
 		{
 			"id": "gpt-4o-mini",
@@ -784,7 +865,8 @@
 				"output": 0.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 16384
+			"max_tokens": 16384,
+			"supported": true
 		},
 		{
 			"id": "gpt-4-1",
@@ -794,7 +876,8 @@
 				"output": 10.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 16384
+			"max_tokens": 16384,
+			"supported": true
 		}
 	],
 	"bedrock": [
@@ -805,7 +888,8 @@
 				"input": 0.25,
 				"output": 1.25
 			},
-			"allowed_roles": ["main", "fallback"]
+			"allowed_roles": ["main", "fallback"],
+			"supported": true
 		},
 		{
 			"id": "us.anthropic.claude-3-opus-20240229-v1:0",
@@ -814,7 +898,8 @@
 				"input": 15,
 				"output": 75
 			},
-			"allowed_roles": ["main", "fallback", "research"]
+			"allowed_roles": ["main", "fallback", "research"],
+			"supported": true
 		},
 		{
 			"id": "us.anthropic.claude-3-5-sonnet-20240620-v1:0",
@@ -823,7 +908,8 @@
 				"input": 3,
 				"output": 15
 			},
-			"allowed_roles": ["main", "fallback", "research"]
+			"allowed_roles": ["main", "fallback", "research"],
+			"supported": true
 		},
 		{
 			"id": "us.anthropic.claude-3-5-sonnet-20241022-v2:0",
@@ -832,7 +918,8 @@
 				"input": 3,
 				"output": 15
 			},
-			"allowed_roles": ["main", "fallback", "research"]
+			"allowed_roles": ["main", "fallback", "research"],
+			"supported": true
 		},
 		{
 			"id": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
@@ -842,7 +929,8 @@
 				"output": 15
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 65536
+			"max_tokens": 65536,
+			"supported": true
 		},
 		{
 			"id": "us.anthropic.claude-3-5-haiku-20241022-v1:0",
@@ -851,7 +939,8 @@
 				"input": 0.8,
 				"output": 4
 			},
-			"allowed_roles": ["main", "fallback"]
+			"allowed_roles": ["main", "fallback"],
+			"supported": true
 		},
 		{
 			"id": "us.anthropic.claude-opus-4-20250514-v1:0",
@@ -860,7 +949,8 @@
 				"input": 15,
 				"output": 75
 			},
-			"allowed_roles": ["main", "fallback", "research"]
+			"allowed_roles": ["main", "fallback", "research"],
+			"supported": true
 		},
 		{
 			"id": "us.anthropic.claude-sonnet-4-20250514-v1:0",
@@ -869,7 +959,8 @@
 				"input": 3,
 				"output": 15
 			},
-			"allowed_roles": ["main", "fallback", "research"]
+			"allowed_roles": ["main", "fallback", "research"],
+			"supported": true
 		},
 		{
 			"id": "us.deepseek.r1-v1:0",
@@ -879,7 +970,8 @@
 				"output": 5.4
 			},
 			"allowed_roles": ["research"],
-			"max_tokens": 65536
+			"max_tokens": 65536,
+			"supported": true
 		}
 	]
 }

scripts/modules/task-manager/add-subtask.js

@@ -21,7 +21,7 @@ async function addSubtask(
 	parentId,
 	existingTaskId = null,
 	newSubtaskData = null,
-	generateFiles = true,
+	generateFiles = false,
 	context = {}
 ) {
 	const { projectRoot, tag } = context;

scripts/modules/task-manager/expand-all-tasks.js

@@ -22,6 +22,7 @@ import boxen from 'boxen';
  * @param {Object} [context.mcpLog] - MCP logger object.
  * @param {string} [context.projectRoot] - Project root path
  * @param {string} [context.tag] - Tag for the task
+ * @param {string} [context.complexityReportPath] - Path to the complexity report file
  * @param {string} [outputFormat='text'] - Output format ('text' or 'json'). MCP calls should use 'json'.
  * @returns {Promise<{success: boolean, expandedCount: number, failedCount: number, skippedCount: number, tasksToExpand: number, telemetryData: Array<Object>}>} - Result summary.
  */
@@ -34,7 +35,13 @@ async function expandAllTasks(
 	context = {},
 	outputFormat = 'text' // Assume text default for CLI
 ) {
-	const { session, mcpLog, projectRoot: providedProjectRoot, tag } = context;
+	const {
+		session,
+		mcpLog,
+		projectRoot: providedProjectRoot,
+		tag,
+		complexityReportPath
+	} = context;
 	const isMCPCall = !!mcpLog; // Determine if called from MCP
 
 	const projectRoot = providedProjectRoot || findProjectRoot();
@@ -126,7 +133,12 @@ async function expandAllTasks(
 					numSubtasks,
 					useResearch,
 					additionalContext,
-					{ ...context, projectRoot, tag: data.tag || tag }, // Pass the whole context object with projectRoot and resolved tag
+					{
+						...context,
+						projectRoot,
+						tag: data.tag || tag,
+						complexityReportPath
+					}, // Pass the whole context object with projectRoot and resolved tag
 					force
 				);
 				expandedCount++;

scripts/modules/task-manager/expand-task.js

@@ -40,8 +40,10 @@ const subtaskSchema = z
 			.min(10)
 			.describe('Detailed description of the subtask'),
 		dependencies: z
-			.array(z.number().int())
-			.describe('IDs of prerequisite subtasks within this expansion'),
+			.array(z.string())
+			.describe(
+				'Array of subtask dependencies within the same parent task. Use format ["parentTaskId.1", "parentTaskId.2"]. Subtasks can only depend on siblings, not external tasks.'
+			),
 		details: z.string().min(20).describe('Implementation details and guidance'),
 		status: z
 			.string()
@@ -235,11 +237,9 @@ function parseSubtasksFromText(
 			...rawSubtask,
 			id: currentId,
 			dependencies: Array.isArray(rawSubtask.dependencies)
-				? rawSubtask.dependencies
-						.map((dep) => (typeof dep === 'string' ? parseInt(dep, 10) : dep))
-						.filter(
-							(depId) =>
-								!Number.isNaN(depId) && depId >= startId && depId < currentId
+				? rawSubtask.dependencies.filter(
+						(dep) =>
+							typeof dep === 'string' && dep.startsWith(`${parentTaskId}.`)
 					)
 				: [],
 			status: 'pending'

scripts/modules/task-manager/models.js

@@ -25,6 +25,10 @@ import { findConfigPath } from '../../../src/utils/path-utils.js';
 import { log } from '../utils.js';
 import { CUSTOM_PROVIDERS } from '../../../src/constants/providers.js';
 
+// Constants
+const CONFIG_MISSING_ERROR =
+	'The configuration file is missing. Run "task-master init" to create it.';
+
 /**
  * Fetches the list of models from OpenRouter API.
  * @returns {Promise<Array|null>} A promise that resolves with the list of model IDs or null if fetch fails.
@@ -168,9 +172,7 @@ async function getModelConfiguration(options = {}) {
 	);
 
 	if (!configExists) {
-		throw new Error(
-			'The configuration file is missing. Run "task-master models --setup" to create it.'
-		);
+		throw new Error(CONFIG_MISSING_ERROR);
 	}
 
 	try {
@@ -298,9 +300,7 @@ async function getAvailableModelsList(options = {}) {
 	);
 
 	if (!configExists) {
-		throw new Error(
-			'The configuration file is missing. Run "task-master models --setup" to create it.'
-		);
+		throw new Error(CONFIG_MISSING_ERROR);
 	}
 
 	try {
@@ -391,9 +391,7 @@ async function setModel(role, modelId, options = {}) {
 	);
 
 	if (!configExists) {
-		throw new Error(
-			'The configuration file is missing. Run "task-master models --setup" to create it.'
-		);
+		throw new Error(CONFIG_MISSING_ERROR);
 	}
 
 	// Validate role

scripts/modules/task-manager/parse-prd.js

@@ -19,7 +19,6 @@ import {
 import { generateObjectService } from '../ai-services-unified.js';
 import { getDebugFlag } from '../config-manager.js';
 import { getPromptManager } from '../prompt-manager.js';
-import generateTaskFiles from './generate-task-files.js';
 import { displayAiUsageSummary } from '../ui.js';
 
 // Define the Zod schema for a SINGLE task object

scripts/modules/task-manager/remove-subtask.js

@@ -17,7 +17,7 @@ async function removeSubtask(
 	tasksPath,
 	subtaskId,
 	convertToTask = false,
-	generateFiles = true,
+	generateFiles = false,
 	context = {}
 ) {
 	const { projectRoot, tag } = context;
@@ -111,7 +111,7 @@ async function removeSubtask(
 		// Generate task files if requested
 		if (generateFiles) {
 			log('info', 'Regenerating task files...');
-			// await generateTaskFiles(tasksPath, path.dirname(tasksPath), context);
+			await generateTaskFiles(tasksPath, path.dirname(tasksPath), context);
 		}
 
 		return convertedTask;

scripts/modules/task-manager/remove-task.js

@@ -192,18 +192,18 @@ async function removeTask(tasksPath, taskIds, context = {}) {
 			}
 
 			// Generate updated task files ONCE, with context
-			try {
-				await generateTaskFiles(tasksPath, path.dirname(tasksPath), {
-					projectRoot,
-					tag
-				});
-				results.messages.push('Task files regenerated successfully.');
-			} catch (genError) {
-				const genErrMsg = `Failed to regenerate task files: ${genError.message}`;
-				results.errors.push(genErrMsg);
-				results.success = false;
-				log('warn', genErrMsg);
-			}
+			// try {
+			// 	await generateTaskFiles(tasksPath, path.dirname(tasksPath), {
+			// 		projectRoot,
+			// 		tag
+			// 	});
+			// 	results.messages.push('Task files regenerated successfully.');
+			// } catch (genError) {
+			// 	const genErrMsg = `Failed to regenerate task files: ${genError.message}`;
+			// 	results.errors.push(genErrMsg);
+			// 	results.success = false;
+			// 	log('warn', genErrMsg);
+			// }
 		} else if (results.errors.length === 0) {
 			results.messages.push('No tasks found matching the provided IDs.');
 		}

scripts/modules/task-manager/response-language.js

@@ -34,7 +34,7 @@ function setResponseLanguage(lang, options = {}) {
 			error: {
 				code: 'CONFIG_MISSING',
 				message:
-					'The configuration file is missing. Run "task-master models --setup" to create it.'
+					'The configuration file is missing. Run "task-master init" to create it.'
 			}
 		};
 	}

scripts/modules/task-manager/update-tasks.js

@@ -42,7 +42,39 @@ const updatedTaskSchema = z
 		subtasks: z.array(z.any()).nullable() // Keep subtasks flexible for now
 	})
 	.strip(); // Allow potential extra fields during parsing if needed, then validate structure
+
+// Preprocessing schema that adds defaults before validation
+const preprocessTaskSchema = z.preprocess((task) => {
+	// Ensure task is an object
+	if (typeof task !== 'object' || task === null) {
+		return {};
+	}
+
+	// Return task with defaults for missing fields
+	return {
+		...task,
+		// Add defaults for required fields if missing
+		id: task.id ?? 0,
+		title: task.title ?? 'Untitled Task',
+		description: task.description ?? '',
+		status: task.status ?? 'pending',
+		dependencies: Array.isArray(task.dependencies) ? task.dependencies : [],
+		// Optional fields - preserve undefined/null distinction
+		priority: task.hasOwnProperty('priority') ? task.priority : null,
+		details: task.hasOwnProperty('details') ? task.details : null,
+		testStrategy: task.hasOwnProperty('testStrategy')
+			? task.testStrategy
+			: null,
+		subtasks: Array.isArray(task.subtasks)
+			? task.subtasks
+			: task.subtasks === null
+				? null
+				: []
+	};
+}, updatedTaskSchema);
+
 const updatedTaskArraySchema = z.array(updatedTaskSchema);
+const preprocessedTaskArraySchema = z.array(preprocessTaskSchema);
 
 /**
  * Parses an array of task objects from AI's text response.
@@ -195,32 +227,50 @@ function parseUpdatedTasksFromText(text, expectedCount, logFn, isMCP) {
 		);
 	}
 
-	// Preprocess tasks to ensure required fields have proper defaults
-	const preprocessedTasks = parsedTasks.map((task) => ({
-		...task,
-		// Ensure subtasks is always an array (not null or undefined)
-		subtasks: Array.isArray(task.subtasks) ? task.subtasks : [],
-		// Ensure status has a default value if missing
-		status: task.status || 'pending',
-		// Ensure dependencies is always an array
-		dependencies: Array.isArray(task.dependencies) ? task.dependencies : []
-	}));
+	// Log missing fields for debugging before preprocessing
+	let hasWarnings = false;
+	parsedTasks.forEach((task, index) => {
+		const missingFields = [];
+		if (!task.hasOwnProperty('id')) missingFields.push('id');
+		if (!task.hasOwnProperty('status')) missingFields.push('status');
+		if (!task.hasOwnProperty('dependencies'))
+			missingFields.push('dependencies');
 
-	const validationResult = updatedTaskArraySchema.safeParse(preprocessedTasks);
-	if (!validationResult.success) {
-		report('error', 'Parsed task array failed Zod validation.');
-		validationResult.error.errors.forEach((err) => {
-			report('error', `  - Path '${err.path.join('.')}': ${err.message}`);
+		if (missingFields.length > 0) {
+			hasWarnings = true;
+			report(
+				'warn',
+				`Task ${index} is missing fields: ${missingFields.join(', ')} - will use defaults`
+			);
+		}
 	});
-		throw new Error(
-			`AI response failed task structure validation: ${validationResult.error.message}`
+
+	if (hasWarnings) {
+		report(
+			'warn',
+			'Some tasks were missing required fields. Applying defaults...'
 		);
 	}
 
-	report('info', 'Successfully validated task structure.');
-	return validationResult.data.slice(
+	// Use the preprocessing schema to add defaults and validate
+	const preprocessResult = preprocessedTaskArraySchema.safeParse(parsedTasks);
+
+	if (!preprocessResult.success) {
+		// This should rarely happen now since preprocessing adds defaults
+		report('error', 'Failed to validate task array even after preprocessing.');
+		preprocessResult.error.errors.forEach((err) => {
+			report('error', `  - Path '${err.path.join('.')}': ${err.message}`);
+		});
+
+		throw new Error(
+			`AI response failed validation: ${preprocessResult.error.message}`
+		);
+	}
+
+	report('info', 'Successfully validated and transformed task structure.');
+	return preprocessResult.data.slice(
 		0,
-		expectedCount || validationResult.data.length
+		expectedCount || preprocessResult.data.length
 	);
 }
 

src/profiles/base-profile.js

@@ -234,6 +234,7 @@ export function createProfile(editorConfig) {
 		globalReplacements: baseGlobalReplacements,
 		conversionConfig,
 		getTargetRuleFilename,
+		targetExtension,
 		// Optional lifecycle hooks
 		...(onAdd && { onAddRulesProfile: onAdd }),
 		...(onRemove && { onRemoveRulesProfile: onRemove }),

src/profiles/kiro.js

@@ -1,5 +1,8 @@
 // Kiro profile for rule-transformer
 import { createProfile } from './base-profile.js';
+import fs from 'fs';
+import path from 'path';
+import { log } from '../../scripts/modules/utils.js';
 
 // Create and export kiro profile using the base factory
 export const kiroProfile = createProfile({
@@ -20,6 +23,7 @@ export const kiroProfile = createProfile({
 		// 'rules/self_improve.mdc': 'self_improve.md'
 		// 'rules/taskmaster.mdc': 'taskmaster.md'
 		// We can add additional custom mappings here if needed
+		'rules/taskmaster_hooks_workflow.mdc': 'taskmaster_hooks_workflow.md'
 	},
 	customReplacements: [
 		// Core Kiro directory structure changes
@@ -37,6 +41,45 @@ export const kiroProfile = createProfile({
 
 		// Kiro specific terminology
 		{ from: /rules directory/g, to: 'steering directory' },
-		{ from: /cursor rules/gi, to: 'Kiro steering files' }
-	]
+		{ from: /cursor rules/gi, to: 'Kiro steering files' },
+
+		// Transform frontmatter to Kiro format
+		// This regex matches the entire frontmatter block and replaces it
+		{
+			from: /^---\n(?:description:\s*[^\n]*\n)?(?:globs:\s*[^\n]*\n)?(?:alwaysApply:\s*true\n)?---/m,
+			to: '---\ninclusion: always\n---'
+		}
+	],
+
+	// Add lifecycle hook to copy Kiro hooks
+	onPostConvert: (projectRoot, assetsDir) => {
+		const hooksSourceDir = path.join(assetsDir, 'kiro-hooks');
+		const hooksTargetDir = path.join(projectRoot, '.kiro', 'hooks');
+
+		// Create hooks directory if it doesn't exist
+		if (!fs.existsSync(hooksTargetDir)) {
+			fs.mkdirSync(hooksTargetDir, { recursive: true });
+		}
+
+		// Copy all .kiro.hook files
+		if (fs.existsSync(hooksSourceDir)) {
+			const hookFiles = fs
+				.readdirSync(hooksSourceDir)
+				.filter((f) => f.endsWith('.kiro.hook'));
+
+			hookFiles.forEach((file) => {
+				const sourcePath = path.join(hooksSourceDir, file);
+				const targetPath = path.join(hooksTargetDir, file);
+
+				fs.copyFileSync(sourcePath, targetPath);
+			});
+
+			if (hookFiles.length > 0) {
+				log(
+					'info',
+					`[Kiro] Installed ${hookFiles.length} Taskmaster hooks in .kiro/hooks/`
+				);
+			}
+		}
+	}
 });

src/profiles/vscode.js

@@ -166,6 +166,7 @@ export const vscodeProfile = createProfile({
 	rulesDir: '.github/instructions', // VS Code instructions location
 	profileDir: '.vscode', // VS Code configuration directory
 	mcpConfigName: 'mcp.json', // VS Code uses mcp.json in .vscode directory
+	targetExtension: '.instructions.md',
 	customReplacements: [
 		// Core VS Code directory structure changes
 		{ from: /\.cursor\/rules/g, to: '.github/instructions' },
@@ -177,10 +178,13 @@ export const vscodeProfile = createProfile({
 		// VS Code custom instructions format - use applyTo with quoted patterns instead of globs
 		{ from: /^globs:\s*(.+)$/gm, to: 'applyTo: "$1"' },
 
+		// Remove unsupported property - alwaysApply
+		{ from: /^alwaysApply:\s*(true|false)\s*\n?/gm, to: '' },
+
 		// Essential markdown link transformations for VS Code structure
 		{
 			from: /\[(.+?)\]\(mdc:\.cursor\/rules\/(.+?)\.mdc\)/g,
-			to: '[$1](.github/instructions/$2.md)'
+			to: '[$1](.github/instructions/$2.instructions.md)'
 		},
 
 		// VS Code specific terminology

src/prompts/expand-task.json

@@ -56,17 +56,17 @@
 	"prompts": {
 		"complexity-report": {
 			"condition": "expansionPrompt",
-			"system": "You are an AI assistant helping with task breakdown. Generate {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} subtasks based on the provided prompt and context.\nRespond ONLY with a valid JSON object containing a single key \"subtasks\" whose value is an array of the generated subtask objects.\nEach subtask object in the array must have keys: \"id\", \"title\", \"description\", \"dependencies\", \"details\", \"status\".\nEnsure the 'id' starts from {{nextSubtaskId}} and is sequential.\nEnsure 'dependencies' only reference valid prior subtask IDs generated in this response (starting from {{nextSubtaskId}}).\nEnsure 'status' is 'pending'.\nDo not include any other text or explanation.",
+			"system": "You are an AI assistant helping with task breakdown. Generate {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} subtasks based on the provided prompt and context.\nRespond ONLY with a valid JSON object containing a single key \"subtasks\" whose value is an array of the generated subtask objects.\nEach subtask object in the array must have keys: \"id\", \"title\", \"description\", \"dependencies\", \"details\", \"status\".\nEnsure the 'id' starts from {{nextSubtaskId}} and is sequential.\nFor 'dependencies', use the full subtask ID format: \"{{task.id}}.1\", \"{{task.id}}.2\", etc. Only reference subtasks within this same task.\nEnsure 'status' is 'pending'.\nDo not include any other text or explanation.",
 			"user": "{{expansionPrompt}}{{#if additionalContext}}\n\n{{additionalContext}}{{/if}}{{#if complexityReasoningContext}}\n\n{{complexityReasoningContext}}{{/if}}{{#if gatheredContext}}\n\n# Project Context\n\n{{gatheredContext}}{{/if}}"
 		},
 		"research": {
 			"condition": "useResearch === true && !expansionPrompt",
 			"system": "You are an AI assistant that responds ONLY with valid JSON objects as requested. The object should contain a 'subtasks' array.",
-			"user": "Analyze the following task and break it down into {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks using your research capabilities. Assign sequential IDs starting from {{nextSubtaskId}}.\n\nParent Task:\nID: {{task.id}}\nTitle: {{task.title}}\nDescription: {{task.description}}\nCurrent details: {{#if task.details}}{{task.details}}{{else}}None{{/if}}{{#if additionalContext}}\nConsider this context: {{additionalContext}}{{/if}}{{#if complexityReasoningContext}}\nComplexity Analysis Reasoning: {{complexityReasoningContext}}{{/if}}{{#if gatheredContext}}\n\n# Project Context\n\n{{gatheredContext}}{{/if}}\n\nCRITICAL: Respond ONLY with a valid JSON object containing a single key \"subtasks\". The value must be an array of the generated subtasks, strictly matching this structure:\n\n{\n  \"subtasks\": [\n    {\n      \"id\": <number>, // Sequential ID starting from {{nextSubtaskId}}\n      \"title\": \"<string>\",\n      \"description\": \"<string>\",\n      \"dependencies\": [<number>], // e.g., [{{nextSubtaskId}} + 1]. If no dependencies, use an empty array [].\n      \"details\": \"<string>\",\n      \"testStrategy\": \"<string>\" // Optional\n    },\n    // ... (repeat for {{#if (gt subtaskCount 0)}}{{subtaskCount}}{{else}}appropriate number of{{/if}} subtasks)\n  ]\n}\n\nImportant: For the 'dependencies' field, if a subtask has no dependencies, you MUST use an empty array, for example: \"dependencies\": []. Do not use null or omit the field.\n\nDo not include ANY explanatory text, markdown, or code block markers. Just the JSON object."
+			"user": "Analyze the following task and break it down into {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks using your research capabilities. Assign sequential IDs starting from {{nextSubtaskId}}.\n\nParent Task:\nID: {{task.id}}\nTitle: {{task.title}}\nDescription: {{task.description}}\nCurrent details: {{#if task.details}}{{task.details}}{{else}}None{{/if}}{{#if additionalContext}}\nConsider this context: {{additionalContext}}{{/if}}{{#if complexityReasoningContext}}\nComplexity Analysis Reasoning: {{complexityReasoningContext}}{{/if}}{{#if gatheredContext}}\n\n# Project Context\n\n{{gatheredContext}}{{/if}}\n\nCRITICAL: Respond ONLY with a valid JSON object containing a single key \"subtasks\". The value must be an array of the generated subtasks, strictly matching this structure:\n\n{\n  \"subtasks\": [\n    {\n      \"id\": <number>, // Sequential ID starting from {{nextSubtaskId}}\n      \"title\": \"<string>\",\n      \"description\": \"<string>\",\n      \"dependencies\": [\"<string>\"], // Use full subtask IDs like [\"{{task.id}}.1\", \"{{task.id}}.2\"]. If no dependencies, use an empty array [].\n      \"details\": \"<string>\",\n      \"testStrategy\": \"<string>\" // Optional\n    },\n    // ... (repeat for {{#if (gt subtaskCount 0)}}{{subtaskCount}}{{else}}appropriate number of{{/if}} subtasks)\n  ]\n}\n\nImportant: For the 'dependencies' field, if a subtask has no dependencies, you MUST use an empty array, for example: \"dependencies\": []. Do not use null or omit the field.\n\nDo not include ANY explanatory text, markdown, or code block markers. Just the JSON object."
 		},
 		"default": {
-			"system": "You are an AI assistant helping with task breakdown for software development.\nYou need to break down a high-level task into {{#if (gt subtaskCount 0)}}{{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks that can be implemented one by one.\n\nSubtasks should:\n1. Be specific and actionable implementation steps\n2. Follow a logical sequence\n3. Each handle a distinct part of the parent task\n4. Include clear guidance on implementation approach\n5. Have appropriate dependency chains between subtasks (using the new sequential IDs)\n6. Collectively cover all aspects of the parent task\n\nFor each subtask, provide:\n- id: Sequential integer starting from the provided nextSubtaskId\n- title: Clear, specific title\n- description: Detailed description\n- dependencies: Array of prerequisite subtask IDs (use the new sequential IDs)\n- details: Implementation details, the output should be in string\n- testStrategy: Optional testing approach\n\nRespond ONLY with a valid JSON object containing a single key \"subtasks\" whose value is an array matching the structure described. Do not include any explanatory text, markdown formatting, or code block markers.",
-			"user": "Break down this task into {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks:\n\nTask ID: {{task.id}}\nTitle: {{task.title}}\nDescription: {{task.description}}\nCurrent details: {{#if task.details}}{{task.details}}{{else}}None{{/if}}{{#if additionalContext}}\nAdditional context: {{additionalContext}}{{/if}}{{#if complexityReasoningContext}}\nComplexity Analysis Reasoning: {{complexityReasoningContext}}{{/if}}{{#if gatheredContext}}\n\n# Project Context\n\n{{gatheredContext}}{{/if}}\n\nReturn ONLY the JSON object containing the \"subtasks\" array, matching this structure:\n\n{\n  \"subtasks\": [\n    {\n      \"id\": {{nextSubtaskId}}, // First subtask ID\n      \"title\": \"Specific subtask title\",\n      \"description\": \"Detailed description\",\n      \"dependencies\": [], // e.g., [{{nextSubtaskId}} + 1] if it depends on the next\n      \"details\": \"Implementation guidance\",\n      \"testStrategy\": \"Optional testing approach\"\n    },\n    // ... (repeat for {{#if (gt subtaskCount 0)}}a total of {{subtaskCount}}{{else}}an appropriate number of{{/if}} subtasks with sequential IDs)\n  ]\n}"
+			"system": "You are an AI assistant helping with task breakdown for software development.\nYou need to break down a high-level task into {{#if (gt subtaskCount 0)}}{{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks that can be implemented one by one.\n\nSubtasks should:\n1. Be specific and actionable implementation steps\n2. Follow a logical sequence\n3. Each handle a distinct part of the parent task\n4. Include clear guidance on implementation approach\n5. Have appropriate dependency chains between subtasks (using full subtask IDs)\n6. Collectively cover all aspects of the parent task\n\nFor each subtask, provide:\n- id: Sequential integer starting from the provided nextSubtaskId\n- title: Clear, specific title\n- description: Detailed description\n- dependencies: Array of prerequisite subtask IDs using full format like [\"{{task.id}}.1\", \"{{task.id}}.2\"]\n- details: Implementation details, the output should be in string\n- testStrategy: Optional testing approach\n\nRespond ONLY with a valid JSON object containing a single key \"subtasks\" whose value is an array matching the structure described. Do not include any explanatory text, markdown formatting, or code block markers.",
+			"user": "Break down this task into {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks:\n\nTask ID: {{task.id}}\nTitle: {{task.title}}\nDescription: {{task.description}}\nCurrent details: {{#if task.details}}{{task.details}}{{else}}None{{/if}}{{#if additionalContext}}\nAdditional context: {{additionalContext}}{{/if}}{{#if complexityReasoningContext}}\nComplexity Analysis Reasoning: {{complexityReasoningContext}}{{/if}}{{#if gatheredContext}}\n\n# Project Context\n\n{{gatheredContext}}{{/if}}\n\nReturn ONLY the JSON object containing the \"subtasks\" array, matching this structure:\n\n{\n  \"subtasks\": [\n    {\n      \"id\": {{nextSubtaskId}}, // First subtask ID\n      \"title\": \"Specific subtask title\",\n      \"description\": \"Detailed description\",\n      \"dependencies\": [], // e.g., [\"{{task.id}}.1\", \"{{task.id}}.2\"] for dependencies. Use empty array [] if no dependencies\n      \"details\": \"Implementation guidance\",\n      \"testStrategy\": \"Optional testing approach\"\n    },\n    // ... (repeat for {{#if (gt subtaskCount 0)}}a total of {{subtaskCount}}{{else}}an appropriate number of{{/if}} subtasks with sequential IDs)\n  ]\n}"
 		}
 	}
 }

src/prompts/update-tasks.json

@@ -31,8 +31,8 @@
 	},
 	"prompts": {
 		"default": {
-			"system": "You are an AI assistant helping to update software development tasks based on new context.\nYou will be given a set of tasks and a prompt describing changes or new implementation details.\nYour job is to update the tasks to reflect these changes, while preserving their basic structure.\n\nGuidelines:\n1. Maintain the same IDs, statuses, and dependencies unless specifically mentioned in the prompt\n2. Update titles, descriptions, details, and test strategies to reflect the new information\n3. Do not change anything unnecessarily - just adapt what needs to change based on the prompt\n4. You should return ALL the tasks in order, not just the modified ones\n5. Return a complete valid JSON object with the updated tasks array\n6. VERY IMPORTANT: Preserve all subtasks marked as \"done\" or \"completed\" - do not modify their content\n7. For tasks with completed subtasks, build upon what has already been done rather than rewriting everything\n8. If an existing completed subtask needs to be changed/undone based on the new context, DO NOT modify it directly\n9. Instead, add a new subtask that clearly indicates what needs to be changed or replaced\n10. Use the existence of completed subtasks as an opportunity to make new subtasks more specific and targeted\n\nThe changes described in the prompt should be applied to ALL tasks in the list.",
-			"user": "Here are the tasks to update:\n{{{json tasks}}}\n\nPlease update these tasks based on the following new context:\n{{updatePrompt}}\n\nIMPORTANT: In the tasks JSON above, any subtasks with \"status\": \"done\" or \"status\": \"completed\" should be preserved exactly as is. Build your changes around these completed items.{{#if projectContext}}\n\n# Project Context\n\n{{projectContext}}{{/if}}\n\nReturn only the updated tasks as a valid JSON array."
+			"system": "You are an AI assistant helping to update software development tasks based on new context.\nYou will be given a set of tasks and a prompt describing changes or new implementation details.\nYour job is to update the tasks to reflect these changes, while preserving their basic structure.\n\nCRITICAL RULES:\n1. Return ONLY a JSON array - no explanations, no markdown, no additional text before or after\n2. Each task MUST have ALL fields from the original (do not omit any fields)\n3. Maintain the same IDs, statuses, and dependencies unless specifically mentioned in the prompt\n4. Update titles, descriptions, details, and test strategies to reflect the new information\n5. Do not change anything unnecessarily - just adapt what needs to change based on the prompt\n6. You should return ALL the tasks in order, not just the modified ones\n7. Return a complete valid JSON array with all tasks\n8. VERY IMPORTANT: Preserve all subtasks marked as \"done\" or \"completed\" - do not modify their content\n9. For tasks with completed subtasks, build upon what has already been done rather than rewriting everything\n10. If an existing completed subtask needs to be changed/undone based on the new context, DO NOT modify it directly\n11. Instead, add a new subtask that clearly indicates what needs to be changed or replaced\n12. Use the existence of completed subtasks as an opportunity to make new subtasks more specific and targeted\n\nThe changes described in the prompt should be applied to ALL tasks in the list.",
+			"user": "Here are the tasks to update:\n{{{json tasks}}}\n\nPlease update these tasks based on the following new context:\n{{updatePrompt}}\n\nIMPORTANT: In the tasks JSON above, any subtasks with \"status\": \"done\" or \"status\": \"completed\" should be preserved exactly as is. Build your changes around these completed items.{{#if projectContext}}\n\n# Project Context\n\n{{projectContext}}{{/if}}\n\nRequired JSON structure for EACH task (ALL fields MUST be present):\n{\n  \"id\": <number>,\n  \"title\": <string>,\n  \"description\": <string>,\n  \"status\": <string>,\n  \"dependencies\": <array>,\n  \"priority\": <string or null>,\n  \"details\": <string or null>,\n  \"testStrategy\": <string or null>,\n  \"subtasks\": <array or null>\n}\n\nReturn a valid JSON array containing ALL the tasks with ALL their fields:\n- id (number) - preserve existing value\n- title (string)\n- description (string)\n- status (string) - preserve existing value unless explicitly changing\n- dependencies (array) - preserve existing value unless explicitly changing\n- priority (string or null)\n- details (string or null)\n- testStrategy (string or null)\n- subtasks (array or null)\n\nReturn ONLY the JSON array now:"
 		}
 	}
 }

src/task-master.js

@@ -17,6 +17,7 @@ import {
 	LEGACY_CONFIG_FILE,
 	COMPLEXITY_REPORT_FILE
 } from './constants/paths.js';
+import { findProjectRoot } from './utils/path-utils.js';
 
 /**
  * TaskMaster class manages all the paths for the application.
@@ -159,22 +160,6 @@ export class TaskMaster {
  * @returns {TaskMaster} An initialized TaskMaster instance.
  */
 export function initTaskMaster(overrides = {}) {
-	const findProjectRoot = (startDir = process.cwd()) => {
-		const projectMarkers = [TASKMASTER_DIR, LEGACY_CONFIG_FILE];
-		let currentDir = path.resolve(startDir);
-		const rootDir = path.parse(currentDir).root;
-		while (currentDir !== rootDir) {
-			for (const marker of projectMarkers) {
-				const markerPath = path.join(currentDir, marker);
-				if (fs.existsSync(markerPath)) {
-					return currentDir;
-				}
-			}
-			currentDir = path.dirname(currentDir);
-		}
-		return null;
-	};
-
 	const resolvePath = (
 		pathType,
 		override,
@@ -264,13 +249,8 @@ export function initTaskMaster(overrides = {}) {
 
 		paths.projectRoot = resolvedOverride;
 	} else {
-		const foundRoot = findProjectRoot();
-		if (!foundRoot) {
-			throw new Error(
-				'Unable to find project root. No project markers found. Run "init" command first.'
-			);
-		}
-		paths.projectRoot = foundRoot;
+		// findProjectRoot now always returns a value (fallback to cwd)
+		paths.projectRoot = findProjectRoot();
 	}
 
 	// TaskMaster Directory

src/utils/path-utils.js

@@ -66,8 +66,10 @@ export function findProjectRoot(startDir = process.cwd()) {
 
 	let currentDir = path.resolve(startDir);
 	const rootDir = path.parse(currentDir).root;
+	const maxDepth = 50; // Reasonable limit to prevent infinite loops
+	let depth = 0;
 
-	while (currentDir !== rootDir) {
+	while (currentDir !== rootDir && depth < maxDepth) {
 		// Check if current directory contains any project markers
 		for (const marker of projectMarkers) {
 			const markerPath = path.join(currentDir, marker);
@@ -76,9 +78,11 @@ export function findProjectRoot(startDir = process.cwd()) {
 			}
 		}
 		currentDir = path.dirname(currentDir);
+		depth++;
 	}
 
-	return null;
+	// Fallback to current working directory if no project root found
+	return process.cwd();
 }
 
 /**

tests/e2e/README.md

@@ -1,204 +0,0 @@
-# Task Master E2E Tests
-
-This directory contains the modern end-to-end test suite for Task Master AI. The JavaScript implementation provides parallel execution, better error handling, and improved maintainability compared to the legacy bash script.
-
-## Features
-
-- **Parallel Execution**: Run test groups concurrently for faster test completion
-- **Modular Architecture**: Tests are organized into logical groups (setup, core, providers, advanced)
-- **Comprehensive Logging**: Detailed logs with timestamps, cost tracking, and color-coded output
-- **LLM Analysis**: Automatic analysis of test results using AI
-- **Error Handling**: Robust error handling with categorization and recommendations
-- **Flexible Configuration**: Easy to configure test settings and provider configurations
-
-## Structure
-
-```
-tests/e2e/
-├── config/
-│   └── test-config.js      # Test configuration and settings
-├── utils/
-│   ├── logger.js           # Test logging utilities
-│   ├── test-helpers.js     # Common test helper functions
-│   ├── llm-analyzer.js     # LLM-based log analysis
-│   └── error-handler.js    # Error handling and reporting
-├── tests/
-│   ├── setup.test.js       # Setup and initialization tests
-│   ├── core.test.js        # Core task management tests
-│   ├── providers.test.js   # Multi-provider tests
-│   └── advanced.test.js    # Advanced feature tests
-├── runners/
-│   ├── parallel-runner.js  # Parallel test execution
-│   └── test-worker.js      # Worker thread for parallel execution
-├── run-e2e-tests.js        # Main test runner
-├── run_e2e.sh              # Legacy bash implementation
-└── e2e_helpers.sh          # Legacy bash helpers
-```
-
-## Usage
-
-### Run All Tests (Recommended)
-
-```bash
-# Runs all test groups in the correct order
-npm run test:e2e
-```
-
-### Run Tests Sequentially
-
-```bash
-# Runs all test groups sequentially instead of in parallel
-npm run test:e2e:sequential
-```
-
-### Run Individual Test Groups
-
-Each test command automatically handles setup if needed, creating a fresh test directory:
-
-```bash
-# Each command creates its own test environment automatically
-npm run test:e2e:setup      # Setup only (initialize, parse PRD, analyze complexity)
-npm run test:e2e:core       # Auto-runs setup + core tests (task CRUD, dependencies, status)
-npm run test:e2e:providers  # Auto-runs setup + provider tests (multi-provider testing)
-npm run test:e2e:advanced   # Auto-runs setup + advanced tests (tags, subtasks, expand)
-```
-
-**Note**: Each command creates a fresh test directory, so running individual tests will not share state. This ensures test isolation but means each run will parse the PRD and set up from scratch.
-
-### Run Multiple Groups
-
-```bash
-# Specify multiple groups to run together
-node tests/e2e/run-e2e-tests.js --groups core,providers
-
-# This automatically runs setup first if needed
-node tests/e2e/run-e2e-tests.js --groups providers,advanced
-```
-
-### Run Tests Against Existing Directory
-
-If you want to reuse a test directory from a previous run:
-
-```bash
-# First, find your test directory from a previous run:
-ls tests/e2e/_runs/
-
-# Then run specific tests against that directory:
-node tests/e2e/run-e2e-tests.js --groups core --test-dir tests/e2e/_runs/run_2025-07-03_094800611
-```
-
-### Analyze Existing Log
-```bash
-npm run test:e2e:analyze
-
-# Or analyze specific log file
-node tests/e2e/run-e2e-tests.js --analyze-log path/to/log.log
-```
-
-### Skip Verification Tests
-```bash
-node tests/e2e/run-e2e-tests.js --skip-verification
-```
-
-### Run Legacy Bash Tests
-```bash
-npm run test:e2e:bash
-```
-
-## Test Groups
-
-### Setup (`setup`)
-- NPM global linking
-- Project initialization
-- PRD parsing
-- Complexity analysis
-
-### Core (`core`)
-- Task CRUD operations
-- Dependency management
-- Status management
-- Subtask operations
-
-### Providers (`providers`)
-- Multi-provider add-task testing
-- Provider comparison
-- Model switching
-- Error handling per provider
-
-### Advanced (`advanced`)
-- Tag management
-- Model configuration
-- Task expansion
-- File generation
-
-## Configuration
-
-Edit `config/test-config.js` to customize:
-
-- Test paths and directories
-- Provider configurations
-- Test prompts
-- Parallel execution settings
-- LLM analysis settings
-
-## Output
-
-- **Log Files**: Saved to `tests/e2e/log/` with timestamp
-- **Test Artifacts**: Created in `tests/e2e/_runs/run_TIMESTAMP/`
-- **Console Output**: Color-coded with progress indicators
-- **Cost Tracking**: Automatic tracking of AI API costs
-
-## Requirements
-
-- Node.js >= 18.0.0
-- Dependencies: chalk, boxen, dotenv, node-fetch
-- System utilities: jq, bc
-- Valid API keys in `.env` file
-
-## Comparison with Bash Tests
-
-| Feature | Bash Script | JavaScript |
-|---------|------------|------------|
-| Parallel Execution | ❌ | ✅ |
-| Error Categorization | Basic | Advanced |
-| Test Isolation | Limited | Full |
-| Performance | Slower | Faster |
-| Debugging | Harder | Easier |
-| Cross-platform | Limited | Better |
-
-## Troubleshooting
-
-1. **Missing Dependencies**: Install system utilities with `brew install jq bc` (macOS) or `apt-get install jq bc` (Linux)
-2. **API Errors**: Check `.env` file for valid API keys
-3. **Permission Errors**: Ensure proper file permissions
-4. **Timeout Issues**: Adjust timeout in config file
-
-## Development
-
-To add new tests:
-
-1. Create a new test file in `tests/` directory
-2. Export a default async function that accepts (logger, helpers, context)
-3. Return a results object with status and errors
-4. Add the test to appropriate group in `test-config.js`
-
-Example test structure:
-```javascript
-export default async function myTest(logger, helpers, context) {
-  const results = {
-    status: 'passed',
-    errors: []
-  };
-
-  try {
-    logger.step('Running my test');
-    // Test implementation
-    logger.success('Test passed');
-  } catch (error) {
-    results.status = 'failed';
-    results.errors.push(error.message);
-  }
-
-  return results;
-}
-```

tests/e2e/TEST-REPORTS.md

@@ -1,81 +0,0 @@
-# E2E Test Reports
-
-Task Master's E2E tests now generate comprehensive test reports using Jest Stare, providing an interactive and visually appealing test report similar to Playwright's reporting capabilities.
-
-## Test Report Formats
-
-When you run `npm run test:e2e:jest`, the following reports are generated:
-
-### 1. Jest Stare HTML Report
-- **Location**: `test-results/index.html`
-- **Features**:
-  - Interactive dashboard with charts and graphs
-  - Test execution timeline and performance metrics
-  - Detailed failure messages with stack traces
-  - Console output for each test
-  - Search and filter capabilities
-  - Pass/Fail/Skip statistics with visual charts
-  - Test duration analysis
-  - Collapsible test suites
-  - Coverage link integration
-  - Summary statistics
-
-### 2. JSON Results
-- **Location**: `test-results/jest-results.json`
-- **Use Cases**:
-  - Programmatic access to test results
-  - Custom reporting tools
-  - Test result analysis
-
-### 3. JUnit XML Report
-- **Location**: `test-results/e2e-junit.xml`
-- **Use Cases**:
-  - CI/CD integration
-  - Test result parsing
-  - Historical tracking
-
-### 4. Console Output
-- Standard Jest terminal output with verbose mode enabled
-
-## Running Tests with Reports
-
-```bash
-# Run all E2E tests and generate reports
-npm run test:e2e:jest
-
-# View the HTML report
-npm run test:e2e:jest:report
-
-# Run specific tests
-npm run test:e2e:jest:command "add-task"
-```
-
-## Report Configuration
-
-The report configuration is defined in `jest.e2e.config.js`:
-
-- **HTML Reporter**: Includes failure messages, console logs, and execution warnings
-- **JUnit Reporter**: Includes console output and suite errors
-- **Coverage**: Separate coverage directory at `coverage-e2e/`
-
-## CI/CD Integration
-
-The JUnit XML report can be consumed by CI tools like:
-- Jenkins (JUnit plugin)
-- GitHub Actions (test-reporter action)
-- GitLab CI (artifact reports)
-- CircleCI (test results)
-
-## Ignored Files
-
-The following are automatically ignored by git:
-- `test-results/` directory
-- `coverage-e2e/` directory
-- Individual report files
-
-## Viewing Historical Results
-
-To keep historical test results:
-1. Copy the `test-results` directory before running new tests
-2. Use a timestamp suffix: `test-results-2024-01-15/`
-3. Compare HTML reports side by side

tests/e2e/config/test-config.js

@@ -1,72 +0,0 @@
-import { fileURLToPath } from 'url';
-import { dirname, join } from 'path';
-import { config as dotenvConfig } from 'dotenv';
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = dirname(__filename);
-
-// Load environment variables
-const projectRoot = join(__dirname, '../../..');
-dotenvConfig({ path: join(projectRoot, '.env') });
-
-export const testConfig = {
-	// Paths
-	paths: {
-		projectRoot,
-		sourceDir: projectRoot,
-		baseTestDir: join(projectRoot, 'tests/e2e/_runs'),
-		logDir: join(projectRoot, 'tests/e2e/log'),
-		samplePrdSource: join(projectRoot, 'tests/fixtures/sample-prd.txt'),
-		mainEnvFile: join(projectRoot, '.env'),
-		supportedModelsFile: join(
-			projectRoot,
-			'scripts/modules/supported-models.json'
-		)
-	},
-
-	// Test settings
-	settings: {
-		runVerificationTest: true,
-		parallelTestGroups: 4, // Number of parallel test groups
-		timeout: 600000, // 10 minutes default timeout
-		retryAttempts: 2
-	},
-
-	// Provider test configuration
-	providers: [
-		{ name: 'anthropic', model: 'claude-3-7-sonnet-20250219', flags: [] },
-		{ name: 'openai', model: 'gpt-4o', flags: [] },
-		{ name: 'google', model: 'gemini-2.5-pro-preview-05-06', flags: [] },
-		{ name: 'perplexity', model: 'sonar-pro', flags: [] },
-		{ name: 'xai', model: 'grok-3', flags: [] },
-		{ name: 'openrouter', model: 'anthropic/claude-3.7-sonnet', flags: [] }
-	],
-
-	// Test prompts
-	prompts: {
-		addTask:
-			'Create a task to implement user authentication using OAuth 2.0 with Google as the provider. Include steps for registering the app, handling the callback, and storing user sessions.',
-		updateTask:
-			'Update backend server setup: Ensure CORS is configured to allow requests from the frontend origin.',
-		updateFromTask:
-			'Refactor the backend storage module to use a simple JSON file (storage.json) instead of an in-memory object for persistence. Update relevant tasks.',
-		updateSubtask:
-			'Implementation note: Remember to handle potential API errors and display a user-friendly message.'
-	},
-
-	// LLM Analysis settings
-	llmAnalysis: {
-		enabled: true,
-		model: 'claude-3-7-sonnet-20250219',
-		provider: 'anthropic',
-		maxTokens: 3072
-	}
-};
-
-// Export test groups for parallel execution
-export const testGroups = {
-	setup: ['setup'],
-	core: ['core'],
-	providers: ['providers'],
-	advanced: ['advanced']
-};

tests/e2e/runners/parallel-runner.js

@@ -1,225 +0,0 @@
-import { Worker } from 'worker_threads';
-import { fileURLToPath } from 'url';
-import { dirname, join } from 'path';
-import { EventEmitter } from 'events';
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = dirname(__filename);
-
-export class ParallelTestRunner extends EventEmitter {
-	constructor(logger) {
-		super();
-		this.logger = logger;
-		this.workers = [];
-		this.results = {};
-	}
-
-	/**
-	 * Run test groups in parallel
-	 * @param {Object} testGroups - Groups of tests to run
-	 * @param {Object} sharedContext - Shared context for all tests
-	 * @returns {Promise<Object>} Combined results from all test groups
-	 */
-	async runTestGroups(testGroups, sharedContext) {
-		const groupNames = Object.keys(testGroups);
-		const workerPromises = [];
-
-		this.logger.info(
-			`Starting parallel execution of ${groupNames.length} test groups`
-		);
-
-		for (const groupName of groupNames) {
-			const workerPromise = this.runTestGroup(
-				groupName,
-				testGroups[groupName],
-				sharedContext
-			);
-			workerPromises.push(workerPromise);
-		}
-
-		// Wait for all workers to complete
-		const results = await Promise.allSettled(workerPromises);
-
-		// Process results
-		const combinedResults = {
-			overall: 'passed',
-			groups: {},
-			summary: {
-				totalGroups: groupNames.length,
-				passedGroups: 0,
-				failedGroups: 0,
-				errors: []
-			}
-		};
-
-		results.forEach((result, index) => {
-			const groupName = groupNames[index];
-
-			if (result.status === 'fulfilled') {
-				combinedResults.groups[groupName] = result.value;
-				if (result.value.status === 'passed') {
-					combinedResults.summary.passedGroups++;
-				} else {
-					combinedResults.summary.failedGroups++;
-					combinedResults.overall = 'failed';
-				}
-			} else {
-				combinedResults.groups[groupName] = {
-					status: 'failed',
-					error: result.reason.message || 'Unknown error'
-				};
-				combinedResults.summary.failedGroups++;
-				combinedResults.summary.errors.push({
-					group: groupName,
-					error: result.reason.message
-				});
-				combinedResults.overall = 'failed';
-			}
-		});
-
-		return combinedResults;
-	}
-
-	/**
-	 * Run a single test group in a worker thread
-	 */
-	async runTestGroup(groupName, testModules, sharedContext) {
-		return new Promise((resolve, reject) => {
-			const workerPath = join(__dirname, 'test-worker.js');
-
-			const worker = new Worker(workerPath, {
-				workerData: {
-					groupName,
-					testModules,
-					sharedContext,
-					logDir: this.logger.logDir,
-					testRunId: this.logger.testRunId
-				}
-			});
-
-			this.workers.push(worker);
-
-			// Handle messages from worker
-			worker.on('message', (message) => {
-				if (message.type === 'log') {
-					const level = message.level.toLowerCase();
-					if (typeof this.logger[level] === 'function') {
-						this.logger[level](message.message);
-					} else {
-						// Fallback to info if the level doesn't exist
-						this.logger.info(message.message);
-					}
-				} else if (message.type === 'step') {
-					this.logger.step(message.message);
-				} else if (message.type === 'cost') {
-					this.logger.addCost(message.cost);
-				} else if (message.type === 'results') {
-					this.results[groupName] = message.results;
-				}
-			});
-
-			// Handle worker completion
-			worker.on('exit', (code) => {
-				this.workers = this.workers.filter((w) => w !== worker);
-
-				if (code === 0) {
-					resolve(
-						this.results[groupName] || { status: 'passed', group: groupName }
-					);
-				} else {
-					reject(
-						new Error(`Worker for group ${groupName} exited with code ${code}`)
-					);
-				}
-			});
-
-			// Handle worker errors
-			worker.on('error', (error) => {
-				this.workers = this.workers.filter((w) => w !== worker);
-				reject(error);
-			});
-		});
-	}
-
-	/**
-	 * Terminate all running workers
-	 */
-	async terminate() {
-		const terminationPromises = this.workers.map((worker) =>
-			worker
-				.terminate()
-				.catch((err) =>
-					this.logger.warning(`Failed to terminate worker: ${err.message}`)
-				)
-		);
-
-		await Promise.all(terminationPromises);
-		this.workers = [];
-	}
-}
-
-/**
- * Sequential test runner for comparison or fallback
- */
-export class SequentialTestRunner {
-	constructor(logger, helpers) {
-		this.logger = logger;
-		this.helpers = helpers;
-	}
-
-	/**
-	 * Run tests sequentially
-	 */
-	async runTests(testModules, context) {
-		const results = {
-			overall: 'passed',
-			tests: {},
-			summary: {
-				totalTests: testModules.length,
-				passedTests: 0,
-				failedTests: 0,
-				errors: []
-			}
-		};
-
-		for (const testModule of testModules) {
-			try {
-				this.logger.step(`Running ${testModule} tests`);
-
-				// Dynamic import of test module
-				const testPath = join(
-					dirname(__dirname),
-					'tests',
-					`${testModule}.test.js`
-				);
-				const { default: testFn } = await import(testPath);
-
-				// Run the test
-				const testResults = await testFn(this.logger, this.helpers, context);
-
-				results.tests[testModule] = testResults;
-
-				if (testResults.status === 'passed') {
-					results.summary.passedTests++;
-				} else {
-					results.summary.failedTests++;
-					results.overall = 'failed';
-				}
-			} catch (error) {
-				this.logger.error(`Failed to run ${testModule}: ${error.message}`);
-				results.tests[testModule] = {
-					status: 'failed',
-					error: error.message
-				};
-				results.summary.failedTests++;
-				results.summary.errors.push({
-					test: testModule,
-					error: error.message
-				});
-				results.overall = 'failed';
-			}
-		}
-
-		return results;
-	}
-}

tests/e2e/runners/test-worker.js

@@ -1,135 +0,0 @@
-import { parentPort, workerData } from 'worker_threads';
-import { fileURLToPath } from 'url';
-import { dirname, join } from 'path';
-import { TestLogger } from '../utils/logger.js';
-import { TestHelpers } from '../utils/test-helpers.js';
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = dirname(__filename);
-
-// Worker logger that sends messages to parent
-class WorkerLogger extends TestLogger {
-	constructor(logDir, testRunId, groupName) {
-		super(logDir, `${testRunId}_${groupName}`);
-		this.groupName = groupName;
-	}
-
-	log(level, message, options = {}) {
-		super.log(level, message, options);
-
-		// Send log to parent
-		parentPort.postMessage({
-			type: 'log',
-			level: level.toLowerCase(),
-			message: `[${this.groupName}] ${message}`
-		});
-	}
-
-	step(message) {
-		super.step(message);
-
-		parentPort.postMessage({
-			type: 'step',
-			message: `[${this.groupName}] ${message}`
-		});
-	}
-
-	addCost(cost) {
-		super.addCost(cost);
-
-		parentPort.postMessage({
-			type: 'cost',
-			cost
-		});
-	}
-}
-
-// Main worker execution
-async function runTestGroup() {
-	const { groupName, testModules, sharedContext, logDir, testRunId } =
-		workerData;
-
-	const logger = new WorkerLogger(logDir, testRunId, groupName);
-	const helpers = new TestHelpers(logger);
-
-	logger.info(`Worker started for test group: ${groupName}`);
-
-	const results = {
-		group: groupName,
-		status: 'passed',
-		tests: {},
-		errors: [],
-		startTime: Date.now()
-	};
-
-	try {
-		// Run each test module in the group
-		for (const testModule of testModules) {
-			try {
-				logger.info(`Running test: ${testModule}`);
-
-				// Dynamic import of test module
-				const testPath = join(
-					dirname(__dirname),
-					'tests',
-					`${testModule}.test.js`
-				);
-				const { default: testFn } = await import(testPath);
-
-				// Run the test with shared context
-				const testResults = await testFn(logger, helpers, sharedContext);
-
-				results.tests[testModule] = testResults;
-
-				if (testResults.status !== 'passed') {
-					results.status = 'failed';
-					if (testResults.errors) {
-						results.errors.push(...testResults.errors);
-					}
-				}
-			} catch (error) {
-				logger.error(`Test ${testModule} failed: ${error.message}`);
-				results.tests[testModule] = {
-					status: 'failed',
-					error: error.message,
-					stack: error.stack
-				};
-				results.status = 'failed';
-				results.errors.push({
-					test: testModule,
-					error: error.message
-				});
-			}
-		}
-	} catch (error) {
-		logger.error(`Worker error: ${error.message}`);
-		results.status = 'failed';
-		results.errors.push({
-			group: groupName,
-			error: error.message,
-			stack: error.stack
-		});
-	}
-
-	results.endTime = Date.now();
-	results.duration = results.endTime - results.startTime;
-
-	// Flush logs and get summary
-	logger.flush();
-	const summary = logger.getSummary();
-	results.summary = summary;
-
-	// Send results to parent
-	parentPort.postMessage({
-		type: 'results',
-		results
-	});
-
-	logger.info(`Worker completed for test group: ${groupName}`);
-}
-
-// Run the test group
-runTestGroup().catch((error) => {
-	console.error('Worker fatal error:', error);
-	process.exit(1);
-});

tests/e2e/setup/global-setup.js

@@ -1,59 +0,0 @@
-/**
- * Global setup for E2E tests
- * Runs once before all test suites
- */
-
-import { execSync } from 'child_process';
-import { existsSync } from 'fs';
-import { join } from 'path';
-import { fileURLToPath } from 'url';
-import { dirname } from 'path';
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = dirname(__filename);
-
-export default async () => {
-	// Silent mode for cleaner output
-	if (!process.env.JEST_SILENT_REPORTER) {
-		console.log('\n🚀 Setting up E2E test environment...\n');
-	}
-
-	try {
-		// Ensure task-master is linked globally
-		const projectRoot = join(__dirname, '../../..');
-		if (!process.env.JEST_SILENT_REPORTER) {
-			console.log('📦 Linking task-master globally...');
-		}
-		execSync('npm link', {
-			cwd: projectRoot,
-			stdio: 'inherit'
-		});
-
-		// Verify .env file exists
-		const envPath = join(projectRoot, '.env');
-		if (!existsSync(envPath)) {
-			console.warn(
-				'⚠️  Warning: .env file not found. Some tests may fail without API keys.'
-			);
-		} else {
-			if (!process.env.JEST_SILENT_REPORTER) {
-				console.log('✅ .env file found');
-			}
-		}
-
-		// Verify task-master command is available
-		try {
-			execSync('task-master --version', { stdio: 'pipe' });
-			if (!process.env.JEST_SILENT_REPORTER) {
-				console.log('✅ task-master command is available\n');
-			}
-		} catch (error) {
-			throw new Error(
-				'task-master command not found. Please ensure npm link succeeded.'
-			);
-		}
-	} catch (error) {
-		console.error('❌ Global setup failed:', error.message);
-		throw error;
-	}
-};

tests/e2e/setup/global-teardown.js

@@ -1,14 +0,0 @@
-/**
- * Global teardown for E2E tests
- * Runs once after all test suites
- */
-
-export default async () => {
-	// Silent mode for cleaner output
-	if (!process.env.JEST_SILENT_REPORTER) {
-		console.log('\n🧹 Cleaning up E2E test environment...\n');
-	}
-
-	// Any global cleanup needed
-	// Note: Individual test directories are cleaned up in afterEach hooks
-};

tests/e2e/setup/jest-setup.js

@@ -1,91 +0,0 @@
-/**
- * Jest setup file for E2E tests
- * Runs before each test file
- */
-
-import { jest, expect, afterAll } from '@jest/globals';
-import { TestHelpers } from '../utils/test-helpers.js';
-import { TestLogger } from '../utils/logger.js';
-
-// Increase timeout for all E2E tests (can be overridden per test)
-jest.setTimeout(600000);
-
-// Add custom matchers for CLI testing
-expect.extend({
-	toContainTaskId(received) {
-		const taskIdRegex = /#?\d+/;
-		const pass = taskIdRegex.test(received);
-
-		if (pass) {
-			return {
-				message: () => `expected ${received} not to contain a task ID`,
-				pass: true
-			};
-		} else {
-			return {
-				message: () => `expected ${received} to contain a task ID (e.g., #123)`,
-				pass: false
-			};
-		}
-	},
-
-	toHaveExitCode(received, expected) {
-		const pass = received.exitCode === expected;
-
-		if (pass) {
-			return {
-				message: () => `expected exit code not to be ${expected}`,
-				pass: true
-			};
-		} else {
-			return {
-				message: () =>
-					`expected exit code ${expected} but got ${received.exitCode}\nstderr: ${received.stderr}`,
-				pass: false
-			};
-		}
-	},
-
-	toContainInOutput(received, expected) {
-		const output = (received.stdout || '') + (received.stderr || '');
-		const pass = output.includes(expected);
-
-		if (pass) {
-			return {
-				message: () => `expected output not to contain "${expected}"`,
-				pass: true
-			};
-		} else {
-			return {
-				message: () =>
-					`expected output to contain "${expected}"\nstdout: ${received.stdout}\nstderr: ${received.stderr}`,
-				pass: false
-			};
-		}
-	}
-});
-
-// Global test helpers
-global.TestHelpers = TestHelpers;
-global.TestLogger = TestLogger;
-
-// Helper to create test context
-import { mkdtempSync } from 'fs';
-import { join } from 'path';
-import { tmpdir } from 'os';
-
-global.createTestContext = (testName) => {
-	// Create a proper log directory in temp for tests
-	const testLogDir = mkdtempSync(join(tmpdir(), `task-master-test-logs-${testName}-`));
-	const testRunId = Date.now().toString();
-	
-	const logger = new TestLogger(testLogDir, testRunId);
-	const helpers = new TestHelpers(logger);
-	return { logger, helpers };
-};
-
-// Clean up any hanging processes
-afterAll(async () => {
-	// Give time for any async operations to complete
-	await new Promise((resolve) => setTimeout(resolve, 100));
-});

tests/e2e/setup/rate-limit-sequencer.cjs

@@ -1,73 +0,0 @@
-/**
- * Custom Jest test sequencer to manage parallel execution
- * and avoid hitting AI rate limits
- */
-
-const Sequencer = require('@jest/test-sequencer').default;
-
-class RateLimitSequencer extends Sequencer {
-	/**
-	 * Sort tests to optimize execution and avoid rate limits
-	 */
-	sort(tests) {
-		// Categorize tests by their AI usage
-		const aiHeavyTests = [];
-		const aiLightTests = [];
-		const nonAiTests = [];
-
-		tests.forEach((test) => {
-			const testPath = test.path.toLowerCase();
-			
-			// Tests that make heavy use of AI APIs
-			if (
-				testPath.includes('update-task') ||
-				testPath.includes('expand-task') ||
-				testPath.includes('research') ||
-				testPath.includes('parse-prd') ||
-				testPath.includes('generate') ||
-				testPath.includes('analyze-complexity')
-			) {
-				aiHeavyTests.push(test);
-			}
-			// Tests that make light use of AI APIs
-			else if (
-				testPath.includes('add-task') ||
-				testPath.includes('update-subtask')
-			) {
-				aiLightTests.push(test);
-			}
-			// Tests that don't use AI APIs
-			else {
-				nonAiTests.push(test);
-			}
-		});
-
-		// Sort each category by duration (fastest first)
-		const sortByDuration = (a, b) => {
-			const aTime = a.duration || 0;
-			const bTime = b.duration || 0;
-			return aTime - bTime;
-		};
-
-		aiHeavyTests.sort(sortByDuration);
-		aiLightTests.sort(sortByDuration);
-		nonAiTests.sort(sortByDuration);
-
-		// Return tests in order: non-AI first, then light AI, then heavy AI
-		// This allows non-AI tests to run quickly while AI tests are distributed
-		return [...nonAiTests, ...aiLightTests, ...aiHeavyTests];
-	}
-
-	/**
-	 * Shard tests across workers to balance AI load
-	 */
-	shard(tests, { shardIndex, shardCount }) {
-		const shardSize = Math.ceil(tests.length / shardCount);
-		const start = shardSize * shardIndex;
-		const end = shardSize * (shardIndex + 1);
-
-		return tests.slice(start, end);
-	}
-}
-
-module.exports = RateLimitSequencer;

tests/e2e/tests/commands/add-dependency.test.js

@@ -1,501 +0,0 @@
-/**
- * E2E tests for add-dependency command
- * Tests dependency management functionality
- */
-
-import { describe, it, expect, beforeEach, afterEach } from '@jest/globals';
-import { mkdtempSync, existsSync, readFileSync, rmSync, writeFileSync, mkdirSync } from 'fs';
-import { join } from 'path';
-import { tmpdir } from 'os';
-
-describe('task-master add-dependency', () => {
-	let testDir;
-	let helpers;
-
-	beforeEach(async () => {
-		// Create test directory
-		testDir = mkdtempSync(join(tmpdir(), 'task-master-add-dep-'));
-
-		// Initialize test helpers
-		const context = global.createTestContext('add-dependency');
-		helpers = context.helpers;
-
-		// Copy .env file if it exists
-		const mainEnvPath = join(process.cwd(), '.env');
-		const testEnvPath = join(testDir, '.env');
-		if (existsSync(mainEnvPath)) {
-			const envContent = readFileSync(mainEnvPath, 'utf8');
-			writeFileSync(testEnvPath, envContent);
-		}
-
-		// Initialize task-master project
-		const initResult = await helpers.taskMaster('init', ['-y'], {
-			cwd: testDir
-		});
-		expect(initResult).toHaveExitCode(0);
-
-		// Ensure tasks.json exists (bug workaround)
-		const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-		if (!existsSync(tasksJsonPath)) {
-			mkdirSync(join(testDir, '.taskmaster/tasks'), { recursive: true });
-			writeFileSync(tasksJsonPath, JSON.stringify({ master: { tasks: [] } }));
-		}
-	});
-
-	afterEach(() => {
-		// Clean up test directory
-		if (testDir && existsSync(testDir)) {
-			rmSync(testDir, { recursive: true, force: true });
-		}
-	});
-
-	describe('Basic dependency creation', () => {
-		it('should add a single dependency to a task', async () => {
-			// Create tasks
-			const dep = await helpers.taskMaster('add-task', ['--title', 'Dependency task', '--description', 'A dependency'], { cwd: testDir });
-			const depId = helpers.extractTaskId(dep.stdout);
-
-			const task = await helpers.taskMaster('add-task', ['--title', 'Main task', '--description', 'Main task description'], { cwd: testDir });
-			const taskId = helpers.extractTaskId(task.stdout);
-
-			// Add dependency
-			const result = await helpers.taskMaster('add-dependency', ['--id', taskId, '--depends-on', depId], { cwd: testDir });
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully added dependency');
-
-			// Verify dependency was added
-			const showResult = await helpers.taskMaster('show', [taskId], { cwd: testDir });
-			expect(showResult.stdout).toContain('Dependencies:');
-			expect(showResult.stdout).toContain(depId);
-		});
-
-		it('should add multiple dependencies one by one', async () => {
-			// Create dependency tasks
-			const dep1 = await helpers.taskMaster('add-task', ['--title', 'First dependency', '--description', 'First dep'], { cwd: testDir });
-			const depId1 = helpers.extractTaskId(dep1.stdout);
-
-			const dep2 = await helpers.taskMaster('add-task', ['--title', 'Second dependency', '--description', 'Second dep'], { cwd: testDir });
-			const depId2 = helpers.extractTaskId(dep2.stdout);
-
-			const dep3 = await helpers.taskMaster('add-task', ['--title', 'Third dependency', '--description', 'Third dep'], { cwd: testDir });
-			const depId3 = helpers.extractTaskId(dep3.stdout);
-
-			const task = await helpers.taskMaster('add-task', ['--title', 'Main task', '--description', 'Main task'], { cwd: testDir });
-			const taskId = helpers.extractTaskId(task.stdout);
-
-			// Add dependencies one by one
-			const result1 = await helpers.taskMaster('add-dependency', ['--id', taskId, '--depends-on', depId1], { cwd: testDir });
-			expect(result1).toHaveExitCode(0);
-
-			const result2 = await helpers.taskMaster('add-dependency', ['--id', taskId, '--depends-on', depId2], { cwd: testDir });
-			expect(result2).toHaveExitCode(0);
-
-			const result3 = await helpers.taskMaster('add-dependency', ['--id', taskId, '--depends-on', depId3], { cwd: testDir });
-			expect(result3).toHaveExitCode(0);
-
-			// Verify all dependencies were added
-			const showResult = await helpers.taskMaster('show', [taskId], { cwd: testDir });
-			expect(showResult.stdout).toContain(depId1);
-			expect(showResult.stdout).toContain(depId2);
-			expect(showResult.stdout).toContain(depId3);
-		});
-	});
-
-	describe('Dependency validation', () => {
-		it('should prevent circular dependencies', async () => {
-			// Create circular dependency chain
-			const task1 = await helpers.taskMaster('add-task', ['--title', 'Task 1', '--description', 'First task'], { cwd: testDir });
-			const id1 = helpers.extractTaskId(task1.stdout);
-
-			const task2 = await helpers.taskMaster('add-task', ['--title', 'Task 2', '--description', 'Second task'], { cwd: testDir });
-			const id2 = helpers.extractTaskId(task2.stdout);
-
-			// Add first dependency
-			await helpers.taskMaster('add-dependency', ['--id', id2, '--depends-on', id1], { cwd: testDir });
-
-			// Try to create circular dependency
-			const result = await helpers.taskMaster('add-dependency', ['--id', id1, '--depends-on', id2], {
-				cwd: testDir,
-				allowFailure: true
-			});
-			expect(result.exitCode).not.toBe(0);
-			// The command exits with code 1 but doesn't output to stderr
-		});
-
-		it('should prevent self-dependencies', async () => {
-			const task = await helpers.taskMaster('add-task', ['--title', 'Task', '--description', 'A task'], { cwd: testDir });
-			const taskId = helpers.extractTaskId(task.stdout);
-
-			const result = await helpers.taskMaster('add-dependency', ['--id', taskId, '--depends-on', taskId], {
-				cwd: testDir,
-				allowFailure: true
-			});
-			expect(result.exitCode).not.toBe(0);
-			// The command exits with code 1 but doesn't output to stderr
-		});
-
-		it('should detect transitive circular dependencies', async () => {
-			// Create chain: A -> B -> C, then try C -> A
-			const taskA = await helpers.taskMaster('add-task', ['--title', 'Task A', '--description', 'Task A'], { cwd: testDir });
-			const idA = helpers.extractTaskId(taskA.stdout);
-
-			const taskB = await helpers.taskMaster('add-task', ['--title', 'Task B', '--description', 'Task B'], { cwd: testDir });
-			const idB = helpers.extractTaskId(taskB.stdout);
-
-			const taskC = await helpers.taskMaster('add-task', ['--title', 'Task C', '--description', 'Task C'], { cwd: testDir });
-			const idC = helpers.extractTaskId(taskC.stdout);
-
-			// Create chain
-			await helpers.taskMaster('add-dependency', ['--id', idB, '--depends-on', idA], { cwd: testDir });
-			await helpers.taskMaster('add-dependency', ['--id', idC, '--depends-on', idB], { cwd: testDir });
-
-			// Try to create circular dependency
-			const result = await helpers.taskMaster('add-dependency', ['--id', idA, '--depends-on', idC], {
-				cwd: testDir,
-				allowFailure: true
-			});
-			expect(result.exitCode).not.toBe(0);
-			// The command exits with code 1 but doesn't output to stderr
-		});
-
-		it('should prevent duplicate dependencies', async () => {
-			const dep = await helpers.taskMaster('add-task', ['--title', 'Dependency', '--description', 'A dependency'], { cwd: testDir });
-			const depId = helpers.extractTaskId(dep.stdout);
-
-			const task = await helpers.taskMaster('add-task', ['--title', 'Task', '--description', 'A task'], { cwd: testDir });
-			const taskId = helpers.extractTaskId(task.stdout);
-
-			// Add dependency first time
-			await helpers.taskMaster('add-dependency', ['--id', taskId, '--depends-on', depId], { cwd: testDir });
-
-			// Try to add same dependency again
-			const result = await helpers.taskMaster('add-dependency', ['--id', taskId, '--depends-on', depId], { cwd: testDir });
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('already exists');
-		});
-	});
-
-	describe('Status updates', () => {
-		it('should update task status to blocked when adding dependencies', async () => {
-			const dep = await helpers.taskMaster('add-task', [
-				'--title',
-				'Incomplete dependency',
-				'--description',
-				'Not done yet'
-			], { cwd: testDir });
-			const depId = helpers.extractTaskId(dep.stdout);
-
-			const task = await helpers.taskMaster('add-task', ['--title', 'Task', '--description', 'A task'], { cwd: testDir });
-			const taskId = helpers.extractTaskId(task.stdout);
-
-			// Start the task
-			await helpers.taskMaster('set-status', ['--id', taskId, '--status', 'in-progress'], { cwd: testDir });
-
-			// Add dependency (does not automatically change status to blocked)
-			const result = await helpers.taskMaster('add-dependency', ['--id', taskId, '--depends-on', depId], { cwd: testDir });
-			expect(result).toHaveExitCode(0);
-			// The add-dependency command doesn't automatically change task status
-
-			// Verify status remains in-progress
-			const showResult = await helpers.taskMaster('show', [taskId], { cwd: testDir });
-			expect(showResult.stdout).toContain('► in-progress');
-		});
-
-		it('should not change status if all dependencies are complete', async () => {
-			const dep = await helpers.taskMaster('add-task', ['--title', 'Complete dependency', '--description', 'Done'], { cwd: testDir });
-			const depId = helpers.extractTaskId(dep.stdout);
-			await helpers.taskMaster('set-status', ['--id', depId, '--status', 'done'], { cwd: testDir });
-
-			const task = await helpers.taskMaster('add-task', ['--title', 'Task', '--description', 'A task'], { cwd: testDir });
-			const taskId = helpers.extractTaskId(task.stdout);
-			await helpers.taskMaster('set-status', ['--id', taskId, '--status', 'in-progress'], { cwd: testDir });
-
-			// Add completed dependency
-			const result = await helpers.taskMaster('add-dependency', ['--id', taskId, '--depends-on', depId], { cwd: testDir });
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).not.toContain('Status changed');
-
-			// Status should remain in-progress
-			const showResult = await helpers.taskMaster('show', [taskId], { cwd: testDir });
-			expect(showResult.stdout).toContain('► in-progress');
-		});
-	});
-
-	describe('Subtask dependencies', () => {
-		it('should add dependency to a subtask', async () => {
-			// Create parent and dependency
-			const parent = await helpers.taskMaster('add-task', ['--title', 'Parent task', '--description', 'Parent'], { cwd: testDir });
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			const dep = await helpers.taskMaster('add-task', ['--title', 'Dependency', '--description', 'A dependency'], { cwd: testDir });
-			const depId = helpers.extractTaskId(dep.stdout);
-
-			// Expand parent
-			const expandResult = await helpers.taskMaster('expand', ['--id', parentId, '--num', '2'], {
-				cwd: testDir,
-				timeout: 60000
-			});
-			
-			// Verify expand succeeded
-			expect(expandResult).toHaveExitCode(0);
-
-			// Add dependency to subtask
-			const subtaskId = `${parentId}.1`;
-			const result = await helpers.taskMaster('add-dependency', ['--id', subtaskId, '--depends-on', depId], { cwd: testDir, allowFailure: true });
-			
-			// Debug output
-			if (result.exitCode !== 0) {
-				console.log('STDERR:', result.stderr);
-				console.log('STDOUT:', result.stdout);
-			}
-			
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully added dependency');
-		});
-
-		it('should allow subtask to depend on another subtask', async () => {
-			// Create parent task
-			const parent = await helpers.taskMaster('add-task', ['--title', 'Parent', '--description', 'Parent task'], { cwd: testDir });
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			// Expand to create subtasks
-			const expandResult = await helpers.taskMaster('expand', ['--id', parentId, '--num', '3'], {
-				cwd: testDir,
-				timeout: 60000
-			});
-			expect(expandResult).toHaveExitCode(0);
-
-			// Make subtask 2 depend on subtask 1
-			const result = await helpers.taskMaster('add-dependency', [
-				'--id', `${parentId}.2`,
-				'--depends-on', `${parentId}.1`
-			], { cwd: testDir, allowFailure: true });
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully added dependency');
-		});
-
-		it('should allow parent to depend on its own subtask', async () => {
-			// Note: Current implementation allows parent-subtask dependencies
-			const parent = await helpers.taskMaster('add-task', ['--title', 'Parent', '--description', 'Parent task'], { cwd: testDir });
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			const expandResult = await helpers.taskMaster('expand', ['--id', parentId, '--num', '2'], {
-				cwd: testDir,
-				timeout: 60000
-			});
-			expect(expandResult).toHaveExitCode(0);
-
-			const result = await helpers.taskMaster(
-				'add-dependency',
-				['--id', parentId, '--depends-on', `${parentId}.1`],
-				{ cwd: testDir, allowFailure: true }
-			);
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully added dependency');
-		});
-	});
-
-	// Note: The add-dependency command only supports single task/dependency operations
-	// Bulk operations are not implemented in the current version
-
-	describe('Complex dependency graphs', () => {
-		it('should handle diamond dependency pattern', async () => {
-			// Create diamond: A depends on B and C, both B and C depend on D
-			const taskD = await helpers.taskMaster('add-task', ['--title', 'Task D - base', '--description', 'Base task'], { cwd: testDir });
-			const idD = helpers.extractTaskId(taskD.stdout);
-
-			const taskB = await helpers.taskMaster('add-task', ['--title', 'Task B', '--description', 'Middle task B'], { cwd: testDir });
-			const idB = helpers.extractTaskId(taskB.stdout);
-			await helpers.taskMaster('add-dependency', ['--id', idB, '--depends-on', idD], { cwd: testDir });
-
-			const taskC = await helpers.taskMaster('add-task', ['--title', 'Task C', '--description', 'Middle task C'], { cwd: testDir });
-			const idC = helpers.extractTaskId(taskC.stdout);
-			await helpers.taskMaster('add-dependency', ['--id', idC, '--depends-on', idD], { cwd: testDir });
-
-			const taskA = await helpers.taskMaster('add-task', ['--title', 'Task A - top', '--description', 'Top task'], { cwd: testDir });
-			const idA = helpers.extractTaskId(taskA.stdout);
-
-			// Add both dependencies to create diamond (one by one)
-			const result1 = await helpers.taskMaster('add-dependency', ['--id', idA, '--depends-on', idB], { cwd: testDir });
-			expect(result1).toHaveExitCode(0);
-			expect(result1.stdout).toContain('Successfully added dependency');
-
-			const result2 = await helpers.taskMaster('add-dependency', ['--id', idA, '--depends-on', idC], { cwd: testDir });
-			expect(result2).toHaveExitCode(0);
-			expect(result2.stdout).toContain('Successfully added dependency');
-
-			// Verify the structure
-			const showResult = await helpers.taskMaster('show', [idA], { cwd: testDir });
-			expect(showResult.stdout).toContain(idB);
-			expect(showResult.stdout).toContain(idC);
-		});
-
-		it('should show transitive dependencies', async () => {
-			// Create chain A -> B -> C -> D
-			const taskD = await helpers.taskMaster('add-task', ['--title', 'Task D', '--description', 'End task'], { cwd: testDir });
-			const idD = helpers.extractTaskId(taskD.stdout);
-
-			const taskC = await helpers.taskMaster('add-task', ['--title', 'Task C', '--description', 'Middle task'], { cwd: testDir });
-			const idC = helpers.extractTaskId(taskC.stdout);
-			await helpers.taskMaster('add-dependency', ['--id', idC, '--depends-on', idD], { cwd: testDir });
-
-			const taskB = await helpers.taskMaster('add-task', ['--title', 'Task B', '--description', 'Middle task'], { cwd: testDir });
-			const idB = helpers.extractTaskId(taskB.stdout);
-			await helpers.taskMaster('add-dependency', ['--id', idB, '--depends-on', idC], { cwd: testDir });
-
-			const taskA = await helpers.taskMaster('add-task', ['--title', 'Task A', '--description', 'Start task'], { cwd: testDir });
-			const idA = helpers.extractTaskId(taskA.stdout);
-			await helpers.taskMaster('add-dependency', ['--id', idA, '--depends-on', idB], { cwd: testDir });
-
-			// Show should indicate full dependency chain
-			const result = await helpers.taskMaster('show', [idA], { cwd: testDir });
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Dependencies:');
-			expect(result.stdout).toContain(idB);
-			// May also show transitive dependencies in some views
-		});
-	});
-
-	describe('Tag context', () => {
-		it('should add dependencies within a tag', async () => {
-			// Create tag
-			await helpers.taskMaster('add-tag', ['feature'], { cwd: testDir });
-			await helpers.taskMaster('use-tag', ['feature'], { cwd: testDir });
-
-			// Create tasks in feature tag
-			const dep = await helpers.taskMaster('add-task', ['--title', 'Feature dependency', '--description', 'Dep in feature'], { cwd: testDir });
-			const depId = helpers.extractTaskId(dep.stdout);
-
-			const task = await helpers.taskMaster('add-task', ['--title', 'Feature task', '--description', 'Task in feature'], { cwd: testDir });
-			const taskId = helpers.extractTaskId(task.stdout);
-
-			// Add dependency with tag context
-			const result = await helpers.taskMaster('add-dependency', [
-				'--id', taskId,
-				'--depends-on', depId,
-				'--tag',
-				'feature'
-			], { cwd: testDir });
-			expect(result).toHaveExitCode(0);
-			// Tag context is shown in the emoji header
-			expect(result.stdout).toContain('🏷️ tag: feature');
-		});
-
-		it('should prevent cross-tag dependencies by default', async () => {
-			// Create tasks in different tags
-			const masterTask = await helpers.taskMaster('add-task', ['--title', 'Master task', '--description', 'In master tag'], { cwd: testDir });
-			const masterId = helpers.extractTaskId(masterTask.stdout);
-
-			await helpers.taskMaster('add-tag', ['feature'], { cwd: testDir });
-			await helpers.taskMaster('use-tag', ['feature'], { cwd: testDir });
-			const featureTask = await helpers.taskMaster('add-task', [
-				'--title',
-				'Feature task',
-				'--description',
-				'In feature tag'
-			], { cwd: testDir });
-			const featureId = helpers.extractTaskId(featureTask.stdout);
-
-			// Try to add cross-tag dependency
-			const result = await helpers.taskMaster(
-				'add-dependency',
-				['--id', featureId, '--depends-on', masterId, '--tag', 'feature'],
-				{ cwd: testDir, allowFailure: true }
-			);
-			// Depending on implementation, this might warn or fail
-		});
-	});
-
-	describe('Error handling', () => {
-		it('should handle non-existent task IDs', async () => {
-			const task = await helpers.taskMaster('add-task', ['--title', 'Task', '--description', 'A task'], { cwd: testDir });
-			const taskId = helpers.extractTaskId(task.stdout);
-
-			const result = await helpers.taskMaster('add-dependency', ['--id', taskId, '--depends-on', '999'], {
-				cwd: testDir,
-				allowFailure: true
-			});
-			expect(result.exitCode).not.toBe(0);
-			// The command exits with code 1 but doesn't output to stderr
-		});
-
-		it('should handle invalid task ID format', async () => {
-			const result = await helpers.taskMaster('add-dependency', ['--id', 'invalid-id', '--depends-on', '1'], {
-				cwd: testDir,
-				allowFailure: true
-			});
-			expect(result.exitCode).not.toBe(0);
-			// The command exits with code 1 but doesn't output to stderr
-		});
-
-		it('should require both task and dependency IDs', async () => {
-			const result = await helpers.taskMaster('add-dependency', ['--id', '1'], {
-				cwd: testDir,
-				allowFailure: true
-			});
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('required');
-		});
-	});
-
-	describe('Output options', () => {
-		it.skip('should support quiet mode (not implemented)', async () => {
-			// The -q flag is not supported by add-dependency command
-			const dep = await helpers.taskMaster('add-task', ['--title', 'Dep', '--description', 'A dep'], { cwd: testDir });
-			const depId = helpers.extractTaskId(dep.stdout);
-
-			const task = await helpers.taskMaster('add-task', ['--title', 'Task', '--description', 'A task'], { cwd: testDir });
-			const taskId = helpers.extractTaskId(task.stdout);
-
-			const result = await helpers.taskMaster('add-dependency', [
-				'--id', taskId,
-				'--depends-on', depId
-			], { cwd: testDir });
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully added dependency');
-		});
-
-		it.skip('should support JSON output (not implemented)', async () => {
-			// The --json flag is not supported by add-dependency command
-			const dep = await helpers.taskMaster('add-task', ['--title', 'Dep', '--description', 'A dep'], { cwd: testDir });
-			const depId = helpers.extractTaskId(dep.stdout);
-
-			const task = await helpers.taskMaster('add-task', ['--title', 'Task', '--description', 'A task'], { cwd: testDir });
-			const taskId = helpers.extractTaskId(task.stdout);
-
-			const result = await helpers.taskMaster('add-dependency', [
-				'--id', taskId,
-				'--depends-on', depId,
-				'--json'
-			], { cwd: testDir });
-			expect(result).toHaveExitCode(0);
-
-			const json = JSON.parse(result.stdout);
-			expect(json.task.id).toBe(parseInt(taskId));
-			expect(json.task.dependencies).toContain(parseInt(depId));
-			expect(json.added).toBe(1);
-		});
-	});
-
-	describe('Visualization', () => {
-		it('should show dependency graph after adding', async () => {
-			// Create simple dependency chain
-			const task1 = await helpers.taskMaster('add-task', ['--title', 'Base task', '--description', 'Base'], { cwd: testDir });
-			const id1 = helpers.extractTaskId(task1.stdout);
-
-			const task2 = await helpers.taskMaster('add-task', ['--title', 'Middle task', '--description', 'Middle'], { cwd: testDir });
-			const id2 = helpers.extractTaskId(task2.stdout);
-
-			const task3 = await helpers.taskMaster('add-task', ['--title', 'Top task', '--description', 'Top'], { cwd: testDir });
-			const id3 = helpers.extractTaskId(task3.stdout);
-
-			// Build chain
-			await helpers.taskMaster('add-dependency', ['--id', id2, '--depends-on', id1], { cwd: testDir });
-			const result = await helpers.taskMaster('add-dependency', ['--id', id3, '--depends-on', id2], { cwd: testDir });
-
-			expect(result).toHaveExitCode(0);
-			// Check for dependency added message
-			expect(result.stdout).toContain('Successfully added dependency');
-		});
-	});
-});

tests/e2e/tests/commands/add-subtask.test.js

@@ -1,405 +0,0 @@
-/**
- * E2E tests for add-subtask command
- * Tests subtask creation and conversion functionality
- */
-
-import { describe, it, expect, beforeEach, afterEach } from '@jest/globals';
-import {
-	mkdtempSync,
-	existsSync,
-	readFileSync,
-	rmSync,
-	writeFileSync,
-	mkdirSync
-} from 'fs';
-import { join } from 'path';
-import { tmpdir } from 'os';
-
-describe('task-master add-subtask', () => {
-	let testDir;
-	let helpers;
-
-	beforeEach(async () => {
-		// Create test directory
-		testDir = mkdtempSync(join(tmpdir(), 'task-master-add-subtask-'));
-
-		// Initialize test helpers
-		const context = global.createTestContext('add-subtask');
-		helpers = context.helpers;
-
-		// Copy .env file if it exists
-		const mainEnvPath = join(process.cwd(), '.env');
-		const testEnvPath = join(testDir, '.env');
-		if (existsSync(mainEnvPath)) {
-			const envContent = readFileSync(mainEnvPath, 'utf8');
-			writeFileSync(testEnvPath, envContent);
-		}
-
-		// Initialize task-master project
-		const initResult = await helpers.taskMaster('init', ['-y'], {
-			cwd: testDir
-		});
-		expect(initResult).toHaveExitCode(0);
-
-		// Ensure tasks.json exists (bug workaround)
-		const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-		if (!existsSync(tasksJsonPath)) {
-			mkdirSync(join(testDir, '.taskmaster/tasks'), { recursive: true });
-			writeFileSync(tasksJsonPath, JSON.stringify({ master: { tasks: [] } }));
-		}
-	});
-
-	afterEach(() => {
-		// Clean up test directory
-		if (testDir && existsSync(testDir)) {
-			rmSync(testDir, { recursive: true, force: true });
-		}
-	});
-
-	describe('Basic subtask creation', () => {
-		it('should add a new subtask to a parent task', async () => {
-			// Create parent task
-			const parent = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Parent task', '--description', 'A parent task'],
-				{ cwd: testDir }
-			);
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			// Add subtask
-			const result = await helpers.taskMaster(
-				'add-subtask',
-				[
-					'--parent',
-					parentId,
-					'--title',
-					'New subtask',
-					'--description',
-					'This is a new subtask',
-					'--skip-generate'
-				],
-				{ cwd: testDir }
-			);
-
-			// Verify success
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Creating new subtask');
-			expect(result.stdout).toContain('successfully created');
-			expect(result.stdout).toContain(`${parentId}.1`); // subtask ID
-
-			// Verify subtask was added
-			const showResult = await helpers.taskMaster('show', [parentId], {
-				cwd: testDir
-			});
-			expect(showResult.stdout).toContain('New'); // Truncated in table
-			expect(showResult.stdout).toContain('Subtasks'); // Section header
-		});
-
-		it('should add a subtask with custom status and details', async () => {
-			// Create parent task
-			const parent = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Parent task', '--description', 'A parent task'],
-				{ cwd: testDir }
-			);
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			// Add subtask with custom options
-			const result = await helpers.taskMaster(
-				'add-subtask',
-				[
-					'--parent',
-					parentId,
-					'--title',
-					'Advanced subtask',
-					'--description',
-					'Subtask with details',
-					'--details',
-					'Implementation details here',
-					'--status',
-					'in-progress',
-					'--skip-generate'
-				],
-				{ cwd: testDir }
-			);
-
-			// Verify success
-			expect(result).toHaveExitCode(0);
-
-			// Verify subtask properties
-			const showResult = await helpers.taskMaster('show', [`${parentId}.1`], {
-				cwd: testDir
-			});
-			expect(showResult.stdout).toContain('Advanced'); // Truncated in table
-			expect(showResult.stdout).toContain('Subtask'); // Part of description
-			expect(showResult.stdout).toContain('Implementation'); // Part of details
-			expect(showResult.stdout).toContain('in-progress');
-		});
-
-		it('should add a subtask with dependencies', async () => {
-			// Create dependency task
-			const dep = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Dependency task', '--description', 'A dependency'],
-				{ cwd: testDir }
-			);
-			const depId = helpers.extractTaskId(dep.stdout);
-
-			// Create parent task and subtask
-			const parent = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Parent task', '--description', 'A parent task'],
-				{ cwd: testDir }
-			);
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			// Add first subtask
-			await helpers.taskMaster(
-				'add-subtask',
-				['--parent', parentId, '--title', 'First subtask', '--skip-generate'],
-				{ cwd: testDir }
-			);
-
-			// Add second subtask with dependencies
-			const result = await helpers.taskMaster(
-				'add-subtask',
-				[
-					'--parent',
-					parentId,
-					'--title',
-					'Subtask with deps',
-					'--dependencies',
-					`${parentId}.1,${depId}`,
-					'--skip-generate'
-				],
-				{ cwd: testDir }
-			);
-
-			// Verify success
-			expect(result).toHaveExitCode(0);
-
-			// Verify subtask was created (dependencies may not show in standard show output)
-			const showResult = await helpers.taskMaster('show', [`${parentId}.2`], {
-				cwd: testDir
-			});
-			expect(showResult.stdout).toContain('Subtask'); // Part of title
-		});
-	});
-
-	describe('Task conversion', () => {
-		it('should convert an existing task to a subtask', async () => {
-			// Create tasks
-			const parent = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Parent task', '--description', 'A parent task'],
-				{ cwd: testDir }
-			);
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			const taskToConvert = await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'Task to be converted',
-					'--description',
-					'This will become a subtask'
-				],
-				{ cwd: testDir }
-			);
-			const convertId = helpers.extractTaskId(taskToConvert.stdout);
-
-			// Convert task to subtask
-			const result = await helpers.taskMaster(
-				'add-subtask',
-				['--parent', parentId, '--task-id', convertId, '--skip-generate'],
-				{ cwd: testDir }
-			);
-
-			// Verify success
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain(`Converting task ${convertId}`);
-			expect(result.stdout).toContain('successfully converted');
-
-			// Verify task was converted
-			const showParent = await helpers.taskMaster('show', [parentId], {
-				cwd: testDir
-			});
-			expect(showParent.stdout).toContain('Task'); // Truncated title in table
-
-			// Verify original task no longer exists as top-level
-			const listResult = await helpers.taskMaster('list', [], { cwd: testDir });
-			expect(listResult.stdout).not.toContain(`${convertId}:`);
-		});
-	});
-
-	describe('Error handling', () => {
-		it('should fail when parent ID is not provided', async () => {
-			const result = await helpers.taskMaster(
-				'add-subtask',
-				['--title', 'Orphan subtask'],
-				{
-					cwd: testDir,
-					allowFailure: true
-				}
-			);
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('--parent parameter is required');
-		});
-
-		it('should fail when neither task-id nor title is provided', async () => {
-			// Create parent task first
-			const parent = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Parent task', '--description', 'A parent task'],
-				{ cwd: testDir }
-			);
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			const result = await helpers.taskMaster(
-				'add-subtask',
-				['--parent', parentId],
-				{
-					cwd: testDir,
-					allowFailure: true
-				}
-			);
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain(
-				'Either --task-id or --title must be provided'
-			);
-		});
-
-		it('should handle non-existent parent task', async () => {
-			const result = await helpers.taskMaster(
-				'add-subtask',
-				['--parent', '999', '--title', 'Lost subtask'],
-				{
-					cwd: testDir,
-					allowFailure: true
-				}
-			);
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('Error');
-		});
-
-		it('should handle non-existent task ID for conversion', async () => {
-			// Create parent task first
-			const parent = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Parent task', '--description', 'A parent task'],
-				{ cwd: testDir }
-			);
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			const result = await helpers.taskMaster(
-				'add-subtask',
-				['--parent', parentId, '--task-id', '999'],
-				{
-					cwd: testDir,
-					allowFailure: true
-				}
-			);
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('Error');
-		});
-	});
-
-	describe('Tag context', () => {
-		it('should work with tag option', async () => {
-			// Create tag and switch to it
-			await helpers.taskMaster('add-tag', ['feature'], { cwd: testDir });
-			await helpers.taskMaster('use-tag', ['feature'], { cwd: testDir });
-
-			// Create parent task in feature tag
-			const parent = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Feature task', '--description', 'A feature task'],
-				{ cwd: testDir }
-			);
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			// Add subtask to feature tag
-			const result = await helpers.taskMaster(
-				'add-subtask',
-				[
-					'--parent',
-					parentId,
-					'--title',
-					'Feature subtask',
-					'--tag',
-					'feature',
-					'--skip-generate'
-				],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-
-			// Verify subtask is in feature tag
-			const showResult = await helpers.taskMaster(
-				'show',
-				[parentId, '--tag', 'feature'],
-				{ cwd: testDir }
-			);
-			expect(showResult.stdout).toContain('Feature'); // Truncated title
-
-			// Verify master tag is unaffected
-			await helpers.taskMaster('use-tag', ['master'], { cwd: testDir });
-			const masterList = await helpers.taskMaster('list', [], { cwd: testDir });
-			expect(masterList.stdout).not.toContain('Feature subtask');
-		});
-	});
-
-	describe('Output format', () => {
-		it('should create subtask successfully with standard output', async () => {
-			// Create parent task
-			const parent = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Parent task', '--description', 'A parent task'],
-				{ cwd: testDir }
-			);
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			const result = await helpers.taskMaster(
-				'add-subtask',
-				[
-					'--parent',
-					parentId,
-					'--title',
-					'Standard subtask',
-					'--skip-generate'
-				],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Creating new subtask');
-			expect(result.stdout).toContain('successfully created');
-		});
-
-		it('should display success box with next steps', async () => {
-			// Create parent task
-			const parent = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Parent task', '--description', 'A parent task'],
-				{ cwd: testDir }
-			);
-			const parentId = helpers.extractTaskId(parent.stdout);
-
-			const result = await helpers.taskMaster(
-				'add-subtask',
-				['--parent', parentId, '--title', 'Success subtask', '--skip-generate'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Next Steps:');
-			expect(result.stdout).toContain('task-master show');
-			expect(result.stdout).toContain('task-master set-status');
-		});
-	});
-});

tests/e2e/tests/commands/add-tag.test.js

@@ -1,433 +0,0 @@
-/**
- * E2E tests for add-tag command
- * Tests tag creation functionality
- */
-
-import { describe, it, expect, beforeEach, afterEach } from '@jest/globals';
-import {
-	mkdtempSync,
-	existsSync,
-	readFileSync,
-	rmSync,
-	writeFileSync,
-	mkdirSync
-} from 'fs';
-import { join } from 'path';
-import { tmpdir } from 'os';
-
-describe('task-master add-tag', () => {
-	let testDir;
-	let helpers;
-
-	beforeEach(async () => {
-		// Create test directory
-		testDir = mkdtempSync(join(tmpdir(), 'task-master-add-tag-'));
-
-		// Initialize test helpers
-		const context = global.createTestContext('add-tag');
-		helpers = context.helpers;
-
-		// Copy .env file if it exists
-		const mainEnvPath = join(process.cwd(), '.env');
-		const testEnvPath = join(testDir, '.env');
-		if (existsSync(mainEnvPath)) {
-			const envContent = readFileSync(mainEnvPath, 'utf8');
-			writeFileSync(testEnvPath, envContent);
-		}
-
-		// Initialize task-master project
-		const initResult = await helpers.taskMaster('init', ['-y'], {
-			cwd: testDir
-		});
-		expect(initResult).toHaveExitCode(0);
-
-		// Ensure tasks.json exists (bug workaround)
-		const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-		if (!existsSync(tasksJsonPath)) {
-			mkdirSync(join(testDir, '.taskmaster/tasks'), { recursive: true });
-			writeFileSync(tasksJsonPath, JSON.stringify({ master: { tasks: [] } }));
-		}
-	});
-
-	afterEach(() => {
-		// Clean up test directory
-		if (testDir && existsSync(testDir)) {
-			rmSync(testDir, { recursive: true, force: true });
-		}
-	});
-
-	describe('Basic tag creation', () => {
-		it('should create a new tag successfully', async () => {
-			const result = await helpers.taskMaster('add-tag', ['feature-x'], {
-				cwd: testDir
-			});
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully created tag "feature-x"');
-
-			// Verify tag was created in tasks.json
-			const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-			const tasksContent = JSON.parse(readFileSync(tasksJsonPath, 'utf8'));
-			expect(tasksContent).toHaveProperty('feature-x');
-			expect(tasksContent['feature-x']).toHaveProperty('tasks');
-			expect(Array.isArray(tasksContent['feature-x'].tasks)).toBe(true);
-		});
-
-		it('should create tag with description', async () => {
-			const result = await helpers.taskMaster(
-				'add-tag',
-				['release-v1', '--description', '"First major release"'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully created tag "release-v1"');
-
-			// Verify tag has description
-			const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-			const tasksContent = JSON.parse(readFileSync(tasksJsonPath, 'utf8'));
-			expect(tasksContent['release-v1']).toHaveProperty('metadata');
-			expect(tasksContent['release-v1'].metadata).toHaveProperty(
-				'description',
-				'First major release'
-			);
-		});
-
-		it('should handle tag name with hyphens and underscores', async () => {
-			const result = await helpers.taskMaster(
-				'add-tag',
-				['feature_auth-system'],
-				{
-					cwd: testDir
-				}
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain(
-				'Successfully created tag "feature_auth-system"'
-			);
-		});
-	});
-
-	describe('Duplicate tag handling', () => {
-		it('should fail when creating a tag that already exists', async () => {
-			// Create initial tag
-			const firstResult = await helpers.taskMaster('add-tag', ['duplicate'], {
-				cwd: testDir
-			});
-			expect(firstResult).toHaveExitCode(0);
-
-			// Try to create same tag again
-			const secondResult = await helpers.taskMaster('add-tag', ['duplicate'], {
-				cwd: testDir,
-				allowFailure: true
-			});
-
-			expect(secondResult.exitCode).not.toBe(0);
-			expect(secondResult.stderr).toContain('already exists');
-		});
-
-		it('should not allow creating master tag', async () => {
-			const result = await helpers.taskMaster('add-tag', ['master'], {
-				cwd: testDir,
-				allowFailure: true
-			});
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('reserved tag name');
-		});
-	});
-
-	describe('Special characters handling', () => {
-		it('should handle tag names with numbers', async () => {
-			const result = await helpers.taskMaster('add-tag', ['sprint-123'], {
-				cwd: testDir
-			});
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully created tag "sprint-123"');
-		});
-
-		it('should reject tag names with spaces', async () => {
-			// When passed through shell, 'my tag' becomes two arguments: 'my' and 'tag'
-			// The command receives 'my' as the tag name (which is valid) and 'tag' is ignored
-			// This test actually creates a tag named 'my' successfully
-			// To properly test space rejection, we would need to quote the argument
-			const result = await helpers.taskMaster('add-tag', ['"my tag"'], {
-				cwd: testDir,
-				allowFailure: true
-			});
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('can only contain letters, numbers, hyphens, and underscores');
-		});
-
-		it('should reject tag names with special characters', async () => {
-			// Test each special character individually to avoid shell interpretation issues
-			const testCases = [
-				{ name: 'tag@name', quoted: '"tag@name"' },
-				{ name: 'tag#name', quoted: '"tag#name"' },
-				{ name: 'tag\\$name', quoted: '"tag\\$name"' }, // Escape $ to prevent shell variable expansion
-				{ name: 'tag%name', quoted: '"tag%name"' }
-			];
-
-			for (const { name, quoted } of testCases) {
-				const result = await helpers.taskMaster('add-tag', [quoted], {
-					cwd: testDir,
-					allowFailure: true
-				});
-
-				expect(result.exitCode).not.toBe(0);
-				expect(result.stderr).toMatch(/can only contain letters, numbers, hyphens, and underscores/i);
-			}
-		});
-
-		it('should handle very long tag names', async () => {
-			const longName = 'a'.repeat(100);
-			const result = await helpers.taskMaster('add-tag', [longName], {
-				cwd: testDir,
-				allowFailure: true
-			});
-
-			// Should either succeed or fail with appropriate error
-			if (result.exitCode !== 0) {
-				expect(result.stderr).toMatch(/too long|Invalid/i);
-			} else {
-				expect(result.stdout).toContain('Successfully created tag');
-			}
-		});
-	});
-
-	describe('Multiple tag creation', () => {
-		it('should create multiple tags sequentially', async () => {
-			const tags = ['dev', 'staging', 'production'];
-
-			for (const tag of tags) {
-				const result = await helpers.taskMaster('add-tag', [tag], {
-					cwd: testDir
-				});
-				expect(result).toHaveExitCode(0);
-				expect(result.stdout).toContain(`Successfully created tag "${tag}"`);
-			}
-
-			// Verify all tags exist
-			const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-			const tasksContent = JSON.parse(readFileSync(tasksJsonPath, 'utf8'));
-
-			for (const tag of tags) {
-				expect(tasksContent).toHaveProperty(tag);
-			}
-		});
-
-		it('should handle concurrent tag creation', async () => {
-			const tags = ['concurrent-1', 'concurrent-2', 'concurrent-3'];
-			const promises = tags.map((tag) =>
-				helpers.taskMaster('add-tag', [tag], { cwd: testDir })
-			);
-
-			const results = await Promise.all(promises);
-
-			// All should succeed
-			results.forEach((result, index) => {
-				expect(result).toHaveExitCode(0);
-				expect(result.stdout).toContain(
-					`Successfully created tag "${tags[index]}"`
-				);
-			});
-		});
-	});
-
-	describe('Tag creation with copy options', () => {
-		it('should create tag with copy-from-current option', async () => {
-			// Create new tag with copy option (even if no tasks to copy)
-			const result = await helpers.taskMaster(
-				'add-tag',
-				['feature-copy', '--copy-from-current'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain(
-				'Successfully created tag "feature-copy"'
-			);
-
-			// Verify tag was created
-			const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-			const tasksContent = JSON.parse(readFileSync(tasksJsonPath, 'utf8'));
-			expect(tasksContent).toHaveProperty('feature-copy');
-		});
-	});
-
-	describe('Git branch integration', () => {
-		it.skip('should create tag from current git branch', async () => {
-			// Initialize git repo
-			await helpers.executeCommand('git', ['init'], { cwd: testDir });
-			await helpers.executeCommand(
-				'git',
-				['config', 'user.email', 'test@example.com'],
-				{ cwd: testDir }
-			);
-			await helpers.executeCommand(
-				'git',
-				['config', 'user.name', 'Test User'],
-				{ cwd: testDir }
-			);
-
-			// Create and checkout a feature branch
-			await helpers.executeCommand('git', ['checkout', '-b', 'feature/auth'], {
-				cwd: testDir
-			});
-
-			// Create tag from branch
-			const result = await helpers.taskMaster('add-tag', ['--from-branch'], {
-				cwd: testDir
-			});
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully created tag');
-			expect(result.stdout).toContain('feature/auth');
-
-			// Verify tag was created with branch-based name
-			const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-			const tasksContent = JSON.parse(readFileSync(tasksJsonPath, 'utf8'));
-			const tagNames = Object.keys(tasksContent);
-			const branchTag = tagNames.find((tag) => tag.includes('auth'));
-			expect(branchTag).toBeTruthy();
-		});
-
-		it.skip('should fail when not in a git repository', async () => {
-			const result = await helpers.taskMaster('add-tag', ['--from-branch'], {
-				cwd: testDir,
-				allowFailure: true
-			});
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('Not in a git repository');
-		});
-	});
-
-	describe('Error handling', () => {
-		it('should fail without tag name argument', async () => {
-			const result = await helpers.taskMaster('add-tag', [], {
-				cwd: testDir,
-				allowFailure: true
-			});
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('Either tagName argument or --from-branch option is required');
-		});
-
-		it('should handle empty tag name', async () => {
-			const result = await helpers.taskMaster('add-tag', [''], {
-				cwd: testDir,
-				allowFailure: true
-			});
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('Either tagName argument or --from-branch option is required');
-		});
-
-		it.skip('should handle file system errors gracefully', async () => {
-			// Make tasks.json read-only
-			const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-			await helpers.executeCommand('chmod', ['444', tasksJsonPath], {
-				cwd: testDir
-			});
-
-			const result = await helpers.taskMaster('add-tag', ['readonly-test'], {
-				cwd: testDir,
-				allowFailure: true
-			});
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toBeTruthy();
-
-			// Restore permissions for cleanup
-			await helpers.executeCommand('chmod', ['644', tasksJsonPath], {
-				cwd: testDir
-			});
-		});
-	});
-
-	describe('Tag aliases', () => {
-		it('should work with add-tag alias', async () => {
-			const result = await helpers.taskMaster('add-tag', ['alias-test'], {
-				cwd: testDir
-			});
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully created tag "alias-test"');
-		});
-	});
-
-	describe('Integration with other commands', () => {
-		it('should allow switching to newly created tag', async () => {
-			// Create tag
-			const createResult = await helpers.taskMaster('add-tag', ['switchable'], {
-				cwd: testDir
-			});
-			expect(createResult).toHaveExitCode(0);
-
-			// Switch to new tag
-			const switchResult = await helpers.taskMaster('use-tag', ['switchable'], {
-				cwd: testDir
-			});
-			expect(switchResult).toHaveExitCode(0);
-			expect(switchResult.stdout).toContain('Successfully switched to tag "switchable"');
-		});
-
-		it('should allow adding tasks to newly created tag', async () => {
-			// Create tag
-			await helpers.taskMaster('add-tag', ['task-container'], {
-				cwd: testDir
-			});
-
-			// Add task to specific tag
-			const result = await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'Task in new tag',
-					'--description',
-					'Testing',
-					'--tag',
-					'task-container'
-				],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-
-			// Verify task is in the correct tag
-			const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-			const tasksContent = JSON.parse(readFileSync(tasksJsonPath, 'utf8'));
-			expect(tasksContent['task-container'].tasks).toHaveLength(1);
-		});
-	});
-
-	describe('Tag metadata', () => {
-		it('should store tag creation timestamp', async () => {
-			const beforeTime = Date.now();
-
-			const result = await helpers.taskMaster('add-tag', ['timestamped'], {
-				cwd: testDir
-			});
-
-			const afterTime = Date.now();
-			expect(result).toHaveExitCode(0);
-
-			// Check if tag has creation metadata
-			const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-			const tasksContent = JSON.parse(readFileSync(tasksJsonPath, 'utf8'));
-
-			// If implementation includes timestamps, verify them
-			if (tasksContent.timestamped?.createdAt) {
-				const createdAt = new Date(
-					tasksContent.timestamped.createdAt
-				).getTime();
-				expect(createdAt).toBeGreaterThanOrEqual(beforeTime);
-				expect(createdAt).toBeLessThanOrEqual(afterTime);
-			}
-		});
-	});
-});

tests/e2e/tests/commands/add-task.test.js

@@ -1,600 +0,0 @@
-/**
- * Comprehensive E2E tests for add-task command
- * Tests all aspects of task creation including AI and manual modes
- */
-
-import {
-	mkdtempSync,
-	existsSync,
-	readFileSync,
-	rmSync,
-	writeFileSync,
-	mkdirSync
-} from 'fs';
-import { join } from 'path';
-import { tmpdir } from 'os';
-import { copyConfigFiles } from '../../utils/test-setup.js';
-
-describe('add-task command', () => {
-	let testDir;
-	let helpers;
-
-	beforeEach(async () => {
-		// Create test directory
-		testDir = mkdtempSync(join(tmpdir(), 'task-master-add-task-'));
-
-		// Initialize test helpers
-		const context = global.createTestContext('add-task');
-		helpers = context.helpers;
-
-		copyConfigFiles(testDir);
-
-		// Initialize task-master project
-		const initResult = await helpers.taskMaster('init', ['-y'], {
-			cwd: testDir
-		});
-		expect(initResult).toHaveExitCode(0);
-
-		// Ensure tasks.json exists (bug workaround)
-		const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-		if (!existsSync(tasksJsonPath)) {
-			mkdirSync(join(testDir, '.taskmaster/tasks'), { recursive: true });
-			writeFileSync(tasksJsonPath, JSON.stringify({ master: { tasks: [] } }));
-		}
-	});
-
-	afterEach(() => {
-		// Clean up test directory
-		if (testDir && existsSync(testDir)) {
-			rmSync(testDir, { recursive: true, force: true });
-		}
-	});
-
-	describe('AI-powered task creation', () => {
-		it('should create task with AI prompt', async () => {
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Create a user authentication system with JWT tokens'],
-				{ cwd: testDir, timeout: 30000 }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContainTaskId();
-
-			const taskId = helpers.extractTaskId(result.stdout);
-			const showResult = await helpers.taskMaster('show', [taskId], {
-				cwd: testDir
-			});
-
-			// AI generated task should contain a title and description
-			expect(showResult.stdout).toContain('Title:');
-			expect(showResult.stdout).toContain('Description:');
-			expect(showResult.stdout).toContain('Implementation Details:');
-		}, 45000); // 45 second timeout for this test
-
-		it('should handle very long prompts', async () => {
-			const longPrompt =
-				'Create a comprehensive system that ' +
-				'handles many features '.repeat(50);
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--prompt', longPrompt],
-				{ cwd: testDir, timeout: 30000 }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContainTaskId();
-		}, 45000);
-
-		it('should handle special characters in prompt', async () => {
-			const specialPrompt =
-				'Implement feature: User data and settings with special chars';
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--prompt', specialPrompt],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContainTaskId();
-		});
-
-		it('should verify AI generates reasonable output', async () => {
-			const result = await helpers.taskMaster(
-				'add-task',
-				[
-					'--prompt',
-					'Build a responsive navigation menu with dropdown support'
-				],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-
-			const taskId = helpers.extractTaskId(result.stdout);
-			const showResult = await helpers.taskMaster('show', [taskId], {
-				cwd: testDir
-			});
-			// Verify AI generated task has proper structure
-			expect(showResult.stdout).toContain('Title:');
-			expect(showResult.stdout).toContain('Status:');
-			expect(showResult.stdout).toContain('Priority:');
-			expect(showResult.stdout).toContain('Description:');
-		});
-	});
-
-	describe('Manual task creation', () => {
-		it('should create task with title and description', async () => {
-			const result = await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'Setup database connection',
-					'--description',
-					'Configure PostgreSQL connection with connection pooling'
-				],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContainTaskId();
-
-			const taskId = helpers.extractTaskId(result.stdout);
-			const showResult = await helpers.taskMaster('show', [taskId], {
-				cwd: testDir
-			});
-
-			// Check that at least part of our title and description are shown
-			expect(showResult.stdout).toContain('Setup');
-			expect(showResult.stdout).toContain('Configure');
-		});
-
-		it('should create task with manual details', async () => {
-			const result = await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'Implement caching layer',
-					'--description',
-					'Add Redis caching to improve performance',
-					'--details',
-					'Use Redis for session storage and API response caching'
-				],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContainTaskId();
-		});
-	});
-
-	describe('Task creation with options', () => {
-		it('should create task with priority', async () => {
-			const result = await helpers.taskMaster(
-				'add-task',
-				[
-					'--prompt',
-					'Fix critical security vulnerability',
-					'--priority',
-					'high'
-				],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			const taskId = helpers.extractTaskId(result.stdout);
-
-			const showResult = await helpers.taskMaster('show', [taskId], {
-				cwd: testDir
-			});
-			expect(showResult.stdout.toLowerCase()).toContain('high');
-		});
-
-		it('should create task with dependencies', async () => {
-			// Create dependency task first
-			const depResult = await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'Setup environment',
-					'--description',
-					'Initial environment setup'
-				],
-				{ cwd: testDir }
-			);
-			const depTaskId = helpers.extractTaskId(depResult.stdout);
-
-			// Create task with dependency
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Deploy application', '--dependencies', depTaskId],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			const taskId = helpers.extractTaskId(result.stdout);
-
-			const showResult = await helpers.taskMaster('show', [taskId], {
-				cwd: testDir
-			});
-			expect(showResult.stdout).toContain(depTaskId);
-		});
-
-		it('should handle multiple dependencies', async () => {
-			// Create multiple dependency tasks
-			const dep1 = await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Setup environment'],
-				{ cwd: testDir }
-			);
-			const depId1 = helpers.extractTaskId(dep1.stdout);
-
-			const dep2 = await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Configure database'],
-				{ cwd: testDir }
-			);
-			const depId2 = helpers.extractTaskId(dep2.stdout);
-
-			// Create task with multiple dependencies
-			const result = await helpers.taskMaster(
-				'add-task',
-				[
-					'--prompt',
-					'Deploy application',
-					'--dependencies',
-					`${depId1},${depId2}`
-				],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			const taskId = helpers.extractTaskId(result.stdout);
-
-			const showResult = await helpers.taskMaster('show', [taskId], {
-				cwd: testDir
-			});
-			expect(showResult.stdout).toContain(depId1);
-			expect(showResult.stdout).toContain(depId2);
-		});
-
-		it('should create task with all options combined', async () => {
-			// Setup
-			const depResult = await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'Prerequisite task',
-					'--description',
-					'Task that must be completed first'
-				],
-				{ cwd: testDir }
-			);
-			const depTaskId = helpers.extractTaskId(depResult.stdout);
-
-			await helpers.taskMaster(
-				'add-tag',
-				['feature-complete', '--description', 'Complete feature test'],
-				{ cwd: testDir }
-			);
-
-			// Create task with all options
-			const result = await helpers.taskMaster(
-				'add-task',
-				[
-					'--prompt',
-					'Comprehensive task with all features',
-					'--priority',
-					'medium',
-					'--dependencies',
-					depTaskId
-				],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			const taskId = helpers.extractTaskId(result.stdout);
-
-			// Verify all options
-			const showResult = await helpers.taskMaster('show', [taskId], {
-				cwd: testDir
-			});
-			expect(showResult.stdout.toLowerCase()).toContain('medium');
-			expect(showResult.stdout).toContain(depTaskId);
-		});
-	});
-
-	describe('Error handling', () => {
-		it('should fail without prompt or title+description', async () => {
-			const result = await helpers.taskMaster('add-task', [], {
-				cwd: testDir,
-				allowFailure: true
-			});
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain(
-				'Either --prompt or both --title and --description must be provided'
-			);
-		});
-
-		it('should fail with only title (missing description)', async () => {
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Incomplete task'],
-				{ cwd: testDir, allowFailure: true }
-			);
-
-			expect(result.exitCode).not.toBe(0);
-		});
-
-		it('should handle invalid priority by defaulting to medium', async () => {
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Test task', '--priority', 'invalid'],
-				{ cwd: testDir }
-			);
-
-			// Should succeed but use default priority and show warning
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Invalid priority "invalid"');
-			expect(result.stdout).toContain('Using default priority "medium"');
-
-			const taskId = helpers.extractTaskId(result.stdout);
-
-			const showResult = await helpers.taskMaster('show', [taskId], {
-				cwd: testDir
-			});
-			expect(showResult.stdout).toContain('Priority:');
-			expect(showResult.stdout).toContain('medium');
-		});
-
-		it('should warn and continue with non-existent dependency', async () => {
-			// Based on the implementation, invalid dependencies are filtered out with a warning
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Test task', '--dependencies', '99999'],
-				{ cwd: testDir }
-			);
-
-			// Should succeed but with warning
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('do not exist');
-		});
-	});
-
-	describe('Concurrent operations', () => {
-		it('should handle multiple tasks created in parallel', async () => {
-			const promises = [];
-			for (let i = 0; i < 3; i++) {
-				promises.push(
-					helpers.taskMaster(
-						'add-task',
-						['--prompt', `Parallel task ${i + 1}`],
-						{ cwd: testDir }
-					)
-				);
-			}
-
-			const results = await Promise.all(promises);
-
-			results.forEach((result) => {
-				expect(result).toHaveExitCode(0);
-				expect(result.stdout).toContainTaskId();
-			});
-		});
-	});
-
-	describe('Research mode', () => {
-		it('should create task using research mode', async () => {
-			const result = await helpers.taskMaster(
-				'add-task',
-				[
-					'--prompt',
-					'Research best practices for implementing OAuth2 authentication',
-					'--research'
-				],
-				{ cwd: testDir, timeout: 45000 }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContainTaskId();
-
-			// Verify task was created
-			const taskId = helpers.extractTaskId(result.stdout);
-			const showResult = await helpers.taskMaster('show', [taskId], {
-				cwd: testDir
-			});
-			// Verify task was created with research mode (should have more detailed output)
-			expect(showResult.stdout).toContain('Title:');
-			expect(showResult.stdout).toContain('Implementation Details:');
-		}, 60000);
-	});
-
-	describe('File path handling', () => {
-		it('should use custom tasks file path', async () => {
-			// Create custom tasks file
-			const customPath = join(testDir, 'custom-tasks.json');
-			writeFileSync(customPath, JSON.stringify({ master: { tasks: [] } }));
-
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--file', customPath, '--prompt', 'Task in custom file'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-
-			// Verify task was added to custom file
-			const customContent = JSON.parse(readFileSync(customPath, 'utf8'));
-			expect(customContent.master.tasks.length).toBe(1);
-		});
-	});
-
-	describe('Priority validation', () => {
-		it('should accept all valid priority values', async () => {
-			const priorities = ['high', 'medium', 'low'];
-
-			for (const priority of priorities) {
-				const result = await helpers.taskMaster(
-					'add-task',
-					[
-						'--prompt',
-						`Task with ${priority} priority`,
-						'--priority',
-						priority
-					],
-					{ cwd: testDir }
-				);
-
-				expect(result).toHaveExitCode(0);
-				const taskId = helpers.extractTaskId(result.stdout);
-
-				const showResult = await helpers.taskMaster('show', [taskId], {
-					cwd: testDir
-				});
-				expect(showResult.stdout.toLowerCase()).toContain(priority);
-			}
-		});
-
-		it('should accept priority values case-insensitively', async () => {
-			const priorities = ['HIGH', 'Medium', 'LoW'];
-			const expected = ['high', 'medium', 'low'];
-
-			for (let i = 0; i < priorities.length; i++) {
-				const result = await helpers.taskMaster(
-					'add-task',
-					[
-						'--prompt',
-						`Task with ${priorities[i]} priority`,
-						'--priority',
-						priorities[i]
-					],
-					{ cwd: testDir }
-				);
-
-				expect(result).toHaveExitCode(0);
-				const taskId = helpers.extractTaskId(result.stdout);
-
-				const showResult = await helpers.taskMaster('show', [taskId], {
-					cwd: testDir
-				});
-				expect(showResult.stdout).toContain('Priority:');
-				expect(showResult.stdout).toContain(expected[i]);
-			}
-		});
-
-		it('should default to medium priority when not specified', async () => {
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Task without explicit priority'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			const taskId = helpers.extractTaskId(result.stdout);
-
-			const showResult = await helpers.taskMaster('show', [taskId], {
-				cwd: testDir
-			});
-			expect(showResult.stdout.toLowerCase()).toContain('medium');
-		});
-	});
-
-	describe('AI dependency suggestions', () => {
-		it('should let AI suggest dependencies based on context', async () => {
-			// Create some existing tasks that AI might reference
-			// Create an existing task that AI might reference
-			await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Setup authentication system'],
-				{ cwd: testDir }
-			);
-
-			// Create a task that should logically depend on auth
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Implement user profile page with authentication checks'],
-				{ cwd: testDir, timeout: 45000 }
-			);
-
-			expect(result).toHaveExitCode(0);
-			// Check if AI suggested dependencies
-			if (result.stdout.includes('AI suggested')) {
-				expect(result.stdout).toContain('Dependencies');
-			}
-		}, 60000);
-	});
-
-	describe('Tag support', () => {
-		it('should add task to specific tag', async () => {
-			// Create a new tag
-			await helpers.taskMaster(
-				'add-tag',
-				['feature-branch', '--description', 'Feature branch tag'],
-				{ cwd: testDir }
-			);
-
-			// Add task to specific tag
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Task for feature branch', '--tag', 'feature-branch'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContainTaskId();
-
-			// Verify task is in the correct tag
-			const taskId = helpers.extractTaskId(result.stdout);
-			const showResult = await helpers.taskMaster(
-				'show',
-				[taskId, '--tag', 'feature-branch'],
-				{ cwd: testDir }
-			);
-			expect(showResult).toHaveExitCode(0);
-		});
-
-		it('should add to master tag by default', async () => {
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Task for master tag'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-
-			// Verify task is in master tag
-			const tasksContent = JSON.parse(
-				readFileSync(join(testDir, '.taskmaster/tasks/tasks.json'), 'utf8')
-			);
-			expect(tasksContent.master.tasks.length).toBeGreaterThan(0);
-		});
-	});
-
-	describe('AI fallback behavior', () => {
-		it('should handle invalid model gracefully', async () => {
-			// Set an invalid model
-			await helpers.taskMaster('models', ['--set-main', 'invalid-model-xyz'], {
-				cwd: testDir
-			});
-
-			const result = await helpers.taskMaster(
-				'add-task',
-				['--prompt', 'Test fallback behavior'],
-				{ cwd: testDir, allowFailure: true }
-			);
-
-			// Should either use fallback or fail gracefully
-			if (result.exitCode === 0) {
-				expect(result.stdout).toContainTaskId();
-			} else {
-				expect(result.stderr).toBeTruthy();
-			}
-
-			// Reset to valid model for other tests
-			await helpers.taskMaster('models', ['--set-main', 'gpt-3.5-turbo'], {
-				cwd: testDir
-			});
-		});
-	});
-});

tests/e2e/tests/commands/analyze-complexity.test.js

@@ -1,377 +0,0 @@
-/**
- * Comprehensive E2E tests for analyze-complexity command
- * Tests all aspects of complexity analysis including research mode and output formats
- */
-
-import { describe, it, expect, beforeEach, afterEach } from '@jest/globals';
-import {
-	mkdtempSync,
-	existsSync,
-	readFileSync,
-	rmSync,
-	writeFileSync,
-	mkdirSync
-} from 'fs';
-import { join } from 'path';
-import { tmpdir } from 'os';
-import { execSync } from 'child_process';
-import { copyConfigFiles } from '../../utils/test-setup.js';
-
-describe('analyze-complexity command', () => {
-	let testDir;
-	let helpers;
-	let taskIds;
-
-	beforeEach(async () => {
-		// Create test directory
-		testDir = mkdtempSync(join(tmpdir(), 'task-master-analyze-complexity-'));
-
-		// Initialize test helpers
-		const context = global.createTestContext('analyze-complexity');
-		helpers = context.helpers;
-
-		copyConfigFiles(testDir);
-
-		// Initialize task-master project
-		const initResult = await helpers.taskMaster('init', ['-y'], {
-			cwd: testDir
-		});
-		expect(initResult).toHaveExitCode(0);
-
-		// Ensure tasks.json exists (bug workaround)
-		const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-		if (!existsSync(tasksJsonPath)) {
-			mkdirSync(join(testDir, '.taskmaster/tasks'), { recursive: true });
-			writeFileSync(tasksJsonPath, JSON.stringify({ master: { tasks: [] } }));
-		}
-
-		// Setup test tasks for analysis
-		taskIds = [];
-
-		// Create simple task
-		const simple = await helpers.taskMaster(
-			'add-task',
-			['--title', 'Simple task', '--description', 'A very simple task'],
-			{ cwd: testDir }
-		);
-		taskIds.push(helpers.extractTaskId(simple.stdout));
-
-		// Create complex task with subtasks
-		const complex = await helpers.taskMaster(
-			'add-task',
-			[
-				'--prompt',
-				'Build a complete e-commerce platform with payment processing'
-			],
-			{ cwd: testDir }
-		);
-		const complexId = helpers.extractTaskId(complex.stdout);
-		taskIds.push(complexId);
-
-		// Expand complex task to add subtasks
-		await helpers.taskMaster('expand', ['-i', complexId, '-n', '3'], { cwd: testDir, timeout: 60000 });
-
-		// Create task with dependencies
-		const withDeps = await helpers.taskMaster(
-			'add-task',
-			['--title', 'Deployment task', '--description', 'Deploy the application'],
-			{ cwd: testDir }
-		);
-		const withDepsId = helpers.extractTaskId(withDeps.stdout);
-		taskIds.push(withDepsId);
-		
-		// Add dependency
-		await helpers.taskMaster('add-dependency', ['--id', withDepsId, '--depends-on', taskIds[0]], { cwd: testDir });
-	});
-
-	afterEach(() => {
-		// Clean up test directory
-		if (testDir && existsSync(testDir)) {
-			rmSync(testDir, { recursive: true, force: true });
-		}
-	});
-
-	describe('Basic complexity analysis', () => {
-		it('should analyze complexity without flags', async () => {
-			const result = await helpers.taskMaster('analyze-complexity', [], {
-				cwd: testDir
-			});
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout.toLowerCase()).toContain('complexity');
-		});
-
-		it.skip('should analyze with research flag', async () => {
-			// Skip this test - research mode takes too long for CI
-			// Research flag requires internet access and can timeout
-		});
-	});
-
-	describe('Output options', () => {
-		it('should save to custom output file', async () => {
-			// Create reports directory first
-			const reportsDir = join(testDir, '.taskmaster/reports');
-			mkdirSync(reportsDir, { recursive: true });
-			
-			// Create the output file first (the command expects it to exist)
-			const outputPath = '.taskmaster/reports/custom-complexity.json';
-			const fullPath = join(testDir, outputPath);
-			writeFileSync(fullPath, '{}');
-			
-			const result = await helpers.taskMaster(
-				'analyze-complexity',
-				['--output', outputPath],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(existsSync(fullPath)).toBe(true);
-
-			// Verify it's valid JSON
-			const report = JSON.parse(readFileSync(fullPath, 'utf8'));
-			expect(report).toBeDefined();
-			expect(typeof report).toBe('object');
-		});
-
-		it('should save analysis to default location', async () => {
-			const result = await helpers.taskMaster(
-				'analyze-complexity',
-				[],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-
-			// Check if report was saved
-			const defaultPath = join(testDir, '.taskmaster/reports/task-complexity-report.json');
-			expect(existsSync(defaultPath)).toBe(true);
-		});
-
-		it('should show task analysis in output', async () => {
-			const result = await helpers.taskMaster(
-				'analyze-complexity',
-				[],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-
-			// Check for basic analysis output
-			const output = result.stdout.toLowerCase();
-			expect(output).toContain('analyzing');
-			
-			// Check if tasks are mentioned
-			taskIds.forEach(id => {
-				expect(result.stdout).toContain(id.toString());
-			});
-		});
-	});
-
-	describe('Filtering options', () => {
-		it('should analyze specific tasks', async () => {
-			const result = await helpers.taskMaster(
-				'analyze-complexity',
-				['--id', taskIds.join(',')],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-
-			// Should analyze only specified tasks
-			taskIds.forEach((taskId) => {
-				expect(result.stdout).toContain(taskId.toString());
-			});
-		});
-
-		it('should filter by tag', async () => {
-			// Create tag
-			await helpers.taskMaster('add-tag', ['complex-tag'], { cwd: testDir });
-			
-			// Switch to the tag context
-			await helpers.taskMaster('use-tag', ['complex-tag'], { cwd: testDir });
-			
-			// Create task in that tag
-			const taggedResult = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Tagged complex task', '--description', 'Task in complex-tag'],
-				{ cwd: testDir }
-			);
-			const taggedId = helpers.extractTaskId(taggedResult.stdout);
-
-			const result = await helpers.taskMaster(
-				'analyze-complexity',
-				['--tag', 'complex-tag'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain(taggedId);
-		});
-
-		it.skip('should filter by status', async () => {
-			// Skip this test - status filtering is not implemented
-			// The analyze-complexity command doesn't support --status flag
-		});
-	});
-
-	describe('Threshold configuration', () => {
-		it('should use custom threshold', async () => {
-			const result = await helpers.taskMaster(
-				'analyze-complexity',
-				['--threshold', '7'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			
-			// Check that the analysis completed
-			const output = result.stdout;
-			expect(output).toContain('Task complexity analysis complete');
-		});
-
-		it('should accept threshold values between 1-10', async () => {
-			// Test valid threshold
-			const result = await helpers.taskMaster(
-				'analyze-complexity',
-				['--threshold', '10'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Task complexity analysis complete');
-		});
-	});
-
-	describe('Edge cases', () => {
-		it('should handle empty project', async () => {
-			// Create a new temp directory
-			const emptyDir = mkdtempSync(join(tmpdir(), 'task-master-empty-'));
-
-			try {
-				await helpers.taskMaster('init', ['-y'], { cwd: emptyDir });
-				
-				// Ensure tasks.json exists (bug workaround)
-				const tasksJsonPath = join(emptyDir, '.taskmaster/tasks/tasks.json');
-				if (!existsSync(tasksJsonPath)) {
-					mkdirSync(join(emptyDir, '.taskmaster/tasks'), { recursive: true });
-					writeFileSync(tasksJsonPath, JSON.stringify({ master: { tasks: [] } }));
-				}
-
-				const result = await helpers.taskMaster('analyze-complexity', [], {
-					cwd: emptyDir
-				});
-
-				expect(result.exitCode).not.toBe(0);
-				expect(result.stderr).toContain('No tasks found');
-			} finally {
-				rmSync(emptyDir, { recursive: true, force: true });
-			}
-		});
-
-		it('should handle invalid output path', async () => {
-			const result = await helpers.taskMaster(
-				'analyze-complexity',
-				['--output', '/invalid/path/report.json'],
-				{ cwd: testDir, allowFailure: true }
-			);
-
-			expect(result.exitCode).not.toBe(0);
-		});
-	});
-
-	describe('Performance', () => {
-		it('should analyze many tasks efficiently', async () => {
-			// Create 20 more tasks
-			const promises = [];
-			for (let i = 0; i < 20; i++) {
-				promises.push(
-					helpers.taskMaster(
-						'add-task',
-						['--title', `Performance test task ${i}`, '--description', `Test task ${i} for performance testing`],
-						{ cwd: testDir }
-					)
-				);
-			}
-			await Promise.all(promises);
-
-			const startTime = Date.now();
-			const result = await helpers.taskMaster('analyze-complexity', [], {
-				cwd: testDir
-			});
-			const duration = Date.now() - startTime;
-
-			expect(result).toHaveExitCode(0);
-			expect(duration).toBeLessThan(60000); // Should complete in less than 60 seconds
-		});
-	});
-
-	describe('Complexity scoring', () => {
-		it.skip('should score complex tasks higher than simple ones', async () => {
-			// Skip this test as it requires AI API access
-			const result = await helpers.taskMaster(
-				'analyze-complexity',
-				[],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-
-			// Read the saved report
-			const reportPath = join(testDir, '.taskmaster/reports/task-complexity-report.json');
-			
-			// Check if report exists
-			expect(existsSync(reportPath)).toBe(true);
-			
-			const analysis = JSON.parse(readFileSync(reportPath, 'utf8'));
-			
-			// The report structure might have tasks or complexityAnalysis array
-			const tasks = analysis.tasks || analysis.complexityAnalysis || analysis.results || [];
-			
-			// If no tasks found, check if analysis itself is an array
-			const taskArray = Array.isArray(analysis) ? analysis : tasks;
-			
-			// Convert taskIds to numbers if they're strings
-			const simpleTaskId = parseInt(taskIds[0], 10);
-			const complexTaskId = parseInt(taskIds[1], 10);
-			
-			// Try to find tasks by different possible ID fields
-			const simpleTask = taskArray.find((t) => 
-				t.id === simpleTaskId || 
-				t.id === taskIds[0] || 
-				t.taskId === simpleTaskId || 
-				t.taskId === taskIds[0]
-			);
-			const complexTask = taskArray.find((t) => 
-				t.id === complexTaskId || 
-				t.id === taskIds[1] || 
-				t.taskId === complexTaskId || 
-				t.taskId === taskIds[1]
-			);
-
-			expect(simpleTask).toBeDefined();
-			expect(complexTask).toBeDefined();
-			
-			// Get the complexity score from whichever property is used
-			const simpleScore = simpleTask.complexityScore || simpleTask.complexity?.score || 0;
-			const complexScore = complexTask.complexityScore || complexTask.complexity?.score || 0;
-			expect(complexScore).toBeGreaterThan(simpleScore);
-		});
-	});
-
-	describe('Report generation', () => {
-		it('should generate complexity report', async () => {
-			// First run analyze-complexity to generate the default report
-			await helpers.taskMaster('analyze-complexity', [], { cwd: testDir });
-
-			// Then run complexity-report to display it
-			const result = await helpers.taskMaster('complexity-report', [], {
-				cwd: testDir
-			});
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout.toLowerCase()).toMatch(
-				/complexity.*report|analysis/
-			);
-		});
-	});
-});

tests/e2e/tests/commands/clear-subtasks.test.js

@@ -1,240 +0,0 @@
-import { describe, it, expect, beforeEach, afterEach } from '@jest/globals';
-import { mkdtempSync, existsSync, readFileSync, rmSync, writeFileSync, mkdirSync } from 'fs';
-import { join, dirname } from 'path';
-import { tmpdir } from 'os';
-describe('task-master clear-subtasks command', () => {
-	let testDir;
-	let helpers;
-	let tasksPath;
-
-	beforeEach(async () => {
-		// Create test directory
-		testDir = mkdtempSync(join(tmpdir(), 'task-master-clear-subtasks-command-'));
-
-		// Initialize test helpers
-		const context = global.createTestContext('clear-subtasks command');
-		helpers = context.helpers;
-
-		// Copy .env file if it exists
-		const mainEnvPath = join(process.cwd(), '.env');
-		const testEnvPath = join(testDir, '.env');
-		if (existsSync(mainEnvPath)) {
-			const envContent = readFileSync(mainEnvPath, 'utf8');
-			writeFileSync(testEnvPath, envContent);
-		}
-
-		// Initialize task-master project
-		const initResult = await helpers.taskMaster('init', ['-y'], {
-			cwd: testDir
-		});
-		expect(initResult).toHaveExitCode(0);
-
-		// Ensure tasks.json exists (bug workaround)
-		const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-		if (!existsSync(tasksJsonPath)) {
-			mkdirSync(join(testDir, '.taskmaster/tasks'), { recursive: true });
-			writeFileSync(tasksJsonPath, JSON.stringify({ master: { tasks: [] } }));
-		}
-
-		// Set up tasks path
-		tasksPath = join(testDir, '.taskmaster', 'tasks', 'tasks.json');
-
-		// Create test tasks with subtasks
-		const testTasks = {
-			tasks: [
-					{
-						id: 1,
-						description: 'Task with subtasks',
-						status: 'pending',
-						priority: 'high',
-						dependencies: [],
-						subtasks: [
-							{
-								id: 1.1,
-								description: 'Subtask 1',
-								status: 'pending',
-								priority: 'medium'
-							},
-							{
-								id: 1.2,
-								description: 'Subtask 2',
-								status: 'pending',
-								priority: 'medium'
-							}
-						]
-					},
-					{
-						id: 2,
-						description: 'Another task with subtasks',
-						status: 'in_progress',
-						priority: 'medium',
-						dependencies: [],
-						subtasks: [
-							{
-								id: 2.1,
-								description: 'Subtask 2.1',
-								status: 'pending',
-								priority: 'low'
-							}
-						]
-					},
-					{
-						id: 3,
-						description: 'Task without subtasks',
-						status: 'pending',
-						priority: 'low',
-						dependencies: [],
-						subtasks: []
-					}
-				]
-		};
-
-		// Ensure .taskmaster directory exists
-		mkdirSync(dirname(tasksPath), { recursive: true });
-		writeFileSync(tasksPath, JSON.stringify(testTasks, null, 2));
-	});
-
-	afterEach(() => {
-		// Clean up test directory
-		if (testDir && existsSync(testDir)) {
-			rmSync(testDir, { recursive: true, force: true });
-		}
-	});
-
-	it('should clear subtasks from a specific task', async () => {
-		// Run clear-subtasks command for task 1
-		const result = await helpers.taskMaster('clear-subtasks', ['-f', tasksPath, '-i', '1'], { cwd: testDir });
-
-		// Verify success
-		expect(result).toHaveExitCode(0);
-		expect(result.stdout).toContain('Clearing Subtasks');
-		expect(result.stdout).toContain('Cleared 2 subtasks from task 1');
-
-		// Read updated tasks
-		const updatedTasks = JSON.parse(readFileSync(tasksPath, 'utf8'));
-		// Handle both formats: direct tasks array or master.tasks
-		const tasks = updatedTasks.master ? updatedTasks.master.tasks : updatedTasks.tasks;
-		const task1 = tasks.find(t => t.id === 1);
-		const task2 = tasks.find(t => t.id === 2);
-
-		// Verify task 1 has no subtasks
-		expect(task1.subtasks).toHaveLength(0);
-
-		// Verify task 2 still has subtasks
-		expect(task2.subtasks).toHaveLength(1);
-	});
-
-	it('should clear subtasks from multiple tasks', async () => {
-		// Run clear-subtasks command for tasks 1 and 2
-		const result = await helpers.taskMaster('clear-subtasks', ['-f', tasksPath, '-i', '1,2'], { cwd: testDir });
-
-		// Verify success
-		expect(result).toHaveExitCode(0);
-		expect(result.stdout).toContain('Clearing Subtasks');
-		// The success message appears in a decorative box with chalk formatting and ANSI codes
-		// Using a more flexible pattern to account for ANSI escape codes and formatting
-		expect(result.stdout).toMatch(/Successfully\s+cleared\s+subtasks\s+from\s+.*2.*\s+task\(s\)/i);
-
-		// Read updated tasks
-		const updatedTasks = JSON.parse(readFileSync(tasksPath, 'utf8'));
-		// Handle both formats: direct tasks array or master.tasks
-		const tasks = updatedTasks.master ? updatedTasks.master.tasks : updatedTasks.tasks;
-		const task1 = tasks.find(t => t.id === 1);
-		const task2 = tasks.find(t => t.id === 2);
-
-		// Verify both tasks have no subtasks
-		expect(task1.subtasks).toHaveLength(0);
-		expect(task2.subtasks).toHaveLength(0);
-	});
-
-	it('should clear subtasks from all tasks with --all flag', async () => {
-		// Run clear-subtasks command with --all
-		const result = await helpers.taskMaster('clear-subtasks', ['-f', tasksPath, '--all'], { cwd: testDir });
-
-		// Verify success
-		expect(result).toHaveExitCode(0);
-		expect(result.stdout).toContain('Clearing Subtasks');
-		// The success message appears in a decorative box with extra spaces
-		expect(result.stdout).toMatch(/Successfully\s+cleared\s+subtasks\s+from/i);
-
-		// Read updated tasks
-		const updatedTasks = JSON.parse(readFileSync(tasksPath, 'utf8'));
-		
-		// Verify all tasks have no subtasks
-		const tasks = updatedTasks.master ? updatedTasks.master.tasks : updatedTasks.tasks;
-		tasks.forEach(task => {
-			expect(task.subtasks).toHaveLength(0);
-		});
-	});
-
-	it('should handle task without subtasks gracefully', async () => {
-		// Run clear-subtasks command for task 3 (which has no subtasks)
-		const result = await helpers.taskMaster('clear-subtasks', ['-f', tasksPath, '-i', '3'], { cwd: testDir });
-
-		// Should succeed without error
-		expect(result).toHaveExitCode(0);
-		expect(result.stdout).toContain('Clearing Subtasks');
-
-		// Task should remain unchanged
-		const updatedTasks = JSON.parse(readFileSync(tasksPath, 'utf8'));
-		const tasks = updatedTasks.master ? updatedTasks.master.tasks : updatedTasks.tasks;
-		const task3 = tasks.find(t => t.id === 3);
-		expect(task3.subtasks).toHaveLength(0);
-	});
-
-	it('should fail when neither --id nor --all is specified', async () => {
-		// Run clear-subtasks command without specifying tasks
-		const result = await helpers.taskMaster('clear-subtasks', ['-f', tasksPath], { cwd: testDir });
-
-		// Should fail with error
-		expect(result.exitCode).not.toBe(0);
-		expect(result.stderr).toContain('Error');
-		expect(result.stderr).toContain('Please specify task IDs');
-	});
-
-	it('should handle non-existent task ID', async () => {
-		// Run clear-subtasks command with non-existent task ID
-		const result = await helpers.taskMaster('clear-subtasks', ['-f', tasksPath, '-i', '999'], { cwd: testDir });
-
-		// Should handle gracefully
-		expect(result).toHaveExitCode(0);
-		// Original tasks should remain unchanged
-		const updatedTasks = JSON.parse(readFileSync(tasksPath, 'utf8'));
-		// Check if master tag was created (which happens with readJSON/writeJSON)
-		const tasks = updatedTasks.master ? updatedTasks.master.tasks : updatedTasks.tasks;
-		expect(tasks).toHaveLength(3);
-	});
-
-	it.skip('should work with tag option', async () => {
-		// Skip this test as tag support might not be implemented yet
-		// Create tasks with different tags
-		const multiTagTasks = {
-			master: {
-				tasks: [{
-					id: 1,
-					description: 'Master task',
-					subtasks: [{ id: 1.1, description: 'Master subtask' }]
-				}]
-			},
-			feature: {
-				tasks: [{
-					id: 1,
-					description: 'Feature task',
-					subtasks: [{ id: 1.1, description: 'Feature subtask' }]
-				}]
-			}
-		};
-
-		writeFileSync(tasksPath, JSON.stringify(multiTagTasks, null, 2));
-
-		// Clear subtasks from feature tag
-		const result = await helpers.taskMaster('clear-subtasks', ['-f', tasksPath, '-i', '1', '--tag', 'feature'], { cwd: testDir });
-
-		expect(result).toHaveExitCode(0);
-
-		// Verify only feature tag was affected
-		const updatedTasks = JSON.parse(readFileSync(tasksPath, 'utf8'));
-		expect(updatedTasks.master.tasks[0].subtasks).toHaveLength(1);
-		expect(updatedTasks.feature.tasks[0].subtasks).toHaveLength(0);
-	});
-});

tests/e2e/tests/commands/command-coverage.md

@@ -1,128 +0,0 @@
-# Command Test Coverage
-
-## Commands Found in commands.js
-
-1. **parse-prd** ✅ (has test: parse-prd.test.js)
-2. **update** ✅ (has test: update.test.js)
-3. **update-task** ✅ (has test: update-task.test.js)
-4. **update-subtask** ✅ (has test: update-subtask.test.js)
-5. **generate** ✅ (has test: generate.test.js)
-6. **set-status** (aliases: mark, set) ✅ (has test: set-status.test.js)
-7. **list** ✅ (has test: list.test.js)
-8. **expand** ✅ (has test: expand-task.test.js)
-9. **analyze-complexity** ✅ (has test: analyze-complexity.test.js)
-10. **research** ✅ (has test: research.test.js, research-save.test.js)
-11. **clear-subtasks** ✅ (has test: clear-subtasks.test.js)
-12. **add-task** ✅ (has test: add-task.test.js)
-13. **next** ✅ (has test: next.test.js)
-14. **show** ✅ (has test: show.test.js)
-15. **add-dependency** ✅ (has test: add-dependency.test.js)
-16. **remove-dependency** ✅ (has test: remove-dependency.test.js)
-17. **validate-dependencies** ✅ (has test: validate-dependencies.test.js)
-18. **fix-dependencies** ✅ (has test: fix-dependencies.test.js)
-19. **complexity-report** ✅ (has test: complexity-report.test.js)
-20. **add-subtask** ✅ (has test: add-subtask.test.js)
-21. **remove-subtask** ✅ (has test: remove-subtask.test.js)
-22. **remove-task** ✅ (has test: remove-task.test.js)
-23. **init** ✅ (has test: init.test.js)
-24. **models** ✅ (has test: models.test.js)
-25. **lang** ✅ (has test: lang.test.js)
-26. **move** ✅ (has test: move.test.js)
-27. **rules** ✅ (has test: rules.test.js)
-28. **migrate** ✅ (has test: migrate.test.js)
-29. **sync-readme** ✅ (has test: sync-readme.test.js)
-30. **add-tag** ✅ (has test: add-tag.test.js)
-31. **delete-tag** ✅ (has test: delete-tag.test.js)
-32. **tags** ✅ (has test: tags.test.js)
-33. **use-tag** ✅ (has test: use-tag.test.js)
-34. **rename-tag** ✅ (has test: rename-tag.test.js)
-35. **copy-tag** ✅ (has test: copy-tag.test.js)
-
-## Summary
-
-- **Total Commands**: 35
-- **Commands with Tests**: 35 (100%)
-- **Commands without Tests**: 0 (0%)
-
-## Missing Tests (Priority)
-
-### Lower Priority (Additional features)
-1. **lang** - Manages response language settings
-2. **move** - Moves task/subtask to new position
-3. **rules** - Manages task rules/profiles
-4. **migrate** - Migrates project structure
-5. **sync-readme** - Syncs task list to README
-
-### Tag Management (Complete set)
-6. **add-tag** - Creates new tag
-7. **delete-tag** - Deletes existing tag
-8. **tags** - Lists all tags
-9. **use-tag** - Switches tag context
-10. **rename-tag** - Renames existing tag
-11. **copy-tag** - Copies tag with tasks
-
-## Test Execution Status (Updated: 2025-07-17)
-
-### ✅ Fully Passing (All tests pass)
-1. **add-dependency** - 19/21 tests pass (2 skipped as not implemented)
-2. **add-subtask** - 11/11 tests pass (100%)
-3. **add-task** - 24/24 tests pass (100%)
-4. **clear-subtasks** - 6/7 tests pass (1 skipped for tag option)
-5. **copy-tag** - 14/14 tests pass (100%)
-6. **delete-tag** - 15/16 tests pass (1 skipped as aliases not fully supported)
-7. **complexity-report** - 8/8 tests pass (100%)
-8. **fix-dependencies** - 8/8 tests pass (100%)
-9. **generate** - 4/4 tests pass (100%)
-10. **init** - 7/7 tests pass (100%)
-11. **models** - 13/13 tests pass (100%)
-12. **next** - 8/8 tests pass (100%)
-13. **remove-dependency** - 9/9 tests pass (100%)
-14. **remove-subtask** - 9/9 tests pass (100%)
-15. **rename-tag** - 14/14 tests pass (100%)
-16. **show** - 8+/18 tests pass (core functionality working, some multi-word titles still need quoting)
-17. **rules** - 21/21 tests pass (100%)
-18. **set-status** - 17/17 tests pass (100%)
-19. **tags** - 14/14 tests pass (100%)
-20. **update-subtask** - Core functionality working (test file includes tests for unimplemented options)
-21. **update** - Fixed: test file renamed from update-tasks.test.js to update.test.js, uses correct --from parameter instead of non-existent --ids/--status/--priority
-22. **use-tag** - 6/6 tests pass (100%)
-23. **validate-dependencies** - 8/8 tests pass (100%)
-
-### ⚠️ Mostly Passing (Some tests fail/skip)
-22. **add-tag** - 18/21 tests pass (3 skipped: 2 git integration bugs, 1 file system test)
-23. **analyze-complexity** - 12/15 tests pass (3 skipped: 1 research mode timeout, 1 status filtering not implemented, 1 empty project edge case)
-24. **lang** - 16/20 tests pass (4 failing: error handling behaviors changed)
-25. **parse-prd** - 5/18 tests pass (13 timeout due to AI API calls taking 80+ seconds, but core functionality works)
-26. **sync-readme** - 11/20 tests pass (9 fail due to task title truncation in README export, but core functionality works)
-
-### ❌ Failing/Timeout Issues  
-27. **update-task** - ~15/18 tests pass after rewrite (completely rewritten to match actual AI-powered command interface, some tests timeout due to AI calls)
-28. **expand-task** - Tests consistently timeout (AI API calls take 30+ seconds, causing Jest timeout)
-29. **list** - Tests consistently timeout (fixed invalid "blocked" status in tests, command works manually)
-30. **move** - Tests fail with "Task with ID 1 already exists" error, even for basic error handling tests
-31. **remove-task** - Tests consistently timeout during setup or execution
-32. **research-save** - Uses legacy test format, likely timeout due to AI research calls (120s timeout configured)
-32. **research** - 2/24 tests pass (22 timeout due to AI research calls, but fixed command interface issues)
-
-### ❓ Not Yet Tested
-- All other commands...
-
-## Recently Added Tests (2024)
-
-The following tests were just created:
-- generate.test.js
-- init.test.js
-- clear-subtasks.test.js
-- add-subtask.test.js
-- remove-subtask.test.js
-- next.test.js
-- remove-dependency.test.js
-- validate-dependencies.test.js
-- fix-dependencies.test.js
-- complexity-report.test.js
-- models.test.js (fixed 2025-07-17)
-- parse-prd.test.js (fixed 2025-07-17: 5/18 tests pass, core functionality working but some AI calls timeout)
-- set-status.test.js (fixed 2025-07-17: 17/17 tests pass)
-- sync-readme.test.js (fixed 2025-07-17: 11/20 tests pass, core functionality working)
-- use-tag.test.js (verified 2025-07-17: 6/6 tests pass, no fixes needed!)
-- list.test.js (invalid "blocked" status fixed to "review" 2025-07-17, but tests timeout)

tests/e2e/tests/commands/complexity-report.test.js

@@ -1,327 +0,0 @@
-import { describe, it, expect, beforeAll, afterAll } from '@jest/globals';
-import { mkdtempSync, existsSync, readFileSync, rmSync, writeFileSync, mkdirSync } from 'fs';
-import { join, dirname } from 'path';
-import { tmpdir } from 'os';
-describe('task-master complexity-report command', () => {
-	let testDir;
-	let helpers;
-	let reportPath;
-
-	beforeEach(async () => {
-		// Create test directory
-		testDir = mkdtempSync(join(tmpdir(), 'task-master-complexity-report-command-'));
-
-		// Initialize test helpers
-		const context = global.createTestContext('complexity-report command');
-		helpers = context.helpers;
-
-		// Copy .env file if it exists
-		const mainEnvPath = join(process.cwd(), '.env');
-		const testEnvPath = join(testDir, '.env');
-		if (existsSync(mainEnvPath)) {
-			const envContent = readFileSync(mainEnvPath, 'utf8');
-			writeFileSync(testEnvPath, envContent);
-		}
-
-		// Initialize task-master project
-		const initResult = await helpers.taskMaster('init', ['-y'], {
-			cwd: testDir
-		});
-		expect(initResult).toHaveExitCode(0);
-
-		// Ensure tasks.json exists (bug workaround)
-		const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-		if (!existsSync(tasksJsonPath)) {
-			mkdirSync(join(testDir, '.taskmaster/tasks'), { recursive: true });
-			writeFileSync(tasksJsonPath, JSON.stringify({ master: { tasks: [] } }));
-		}
-
-		// Initialize report path
-		reportPath = join(testDir, '.taskmaster/task-complexity-report.json');
-	});
-
-	afterEach(() => {
-		// Clean up test directory
-		if (testDir && existsSync(testDir)) {
-			rmSync(testDir, { recursive: true, force: true });
-		}
-	});
-
-	it('should display complexity report', async () => {
-		// Create a sample complexity report matching actual structure
-		const complexityReport = {
-			meta: {
-				generatedAt: new Date().toISOString(),
-				tasksAnalyzed: 3,
-				totalTasks: 3,
-				analysisCount: 3,
-				thresholdScore: 5,
-				projectName: 'test-project',
-				usedResearch: false
-			},
-			complexityAnalysis: [
-				{
-					taskId: 1,
-					taskTitle: 'Simple task',
-					complexityScore: 3,
-					recommendedSubtasks: 2,
-					expansionPrompt: 'Break down this simple task',
-					reasoning: 'This is a simple task with low complexity'
-				},
-				{
-					taskId: 2,
-					taskTitle: 'Medium complexity task',
-					complexityScore: 5,
-					recommendedSubtasks: 4,
-					expansionPrompt: 'Break down this medium complexity task',
-					reasoning: 'This task has moderate complexity'
-				},
-				{
-					taskId: 3,
-					taskTitle: 'Complex task',
-					complexityScore: 8,
-					recommendedSubtasks: 6,
-					expansionPrompt: 'Break down this complex task',
-					reasoning: 'This is a complex task requiring careful decomposition'
-				}
-			]
-		};
-
-		// Ensure .taskmaster directory exists
-		mkdirSync(dirname(reportPath), { recursive: true });
-		writeFileSync(reportPath, JSON.stringify(complexityReport, null, 2));
-
-		// Run complexity-report command
-		const result = await helpers.taskMaster('complexity-report', ['-f', reportPath], { cwd: testDir });
-
-		// Verify success
-		expect(result).toHaveExitCode(0);
-		expect(result.stdout).toContain('Task Complexity Analysis Report');
-		expect(result.stdout).toContain('Tasks Analyzed:');
-		expect(result.stdout).toContain('3'); // number of tasks
-		expect(result.stdout).toContain('Simple task');
-		expect(result.stdout).toContain('Medium complexity task');
-		expect(result.stdout).toContain('Complex task');
-		// Check for complexity distribution
-		expect(result.stdout).toContain('Complexity Distribution');
-		expect(result.stdout).toContain('Low');
-		expect(result.stdout).toContain('Medium');
-		expect(result.stdout).toContain('High')
-	});
-
-	it('should display detailed task complexity', async () => {
-		// Create a report with detailed task info matching actual structure
-		const detailedReport = {
-			meta: {
-				generatedAt: new Date().toISOString(),
-				tasksAnalyzed: 1,
-				totalTasks: 1,
-				analysisCount: 1,
-				thresholdScore: 5,
-				projectName: 'test-project',
-				usedResearch: false
-			},
-			complexityAnalysis: [
-				{
-					taskId: 1,
-					taskTitle: 'Implement authentication system',
-					complexityScore: 7,
-					recommendedSubtasks: 5,
-					expansionPrompt: 'Break down authentication system implementation with focus on security',
-					reasoning: 'Requires integration with multiple services, security considerations'
-				}
-			]
-		};
-
-		writeFileSync(reportPath, JSON.stringify(detailedReport, null, 2));
-
-		// Run complexity-report command
-		const result = await helpers.taskMaster('complexity-report', ['-f', reportPath], { cwd: testDir });
-
-		// Verify detailed output
-		expect(result).toHaveExitCode(0);
-		// Title might be truncated in display
-		expect(result.stdout).toContain('Implement authentic'); // partial match
-		expect(result.stdout).toContain('7'); // complexity score
-		expect(result.stdout).toContain('5'); // recommended subtasks
-		// Check for expansion prompt text (visible in the expansion command)
-		expect(result.stdout).toContain('authentication');
-		expect(result.stdout).toContain('system');
-		expect(result.stdout).toContain('implementation');
-	});
-
-	it('should handle missing report file', async () => {
-		const nonExistentPath = join(testDir, '.taskmaster', 'non-existent-report.json');
-
-		// Run complexity-report command with non-existent file
-		const result = await helpers.taskMaster('complexity-report', ['-f', nonExistentPath], { cwd: testDir, allowFailure: true });
-
-		// Should fail gracefully
-		expect(result.exitCode).not.toBe(0);
-		expect(result.stderr).toContain('Error');
-		expect(result.stderr).toContain('does not exist');
-		// The error message doesn't contain 'analyze-complexity' but does show path not found
-		expect(result.stderr).toContain('does not exist');
-	});
-
-	it('should handle empty report', async () => {
-		// Create an empty report matching actual structure
-		const emptyReport = {
-			meta: {
-				generatedAt: new Date().toISOString(),
-				tasksAnalyzed: 0,
-				totalTasks: 0,
-				analysisCount: 0,
-				thresholdScore: 5,
-				projectName: 'test-project',
-				usedResearch: false
-			},
-			complexityAnalysis: []
-		};
-
-		writeFileSync(reportPath, JSON.stringify(emptyReport, null, 2));
-
-		// Run complexity-report command
-		const result = await helpers.taskMaster('complexity-report', ['-f', reportPath], { cwd: testDir });
-
-		// Should handle gracefully
-		expect(result).toHaveExitCode(0);
-		expect(result.stdout).toContain('Tasks Analyzed:');
-		expect(result.stdout).toContain('0');
-		// Empty report still shows the table structure
-		expect(result.stdout).toContain('Complexity Distribution');
-	});
-
-	it('should work with tag option for tag-specific reports', async () => {
-		// Create tag-specific report
-		const reportsDir = join(testDir, '.taskmaster/reports');
-		mkdirSync(reportsDir, { recursive: true });
-		// For tags, the path includes the tag name
-		const featureReportPath = join(testDir, '.taskmaster/reports/task-complexity-report_feature.json');
-		const featureReport = {
-			meta: {
-				generatedAt: new Date().toISOString(),
-				tasksAnalyzed: 2,
-				totalTasks: 2,
-				analysisCount: 2,
-				thresholdScore: 5,
-				projectName: 'test-project',
-				usedResearch: false
-			},
-			complexityAnalysis: [
-				{
-					taskId: 1,
-					taskTitle: 'Feature task 1',
-					complexityScore: 3,
-					recommendedSubtasks: 2,
-					expansionPrompt: 'Break down feature task 1',
-					reasoning: 'Low complexity feature task'
-				},
-				{
-					taskId: 2,
-					taskTitle: 'Feature task 2',
-					complexityScore: 5,
-					recommendedSubtasks: 3,
-					expansionPrompt: 'Break down feature task 2',
-					reasoning: 'Medium complexity feature task'
-				}
-			]
-		};
-
-		writeFileSync(featureReportPath, JSON.stringify(featureReport, null, 2));
-
-		// Run complexity-report command with specific file path (not tag)
-		const result = await helpers.taskMaster('complexity-report', ['-f', featureReportPath], { cwd: testDir });
-
-		// Should display feature-specific report
-		expect(result).toHaveExitCode(0);
-		expect(result.stdout).toContain('Feature task 1');
-		expect(result.stdout).toContain('Feature task 2');
-		expect(result.stdout).toContain('Tasks Analyzed:');
-		expect(result.stdout).toContain('2');
-	});
-
-	it('should display complexity distribution chart', async () => {
-		// Create report with various complexity levels
-		const distributionReport = {
-			meta: {
-				generatedAt: new Date().toISOString(),
-				tasksAnalyzed: 10,
-				totalTasks: 10,
-				analysisCount: 10,
-				thresholdScore: 5,
-				projectName: 'test-project',
-				usedResearch: false
-			},
-			complexityAnalysis: Array.from({ length: 10 }, (_, i) => ({
-				taskId: i + 1,
-				taskTitle: `Task ${i + 1}`,
-				complexityScore: i < 3 ? 2 : i < 8 ? 5 : 8,
-				recommendedSubtasks: i < 3 ? 2 : i < 8 ? 3 : 5,
-				expansionPrompt: `Break down task ${i + 1}`,
-				reasoning: `Task ${i + 1} complexity reasoning`
-			}))
-		};
-
-		writeFileSync(reportPath, JSON.stringify(distributionReport, null, 2));
-
-		// Run complexity-report command
-		const result = await helpers.taskMaster('complexity-report', ['-f', reportPath], { cwd: testDir });
-
-		// Should show distribution
-		expect(result).toHaveExitCode(0);
-		expect(result.stdout).toContain('Complexity Distribution');
-		// The distribution text appears with percentages in a decorative box
-		expect(result.stdout).toMatch(/Low \(1-4\): 3 tasks \(\d+%\)/);
-		expect(result.stdout).toMatch(/Medium \(5-7\): 5 tasks \(\d+%\)/);
-		expect(result.stdout).toMatch(/High \(8-10\): 2 tasks \(\d+%\)/);
-	});
-
-	it('should handle malformed report gracefully', async () => {
-		// Create malformed report
-		writeFileSync(reportPath, '{ invalid json }');
-
-		// Run complexity-report command
-		const result = await helpers.taskMaster('complexity-report', ['-f', reportPath], { cwd: testDir });
-
-		// The command exits silently when JSON parsing fails
-		expect(result).toHaveExitCode(0);
-		// Output shows error message and tag footer
-		expect(result.stdout).toContain('🏷️ tag: master');
-		expect(result.stdout).toContain('[ERROR]');
-		expect(result.stdout).toContain('Error reading complexity report');
-	});
-
-	it('should display report generation time', async () => {
-		const generatedAt = '2024-03-15T10:30:00Z';
-		const timedReport = {
-			meta: {
-				generatedAt,
-				tasksAnalyzed: 1,
-				totalTasks: 1,
-				analysisCount: 1,
-				thresholdScore: 5,
-				projectName: 'test-project',
-				usedResearch: false
-			},
-			complexityAnalysis: [{
-				taskId: 1,
-				taskTitle: 'Test task',
-				complexityScore: 5,
-				recommendedSubtasks: 3,
-				expansionPrompt: 'Break down test task',
-				reasoning: 'Medium complexity test task'
-			}]
-		};
-
-		writeFileSync(reportPath, JSON.stringify(timedReport, null, 2));
-
-		// Run complexity-report command
-		const result = await helpers.taskMaster('complexity-report', ['-f', reportPath], { cwd: testDir });
-
-		// Should show generation time
-		expect(result).toHaveExitCode(0);
-		expect(result.stdout).toContain('Generated');
-		expect(result.stdout).toMatch(/2024|Mar|15/); // Date formatting may vary
-	});
-});

tests/e2e/tests/commands/copy-tag.test.js

@@ -1,487 +0,0 @@
-/**
- * E2E tests for copy-tag command
- * Tests tag copying functionality
- */
-
-import { describe, it, expect, beforeEach, afterEach } from '@jest/globals';
-import {
-	mkdtempSync,
-	existsSync,
-	readFileSync,
-	rmSync,
-	writeFileSync,
-	mkdirSync
-} from 'fs';
-import { join } from 'path';
-import { tmpdir } from 'os';
-import { copyConfigFiles } from '../../utils/test-setup.js';
-
-describe('task-master copy-tag', () => {
-	let testDir;
-	let helpers;
-
-	beforeEach(async () => {
-		// Create test directory
-		testDir = mkdtempSync(join(tmpdir(), 'task-master-copy-tag-'));
-
-		// Initialize test helpers
-		const context = global.createTestContext('copy-tag');
-		helpers = context.helpers;
-
-		// Copy .env file if it exists
-		const mainEnvPath = join(process.cwd(), '.env');
-		const testEnvPath = join(testDir, '.env');
-		if (existsSync(mainEnvPath)) {
-			const envContent = readFileSync(mainEnvPath, 'utf8');
-			writeFileSync(testEnvPath, envContent);
-		}
-
-		// Copy configuration files
-		copyConfigFiles(testDir);
-
-		// Initialize task-master project
-		const initResult = await helpers.taskMaster('init', ['-y'], {
-			cwd: testDir
-		});
-		expect(initResult).toHaveExitCode(0);
-
-		// Ensure tasks.json exists (bug workaround)
-		const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-		if (!existsSync(tasksJsonPath)) {
-			mkdirSync(join(testDir, '.taskmaster/tasks'), { recursive: true });
-			writeFileSync(tasksJsonPath, JSON.stringify({ master: { tasks: [] } }));
-		}
-	});
-
-	afterEach(() => {
-		// Clean up test directory
-		if (testDir && existsSync(testDir)) {
-			rmSync(testDir, { recursive: true, force: true });
-		}
-	});
-
-	describe('Basic copying', () => {
-		it('should copy an existing tag with all its tasks', async () => {
-			// Create a tag with tasks
-			await helpers.taskMaster(
-				'add-tag',
-				['feature', '--description', 'Feature branch'],
-				{ cwd: testDir }
-			);
-			await helpers.taskMaster('use-tag', ['feature'], { cwd: testDir });
-
-			// Add tasks to feature tag
-			const task1 = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Feature task 1', '--description', 'First task in feature'],
-				{ cwd: testDir }
-			);
-			const taskId1 = helpers.extractTaskId(task1.stdout);
-			const task2 = await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'Feature task 2',
-					'--description',
-					'Second task in feature'
-				],
-				{ cwd: testDir }
-			);
-			const taskId2 = helpers.extractTaskId(task2.stdout);
-
-			// Switch to master and add a task
-			await helpers.taskMaster('use-tag', ['master'], { cwd: testDir });
-			const task3 = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Master task', '--description', 'Task only in master'],
-				{ cwd: testDir }
-			);
-			const taskId3 = helpers.extractTaskId(task3.stdout);
-
-			// Copy the feature tag
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['feature', 'feature-backup'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully copied tag');
-			expect(result.stdout).toContain('feature');
-			expect(result.stdout).toContain('feature-backup');
-			// The output has a single space after the colon in the formatted box
-			expect(result.stdout).toMatch(/Tasks Copied:\s*2/);
-
-			// Verify the new tag exists
-			const tagsResult = await helpers.taskMaster('tags', [], { cwd: testDir });
-			expect(tagsResult.stdout).toContain('feature');
-			expect(tagsResult.stdout).toContain('feature-backup');
-
-			// Verify tasks are in the new tag
-			await helpers.taskMaster('use-tag', ['feature-backup'], { cwd: testDir });
-			const listResult = await helpers.taskMaster('list', [], { cwd: testDir });
-			// Just verify we have 2 tasks copied
-			expect(listResult.stdout).toContain('Pending: 2');
-			// Verify we're showing tasks (the table has task IDs)
-			expect(listResult.stdout).toContain('│ 1  │');
-			expect(listResult.stdout).toContain('│ 2  │');
-		});
-
-		it('should copy tag with custom description', async () => {
-			await helpers.taskMaster(
-				'add-tag',
-				['original', '--description', 'Original description'],
-				{ cwd: testDir }
-			);
-
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['original', 'copy', '--description', 'Custom copy description'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-
-			// Verify description in metadata
-			const tagsResult = await helpers.taskMaster('tags', ['--show-metadata'], {
-				cwd: testDir
-			});
-			expect(tagsResult.stdout).toContain('copy');
-			// The table truncates descriptions, so just check for 'Custom'
-			expect(tagsResult.stdout).toContain('Custom');
-		});
-	});
-
-	describe('Error handling', () => {
-		it('should fail when copying non-existent tag', async () => {
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['nonexistent', 'new-tag'],
-				{
-					cwd: testDir,
-					allowFailure: true
-				}
-			);
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('not exist');
-		});
-
-		it('should fail when target tag already exists', async () => {
-			await helpers.taskMaster('add-tag', ['existing'], { cwd: testDir });
-
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['master', 'existing'],
-				{
-					cwd: testDir,
-					allowFailure: true
-				}
-			);
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('already exists');
-		});
-
-		it('should validate tag name format', async () => {
-			await helpers.taskMaster('add-tag', ['source'], { cwd: testDir });
-
-			// Try invalid tag names
-			const invalidNames = [
-				'tag with spaces',
-				'tag/with/slashes',
-				'tag@with@special'
-			];
-
-			for (const invalidName of invalidNames) {
-				const result = await helpers.taskMaster(
-					'copy-tag',
-					['source', `"${invalidName}"`],
-					{
-						cwd: testDir,
-						allowFailure: true
-					}
-				);
-				expect(result.exitCode).not.toBe(0);
-				// The error should mention valid characters
-				expect(result.stderr).toContain(
-					'letters, numbers, hyphens, and underscores'
-				);
-			}
-		});
-	});
-
-	describe('Special cases', () => {
-		it('should copy master tag successfully', async () => {
-			// Add tasks to master
-			const task1 = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Master task 1', '--description', 'First task'],
-				{ cwd: testDir }
-			);
-			const task2 = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Master task 2', '--description', 'Second task'],
-				{ cwd: testDir }
-			);
-
-			// Copy master tag
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['master', 'master-backup'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully copied tag');
-			// The output has a single space after the colon in the formatted box
-			expect(result.stdout).toMatch(/Tasks Copied:\s*2/);
-
-			// Verify both tags exist
-			const tagsResult = await helpers.taskMaster('tags', [], { cwd: testDir });
-			expect(tagsResult.stdout).toContain('master');
-			expect(tagsResult.stdout).toContain('master-backup');
-		});
-
-		it('should handle tag with no tasks', async () => {
-			// Create empty tag
-			await helpers.taskMaster(
-				'add-tag',
-				['empty', '--description', 'Empty tag'],
-				{ cwd: testDir }
-			);
-
-			// Copy the empty tag
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['empty', 'empty-copy'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully copied tag');
-			// The output has a single space after the colon in the formatted box
-			expect(result.stdout).toMatch(/Tasks Copied:\s*0/);
-
-			// Verify copy exists
-			const tagsResult = await helpers.taskMaster('tags', [], { cwd: testDir });
-			expect(tagsResult.stdout).toContain('empty');
-			expect(tagsResult.stdout).toContain('empty-copy');
-		});
-
-		it('should create tag with same name but different case', async () => {
-			await helpers.taskMaster('add-tag', ['feature'], { cwd: testDir });
-
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['feature', 'FEATURE'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully copied tag');
-
-			// Verify both tags exist
-			const tagsResult = await helpers.taskMaster('tags', [], { cwd: testDir });
-			expect(tagsResult.stdout).toContain('feature');
-			expect(tagsResult.stdout).toContain('FEATURE');
-		});
-	});
-
-	describe('Tasks with subtasks', () => {
-		it('should preserve subtasks when copying', async () => {
-			// Create tag with task that has subtasks
-			await helpers.taskMaster('add-tag', ['sprint'], { cwd: testDir });
-			await helpers.taskMaster('use-tag', ['sprint'], { cwd: testDir });
-
-			// Add task and expand it
-			const task = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Epic task', '--description', 'Task with subtasks'],
-				{ cwd: testDir }
-			);
-			const taskId = helpers.extractTaskId(task.stdout);
-
-			// Expand to create subtasks
-			const expandResult = await helpers.taskMaster('expand', ['-i', taskId, '-n', '3'], {
-				cwd: testDir,
-				timeout: 60000
-			});
-			expect(expandResult).toHaveExitCode(0);
-			
-			// Verify subtasks were created in the source tag
-			const verifyResult = await helpers.taskMaster('show', [taskId], { cwd: testDir });
-			if (!verifyResult.stdout.includes('Subtasks')) {
-				// If expand didn't create subtasks, add them manually
-				await helpers.taskMaster('add-subtask', ['--parent', taskId, '--title', 'Subtask 1', '--description', 'First subtask'], { cwd: testDir });
-				await helpers.taskMaster('add-subtask', ['--parent', taskId, '--title', 'Subtask 2', '--description', 'Second subtask'], { cwd: testDir });
-				await helpers.taskMaster('add-subtask', ['--parent', taskId, '--title', 'Subtask 3', '--description', 'Third subtask'], { cwd: testDir });
-			}
-
-			// Copy the tag
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['sprint', 'sprint-backup'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully copied tag');
-
-			// Verify subtasks are preserved
-			await helpers.taskMaster('use-tag', ['sprint-backup'], { cwd: testDir });
-			const showResult = await helpers.taskMaster('show', [taskId], {
-				cwd: testDir
-			});
-			expect(showResult.stdout).toContain('Epic');
-			
-			// Check if subtasks were preserved
-			if (showResult.stdout.includes('Subtasks')) {
-				// If subtasks are shown, verify they exist
-				expect(showResult.stdout).toContain('Subtasks');
-				// The subtask IDs might be numeric (1, 2, 3) instead of dot notation
-				expect(showResult.stdout).toMatch(/[1-3]/);
-			} else {
-				// If copy-tag doesn't preserve subtasks, this is a known limitation
-				console.log('Note: copy-tag command may not preserve subtasks - this could be expected behavior');
-				expect(showResult.stdout).toContain('No subtasks found');
-			}
-		});
-	});
-
-	describe('Tag metadata', () => {
-		it('should preserve original tag description by default', async () => {
-			const description = 'This is the original feature branch';
-			await helpers.taskMaster(
-				'add-tag',
-				['feature', '--description', `"${description}"`],
-				{ cwd: testDir }
-			);
-
-			// Copy without custom description
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['feature', 'feature-copy'],
-				{ cwd: testDir }
-			);
-			expect(result).toHaveExitCode(0);
-
-			// Check the copy has a default description mentioning it's a copy
-			const tagsResult = await helpers.taskMaster('tags', ['--show-metadata'], {
-				cwd: testDir
-			});
-			expect(tagsResult.stdout).toContain('feature-copy');
-			// The default behavior is to create a description like "Copy of 'feature' created on ..."
-			expect(tagsResult.stdout).toContain('Copy of');
-			expect(tagsResult.stdout).toContain('feature');
-		});
-
-		it('should set creation date for new tag', async () => {
-			await helpers.taskMaster('add-tag', ['source'], { cwd: testDir });
-
-			// Copy the tag
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['source', 'destination'],
-				{ cwd: testDir }
-			);
-			expect(result).toHaveExitCode(0);
-
-			// Check metadata shows creation date
-			const tagsResult = await helpers.taskMaster('tags', ['--show-metadata'], {
-				cwd: testDir
-			});
-			expect(tagsResult.stdout).toContain('destination');
-			// Should show date in format like MM/DD/YYYY or YYYY-MM-DD
-			const datePattern = /\d{1,2}\/\d{1,2}\/\d{4}|\d{4}-\d{2}-\d{2}/;
-			expect(tagsResult.stdout).toMatch(datePattern);
-		});
-	});
-
-	describe('Cross-tag operations', () => {
-		it('should handle tasks that belong to multiple tags', async () => {
-			// Create two tags
-			await helpers.taskMaster('add-tag', ['feature'], { cwd: testDir });
-			await helpers.taskMaster('add-tag', ['bugfix'], { cwd: testDir });
-
-			// Add task to feature
-			await helpers.taskMaster('use-tag', ['feature'], { cwd: testDir });
-			const task1 = await helpers.taskMaster(
-				'add-task',
-				['--title', 'Shared task', '--description', 'Task in multiple tags'],
-				{ cwd: testDir }
-			);
-			const taskId = helpers.extractTaskId(task1.stdout);
-
-			// Also add it to bugfix (by switching and creating another task, then we'll test the copy behavior)
-			await helpers.taskMaster('use-tag', ['bugfix'], { cwd: testDir });
-			await helpers.taskMaster(
-				'add-task',
-				['--title', 'Bugfix only', '--description', 'Only in bugfix'],
-				{ cwd: testDir }
-			);
-
-			// Copy feature tag
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['feature', 'feature-v2'],
-				{ cwd: testDir }
-			);
-			expect(result).toHaveExitCode(0);
-
-			// Verify task is in new tag
-			await helpers.taskMaster('use-tag', ['feature-v2'], { cwd: testDir });
-			const listResult = await helpers.taskMaster('list', [], { cwd: testDir });
-			// Just verify the task is there (title may be truncated)
-			expect(listResult.stdout).toContain('Shared');
-			// Check for the pending count in the Project Dashboard - it appears after other counts
-			expect(listResult.stdout).toMatch(/Pending:\s*1/);
-		});
-	});
-
-	describe('Output format', () => {
-		it('should provide clear success message', async () => {
-			await helpers.taskMaster('add-tag', ['dev'], { cwd: testDir });
-
-			// Add some tasks
-			await helpers.taskMaster('use-tag', ['dev'], { cwd: testDir });
-			await helpers.taskMaster(
-				'add-task',
-				['--title', 'Task 1', '--description', 'First'],
-				{ cwd: testDir }
-			);
-			await helpers.taskMaster(
-				'add-task',
-				['--title', 'Task 2', '--description', 'Second'],
-				{ cwd: testDir }
-			);
-
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['dev', 'dev-backup'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully copied tag');
-			expect(result.stdout).toContain('dev');
-			expect(result.stdout).toContain('dev-backup');
-			// The output has a single space after the colon in the formatted box
-			expect(result.stdout).toMatch(/Tasks Copied:\s*2/);
-		});
-
-		it('should handle verbose output if supported', async () => {
-			await helpers.taskMaster('add-tag', ['test'], { cwd: testDir });
-
-			// Try with potential verbose flag (if supported)
-			const result = await helpers.taskMaster(
-				'copy-tag',
-				['test', 'test-copy'],
-				{ cwd: testDir }
-			);
-
-			// Basic success is enough
-			expect(result).toHaveExitCode(0);
-		});
-	});
-});

tests/e2e/tests/commands/delete-tag.test.js

@@ -1,529 +0,0 @@
-/**
- * Comprehensive E2E tests for delete-tag command
- * Tests all aspects of tag deletion including safeguards and edge cases
- */
-
-import { describe, it, expect, beforeEach, afterEach } from '@jest/globals';
-import {
-	mkdtempSync,
-	existsSync,
-	readFileSync,
-	rmSync,
-	writeFileSync,
-	mkdirSync
-} from 'fs';
-import { join } from 'path';
-import { tmpdir } from 'os';
-
-describe('delete-tag command', () => {
-	let testDir;
-	let helpers;
-
-	beforeEach(async () => {
-		// Create test directory
-		testDir = mkdtempSync(join(tmpdir(), 'task-master-delete-tag-'));
-
-		// Initialize test helpers
-		const context = global.createTestContext('delete-tag');
-		helpers = context.helpers;
-
-		// Copy .env file if it exists
-		const mainEnvPath = join(process.cwd(), '.env');
-		const testEnvPath = join(testDir, '.env');
-		if (existsSync(mainEnvPath)) {
-			const envContent = readFileSync(mainEnvPath, 'utf8');
-			writeFileSync(testEnvPath, envContent);
-		}
-
-		// Initialize task-master project
-		const initResult = await helpers.taskMaster('init', ['-y'], {
-			cwd: testDir
-		});
-		expect(initResult).toHaveExitCode(0);
-
-		// Ensure tasks.json exists (bug workaround)
-		const tasksJsonPath = join(testDir, '.taskmaster/tasks/tasks.json');
-		if (!existsSync(tasksJsonPath)) {
-			mkdirSync(join(testDir, '.taskmaster/tasks'), { recursive: true });
-			writeFileSync(tasksJsonPath, JSON.stringify({ master: { tasks: [] } }));
-		}
-	});
-
-	afterEach(() => {
-		// Clean up test directory
-		if (testDir && existsSync(testDir)) {
-			rmSync(testDir, { recursive: true, force: true });
-		}
-	});
-
-	describe('Basic tag deletion', () => {
-		it('should delete an existing tag with confirmation bypass', async () => {
-			// Create a new tag
-			const addTagResult = await helpers.taskMaster(
-				'add-tag',
-				['feature-xyz', '--description', 'Feature branch for XYZ'],
-				{ cwd: testDir }
-			);
-			expect(addTagResult).toHaveExitCode(0);
-
-			// Delete the tag with --yes flag
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['feature-xyz', '--yes'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully deleted tag "feature-xyz"');
-			expect(result.stdout).toContain('✓ Tag Deleted Successfully');
-
-			// Verify tag is deleted by listing tags
-			const listResult = await helpers.taskMaster('tags', [], { cwd: testDir });
-			expect(listResult.stdout).not.toContain('feature-xyz');
-		});
-
-		it('should delete a tag with tasks', async () => {
-			// Create a new tag
-			await helpers.taskMaster(
-				'add-tag',
-				['temp-feature', '--description', 'Temporary feature'],
-				{ cwd: testDir }
-			);
-
-			// Switch to the new tag
-			await helpers.taskMaster('use-tag', ['temp-feature'], { cwd: testDir });
-
-			// Add some tasks to the tag
-			const task1Result = await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'"Task 1"',
-					'--description',
-					'"First task in temp-feature"'
-				],
-				{ cwd: testDir }
-			);
-			expect(task1Result).toHaveExitCode(0);
-
-			const task2Result = await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'"Task 2"',
-					'--description',
-					'"Second task in temp-feature"'
-				],
-				{ cwd: testDir }
-			);
-			expect(task2Result).toHaveExitCode(0);
-
-			// Verify tasks were created by listing them
-			const listResult = await helpers.taskMaster(
-				'list',
-				['--tag', 'temp-feature'],
-				{ cwd: testDir }
-			);
-			expect(listResult.stdout).toContain('Task 1');
-			expect(listResult.stdout).toContain('Task 2');
-
-			// Delete the tag while it's current
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['temp-feature', '--yes'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toMatch(/Tasks Deleted:\s*2/);
-			expect(result.stdout).toContain('Switched current tag to "master"');
-
-			// Verify we're on master tag
-			const showResult = await helpers.taskMaster('show', [], { cwd: testDir });
-			expect(showResult.stdout).toContain('🏷️ tag: master');
-		});
-	});
-
-	describe('Error cases', () => {
-		it('should fail when deleting non-existent tag', async () => {
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['non-existent-tag', '--yes'],
-				{ cwd: testDir, allowFailure: true }
-			);
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('Tag "non-existent-tag" does not exist');
-		});
-
-		it('should fail when trying to delete master tag', async () => {
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['master', '--yes'],
-				{ cwd: testDir, allowFailure: true }
-			);
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('Cannot delete the "master" tag');
-		});
-
-		it('should fail with invalid tag name', async () => {
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['invalid/tag/name', '--yes'],
-				{ cwd: testDir, allowFailure: true }
-			);
-
-			expect(result.exitCode).not.toBe(0);
-			// The error might come from not finding the tag or invalid name
-			expect(result.stderr).toMatch(/does not exist|invalid/i);
-		});
-
-		it('should fail when no tag name is provided', async () => {
-			const result = await helpers.taskMaster('delete-tag', [], {
-				cwd: testDir,
-				allowFailure: true
-			});
-
-			expect(result.exitCode).not.toBe(0);
-			expect(result.stderr).toContain('required');
-		});
-	});
-
-	describe('Interactive confirmation flow', () => {
-		it('should require confirmation without --yes flag', async () => {
-			// Create a tag
-			await helpers.taskMaster('add-tag', ['interactive-test'], {
-				cwd: testDir
-			});
-
-			// Try to delete without --yes flag
-			// Since this would require interactive input, we expect it to fail or timeout
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['interactive-test'],
-				{ cwd: testDir, allowFailure: true, timeout: 2000 }
-			);
-
-			// Check what happened
-			if (result.stdout.includes('Successfully deleted')) {
-				// If delete succeeded without confirmation, skip the test
-				// as the feature may not be implemented
-				console.log(
-					'Interactive confirmation may not be implemented - tag was deleted without --yes flag'
-				);
-				expect(true).toBe(true); // Pass the test with a note
-			} else {
-				// If the command failed or timed out, tag should still exist
-				expect(result.exitCode).not.toBe(0);
-				const tagsResult = await helpers.taskMaster('tags', [], {
-					cwd: testDir
-				});
-				expect(tagsResult.stdout).toContain('interactive-test');
-			}
-		});
-	});
-
-	describe('Current tag handling', () => {
-		it('should switch to master when deleting the current tag', async () => {
-			// Create and switch to a new tag
-			await helpers.taskMaster('add-tag', ['current-feature'], {
-				cwd: testDir
-			});
-			await helpers.taskMaster('use-tag', ['current-feature'], {
-				cwd: testDir
-			});
-
-			// Add a task to verify we're on the current tag
-			await helpers.taskMaster(
-				'add-task',
-				['--title', '"Task in current feature"'],
-				{ cwd: testDir }
-			);
-
-			// Delete the current tag
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['current-feature', '--yes'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Switched current tag to "master"');
-
-			// Verify we're on master tag
-			const currentTagResult = await helpers.taskMaster('tags', [], {
-				cwd: testDir
-			});
-			expect(currentTagResult.stdout).toMatch(/●\s*master\s*\(current\)/);
-		});
-
-		it('should not switch tags when deleting a non-current tag', async () => {
-			// Create two tags
-			await helpers.taskMaster('add-tag', ['feature-a'], { cwd: testDir });
-			await helpers.taskMaster('add-tag', ['feature-b'], { cwd: testDir });
-
-			// Switch to feature-a
-			await helpers.taskMaster('use-tag', ['feature-a'], { cwd: testDir });
-
-			// Delete feature-b (not current)
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['feature-b', '--yes'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).not.toContain('Switched current tag');
-
-			// Verify we're still on feature-a
-			const currentTagResult = await helpers.taskMaster('tags', [], {
-				cwd: testDir
-			});
-			expect(currentTagResult.stdout).toMatch(/●\s*feature-a\s*\(current\)/);
-		});
-	});
-
-	describe('Tag with complex data', () => {
-		it('should delete tag with subtasks and dependencies', async () => {
-			// Create a tag with complex task structure
-			await helpers.taskMaster('add-tag', ['complex-feature'], {
-				cwd: testDir
-			});
-			await helpers.taskMaster('use-tag', ['complex-feature'], {
-				cwd: testDir
-			});
-
-			// Add parent task
-			const parentResult = await helpers.taskMaster(
-				'add-task',
-				['--title', '"Parent task"', '--description', '"Has subtasks"'],
-				{ cwd: testDir }
-			);
-			const parentId = helpers.extractTaskId(parentResult.stdout);
-
-			// Add subtasks
-			await helpers.taskMaster(
-				'add-subtask',
-				['--parent', parentId, '--title', '"Subtask 1"'],
-				{ cwd: testDir }
-			);
-			await helpers.taskMaster(
-				'add-subtask',
-				['--parent', parentId, '--title', '"Subtask 2"'],
-				{ cwd: testDir }
-			);
-
-			// Add task with dependencies
-			const depResult = await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'"Dependent task"',
-					'--description',
-					'"Task that depends on parent"',
-					'--dependencies',
-					parentId
-				],
-				{ cwd: testDir }
-			);
-			expect(depResult).toHaveExitCode(0);
-
-			// Delete the tag
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['complex-feature', '--yes'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			// Check that tasks were deleted - actual count may vary depending on implementation
-			expect(result.stdout).toMatch(/Tasks Deleted:\s*\d+/);
-			expect(result.stdout).toContain(
-				'Successfully deleted tag "complex-feature"'
-			);
-		});
-
-		it('should handle tag with many tasks efficiently', async () => {
-			// Create a tag
-			await helpers.taskMaster('add-tag', ['bulk-feature'], { cwd: testDir });
-			await helpers.taskMaster('use-tag', ['bulk-feature'], { cwd: testDir });
-
-			// Add many tasks
-			const taskCount = 10;
-			for (let i = 1; i <= taskCount; i++) {
-				await helpers.taskMaster(
-					'add-task',
-					[
-						'--title',
-						`Task ${i}`,
-						'--description',
-						`Description for task ${i}`
-					],
-					{ cwd: testDir }
-				);
-			}
-
-			// Delete the tag
-			const startTime = Date.now();
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['bulk-feature', '--yes'],
-				{ cwd: testDir }
-			);
-			const endTime = Date.now();
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toMatch(new RegExp(`Tasks Deleted:\\s*${taskCount}`));
-
-			// Should complete within reasonable time (5 seconds)
-			expect(endTime - startTime).toBeLessThan(5000);
-		});
-	});
-
-	describe('File path handling', () => {
-		it('should work with custom tasks file path', async () => {
-			// Create custom tasks file with a tag
-			const customPath = join(testDir, 'custom-tasks.json');
-			writeFileSync(
-				customPath,
-				JSON.stringify({
-					master: { tasks: [] },
-					'custom-tag': {
-						tasks: [
-							{
-								id: 1,
-								title: 'Task in custom tag',
-								status: 'pending'
-							}
-						],
-						metadata: {
-							created: new Date().toISOString(),
-							description: 'Custom tag'
-						}
-					}
-				})
-			);
-
-			// Delete tag from custom file
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['custom-tag', '--yes', '--file', customPath],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain('Successfully deleted tag "custom-tag"');
-
-			// Verify tag is deleted from custom file
-			const fileContent = JSON.parse(readFileSync(customPath, 'utf8'));
-			expect(fileContent['custom-tag']).toBeUndefined();
-			expect(fileContent.master).toBeDefined();
-		});
-	});
-
-	describe('Edge cases', () => {
-		it('should handle empty tag gracefully', async () => {
-			// Create an empty tag
-			await helpers.taskMaster('add-tag', ['empty-tag'], { cwd: testDir });
-
-			// Delete the empty tag
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['empty-tag', '--yes'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toMatch(/Tasks Deleted:\s*0/);
-		});
-
-		it('should handle special characters in tag names', async () => {
-			// Create tag with hyphens and numbers
-			const tagName = 'feature-123-test';
-			await helpers.taskMaster('add-tag', [tagName], { cwd: testDir });
-
-			// Delete it
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				[tagName, '--yes'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-			expect(result.stdout).toContain(`Successfully deleted tag "${tagName}"`);
-		});
-
-		it('should preserve other tags when deleting one', async () => {
-			// Create multiple tags
-			await helpers.taskMaster('add-tag', ['keep-me-1'], { cwd: testDir });
-			await helpers.taskMaster('add-tag', ['delete-me'], { cwd: testDir });
-			await helpers.taskMaster('add-tag', ['keep-me-2'], { cwd: testDir });
-
-			// Add tasks to each
-			await helpers.taskMaster('use-tag', ['keep-me-1'], { cwd: testDir });
-			await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'"Task in keep-me-1"',
-					'--description',
-					'"Description for keep-me-1"'
-				],
-				{ cwd: testDir }
-			);
-
-			await helpers.taskMaster('use-tag', ['delete-me'], { cwd: testDir });
-			await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'"Task in delete-me"',
-					'--description',
-					'"Description for delete-me"'
-				],
-				{ cwd: testDir }
-			);
-
-			await helpers.taskMaster('use-tag', ['keep-me-2'], { cwd: testDir });
-			await helpers.taskMaster(
-				'add-task',
-				[
-					'--title',
-					'"Task in keep-me-2"',
-					'--description',
-					'"Description for keep-me-2"'
-				],
-				{ cwd: testDir }
-			);
-
-			// Delete middle tag
-			const result = await helpers.taskMaster(
-				'delete-tag',
-				['delete-me', '--yes'],
-				{ cwd: testDir }
-			);
-
-			expect(result).toHaveExitCode(0);
-
-			// Verify other tags still exist with their tasks
-			const tagsResult = await helpers.taskMaster('tags', [], { cwd: testDir });
-			expect(tagsResult.stdout).toContain('keep-me-1');
-			expect(tagsResult.stdout).toContain('keep-me-2');
-			expect(tagsResult.stdout).not.toContain('delete-me');
-
-			// Verify tasks in other tags are preserved
-			await helpers.taskMaster('use-tag', ['keep-me-1'], { cwd: testDir });
-			const list1 = await helpers.taskMaster('list', ['--tag', 'keep-me-1'], {
-				cwd: testDir
-			});
-			expect(list1.stdout).toContain('Task in keep-me-1');
-
-			await helpers.taskMaster('use-tag', ['keep-me-2'], { cwd: testDir });
-			const list2 = await helpers.taskMaster('list', ['--tag', 'keep-me-2'], {
-				cwd: testDir
-			});
-			expect(list2.stdout).toContain('Task in keep-me-2');
-		});
-	});
-});