fix: improve ollama object to telemetry structure

.changeset/beige-doodles-type.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Resolve all issues related to MCP

.changeset/config.json

@@ -2,16 +2,13 @@
   "$schema": "https://unpkg.com/@changesets/config@3.1.1/schema.json",
   "changelog": [
     "@changesets/changelog-github",
-    {
-      "repo": "eyaltoledano/claude-task-master"
-    }
+    { "repo": "eyaltoledano/claude-task-master" }
   ],
   "commit": false,
   "fixed": [],
+  "linked": [],
   "access": "public",
   "baseBranch": "main",
-  "ignore": [
-    "docs",
-    "@tm/claude-code-plugin"
-  ]
-}
+  "updateInternalDependencies": "patch",
+  "ignore": []
+}

.changeset/dirty-hairs-know.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Improve auth token refresh flow

.changeset/fix-parent-directory-traversal.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": patch
----
-
-Enable Task Master commands to traverse parent directories to find project root from nested paths
-
-Fixes #1301

.changeset/fix-warning-box-alignment.md

@@ -1,5 +0,0 @@
----
-"@tm/cli": patch
----
-
-Fix warning message box width to match dashboard box width for consistent UI alignment

.changeset/floppy-plants-marry.md

@@ -0,0 +1,9 @@
+---
+'task-master-ai': patch
+---
+
+Fix CLI --force flag for parse-prd command
+
+Previously, the --force flag was not respected when running `parse-prd`, causing the command to prompt for confirmation or fail even when --force was provided. This patch ensures that the flag is correctly passed and handled, allowing users to overwrite existing tasks.json files as intended.
+
+- Fixes #477

.changeset/forty-plums-stay.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': minor
+---
+
+.taskmasterconfig now supports a baseUrl field per model role (main, research, fallback), allowing endpoint overrides for any provider.

.changeset/free-bikes-smile.md

@@ -0,0 +1,11 @@
+---
+'task-master-ai': minor
+---
+
+Add Ollama as a supported AI provider.
+
+- You can now add it by running `task-master models --setup` and selecting it.
+- Ollama is a local model provider, so no API key is required.
+- Ollama models are available at `http://localhost:11434/api` by default.
+- You can change the default URL by setting the `OLLAMA_BASE_URL` environment variable or by adding a `baseUrl` property to the `ollama` model role in `.taskmasterconfig`.
+  - If you want to use a custom API key, you can set it in the `OLLAMA_API_KEY` environment variable.   

.changeset/kind-lines-melt.md

@@ -1,21 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix MCP server compatibility with Draft-07 clients (Augment IDE, gemini-cli, gemini code assist)
-
-- Resolves #1284
-
-**Problem:**
-
-- MCP tools were using Zod v4, which outputs JSON Schema Draft 2020-12
-- MCP clients only support Draft-07
-- Tools were not discoverable in gemini-cli and other clients
-
-**Solution:**
-
-- Updated all MCP tools to import from `zod/v3` instead of `zod`
-- Zod v3 schemas convert to Draft-07 via FastMCP's zod-to-json-schema
-- Fixed logger to use stderr instead of stdout (MCP protocol requirement)
-
-This is a temporary workaround until FastMCP adds JSON Schema version configuration.

.changeset/light-owls-stay.md

@@ -1,35 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add configurable MCP tool loading to optimize LLM context usage
-
-You can now control which Task Master MCP tools are loaded by setting the `TASK_MASTER_TOOLS` environment variable in your MCP configuration. This helps reduce context usage for LLMs by only loading the tools you need.
-
-**Configuration Options:**
-
-- `all` (default): Load all 36 tools
-- `core` or `lean`: Load only 7 essential tools for daily development
-  - Includes: `get_tasks`, `next_task`, `get_task`, `set_task_status`, `update_subtask`, `parse_prd`, `expand_task`
-- `standard`: Load 15 commonly used tools (all core tools plus 8 more)
-  - Additional tools: `initialize_project`, `analyze_project_complexity`, `expand_all`, `add_subtask`, `remove_task`, `generate`, `add_task`, `complexity_report`
-- Custom list: Comma-separated tool names (e.g., `get_tasks,next_task,set_task_status`)
-
-**Example .mcp.json configuration:**
-
-```json
-{
-  "mcpServers": {
-    "task-master-ai": {
-      "command": "npx",
-      "args": ["-y", "task-master-ai"],
-      "env": {
-        "TASK_MASTER_TOOLS": "standard",
-        "ANTHROPIC_API_KEY": "your_key_here"
-      }
-    }
-  }
-}
-```
-
-For complete details on all available tools, configuration examples, and usage guidelines, see the [MCP Tools documentation](https://docs.task-master.dev/capabilities/mcp#configurable-tool-loading).

.changeset/many-wasps-sell.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Task Master no longer tells you to update when you're already up to date

.changeset/metal-rocks-help.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": minor
----
-
-Improve next command to work with remote

.changeset/nice-lies-cover.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Adds costs information to AI commands using input/output tokens and model costs.

.changeset/open-tips-notice.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add 4.5 haiku and sonnet to supported models for claude-code and anthropic ai providers

.changeset/pre.json

@@ -1,22 +1,26 @@
 {
-  "mode": "pre",
+  "mode": "exit",
   "tag": "rc",
   "initialVersions": {
-    "task-master-ai": "0.29.0",
-    "@tm/cli": "",
-    "docs": "0.0.6",
-    "extension": "0.25.6",
-    "@tm/mcp": "0.28.0-rc.2",
-    "@tm/ai-sdk-provider-grok-cli": "",
-    "@tm/build-config": "",
-    "@tm/claude-code-plugin": "0.0.2",
-    "@tm/core": ""
+    "task-master-ai": "0.14.0-rc.0"
   },
   "changesets": [
-    "dirty-hairs-know",
-    "fix-parent-directory-traversal",
-    "fix-warning-box-alignment",
-    "light-owls-stay",
-    "metal-rocks-help"
+    "beige-doodles-type",
+    "floppy-plants-marry",
+    "forty-plums-stay",
+    "free-bikes-smile",
+    "many-wasps-sell",
+    "nice-lies-cover",
+    "red-oranges-attend",
+    "red-suns-wash",
+    "sharp-dingos-melt",
+    "six-cloths-happen",
+    "slow-singers-swim",
+    "small-toys-fly",
+    "social-masks-fold",
+    "soft-zoos-flow",
+    "ten-ways-mate",
+    "tricky-wombats-spend",
+    "wide-eyes-relax"
   ]
 }

.changeset/red-oranges-attend.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Fix ERR_MODULE_NOT_FOUND when trying to run MCP Server

.changeset/red-suns-wash.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Add src directory to exports

.changeset/sharp-dingos-melt.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Fix the error handling of task status settings

.changeset/six-cloths-happen.md

@@ -0,0 +1,7 @@
+---
+'task-master-ai': patch
+---
+
+Remove caching layer from MCP direct functions for task listing, next task, and complexity report
+
+- Fixes issues users where having where they were getting stale data

.changeset/slow-singers-swim.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Fix for issue #409 LOG_LEVEL Pydantic validation error

.changeset/small-toys-fly.md

@@ -0,0 +1,7 @@
+---
+'task-master-ai': patch
+---
+
+Small fixes
+    - `next` command no longer incorrectly suggests that subtasks be broken down into subtasks in the CLI
+    - fixes the `append` flag so it properly works in the CLI

.changeset/social-masks-fold.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': minor
+---
+
+Display task complexity scores in task lists, next task, and task details views.

.changeset/soft-zoos-flow.md

@@ -0,0 +1,7 @@
+---
+'task-master-ai': patch
+---
+
+Fix initial .env.example to work out of the box
+
+- Closes #419

.changeset/some-dodos-wonder.md

@@ -1,36 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add autonomous TDD workflow automation system with new `tm autopilot` commands and MCP tools for AI-driven test-driven development.
-
-**New CLI Commands:**
-
-- `tm autopilot start <taskId>` - Initialize TDD workflow
-- `tm autopilot next` - Get next action in workflow
-- `tm autopilot status` - Check workflow progress
-- `tm autopilot complete` - Advance phase with test results
-- `tm autopilot commit` - Save progress with metadata
-- `tm autopilot resume` - Continue from checkpoint
-- `tm autopilot abort` - Cancel workflow
-
-**New MCP Tools:**
-Seven new autopilot tools for programmatic control: `autopilot_start`, `autopilot_next`, `autopilot_status`, `autopilot_complete_phase`, `autopilot_commit`, `autopilot_resume`, `autopilot_abort`
-
-**Features:**
-
-- Complete RED → GREEN → COMMIT cycle enforcement
-- Intelligent commit message generation with metadata
-- Activity logging and state persistence
-- Configurable workflow settings via `.taskmaster/config.json`
-- Comprehensive AI agent integration documentation
-
-**Documentation:**
-
-- AI Agent Integration Guide (2,800+ lines)
-- TDD Quick Start Guide
-- Example prompts and integration patterns
-
-> **Learn more:** [TDD Workflow Quickstart Guide](https://dev.task-master.dev/tdd-workflow/quickstart)
-
-This release enables AI agents to autonomously execute test-driven development workflows with full state management and recovery capabilities.

.changeset/ten-ways-mate.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Fix default fallback model and maxTokens in Taskmaster initialization

.changeset/tricky-wombats-spend.md

@@ -0,0 +1,5 @@
+---
+'task-master-ai': patch
+---
+
+Fix bug when updating tasks on the MCP server (#412)

.changeset/wide-eyes-relax.md

@@ -0,0 +1,11 @@
+---
+'task-master-ai': patch
+---
+
+Fix duplicate output on CLI help screen
+
+- Prevent the Task Master CLI from printing the help screen more than once when using `-h` or `--help`.
+- Removed redundant manual event handlers and guards for help output; now only the Commander `.helpInformation` override is used for custom help.
+- Simplified logic so that help is only shown once for both "no arguments" and help flag flows.
+- Ensures a clean, branded help experience with no repeated content.
+- Fixes #339

.claude-plugin/marketplace.json

@@ -1,32 +0,0 @@
-{
-	"name": "taskmaster",
-	"owner": {
-		"name": "Hamster",
-		"email": "ralph@tryhamster.com"
-	},
-	"metadata": {
-		"description": "Official marketplace for Taskmaster AI - AI-powered task management for ambitious development",
-		"version": "1.0.0"
-	},
-	"plugins": [
-		{
-			"name": "taskmaster",
-			"source": "./packages/claude-code-plugin",
-			"description": "AI-powered task management system for ambitious development workflows with intelligent orchestration, complexity analysis, and automated coordination",
-			"author": {
-				"name": "Hamster"
-			},
-			"homepage": "https://github.com/eyaltoledano/claude-task-master",
-			"repository": "https://github.com/eyaltoledano/claude-task-master",
-			"keywords": [
-				"task-management",
-				"ai",
-				"workflow",
-				"orchestration",
-				"automation",
-				"mcp"
-			],
-			"category": "productivity"
-		}
-	]
-}

.claude/TM_COMMANDS_GUIDE.md

@@ -1,147 +0,0 @@
-# Task Master Commands for Claude Code
-
-Complete guide to using Task Master through Claude Code's slash commands.
-
-## Overview
-
-All Task Master functionality is available through the `/project:tm/` namespace with natural language support and intelligent features.
-
-## Quick Start
-
-```bash
-# Install Task Master
-/project:tm/setup/quick-install
-
-# Initialize project
-/project:tm/init/quick
-
-# Parse requirements
-/project:tm/parse-prd requirements.md
-
-# Start working
-/project:tm/next
-```
-
-## Command Structure
-
-Commands are organized hierarchically to match Task Master's CLI:
-- Main commands at `/project:tm/[command]`
-- Subcommands for specific operations `/project:tm/[command]/[subcommand]`
-- Natural language arguments accepted throughout
-
-## Complete Command Reference
-
-### Setup & Configuration
-- `/project:tm/setup/install` - Full installation guide
-- `/project:tm/setup/quick-install` - One-line install
-- `/project:tm/init` - Initialize project
-- `/project:tm/init/quick` - Quick init with -y
-- `/project:tm/models` - View AI config
-- `/project:tm/models/setup` - Configure AI
-
-### Task Generation
-- `/project:tm/parse-prd` - Generate from PRD
-- `/project:tm/parse-prd/with-research` - Enhanced parsing
-- `/project:tm/generate` - Create task files
-
-### Task Management
-- `/project:tm/list` - List with natural language filters
-- `/project:tm/list/with-subtasks` - Hierarchical view
-- `/project:tm/list/by-status <status>` - Filter by status
-- `/project:tm/show <id>` - Task details
-- `/project:tm/add-task` - Create task
-- `/project:tm/update` - Update tasks
-- `/project:tm/remove-task` - Delete task
-
-### Status Management
-- `/project:tm/set-status/to-pending <id>`
-- `/project:tm/set-status/to-in-progress <id>`
-- `/project:tm/set-status/to-done <id>`
-- `/project:tm/set-status/to-review <id>`
-- `/project:tm/set-status/to-deferred <id>`
-- `/project:tm/set-status/to-cancelled <id>`
-
-### Task Analysis
-- `/project:tm/analyze-complexity` - AI analysis
-- `/project:tm/complexity-report` - View report
-- `/project:tm/expand <id>` - Break down task
-- `/project:tm/expand/all` - Expand all complex
-
-### Dependencies
-- `/project:tm/add-dependency` - Add dependency
-- `/project:tm/remove-dependency` - Remove dependency
-- `/project:tm/validate-dependencies` - Check issues
-- `/project:tm/fix-dependencies` - Auto-fix
-
-### Workflows
-- `/project:tm/workflows/smart-flow` - Adaptive workflows
-- `/project:tm/workflows/pipeline` - Chain commands
-- `/project:tm/workflows/auto-implement` - AI implementation
-
-### Utilities
-- `/project:tm/status` - Project dashboard
-- `/project:tm/next` - Next task recommendation
-- `/project:tm/utils/analyze` - Project analysis
-- `/project:tm/learn` - Interactive help
-
-## Key Features
-
-### Natural Language Support
-All commands understand natural language:
-```
-/project:tm/list pending high priority
-/project:tm/update mark 23 as done
-/project:tm/add-task implement OAuth login
-```
-
-### Smart Context
-Commands analyze project state and provide intelligent suggestions based on:
-- Current task status
-- Dependencies
-- Team patterns
-- Project phase
-
-### Visual Enhancements
-- Progress bars and indicators
-- Status badges
-- Organized displays
-- Clear hierarchies
-
-## Common Workflows
-
-### Daily Development
-```
-/project:tm/workflows/smart-flow morning
-/project:tm/next
-/project:tm/set-status/to-in-progress <id>
-/project:tm/set-status/to-done <id>
-```
-
-### Task Breakdown
-```
-/project:tm/show <id>
-/project:tm/expand <id>
-/project:tm/list/with-subtasks
-```
-
-### Sprint Planning
-```
-/project:tm/analyze-complexity
-/project:tm/workflows/pipeline init → expand/all → status
-```
-
-## Migration from Old Commands
-
-| Old | New |
-|-----|-----|
-| `/project:task-master:list` | `/project:tm/list` |
-| `/project:task-master:complete` | `/project:tm/set-status/to-done` |
-| `/project:workflows:auto-implement` | `/project:tm/workflows/auto-implement` |
-
-## Tips
-
-1. Use `/project:tm/` + Tab for command discovery
-2. Natural language is supported everywhere
-3. Commands provide smart defaults
-4. Chain commands for automation
-5. Check `/project:tm/learn` for interactive help

.claude/commands/dedupe.md

@@ -1,38 +0,0 @@
----
-allowed-tools: Bash(gh issue view:*), Bash(gh search:*), Bash(gh issue list:*), Bash(gh api:*), Bash(gh issue comment:*)
-description: Find duplicate GitHub issues
----
-
-Find up to 3 likely duplicate issues for a given GitHub issue.
-
-To do this, follow these steps precisely:
-
-1. Use an agent to check if the Github issue (a) is closed, (b) does not need to be deduped (eg. because it is broad product feedback without a specific solution, or positive feedback), or (c) already has a duplicates comment that you made earlier. If so, do not proceed.
-2. Use an agent to view a Github issue, and ask the agent to return a summary of the issue
-3. Then, launch 5 parallel agents to search Github for duplicates of this issue, using diverse keywords and search approaches, using the summary from #1
-4. Next, feed the results from #1 and #2 into another agent, so that it can filter out false positives, that are likely not actually duplicates of the original issue. If there are no duplicates remaining, do not proceed.
-5. Finally, comment back on the issue with a list of up to three duplicate issues (or zero, if there are no likely duplicates)
-
-Notes (be sure to tell this to your agents, too):
-
-- Use `gh` to interact with Github, rather than web fetch
-- Do not use other tools, beyond `gh` (eg. don't use other MCP servers, file edit, etc.)
-- Make a todo list first
-- For your comment, follow the following format precisely (assuming for this example that you found 3 suspected duplicates):
-
----
-
-Found 3 possible duplicate issues:
-
-1. <link to issue>
-2. <link to issue>
-3. <link to issue>
-
-This issue will be automatically closed as a duplicate in 3 days.
-
-- If your issue is a duplicate, please close it and 👍 the existing issue instead
-- To prevent auto-closure, add a comment or 👎 this comment
-
-🤖 Generated with \[Task Master Bot\]
-
----

.coderabbit.yaml

@@ -1,7 +0,0 @@
-reviews:
-  profile: chill
-  poem: false
-  auto_review:
-    enabled: true
-    base_branches:
-      - ".*"

.cursor/mcp.json

@@ -2,19 +2,17 @@
 	"mcpServers": {
 		"task-master-ai": {
 			"command": "node",
-			"args": ["./dist/mcp-server.js"],
+			"args": ["./mcp-server/server.js"],
 			"env": {
 				"ANTHROPIC_API_KEY": "ANTHROPIC_API_KEY_HERE",
 				"PERPLEXITY_API_KEY": "PERPLEXITY_API_KEY_HERE",
 				"OPENAI_API_KEY": "OPENAI_API_KEY_HERE",
 				"GOOGLE_API_KEY": "GOOGLE_API_KEY_HERE",
-				"GROQ_API_KEY": "GROQ_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",
-				"GITHUB_API_KEY": "GITHUB_API_KEY_HERE"
+				"OLLAMA_API_KEY": "OLLAMA_API_KEY_HERE"
 			}
 		}
 	}

.cursor/rules/architecture.mdc

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

.cursor/rules/commands.mdc

@@ -329,60 +329,6 @@ When implementing commands that delete or remove data (like `remove-task` or `re
   };
   ```
 
-## Context-Aware Command Pattern
-
-For AI-powered commands that benefit from project context, follow the research command pattern:
-
-- **Context Integration**:
-  - ✅ DO: Use `ContextGatherer` utility for multi-source context extraction
-  - ✅ DO: Support task IDs, file paths, custom context, and project tree
-  - ✅ DO: Implement fuzzy search for automatic task discovery
-  - ✅ DO: Display detailed token breakdown for transparency
-
-  ```javascript
-  // ✅ DO: Follow this pattern for context-aware commands
-  programInstance
-    .command('research')
-    .description('Perform AI-powered research queries with project context')
-    .argument('<prompt>', 'Research prompt to investigate')
-    .option('-i, --id <ids>', 'Comma-separated task/subtask IDs to include as context')
-    .option('-f, --files <paths>', 'Comma-separated file paths to include as context')
-    .option('-c, --context <text>', 'Additional custom context')
-    .option('--tree', 'Include project file tree structure')
-    .option('-d, --detail <level>', 'Output detail level: low, medium, high', 'medium')
-    .action(async (prompt, options) => {
-      // 1. Parameter validation and parsing
-      const taskIds = options.id ? parseTaskIds(options.id) : [];
-      const filePaths = options.files ? parseFilePaths(options.files) : [];
-      
-      // 2. Initialize context gatherer
-      const projectRoot = findProjectRoot() || '.';
-      const gatherer = new ContextGatherer(projectRoot, tasksPath);
-      
-      // 3. Auto-discover relevant tasks if none specified
-      if (taskIds.length === 0) {
-        const fuzzySearch = new FuzzyTaskSearch(tasksData.tasks, 'research');
-        const discoveredIds = fuzzySearch.getTaskIds(
-          fuzzySearch.findRelevantTasks(prompt)
-        );
-        taskIds.push(...discoveredIds);
-      }
-      
-      // 4. Gather context with token breakdown
-      const contextResult = await gatherer.gather({
-        tasks: taskIds,
-        files: filePaths,
-        customContext: options.context,
-        includeProjectTree: options.projectTree,
-        format: 'research',
-        includeTokenCounts: true
-      });
-      
-      // 5. Display token breakdown and execute AI call
-      // Implementation continues...
-    });
-  ```
-
 ## Error Handling
 
 - **Exception Management**:
@@ -523,7 +469,7 @@ 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('--generate', 'Regenerate task files after adding subtask')
+    .option('--skip-generate', 'Skip regenerating task files')
     .action(async (options) => {
       // Validate required parameters
       if (!options.parent) {
@@ -545,7 +491,7 @@ 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('--generate', 'Regenerate task files after removing subtask')
+    .option('--skip-generate', 'Skip regenerating task files')
     .action(async (options) => {
       // Implementation with detailed error handling
     })
@@ -633,11 +579,11 @@ 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' +
-    '  --generate                Regenerate task files after adding subtask\n\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\'\n' +
-    '  task-master add-subtask -p \'5\' -t \'Handle API Errors\' --details "Handle 401 Unauthorized.\\nHandle 500 Server Error." --generate',
+    '  task-master add-subtask -p \'5\' -t \'Handle API Errors\' --details $\'Handle 401 Unauthorized.\nHandle 500 Server Error.\'',
     { padding: 1, borderColor: 'blue', borderStyle: 'round' }
   ));
 }
@@ -652,7 +598,7 @@ 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' +
-    '  --generate          Regenerate task files after removing subtask\n\n' +
+    '  --skip-generate     Skip regenerating task files\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/context_gathering.mdc

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

.cursor/rules/dev_workflow.mdc

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

.cursor/rules/git_workflow.mdc

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

.cursor/rules/glossary.mdc

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

.cursor/rules/new_features.mdc

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

.cursor/rules/tags.mdc

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

.cursor/rules/taskmaster.mdc

@@ -11,8 +11,6 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 
 **Important:** Several MCP tools involve AI processing... The AI-powered tools include `parse_prd`, `analyze_project_complexity`, `update_subtask`, `update_task`, `update`, `expand_all`, `expand_task`, and `add_task`.
 
-**🏷️ Tagged Task Lists System:** Task Master now supports **tagged task lists** for multi-context task management. This allows you to maintain separate, isolated lists of tasks for different features, branches, or experiments. Existing projects are seamlessly migrated to use a default "master" tag. Most commands now support a `--tag <name>` flag to specify which context to operate on. If omitted, commands use the currently active tag.
-
 ---
 
 ## Initialization & Setup
@@ -26,7 +24,6 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `--name <name>`: `Set the name for your project in Taskmaster's configuration.`
     *   `--description <text>`: `Provide a brief description for your project.`
     *   `--version <version>`: `Set the initial version for your project, e.g., '0.1.0'.`
-    *   `--no-git`: `Skip initializing a Git repository entirely.`
     *   `-y, --yes`: `Initialize Taskmaster quickly using default settings without interactive prompts.`
 *   **Usage:** Run this once at the beginning of a new project.
 *   **MCP Variant Description:** `Set up the basic Taskmaster file structure and configuration in the current directory for a new project by running the 'task-master init' command.`
@@ -37,11 +34,9 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `authorName`: `Author name.` (CLI: `--author <author>`)
     *   `skipInstall`: `Skip installing dependencies. Default is false.` (CLI: `--skip-install`)
     *   `addAliases`: `Add shell aliases tm and taskmaster. Default is false.` (CLI: `--aliases`)
-    *   `noGit`: `Skip initializing a Git repository entirely. Default is false.` (CLI: `--no-git`)
     *   `yes`: `Skip prompts and use defaults/provided arguments. Default is false.` (CLI: `-y, --yes`)
 *   **Usage:** Run this once at the beginning of a new project, typically via an integrated tool like Cursor. Operates on the current working directory of the MCP server. 
-*   **Important:** Once complete, you *MUST* parse a prd in order to generate tasks. There will be no tasks files until then. The next step after initializing should be to create a PRD using the example PRD in .taskmaster/templates/example_prd.txt. 
-*   **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`.
+*   **Important:** Once complete, you *MUST* parse a prd in order to generate tasks. There will be no tasks files until then. The next step after initializing should be to create a PRD using the example PRD in scripts/example_prd.txt. 
 
 ### 2. Parse PRD (`parse_prd`)
 
@@ -50,12 +45,12 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Description:** `Parse a Product Requirements Document, PRD, or text file with Taskmaster to automatically generate an initial set of tasks in tasks.json.`
 *   **Key Parameters/Options:**
     *   `input`: `Path to your PRD or requirements text file that Taskmaster should parse for tasks.` (CLI: `[file]` positional or `-i, --input <file>`)
-    *   `output`: `Specify where Taskmaster should save the generated 'tasks.json' file. Defaults to '.taskmaster/tasks/tasks.json'.` (CLI: `-o, --output <file>`)
+    *   `output`: `Specify where Taskmaster should save the generated 'tasks.json' file. Defaults to 'tasks/tasks.json'.` (CLI: `-o, --output <file>`)
     *   `numTasks`: `Approximate number of top-level tasks Taskmaster should aim to generate from the document.` (CLI: `-n, --num-tasks <number>`)
     *   `force`: `Use this to allow Taskmaster to overwrite an existing 'tasks.json' without asking for confirmation.` (CLI: `-f, --force`)
 *   **Usage:** Useful for bootstrapping a project from an existing requirements document.
 *   **Notes:** Task Master will strictly adhere to any specific requirements mentioned in the PRD, such as libraries, database schemas, frameworks, tech stacks, etc., while filling in any gaps where the PRD isn't fully specified. Tasks are designed to provide the most direct implementation path while avoiding over-engineering.
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress. If the user does not have a PRD, suggest discussing their idea and then use the example PRD in `.taskmaster/templates/example_prd.txt` as a template for creating the PRD based on their idea, for use with `parse-prd`.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress. If the user does not have a PRD, suggest discussing their idea and then use the example PRD in `scripts/example_prd.txt` as a template for creating the PRD based on their idea, for use with `parse-prd`.
 
 ---
 
@@ -79,14 +74,13 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `--set-fallback <model_id>`: `Set the fallback model.`
     *   `--ollama`: `Specify that the provided model ID is for Ollama (use with --set-*).`
     *   `--openrouter`: `Specify that the provided model ID is for OpenRouter (use with --set-*). Validates against OpenRouter API.`
-    *   `--bedrock`: `Specify that the provided model ID is for AWS Bedrock (use with --set-*).`
     *   `--setup`: `Run interactive setup to configure models, including custom Ollama/OpenRouter IDs.`
 *   **Usage (MCP):** Call without set flags to get current config. Use `setMain`, `setResearch`, or `setFallback` with a valid model ID to update the configuration. Use `listAvailableModels: true` to get a list of unassigned models. To set a custom model, provide the model ID and set `ollama: true` or `openrouter: true`.
 *   **Usage (CLI):** Run without flags to view current configuration and available models. Use set flags to update specific roles. Use `--setup` for guided configuration, including custom models. To set a custom model via flags, use `--set-<role>=<model_id>` along with either `--ollama` or `--openrouter`.
-*   **Notes:** Configuration is stored in `.taskmaster/config.json` in the project root. This command/tool modifies that file. Use `listAvailableModels` or `task-master models` to see internally supported models. OpenRouter custom models are validated against their live API. Ollama custom models are not validated live.
+*   **Notes:** Configuration is stored in `.taskmasterconfig` in the project root. This command/tool modifies that file. Use `listAvailableModels` or `task-master models` to see internally supported models. OpenRouter custom models are validated against their live API. Ollama custom models are not validated live.
 *   **API note:** API keys for selected AI providers (based on their model) need to exist in the mcp.json file to be accessible in MCP context. The API keys must be present in the local .env file for the CLI to be able to read them.
 *   **Model costs:** The costs in supported models are expressed in dollars. An input/output value of 3 is $3.00. A value of 0.8 is $0.80. 
-*   **Warning:** DO NOT MANUALLY EDIT THE .taskmaster/config.json FILE. Use the included commands either in the MCP or CLI format as needed. Always prioritize MCP tools when available and use the CLI as a fallback.
+*   **Warning:** DO NOT MANUALLY EDIT THE .taskmasterconfig FILE. Use the included commands either in the MCP or CLI format as needed. Always prioritize MCP tools when available and use the CLI as a fallback.
 
 ---
 
@@ -98,9 +92,8 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **CLI Command:** `task-master list [options]`
 *   **Description:** `List your Taskmaster tasks, optionally filtering by status and showing subtasks.`
 *   **Key Parameters/Options:**
-    *   `status`: `Show only Taskmaster tasks matching this status (or multiple statuses, comma-separated), e.g., 'pending' or 'done,in-progress'.` (CLI: `-s, --status <status>`)
+    *   `status`: `Show only Taskmaster tasks matching this status, e.g., 'pending' or 'done'.` (CLI: `-s, --status <status>`)
     *   `withSubtasks`: `Include subtasks indented under their parent tasks in the list.` (CLI: `--with-subtasks`)
-    *   `tag`: `Specify which tag context to list tasks from. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Get an overview of the project status, often used at the start of a work session.
 
@@ -111,20 +104,17 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Description:** `Ask Taskmaster to show the next available task you can work on, based on status and completed dependencies.`
 *   **Key Parameters/Options:**
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-    *   `tag`: `Specify which tag context to use. Defaults to the current active tag.` (CLI: `--tag <name>`)
 *   **Usage:** Identify what to work on next according to the plan.
 
 ### 5. Get Task Details (`get_task`)
 
 *   **MCP Tool:** `get_task`
 *   **CLI Command:** `task-master show [id] [options]`
-*   **Description:** `Display detailed information for one or more specific Taskmaster tasks or subtasks by ID.`
+*   **Description:** `Display detailed information for a specific Taskmaster task or subtask by its ID.`
 *   **Key Parameters/Options:**
-    *   `id`: `Required. The ID of the Taskmaster task (e.g., '15'), subtask (e.g., '15.2'), or a comma-separated list of IDs ('1,5,10.2') you want to view.` (CLI: `[id]` positional or `-i, --id <id>`)
-    *   `tag`: `Specify which tag context to get the task(s) from. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `id`: `Required. The ID of the Taskmaster task, e.g., '15', or subtask, e.g., '15.2', you want to view.` (CLI: `[id]` positional or `-i, --id <id>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Understand the full details for a specific task. When multiple IDs are provided, a summary table is shown.
-*   **CRITICAL INFORMATION** If you need to collect information from multiple tasks, use comma-separated IDs (i.e. 1,2,3) to receive an array of tasks. Do not needlessly get tasks one at a time if you need to get many as that is wasteful.
+*   **Usage:** Understand the full details, implementation notes, and test strategy for a specific task before starting work.
 
 ---
 
@@ -140,7 +130,6 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `dependencies`: `Specify the IDs of any Taskmaster tasks that must be completed before this new one can start, e.g., '12,14'.` (CLI: `-d, --dependencies <ids>`)
     *   `priority`: `Set the priority for the new task: 'high', 'medium', or 'low'. Default is 'medium'.` (CLI: `--priority <priority>`)
     *   `research`: `Enable Taskmaster to use the research role for potentially more informed task creation.` (CLI: `-r, --research`)
-    *   `tag`: `Specify which tag context to add the task to. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Quickly add newly identified tasks during development.
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
@@ -158,8 +147,7 @@ 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>`)
-    *   `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>`)
+    *   `skipGenerate`: `Prevent Taskmaster from automatically regenerating markdown task files after adding the subtask.` (CLI: `--skip-generate`)
     *   `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.
 
@@ -172,7 +160,6 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `from`: `Required. The ID of the first task Taskmaster should update. All tasks with this ID or higher that are not 'done' will be considered.` (CLI: `--from <id>`)
     *   `prompt`: `Required. Explain the change or new context for Taskmaster to apply to the tasks, e.g., "We are now using React Query instead of Redux Toolkit for data fetching".` (CLI: `-p, --prompt <text>`)
     *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Handle significant implementation changes or pivots that affect multiple future tasks. Example CLI: `task-master update --from='18' --prompt='Switching to React Query.\nNeed to refactor data fetching...'`
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
@@ -181,15 +168,13 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 
 *   **MCP Tool:** `update_task`
 *   **CLI Command:** `task-master update-task [options]`
-*   **Description:** `Modify a specific Taskmaster task by ID, incorporating new information or changes. By default, this replaces the existing task details.`
+*   **Description:** `Modify a specific Taskmaster task or subtask by its ID, incorporating new information or changes.`
 *   **Key Parameters/Options:**
-    *   `id`: `Required. The specific ID of the Taskmaster task, e.g., '15', you want to update.` (CLI: `-i, --id <id>`)
+    *   `id`: `Required. The specific ID of the Taskmaster task, e.g., '15', or subtask, e.g., '15.2', you want to update.` (CLI: `-i, --id <id>`)
     *   `prompt`: `Required. Explain the specific changes or provide the new information Taskmaster should incorporate into this task.` (CLI: `-p, --prompt <text>`)
-    *   `append`: `If true, appends the prompt content to the task's details with a timestamp, rather than replacing them. Behaves like update-subtask.` (CLI: `--append`)
     *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
-    *   `tag`: `Specify which tag context the task belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Refine a specific task based on new understanding. Use `--append` to log progress without creating subtasks.
+*   **Usage:** Refine a specific task based on new understanding or feedback. Example CLI: `task-master update-task --id='15' --prompt='Clarification: Use PostgreSQL instead of MySQL.\nUpdate schema details...'`
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
 
 ### 10. Update Subtask (`update_subtask`)
@@ -198,12 +183,11 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **CLI Command:** `task-master update-subtask [options]`
 *   **Description:** `Append timestamped notes or details to a specific Taskmaster subtask without overwriting existing content. Intended for iterative implementation logging.`
 *   **Key Parameters/Options:**
-    *   `id`: `Required. The ID of the Taskmaster subtask, e.g., '5.2', to update with new information.` (CLI: `-i, --id <id>`)
-    *   `prompt`: `Required. The information, findings, or progress notes to append to the subtask's details with a timestamp.` (CLI: `-p, --prompt <text>`)
+    *   `id`: `Required. The specific ID of the Taskmaster subtask, e.g., '15.2', you want to add information to.` (CLI: `-i, --id <id>`)
+    *   `prompt`: `Required. Provide the information or notes Taskmaster should append to the subtask's details. Ensure this adds *new* information not already present.` (CLI: `-p, --prompt <text>`)
     *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
-    *   `tag`: `Specify which tag context the subtask belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Log implementation progress, findings, and discoveries during subtask development. Each update is timestamped and appended to preserve the implementation journey.
+*   **Usage:** Add implementation notes, code snippets, or clarifications to a subtask during development. Before calling, review the subtask's current details to append only fresh insights, helping to build a detailed log of the implementation journey and avoid redundancy. Example CLI: `task-master update-subtask --id='15.2' --prompt='Discovered that the API requires header X.\nImplementation needs adjustment...'`
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
 
 ### 11. Set Task Status (`set_task_status`)
@@ -214,7 +198,6 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Key Parameters/Options:**
     *   `id`: `Required. The ID(s) of the Taskmaster task(s) or subtask(s), e.g., '15', '15.2', or '16,17.1', to update.` (CLI: `-i, --id <id>`)
     *   `status`: `Required. The new status to set, e.g., 'done', 'pending', 'in-progress', 'review', 'cancelled'.` (CLI: `-s, --status <status>`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Mark progress as tasks move through the development cycle.
 
@@ -226,7 +209,6 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Key Parameters/Options:**
     *   `id`: `Required. The ID of the Taskmaster task, e.g., '5', or subtask, e.g., '5.2', to permanently remove.` (CLI: `-i, --id <id>`)
     *   `yes`: `Skip the confirmation prompt and immediately delete the task.` (CLI: `-y, --yes`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Permanently delete tasks or subtasks that are no longer needed in the project.
 *   **Notes:** Use with caution as this operation cannot be undone. Consider using 'blocked', 'cancelled', or 'deferred' status instead if you just want to exclude a task from active planning but keep it for reference. The command automatically cleans up dependency references in other tasks.
@@ -246,7 +228,6 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `research`: `Enable Taskmaster to use the research role for more informed subtask generation. Requires appropriate API key.` (CLI: `-r, --research`)
     *   `prompt`: `Optional: Provide extra context or specific instructions to Taskmaster for generating the subtasks.` (CLI: `-p, --prompt <text>`)
     *   `force`: `Optional: If true, clear existing subtasks before generating new ones. Default is false (append).` (CLI: `--force`)
-    *   `tag`: `Specify which tag context the task belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Generate a detailed implementation plan for a complex task before starting coding. Automatically uses complexity report recommendations if available and `num` is not specified.
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
@@ -261,7 +242,6 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `research`: `Enable research role for more informed subtask generation. Requires appropriate API key.` (CLI: `-r, --research`)
     *   `prompt`: `Optional: Provide extra context for Taskmaster to apply generally during expansion.` (CLI: `-p, --prompt <text>`)
     *   `force`: `Optional: If true, clear existing subtasks before generating new ones for each eligible task. Default is false (append).` (CLI: `--force`)
-    *   `tag`: `Specify which tag context to expand. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Useful after initial task generation or complexity analysis to break down multiple tasks at once.
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
@@ -272,9 +252,8 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **CLI Command:** `task-master clear-subtasks [options]`
 *   **Description:** `Remove all subtasks from one or more specified Taskmaster parent tasks.`
 *   **Key Parameters/Options:**
-    *   `id`: `The ID(s) of the Taskmaster parent task(s) whose subtasks you want to remove, e.g., '15' or '16,18'. Required unless using 'all'.` (CLI: `-i, --id <ids>`)
+    *   `id`: `The ID(s) of the Taskmaster parent task(s) whose subtasks you want to remove, e.g., '15' or '16,18'. Required unless using `all`.) (CLI: `-i, --id <ids>`)
     *   `all`: `Tell Taskmaster to remove subtasks from all parent tasks.` (CLI: `--all`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Used before regenerating subtasks with `expand_task` if the previous breakdown needs replacement.
 
@@ -286,42 +265,15 @@ 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`)
-    *   `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>`)
+    *   `skipGenerate`: `Prevent Taskmaster from automatically regenerating markdown task files after removing the subtask.` (CLI: `--skip-generate`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Delete unnecessary subtasks or promote a subtask to a top-level task.
 
-### 17. Move Task (`move_task`)
-
-*   **MCP Tool:** `move_task`
-*   **CLI Command:** `task-master move [options]`
-*   **Description:** `Move a task or subtask to a new position within the task hierarchy.`
-*   **Key Parameters/Options:**
-    *   `from`: `Required. ID of the task/subtask to move (e.g., "5" or "5.2"). Can be comma-separated for multiple tasks.` (CLI: `--from <id>`)
-    *   `to`: `Required. ID of the destination (e.g., "7" or "7.3"). Must match the number of source IDs if comma-separated.` (CLI: `--to <id>`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Reorganize tasks by moving them within the hierarchy. Supports various scenarios like:
-    *   Moving a task to become a subtask
-    *   Moving a subtask to become a standalone task
-    *   Moving a subtask to a different parent
-    *   Reordering subtasks within the same parent
-    *   Moving a task to a new, non-existent ID (automatically creates placeholders)
-    *   Moving multiple tasks at once with comma-separated IDs
-*   **Validation Features:**
-    *   Allows moving tasks to non-existent destination IDs (creates placeholder tasks)
-    *   Prevents moving to existing task IDs that already have content (to avoid overwriting)
-    *   Validates that source tasks exist before attempting to move them
-    *   Maintains proper parent-child relationships
-*   **Example CLI:** `task-master move --from=5.2 --to=7.3` to move subtask 5.2 to become subtask 7.3.
-*   **Example Multi-Move:** `task-master move --from=10,11,12 --to=16,17,18` to move multiple tasks to new positions.
-*   **Common Use:** Resolving merge conflicts in tasks.json when multiple team members create tasks on different branches.
-
 ---
 
 ## Dependency Management
 
-### 18. Add Dependency (`add_dependency`)
+### 17. Add Dependency (`add_dependency`)
 
 *   **MCP Tool:** `add_dependency`
 *   **CLI Command:** `task-master add-dependency [options]`
@@ -329,11 +281,10 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Key Parameters/Options:**
     *   `id`: `Required. The ID of the Taskmaster task that will depend on another.` (CLI: `-i, --id <id>`)
     *   `dependsOn`: `Required. The ID of the Taskmaster task that must be completed first, the prerequisite.` (CLI: `-d, --depends-on <id>`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <path>`)
 *   **Usage:** Establish the correct order of execution between tasks.
 
-### 19. Remove Dependency (`remove_dependency`)
+### 18. Remove Dependency (`remove_dependency`)
 
 *   **MCP Tool:** `remove_dependency`
 *   **CLI Command:** `task-master remove-dependency [options]`
@@ -341,27 +292,24 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Key Parameters/Options:**
     *   `id`: `Required. The ID of the Taskmaster task you want to remove a prerequisite from.` (CLI: `-i, --id <id>`)
     *   `dependsOn`: `Required. The ID of the Taskmaster task that should no longer be a prerequisite.` (CLI: `-d, --depends-on <id>`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Update task relationships when the order of execution changes.
 
-### 20. Validate Dependencies (`validate_dependencies`)
+### 19. Validate Dependencies (`validate_dependencies`)
 
 *   **MCP Tool:** `validate_dependencies`
 *   **CLI Command:** `task-master validate-dependencies [options]`
 *   **Description:** `Check your Taskmaster tasks for dependency issues (like circular references or links to non-existent tasks) without making changes.`
 *   **Key Parameters/Options:**
-    *   `tag`: `Specify which tag context to validate. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Audit the integrity of your task dependencies.
 
-### 21. Fix Dependencies (`fix_dependencies`)
+### 20. Fix Dependencies (`fix_dependencies`)
 
 *   **MCP Tool:** `fix_dependencies`
 *   **CLI Command:** `task-master fix-dependencies [options]`
 *   **Description:** `Automatically fix dependency issues (like circular references or links to non-existent tasks) in your Taskmaster tasks.`
 *   **Key Parameters/Options:**
-    *   `tag`: `Specify which tag context to fix dependencies in. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Clean up dependency errors automatically.
 
@@ -369,172 +317,47 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 
 ## Analysis & Reporting
 
-### 22. Analyze Project Complexity (`analyze_project_complexity`)
+### 21. Analyze Project Complexity (`analyze_project_complexity`)
 
 *   **MCP Tool:** `analyze_project_complexity`
 *   **CLI Command:** `task-master analyze-complexity [options]`
 *   **Description:** `Have Taskmaster analyze your tasks to determine their complexity and suggest which ones need to be broken down further.`
 *   **Key Parameters/Options:**
-    *   `output`: `Where to save the complexity analysis report. Default is '.taskmaster/reports/task-complexity-report.json' (or '..._tagname.json' if a tag is used).` (CLI: `-o, --output <file>`)
+    *   `output`: `Where to save the complexity analysis report (default: 'scripts/task-complexity-report.json').` (CLI: `-o, --output <file>`)
     *   `threshold`: `The minimum complexity score (1-10) that should trigger a recommendation to expand a task.` (CLI: `-t, --threshold <number>`)
     *   `research`: `Enable research role for more accurate complexity analysis. Requires appropriate API key.` (CLI: `-r, --research`)
-    *   `tag`: `Specify which tag context to analyze. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Used before breaking down tasks to identify which ones need the most attention.
 *   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
 
-### 23. View Complexity Report (`complexity_report`)
+### 22. View Complexity Report (`complexity_report`)
 
 *   **MCP Tool:** `complexity_report`
 *   **CLI Command:** `task-master complexity-report [options]`
 *   **Description:** `Display the task complexity analysis report in a readable format.`
 *   **Key Parameters/Options:**
-    *   `tag`: `Specify which tag context to show the report for. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to the complexity report (default: '.taskmaster/reports/task-complexity-report.json').` (CLI: `-f, --file <file>`)
+    *   `file`: `Path to the complexity report (default: 'scripts/task-complexity-report.json').` (CLI: `-f, --file <file>`)
 *   **Usage:** Review and understand the complexity analysis results after running analyze-complexity.
 
 ---
 
 ## File Management
 
-### 24. Generate Task Files (`generate`)
+### 23. Generate Task Files (`generate`)
 
 *   **MCP Tool:** `generate`
 *   **CLI Command:** `task-master generate [options]`
 *   **Description:** `Create or update individual Markdown files for each task based on your tasks.json.`
 *   **Key Parameters/Options:**
     *   `output`: `The directory where Taskmaster should save the task files (default: in a 'tasks' directory).` (CLI: `-o, --output <directory>`)
-    *   `tag`: `Specify which tag context to generate files for. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Run this after making changes to tasks.json to keep individual task files up to date. This command is now manual and no longer runs automatically.
-
----
-
-## AI-Powered Research
-
-### 25. Research (`research`)
-
-*   **MCP Tool:** `research`
-*   **CLI Command:** `task-master research [options]`
-*   **Description:** `Perform AI-powered research queries with project context to get fresh, up-to-date information beyond the AI's knowledge cutoff.`
-*   **Key Parameters/Options:**
-    *   `query`: `Required. Research query/prompt (e.g., "What are the latest best practices for React Query v5?").` (CLI: `[query]` positional or `-q, --query <text>`)
-    *   `taskIds`: `Comma-separated list of task/subtask IDs from the current tag context (e.g., "15,16.2,17").` (CLI: `-i, --id <ids>`)
-    *   `filePaths`: `Comma-separated list of file paths for context (e.g., "src/api.js,docs/readme.md").` (CLI: `-f, --files <paths>`)
-    *   `customContext`: `Additional custom context text to include in the research.` (CLI: `-c, --context <text>`)
-    *   `includeProjectTree`: `Include project file tree structure in context (default: false).` (CLI: `--tree`)
-    *   `detailLevel`: `Detail level for the research response: 'low', 'medium', 'high' (default: medium).` (CLI: `--detail <level>`)
-    *   `saveTo`: `Task or subtask ID (e.g., "15", "15.2") to automatically save the research conversation to.` (CLI: `--save-to <id>`)
-    *   `saveFile`: `If true, saves the research conversation to a markdown file in '.taskmaster/docs/research/'.` (CLI: `--save-file`)
-    *   `noFollowup`: `Disables the interactive follow-up question menu in the CLI.` (CLI: `--no-followup`)
-    *   `tag`: `Specify which tag context to use for task-based context gathering. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `projectRoot`: `The directory of the project. Must be an absolute path.` (CLI: Determined automatically)
-*   **Usage:** **This is a POWERFUL tool that agents should use FREQUENTLY** to:
-    *   Get fresh information beyond knowledge cutoff dates
-    *   Research latest best practices, library updates, security patches
-    *   Find implementation examples for specific technologies
-    *   Validate approaches against current industry standards
-    *   Get contextual advice based on project files and tasks
-*   **When to Consider Using Research:**
-    *   **Before implementing any task** - Research current best practices
-    *   **When encountering new technologies** - Get up-to-date implementation guidance (libraries, apis, etc)
-    *   **For security-related tasks** - Find latest security recommendations
-    *   **When updating dependencies** - Research breaking changes and migration guides
-    *   **For performance optimization** - Get current performance best practices
-    *   **When debugging complex issues** - Research known solutions and workarounds
-*   **Research + Action Pattern:**
-    *   Use `research` to gather fresh information
-    *   Use `update_subtask` to commit findings with timestamps
-    *   Use `update_task` to incorporate research into task details
-    *   Use `add_task` with research flag for informed task creation
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. The research provides FRESH data beyond the AI's training cutoff, making it invaluable for current best practices and recent developments.
-
----
-
-## Tag Management
-
-This new suite of commands allows you to manage different task contexts (tags).
-
-### 26. List Tags (`tags`)
-
-*   **MCP Tool:** `list_tags`
-*   **CLI Command:** `task-master tags [options]`
-*   **Description:** `List all available tags with task counts, completion status, and other metadata.`
-*   **Key Parameters/Options:**
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-    *   `--show-metadata`: `Include detailed metadata in the output (e.g., creation date, description).` (CLI: `--show-metadata`)
-
-### 27. Add Tag (`add_tag`)
-
-*   **MCP Tool:** `add_tag`
-*   **CLI Command:** `task-master add-tag <tagName> [options]`
-*   **Description:** `Create a new, empty tag context, or copy tasks from another tag.`
-*   **Key Parameters/Options:**
-    *   `tagName`: `Name of the new tag to create (alphanumeric, hyphens, underscores).` (CLI: `<tagName>` positional)
-    *   `--from-branch`: `Creates a tag with a name derived from the current git branch, ignoring the <tagName> argument.` (CLI: `--from-branch`)
-    *   `--copy-from-current`: `Copy tasks from the currently active tag to the new tag.` (CLI: `--copy-from-current`)
-    *   `--copy-from <tag>`: `Copy tasks from a specific source tag to the new tag.` (CLI: `--copy-from <tag>`)
-    *   `--description <text>`: `Provide an optional description for the new tag.` (CLI: `-d, --description <text>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-
-### 28. Delete Tag (`delete_tag`)
-
-*   **MCP Tool:** `delete_tag`
-*   **CLI Command:** `task-master delete-tag <tagName> [options]`
-*   **Description:** `Permanently delete a tag and all of its associated tasks.`
-*   **Key Parameters/Options:**
-    *   `tagName`: `Name of the tag to delete.` (CLI: `<tagName>` positional)
-    *   `--yes`: `Skip the confirmation prompt.` (CLI: `-y, --yes`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-
-### 29. Use Tag (`use_tag`)
-
-*   **MCP Tool:** `use_tag`
-*   **CLI Command:** `task-master use-tag <tagName>`
-*   **Description:** `Switch your active task context to a different tag.`
-*   **Key Parameters/Options:**
-    *   `tagName`: `Name of the tag to switch to.` (CLI: `<tagName>` positional)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-
-### 30. Rename Tag (`rename_tag`)
-
-*   **MCP Tool:** `rename_tag`
-*   **CLI Command:** `task-master rename-tag <oldName> <newName>`
-*   **Description:** `Rename an existing tag.`
-*   **Key Parameters/Options:**
-    *   `oldName`: `The current name of the tag.` (CLI: `<oldName>` positional)
-    *   `newName`: `The new name for the tag.` (CLI: `<newName>` positional)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-
-### 31. Copy Tag (`copy_tag`)
-
-*   **MCP Tool:** `copy_tag`
-*   **CLI Command:** `task-master copy-tag <sourceName> <targetName> [options]`
-*   **Description:** `Copy an entire tag context, including all its tasks and metadata, to a new tag.`
-*   **Key Parameters/Options:**
-    *   `sourceName`: `Name of the tag to copy from.` (CLI: `<sourceName>` positional)
-    *   `targetName`: `Name of the new tag to create.` (CLI: `<targetName>` positional)
-    *   `--description <text>`: `Optional description for the new tag.` (CLI: `-d, --description <text>`)
-
----
-
-## Miscellaneous
-
-### 32. Sync Readme (`sync-readme`) -- experimental
-
-*   **MCP Tool:** N/A
-*   **CLI Command:** `task-master sync-readme [options]`
-*   **Description:** `Exports your task list to your project's README.md file, useful for showcasing progress.`
-*   **Key Parameters/Options:**
-    *   `status`: `Filter tasks by status (e.g., 'pending', 'done').` (CLI: `-s, --status <status>`)
-    *   `withSubtasks`: `Include subtasks in the export.` (CLI: `--with-subtasks`)
-    *   `tag`: `Specify which tag context to export from. Defaults to the current active tag.` (CLI: `--tag <name>`)
+*   **Usage:** Run this after making changes to tasks.json to keep individual task files up to date.
 
 ---
 
 ## Environment Variables Configuration (Updated)
 
-Taskmaster primarily uses the **`.taskmaster/config.json`** file (in project root) for configuration (models, parameters, logging level, etc.), managed via `task-master models --setup`.
+Taskmaster primarily uses the **`.taskmasterconfig`** file (in project root) for configuration (models, parameters, logging level, etc.), managed via `task-master models --setup`.
 
 Environment variables are used **only** for sensitive API keys related to AI providers and specific overrides like the Ollama base URL:
 
@@ -547,13 +370,13 @@ Environment variables are used **only** for sensitive API keys related to AI pro
     *   `AZURE_OPENAI_API_KEY` (Requires `AZURE_OPENAI_ENDPOINT` too)
     *   `OPENROUTER_API_KEY`
     *   `XAI_API_KEY`
-    *   `OLLAMA_API_KEY` (Requires `OLLAMA_BASE_URL` too)
-*   **Endpoints (Optional/Provider Specific inside .taskmaster/config.json):**
+    *   `OLLANA_API_KEY` (Requires `OLLAMA_BASE_URL` too)
+*   **Endpoints (Optional/Provider Specific inside .taskmasterconfig):**
     *   `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 **`.cursor/mcp.json`** file (for MCP/Cursor integration). All other settings (model choice, max tokens, temperature, log level, custom endpoints) are managed in `.taskmasterconfig` via `task-master models` command or `models` MCP tool.
 
 ---
 
-For details on how these commands fit into the development process, see the [Development Workflow Guide](mdc:.cursor/rules/dev_workflow.mdc).
+For details on how these commands fit into the development process, see the [Development Workflow Guide](mdc:.cursor/rules/dev_workflow.mdc).

.cursor/rules/tasks.mdc

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

.cursor/rules/test_workflow.mdc

@@ -1,803 +0,0 @@
----
-description: 
-globs: 
-alwaysApply: true
----
-# Test Workflow & Development Process
-
-## **Initial Testing Framework Setup**
-
-Before implementing the TDD workflow, ensure your project has a proper testing framework configured. This section covers setup for different technology stacks.
-
-### **Detecting Project Type & Framework Needs**
-
-**AI Agent Assessment Checklist:**
-1. **Language Detection**: Check for `package.json` (Node.js/JavaScript), `requirements.txt` (Python), `Cargo.toml` (Rust), etc.
-2. **Existing Tests**: Look for test files (`.test.`, `.spec.`, `_test.`) or test directories
-3. **Framework Detection**: Check for existing test runners in dependencies
-4. **Project Structure**: Analyze directory structure for testing patterns
-
-### **JavaScript/Node.js Projects (Jest Setup)**
-
-#### **Prerequisites Check**
-```bash
-# Verify Node.js project
-ls package.json  # Should exist
-
-# Check for existing testing setup
-ls jest.config.js jest.config.ts  # Check for Jest config
-grep -E "(jest|vitest|mocha)" package.json  # Check for test runners
-```
-
-#### **Jest Installation & Configuration**
-
-**Step 1: Install Dependencies**
-```bash
-# Core Jest dependencies
-npm install --save-dev jest
-
-# TypeScript support (if using TypeScript)
-npm install --save-dev ts-jest @types/jest
-
-# Additional useful packages
-npm install --save-dev supertest @types/supertest  # For API testing
-npm install --save-dev jest-watch-typeahead  # Enhanced watch mode
-```
-
-**Step 2: Create Jest Configuration**
-
-Create `jest.config.js` with the following production-ready configuration:
-
-```javascript
-/** @type {import('jest').Config} */
-module.exports = {
-  // Use ts-jest preset for TypeScript support
-  preset: 'ts-jest',
-
-  // Test environment
-  testEnvironment: 'node',
-
-  // Roots for test discovery
-  roots: ['<rootDir>/src', '<rootDir>/tests'],
-
-  // Test file patterns
-  testMatch: ['**/__tests__/**/*.ts', '**/?(*.)+(spec|test).ts'],
-
-  // Transform files
-  transform: {
-    '^.+\\.ts$': [
-      'ts-jest',
-      {
-        tsconfig: {
-          target: 'es2020',
-          module: 'commonjs',
-          esModuleInterop: true,
-          allowSyntheticDefaultImports: true,
-          skipLibCheck: true,
-          strict: false,
-          noImplicitAny: false,
-        },
-      },
-    ],
-    '^.+\\.js$': [
-      'ts-jest',
-      {
-        useESM: false,
-        tsconfig: {
-          target: 'es2020',
-          module: 'commonjs',
-          esModuleInterop: true,
-          allowSyntheticDefaultImports: true,
-          allowJs: true,
-        },
-      },
-    ],
-  },
-
-  // Module file extensions
-  moduleFileExtensions: ['ts', 'tsx', 'js', 'jsx', 'json', 'node'],
-
-  // Transform ignore patterns - adjust for ES modules
-  transformIgnorePatterns: ['node_modules/(?!(your-es-module-deps|.*\\.mjs$))'],
-
-  // Coverage configuration
-  collectCoverage: true,
-  coverageDirectory: 'coverage',
-  coverageReporters: [
-    'text', // Console output
-    'text-summary', // Brief summary
-    'lcov', // For IDE integration
-    'html', // Detailed HTML report
-  ],
-
-  // Files to collect coverage from
-  collectCoverageFrom: [
-    'src/**/*.ts',
-    '!src/**/*.d.ts',
-    '!src/**/*.test.ts',
-    '!src/**/index.ts', // Often just exports
-    '!src/generated/**', // Generated code
-    '!src/config/database.ts', // Database config (tested via integration)
-  ],
-
-  // Coverage thresholds - TaskMaster standards
-  coverageThreshold: {
-    global: {
-      branches: 70,
-      functions: 80,
-      lines: 80,
-      statements: 80,
-    },
-    // Higher standards for critical business logic
-    './src/utils/': {
-      branches: 85,
-      functions: 90,
-      lines: 90,
-      statements: 90,
-    },
-    './src/middleware/': {
-      branches: 80,
-      functions: 85,
-      lines: 85,
-      statements: 85,
-    },
-  },
-
-  // Setup files
-  setupFilesAfterEnv: ['<rootDir>/tests/setup.ts'],
-
-  // Global teardown to prevent worker process leaks
-  globalTeardown: '<rootDir>/tests/teardown.ts',
-
-  // Module path mapping (if needed)
-  moduleNameMapper: {
-    '^@/(.*)$': '<rootDir>/src/$1',
-  },
-
-  // Clear mocks between tests
-  clearMocks: true,
-
-  // Restore mocks after each test
-  restoreMocks: true,
-
-  // Global test timeout
-  testTimeout: 10000,
-
-  // Projects for different test types
-  projects: [
-    // Unit tests - for pure functions only
-    {
-      displayName: 'unit',
-      testMatch: ['<rootDir>/src/**/*.test.ts'],
-      testPathIgnorePatterns: ['.*\\.integration\\.test\\.ts$', '/tests/'],
-      preset: 'ts-jest',
-      testEnvironment: 'node',
-      collectCoverageFrom: [
-        'src/**/*.ts',
-        '!src/**/*.d.ts',
-        '!src/**/*.test.ts',
-        '!src/**/*.integration.test.ts',
-      ],
-      coverageThreshold: {
-        global: {
-          branches: 70,
-          functions: 80,
-          lines: 80,
-          statements: 80,
-        },
-      },
-    },
-    // Integration tests - real database/services
-    {
-      displayName: 'integration',
-      testMatch: [
-        '<rootDir>/src/**/*.integration.test.ts',
-        '<rootDir>/tests/integration/**/*.test.ts',
-      ],
-      preset: 'ts-jest',
-      testEnvironment: 'node',
-      setupFilesAfterEnv: ['<rootDir>/tests/setup/integration.ts'],
-      testTimeout: 10000,
-    },
-    // E2E tests - full workflows
-    {
-      displayName: 'e2e',
-      testMatch: ['<rootDir>/tests/e2e/**/*.test.ts'],
-      preset: 'ts-jest',
-      testEnvironment: 'node',
-      setupFilesAfterEnv: ['<rootDir>/tests/setup/e2e.ts'],
-      testTimeout: 30000,
-    },
-  ],
-
-  // Verbose output for better debugging
-  verbose: true,
-
-  // Run projects sequentially to avoid conflicts
-  maxWorkers: 1,
-
-  // Enable watch mode plugins
-  watchPlugins: ['jest-watch-typeahead/filename', 'jest-watch-typeahead/testname'],
-};
-```
-
-**Step 3: Update package.json Scripts**
-
-Add these scripts to your `package.json`:
-
-```json
-{
-  "scripts": {
-    "test": "jest",
-    "test:watch": "jest --watch",
-    "test:coverage": "jest --coverage",
-    "test:unit": "jest --selectProjects unit",
-    "test:integration": "jest --selectProjects integration", 
-    "test:e2e": "jest --selectProjects e2e",
-    "test:ci": "jest --ci --coverage --watchAll=false"
-  }
-}
-```
-
-**Step 4: Create Test Setup Files**
-
-Create essential test setup files:
-
-```typescript
-// tests/setup.ts - Global setup
-import { jest } from '@jest/globals';
-
-// Global test configuration
-beforeAll(() => {
-  // Set test timeout
-  jest.setTimeout(10000);
-});
-
-afterEach(() => {
-  // Clean up mocks after each test
-  jest.clearAllMocks();
-});
-```
-
-```typescript
-// tests/setup/integration.ts - Integration test setup
-import { PrismaClient } from '@prisma/client';
-
-const prisma = new PrismaClient();
-
-beforeAll(async () => {
-  // Connect to test database
-  await prisma.$connect();
-});
-
-afterAll(async () => {
-  // Cleanup and disconnect
-  await prisma.$disconnect();
-});
-
-beforeEach(async () => {
-  // Clean test data before each test
-  // Add your cleanup logic here
-});
-```
-
-```typescript
-// tests/teardown.ts - Global teardown
-export default async () => {
-  // Global cleanup after all tests
-  console.log('Global test teardown complete');
-};
-```
-
-**Step 5: Create Initial Test Structure**
-
-```bash
-# Create test directories
-mkdir -p tests/{setup,fixtures,unit,integration,e2e}
-mkdir -p tests/unit/src/{utils,services,middleware}
-
-# Create sample test fixtures
-mkdir tests/fixtures
-```
-
-### **Generic Testing Framework Setup (Any Language)**
-
-#### **Framework Selection Guide**
-
-**Python Projects:**
-- **pytest**: Recommended for most Python projects
-- **unittest**: Built-in, suitable for simple projects
-- **Coverage**: Use `coverage.py` for code coverage
-
-```bash
-# Python setup example
-pip install pytest pytest-cov
-echo "[tool:pytest]" > pytest.ini
-echo "testpaths = tests" >> pytest.ini
-echo "addopts = --cov=src --cov-report=html --cov-report=term" >> pytest.ini
-```
-
-**Go Projects:**
-- **Built-in testing**: Use Go's built-in `testing` package
-- **Coverage**: Built-in with `go test -cover`
-
-```bash
-# Go setup example
-go mod init your-project
-mkdir -p tests
-# Tests are typically *_test.go files alongside source
-```
-
-**Rust Projects:**
-- **Built-in testing**: Use Rust's built-in test framework
-- **cargo-tarpaulin**: For coverage analysis
-
-```bash
-# Rust setup example
-cargo new your-project
-cd your-project
-cargo install cargo-tarpaulin  # For coverage
-```
-
-**Java Projects:**
-- **JUnit 5**: Modern testing framework
-- **Maven/Gradle**: Build tools with testing integration
-
-```xml
-<!-- Maven pom.xml example -->
-<dependency>
-    <groupId>org.junit.jupiter</groupId>
-    <artifactId>junit-jupiter</artifactId>
-    <version>5.9.2</version>
-    <scope>test</scope>
-</dependency>
-```
-
-#### **Universal Testing Principles**
-
-**Coverage Standards (Adapt to Your Language):**
-- **Global Minimum**: 70-80% line coverage
-- **Critical Code**: 85-90% coverage
-- **New Features**: Must meet or exceed standards
-- **Legacy Code**: Gradual improvement strategy
-
-**Test Organization:**
-- **Unit Tests**: Fast, isolated, no external dependencies
-- **Integration Tests**: Test component interactions
-- **E2E Tests**: Test complete user workflows
-- **Performance Tests**: Load and stress testing (if applicable)
-
-**Naming Conventions:**
-- **Test Files**: `*.test.*`, `*_test.*`, or language-specific patterns
-- **Test Functions**: Descriptive names (e.g., `should_return_error_for_invalid_input`)
-- **Test Directories**: Organized by test type and mirroring source structure
-
-#### **TaskMaster Integration for Any Framework**
-
-**Document Testing Setup in Subtasks:**
-```bash
-# Update subtask with testing framework setup
-task-master update-subtask --id=X.Y --prompt="Testing framework setup:
-- Installed [Framework Name] with coverage support
-- Configured [Coverage Tool] with thresholds: 80% lines, 70% branches
-- Created test directory structure: unit/, integration/, e2e/
-- Added test scripts to build configuration
-- All setup tests passing"
-```
-
-**Testing Framework Verification:**
-```bash
-# Verify setup works
-[test-command]  # e.g., npm test, pytest, go test, cargo test
-
-# Check coverage reporting
-[coverage-command]  # e.g., npm run test:coverage
-
-# Update task with verification
-task-master update-subtask --id=X.Y --prompt="Testing framework verified:
-- Sample tests running successfully
-- Coverage reporting functional
-- CI/CD integration ready
-- Ready to begin TDD workflow"
-```
-
-## **Test-Driven Development (TDD) Integration**
-
-### **Core TDD Cycle with Jest**
-```bash
-# 1. Start development with watch mode
-npm run test:watch
-
-# 2. Write failing test first
-# Create test file: src/utils/newFeature.test.ts
-# Write test that describes expected behavior
-
-# 3. Implement minimum code to make test pass
-# 4. Refactor while keeping tests green
-# 5. Add edge cases and error scenarios
-```
-
-### **TDD Workflow Per Subtask**
-```bash
-# When starting a new subtask:
-task-master set-status --id=4.1 --status=in-progress
-
-# Begin TDD cycle:
-npm run test:watch  # Keep running during development
-
-# Document TDD progress in subtask:
-task-master update-subtask --id=4.1 --prompt="TDD Progress:
-- Written 3 failing tests for core functionality
-- Implemented basic feature, tests now passing
-- Adding edge case tests for error handling"
-
-# Complete subtask with test summary:
-task-master update-subtask --id=4.1 --prompt="Implementation complete:
-- Feature implemented with 8 unit tests
-- Coverage: 95% statements, 88% branches  
-- All tests passing, TDD cycle complete"
-```
-
-## **Testing Commands & Usage**
-
-### **Development Commands**
-```bash
-# Primary development command - use during coding
-npm run test:watch              # Watch mode with Jest
-npm run test:watch -- --testNamePattern="auth"  # Watch specific tests
-
-# Targeted testing during development
-npm run test:unit               # Run only unit tests
-npm run test:unit -- --coverage # Unit tests with coverage
-
-# Integration testing when APIs are ready
-npm run test:integration        # Run integration tests
-npm run test:integration -- --detectOpenHandles  # Debug hanging tests
-
-# End-to-end testing for workflows
-npm run test:e2e               # Run E2E tests
-npm run test:e2e -- --timeout=30000  # Extended timeout for E2E
-```
-
-### **Quality Assurance Commands**
-```bash
-# Full test suite with coverage (before commits)
-npm run test:coverage          # Complete coverage analysis
-
-# All tests (CI/CD pipeline)
-npm test                       # Run all test projects
-
-# Specific test file execution
-npm test -- auth.test.ts       # Run specific test file
-npm test -- --testNamePattern="should handle errors"  # Run specific tests
-```
-
-## **Test Implementation Patterns**
-
-### **Unit Test Development**
-```typescript
-// ✅ DO: Follow established patterns from auth.test.ts
-describe('FeatureName', () => {
-  beforeEach(() => {
-    jest.clearAllMocks();
-    // Setup mocks with proper typing
-  });
-
-  describe('functionName', () => {
-    it('should handle normal case', () => {
-      // Test implementation with specific assertions
-    });
-    
-    it('should throw error for invalid input', async () => {
-      // Error scenario testing
-      await expect(functionName(invalidInput))
-        .rejects.toThrow('Specific error message');
-    });
-  });
-});
-```
-
-### **Integration Test Development**  
-```typescript
-// ✅ DO: Use supertest for API endpoint testing
-import request from 'supertest';
-import { app } from '../../src/app';
-
-describe('POST /api/auth/register', () => {
-  beforeEach(async () => {
-    await integrationTestUtils.cleanupTestData();
-  });
-  
-  it('should register user successfully', async () => {
-    const userData = createTestUser();
-    
-    const response = await request(app)
-      .post('/api/auth/register')
-      .send(userData)
-      .expect(201);
-      
-    expect(response.body).toMatchObject({
-      id: expect.any(String),
-      email: userData.email
-    });
-    
-    // Verify database state
-    const user = await prisma.user.findUnique({
-      where: { email: userData.email }
-    });
-    expect(user).toBeTruthy();
-  });
-});
-```
-
-### **E2E Test Development**
-```typescript
-// ✅ DO: Test complete user workflows
-describe('User Authentication Flow', () => {
-  it('should complete registration → login → protected access', async () => {
-    // Step 1: Register
-    const userData = createTestUser();
-    await request(app)
-      .post('/api/auth/register')
-      .send(userData)
-      .expect(201);
-    
-    // Step 2: Login
-    const loginResponse = await request(app)
-      .post('/api/auth/login')
-      .send({ email: userData.email, password: userData.password })
-      .expect(200);
-    
-    const { token } = loginResponse.body;
-    
-    // Step 3: Access protected resource
-    await request(app)
-      .get('/api/profile')
-      .set('Authorization', `Bearer ${token}`)
-      .expect(200);
-  }, 30000); // Extended timeout for E2E
-});
-```
-
-## **Mocking & Test Utilities**
-
-### **Established Mocking Patterns**
-```typescript
-// ✅ DO: Use established bcrypt mocking pattern
-jest.mock('bcrypt');
-import bcrypt from 'bcrypt';
-const mockHash = bcrypt.hash as jest.MockedFunction<typeof bcrypt.hash>;
-const mockCompare = bcrypt.compare as jest.MockedFunction<typeof bcrypt.compare>;
-
-// ✅ DO: Use Prisma mocking for unit tests
-jest.mock('@prisma/client', () => ({
-  PrismaClient: jest.fn().mockImplementation(() => ({
-    user: {
-      create: jest.fn(),
-      findUnique: jest.fn(),
-    },
-    $connect: jest.fn(),
-    $disconnect: jest.fn(),
-  })),
-}));
-```
-
-### **Test Fixtures Usage**
-```typescript
-// ✅ DO: Use centralized test fixtures
-import { createTestUser, adminUser, invalidUser } from '../fixtures/users';
-
-describe('User Service', () => {
-  it('should handle admin user creation', async () => {
-    const userData = createTestUser(adminUser);
-    // Test implementation
-  });
-  
-  it('should reject invalid user data', async () => {
-    const userData = createTestUser(invalidUser);
-    // Error testing
-  });
-});
-```
-
-## **Coverage Standards & Monitoring**
-
-### **Coverage Thresholds**
-- **Global Standards**: 80% lines/functions, 70% branches
-- **Critical Code**: 90% utils, 85% middleware
-- **New Features**: Must meet or exceed global thresholds
-- **Legacy Code**: Gradual improvement with each change
-
-### **Coverage Reporting & Analysis**
-```bash
-# Generate coverage reports
-npm run test:coverage
-
-# View detailed HTML report
-open coverage/lcov-report/index.html
-
-# Coverage files generated:
-# - coverage/lcov-report/index.html  # Detailed HTML report
-# - coverage/lcov.info               # LCOV format for IDE integration  
-# - coverage/coverage-final.json     # JSON format for tooling
-```
-
-### **Coverage Quality Checks**
-```typescript
-// ✅ DO: Test all code paths
-describe('validateInput', () => {
-  it('should return true for valid input', () => {
-    expect(validateInput('valid')).toBe(true);
-  });
-  
-  it('should return false for various invalid inputs', () => {
-    expect(validateInput('')).toBe(false);      // Empty string
-    expect(validateInput(null)).toBe(false);    // Null value
-    expect(validateInput(undefined)).toBe(false); // Undefined
-  });
-  
-  it('should throw for unexpected input types', () => {
-    expect(() => validateInput(123)).toThrow('Invalid input type');
-  });
-});
-```
-
-## **Testing During Development Phases**
-
-### **Feature Development Phase**
-```bash
-# 1. Start feature development
-task-master set-status --id=X.Y --status=in-progress
-
-# 2. Begin TDD cycle  
-npm run test:watch
-
-# 3. Document test progress in subtask
-task-master update-subtask --id=X.Y --prompt="Test development:
-- Created test file with 5 failing tests
-- Implemented core functionality
-- Tests passing, adding error scenarios"
-
-# 4. Verify coverage before completion
-npm run test:coverage
-
-# 5. Update subtask with final test status
-task-master update-subtask --id=X.Y --prompt="Testing complete:
-- 12 unit tests with full coverage
-- All edge cases and error scenarios covered
-- Ready for integration testing"
-```
-
-### **Integration Testing Phase**
-```bash
-# After API endpoints are implemented
-npm run test:integration
-
-# Update integration test templates
-# Replace placeholder tests with real endpoint calls
-
-# Document integration test results
-task-master update-subtask --id=X.Y --prompt="Integration tests:
-- Updated auth endpoint tests  
-- Database integration verified
-- All HTTP status codes and responses tested"
-```
-
-### **Pre-Commit Testing Phase**
-```bash
-# Before committing code
-npm run test:coverage         # Verify all tests pass with coverage
-npm run test:unit            # Quick unit test verification
-npm run test:integration     # Integration test verification (if applicable)
-
-# Commit pattern for test updates
-git add tests/ src/**/*.test.ts
-git commit -m "test(task-X): Add comprehensive tests for Feature Y
-
-- Unit tests with 95% coverage (exceeds 90% threshold)
-- Integration tests for API endpoints
-- Test fixtures for data generation
-- Proper mocking patterns established
-
-Task X: Feature Y - Testing complete"
-```
-
-## **Error Handling & Debugging**
-
-### **Test Debugging Techniques**
-```typescript
-// ✅ DO: Use test utilities for debugging
-import { testUtils } from '../setup';
-
-it('should debug complex operation', () => {
-  testUtils.withConsole(() => {
-    // Console output visible only for this test
-    console.log('Debug info:', complexData);
-    service.complexOperation();
-  });
-});
-
-// ✅ DO: Use proper async debugging
-it('should handle async operations', async () => {
-  const promise = service.asyncOperation();
-  
-  // Test intermediate state
-  expect(service.isProcessing()).toBe(true);
-  
-  const result = await promise;
-  expect(result).toBe('expected');
-  expect(service.isProcessing()).toBe(false);
-});
-```
-
-### **Common Test Issues & Solutions**
-```bash
-# Hanging tests (common with database connections)
-npm run test:integration -- --detectOpenHandles
-
-# Memory leaks in tests
-npm run test:unit -- --logHeapUsage
-
-# Slow tests identification
-npm run test:coverage -- --verbose
-
-# Mock not working properly
-# Check: mock is declared before imports
-# Check: jest.clearAllMocks() in beforeEach
-# Check: TypeScript typing is correct
-```
-
-## **Continuous Integration Integration**
-
-### **CI/CD Pipeline Testing**
-```yaml
-# Example GitHub Actions integration
-- name: Run tests
-  run: |
-    npm ci
-    npm run test:coverage
-    
-- name: Upload coverage reports
-  uses: codecov/codecov-action@v3
-  with:
-    file: ./coverage/lcov.info
-```
-
-### **Pre-commit Hooks**
-```bash
-# Setup pre-commit testing (recommended)
-# In package.json scripts:
-"pre-commit": "npm run test:unit && npm run test:integration"
-
-# Husky integration example:
-npx husky add .husky/pre-commit "npm run test:unit"
-```
-
-## **Test Maintenance & Evolution**
-
-### **Adding Tests for New Features**
-1. **Create test file** alongside source code or in `tests/unit/`
-2. **Follow established patterns** from `src/utils/auth.test.ts`
-3. **Use existing fixtures** from `tests/fixtures/`
-4. **Apply proper mocking** patterns for dependencies
-5. **Meet coverage thresholds** for the module
-
-### **Updating Integration/E2E Tests**
-1. **Update templates** in `tests/integration/` when APIs change
-2. **Modify E2E workflows** in `tests/e2e/` for new user journeys  
-3. **Update test fixtures** for new data requirements
-4. **Maintain database cleanup** utilities
-
-### **Test Performance Optimization**
-- **Parallel execution**: Jest runs tests in parallel by default
-- **Test isolation**: Use proper setup/teardown for independence
-- **Mock optimization**: Mock heavy dependencies appropriately  
-- **Database efficiency**: Use transaction rollbacks where possible
-
----
-
-**Key References:**
-- [Testing Standards](mdc:.cursor/rules/tests.mdc)
-- [Git Workflow](mdc:.cursor/rules/git_workflow.mdc)
-- [Development Workflow](mdc:.cursor/rules/dev_workflow.mdc)
-- [Jest Configuration](mdc:jest.config.js)

.cursor/rules/ui.mdc

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

.cursor/rules/utilities.mdc

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

.env.example

@@ -4,14 +4,6 @@ PERPLEXITY_API_KEY=YOUR_PERPLEXITY_KEY_HERE
 OPENAI_API_KEY=YOUR_OPENAI_KEY_HERE
 GOOGLE_API_KEY=YOUR_GOOGLE_KEY_HERE
 MISTRAL_API_KEY=YOUR_MISTRAL_KEY_HERE
-GROQ_API_KEY=YOUR_GROQ_KEY_HERE
 OPENROUTER_API_KEY=YOUR_OPENROUTER_KEY_HERE
 XAI_API_KEY=YOUR_XAI_KEY_HERE
 AZURE_OPENAI_API_KEY=YOUR_AZURE_KEY_HERE
-OLLAMA_API_KEY=YOUR_OLLAMA_API_KEY_HERE
-
-# Google Vertex AI Configuration
-VERTEX_PROJECT_ID=your-gcp-project-id
-VERTEX_LOCATION=us-central1
-# Optional: Path to service account credentials JSON file (alternative to API key)
-GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account-credentials.json

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,45 +0,0 @@
-# What type of PR is this?
-<!-- Check one -->
-
- - [ ] 🐛 Bug fix
- - [ ] ✨ Feature
- - [ ] 🔌 Integration
- - [ ] 📝 Docs
- - [ ] 🧹 Refactor
- - [ ] Other:
-## Description
-<!-- What does this PR do? -->
-
-## Related Issues
-<!-- Link issues: Fixes #123 -->
-
-## How to Test This
-<!-- Quick steps to verify the changes work -->
-```bash
-# Example commands or steps
-```
-
-**Expected result:**
-<!-- What should happen? -->
-
-## Contributor Checklist
-
-- [ ] Created changeset: `npm run changeset`
-- [ ] Tests pass: `npm test`
-- [ ] Format check passes: `npm run format-check` (or `npm run format` to fix)
-- [ ] Addressed CodeRabbit comments (if any)
-- [ ] Linked related issues (if any)
-- [ ] Manually tested the changes
-
-## Changelog Entry
-<!-- One line describing the change for users -->
-<!-- Example: "Added Kiro IDE integration with automatic task status updates" -->
-
----
-
-### For Maintainers
-
-- [ ] PR title follows conventional commits
-- [ ] Target branch correct
-- [ ] Labels added
-- [ ] Milestone assigned (if applicable)

.github/PULL_REQUEST_TEMPLATE/bugfix.md

@@ -1,39 +0,0 @@
-## 🐛 Bug Fix
-
-### 🔍 Bug Description
-<!-- Describe the bug -->
-
-### 🔗 Related Issues
-<!-- Fixes #123 -->
-
-### ✨ Solution
-<!-- How does this PR fix the bug? -->
-
-## How to Test
-
-### Steps that caused the bug:
-1. 
-2. 
-
-**Before fix:** 
-**After fix:** 
-
-### Quick verification:
-```bash
-# Commands to verify the fix
-```
-
-## Contributor Checklist
-- [ ] Created changeset: `npm run changeset`
-- [ ] Tests pass: `npm test`
-- [ ] Format check passes: `npm run format-check`
-- [ ] Addressed CodeRabbit comments
-- [ ] Added unit tests (if applicable)
-- [ ] Manually verified the fix works
-
----
-
-### For Maintainers
-- [ ] Root cause identified
-- [ ] Fix doesn't introduce new issues
-- [ ] CI passes

.github/PULL_REQUEST_TEMPLATE/config.yml

@@ -1,11 +0,0 @@
-blank_issues_enabled: false
-contact_links:
-  - name: 🐛 Bug Fix
-    url: https://github.com/eyaltoledano/claude-task-master/compare/next...HEAD?template=bugfix.md
-    about: Fix a bug in Task Master
-  - name: ✨ New Feature
-    url: https://github.com/eyaltoledano/claude-task-master/compare/next...HEAD?template=feature.md
-    about: Add a new feature to Task Master
-  - name: 🔌 New Integration
-    url: https://github.com/eyaltoledano/claude-task-master/compare/next...HEAD?template=integration.md
-    about: Add support for a new tool, IDE, or platform

.github/PULL_REQUEST_TEMPLATE/feature.md

@@ -1,49 +0,0 @@
-## ✨ New Feature
-
-### 📋 Feature Description
-<!-- Brief description -->
-
-### 🎯 Problem Statement
-<!-- What problem does this feature solve? Why is it needed? -->
-
-### 💡 Solution
-<!-- How does this feature solve the problem? What's the approach? -->
-
-### 🔗 Related Issues
-<!-- Link related issues: Fixes #123, Part of #456 -->
-
-## How to Use It
-
-### Quick Start
-```bash
-# Basic usage example
-```
-
-### Example
-<!-- Show a real use case -->
-```bash
-# Practical example
-```
-
-**What you should see:**
-<!-- Expected behavior -->
-
-## Contributor Checklist
-- [ ] Created changeset: `npm run changeset`
-- [ ] Tests pass: `npm test`
-- [ ] Format check passes: `npm run format-check`
-- [ ] Addressed CodeRabbit comments
-- [ ] Added tests for new functionality
-- [ ] Manually tested in CLI mode
-- [ ] Manually tested in MCP mode (if applicable)
-
-## Changelog Entry
-<!-- One-liner for release notes -->
-
----
-
-### For Maintainers
-
-- [ ] Feature aligns with project vision
-- [ ] CIs pass
-- [ ] Changeset file exists

.github/PULL_REQUEST_TEMPLATE/integration.md

@@ -1,53 +0,0 @@
-# 🔌 New Integration
-
-## What tool/IDE is being integrated?
-
-<!-- Name and brief description -->
-
-## What can users do with it?
-
-<!-- Key benefits -->
-
-## How to Enable
-
-### Setup
-
-```bash
-task-master rules add [name]
-# Any other setup steps
-```
-
-### Example Usage
-
-<!-- Show it in action -->
-
-```bash
-# Real example
-```
-
-### Natural Language Hooks (if applicable)
-
-```
-"When tests pass, mark task as done"
-# Other examples
-```
-
-## Contributor Checklist
-
-- [ ] Created changeset: `npm run changeset`
-- [ ] Tests pass: `npm test`
-- [ ] Format check passes: `npm run format-check`
-- [ ] Addressed CodeRabbit comments
-- [ ] Integration fully tested with target tool/IDE
-- [ ] Error scenarios tested
-- [ ] Added integration tests
-- [ ] Documentation includes setup guide
-- [ ] Examples are working and clear
-
----
-
-## For Maintainers
-
-- [ ] Integration stability verified
-- [ ] Documentation comprehensive
-- [ ] Examples working

.github/scripts/auto-close-duplicates.mjs

@@ -1,259 +0,0 @@
-#!/usr/bin/env node
-
-async function githubRequest(endpoint, token, method = 'GET', body) {
-	const response = await fetch(`https://api.github.com${endpoint}`, {
-		method,
-		headers: {
-			Authorization: `Bearer ${token}`,
-			Accept: 'application/vnd.github.v3+json',
-			'User-Agent': 'auto-close-duplicates-script',
-			...(body && { 'Content-Type': 'application/json' })
-		},
-		...(body && { body: JSON.stringify(body) })
-	});
-
-	if (!response.ok) {
-		throw new Error(
-			`GitHub API request failed: ${response.status} ${response.statusText}`
-		);
-	}
-
-	return response.json();
-}
-
-function extractDuplicateIssueNumber(commentBody) {
-	const match = commentBody.match(/#(\d+)/);
-	return match ? parseInt(match[1], 10) : null;
-}
-
-async function closeIssueAsDuplicate(
-	owner,
-	repo,
-	issueNumber,
-	duplicateOfNumber,
-	token
-) {
-	await githubRequest(
-		`/repos/${owner}/${repo}/issues/${issueNumber}`,
-		token,
-		'PATCH',
-		{
-			state: 'closed',
-			state_reason: 'not_planned',
-			labels: ['duplicate']
-		}
-	);
-
-	await githubRequest(
-		`/repos/${owner}/${repo}/issues/${issueNumber}/comments`,
-		token,
-		'POST',
-		{
-			body: `This issue has been automatically closed as a duplicate of #${duplicateOfNumber}.
-
-If this is incorrect, please re-open this issue or create a new one.
-
-🤖 Generated with [Task Master Bot]`
-		}
-	);
-}
-
-async function autoCloseDuplicates() {
-	console.log('[DEBUG] Starting auto-close duplicates script');
-
-	const token = process.env.GITHUB_TOKEN;
-	if (!token) {
-		throw new Error('GITHUB_TOKEN environment variable is required');
-	}
-	console.log('[DEBUG] GitHub token found');
-
-	const owner = process.env.GITHUB_REPOSITORY_OWNER || 'eyaltoledano';
-	const repo = process.env.GITHUB_REPOSITORY_NAME || 'claude-task-master';
-	console.log(`[DEBUG] Repository: ${owner}/${repo}`);
-
-	const threeDaysAgo = new Date();
-	threeDaysAgo.setDate(threeDaysAgo.getDate() - 3);
-	console.log(
-		`[DEBUG] Checking for duplicate comments older than: ${threeDaysAgo.toISOString()}`
-	);
-
-	console.log('[DEBUG] Fetching open issues created more than 3 days ago...');
-	const allIssues = [];
-	let page = 1;
-	const perPage = 100;
-
-	const MAX_PAGES = 50; // Increase limit for larger repos
-	let foundRecentIssue = false;
-
-	while (true) {
-		const pageIssues = await githubRequest(
-			`/repos/${owner}/${repo}/issues?state=open&per_page=${perPage}&page=${page}&sort=created&direction=desc`,
-			token
-		);
-
-		if (pageIssues.length === 0) break;
-
-		// Filter for issues created more than 3 days ago
-		const oldEnoughIssues = pageIssues.filter(
-			(issue) => new Date(issue.created_at) <= threeDaysAgo
-		);
-
-		allIssues.push(...oldEnoughIssues);
-
-		// If all issues on this page are newer than 3 days, we can stop
-		if (oldEnoughIssues.length === 0 && page === 1) {
-			foundRecentIssue = true;
-			break;
-		}
-
-		// If we found some old issues but not all, continue to next page
-		// as there might be more old issues
-		page++;
-
-		// Safety limit to avoid infinite loops
-		if (page > MAX_PAGES) {
-			console.log(`[WARNING] Reached maximum page limit of ${MAX_PAGES}`);
-			break;
-		}
-	}
-
-	const issues = allIssues;
-	console.log(`[DEBUG] Found ${issues.length} open issues`);
-
-	let processedCount = 0;
-	let candidateCount = 0;
-
-	for (const issue of issues) {
-		processedCount++;
-		console.log(
-			`[DEBUG] Processing issue #${issue.number} (${processedCount}/${issues.length}): ${issue.title}`
-		);
-
-		console.log(`[DEBUG] Fetching comments for issue #${issue.number}...`);
-		const comments = await githubRequest(
-			`/repos/${owner}/${repo}/issues/${issue.number}/comments`,
-			token
-		);
-		console.log(
-			`[DEBUG] Issue #${issue.number} has ${comments.length} comments`
-		);
-
-		const dupeComments = comments.filter(
-			(comment) =>
-				comment.body.includes('Found') &&
-				comment.body.includes('possible duplicate') &&
-				comment.user.type === 'Bot'
-		);
-		console.log(
-			`[DEBUG] Issue #${issue.number} has ${dupeComments.length} duplicate detection comments`
-		);
-
-		if (dupeComments.length === 0) {
-			console.log(
-				`[DEBUG] Issue #${issue.number} - no duplicate comments found, skipping`
-			);
-			continue;
-		}
-
-		const lastDupeComment = dupeComments[dupeComments.length - 1];
-		const dupeCommentDate = new Date(lastDupeComment.created_at);
-		console.log(
-			`[DEBUG] Issue #${
-				issue.number
-			} - most recent duplicate comment from: ${dupeCommentDate.toISOString()}`
-		);
-
-		if (dupeCommentDate > threeDaysAgo) {
-			console.log(
-				`[DEBUG] Issue #${issue.number} - duplicate comment is too recent, skipping`
-			);
-			continue;
-		}
-		console.log(
-			`[DEBUG] Issue #${
-				issue.number
-			} - duplicate comment is old enough (${Math.floor(
-				(Date.now() - dupeCommentDate.getTime()) / (1000 * 60 * 60 * 24)
-			)} days)`
-		);
-
-		const commentsAfterDupe = comments.filter(
-			(comment) => new Date(comment.created_at) > dupeCommentDate
-		);
-		console.log(
-			`[DEBUG] Issue #${issue.number} - ${commentsAfterDupe.length} comments after duplicate detection`
-		);
-
-		if (commentsAfterDupe.length > 0) {
-			console.log(
-				`[DEBUG] Issue #${issue.number} - has activity after duplicate comment, skipping`
-			);
-			continue;
-		}
-
-		console.log(
-			`[DEBUG] Issue #${issue.number} - checking reactions on duplicate comment...`
-		);
-		const reactions = await githubRequest(
-			`/repos/${owner}/${repo}/issues/comments/${lastDupeComment.id}/reactions`,
-			token
-		);
-		console.log(
-			`[DEBUG] Issue #${issue.number} - duplicate comment has ${reactions.length} reactions`
-		);
-
-		const authorThumbsDown = reactions.some(
-			(reaction) =>
-				reaction.user.id === issue.user.id && reaction.content === '-1'
-		);
-		console.log(
-			`[DEBUG] Issue #${issue.number} - author thumbs down reaction: ${authorThumbsDown}`
-		);
-
-		if (authorThumbsDown) {
-			console.log(
-				`[DEBUG] Issue #${issue.number} - author disagreed with duplicate detection, skipping`
-			);
-			continue;
-		}
-
-		const duplicateIssueNumber = extractDuplicateIssueNumber(
-			lastDupeComment.body
-		);
-		if (!duplicateIssueNumber) {
-			console.log(
-				`[DEBUG] Issue #${issue.number} - could not extract duplicate issue number from comment, skipping`
-			);
-			continue;
-		}
-
-		candidateCount++;
-		const issueUrl = `https://github.com/${owner}/${repo}/issues/${issue.number}`;
-
-		try {
-			console.log(
-				`[INFO] Auto-closing issue #${issue.number} as duplicate of #${duplicateIssueNumber}: ${issueUrl}`
-			);
-			await closeIssueAsDuplicate(
-				owner,
-				repo,
-				issue.number,
-				duplicateIssueNumber,
-				token
-			);
-			console.log(
-				`[SUCCESS] Successfully closed issue #${issue.number} as duplicate of #${duplicateIssueNumber}`
-			);
-		} catch (error) {
-			console.error(
-				`[ERROR] Failed to close issue #${issue.number} as duplicate: ${error}`
-			);
-		}
-	}
-
-	console.log(
-		`[DEBUG] Script completed. Processed ${processedCount} issues, found ${candidateCount} candidates for auto-close`
-	);
-}
-
-autoCloseDuplicates().catch(console.error);

.github/scripts/backfill-duplicate-comments.mjs

@@ -1,178 +0,0 @@
-#!/usr/bin/env node
-
-async function githubRequest(endpoint, token, method = 'GET', body) {
-	const response = await fetch(`https://api.github.com${endpoint}`, {
-		method,
-		headers: {
-			Authorization: `Bearer ${token}`,
-			Accept: 'application/vnd.github.v3+json',
-			'User-Agent': 'backfill-duplicate-comments-script',
-			...(body && { 'Content-Type': 'application/json' })
-		},
-		...(body && { body: JSON.stringify(body) })
-	});
-
-	if (!response.ok) {
-		throw new Error(
-			`GitHub API request failed: ${response.status} ${response.statusText}`
-		);
-	}
-
-	return response.json();
-}
-
-async function triggerDedupeWorkflow(
-	owner,
-	repo,
-	issueNumber,
-	token,
-	dryRun = true
-) {
-	if (dryRun) {
-		console.log(
-			`[DRY RUN] Would trigger dedupe workflow for issue #${issueNumber}`
-		);
-		return;
-	}
-
-	await githubRequest(
-		`/repos/${owner}/${repo}/actions/workflows/claude-dedupe-issues.yml/dispatches`,
-		token,
-		'POST',
-		{
-			ref: 'main',
-			inputs: {
-				issue_number: issueNumber.toString()
-			}
-		}
-	);
-}
-
-async function backfillDuplicateComments() {
-	console.log('[DEBUG] Starting backfill duplicate comments script');
-
-	const token = process.env.GITHUB_TOKEN;
-	if (!token) {
-		throw new Error(`GITHUB_TOKEN environment variable is required
-
-Usage:
-  node .github/scripts/backfill-duplicate-comments.mjs
-
-Environment Variables:
-  GITHUB_TOKEN - GitHub personal access token with repo and actions permissions (required)
-  DRY_RUN - Set to "false" to actually trigger workflows (default: true for safety)
-  DAYS_BACK - How many days back to look for old issues (default: 90)`);
-	}
-	console.log('[DEBUG] GitHub token found');
-
-	const owner = process.env.GITHUB_REPOSITORY_OWNER || 'eyaltoledano';
-	const repo = process.env.GITHUB_REPOSITORY_NAME || 'claude-task-master';
-	const dryRun = process.env.DRY_RUN !== 'false';
-	const daysBack = parseInt(process.env.DAYS_BACK || '90', 10);
-
-	console.log(`[DEBUG] Repository: ${owner}/${repo}`);
-	console.log(`[DEBUG] Dry run mode: ${dryRun}`);
-	console.log(`[DEBUG] Looking back ${daysBack} days`);
-
-	const cutoffDate = new Date();
-	cutoffDate.setDate(cutoffDate.getDate() - daysBack);
-
-	console.log(
-		`[DEBUG] Fetching issues created since ${cutoffDate.toISOString()}...`
-	);
-	const allIssues = [];
-	let page = 1;
-	const perPage = 100;
-
-	while (true) {
-		const pageIssues = await githubRequest(
-			`/repos/${owner}/${repo}/issues?state=all&per_page=${perPage}&page=${page}&since=${cutoffDate.toISOString()}`,
-			token
-		);
-
-		if (pageIssues.length === 0) break;
-
-		allIssues.push(...pageIssues);
-		page++;
-
-		// Safety limit to avoid infinite loops
-		if (page > 100) {
-			console.log('[DEBUG] Reached page limit, stopping pagination');
-			break;
-		}
-	}
-
-	console.log(
-		`[DEBUG] Found ${allIssues.length} issues from the last ${daysBack} days`
-	);
-
-	let processedCount = 0;
-	let candidateCount = 0;
-	let triggeredCount = 0;
-
-	for (const issue of allIssues) {
-		processedCount++;
-		console.log(
-			`[DEBUG] Processing issue #${issue.number} (${processedCount}/${allIssues.length}): ${issue.title}`
-		);
-
-		console.log(`[DEBUG] Fetching comments for issue #${issue.number}...`);
-		const comments = await githubRequest(
-			`/repos/${owner}/${repo}/issues/${issue.number}/comments`,
-			token
-		);
-		console.log(
-			`[DEBUG] Issue #${issue.number} has ${comments.length} comments`
-		);
-
-		// Look for existing duplicate detection comments (from the dedupe bot)
-		const dupeDetectionComments = comments.filter(
-			(comment) =>
-				comment.body.includes('Found') &&
-				comment.body.includes('possible duplicate') &&
-				comment.user.type === 'Bot'
-		);
-
-		console.log(
-			`[DEBUG] Issue #${issue.number} has ${dupeDetectionComments.length} duplicate detection comments`
-		);
-
-		// Skip if there's already a duplicate detection comment
-		if (dupeDetectionComments.length > 0) {
-			console.log(
-				`[DEBUG] Issue #${issue.number} already has duplicate detection comment, skipping`
-			);
-			continue;
-		}
-
-		candidateCount++;
-		const issueUrl = `https://github.com/${owner}/${repo}/issues/${issue.number}`;
-
-		try {
-			console.log(
-				`[INFO] ${dryRun ? '[DRY RUN] ' : ''}Triggering dedupe workflow for issue #${issue.number}: ${issueUrl}`
-			);
-			await triggerDedupeWorkflow(owner, repo, issue.number, token, dryRun);
-
-			if (!dryRun) {
-				console.log(
-					`[SUCCESS] Successfully triggered dedupe workflow for issue #${issue.number}`
-				);
-			}
-			triggeredCount++;
-		} catch (error) {
-			console.error(
-				`[ERROR] Failed to trigger workflow for issue #${issue.number}: ${error}`
-			);
-		}
-
-		// Add a delay between workflow triggers to avoid overwhelming the system
-		await new Promise((resolve) => setTimeout(resolve, 1000));
-	}
-
-	console.log(
-		`[DEBUG] Script completed. Processed ${processedCount} issues, found ${candidateCount} candidates without duplicate comments, ${dryRun ? 'would trigger' : 'triggered'} ${triggeredCount} workflows`
-	);
-}
-
-backfillDuplicateComments().catch(console.error);

.github/scripts/check-pre-release-mode.mjs

@@ -1,102 +0,0 @@
-#!/usr/bin/env node
-import { readFileSync, existsSync } from 'node:fs';
-import { join, dirname, resolve } from 'node:path';
-import { fileURLToPath } from 'node:url';
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = dirname(__filename);
-
-// Get context from command line argument or environment
-const context = process.argv[2] || process.env.GITHUB_WORKFLOW || 'manual';
-
-function findRootDir(startDir) {
-	let currentDir = resolve(startDir);
-	while (currentDir !== '/') {
-		if (existsSync(join(currentDir, 'package.json'))) {
-			try {
-				const pkg = JSON.parse(
-					readFileSync(join(currentDir, 'package.json'), 'utf8')
-				);
-				if (pkg.name === 'task-master-ai' || pkg.repository) {
-					return currentDir;
-				}
-			} catch {}
-		}
-		currentDir = dirname(currentDir);
-	}
-	throw new Error('Could not find root directory');
-}
-
-function checkPreReleaseMode() {
-	console.log('🔍 Checking if branch is in pre-release mode...');
-
-	const rootDir = findRootDir(__dirname);
-	const preJsonPath = join(rootDir, '.changeset', 'pre.json');
-
-	// Check if pre.json exists
-	if (!existsSync(preJsonPath)) {
-		console.log('✅ Not in active pre-release mode - safe to proceed');
-		process.exit(0);
-	}
-
-	try {
-		// Read and parse pre.json
-		const preJsonContent = readFileSync(preJsonPath, 'utf8');
-		const preJson = JSON.parse(preJsonContent);
-
-		// Check if we're in active pre-release mode
-		if (preJson.mode === 'pre') {
-			console.error('❌ ERROR: This branch is in active pre-release mode!');
-			console.error('');
-
-			// Provide context-specific error messages
-			if (context === 'Release Check' || context === 'pull_request') {
-				console.error(
-					'Pre-release mode must be exited before merging to main.'
-				);
-				console.error('');
-				console.error(
-					'To fix this, run the following commands in your branch:'
-				);
-				console.error('  npx changeset pre exit');
-				console.error('  git add -u');
-				console.error('  git commit -m "chore: exit pre-release mode"');
-				console.error('  git push');
-				console.error('');
-				console.error('Then update this pull request.');
-			} else if (context === 'Release' || context === 'main') {
-				console.error(
-					'Pre-release mode should only be used on feature branches, not main.'
-				);
-				console.error('');
-				console.error('To fix this, run the following commands locally:');
-				console.error('  npx changeset pre exit');
-				console.error('  git add -u');
-				console.error('  git commit -m "chore: exit pre-release mode"');
-				console.error('  git push origin main');
-				console.error('');
-				console.error('Then re-run this workflow.');
-			} else {
-				console.error('Pre-release mode must be exited before proceeding.');
-				console.error('');
-				console.error('To fix this, run the following commands:');
-				console.error('  npx changeset pre exit');
-				console.error('  git add -u');
-				console.error('  git commit -m "chore: exit pre-release mode"');
-				console.error('  git push');
-			}
-
-			process.exit(1);
-		}
-
-		console.log('✅ Not in active pre-release mode - safe to proceed');
-		process.exit(0);
-	} catch (error) {
-		console.error(`❌ ERROR: Unable to parse .changeset/pre.json – aborting.`);
-		console.error(`Error details: ${error.message}`);
-		process.exit(1);
-	}
-}
-
-// Run the check
-checkPreReleaseMode();

.github/scripts/parse-metrics.mjs

@@ -1,157 +0,0 @@
-#!/usr/bin/env node
-
-import { readFileSync, existsSync, writeFileSync } from 'fs';
-
-function parseMetricsTable(content, metricName) {
-	const lines = content.split('\n');
-
-	for (let i = 0; i < lines.length; i++) {
-		const line = lines[i].trim();
-		// Match a markdown table row like: | Metric Name | value | ...
-		const safeName = metricName.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
-		const re = new RegExp(`^\\|\\s*${safeName}\\s*\\|\\s*([^|]+)\\|?`);
-		const match = line.match(re);
-		if (match) {
-			return match[1].trim() || 'N/A';
-		}
-	}
-	return 'N/A';
-}
-
-function parseCountMetric(content, metricName) {
-	const result = parseMetricsTable(content, metricName);
-	// Extract number from string, handling commas and spaces
-	const numberMatch = result.toString().match(/[\d,]+/);
-	if (numberMatch) {
-		const number = parseInt(numberMatch[0].replace(/,/g, ''));
-		return isNaN(number) ? 0 : number;
-	}
-	return 0;
-}
-
-function main() {
-	const metrics = {
-		issues_created: 0,
-		issues_closed: 0,
-		prs_created: 0,
-		prs_merged: 0,
-		issue_avg_first_response: 'N/A',
-		issue_avg_time_to_close: 'N/A',
-		pr_avg_first_response: 'N/A',
-		pr_avg_merge_time: 'N/A'
-	};
-
-	// Parse issue metrics
-	if (existsSync('issue_metrics.md')) {
-		console.log('📄 Found issue_metrics.md, parsing...');
-		const issueContent = readFileSync('issue_metrics.md', 'utf8');
-
-		metrics.issues_created = parseCountMetric(
-			issueContent,
-			'Total number of items created'
-		);
-		metrics.issues_closed = parseCountMetric(
-			issueContent,
-			'Number of items closed'
-		);
-		metrics.issue_avg_first_response = parseMetricsTable(
-			issueContent,
-			'Time to first response'
-		);
-		metrics.issue_avg_time_to_close = parseMetricsTable(
-			issueContent,
-			'Time to close'
-		);
-	} else {
-		console.warn('[parse-metrics] issue_metrics.md not found; using defaults.');
-	}
-
-	// Parse PR created metrics
-	if (existsSync('pr_created_metrics.md')) {
-		console.log('📄 Found pr_created_metrics.md, parsing...');
-		const prCreatedContent = readFileSync('pr_created_metrics.md', 'utf8');
-
-		metrics.prs_created = parseCountMetric(
-			prCreatedContent,
-			'Total number of items created'
-		);
-		metrics.pr_avg_first_response = parseMetricsTable(
-			prCreatedContent,
-			'Time to first response'
-		);
-	} else {
-		console.warn(
-			'[parse-metrics] pr_created_metrics.md not found; using defaults.'
-		);
-	}
-
-	// Parse PR merged metrics (for more accurate merge data)
-	if (existsSync('pr_merged_metrics.md')) {
-		console.log('📄 Found pr_merged_metrics.md, parsing...');
-		const prMergedContent = readFileSync('pr_merged_metrics.md', 'utf8');
-
-		metrics.prs_merged = parseCountMetric(
-			prMergedContent,
-			'Total number of items created'
-		);
-		// For merged PRs, "Time to close" is actually time to merge
-		metrics.pr_avg_merge_time = parseMetricsTable(
-			prMergedContent,
-			'Time to close'
-		);
-	} else {
-		console.warn(
-			'[parse-metrics] pr_merged_metrics.md not found; falling back to pr_metrics.md.'
-		);
-		// Fallback: try old pr_metrics.md if it exists
-		if (existsSync('pr_metrics.md')) {
-			console.log('📄 Falling back to pr_metrics.md...');
-			const prContent = readFileSync('pr_metrics.md', 'utf8');
-
-			const mergedCount = parseCountMetric(prContent, 'Number of items merged');
-			metrics.prs_merged =
-				mergedCount || parseCountMetric(prContent, 'Number of items closed');
-
-			const maybeMergeTime = parseMetricsTable(
-				prContent,
-				'Average time to merge'
-			);
-			metrics.pr_avg_merge_time =
-				maybeMergeTime !== 'N/A'
-					? maybeMergeTime
-					: parseMetricsTable(prContent, 'Time to close');
-		} else {
-			console.warn('[parse-metrics] pr_metrics.md not found; using defaults.');
-		}
-	}
-
-	// Output for GitHub Actions
-	const output = Object.entries(metrics)
-		.map(([key, value]) => `${key}=${value}`)
-		.join('\n');
-
-	// Always output to stdout for debugging
-	console.log('\n=== FINAL METRICS ===');
-	Object.entries(metrics).forEach(([key, value]) => {
-		console.log(`${key}: ${value}`);
-	});
-
-	// Write to GITHUB_OUTPUT if in GitHub Actions
-	if (process.env.GITHUB_OUTPUT) {
-		try {
-			writeFileSync(process.env.GITHUB_OUTPUT, output + '\n', { flag: 'a' });
-			console.log(
-				`\nSuccessfully wrote metrics to ${process.env.GITHUB_OUTPUT}`
-			);
-		} catch (error) {
-			console.error(`Failed to write to GITHUB_OUTPUT: ${error.message}`);
-			process.exit(1);
-		}
-	} else {
-		console.log(
-			'\nNo GITHUB_OUTPUT environment variable found, skipping file write'
-		);
-	}
-}
-
-main();

.github/scripts/release.mjs

@@ -1,30 +0,0 @@
-#!/usr/bin/env node
-import { existsSync, unlinkSync } from 'node:fs';
-import { join, dirname } from 'node:path';
-import { fileURLToPath } from 'node:url';
-import { findRootDir, runCommand } from './utils.mjs';
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = dirname(__filename);
-
-const rootDir = findRootDir(__dirname);
-
-console.log('🚀 Starting release process...');
-
-// Double-check we're not in pre-release mode (safety net)
-const preJsonPath = join(rootDir, '.changeset', 'pre.json');
-if (existsSync(preJsonPath)) {
-	console.log('⚠️  Warning: pre.json still exists. Removing it...');
-	unlinkSync(preJsonPath);
-}
-
-// Check if the extension version has changed and tag it
-// This prevents changeset from trying to publish the private package
-runCommand('node', [join(__dirname, 'tag-extension.mjs')]);
-
-// Run changeset publish for npm packages
-runCommand('npx', ['changeset', 'publish']);
-
-console.log('✅ Release process completed!');
-
-// The extension tag (if created) will trigger the extension-release workflow

.github/scripts/tag-extension.mjs

@@ -1,33 +0,0 @@
-#!/usr/bin/env node
-import assert from 'node:assert/strict';
-import { readFileSync } from 'node:fs';
-import { join, dirname } from 'node:path';
-import { fileURLToPath } from 'node:url';
-import { findRootDir, createAndPushTag } from './utils.mjs';
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = dirname(__filename);
-
-const rootDir = findRootDir(__dirname);
-
-// Read the extension's package.json
-const extensionDir = join(rootDir, 'apps', 'extension');
-const pkgPath = join(extensionDir, 'package.json');
-
-let pkg;
-try {
-	const pkgContent = readFileSync(pkgPath, 'utf8');
-	pkg = JSON.parse(pkgContent);
-} catch (error) {
-	console.error('Failed to read package.json:', error.message);
-	process.exit(1);
-}
-
-// Ensure we have required fields
-assert(pkg.name, 'package.json must have a name field');
-assert(pkg.version, 'package.json must have a version field');
-
-const tag = `${pkg.name}@${pkg.version}`;
-
-// Create and push the tag if it doesn't exist
-createAndPushTag(tag);

.github/scripts/utils.mjs

@@ -1,88 +0,0 @@
-#!/usr/bin/env node
-import { spawnSync } from 'node:child_process';
-import { readFileSync } from 'node:fs';
-import { join, dirname, resolve } from 'node:path';
-
-// Find the root directory by looking for package.json with task-master-ai
-export function findRootDir(startDir) {
-	let currentDir = resolve(startDir);
-	while (currentDir !== '/') {
-		const pkgPath = join(currentDir, 'package.json');
-		try {
-			const pkg = JSON.parse(readFileSync(pkgPath, 'utf8'));
-			if (pkg.name === 'task-master-ai' || pkg.repository) {
-				return currentDir;
-			}
-		} catch {}
-		currentDir = dirname(currentDir);
-	}
-	throw new Error('Could not find root directory');
-}
-
-// Run a command with proper error handling
-export function runCommand(command, args = [], options = {}) {
-	console.log(`Running: ${command} ${args.join(' ')}`);
-	const result = spawnSync(command, args, {
-		encoding: 'utf8',
-		stdio: 'inherit',
-		...options
-	});
-
-	if (result.status !== 0) {
-		console.error(`Command failed with exit code ${result.status}`);
-		process.exit(result.status);
-	}
-
-	return result;
-}
-
-// Get package version from a package.json file
-export function getPackageVersion(packagePath) {
-	try {
-		const pkg = JSON.parse(readFileSync(packagePath, 'utf8'));
-		return pkg.version;
-	} catch (error) {
-		console.error(
-			`Failed to read package version from ${packagePath}:`,
-			error.message
-		);
-		process.exit(1);
-	}
-}
-
-// Check if a git tag exists on remote
-export function tagExistsOnRemote(tag, remote = 'origin') {
-	const result = spawnSync('git', ['ls-remote', remote, tag], {
-		encoding: 'utf8'
-	});
-
-	return result.status === 0 && result.stdout.trim() !== '';
-}
-
-// Create and push a git tag if it doesn't exist
-export function createAndPushTag(tag, remote = 'origin') {
-	// Check if tag already exists
-	if (tagExistsOnRemote(tag, remote)) {
-		console.log(`Tag ${tag} already exists on remote, skipping`);
-		return false;
-	}
-
-	console.log(`Creating new tag: ${tag}`);
-
-	// Create the tag locally
-	const tagResult = spawnSync('git', ['tag', tag]);
-	if (tagResult.status !== 0) {
-		console.error('Failed to create tag:', tagResult.error || tagResult.stderr);
-		process.exit(1);
-	}
-
-	// Push the tag to remote
-	const pushResult = spawnSync('git', ['push', remote, tag]);
-	if (pushResult.status !== 0) {
-		console.error('Failed to push tag:', pushResult.error || pushResult.stderr);
-		process.exit(1);
-	}
-
-	console.log(`✅ Successfully created and pushed tag: ${tag}`);
-	return true;
-}

.github/workflows/auto-close-duplicates.yml

@@ -1,31 +0,0 @@
-name: Auto-close duplicate issues
-# description: Auto-closes issues that are duplicates of existing issues
-
-on:
-  schedule:
-    - cron: "0 9 * * *"  # Runs daily at 9 AM UTC
-  workflow_dispatch:
-
-jobs:
-  auto-close-duplicates:
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
-      issues: write  # Need write permission to close issues and add comments
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: 20
-
-      - name: Auto-close duplicate issues
-        run: node .github/scripts/auto-close-duplicates.mjs
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          GITHUB_REPOSITORY_OWNER: ${{ github.repository_owner }}
-          GITHUB_REPOSITORY_NAME: ${{ github.event.repository.name }}

.github/workflows/backfill-duplicate-comments.yml

@@ -1,46 +0,0 @@
-name: Backfill Duplicate Comments
-# description: Triggers duplicate detection for old issues that don't have duplicate comments
-
-on:
-  workflow_dispatch:
-    inputs:
-      days_back:
-        description: "How many days back to look for old issues"
-        required: false
-        default: "90"
-        type: string
-      dry_run:
-        description: "Dry run mode (true to only log what would be done)"
-        required: false
-        default: "true"
-        type: choice
-        options:
-          - "true"
-          - "false"
-
-jobs:
-  backfill-duplicate-comments:
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    permissions:
-      contents: read
-      issues: read
-      actions: write
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: 20
-
-      - name: Backfill duplicate comments
-        run: node .github/scripts/backfill-duplicate-comments.mjs
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          GITHUB_REPOSITORY_OWNER: ${{ github.repository_owner }}
-          GITHUB_REPOSITORY_NAME: ${{ github.event.repository.name }}
-          DAYS_BACK: ${{ inputs.days_back }}
-          DRY_RUN: ${{ inputs.dry_run }}

.github/workflows/ci.yml

@@ -6,124 +6,73 @@ on:
       - main
       - next
   pull_request:
-  workflow_dispatch:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
+    branches:
+      - main
+      - next
 
 permissions:
   contents: read
 
-env:
-  DO_NOT_TRACK: 1
-  NODE_ENV: development
-
 jobs:
-  # Fast checks that can run in parallel
-  format-check:
-    name: Format Check
+  setup:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
         with:
-          fetch-depth: 2
+          fetch-depth: 0
 
       - uses: actions/setup-node@v4
         with:
           node-version: 20
-          cache: "npm"
+          cache: 'npm'
 
-      - name: Install dependencies
-        run: npm install --frozen-lockfile --prefer-offline
-        timeout-minutes: 5
+      - name: Install Dependencies
+        id: install
+        run: npm ci
+        timeout-minutes: 2
+
+      - name: Cache node_modules
+        uses: actions/cache@v4
+        with:
+          path: node_modules
+          key: ${{ runner.os }}-node-modules-${{ hashFiles('**/package-lock.json') }}
+
+  format-check:
+    needs: setup
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Restore node_modules
+        uses: actions/cache@v4
+        with:
+          path: node_modules
+          key: ${{ runner.os }}-node-modules-${{ hashFiles('**/package-lock.json') }}
 
       - name: Format Check
         run: npm run format-check
         env:
           FORCE_COLOR: 1
 
-  typecheck:
-    name: Typecheck
-    timeout-minutes: 10
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 2
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 20
-          cache: "npm"
-
-      - name: Install dependencies
-        run: npm install --frozen-lockfile --prefer-offline
-        timeout-minutes: 5
-
-      - name: Typecheck
-        run: npm run turbo:typecheck
-        env:
-          FORCE_COLOR: 1
-
-  # Build job to ensure everything compiles
-  build:
-    name: Build
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 2
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 20
-          cache: "npm"
-
-      - name: Install dependencies
-        run: npm install --frozen-lockfile --prefer-offline
-        timeout-minutes: 5
-
-      - name: Build
-        run: npm run turbo:build
-        env:
-          NODE_ENV: production
-          FORCE_COLOR: 1
-          TM_PUBLIC_BASE_DOMAIN: ${{ secrets.TM_PUBLIC_BASE_DOMAIN }}
-          TM_PUBLIC_SUPABASE_URL: ${{ secrets.TM_PUBLIC_SUPABASE_URL }}
-          TM_PUBLIC_SUPABASE_ANON_KEY: ${{ secrets.TM_PUBLIC_SUPABASE_ANON_KEY }}
-
-      - name: Upload build artifacts
-        uses: actions/upload-artifact@v4
-        with:
-          name: build-artifacts
-          path: dist/
-          retention-days: 1
-
   test:
-    name: Test
-    timeout-minutes: 15
+    needs: setup
     runs-on: ubuntu-latest
-    needs: [format-check, typecheck, build]
     steps:
       - uses: actions/checkout@v4
-        with:
-          fetch-depth: 2
 
       - uses: actions/setup-node@v4
         with:
           node-version: 20
-          cache: "npm"
 
-      - name: Install dependencies
-        run: npm install --frozen-lockfile --prefer-offline
-        timeout-minutes: 5
-
-      - name: Download build artifacts
-        uses: actions/download-artifact@v4
+      - name: Restore node_modules
+        uses: actions/cache@v4
         with:
-          name: build-artifacts
-          path: dist/
+          path: node_modules
+          key: ${{ runner.os }}-node-modules-${{ hashFiles('**/package-lock.json') }}
 
       - name: Run Tests
         run: |
@@ -132,6 +81,7 @@ jobs:
           NODE_ENV: test
           CI: true
           FORCE_COLOR: 1
+        timeout-minutes: 10
 
       - name: Upload Test Results
         if: always()

.github/workflows/claude-dedupe-issues.yml

@@ -1,81 +0,0 @@
-name: Claude Issue Dedupe
-# description: Automatically dedupe GitHub issues using Claude Code
-
-on:
-  issues:
-    types: [opened]
-  workflow_dispatch:
-    inputs:
-      issue_number:
-        description: "Issue number to process for duplicate detection"
-        required: true
-        type: string
-
-jobs:
-  claude-dedupe-issues:
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
-      issues: write
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Run Claude Code slash command
-        uses: anthropics/claude-code-base-action@beta
-        with:
-          prompt: "/dedupe ${{ github.repository }}/issues/${{ github.event.issue.number || inputs.issue_number }}"
-          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          claude_env: |
-            GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Log duplicate comment event to Statsig
-        if: always()
-        env:
-          STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}
-        run: |
-          ISSUE_NUMBER=${{ github.event.issue.number || inputs.issue_number }}
-          REPO=${{ github.repository }}
-
-          if [ -z "$STATSIG_API_KEY" ]; then
-            echo "STATSIG_API_KEY not found, skipping Statsig logging"
-            exit 0
-          fi
-
-          # Prepare the event payload
-          EVENT_PAYLOAD=$(jq -n \
-            --arg issue_number "$ISSUE_NUMBER" \
-            --arg repo "$REPO" \
-            --arg triggered_by "${{ github.event_name }}" \
-            '{
-              events: [{
-                eventName: "github_duplicate_comment_added",
-                value: 1,
-                metadata: {
-                  repository: $repo,
-                  issue_number: ($issue_number | tonumber),
-                  triggered_by: $triggered_by,
-                  workflow_run_id: "${{ github.run_id }}"
-                },
-                time: (now | floor | tostring)
-              }]
-            }')
-
-          # Send to Statsig API
-          echo "Logging duplicate comment event to Statsig for issue #${ISSUE_NUMBER}"
-
-          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST https://events.statsigapi.net/v1/log_event \
-            -H "Content-Type: application/json" \
-            -H "STATSIG-API-KEY: ${STATSIG_API_KEY}" \
-            -d "$EVENT_PAYLOAD")
-
-          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
-          BODY=$(echo "$RESPONSE" | head -n-1)
-
-          if [ "$HTTP_CODE" -eq 200 ] || [ "$HTTP_CODE" -eq 202 ]; then
-            echo "Successfully logged duplicate comment event for issue #${ISSUE_NUMBER}"
-          else
-            echo "Failed to log duplicate comment event for issue #${ISSUE_NUMBER}. HTTP ${HTTP_CODE}: ${BODY}"
-          fi

.github/workflows/claude-docs-trigger.yml

@@ -1,57 +0,0 @@
-name: Trigger Claude Documentation Update
-
-on:
-  push:
-    branches:
-      - next
-    paths-ignore:
-      - "apps/docs/**"
-      - "*.md"
-      - ".github/workflows/**"
-
-jobs:
-  trigger-docs-update:
-    # Only run if changes were merged (not direct pushes from bots)
-    if: github.actor != 'github-actions[bot]' && github.actor != 'dependabot[bot]'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      actions: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 2 # Need previous commit for comparison
-
-      - name: Get changed files
-        id: changed-files
-        run: |
-          echo "Changed files in this push:"
-          git diff --name-only HEAD^ HEAD | tee changed_files.txt
-
-          # Store changed files for Claude to analyze (escaped for JSON)
-          CHANGED_FILES=$(git diff --name-only HEAD^ HEAD | jq -Rs .)
-          echo "changed_files=$CHANGED_FILES" >> $GITHUB_OUTPUT
-
-          # Get the commit message (escaped for JSON)
-          COMMIT_MSG=$(git log -1 --pretty=%B | jq -Rs .)
-          echo "commit_message=$COMMIT_MSG" >> $GITHUB_OUTPUT
-
-          # Get diff for documentation context (escaped for JSON)
-          COMMIT_DIFF=$(git diff HEAD^ HEAD --stat | jq -Rs .)
-          echo "commit_diff=$COMMIT_DIFF" >> $GITHUB_OUTPUT
-
-          # Get commit SHA
-          echo "commit_sha=${{ github.sha }}" >> $GITHUB_OUTPUT
-
-      - name: Trigger Claude workflow
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          # Trigger the Claude docs updater workflow with the change information
-          gh workflow run claude-docs-updater.yml \
-            --ref next \
-            -f commit_sha="${{ steps.changed-files.outputs.commit_sha }}" \
-            -f commit_message=${{ steps.changed-files.outputs.commit_message }} \
-            -f changed_files=${{ steps.changed-files.outputs.changed_files }} \
-            -f commit_diff=${{ steps.changed-files.outputs.commit_diff }}

.github/workflows/claude-docs-updater.yml

@@ -1,145 +0,0 @@
-name: Claude Documentation Updater
-
-on:
-  workflow_dispatch:
-    inputs:
-      commit_sha:
-        description: 'The commit SHA that triggered this update'
-        required: true
-        type: string
-      commit_message:
-        description: 'The commit message'
-        required: true
-        type: string
-      changed_files:
-        description: 'List of changed files'
-        required: true
-        type: string
-      commit_diff:
-        description: 'Diff summary of changes'
-        required: true
-        type: string
-
-jobs:
-  update-docs:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      pull-requests: write
-      issues: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          ref: next
-          fetch-depth: 0 # Need full history to checkout specific commit
-
-      - name: Create docs update branch
-        id: create-branch
-        run: |
-          BRANCH_NAME="docs/auto-update-$(date +%Y%m%d-%H%M%S)"
-          git checkout -b $BRANCH_NAME
-          echo "branch_name=$BRANCH_NAME" >> $GITHUB_OUTPUT
-
-      - name: Run Claude Code to Update Documentation
-        uses: anthropics/claude-code-action@beta
-        with:
-          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          timeout_minutes: "30"
-          mode: "agent"
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          experimental_allowed_domains: |
-            .anthropic.com
-            .github.com
-            api.github.com
-            .githubusercontent.com
-            registry.npmjs.org
-            .task-master.dev
-          base_branch: "next"
-          direct_prompt: |
-            You are a documentation specialist. Analyze the recent changes pushed to the 'next' branch and update the documentation accordingly.
-
-            Recent changes:
-            - Commit: ${{ inputs.commit_message }}
-            - Changed files:
-            ${{ inputs.changed_files }}
-
-            - Changes summary:
-            ${{ inputs.commit_diff }}
-
-            Your task:
-            1. Analyze the changes to understand what functionality was added, modified, or removed
-            2. Check if these changes require documentation updates in apps/docs/
-            3. If documentation updates are needed:
-               - Update relevant documentation files in apps/docs/
-               - Ensure examples are updated if APIs changed
-               - Update any configuration documentation if config options changed
-               - Add new documentation pages if new features were added
-               - Update the changelog or release notes if applicable
-            4. If no documentation updates are needed, skip creating changes
-
-            Guidelines:
-            - Focus only on user-facing changes that need documentation
-            - Keep documentation clear, concise, and helpful
-            - Include code examples where appropriate
-            - Maintain consistent documentation style with existing docs
-            - Don't document internal implementation details unless they affect users
-            - Update navigation/menu files if new pages are added
-
-            Only make changes if the documentation truly needs updating based on the code changes.
-
-      - name: Check if changes were made
-        id: check-changes
-        run: |
-          if git diff --quiet; then
-            echo "has_changes=false" >> $GITHUB_OUTPUT
-          else
-            echo "has_changes=true" >> $GITHUB_OUTPUT
-            git add -A
-            git config --local user.email "github-actions[bot]@users.noreply.github.com"
-            git config --local user.name "github-actions[bot]"
-            git commit -m "docs: auto-update documentation based on changes in next branch
-
-            This PR was automatically generated to update documentation based on recent changes.
-            
-            Original commit: ${{ inputs.commit_message }}
-            
-            Co-authored-by: Claude <claude-assistant@anthropic.com>"
-          fi
-
-      - name: Push changes and create PR
-        if: steps.check-changes.outputs.has_changes == 'true'
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          git push origin ${{ steps.create-branch.outputs.branch_name }}
-
-          # Create PR using GitHub CLI
-          gh pr create \
-            --title "docs: update documentation for recent changes" \
-            --body "## 📚 Documentation Update
-
-            This PR automatically updates documentation based on recent changes merged to the \`next\` branch.
-
-            ### Original Changes
-            **Commit:** ${{ inputs.commit_sha }}
-            **Message:** ${{ inputs.commit_message }}
-            
-            ### Changed Files in Original Commit
-            \`\`\`
-            ${{ inputs.changed_files }}
-            \`\`\`
-
-            ### Documentation Updates
-            This PR includes documentation updates to reflect the changes above. Please review to ensure:
-            - [ ] Documentation accurately reflects the changes
-            - [ ] Examples are correct and working
-            - [ ] No important details are missing
-            - [ ] Style is consistent with existing documentation
-
-            ---
-            *This PR was automatically generated by Claude Code GitHub Action*" \
-            --base next \
-            --head ${{ steps.create-branch.outputs.branch_name }} \
-            --label "documentation" \
-            --label "automated"

.github/workflows/claude-issue-triage.yml

@@ -1,107 +0,0 @@
-name: Claude Issue Triage
-# description: Automatically triage GitHub issues using Claude Code
-
-on:
-  issues:
-    types: [opened]
-
-jobs:
-  triage-issue:
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
-      issues: write
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Create triage prompt
-        run: |
-          mkdir -p /tmp/claude-prompts
-          cat > /tmp/claude-prompts/triage-prompt.txt << 'EOF'
-          You're an issue triage assistant for GitHub issues. Your task is to analyze the issue and select appropriate labels from the provided list.
-
-          IMPORTANT: Don't post any comments or messages to the issue. Your only action should be to apply labels.
-
-          Issue Information:
-          - REPO: ${{ github.repository }}
-          - ISSUE_NUMBER: ${{ github.event.issue.number }}
-
-          TASK OVERVIEW:
-
-          1. First, fetch the list of labels available in this repository by running: `gh label list`. Run exactly this command with nothing else.
-
-          2. Next, use the GitHub tools to get context about the issue:
-             - You have access to these tools:
-               - mcp__github__get_issue: Use this to retrieve the current issue's details including title, description, and existing labels
-               - mcp__github__get_issue_comments: Use this to read any discussion or additional context provided in the comments
-               - mcp__github__update_issue: Use this to apply labels to the issue (do not use this for commenting)
-               - mcp__github__search_issues: Use this to find similar issues that might provide context for proper categorization and to identify potential duplicate issues
-               - mcp__github__list_issues: Use this to understand patterns in how other issues are labeled
-             - Start by using mcp__github__get_issue to get the issue details
-
-          3. Analyze the issue content, considering:
-             - The issue title and description
-             - The type of issue (bug report, feature request, question, etc.)
-             - Technical areas mentioned
-             - Severity or priority indicators
-             - User impact
-             - Components affected
-
-          4. Select appropriate labels from the available labels list provided above:
-             - Choose labels that accurately reflect the issue's nature
-             - Be specific but comprehensive
-             - Select priority labels if you can determine urgency (high-priority, med-priority, or low-priority)
-             - Consider platform labels (android, ios) if applicable
-             - If you find similar issues using mcp__github__search_issues, consider using a "duplicate" label if appropriate. Only do so if the issue is a duplicate of another OPEN issue.
-
-          5. Apply the selected labels:
-             - Use mcp__github__update_issue to apply your selected labels
-             - DO NOT post any comments explaining your decision
-             - DO NOT communicate directly with users
-             - If no labels are clearly applicable, do not apply any labels
-
-          IMPORTANT GUIDELINES:
-          - Be thorough in your analysis
-          - Only select labels from the provided list above
-          - DO NOT post any comments to the issue
-          - Your ONLY action should be to apply labels using mcp__github__update_issue
-          - It's okay to not add any labels if none are clearly applicable
-          EOF
-
-      - name: Setup GitHub MCP Server
-        run: |
-          mkdir -p /tmp/mcp-config
-          cat > /tmp/mcp-config/mcp-servers.json << 'EOF'
-          {
-            "mcpServers": {
-              "github": {
-                "command": "docker",
-                "args": [
-                  "run",
-                  "-i",
-                  "--rm",
-                  "-e",
-                  "GITHUB_PERSONAL_ACCESS_TOKEN",
-                  "ghcr.io/github/github-mcp-server:sha-7aced2b"
-                ],
-                "env": {
-                  "GITHUB_PERSONAL_ACCESS_TOKEN": "${{ secrets.GITHUB_TOKEN }}"
-                }
-              }
-            }
-          }
-          EOF
-
-      - name: Run Claude Code for Issue Triage
-        uses: anthropics/claude-code-base-action@beta
-        with:
-          prompt_file: /tmp/claude-prompts/triage-prompt.txt
-          allowed_tools: "Bash(gh label list),mcp__github__get_issue,mcp__github__get_issue_comments,mcp__github__update_issue,mcp__github__search_issues,mcp__github__list_issues"
-          timeout_minutes: "5"
-          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          mcp_config: /tmp/mcp-config/mcp-servers.json
-          claude_env: |
-            GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/claude.yml

@@ -1,36 +0,0 @@
-name: Claude Code
-
-on:
-  issue_comment:
-    types: [created]
-  pull_request_review_comment:
-    types: [created]
-  issues:
-    types: [opened, assigned]
-  pull_request_review:
-    types: [submitted]
-
-jobs:
-  claude:
-    if: |
-      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
-      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
-      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
-      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      pull-requests: read
-      issues: read
-      id-token: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
-        with:
-          fetch-depth: 1
-
-      - name: Run Claude Code
-        id: claude
-        uses: anthropics/claude-code-action@beta
-        with:
-          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}

.github/workflows/extension-ci.yml

@@ -1,140 +0,0 @@
-name: Extension CI
-
-on:
-  push:
-    branches:
-      - main
-      - next
-    paths:
-      - 'apps/extension/**'
-      - '.github/workflows/extension-ci.yml'
-  pull_request:
-    branches:
-      - main
-      - next
-    paths:
-      - 'apps/extension/**'
-      - '.github/workflows/extension-ci.yml'
-
-permissions:
-  contents: read
-
-jobs:
-  setup:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 20
-
-      - name: Cache node_modules
-        uses: actions/cache@v4
-        with:
-          path: |
-            node_modules
-            */*/node_modules
-          key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
-          restore-keys: |
-            ${{ runner.os }}-node-
-
-      - name: Install Monorepo Dependencies
-        run: npm ci
-        timeout-minutes: 5
-
-  typecheck:
-    needs: setup
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 20
-
-
-      - name: Restore node_modules
-        uses: actions/cache@v4
-        with:
-          path: |
-            node_modules
-            */*/node_modules
-          key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
-          restore-keys: |
-            ${{ runner.os }}-node-
-
-      - name: Install if cache miss
-        run: npm ci
-        timeout-minutes: 3
-
-      - name: Type Check Extension
-        working-directory: apps/extension
-        run: npm run check-types
-        env:
-          FORCE_COLOR: 1
-
-  build:
-    needs: setup
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 20
-
-
-      - name: Restore node_modules
-        uses: actions/cache@v4
-        with:
-          path: |
-            node_modules
-            */*/node_modules
-          key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
-          restore-keys: |
-            ${{ runner.os }}-node-
-
-      - name: Install if cache miss
-        run: npm ci
-        timeout-minutes: 3
-
-      - name: Build Extension
-        working-directory: apps/extension
-        run: npm run build
-        env:
-          FORCE_COLOR: 1
-
-      - name: Package Extension
-        working-directory: apps/extension
-        run: npm run package
-        env:
-          FORCE_COLOR: 1
-
-      - name: Verify Package Contents
-        working-directory: apps/extension
-        run: |
-          echo "Checking vsix-build contents..."
-          ls -la vsix-build/
-          echo "Checking dist contents..."
-          ls -la vsix-build/dist/
-          echo "Checking package.json exists..."
-          test -f vsix-build/package.json
-
-      - name: Create VSIX Package (Test)
-        working-directory: apps/extension/vsix-build
-        run: npx vsce package --no-dependencies
-        env:
-          FORCE_COLOR: 1
-
-      - name: Upload Extension Artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: extension-package
-          path: |
-            apps/extension/vsix-build/*.vsix
-            apps/extension/dist/
-          retention-days: 30
-

.github/workflows/extension-release.yml

@@ -1,110 +0,0 @@
-name: Extension Release
-
-on:
-  push:
-    tags:
-      - "extension@*"
-
-permissions:
-  contents: write
-
-concurrency: extension-release-${{ github.ref }}
-
-jobs:
-  publish-extension:
-    runs-on: ubuntu-latest
-    environment: extension-release
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 20
-
-      - name: Cache node_modules
-        uses: actions/cache@v4
-        with:
-          path: |
-            node_modules
-            */*/node_modules
-          key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
-          restore-keys: |
-            ${{ runner.os }}-node-
-
-      - name: Install Monorepo Dependencies
-        run: npm ci
-        timeout-minutes: 5
-
-      - name: Type Check Extension
-        working-directory: apps/extension
-        run: npm run check-types
-        env:
-          FORCE_COLOR: 1
-
-      - name: Build Extension
-        working-directory: apps/extension
-        run: npm run build
-        env:
-          FORCE_COLOR: 1
-
-      - name: Package Extension
-        working-directory: apps/extension
-        run: npm run package
-        env:
-          FORCE_COLOR: 1
-
-      - name: Create VSIX Package
-        working-directory: apps/extension/vsix-build
-        run: npx vsce package --no-dependencies
-        env:
-          FORCE_COLOR: 1
-
-      - name: Get VSIX filename
-        id: vsix-info
-        working-directory: apps/extension/vsix-build
-        run: |
-          VSIX_FILE=$(find . -maxdepth 1 -name "*.vsix" -type f | head -n1 | xargs basename)
-          if [ -z "$VSIX_FILE" ]; then
-            echo "Error: No VSIX file found"
-            exit 1
-          fi
-          echo "vsix-filename=$VSIX_FILE" >> "$GITHUB_OUTPUT"
-          echo "Found VSIX: $VSIX_FILE"
-
-      - name: Publish to VS Code Marketplace
-        working-directory: apps/extension/vsix-build
-        run: npx vsce publish --packagePath "${{ steps.vsix-info.outputs.vsix-filename }}"
-        env:
-          VSCE_PAT: ${{ secrets.VSCE_PAT }}
-          FORCE_COLOR: 1
-
-      - name: Install Open VSX CLI
-        run: npm install -g ovsx
-
-      - name: Publish to Open VSX Registry
-        working-directory: apps/extension/vsix-build
-        run: ovsx publish "${{ steps.vsix-info.outputs.vsix-filename }}"
-        env:
-          OVSX_PAT: ${{ secrets.OVSX_PAT }}
-          FORCE_COLOR: 1
-
-      - name: Upload Build Artifacts
-        uses: actions/upload-artifact@v4
-        with:
-          name: extension-release-${{ github.ref_name }}
-          path: |
-            apps/extension/vsix-build/*.vsix
-            apps/extension/dist/
-          retention-days: 90
-
-  notify-success:
-    needs: publish-extension
-    if: success()
-    runs-on: ubuntu-latest
-    steps:
-      - name: Success Notification
-        run: |
-          echo "🎉 Extension ${{ github.ref_name }} successfully published!"
-          echo "📦 Available on VS Code Marketplace"
-          echo "🌍 Available on Open VSX Registry"
-          echo "🏷️ GitHub release created: ${{ github.ref_name }}"

.github/workflows/log-issue-events.yml

@@ -1,176 +0,0 @@
-name: Log GitHub Issue Events
-
-on:
-  issues:
-    types: [opened, closed]
-
-jobs:
-  log-issue-created:
-    if: github.event.action == 'opened'
-    runs-on: ubuntu-latest
-    timeout-minutes: 5
-    permissions:
-      contents: read
-      issues: read
-
-    steps:
-      - name: Log issue creation to Statsig
-        env:
-          STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}
-        run: |
-          ISSUE_NUMBER=${{ github.event.issue.number }}
-          REPO=${{ github.repository }}
-          ISSUE_TITLE=$(echo '${{ github.event.issue.title }}' | sed "s/'/'\\\\''/g")
-          AUTHOR="${{ github.event.issue.user.login }}"
-          CREATED_AT="${{ github.event.issue.created_at }}"
-
-          if [ -z "$STATSIG_API_KEY" ]; then
-            echo "STATSIG_API_KEY not found, skipping Statsig logging"
-            exit 0
-          fi
-
-          # Prepare the event payload
-          EVENT_PAYLOAD=$(jq -n \
-            --arg issue_number "$ISSUE_NUMBER" \
-            --arg repo "$REPO" \
-            --arg title "$ISSUE_TITLE" \
-            --arg author "$AUTHOR" \
-            --arg created_at "$CREATED_AT" \
-            '{
-              events: [{
-                eventName: "github_issue_created",
-                value: 1,
-                metadata: {
-                  repository: $repo,
-                  issue_number: ($issue_number | tonumber),
-                  issue_title: $title,
-                  issue_author: $author,
-                  created_at: $created_at
-                },
-                time: (now | floor | tostring)
-              }]
-            }')
-
-          # Send to Statsig API
-          echo "Logging issue creation to Statsig for issue #${ISSUE_NUMBER}"
-
-          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST https://events.statsigapi.net/v1/log_event \
-            -H "Content-Type: application/json" \
-            -H "STATSIG-API-KEY: ${STATSIG_API_KEY}" \
-            -d "$EVENT_PAYLOAD")
-
-          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
-          BODY=$(echo "$RESPONSE" | head -n-1)
-
-          if [ "$HTTP_CODE" -eq 200 ] || [ "$HTTP_CODE" -eq 202 ]; then
-            echo "Successfully logged issue creation for issue #${ISSUE_NUMBER}"
-          else
-            echo "Failed to log issue creation for issue #${ISSUE_NUMBER}. HTTP ${HTTP_CODE}: ${BODY}"
-          fi
-
-  log-issue-closed:
-    if: github.event.action == 'closed'
-    runs-on: ubuntu-latest
-    timeout-minutes: 5
-    permissions:
-      contents: read
-      issues: read
-
-    steps:
-      - name: Log issue closure to Statsig
-        env:
-          STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          ISSUE_NUMBER=${{ github.event.issue.number }}
-          REPO=${{ github.repository }}
-          ISSUE_TITLE=$(echo '${{ github.event.issue.title }}' | sed "s/'/'\\\\''/g")
-          CLOSED_BY="${{ github.event.issue.closed_by.login }}"
-          CLOSED_AT="${{ github.event.issue.closed_at }}"
-          STATE_REASON="${{ github.event.issue.state_reason }}"
-
-          if [ -z "$STATSIG_API_KEY" ]; then
-            echo "STATSIG_API_KEY not found, skipping Statsig logging"
-            exit 0
-          fi
-
-          # Get additional issue data via GitHub API
-          echo "Fetching additional issue data for #${ISSUE_NUMBER}"
-          ISSUE_DATA=$(curl -s -H "Authorization: token ${GITHUB_TOKEN}" \
-            -H "Accept: application/vnd.github.v3+json" \
-            "https://api.github.com/repos/${REPO}/issues/${ISSUE_NUMBER}")
-
-          COMMENTS_COUNT=$(echo "$ISSUE_DATA" | jq -r '.comments')
-
-          # Get reactions data
-          REACTIONS_DATA=$(curl -s -H "Authorization: token ${GITHUB_TOKEN}" \
-            -H "Accept: application/vnd.github.v3+json" \
-            "https://api.github.com/repos/${REPO}/issues/${ISSUE_NUMBER}/reactions")
-
-          REACTIONS_COUNT=$(echo "$REACTIONS_DATA" | jq '. | length')
-
-          # Check if issue was closed automatically (by checking if closed_by is a bot)
-          CLOSED_AUTOMATICALLY="false"
-          if [[ "$CLOSED_BY" == *"[bot]"* ]]; then
-            CLOSED_AUTOMATICALLY="true"
-          fi
-
-          # Check if closed as duplicate by state_reason
-          CLOSED_AS_DUPLICATE="false"
-          if [ "$STATE_REASON" = "duplicate" ]; then
-            CLOSED_AS_DUPLICATE="true"
-          fi
-
-          # Prepare the event payload
-          EVENT_PAYLOAD=$(jq -n \
-            --arg issue_number "$ISSUE_NUMBER" \
-            --arg repo "$REPO" \
-            --arg title "$ISSUE_TITLE" \
-            --arg closed_by "$CLOSED_BY" \
-            --arg closed_at "$CLOSED_AT" \
-            --arg state_reason "$STATE_REASON" \
-            --arg comments_count "$COMMENTS_COUNT" \
-            --arg reactions_count "$REACTIONS_COUNT" \
-            --arg closed_automatically "$CLOSED_AUTOMATICALLY" \
-            --arg closed_as_duplicate "$CLOSED_AS_DUPLICATE" \
-            '{
-              events: [{
-                eventName: "github_issue_closed",
-                value: 1,
-                metadata: {
-                  repository: $repo,
-                  issue_number: ($issue_number | tonumber),
-                  issue_title: $title,
-                  closed_by: $closed_by,
-                  closed_at: $closed_at,
-                  state_reason: $state_reason,
-                  comments_count: ($comments_count | tonumber),
-                  reactions_count: ($reactions_count | tonumber),
-                  closed_automatically: ($closed_automatically | test("true")),
-                  closed_as_duplicate: ($closed_as_duplicate | test("true"))
-                },
-                time: (now | floor | tostring)
-              }]
-            }')
-
-          # Send to Statsig API
-          echo "Logging issue closure to Statsig for issue #${ISSUE_NUMBER}"
-
-          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST https://events.statsigapi.net/v1/log_event \
-            -H "Content-Type: application/json" \
-            -H "STATSIG-API-KEY: ${STATSIG_API_KEY}" \
-            -d "$EVENT_PAYLOAD")
-
-          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
-          BODY=$(echo "$RESPONSE" | head -n-1)
-
-          if [ "$HTTP_CODE" -eq 200 ] || [ "$HTTP_CODE" -eq 202 ]; then
-            echo "Successfully logged issue closure for issue #${ISSUE_NUMBER}"
-            echo "Closed by: $CLOSED_BY"
-            echo "Comments: $COMMENTS_COUNT"
-            echo "Reactions: $REACTIONS_COUNT"
-            echo "Closed automatically: $CLOSED_AUTOMATICALLY"
-            echo "Closed as duplicate: $CLOSED_AS_DUPLICATE"
-          else
-            echo "Failed to log issue closure for issue #${ISSUE_NUMBER}. HTTP ${HTTP_CODE}: ${BODY}"
-          fi

.github/workflows/pre-release.yml

@@ -3,13 +3,11 @@ name: Pre-Release (RC)
 on:
   workflow_dispatch: # Allows manual triggering from GitHub UI/API
 
-concurrency: pre-release-${{ github.ref_name }}
+concurrency: pre-release-${{ github.ref }}
+
 jobs:
   rc:
     runs-on: ubuntu-latest
-    # Only allow pre-releases on non-main branches
-    if: github.ref != 'refs/heads/main'
-    environment: extension-release
     steps:
       - uses: actions/checkout@v4
         with:
@@ -18,7 +16,7 @@ jobs:
       - uses: actions/setup-node@v4
         with:
           node-version: 20
-          cache: "npm"
+          cache: 'npm'
 
       - name: Cache node_modules
         uses: actions/cache@v4
@@ -34,30 +32,10 @@ jobs:
         run: npm ci
         timeout-minutes: 2
 
-      - name: Enter RC mode (if not already in RC mode)
+      - name: Enter RC mode
         run: |
-          # Check if we're in pre-release mode with the "rc" tag
-          if [ -f .changeset/pre.json ]; then
-            MODE=$(jq -r '.mode' .changeset/pre.json 2>/dev/null || echo '')
-            TAG=$(jq -r '.tag' .changeset/pre.json 2>/dev/null || echo '')
-            
-            if [ "$MODE" = "exit" ]; then
-              echo "Pre-release mode is in 'exit' state, re-entering RC mode..."
-              npx changeset pre enter rc
-            elif [ "$MODE" = "pre" ] && [ "$TAG" != "rc" ]; then
-              echo "In pre-release mode but with wrong tag ($TAG), switching to RC..."
-              npx changeset pre exit
-              npx changeset pre enter rc
-            elif [ "$MODE" = "pre" ] && [ "$TAG" = "rc" ]; then
-              echo "Already in RC pre-release mode"
-            else
-              echo "Unknown mode state: $MODE, entering RC mode..."
-              npx changeset pre enter rc
-            fi
-          else
-            echo "No pre.json found, entering RC mode..."
-            npx changeset pre enter rc
-          fi
+          npx changeset pre exit || true
+          npx changeset pre enter rc
 
       - name: Version RC packages
         run: npx changeset version
@@ -65,31 +43,20 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
 
-      - name: Run format
-        run: npm run format
-        env:
-          FORCE_COLOR: 1
-
-      - name: Build packages
-        run: npm run turbo:build
-        env:
-          NODE_ENV: production
-          FORCE_COLOR: 1
-          TM_PUBLIC_BASE_DOMAIN: ${{ secrets.TM_PUBLIC_BASE_DOMAIN }}
-          TM_PUBLIC_SUPABASE_URL: ${{ secrets.TM_PUBLIC_SUPABASE_URL }}
-          TM_PUBLIC_SUPABASE_ANON_KEY: ${{ secrets.TM_PUBLIC_SUPABASE_ANON_KEY }}
-
       - name: Create Release Candidate Pull Request or Publish Release Candidate to npm
         uses: changesets/action@v1
         with:
-          publish: npx changeset publish
+          publish: npm run release
         env:
           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'

.github/workflows/release-check.yml

@@ -1,21 +0,0 @@
-name: Release Check
-
-on:
-  pull_request:
-    branches:
-      - main
-
-concurrency:
-  group: release-check-${{ github.head_ref }}
-  cancel-in-progress: true
-
-jobs:
-  check-release-mode:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Check release mode
-        run: node ./.github/scripts/check-pre-release-mode.mjs "pull_request"

.github/workflows/release.yml

@@ -6,11 +6,6 @@ on:
 
 concurrency: ${{ github.workflow }}-${{ github.ref }}
 
-permissions:
-  contents: write
-  pull-requests: write
-  id-token: write
-
 jobs:
   release:
     runs-on: ubuntu-latest
@@ -22,7 +17,7 @@ jobs:
       - uses: actions/setup-node@v4
         with:
           node-version: 20
-          cache: "npm"
+          cache: 'npm'
 
       - name: Cache node_modules
         uses: actions/cache@v4
@@ -38,22 +33,13 @@ jobs:
         run: npm ci
         timeout-minutes: 2
 
-      - name: Check pre-release mode
-        run: node ./.github/scripts/check-pre-release-mode.mjs "main"
-
-      - name: Build packages
-        run: npm run turbo:build
-        env:
-          NODE_ENV: production
-          FORCE_COLOR: 1
-          TM_PUBLIC_BASE_DOMAIN: ${{ secrets.TM_PUBLIC_BASE_DOMAIN }}
-          TM_PUBLIC_SUPABASE_URL: ${{ secrets.TM_PUBLIC_SUPABASE_URL }}
-          TM_PUBLIC_SUPABASE_ANON_KEY: ${{ secrets.TM_PUBLIC_SUPABASE_ANON_KEY }}
+      - name: Exit pre-release mode (safety check)
+        run: npx changeset pre exit || true
 
       - name: Create Release Pull Request or Publish to npm
         uses: changesets/action@v1
         with:
-          publish: node ./.github/scripts/release.mjs
+          publish: npm run release
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           NPM_TOKEN: ${{ secrets.NPM_TOKEN }}

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

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

.github/workflows/weekly-metrics-discord.yml

@@ -1,108 +0,0 @@
-name: Weekly Metrics to Discord
-# description: Sends weekly metrics summary to Discord channel
-
-on:
-  schedule:
-    - cron: "0 9 * * 1" # Every Monday at 9 AM
-  workflow_dispatch:
-
-permissions:
-  contents: read
-  issues: read
-  pull-requests: read
-
-jobs:
-  weekly-metrics:
-    runs-on: ubuntu-latest
-    env:
-      DISCORD_WEBHOOK: ${{ secrets.DISCORD_METRICS_WEBHOOK }}
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: '20'
-
-      - name: Get dates for last 14 days
-        run: |
-          set -Eeuo pipefail
-          # Last 14 days
-          first_day=$(date -d "14 days ago" +%Y-%m-%d)
-          last_day=$(date +%Y-%m-%d)
-
-          echo "first_day=$first_day" >> $GITHUB_ENV
-          echo "last_day=$last_day" >> $GITHUB_ENV
-          echo "week_of=$(date -d '7 days ago' +'Week of %B %d, %Y')" >> $GITHUB_ENV
-          echo "date_range=Past 14 days ($first_day to $last_day)" >> $GITHUB_ENV
-
-      - name: Generate issue metrics
-        uses: github/issue-metrics@v3
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          SEARCH_QUERY: "repo:${{ github.repository }} is:issue created:${{ env.first_day }}..${{ env.last_day }}"
-          HIDE_TIME_TO_ANSWER: true
-          HIDE_LABEL_METRICS: false
-          OUTPUT_FILE: issue_metrics.md
-
-      - name: Generate PR created metrics
-        uses: github/issue-metrics@v3
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          SEARCH_QUERY: "repo:${{ github.repository }} is:pr created:${{ env.first_day }}..${{ env.last_day }}"
-          OUTPUT_FILE: pr_created_metrics.md
-
-      - name: Generate PR merged metrics
-        uses: github/issue-metrics@v3
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          SEARCH_QUERY: "repo:${{ github.repository }} is:pr is:merged merged:${{ env.first_day }}..${{ env.last_day }}"
-          OUTPUT_FILE: pr_merged_metrics.md
-
-      - name: Debug generated metrics
-        run: |
-          set -Eeuo pipefail
-          echo "Listing markdown files in workspace:"
-          ls -la *.md || true
-          for f in issue_metrics.md pr_created_metrics.md pr_merged_metrics.md; do
-            if [ -f "$f" ]; then
-              echo "== $f (first 10 lines) =="
-              head -n 10 "$f"
-            else
-              echo "Missing $f"
-            fi
-          done
-
-      - name: Parse metrics
-        id: metrics
-        run: node .github/scripts/parse-metrics.mjs
-
-      - name: Send to Discord
-        uses: sarisia/actions-status-discord@v1
-        if: env.DISCORD_WEBHOOK != ''
-        with:
-          webhook: ${{ env.DISCORD_WEBHOOK }}
-          status: Success
-          title: "📊 Weekly Metrics Report"
-          description: |
-            **${{ env.week_of }}**
-            *${{ env.date_range }}*
-
-            **🎯 Issues**
-            • Created: ${{ steps.metrics.outputs.issues_created }}
-            • Closed: ${{ steps.metrics.outputs.issues_closed }}
-            • Avg Response Time: ${{ steps.metrics.outputs.issue_avg_first_response }}
-            • Avg Time to Close: ${{ steps.metrics.outputs.issue_avg_time_to_close }}
-
-            **🔀 Pull Requests**
-            • Created: ${{ steps.metrics.outputs.prs_created }}
-            • Merged: ${{ steps.metrics.outputs.prs_merged }}
-            • Avg Response Time: ${{ steps.metrics.outputs.pr_avg_first_response }}
-            • Avg Time to Merge: ${{ steps.metrics.outputs.pr_avg_merge_time }}
-
-            **📈 Visual Analytics**
-            https://repobeats.axiom.co/api/embed/b439f28f0ab5bd7a2da19505355693cd2c55bfd4.svg
-          color: 0x58AFFF
-          username: Task Master Metrics Bot
-          avatar_url: https://raw.githubusercontent.com/eyaltoledano/claude-task-master/main/images/logo.png

.gitignore

@@ -19,25 +19,12 @@ npm-debug.log*
 yarn-debug.log*
 yarn-error.log*
 lerna-debug.log*
-
-# Coverage directory used by tools like istanbul
-coverage/
-*.lcov
-
-# Jest cache
-.jest/
-
-# Test temporary files and directories
-tests/temp/
 tests/e2e/_runs/
 tests/e2e/log/
-tests/**/*.log
-tests/**/coverage/
 
-# Test database files (if any)
-tests/**/*.db
-tests/**/*.sqlite
-tests/**/*.sqlite3
+# Coverage directory used by tools like istanbul
+coverage
+*.lcov
 
 # Optional npm cache directory
 .npm
@@ -77,26 +64,3 @@ dev-debug.log
 
 # NPMRC
 .npmrc
-
-# Added by Task Master AI
-# Editor directories and files
-.idea
-.vscode
-*.suo
-*.ntvs*
-*.njsproj
-*.sln
-*.sw?
-
-# VS Code extension test files
-.vscode-test/
-apps/extension/.vscode-test/
-
-# apps/extension
-apps/extension/vsix-build/
-
-# turbo
-.turbo
-
-# TaskMaster Workflow State (now stored in ~/.taskmaster/sessions/)
-# No longer needed in .gitignore as state is stored globally

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

@@ -1,23 +0,0 @@
-{
-  "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

@@ -1,16 +0,0 @@
-{
-  "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

@@ -1,13 +0,0 @@
-{
-  "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

@@ -1,13 +0,0 @@
-{
-  "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

@@ -1,13 +0,0 @@
-{
-  "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

@@ -1,17 +0,0 @@
-{
-  "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

@@ -1,23 +0,0 @@
-{
-  "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

@@ -1,19 +0,0 @@
-{
-	"mcpServers": {
-		"task-master-ai": {
-			"command": "npx",
-			"args": ["-y", "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

@@ -1,422 +0,0 @@
----
-inclusion: always
----
-
-# Taskmaster Development Workflow
-
-This guide outlines the standard process for using Taskmaster to manage software development projects. It is written as a set of instructions for you, the AI agent.
-
-- **Your Default Stance**: For most projects, the user can work directly within the `master` task context. Your initial actions should operate on this default context unless a clear pattern for multi-context work emerges.
-- **Your Goal**: Your role is to elevate the user's workflow by intelligently introducing advanced features like **Tagged Task Lists** when you detect the appropriate context. Do not force tags on the user; suggest them as a helpful solution to a specific need.
-
-## The Basic Loop
-The fundamental development cycle you will facilitate is:
-1.  **`list`**: Show the user what needs to be done.
-2.  **`next`**: Help the user decide what to work on.
-3.  **`show <id>`**: Provide details for a specific task.
-4.  **`expand <id>`**: Break down a complex task into smaller, manageable subtasks.
-5.  **Implement**: The user writes the code and tests.
-6.  **`update-subtask`**: Log progress and findings on behalf of the user.
-7.  **`set-status`**: Mark tasks and subtasks as `done` as work is completed.
-8.  **Repeat**.
-
-All your standard command executions should operate on the user's current task context, which defaults to `master`.
-
----
-
-## Standard Development Workflow Process
-
-### Simple Workflow (Default Starting Point)
-
-For new projects or when users are getting started, operate within the `master` tag context:
-
--   Start new projects by running `initialize_project` tool / `task-master init` or `parse_prd` / `task-master parse-prd --input='<prd-file.txt>'` (see @`taskmaster.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.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.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`)
-
----
-
-## Leveling Up: Agent-Led Multi-Context Workflows
-
-While the basic workflow is powerful, your primary opportunity to add value is by identifying when to introduce **Tagged Task Lists**. These patterns are your tools for creating a more organized and efficient development environment for the user, especially if you detect agentic or parallel development happening across the same session.
-
-**Critical Principle**: Most users should never see a difference in their experience. Only introduce advanced workflows when you detect clear indicators that the project has evolved beyond simple task management.
-
-### When to Introduce Tags: Your Decision Patterns
-
-Here are the patterns to look for. When you detect one, you should propose the corresponding workflow to the user.
-
-#### Pattern 1: Simple Git Feature Branching
-This is the most common and direct use case for tags.
-
-- **Trigger**: The user creates a new git branch (e.g., `git checkout -b feature/user-auth`).
-- **Your Action**: Propose creating a new tag that mirrors the branch name to isolate the feature's tasks from `master`.
-- **Your Suggested Prompt**: *"I see you've created a new branch named 'feature/user-auth'. To keep all related tasks neatly organized and separate from your main list, I can create a corresponding task tag for you. This helps prevent merge conflicts in your `tasks.json` file later. Shall I create the 'feature-user-auth' tag?"*
-- **Tool to Use**: `task-master add-tag --from-branch`
-
-#### Pattern 2: Team Collaboration
-- **Trigger**: The user mentions working with teammates (e.g., "My teammate Alice is handling the database schema," or "I need to review Bob's work on the API.").
-- **Your Action**: Suggest creating a separate tag for the user's work to prevent conflicts with shared master context.
-- **Your Suggested Prompt**: *"Since you're working with Alice, I can create a separate task context for your work to avoid conflicts. This way, Alice can continue working with the master list while you have your own isolated context. When you're ready to merge your work, we can coordinate the tasks back to master. Shall I create a tag for your current work?"*
-- **Tool to Use**: `task-master add-tag my-work --copy-from-current --description="My tasks while collaborating with Alice"`
-
-#### Pattern 3: Experiments or Risky Refactors
-- **Trigger**: The user wants to try something that might not be kept (e.g., "I want to experiment with switching our state management library," or "Let's refactor the old API module, but I want to keep the current tasks as a reference.").
-- **Your Action**: Propose creating a sandboxed tag for the experimental work.
-- **Your Suggested Prompt**: *"This sounds like a great experiment. To keep these new tasks separate from our main plan, I can create a temporary 'experiment-zustand' tag for this work. If we decide not to proceed, we can simply delete the tag without affecting the main task list. Sound good?"*
-- **Tool to Use**: `task-master add-tag experiment-zustand --description="Exploring Zustand migration"`
-
-#### Pattern 4: Large Feature Initiatives (PRD-Driven)
-This is a more structured approach for significant new features or epics.
-
-- **Trigger**: The user describes a large, multi-step feature that would benefit from a formal plan.
-- **Your Action**: Propose a comprehensive, PRD-driven workflow.
-- **Your Suggested Prompt**: *"This sounds like a significant new feature. To manage this effectively, I suggest we create a dedicated task context for it. Here's the plan: I'll create a new tag called 'feature-xyz', then we can draft a Product Requirements Document (PRD) together to scope the work. Once the PRD is ready, I'll automatically generate all the necessary tasks within that new tag. How does that sound?"*
-- **Your Implementation Flow**:
-    1.  **Create an empty tag**: `task-master add-tag feature-xyz --description "Tasks for the new XYZ feature"`. You can also start by creating a git branch if applicable, and then create the tag from that branch.
-    2.  **Collaborate & Create PRD**: Work with the user to create a detailed PRD file (e.g., `.taskmaster/docs/feature-xyz-prd.txt`).
-    3.  **Parse PRD into the new tag**: `task-master parse-prd .taskmaster/docs/feature-xyz-prd.txt --tag feature-xyz`
-    4.  **Prepare the new task list**: Follow up by suggesting `analyze-complexity` and `expand-all` for the newly created tasks within the `feature-xyz` tag.
-
-#### Pattern 5: Version-Based Development
-Tailor your approach based on the project maturity indicated by tag names.
-
-- **Prototype/MVP Tags** (`prototype`, `mvp`, `poc`, `v0.x`):
-  - **Your Approach**: Focus on speed and functionality over perfection
-  - **Task Generation**: Create tasks that emphasize "get it working" over "get it perfect"
-  - **Complexity Level**: Lower complexity, fewer subtasks, more direct implementation paths
-  - **Research Prompts**: Include context like "This is a prototype - prioritize speed and basic functionality over optimization"
-  - **Example Prompt Addition**: *"Since this is for the MVP, I'll focus on tasks that get core functionality working quickly rather than over-engineering."*
-
-- **Production/Mature Tags** (`v1.0+`, `production`, `stable`):
-  - **Your Approach**: Emphasize robustness, testing, and maintainability
-  - **Task Generation**: Include comprehensive error handling, testing, documentation, and optimization
-  - **Complexity Level**: Higher complexity, more detailed subtasks, thorough implementation paths
-  - **Research Prompts**: Include context like "This is for production - prioritize reliability, performance, and maintainability"
-  - **Example Prompt Addition**: *"Since this is for production, I'll ensure tasks include proper error handling, testing, and documentation."*
-
-### Advanced Workflow (Tag-Based & PRD-Driven)
-
-**When to Transition**: Recognize when the project has evolved (or has initiated a project which existing code) beyond simple task management. Look for these indicators:
-- User mentions teammates or collaboration needs
-- Project has grown to 15+ tasks with mixed priorities
-- User creates feature branches or mentions major initiatives
-- User initializes Taskmaster on an existing, complex codebase
-- User describes large features that would benefit from dedicated planning
-
-**Your Role in Transition**: Guide the user to a more sophisticated workflow that leverages tags for organization and PRDs for comprehensive planning.
-
-#### Master List Strategy (High-Value Focus)
-Once you transition to tag-based workflows, the `master` tag should ideally contain only:
-- **High-level deliverables** that provide significant business value
-- **Major milestones** and epic-level features
-- **Critical infrastructure** work that affects the entire project
-- **Release-blocking** items
-
-**What NOT to put in master**:
-- Detailed implementation subtasks (these go in feature-specific tags' parent tasks)
-- Refactoring work (create dedicated tags like `refactor-auth`)
-- Experimental features (use `experiment-*` tags)
-- Team member-specific tasks (use person-specific tags)
-
-#### PRD-Driven Feature Development
-
-**For New Major Features**:
-1. **Identify the Initiative**: When user describes a significant feature
-2. **Create Dedicated Tag**: `add_tag feature-[name] --description="[Feature description]"`
-3. **Collaborative PRD Creation**: Work with user to create comprehensive PRD in `.taskmaster/docs/feature-[name]-prd.txt`
-4. **Parse & Prepare**: 
-   - `parse_prd .taskmaster/docs/feature-[name]-prd.txt --tag=feature-[name]`
-   - `analyze_project_complexity --tag=feature-[name] --research`
-   - `expand_all --tag=feature-[name] --research`
-5. **Add Master Reference**: Create a high-level task in `master` that references the feature tag
-
-**For Existing Codebase Analysis**:
-When users initialize Taskmaster on existing projects:
-1. **Codebase Discovery**: Use your native tools for producing deep context about the code base. You may use `research` tool with `--tree` and `--files` to collect up to date information using the existing architecture as context.
-2. **Collaborative Assessment**: Work with user to identify improvement areas, technical debt, or new features
-3. **Strategic PRD Creation**: Co-author PRDs that include:
-   - Current state analysis (based on your codebase research)
-   - Proposed improvements or new features
-   - Implementation strategy considering existing code
-4. **Tag-Based Organization**: Parse PRDs into appropriate tags (`refactor-api`, `feature-dashboard`, `tech-debt`, etc.)
-5. **Master List Curation**: Keep only the most valuable initiatives in master
-
-The parse-prd's `--append` flag enables the user to parse multiple PRDs within tags or across tags. PRDs should be focused and the number of tasks they are parsed into should be strategically chosen relative to the PRD's complexity and level of detail.
-
-### Workflow Transition Examples
-
-**Example 1: Simple → Team-Based**
-```
-User: "Alice is going to help with the API work"
-Your Response: "Great! To avoid conflicts, I'll create a separate task context for your work. Alice can continue with the master list while you work in your own context. When you're ready to merge, we can coordinate the tasks back together."
-Action: add_tag my-api-work --copy-from-current --description="My API tasks while collaborating with Alice"
-```
-
-**Example 2: Simple → PRD-Driven**
-```
-User: "I want to add a complete user dashboard with analytics, user management, and reporting"
-Your Response: "This sounds like a major feature that would benefit from detailed planning. Let me create a dedicated context for this work and we can draft a PRD together to ensure we capture all requirements."
-Actions: 
-1. add_tag feature-dashboard --description="User dashboard with analytics and management"
-2. Collaborate on PRD creation
-3. parse_prd dashboard-prd.txt --tag=feature-dashboard
-4. Add high-level "User Dashboard" task to master
-```
-
-**Example 3: Existing Project → Strategic Planning**
-```
-User: "I just initialized Taskmaster on my existing React app. It's getting messy and I want to improve it."
-Your Response: "Let me research your codebase to understand the current architecture, then we can create a strategic plan for improvements."
-Actions:
-1. research "Current React app architecture and improvement opportunities" --tree --files=src/
-2. Collaborate on improvement PRD based on findings
-3. Create tags for different improvement areas (refactor-components, improve-state-management, etc.)
-4. Keep only major improvement initiatives in master
-```
-
----
-
-## Primary Interaction: MCP Server vs. CLI
-
-Taskmaster offers two primary ways to interact:
-
-1.  **MCP Server (Recommended for Integrated Tools)**:
-    - For AI agents and integrated development environments (like 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.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.
-
-2.  **`task-master` CLI (For Users & Fallback)**:
-    - The global `task-master` command provides a user-friendly interface for direct terminal interaction.
-    - It can also serve as a fallback if the MCP server is inaccessible or a specific function isn't exposed via MCP.
-    - Install globally with `npm install -g task-master-ai` or use locally via `npx task-master-ai ...`.
-    - The CLI commands often mirror the MCP tools (e.g., `task-master list` corresponds to `get_tasks`).
-    - Refer to @`taskmaster.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)
-
-- **Data Structure**: Tasks are organized into separate contexts (tags) like "master", "feature-branch", or "v2.0".
-- **Silent Migration**: Existing projects automatically migrate to use a "master" tag with zero disruption.
-- **Context Isolation**: Tasks in different tags are completely separate. Changes in one tag do not affect any other tag.
-- **Manual Control**: The user is always in control. There is no automatic switching. You facilitate switching by using `use-tag <name>`.
-- **Full CLI & MCP Support**: All tag management commands are available through both the CLI and MCP tools for you to use. Refer to @`taskmaster.md` for a full command list.
-
----
-
-## Task Complexity Analysis
-
--   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
-
-## Task Breakdown Process
-
--   Use `expand_task` / `task-master expand --id=<id>`. It automatically uses the complexity report if found, otherwise generates default number of subtasks.
--   Use `--num=<number>` to specify an explicit number of subtasks, overriding defaults or complexity report recommendations.
--   Add `--research` flag to leverage Perplexity AI for research-backed expansion.
--   Add `--force` flag to clear existing subtasks before generating new ones (default is to append).
--   Use `--prompt="<context>"` to provide additional context when needed.
--   Review and adjust generated subtasks as necessary.
--   Use `expand_all` tool or `task-master expand --all` to expand multiple pending tasks at once, respecting flags like `--force` and `--research`.
--   If subtasks need complete replacement (regardless of the `--force` flag on `expand`), clear them first with `clear_subtasks` / `task-master clear-subtasks --id=<id>`.
-
-## Implementation Drift Handling
-
--   When implementation differs significantly from planned approach
--   When future tasks need modification due to current implementation choices
--   When new dependencies or requirements emerge
--   Use `update` / `task-master update --from=<futureTaskId> --prompt='<explanation>\nUpdate context...' --research` to update multiple future tasks.
--   Use `update_task` / `task-master update-task --id=<taskId> --prompt='<explanation>\nUpdate context...' --research` to update a single specific task.
-
-## Task Status Management
-
--   Use 'pending' for tasks ready to be worked on
--   Use 'done' for completed and verified tasks
--   Use 'deferred' for postponed tasks
--   Add custom status values as needed for project-specific workflows
-
-## Task Structure Fields
-
-- **id**: Unique identifier for the task (Example: `1`, `1.1`)
-- **title**: Brief, descriptive title (Example: `"Initialize Repo"`)
-- **description**: Concise summary of what the task involves (Example: `"Create a new repository, set up initial structure."`)
-- **status**: Current state of the task (Example: `"pending"`, `"done"`, `"deferred"`)
-- **dependencies**: IDs of prerequisite tasks (Example: `[1, 2.1]`)
-    - Dependencies are displayed with status indicators (✅ for completed, ⏱️ for pending)
-    - This helps quickly identify which prerequisite tasks are blocking work
-- **priority**: Importance level (Example: `"high"`, `"medium"`, `"low"`)
-- **details**: In-depth implementation instructions (Example: `"Use GitHub client ID/secret, handle callback, set session token."`) 
-- **testStrategy**: Verification approach (Example: `"Deploy and call endpoint to confirm 'Hello World' response."`) 
-- **subtasks**: List of smaller, more specific tasks (Example: `[{"id": 1, "title": "Configure OAuth", ...}]`) 
-- Refer to task structure details (previously linked to `tasks.md`).
-
-## Configuration Management (Updated)
-
-Taskmaster configuration is managed through two main mechanisms:
-
-1.  **`.taskmaster/config.json` File (Primary):**
-    *   Located in the project root directory.
-    *   Stores most configuration settings: AI model selections (main, research, fallback), parameters (max tokens, temperature), logging level, default subtasks/priority, project name, etc.
-    *   **Tagged System Settings**: Includes `global.defaultTag` (defaults to "master") and `tags` section for tag management configuration.
-    *   **Managed via `task-master models --setup` command.** Do not edit manually unless you know what you are doing.
-    *   **View/Set specific models via `task-master models` command or `models` MCP tool.**
-    *   Created automatically when you run `task-master models --setup` for the first time or during tagged system migration.
-
-2.  **Environment Variables (`.env` / `mcp.json`):**
-    *   Used **only** for sensitive API keys and specific endpoint URLs.
-    *   Place API keys (one per provider) in a `.env` file in the project root for CLI usage.
-    *   For MCP/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.
-    *   Automatically created during tagged system migration.
-    *   Contains: `currentTag`, `lastSwitched`, `migrationNoticeShown`.
-
-**Important:** Non-API key settings (like model selections, `MAX_TOKENS`, `TASKMASTER_LOG_LEVEL`) are **no longer configured via environment variables**. Use the `task-master models` command (or `--setup` for interactive configuration) or the `models` MCP tool.
-**If AI commands FAIL in MCP** verify that the API key for the selected provider is present in the `env` section of `.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, 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., `.kiro/steering`, `.roo/rules`) with appropriate configuration files
-
-## Determining the Next Task
-
-- Run `next_task` / `task-master next` to show the next task to work on.
-- The command identifies tasks with all dependencies satisfied
-- Tasks are prioritized by priority level, dependency count, and ID
-- The command shows comprehensive task information including:
-    - Basic task details and description
-    - Implementation details
-    - Subtasks (if they exist)
-    - Contextual suggested actions
-- Recommended before starting any new development work
-- Respects your project's dependency structure
-- Ensures tasks are completed in the appropriate sequence
-- Provides ready-to-use commands for common task actions
-
-## Viewing Specific Task Details
-
-- Run `get_task` / `task-master show <id>` to view a specific task.
-- Use dot notation for subtasks: `task-master show 1.2` (shows subtask 2 of task 1)
-- Displays comprehensive information similar to the next command, but for a specific task
-- For parent tasks, shows all subtasks and their current status
-- For subtasks, shows parent task information and relationship
-- Provides contextual suggested actions appropriate for the specific task
-- Useful for examining task details before implementation or checking status
-
-## Managing Task Dependencies
-
-- Use `add_dependency` / `task-master add-dependency --id=<id> --depends-on=<id>` to add a dependency.
-- Use `remove_dependency` / `task-master remove-dependency --id=<id> --depends-on=<id>` to remove a dependency.
-- The system prevents circular dependencies and duplicate dependency entries
-- Dependencies are checked for existence before being added or removed
-- Task files are automatically regenerated after dependency changes
-- Dependencies are visualized with status indicators in task listings and files
-
-## Task Reorganization
-
-- Use `move_task` / `task-master move --from=<id> --to=<id>` to move tasks or subtasks within the hierarchy
-- This command supports several use cases:
-  - Moving a standalone task to become a subtask (e.g., `--from=5 --to=7`)
-  - Moving a subtask to become a standalone task (e.g., `--from=5.2 --to=7`) 
-  - Moving a subtask to a different parent (e.g., `--from=5.2 --to=7.3`)
-  - Reordering subtasks within the same parent (e.g., `--from=5.2 --to=5.4`)
-  - Moving a task to a new, non-existent ID position (e.g., `--from=5 --to=25`)
-  - Moving multiple tasks at once using comma-separated IDs (e.g., `--from=10,11,12 --to=16,17,18`)
-- The system includes validation to prevent data loss:
-  - Allows moving to non-existent IDs by creating placeholder tasks
-  - Prevents moving to existing task IDs that have content (to avoid overwriting)
-  - Validates source tasks exist before attempting to move them
-- The system maintains proper parent-child relationships and dependency integrity
-- Task files are automatically regenerated after the move operation
-- This provides greater flexibility in organizing and refining your task structure as project understanding evolves
-- This is especially useful when dealing with potential merge conflicts arising from teams creating tasks on separate branches. Solve these conflicts very easily by moving your tasks and keeping theirs.
-
-## Iterative Subtask Implementation
-
-Once a task has been broken down into subtasks using `expand_task` or similar methods, follow this iterative process for implementation:
-
-1.  **Understand the Goal (Preparation):**
-    *   Use `get_task` / `task-master show <subtaskId>` (see @`taskmaster.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.
-    *   Explore the codebase to identify the precise files, functions, and even specific lines of code that will need modification.
-    *   Determine the intended code changes (diffs) and their locations.
-    *   Gather *all* relevant details from this exploration phase.
-
-3.  **Log the Plan:**
-    *   Run `update_subtask` / `task-master update-subtask --id=<subtaskId> --prompt='<detailed plan>'`.
-    *   Provide the *complete and detailed* findings from the exploration phase in the prompt. Include file paths, line numbers, proposed diffs, reasoning, and any potential challenges identified. Do not omit details. The goal is to create a rich, timestamped log within the subtask's `details`.
-
-4.  **Verify the Plan:**
-    *   Run `get_task` / `task-master show <subtaskId>` again to confirm that the detailed implementation plan has been successfully appended to the subtask's details.
-
-5.  **Begin Implementation:**
-    *   Set the subtask status using `set_task_status` / `task-master set-status --id=<subtaskId> --status=in-progress`.
-    *   Start coding based on the logged plan.
-
-6.  **Refine and Log Progress (Iteration 2+):**
-    *   As implementation progresses, you will encounter challenges, discover nuances, or confirm successful approaches.
-    *   **Before appending new information**: Briefly review the *existing* details logged in the subtask (using `get_task` or recalling from context) to ensure the update adds fresh insights and avoids redundancy.
-    *   **Regularly** use `update_subtask` / `task-master update-subtask --id=<subtaskId> --prompt='<update details>\n- What worked...\n- What didn't work...'` to append new findings.
-    *   **Crucially, log:**
-        *   What worked ("fundamental truths" discovered).
-        *   What didn't work and why (to avoid repeating mistakes).
-        *   Specific code snippets or configurations that were successful.
-        *   Decisions made, especially if confirmed with user input.
-        *   Any deviations from the initial plan and the reasoning.
-    *   The objective is to continuously enrich the subtask's details, creating a log of the implementation journey that helps the AI (and human developers) learn, adapt, and avoid repeating errors.
-
-7.  **Review & Update Rules (Post-Implementation):**
-    *   Once the implementation for the subtask is functionally complete, review all code changes and the relevant chat history.
-    *   Identify any new or modified code patterns, conventions, or best practices established during the implementation.
-    *   Create new or update existing rules following internal guidelines (previously linked to `cursor_rules.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`.
-
-9.  **Commit Changes (If using Git):**
-    *   Stage the relevant code changes and any updated/new rule files (`git add .`).
-    *   Craft a comprehensive Git commit message summarizing the work done for the subtask, including both code implementation and any rule adjustments.
-    *   Execute the commit command directly in the terminal (e.g., `git commit -m 'feat(module): Implement feature X for subtask <subtaskId>\n\n- Details about changes...\n- Updated rule Y for pattern Z'`).
-    *   Consider if a Changeset is needed according to internal versioning guidelines (previously linked to `changeset.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`).
-
-## Code Analysis & Refactoring Techniques
-
-- **Top-Level Function Search**:
-    - Useful for understanding module structure or planning refactors.
-    - Use grep/ripgrep to find exported functions/constants:
-      `rg "export (async function|function|const) \w+"` or similar patterns.
-    - Can help compare functions between files during migrations or identify potential naming conflicts.
-
----
-*This workflow provides a general guideline. Adapt it based on your specific project needs and team practices.*

.kiro/steering/kiro_rules.md

@@ -1,51 +0,0 @@
----
-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

@@ -1,70 +0,0 @@
----
-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

@@ -1,556 +0,0 @@
----
-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 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. 
-
-**Important:** Several MCP tools involve AI processing... The AI-powered tools include `parse_prd`, `analyze_project_complexity`, `update_subtask`, `update_task`, `update`, `expand_all`, `expand_task`, and `add_task`.
-
-**🏷️ Tagged Task Lists System:** Task Master now supports **tagged task lists** for multi-context task management. This allows you to maintain separate, isolated lists of tasks for different features, branches, or experiments. Existing projects are seamlessly migrated to use a default "master" tag. Most commands now support a `--tag <name>` flag to specify which context to operate on. If omitted, commands use the currently active tag.
-
----
-
-## Initialization & Setup
-
-### 1. Initialize Project (`init`)
-
-*   **MCP Tool:** `initialize_project`
-*   **CLI Command:** `task-master init [options]`
-*   **Description:** `Set up the basic Taskmaster file structure and configuration in the current directory for a new project.`
-*   **Key CLI Options:**
-    *   `--name <name>`: `Set the name for your project in Taskmaster's configuration.`
-    *   `--description <text>`: `Provide a brief description for your project.`
-    *   `--version <version>`: `Set the initial version for your project, e.g., '0.1.0'.`
-    *   `-y, --yes`: `Initialize Taskmaster quickly using default settings without interactive prompts.`
-*   **Usage:** Run this once at the beginning of a new project.
-*   **MCP Variant Description:** `Set up the basic Taskmaster file structure and configuration in the current directory for a new project by running the 'task-master init' command.`
-*   **Key MCP Parameters/Options:**
-    *   `projectName`: `Set the name for your project.` (CLI: `--name <name>`)
-    *   `projectDescription`: `Provide a brief description for your project.` (CLI: `--description <text>`)
-    *   `projectVersion`: `Set the initial version for your project, e.g., '0.1.0'.` (CLI: `--version <version>`)
-    *   `authorName`: `Author name.` (CLI: `--author <author>`)
-    *   `skipInstall`: `Skip installing dependencies. Default is false.` (CLI: `--skip-install`)
-    *   `addAliases`: `Add shell aliases tm and taskmaster. Default is false.` (CLI: `--aliases`)
-    *   `yes`: `Skip prompts and use defaults/provided arguments. Default is false.` (CLI: `-y, --yes`)
-*   **Usage:** Run this once at the beginning of a new project, typically via an integrated tool like 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`.
-
-### 2. Parse PRD (`parse_prd`)
-
-*   **MCP Tool:** `parse_prd`
-*   **CLI Command:** `task-master parse-prd [file] [options]`
-*   **Description:** `Parse a Product Requirements Document, PRD, or text file with Taskmaster to automatically generate an initial set of tasks in tasks.json.`
-*   **Key Parameters/Options:**
-    *   `input`: `Path to your PRD or requirements text file that Taskmaster should parse for tasks.` (CLI: `[file]` positional or `-i, --input <file>`)
-    *   `output`: `Specify where Taskmaster should save the generated 'tasks.json' file. Defaults to '.taskmaster/tasks/tasks.json'.` (CLI: `-o, --output <file>`)
-    *   `numTasks`: `Approximate number of top-level tasks Taskmaster should aim to generate from the document.` (CLI: `-n, --num-tasks <number>`)
-    *   `force`: `Use this to allow Taskmaster to overwrite an existing 'tasks.json' without asking for confirmation.` (CLI: `-f, --force`)
-*   **Usage:** Useful for bootstrapping a project from an existing requirements document.
-*   **Notes:** Task Master will strictly adhere to any specific requirements mentioned in the PRD, such as libraries, database schemas, frameworks, tech stacks, etc., while filling in any gaps where the PRD isn't fully specified. Tasks are designed to provide the most direct implementation path while avoiding over-engineering.
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress. If the user does not have a PRD, suggest discussing their idea and then use the example PRD in `.taskmaster/templates/example_prd.txt` as a template for creating the PRD based on their idea, for use with `parse-prd`.
-
----
-
-## AI Model Configuration
-
-### 2. Manage Models (`models`)
-*   **MCP Tool:** `models`
-*   **CLI Command:** `task-master models [options]`
-*   **Description:** `View the current AI model configuration or set specific models for different roles (main, research, fallback). Allows setting custom model IDs for Ollama and OpenRouter.`
-*   **Key MCP Parameters/Options:**
-    *   `setMain <model_id>`: `Set the primary model ID for task generation/updates.` (CLI: `--set-main <model_id>`)
-    *   `setResearch <model_id>`: `Set the model ID for research-backed operations.` (CLI: `--set-research <model_id>`)
-    *   `setFallback <model_id>`: `Set the model ID to use if the primary fails.` (CLI: `--set-fallback <model_id>`)
-    *   `ollama <boolean>`: `Indicates the set model ID is a custom Ollama model.` (CLI: `--ollama`)
-    *   `openrouter <boolean>`: `Indicates the set model ID is a custom OpenRouter model.` (CLI: `--openrouter`)
-    *   `listAvailableModels <boolean>`: `If true, lists available models not currently assigned to a role.` (CLI: No direct equivalent; CLI lists available automatically)
-    *   `projectRoot <string>`: `Optional. Absolute path to the project root directory.` (CLI: Determined automatically)
-*   **Key CLI Options:**
-    *   `--set-main <model_id>`: `Set the primary model.`
-    *   `--set-research <model_id>`: `Set the research model.`
-    *   `--set-fallback <model_id>`: `Set the fallback model.`
-    *   `--ollama`: `Specify that the provided model ID is for Ollama (use with --set-*).`
-    *   `--openrouter`: `Specify that the provided model ID is for OpenRouter (use with --set-*). Validates against OpenRouter API.`
-    *   `--bedrock`: `Specify that the provided model ID is for AWS Bedrock (use with --set-*).`
-    *   `--setup`: `Run interactive setup to configure models, including custom Ollama/OpenRouter IDs.`
-*   **Usage (MCP):** Call without set flags to get current config. Use `setMain`, `setResearch`, or `setFallback` with a valid model ID to update the configuration. Use `listAvailableModels: true` to get a list of unassigned models. To set a custom model, provide the model ID and set `ollama: true` or `openrouter: true`.
-*   **Usage (CLI):** Run without flags to view current configuration and available models. Use set flags to update specific roles. Use `--setup` for guided configuration, including custom models. To set a custom model via flags, use `--set-<role>=<model_id>` along with either `--ollama` or `--openrouter`.
-*   **Notes:** Configuration is stored in `.taskmaster/config.json` in the project root. This command/tool modifies that file. Use `listAvailableModels` or `task-master models` to see internally supported models. OpenRouter custom models are validated against their live API. Ollama custom models are not validated live.
-*   **API note:** API keys for selected AI providers (based on their model) need to exist in the mcp.json file to be accessible in MCP context. The API keys must be present in the local .env file for the CLI to be able to read them.
-*   **Model costs:** The costs in supported models are expressed in dollars. An input/output value of 3 is $3.00. A value of 0.8 is $0.80. 
-*   **Warning:** DO NOT MANUALLY EDIT THE .taskmaster/config.json FILE. Use the included commands either in the MCP or CLI format as needed. Always prioritize MCP tools when available and use the CLI as a fallback.
-
----
-
-## Task Listing & Viewing
-
-### 3. Get Tasks (`get_tasks`)
-
-*   **MCP Tool:** `get_tasks`
-*   **CLI Command:** `task-master list [options]`
-*   **Description:** `List your Taskmaster tasks, optionally filtering by status and showing subtasks.`
-*   **Key Parameters/Options:**
-    *   `status`: `Show only Taskmaster tasks matching this status (or multiple statuses, comma-separated), e.g., 'pending' or 'done,in-progress'.` (CLI: `-s, --status <status>`)
-    *   `withSubtasks`: `Include subtasks indented under their parent tasks in the list.` (CLI: `--with-subtasks`)
-    *   `tag`: `Specify which tag context to list tasks from. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Get an overview of the project status, often used at the start of a work session.
-
-### 4. Get Next Task (`next_task`)
-
-*   **MCP Tool:** `next_task`
-*   **CLI Command:** `task-master next [options]`
-*   **Description:** `Ask Taskmaster to show the next available task you can work on, based on status and completed dependencies.`
-*   **Key Parameters/Options:**
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-    *   `tag`: `Specify which tag context to use. Defaults to the current active tag.` (CLI: `--tag <name>`)
-*   **Usage:** Identify what to work on next according to the plan.
-
-### 5. Get Task Details (`get_task`)
-
-*   **MCP Tool:** `get_task`
-*   **CLI Command:** `task-master show [id] [options]`
-*   **Description:** `Display detailed information for one or more specific Taskmaster tasks or subtasks by ID.`
-*   **Key Parameters/Options:**
-    *   `id`: `Required. The ID of the Taskmaster task (e.g., '15'), subtask (e.g., '15.2'), or a comma-separated list of IDs ('1,5,10.2') you want to view.` (CLI: `[id]` positional or `-i, --id <id>`)
-    *   `tag`: `Specify which tag context to get the task(s) from. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Understand the full details for a specific task. When multiple IDs are provided, a summary table is shown.
-*   **CRITICAL INFORMATION** If you need to collect information from multiple tasks, use comma-separated IDs (i.e. 1,2,3) to receive an array of tasks. Do not needlessly get tasks one at a time if you need to get many as that is wasteful.
-
----
-
-## Task Creation & Modification
-
-### 6. Add Task (`add_task`)
-
-*   **MCP Tool:** `add_task`
-*   **CLI Command:** `task-master add-task [options]`
-*   **Description:** `Add a new task to Taskmaster by describing it; AI will structure it.`
-*   **Key Parameters/Options:**
-    *   `prompt`: `Required. Describe the new task you want Taskmaster to create, e.g., "Implement user authentication using JWT".` (CLI: `-p, --prompt <text>`)
-    *   `dependencies`: `Specify the IDs of any Taskmaster tasks that must be completed before this new one can start, e.g., '12,14'.` (CLI: `-d, --dependencies <ids>`)
-    *   `priority`: `Set the priority for the new task: 'high', 'medium', or 'low'. Default is 'medium'.` (CLI: `--priority <priority>`)
-    *   `research`: `Enable Taskmaster to use the research role for potentially more informed task creation.` (CLI: `-r, --research`)
-    *   `tag`: `Specify which tag context to add the task to. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Quickly add newly identified tasks during development.
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
-
-### 7. Add Subtask (`add_subtask`)
-
-*   **MCP Tool:** `add_subtask`
-*   **CLI Command:** `task-master add-subtask [options]`
-*   **Description:** `Add a new subtask to a Taskmaster parent task, or convert an existing task into a subtask.`
-*   **Key Parameters/Options:**
-    *   `id` / `parent`: `Required. The ID of the Taskmaster task that will be the parent.` (MCP: `id`, CLI: `-p, --parent <id>`)
-    *   `taskId`: `Use this if you want to convert an existing top-level Taskmaster task into a subtask of the specified parent.` (CLI: `-i, --task-id <id>`)
-    *   `title`: `Required if not using taskId. The title for the new subtask Taskmaster should create.` (CLI: `-t, --title <title>`)
-    *   `description`: `A brief description for the new subtask.` (CLI: `-d, --description <text>`)
-    *   `details`: `Provide implementation notes or details for the new subtask.` (CLI: `--details <text>`)
-    *   `dependencies`: `Specify IDs of other tasks or subtasks, e.g., '15' or '16.1', that must be done before this new subtask.` (CLI: `--dependencies <ids>`)
-    *   `status`: `Set the initial status for the new subtask. Default is 'pending'.` (CLI: `-s, --status <status>`)
-    *   `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.
-
-### 8. Update Tasks (`update`)
-
-*   **MCP Tool:** `update`
-*   **CLI Command:** `task-master update [options]`
-*   **Description:** `Update multiple upcoming tasks in Taskmaster based on new context or changes, starting from a specific task ID.`
-*   **Key Parameters/Options:**
-    *   `from`: `Required. The ID of the first task Taskmaster should update. All tasks with this ID or higher that are not 'done' will be considered.` (CLI: `--from <id>`)
-    *   `prompt`: `Required. Explain the change or new context for Taskmaster to apply to the tasks, e.g., "We are now using React Query instead of Redux Toolkit for data fetching".` (CLI: `-p, --prompt <text>`)
-    *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Handle significant implementation changes or pivots that affect multiple future tasks. Example CLI: `task-master update --from='18' --prompt='Switching to React Query.\nNeed to refactor data fetching...'`
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
-
-### 9. Update Task (`update_task`)
-
-*   **MCP Tool:** `update_task`
-*   **CLI Command:** `task-master update-task [options]`
-*   **Description:** `Modify a specific Taskmaster task by ID, incorporating new information or changes. By default, this replaces the existing task details.`
-*   **Key Parameters/Options:**
-    *   `id`: `Required. The specific ID of the Taskmaster task, e.g., '15', you want to update.` (CLI: `-i, --id <id>`)
-    *   `prompt`: `Required. Explain the specific changes or provide the new information Taskmaster should incorporate into this task.` (CLI: `-p, --prompt <text>`)
-    *   `append`: `If true, appends the prompt content to the task's details with a timestamp, rather than replacing them. Behaves like update-subtask.` (CLI: `--append`)
-    *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
-    *   `tag`: `Specify which tag context the task belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Refine a specific task based on new understanding. Use `--append` to log progress without creating subtasks.
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
-
-### 10. Update Subtask (`update_subtask`)
-
-*   **MCP Tool:** `update_subtask`
-*   **CLI Command:** `task-master update-subtask [options]`
-*   **Description:** `Append timestamped notes or details to a specific Taskmaster subtask without overwriting existing content. Intended for iterative implementation logging.`
-*   **Key Parameters/Options:**
-    *   `id`: `Required. The ID of the Taskmaster subtask, e.g., '5.2', to update with new information.` (CLI: `-i, --id <id>`)
-    *   `prompt`: `Required. The information, findings, or progress notes to append to the subtask's details with a timestamp.` (CLI: `-p, --prompt <text>`)
-    *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
-    *   `tag`: `Specify which tag context the subtask belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Log implementation progress, findings, and discoveries during subtask development. Each update is timestamped and appended to preserve the implementation journey.
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
-
-### 11. Set Task Status (`set_task_status`)
-
-*   **MCP Tool:** `set_task_status`
-*   **CLI Command:** `task-master set-status [options]`
-*   **Description:** `Update the status of one or more Taskmaster tasks or subtasks, e.g., 'pending', 'in-progress', 'done'.`
-*   **Key Parameters/Options:**
-    *   `id`: `Required. The ID(s) of the Taskmaster task(s) or subtask(s), e.g., '15', '15.2', or '16,17.1', to update.` (CLI: `-i, --id <id>`)
-    *   `status`: `Required. The new status to set, e.g., 'done', 'pending', 'in-progress', 'review', 'cancelled'.` (CLI: `-s, --status <status>`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Mark progress as tasks move through the development cycle.
-
-### 12. Remove Task (`remove_task`)
-
-*   **MCP Tool:** `remove_task`
-*   **CLI Command:** `task-master remove-task [options]`
-*   **Description:** `Permanently remove a task or subtask from the Taskmaster tasks list.`
-*   **Key Parameters/Options:**
-    *   `id`: `Required. The ID of the Taskmaster task, e.g., '5', or subtask, e.g., '5.2', to permanently remove.` (CLI: `-i, --id <id>`)
-    *   `yes`: `Skip the confirmation prompt and immediately delete the task.` (CLI: `-y, --yes`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Permanently delete tasks or subtasks that are no longer needed in the project.
-*   **Notes:** Use with caution as this operation cannot be undone. Consider using 'blocked', 'cancelled', or 'deferred' status instead if you just want to exclude a task from active planning but keep it for reference. The command automatically cleans up dependency references in other tasks.
-
----
-
-## Task Structure & Breakdown
-
-### 13. Expand Task (`expand_task`)
-
-*   **MCP Tool:** `expand_task`
-*   **CLI Command:** `task-master expand [options]`
-*   **Description:** `Use Taskmaster's AI to break down a complex task into smaller, manageable subtasks. Appends subtasks by default.`
-*   **Key Parameters/Options:**
-    *   `id`: `The ID of the specific Taskmaster task you want to break down into subtasks.` (CLI: `-i, --id <id>`)
-    *   `num`: `Optional: Suggests how many subtasks Taskmaster should aim to create. Uses complexity analysis/defaults otherwise.` (CLI: `-n, --num <number>`)
-    *   `research`: `Enable Taskmaster to use the research role for more informed subtask generation. Requires appropriate API key.` (CLI: `-r, --research`)
-    *   `prompt`: `Optional: Provide extra context or specific instructions to Taskmaster for generating the subtasks.` (CLI: `-p, --prompt <text>`)
-    *   `force`: `Optional: If true, clear existing subtasks before generating new ones. Default is false (append).` (CLI: `--force`)
-    *   `tag`: `Specify which tag context the task belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Generate a detailed implementation plan for a complex task before starting coding. Automatically uses complexity report recommendations if available and `num` is not specified.
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
-
-### 14. Expand All Tasks (`expand_all`)
-
-*   **MCP Tool:** `expand_all`
-*   **CLI Command:** `task-master expand --all [options]` (Note: CLI uses the `expand` command with the `--all` flag)
-*   **Description:** `Tell Taskmaster to automatically expand all eligible pending/in-progress tasks based on complexity analysis or defaults. Appends subtasks by default.`
-*   **Key Parameters/Options:**
-    *   `num`: `Optional: Suggests how many subtasks Taskmaster should aim to create per task.` (CLI: `-n, --num <number>`)
-    *   `research`: `Enable research role for more informed subtask generation. Requires appropriate API key.` (CLI: `-r, --research`)
-    *   `prompt`: `Optional: Provide extra context for Taskmaster to apply generally during expansion.` (CLI: `-p, --prompt <text>`)
-    *   `force`: `Optional: If true, clear existing subtasks before generating new ones for each eligible task. Default is false (append).` (CLI: `--force`)
-    *   `tag`: `Specify which tag context to expand. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Useful after initial task generation or complexity analysis to break down multiple tasks at once.
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
-
-### 15. Clear Subtasks (`clear_subtasks`)
-
-*   **MCP Tool:** `clear_subtasks`
-*   **CLI Command:** `task-master clear-subtasks [options]`
-*   **Description:** `Remove all subtasks from one or more specified Taskmaster parent tasks.`
-*   **Key Parameters/Options:**
-    *   `id`: `The ID(s) of the Taskmaster parent task(s) whose subtasks you want to remove, e.g., '15' or '16,18'. Required unless using 'all'.` (CLI: `-i, --id <ids>`)
-    *   `all`: `Tell Taskmaster to remove subtasks from all parent tasks.` (CLI: `--all`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Used before regenerating subtasks with `expand_task` if the previous breakdown needs replacement.
-
-### 16. Remove Subtask (`remove_subtask`)
-
-*   **MCP Tool:** `remove_subtask`
-*   **CLI Command:** `task-master remove-subtask [options]`
-*   **Description:** `Remove a subtask from its Taskmaster parent, optionally converting it into a standalone task.`
-*   **Key Parameters/Options:**
-    *   `id`: `Required. The ID(s) of the Taskmaster subtask(s) to remove, e.g., '15.2' or '16.1,16.3'.` (CLI: `-i, --id <id>`)
-    *   `convert`: `If used, Taskmaster will turn the subtask into a regular top-level task instead of deleting it.` (CLI: `-c, --convert`)
-    *   `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.
-
-### 17. Move Task (`move_task`)
-
-*   **MCP Tool:** `move_task`
-*   **CLI Command:** `task-master move [options]`
-*   **Description:** `Move a task or subtask to a new position within the task hierarchy.`
-*   **Key Parameters/Options:**
-    *   `from`: `Required. ID of the task/subtask to move (e.g., "5" or "5.2"). Can be comma-separated for multiple tasks.` (CLI: `--from <id>`)
-    *   `to`: `Required. ID of the destination (e.g., "7" or "7.3"). Must match the number of source IDs if comma-separated.` (CLI: `--to <id>`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Reorganize tasks by moving them within the hierarchy. Supports various scenarios like:
-    *   Moving a task to become a subtask
-    *   Moving a subtask to become a standalone task
-    *   Moving a subtask to a different parent
-    *   Reordering subtasks within the same parent
-    *   Moving a task to a new, non-existent ID (automatically creates placeholders)
-    *   Moving multiple tasks at once with comma-separated IDs
-*   **Validation Features:**
-    *   Allows moving tasks to non-existent destination IDs (creates placeholder tasks)
-    *   Prevents moving to existing task IDs that already have content (to avoid overwriting)
-    *   Validates that source tasks exist before attempting to move them
-    *   Maintains proper parent-child relationships
-*   **Example CLI:** `task-master move --from=5.2 --to=7.3` to move subtask 5.2 to become subtask 7.3.
-*   **Example Multi-Move:** `task-master move --from=10,11,12 --to=16,17,18` to move multiple tasks to new positions.
-*   **Common Use:** Resolving merge conflicts in tasks.json when multiple team members create tasks on different branches.
-
----
-
-## Dependency Management
-
-### 18. Add Dependency (`add_dependency`)
-
-*   **MCP Tool:** `add_dependency`
-*   **CLI Command:** `task-master add-dependency [options]`
-*   **Description:** `Define a dependency in Taskmaster, making one task a prerequisite for another.`
-*   **Key Parameters/Options:**
-    *   `id`: `Required. The ID of the Taskmaster task that will depend on another.` (CLI: `-i, --id <id>`)
-    *   `dependsOn`: `Required. The ID of the Taskmaster task that must be completed first, the prerequisite.` (CLI: `-d, --depends-on <id>`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <path>`)
-*   **Usage:** Establish the correct order of execution between tasks.
-
-### 19. Remove Dependency (`remove_dependency`)
-
-*   **MCP Tool:** `remove_dependency`
-*   **CLI Command:** `task-master remove-dependency [options]`
-*   **Description:** `Remove a dependency relationship between two Taskmaster tasks.`
-*   **Key Parameters/Options:**
-    *   `id`: `Required. The ID of the Taskmaster task you want to remove a prerequisite from.` (CLI: `-i, --id <id>`)
-    *   `dependsOn`: `Required. The ID of the Taskmaster task that should no longer be a prerequisite.` (CLI: `-d, --depends-on <id>`)
-    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Update task relationships when the order of execution changes.
-
-### 20. Validate Dependencies (`validate_dependencies`)
-
-*   **MCP Tool:** `validate_dependencies`
-*   **CLI Command:** `task-master validate-dependencies [options]`
-*   **Description:** `Check your Taskmaster tasks for dependency issues (like circular references or links to non-existent tasks) without making changes.`
-*   **Key Parameters/Options:**
-    *   `tag`: `Specify which tag context to validate. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Audit the integrity of your task dependencies.
-
-### 21. Fix Dependencies (`fix_dependencies`)
-
-*   **MCP Tool:** `fix_dependencies`
-*   **CLI Command:** `task-master fix-dependencies [options]`
-*   **Description:** `Automatically fix dependency issues (like circular references or links to non-existent tasks) in your Taskmaster tasks.`
-*   **Key Parameters/Options:**
-    *   `tag`: `Specify which tag context to fix dependencies in. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Clean up dependency errors automatically.
-
----
-
-## Analysis & Reporting
-
-### 22. Analyze Project Complexity (`analyze_project_complexity`)
-
-*   **MCP Tool:** `analyze_project_complexity`
-*   **CLI Command:** `task-master analyze-complexity [options]`
-*   **Description:** `Have Taskmaster analyze your tasks to determine their complexity and suggest which ones need to be broken down further.`
-*   **Key Parameters/Options:**
-    *   `output`: `Where to save the complexity analysis report. Default is '.taskmaster/reports/task-complexity-report.json' (or '..._tagname.json' if a tag is used).` (CLI: `-o, --output <file>`)
-    *   `threshold`: `The minimum complexity score (1-10) that should trigger a recommendation to expand a task.` (CLI: `-t, --threshold <number>`)
-    *   `research`: `Enable research role for more accurate complexity analysis. Requires appropriate API key.` (CLI: `-r, --research`)
-    *   `tag`: `Specify which tag context to analyze. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Used before breaking down tasks to identify which ones need the most attention.
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
-
-### 23. View Complexity Report (`complexity_report`)
-
-*   **MCP Tool:** `complexity_report`
-*   **CLI Command:** `task-master complexity-report [options]`
-*   **Description:** `Display the task complexity analysis report in a readable format.`
-*   **Key Parameters/Options:**
-    *   `tag`: `Specify which tag context to show the report for. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to the complexity report (default: '.taskmaster/reports/task-complexity-report.json').` (CLI: `-f, --file <file>`)
-*   **Usage:** Review and understand the complexity analysis results after running analyze-complexity.
-
----
-
-## File Management
-
-### 24. Generate Task Files (`generate`)
-
-*   **MCP Tool:** `generate`
-*   **CLI Command:** `task-master generate [options]`
-*   **Description:** `Create or update individual Markdown files for each task based on your tasks.json.`
-*   **Key Parameters/Options:**
-    *   `output`: `The directory where Taskmaster should save the task files (default: in a 'tasks' directory).` (CLI: `-o, --output <directory>`)
-    *   `tag`: `Specify which tag context to generate files for. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-*   **Usage:** Run this after making changes to tasks.json to keep individual task files up to date. This command is now manual and no longer runs automatically.
-
----
-
-## AI-Powered Research
-
-### 25. Research (`research`)
-
-*   **MCP Tool:** `research`
-*   **CLI Command:** `task-master research [options]`
-*   **Description:** `Perform AI-powered research queries with project context to get fresh, up-to-date information beyond the AI's knowledge cutoff.`
-*   **Key Parameters/Options:**
-    *   `query`: `Required. Research query/prompt (e.g., "What are the latest best practices for React Query v5?").` (CLI: `[query]` positional or `-q, --query <text>`)
-    *   `taskIds`: `Comma-separated list of task/subtask IDs from the current tag context (e.g., "15,16.2,17").` (CLI: `-i, --id <ids>`)
-    *   `filePaths`: `Comma-separated list of file paths for context (e.g., "src/api.js,docs/readme.md").` (CLI: `-f, --files <paths>`)
-    *   `customContext`: `Additional custom context text to include in the research.` (CLI: `-c, --context <text>`)
-    *   `includeProjectTree`: `Include project file tree structure in context (default: false).` (CLI: `--tree`)
-    *   `detailLevel`: `Detail level for the research response: 'low', 'medium', 'high' (default: medium).` (CLI: `--detail <level>`)
-    *   `saveTo`: `Task or subtask ID (e.g., "15", "15.2") to automatically save the research conversation to.` (CLI: `--save-to <id>`)
-    *   `saveFile`: `If true, saves the research conversation to a markdown file in '.taskmaster/docs/research/'.` (CLI: `--save-file`)
-    *   `noFollowup`: `Disables the interactive follow-up question menu in the CLI.` (CLI: `--no-followup`)
-    *   `tag`: `Specify which tag context to use for task-based context gathering. Defaults to the current active tag.` (CLI: `--tag <name>`)
-    *   `projectRoot`: `The directory of the project. Must be an absolute path.` (CLI: Determined automatically)
-*   **Usage:** **This is a POWERFUL tool that agents should use FREQUENTLY** to:
-    *   Get fresh information beyond knowledge cutoff dates
-    *   Research latest best practices, library updates, security patches
-    *   Find implementation examples for specific technologies
-    *   Validate approaches against current industry standards
-    *   Get contextual advice based on project files and tasks
-*   **When to Consider Using Research:**
-    *   **Before implementing any task** - Research current best practices
-    *   **When encountering new technologies** - Get up-to-date implementation guidance (libraries, apis, etc)
-    *   **For security-related tasks** - Find latest security recommendations
-    *   **When updating dependencies** - Research breaking changes and migration guides
-    *   **For performance optimization** - Get current performance best practices
-    *   **When debugging complex issues** - Research known solutions and workarounds
-*   **Research + Action Pattern:**
-    *   Use `research` to gather fresh information
-    *   Use `update_subtask` to commit findings with timestamps
-    *   Use `update_task` to incorporate research into task details
-    *   Use `add_task` with research flag for informed task creation
-*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. The research provides FRESH data beyond the AI's training cutoff, making it invaluable for current best practices and recent developments.
-
----
-
-## Tag Management
-
-This new suite of commands allows you to manage different task contexts (tags).
-
-### 26. List Tags (`tags`)
-
-*   **MCP Tool:** `list_tags`
-*   **CLI Command:** `task-master tags [options]`
-*   **Description:** `List all available tags with task counts, completion status, and other metadata.`
-*   **Key Parameters/Options:**
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-    *   `--show-metadata`: `Include detailed metadata in the output (e.g., creation date, description).` (CLI: `--show-metadata`)
-
-### 27. Add Tag (`add_tag`)
-
-*   **MCP Tool:** `add_tag`
-*   **CLI Command:** `task-master add-tag <tagName> [options]`
-*   **Description:** `Create a new, empty tag context, or copy tasks from another tag.`
-*   **Key Parameters/Options:**
-    *   `tagName`: `Name of the new tag to create (alphanumeric, hyphens, underscores).` (CLI: `<tagName>` positional)
-    *   `--from-branch`: `Creates a tag with a name derived from the current git branch, ignoring the <tagName> argument.` (CLI: `--from-branch`)
-    *   `--copy-from-current`: `Copy tasks from the currently active tag to the new tag.` (CLI: `--copy-from-current`)
-    *   `--copy-from <tag>`: `Copy tasks from a specific source tag to the new tag.` (CLI: `--copy-from <tag>`)
-    *   `--description <text>`: `Provide an optional description for the new tag.` (CLI: `-d, --description <text>`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-
-### 28. Delete Tag (`delete_tag`)
-
-*   **MCP Tool:** `delete_tag`
-*   **CLI Command:** `task-master delete-tag <tagName> [options]`
-*   **Description:** `Permanently delete a tag and all of its associated tasks.`
-*   **Key Parameters/Options:**
-    *   `tagName`: `Name of the tag to delete.` (CLI: `<tagName>` positional)
-    *   `--yes`: `Skip the confirmation prompt.` (CLI: `-y, --yes`)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-
-### 29. Use Tag (`use_tag`)
-
-*   **MCP Tool:** `use_tag`
-*   **CLI Command:** `task-master use-tag <tagName>`
-*   **Description:** `Switch your active task context to a different tag.`
-*   **Key Parameters/Options:**
-    *   `tagName`: `Name of the tag to switch to.` (CLI: `<tagName>` positional)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-
-### 30. Rename Tag (`rename_tag`)
-
-*   **MCP Tool:** `rename_tag`
-*   **CLI Command:** `task-master rename-tag <oldName> <newName>`
-*   **Description:** `Rename an existing tag.`
-*   **Key Parameters/Options:**
-    *   `oldName`: `The current name of the tag.` (CLI: `<oldName>` positional)
-    *   `newName`: `The new name for the tag.` (CLI: `<newName>` positional)
-    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
-
-### 31. Copy Tag (`copy_tag`)
-
-*   **MCP Tool:** `copy_tag`
-*   **CLI Command:** `task-master copy-tag <sourceName> <targetName> [options]`
-*   **Description:** `Copy an entire tag context, including all its tasks and metadata, to a new tag.`
-*   **Key Parameters/Options:**
-    *   `sourceName`: `Name of the tag to copy from.` (CLI: `<sourceName>` positional)
-    *   `targetName`: `Name of the new tag to create.` (CLI: `<targetName>` positional)
-    *   `--description <text>`: `Optional description for the new tag.` (CLI: `-d, --description <text>`)
-
----
-
-## Miscellaneous
-
-### 32. Sync Readme (`sync-readme`) -- experimental
-
-*   **MCP Tool:** N/A
-*   **CLI Command:** `task-master sync-readme [options]`
-*   **Description:** `Exports your task list to your project's README.md file, useful for showcasing progress.`
-*   **Key Parameters/Options:**
-    *   `status`: `Filter tasks by status (e.g., 'pending', 'done').` (CLI: `-s, --status <status>`)
-    *   `withSubtasks`: `Include subtasks in the export.` (CLI: `--with-subtasks`)
-    *   `tag`: `Specify which tag context to export from. Defaults to the current active tag.` (CLI: `--tag <name>`)
-
----
-
-## Environment Variables Configuration (Updated)
-
-Taskmaster primarily uses the **`.taskmaster/config.json`** file (in project root) for configuration (models, parameters, logging level, etc.), managed via `task-master models --setup`.
-
-Environment variables are used **only** for sensitive API keys related to AI providers and specific overrides like the Ollama base URL:
-
-*   **API Keys (Required for corresponding provider):**
-    *   `ANTHROPIC_API_KEY`
-    *   `PERPLEXITY_API_KEY`
-    *   `OPENAI_API_KEY`
-    *   `GOOGLE_API_KEY`
-    *   `MISTRAL_API_KEY`
-    *   `AZURE_OPENAI_API_KEY` (Requires `AZURE_OPENAI_ENDPOINT` too)
-    *   `OPENROUTER_API_KEY`
-    *   `XAI_API_KEY`
-    *   `OLLAMA_API_KEY` (Requires `OLLAMA_BASE_URL` too)
-*   **Endpoints (Optional/Provider Specific inside .taskmaster/config.json):**
-    *   `AZURE_OPENAI_ENDPOINT`
-    *   `OLLAMA_BASE_URL` (Default: `http://localhost:11434/api`)
-
-**Set API keys** in your **`.env`** file in the project root (for CLI use) or within the `env` section of your **`.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.md](.kiro/steering/dev_workflow.md).

.kiro/steering/taskmaster_hooks_workflow.md

@@ -1,59 +0,0 @@
----
-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.

.manypkg.json

@@ -1,6 +0,0 @@
-{
-	"$schema": "https://unpkg.com/@manypkg/get-packages@1.1.3/schema.json",
-	"defaultBranch": "main",
-	"ignoredRules": ["ROOT_HAS_DEPENDENCIES", "INTERNAL_MISMATCH"],
-	"ignoredPackages": ["@tm/core", "@tm/cli", "@tm/build-config"]
-}

.mcp.json

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

.nvmrc

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

.prettierignore

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

.prettierrc

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

.taskmaster/CLAUDE.md

@@ -1,417 +0,0 @@
-# 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", "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/config.json

@@ -1,44 +0,0 @@
-{
-	"models": {
-		"main": {
-			"provider": "claude-code",
-			"modelId": "sonnet",
-			"maxTokens": 64000,
-			"temperature": 0.2
-		},
-		"research": {
-			"provider": "perplexity",
-			"modelId": "sonar",
-			"maxTokens": 8700,
-			"temperature": 0.1
-		},
-		"fallback": {
-			"provider": "anthropic",
-			"modelId": "claude-3-7-sonnet-20250219",
-			"maxTokens": 120000,
-			"temperature": 0.2
-		}
-	},
-	"global": {
-		"logLevel": "info",
-		"debug": false,
-		"defaultNumTasks": 10,
-		"defaultSubtasks": 5,
-		"defaultPriority": "medium",
-		"projectName": "Taskmaster",
-		"ollamaBaseURL": "http://localhost:11434/api",
-		"bedrockBaseURL": "https://bedrock.us-east-1.amazonaws.com",
-		"responseLanguage": "English",
-		"enableCodebaseAnalysis": true,
-		"userId": "1234567890",
-		"azureBaseURL": "https://your-endpoint.azure.com/",
-		"defaultTag": "master"
-	},
-	"claudeCode": {},
-	"codexCli": {},
-	"grokCli": {
-		"timeout": 120000,
-		"workingDirectory": null,
-		"defaultModel": "grok-4-latest"
-	}
-}

.taskmaster/docs/MIGRATION-ROADMAP.md

@@ -1,188 +0,0 @@
-# Task Master Migration Roadmap
-
-## Overview
-Gradual migration from scripts-based architecture to a clean monorepo with separated concerns.
-
-## Architecture Vision
-
-```
-┌─────────────────────────────────────────────────┐
-│                  User Interfaces                 │
-├──────────┬──────────┬──────────┬────────────────┤
-│  @tm/cli │ @tm/mcp  │ @tm/ext  │  @tm/web      │
-│  (CLI)   │  (MCP)   │  (VSCode)│  (Future)     │
-└──────────┴──────────┴──────────┴────────────────┘
-                    │
-                    ▼
-        ┌──────────────────────┐
-        │      @tm/core        │
-        │  (Business Logic)    │
-        └──────────────────────┘
-```
-
-## Migration Phases
-
-### Phase 1: Core Extraction ✅ (In Progress)
-**Goal**: Move all business logic to @tm/core
-
-- [x] Create @tm/core package structure
-- [x] Move types and interfaces
-- [x] Implement TaskMasterCore facade
-- [x] Move storage adapters
-- [x] Move task services
-- [ ] Move AI providers
-- [ ] Move parser logic
-- [ ] Complete test coverage
-
-### Phase 2: CLI Package Creation 🚧 (Started)
-**Goal**: Create @tm/cli as a thin presentation layer
-
-- [x] Create @tm/cli package structure
-- [x] Implement Command interface pattern
-- [x] Create CommandRegistry
-- [x] Build legacy bridge/adapter
-- [x] Migrate list-tasks command
-- [ ] Migrate remaining commands one by one
-- [ ] Remove UI logic from core
-
-### Phase 3: Transitional Integration
-**Goal**: Use new packages in existing scripts without breaking changes
-
-```javascript
-// scripts/modules/commands.js gradually adopts new commands
-import { ListTasksCommand } from '@tm/cli';
-const listCommand = new ListTasksCommand();
-
-// Old interface remains the same
-programInstance
-  .command('list')
-  .action(async (options) => {
-    // Use new command internally
-    const result = await listCommand.execute(convertOptions(options));
-  });
-```
-
-### Phase 4: MCP Package
-**Goal**: Separate MCP server as its own package
-
-- [ ] Create @tm/mcp package
-- [ ] Move MCP server code
-- [ ] Use @tm/core for all logic
-- [ ] MCP becomes a thin RPC layer
-
-### Phase 5: Complete Migration
-**Goal**: Remove old scripts, pure monorepo
-
-- [ ] All commands migrated to @tm/cli
-- [ ] Remove scripts/modules/task-manager/*
-- [ ] Remove scripts/modules/commands.js
-- [ ] Update bin/task-master.js to use @tm/cli
-- [ ] Clean up dependencies
-
-## Current Transitional Strategy
-
-### 1. Adapter Pattern (commands-adapter.js)
-```javascript
-// Checks if new CLI is available and uses it
-// Falls back to legacy implementation if not
-export async function listTasksAdapter(...args) {
-  if (cliAvailable) {
-    return useNewImplementation(...args);
-  }
-  return useLegacyImplementation(...args);
-}
-```
-
-### 2. Command Bridge Pattern
-```javascript
-// Allows new commands to work in old code
-const bridge = new CommandBridge(new ListTasksCommand());
-const data = await bridge.run(legacyOptions); // Legacy style
-const result = await bridge.execute(newOptions); // New style
-```
-
-### 3. Gradual File Migration
-Instead of big-bang refactoring:
-1. Create new implementation in @tm/cli
-2. Add adapter in commands-adapter.js
-3. Update commands.js to use adapter
-4. Test both paths work
-5. Eventually remove adapter when all migrated
-
-## Benefits of This Approach
-
-1. **No Breaking Changes**: Existing CLI continues to work
-2. **Incremental PRs**: Each command can be migrated separately
-3. **Parallel Development**: New features can use new architecture
-4. **Easy Rollback**: Can disable new implementation if issues
-5. **Clear Separation**: Business logic (core) vs presentation (cli/mcp/etc)
-
-## Example PR Sequence
-
-### PR 1: Core Package Setup ✅
-- Create @tm/core
-- Move types and interfaces
-- Basic TaskMasterCore implementation
-
-### PR 2: CLI Package Foundation ✅
-- Create @tm/cli
-- Command interface and registry
-- Legacy bridge utilities
-
-### PR 3: First Command Migration
-- Migrate list-tasks to new system
-- Add adapter in scripts
-- Test both implementations
-
-### PR 4-N: Migrate Commands One by One
-- Each PR migrates 1-2 related commands
-- Small, reviewable changes
-- Continuous delivery
-
-### Final PR: Cleanup
-- Remove legacy implementations
-- Remove adapters
-- Update documentation
-
-## Testing Strategy
-
-### Dual Testing During Migration
-```javascript
-describe('List Tasks', () => {
-  it('works with legacy implementation', async () => {
-    // Force legacy
-    const result = await legacyListTasks(...);
-    expect(result).toBeDefined();
-  });
-
-  it('works with new implementation', async () => {
-    // Force new
-    const command = new ListTasksCommand();
-    const result = await command.execute(...);
-    expect(result.success).toBe(true);
-  });
-
-  it('adapter chooses correctly', async () => {
-    // Let adapter decide
-    const result = await listTasksAdapter(...);
-    expect(result).toBeDefined();
-  });
-});
-```
-
-## Success Metrics
-
-- [ ] All commands migrated without breaking changes
-- [ ] Test coverage maintained or improved
-- [ ] Performance maintained or improved
-- [ ] Cleaner, more maintainable codebase
-- [ ] Easy to add new interfaces (web, desktop, etc.)
-
-## Notes for Contributors
-
-1. **Keep PRs Small**: Migrate one command at a time
-2. **Test Both Paths**: Ensure legacy and new both work
-3. **Document Changes**: Update this roadmap as you go
-4. **Communicate**: Discuss in PRs if architecture needs adjustment
-
-This is a living document - update as the migration progresses!

.taskmaster/docs/autonomous-tdd-git-workflow.md

@@ -1,912 +0,0 @@
-## Summary
-
-- Put the existing git and test workflows on rails: a repeatable, automated process that can run autonomously, with guardrails and a compact TUI for visibility.
-
-- Flow: for a selected task, create a branch named with the tag + task id → generate tests for the first subtask (red) using the Surgical Test Generator → implement code (green) → verify tests → commit → repeat per subtask → final verify → push → open PR against the default branch.
-
-- Build on existing rules: .cursor/rules/git_workflow.mdc, .cursor/rules/test_workflow.mdc, .claude/agents/surgical-test-generator.md, and existing CLI/core services.
-
-## Goals
-
-- Deterministic, resumable automation to execute the TDD loop per subtask with minimal human intervention.
-
-- Strong guardrails: never commit to the default branch; only commit when tests pass; enforce status transitions; persist logs/state for debuggability.
-
-- Visibility: a compact terminal UI (like lazygit) to pick tag, view tasks, and start work; right-side pane opens an executor terminal (via tmux) for agent coding.
-
-- Extensible: framework-agnostic test generation via the Surgical Test Generator; detect and use the repo’s test command for execution with coverage thresholds.
-
-## Non‑Goals (initial)
-
-- Full multi-language runner parity beyond detection and executing the project’s test command.
-
-- Complex GUI; start with CLI/TUI + tmux pane. IDE/extension can hook into the same state later.
-
-- Rich executor selection UX (codex/gemini/claude) — we’ll prompt per run; defaults can come later.
-
-## Success Criteria
-
-- One command can autonomously complete a task's subtasks via TDD and open a PR when done.
-
-- All commits made on a branch that includes the tag and task id (see Branch Naming); no commits to the default branch directly.
-
-- Every subtask iteration: failing tests added first (red), then code added to pass them (green), commit only after green.
-
-- End-to-end logs + artifacts stored in .taskmaster/reports/runs/<timestamp-or-id>/.
-
-## Success Metrics (Phase 1)
-
-- **Adoption**: 80% of tasks in a pilot repo completed via `tm autopilot`
-- **Safety**: 0 commits to default branch; 100% of commits have green tests
-- **Efficiency**: Average time from task start to PR < 30min for simple subtasks
-- **Reliability**: < 5% of runs require manual intervention (timeout/conflicts)
-
-## User Stories
-
-- As a developer, I can run tm autopilot <taskId> and watch a structured, safe workflow execute.
-
-- As a reviewer, I can inspect commits per subtask, and a PR summarizing the work when the task completes.
-
-- As an operator, I can see current step, active subtask, tests status, and logs in a compact CLI view and read a final run report.
-
-## Example Workflow Traces
-
-### Happy Path: Complete a 3-subtask feature
-
-```bash
-# Developer starts
-$ tm autopilot 42
-→ Checks preflight: ✓ clean tree, ✓ npm test detected
-→ Creates branch: analytics/task-42-user-metrics
-→ Subtask 42.1: "Add metrics schema"
-  RED: generates test_metrics_schema.test.js → 3 failures
-  GREEN: implements schema.js → all pass
-  COMMIT: "feat(metrics): add metrics schema (task 42.1)"
-→ Subtask 42.2: "Add collection endpoint"
-  RED: generates test_metrics_endpoint.test.js → 5 failures
-  GREEN: implements api/metrics.js → all pass
-  COMMIT: "feat(metrics): add collection endpoint (task 42.2)"
-→ Subtask 42.3: "Add dashboard widget"
-  RED: generates test_metrics_widget.test.js → 4 failures
-  GREEN: implements components/MetricsWidget.jsx → all pass
-  COMMIT: "feat(metrics): add dashboard widget (task 42.3)"
-→ Final: all 3 subtasks complete
-  ✓ Run full test suite → all pass
-  ✓ Coverage check → 85% (meets 80% threshold)
-  PUSH: confirms with user → pushed to origin
-  PR: opens #123 "Task #42 [analytics]: User metrics tracking"
-
-✓ Task 42 complete. PR: https://github.com/org/repo/pull/123
-  Run report: .taskmaster/reports/runs/2025-01-15-142033/
-```
-
-### Error Recovery: Failing tests timeout
-
-```bash
-$ tm autopilot 42
-→ Subtask 42.2 GREEN phase: attempt 1 fails (2 tests still red)
-→ Subtask 42.2 GREEN phase: attempt 2 fails (1 test still red)
-→ Subtask 42.2 GREEN phase: attempt 3 fails (1 test still red)
-
-⚠️  Paused: Could not achieve green state after 3 attempts
-📋 State saved to: .taskmaster/reports/runs/2025-01-15-142033/
-    Last error: "POST /api/metrics returns 500 instead of 201"
-
-Next steps:
-  - Review diff: git diff HEAD
-  - Inspect logs: cat .taskmaster/reports/runs/2025-01-15-142033/log.jsonl
-  - Check test output: cat .taskmaster/reports/runs/2025-01-15-142033/test-results/subtask-42.2-green-attempt3.json
-  - Resume after manual fix: tm autopilot --resume
-
-# Developer manually fixes the issue, then:
-$ tm autopilot --resume
-→ Resuming subtask 42.2 GREEN phase
-  GREEN: all tests pass
-  COMMIT: "feat(metrics): add collection endpoint (task 42.2)"
-→ Continuing to subtask 42.3...
-```
-
-### Dry Run: Preview before execution
-
-```bash
-$ tm autopilot 42 --dry-run
-Autopilot Plan for Task #42 [analytics]: User metrics tracking
-─────────────────────────────────────────────────────────────
-Preflight:
-  ✓ Working tree is clean
-  ✓ Test command detected: npm test
-  ✓ Tools available: git, gh, node, npm
-  ✓ Current branch: main (will create new branch)
-
-Branch & Tag:
-  → Create branch: analytics/task-42-user-metrics
-  → Set active tag: analytics
-
-Subtasks (3 pending):
-  1. 42.1: Add metrics schema
-     - RED: generate tests in src/__tests__/schema.test.js
-     - GREEN: implement src/schema.js
-     - COMMIT: "feat(metrics): add metrics schema (task 42.1)"
-
-  2. 42.2: Add collection endpoint [depends on 42.1]
-     - RED: generate tests in src/api/__tests__/metrics.test.js
-     - GREEN: implement src/api/metrics.js
-     - COMMIT: "feat(metrics): add collection endpoint (task 42.2)"
-
-  3. 42.3: Add dashboard widget [depends on 42.2]
-     - RED: generate tests in src/components/__tests__/MetricsWidget.test.jsx
-     - GREEN: implement src/components/MetricsWidget.jsx
-     - COMMIT: "feat(metrics): add dashboard widget (task 42.3)"
-
-Finalization:
-  → Run full test suite with coverage
-  → Push branch to origin (will confirm)
-  → Create PR targeting main
-
-Run without --dry-run to execute.
-```
-
-## High‑Level Workflow
-
-1) Pre‑flight
-
-   - Verify clean working tree or confirm staging/commit policy (configurable).
-
-   - Detect repo type and the project’s test command (e.g., npm test, pnpm test, pytest, go test).
-
-   - Validate tools: git, gh (optional for PR), node/npm, and (if used) claude CLI.
-
-   - Load TaskMaster state and selected task; if no subtasks exist, automatically run “expand” before working.
-
-2) Branch & Tag Setup
-
-   - Checkout default branch and update (optional), then create a branch using Branch Naming (below).
-
-   - Map branch ↔ tag via existing tag management; explicitly set active tag to the branch’s tag.
-
-3) Subtask Loop (for each pending/in-progress subtask in dependency order)
-
-   - Select next eligible subtask using tm-core TaskService getNextTask() and subtask eligibility logic.
-
-   - Red: generate or update failing tests for the subtask
-
-     - Use the Surgical Test Generator system prompt .claude/agents/surgical-test-generator.md) to produce high-signal tests following project conventions.
-
-     - Run tests to confirm red; record results. If not red (already passing), skip to next subtask or escalate.
-
-   - Green: implement code to pass tests
-
-     - Use executor to implement changes (initial: claude CLI prompt with focused context).
-
-     - Re-run tests until green or timeout/backoff policy triggers.
-
-   - Commit: when green
-
-     - Commit tests + code with conventional commit message. Optionally update subtask status to done.
-
-     - Persist run step metadata/logs.
-
-4) Finalization
-
-   - Run full test suite and coverage (if configured); optionally lint/format.
-
-   - Commit any final adjustments.
-
-   - Push branch (ask user to confirm); create PR (via gh pr create) targeting the default branch. Title format: Task #<id> [<tag>]: <title>.
-
-5) Post‑Run
-
-   - Update task status if desired (e.g., review).
-
-   - Persist run report (JSON + markdown summary) to .taskmaster/reports/runs/<run-id>/.
-
-## Guardrails
-
-- Never commit to the default branch.
-
-- Commit only if all tests (targeted and suite) pass; allow override flags.
-
-- Enforce 80% coverage thresholds (lines/branches/functions/statements) by default; configurable.
-
-- Timebox/model ops and retries; if not green within N attempts, pause with actionable state for resume.
-
-- Always log actions, commands, and outcomes; include dry-run mode.
-
-- Ask before branch creation, pushing, and opening a PR unless --no-confirm is set.
-
-## Integration Points (Current Repo)
-
-- CLI: apps/cli provides command structure and UI components.
-
-  - New command: tm autopilot (alias: task-master autopilot).
-
-  - Reuse UI components under apps/cli/src/ui/components/ for headers/task details/next-task.
-
-- Core services: packages/tm-core
-
-  - TaskService for selection, status, tags.
-
-  - TaskExecutionService for prompt formatting and executor prep.
-
-  - Executors: claude executor and ExecutorFactory to run external tools.
-
-  - Proposed new: WorkflowOrchestrator to drive the autonomous loop and emit progress events.
-
-- Tag/Git utilities: scripts/modules/utils/git-utils.js and scripts/modules/task-manager/tag-management.js for branch→tag mapping and explicit tag switching.
-
-- Rules: .cursor/rules/git_workflow.mdc and .cursor/rules/test_workflow.mdc to steer behavior and ensure consistency.
-
-- Test generation prompt: .claude/agents/surgical-test-generator.md.
-
-## Proposed Components
-
-- Orchestrator (tm-core): WorkflowOrchestrator (new)
-
-  - State machine driving phases: Preflight → Branch/Tag → SubtaskIter (Red/Green/Commit) → Finalize → PR.
-
-  - Exposes an evented API (progress events) that the CLI can render.
-
-  - Stores run state artifacts.
-
-- Test Runner Adapter
-
-  - Detects and runs tests via the project’s test command (e.g., npm test), with targeted runs where feasible.
-
-  - API: runTargeted(files/pattern), runAll(), report summary (failures, duration, coverage), enforce 80% threshold by default.
-
-- Git/PR Adapter
-
-  - Encapsulates git ops: branch create/checkout, add/commit, push.
-
-  - Optional gh integration to open PR; fallback to instructions if gh unavailable.
-
-  - Confirmation gates for branch creation and pushes.
-
-- Prompt/Exec Adapter
-
-  - Uses existing executor service to call the selected coding assistant (initially claude) with tight prompts: task/subtask context, surgical tests first, then minimal code to green.
-
-- Run State + Reporting
-
-  - JSONL log of steps, timestamps, commands, test results.
-
-  - Markdown summary for PR description and post-run artifact.
-
-## CLI UX (MVP)
-
-- Command: tm autopilot [taskId]
-
-  - Flags: --dry-run, --no-push, --no-pr, --no-confirm, --force, --max-attempts <n>, --runner <auto|custom>, --commit-scope <scope>
-
-  - Output: compact header (project, tag, branch), current phase, subtask line, last test summary, next actions.
-
-- Resume: If interrupted, tm autopilot --resume picks up from last checkpoint in run state.
-
-### TUI with tmux (Linear Execution)
-
-- Left pane: Tag selector, task list (status/priority), start/expand shortcuts; "Start" triggers the next task or a selected task.
-
-- Right pane: Executor terminal (tmux split) that runs the coding agent (claude-code/codex). Autopilot can hand over to the right pane during green.
-
-- MCP integration: use MCP tools for task queries/updates and for shell/test invocations where available.
-
-## TUI Layout (tmux-based)
-
-### Pane Structure
-
-```
-┌─────────────────────────────────────┬──────────────────────────────────┐
-│ Task Navigator (left)               │ Executor Terminal (right)        │
-│                                     │                                  │
-│ Project: my-app                     │ $ tm autopilot --executor-mode   │
-│ Branch: analytics/task-42           │ > Running subtask 42.2 GREEN...  │
-│ Tag: analytics                      │ > Implementing endpoint...       │
-│                                     │ > Tests: 3 passed, 0 failed      │
-│ Tasks:                              │ > Ready to commit                │
-│ → 42 [in-progress] User metrics     │                                  │
-│   → 42.1 [done] Schema              │ [Live output from Claude Code]   │
-│   → 42.2 [active] Endpoint ◀        │                                  │
-│   → 42.3 [pending] Dashboard        │                                  │
-│                                     │                                  │
-│ [s] start  [p] pause  [q] quit      │                                  │
-└─────────────────────────────────────┴──────────────────────────────────┘
-```
-
-### Implementation Notes
-
-- **Left pane**: `apps/cli/src/ui/tui/navigator.ts` (new, uses `blessed` or `ink`)
-- **Right pane**: spawned via `tmux split-window -h` running `tm autopilot --executor-mode`
-- **Communication**: shared state file `.taskmaster/state/current-run.json` + file watching or event stream
-- **Keybindings**:
-  - `s` - Start selected task
-  - `p` - Pause/resume current run
-  - `q` - Quit (with confirmation if run active)
-  - `↑/↓` - Navigate task list
-  - `Enter` - Expand/collapse subtasks
-
-## Prompt Composition (Detailed)
-
-### System Prompt Assembly
-
-Prompts are composed in three layers:
-
-1. **Base rules** (loaded in order from `.cursor/rules/` and `.claude/agents/`):
-   - `git_workflow.mdc` → git commit conventions, branch policy, PR guidelines
-   - `test_workflow.mdc` → TDD loop requirements, coverage thresholds, test structure
-   - `surgical-test-generator.md` → test generation methodology, project-specific test patterns
-
-2. **Task context injection**:
-   ```
-   You are implementing:
-   Task #42 [analytics]: User metrics tracking
-   Subtask 42.2: Add collection endpoint
-
-   Description:
-   Implement POST /api/metrics endpoint to collect user metrics events
-
-   Acceptance criteria:
-   - POST /api/metrics accepts { userId, eventType, timestamp }
-   - Validates input schema (reject missing/invalid fields)
-   - Persists to database
-   - Returns 201 on success with created record
-   - Returns 400 on validation errors
-
-   Dependencies:
-   - Subtask 42.1 (metrics schema) is complete
-
-   Current phase: RED (generate failing tests)
-   Test command: npm test
-   Test file convention: src/**/*.test.js (vitest framework detected)
-   Branch: analytics/task-42-user-metrics
-   Project language: JavaScript (Node.js)
-   ```
-
-3. **Phase-specific instructions**:
-   - **RED phase**: "Generate minimal failing tests for this subtask. Do NOT implement any production code. Only create test files. Confirm tests fail with clear error messages indicating missing implementation."
-   - **GREEN phase**: "Implement minimal code to pass the failing tests. Follow existing project patterns in `src/`. Only modify files necessary for this subtask. Keep changes focused and reviewable."
-
-### Example Full Prompt (RED Phase)
-
-```markdown
-<SYSTEM PROMPT>
-[Contents of .cursor/rules/git_workflow.mdc]
-[Contents of .cursor/rules/test_workflow.mdc]
-[Contents of .claude/agents/surgical-test-generator.md]
-
-<TASK CONTEXT>
-You are implementing:
-Task #42.2: Add collection endpoint
-
-Description:
-Implement POST /api/metrics endpoint to collect user metrics events
-
-Acceptance criteria:
-- POST /api/metrics accepts { userId, eventType, timestamp }
-- Validates input schema (reject missing/invalid fields)
-- Persists to database using MetricsSchema from subtask 42.1
-- Returns 201 on success with created record
-- Returns 400 on validation errors with details
-
-Dependencies: Subtask 42.1 (metrics schema) is complete
-
-<INSTRUCTION>
-Generate failing tests for this subtask. Follow project conventions:
-- Test file: src/api/__tests__/metrics.test.js
-- Framework: vitest (detected from package.json)
-- Test cases to cover:
-  * POST /api/metrics with valid payload → should return 201 (will fail: endpoint not implemented)
-  * POST /api/metrics with missing userId → should return 400 (will fail: validation not implemented)
-  * POST /api/metrics with invalid timestamp → should return 400 (will fail: validation not implemented)
-  * POST /api/metrics should persist to database → should save record (will fail: persistence not implemented)
-
-Do NOT implement the endpoint code yet. Only create test file(s).
-Confirm tests fail with messages like "Cannot POST /api/metrics" or "endpoint not defined".
-
-Output format:
-1. File path to create: src/api/__tests__/metrics.test.js
-2. Complete test code
-3. Command to run: npm test src/api/__tests__/metrics.test.js
-```
-
-### Example Full Prompt (GREEN Phase)
-
-```markdown
-<SYSTEM PROMPT>
-[Contents of .cursor/rules/git_workflow.mdc]
-[Contents of .cursor/rules/test_workflow.mdc]
-
-<TASK CONTEXT>
-Task #42.2: Add collection endpoint
-[same context as RED phase]
-
-<CURRENT STATE>
-Tests created in RED phase:
-- src/api/__tests__/metrics.test.js
-- 5 tests written, all failing as expected
-
-Test output:
-```
-FAIL src/api/__tests__/metrics.test.js
-  POST /api/metrics
-    ✗ should return 201 with valid payload (endpoint not found)
-    ✗ should return 400 with missing userId (endpoint not found)
-    ✗ should return 400 with invalid timestamp (endpoint not found)
-    ✗ should persist to database (endpoint not found)
-```
-
-<INSTRUCTION>
-Implement minimal code to make all tests pass.
-
-Guidelines:
-- Create/modify file: src/api/metrics.js
-- Use existing patterns from src/api/ (e.g., src/api/users.js for reference)
-- Import MetricsSchema from subtask 42.1 (src/models/schema.js)
-- Implement validation, persistence, and response handling
-- Follow project error handling conventions
-- Keep implementation focused on this subtask only
-
-After implementation:
-1. Run tests: npm test src/api/__tests__/metrics.test.js
-2. Confirm all 5 tests pass
-3. Report results
-
-Output format:
-1. File(s) created/modified
-2. Implementation code
-3. Test command and results
-```
-
-### Prompt Loading Configuration
-
-See `.taskmaster/config.json` → `prompts` section for paths and load order.
-
-## Configuration Schema
-
-### .taskmaster/config.json
-
-```json
-{
-  "autopilot": {
-    "enabled": true,
-    "requireCleanWorkingTree": true,
-    "commitTemplate": "{type}({scope}): {msg}",
-    "defaultCommitType": "feat",
-    "maxGreenAttempts": 3,
-    "testTimeout": 300000
-  },
-  "test": {
-    "runner": "auto",
-    "coverageThresholds": {
-      "lines": 80,
-      "branches": 80,
-      "functions": 80,
-      "statements": 80
-    },
-    "targetedRunPattern": "**/*.test.js"
-  },
-  "git": {
-    "branchPattern": "{tag}/task-{id}-{slug}",
-    "pr": {
-      "enabled": true,
-      "base": "default",
-      "bodyTemplate": ".taskmaster/templates/pr-body.md"
-    }
-  },
-  "prompts": {
-    "rulesPath": ".cursor/rules",
-    "testGeneratorPath": ".claude/agents/surgical-test-generator.md",
-    "loadOrder": ["git_workflow.mdc", "test_workflow.mdc"]
-  }
-}
-```
-
-### Configuration Fields
-
-#### autopilot
-- `enabled` (boolean): Enable/disable autopilot functionality
-- `requireCleanWorkingTree` (boolean): Require clean git state before starting
-- `commitTemplate` (string): Template for commit messages (tokens: `{type}`, `{scope}`, `{msg}`)
-- `defaultCommitType` (string): Default commit type (feat, fix, chore, etc.)
-- `maxGreenAttempts` (number): Maximum retry attempts to achieve green tests (default: 3)
-- `testTimeout` (number): Timeout in milliseconds per test run (default: 300000 = 5min)
-
-#### test
-- `runner` (string): Test runner detection mode (`"auto"` or explicit command like `"npm test"`)
-- `coverageThresholds` (object): Minimum coverage percentages required
-  - `lines`, `branches`, `functions`, `statements` (number): Threshold percentages (0-100)
-- `targetedRunPattern` (string): Glob pattern for targeted subtask test runs
-
-#### git
-- `branchPattern` (string): Branch naming pattern (tokens: `{tag}`, `{id}`, `{slug}`)
-- `pr.enabled` (boolean): Enable automatic PR creation
-- `pr.base` (string): Target branch for PRs (`"default"` uses repo default, or specify like `"main"`)
-- `pr.bodyTemplate` (string): Path to PR body template file (optional)
-
-#### prompts
-- `rulesPath` (string): Directory containing rule files (e.g., `.cursor/rules`)
-- `testGeneratorPath` (string): Path to test generator prompt file
-- `loadOrder` (array): Order to load rule files from `rulesPath`
-
-### Environment Variables
-
-```bash
-# Required for executor
-ANTHROPIC_API_KEY=sk-ant-...          # Claude API key
-
-# Optional: for PR creation
-GITHUB_TOKEN=ghp_...                  # GitHub personal access token
-
-# Optional: for other executors (future)
-OPENAI_API_KEY=sk-...
-GOOGLE_API_KEY=...
-```
-
-## Run Artifacts & Observability
-
-### Per-Run Artifact Structure
-
-Each autopilot run creates a timestamped directory with complete traceability:
-
-```
-.taskmaster/reports/runs/2025-01-15-142033/
-├── manifest.json          # run metadata (task id, start/end time, status)
-├── log.jsonl              # timestamped event stream
-├── commits.txt            # list of commit SHAs made during run
-├── test-results/
-│   ├── subtask-42.1-red.json
-│   ├── subtask-42.1-green.json
-│   ├── subtask-42.2-red.json
-│   ├── subtask-42.2-green-attempt1.json
-│   ├── subtask-42.2-green-attempt2.json
-│   ├── subtask-42.2-green-attempt3.json
-│   └── final-suite.json
-└── pr.md                  # generated PR body
-```
-
-### manifest.json Format
-
-```json
-{
-  "runId": "2025-01-15-142033",
-  "taskId": "42",
-  "tag": "analytics",
-  "branch": "analytics/task-42-user-metrics",
-  "startTime": "2025-01-15T14:20:33Z",
-  "endTime": "2025-01-15T14:45:12Z",
-  "status": "completed",
-  "subtasksCompleted": ["42.1", "42.2", "42.3"],
-  "subtasksFailed": [],
-  "totalCommits": 3,
-  "prUrl": "https://github.com/org/repo/pull/123",
-  "finalCoverage": {
-    "lines": 85.3,
-    "branches": 82.1,
-    "functions": 88.9,
-    "statements": 85.0
-  }
-}
-```
-
-### log.jsonl Format
-
-Event stream in JSON Lines format for easy parsing and debugging:
-
-```jsonl
-{"ts":"2025-01-15T14:20:33Z","phase":"preflight","status":"ok","details":{"testCmd":"npm test","gitClean":true}}
-{"ts":"2025-01-15T14:20:45Z","phase":"branch","status":"ok","branch":"analytics/task-42-user-metrics"}
-{"ts":"2025-01-15T14:21:00Z","phase":"red","subtask":"42.1","status":"ok","tests":{"failed":3,"passed":0}}
-{"ts":"2025-01-15T14:22:15Z","phase":"green","subtask":"42.1","status":"ok","tests":{"passed":3,"failed":0},"attempts":2}
-{"ts":"2025-01-15T14:22:20Z","phase":"commit","subtask":"42.1","status":"ok","sha":"a1b2c3d","message":"feat(metrics): add metrics schema (task 42.1)"}
-{"ts":"2025-01-15T14:23:00Z","phase":"red","subtask":"42.2","status":"ok","tests":{"failed":5,"passed":0}}
-{"ts":"2025-01-15T14:25:30Z","phase":"green","subtask":"42.2","status":"error","tests":{"passed":3,"failed":2},"attempts":3,"error":"Max attempts reached"}
-{"ts":"2025-01-15T14:25:35Z","phase":"pause","reason":"max_attempts","nextAction":"manual_review"}
-```
-
-### Test Results Format
-
-Each test run stores detailed results:
-
-```json
-{
-  "subtask": "42.2",
-  "phase": "green",
-  "attempt": 3,
-  "timestamp": "2025-01-15T14:25:30Z",
-  "command": "npm test src/api/__tests__/metrics.test.js",
-  "exitCode": 1,
-  "duration": 2340,
-  "summary": {
-    "total": 5,
-    "passed": 3,
-    "failed": 2,
-    "skipped": 0
-  },
-  "failures": [
-    {
-      "test": "POST /api/metrics should return 201 with valid payload",
-      "error": "Expected status 201, got 500",
-      "stack": "..."
-    }
-  ],
-  "coverage": {
-    "lines": 78.5,
-    "branches": 75.0,
-    "functions": 80.0,
-    "statements": 78.5
-  }
-}
-```
-
-## Execution Model
-
-### Orchestration vs Direct Execution
-
-The autopilot system uses an **orchestration model** rather than direct code execution:
-
-**Orchestrator Role** (tm-core WorkflowOrchestrator):
-- Maintains state machine tracking current phase (RED/GREEN/COMMIT) per subtask
-- Validates preconditions (tests pass, git state clean, etc.)
-- Returns "work units" describing what needs to be done next
-- Records completion and advances to next phase
-- Persists state for resumability
-
-**Executor Role** (Claude Code/AI session via MCP):
-- Queries orchestrator for next work unit
-- Executes the work (generates tests, writes code, runs tests, makes commits)
-- Reports results back to orchestrator
-- Handles file operations and tool invocations
-
-**Why This Approach?**
-- Leverages existing AI capabilities (Claude Code) rather than duplicating them
-- MCP protocol provides clean separation between state management and execution
-- Allows human oversight and intervention at each phase
-- Simpler to implement: orchestrator is pure state logic, no code generation needed
-- Enables multiple executor types (Claude Code, other AI tools, human developers)
-
-**Example Flow**:
-```typescript
-// Claude Code (via MCP) queries orchestrator
-const workUnit = await orchestrator.getNextWorkUnit('42');
-// => {
-//      phase: 'RED',
-//      subtask: '42.1',
-//      action: 'Generate failing tests for metrics schema',
-//      context: { title, description, dependencies, testFile: 'src/__tests__/schema.test.js' }
-//    }
-
-// Claude Code executes the work (writes test file, runs tests)
-// Then reports back
-await orchestrator.completeWorkUnit('42', '42.1', 'RED', {
-  success: true,
-  testsCreated: ['src/__tests__/schema.test.js'],
-  testsFailed: 3
-});
-
-// Query again for next phase
-const nextWorkUnit = await orchestrator.getNextWorkUnit('42');
-// => { phase: 'GREEN', subtask: '42.1', action: 'Implement code to pass tests', ... }
-```
-
-## Design Decisions
-
-### Why commit per subtask instead of per task?
-
-**Decision**: Commit after each subtask's green state, not after the entire task.
-
-**Rationale**:
-- Atomic commits make code review easier (reviewers can see logical progression)
-- Easier to revert a single subtask if it causes issues downstream
-- Matches the TDD loop's natural checkpoint and cognitive boundary
-- Provides resumability points if the run is interrupted
-
-**Trade-off**: More commits per task (can use squash-merge in PRs if desired)
-
-### Why not support parallel subtask execution?
-
-**Decision**: Sequential subtask execution in Phase 1; parallel execution deferred to Phase 3.
-
-**Rationale**:
-- Subtasks often have implicit dependencies (e.g., schema before endpoint, endpoint before UI)
-- Simpler orchestrator state machine (less complexity = faster to ship)
-- Parallel execution requires explicit dependency DAG and conflict resolution
-- Can be added in Phase 3 once core workflow is proven stable
-
-**Trade-off**: Slower for truly independent subtasks (mitigated by keeping subtasks small and focused)
-
-### Why require 80% coverage by default?
-
-**Decision**: Enforce 80% coverage threshold (lines/branches/functions/statements) before allowing commits.
-
-**Rationale**:
-- Industry standard baseline for production code quality
-- Forces test generation to be comprehensive, not superficial
-- Configurable per project via `.taskmaster/config.json` if too strict
-- Prevents "green tests" that only test happy paths
-
-**Trade-off**: May require more test generation iterations; can be lowered per project
-
-### Why use tmux instead of a rich GUI?
-
-**Decision**: MVP uses tmux split panes for TUI, not Electron/web-based GUI.
-
-**Rationale**:
-- Tmux is universally available on dev machines; no installation burden
-- Terminal-first workflows match developer mental model (no context switching)
-- Simpler to implement and maintain; can add GUI later via extensions
-- State stored in files allows IDE/extension integration without coupling
-
-**Trade-off**: Less visual polish than GUI; requires tmux familiarity
-
-### Why not support multiple executors (codex/gemini/claude) in Phase 1?
-
-**Decision**: Start with Claude executor only; add others in Phase 2+.
-
-**Rationale**:
-- Reduces scope and complexity for initial delivery
-- Claude Code already integrated with existing executor service
-- Executor abstraction already exists; adding more is straightforward later
-- Different executors may need different prompt strategies (requires experimentation)
-
-**Trade-off**: Users locked to Claude initially; can work around with manual executor selection
-
-## Risks and Mitigations
-
-- Model hallucination/large diffs: restrict prompt scope; enforce minimal changes; show diff previews (optional) before commit.
-
-- Flaky tests: allow retries, isolate targeted runs for speed, then full suite before commit.
-
-- Environment variability: detect runners/tools; provide fallbacks and actionable errors.
-
-- PR creation fails: still push and print manual commands; persist PR body to reuse.
-
-## Open Questions
-
-1) Slugging rules for branch names; any length limits or normalization beyond {slug} token sanitize?
-
-2) PR body standard sections beyond run report (e.g., checklist, coverage table)?
-
-3) Default executor prompt fine-tuning once codex/gemini integration is available.
-
-4) Where to store persistent TUI state (pane layout, last selection) in .taskmaster/state.json?
-
-## Branch Naming
-
-- Include both the tag and the task id in the branch name to make lineage explicit.
-
-- Default pattern: <tag>/task-<id>[-slug] (e.g., master/task-12, tag-analytics/task-4-user-auth).
-
-- Configurable via .taskmaster/config.json: git.branchPattern supports tokens {tag}, {id}, {slug}.
-
-## PR Base Branch
-
-- Use the repository’s default branch (detected via git) unless overridden.
-
-- Title format: Task #<id> [<tag>]: <title>.
-
-## RPG Mapping (Repository Planning Graph)
-
-Functional nodes (capabilities):
-
-- Autopilot Orchestration → drives TDD loop and lifecycle
-
-- Test Generation (Surgical) → produces failing tests from subtask context
-
-- Test Execution + Coverage → runs suite, enforces thresholds
-
-- Git/Branch/PR Management → safe operations and PR creation
-
-- TUI/Terminal Integration → interactive control and visibility via tmux
-
-- MCP Integration → structured task/status/context operations
-
-Structural nodes (code organization):
-
-- packages/tm-core:
-
-  - services/workflow-orchestrator.ts (new)
-
-  - services/test-runner-adapter.ts (new)
-
-  - services/git-adapter.ts (new)
-
-  - existing: task-service.ts, task-execution-service.ts, executors/*
-
-- apps/cli:
-
-  - src/commands/autopilot.command.ts (new)
-
-  - src/ui/tui/ (new tmux/TUI helpers)
-
-- scripts/modules:
-
-  - reuse utils/git-utils.js, task-manager/tag-management.js
-
-- .claude/agents/:
-
-  - surgical-test-generator.md
-
-Edges (data/control flow):
-
-- Autopilot → Test Generation → Test Execution → Git Commit → loop
-
-- Autopilot → Git Adapter (branch, tag, PR)
-
-- Autopilot → TUI (event stream) → tmux pane control
-
-- Autopilot → MCP tools for task/status updates
-
-- Test Execution → Coverage gate → Autopilot decision
-
-Topological traversal (implementation order):
-
-1) Git/Test adapters (foundations)
-
-2) Orchestrator skeleton + events
-
-3) CLI autopilot command and dry-run
-
-4) Surgical test-gen integration and execution gate
-
-5) PR creation, run reports, resumability
-
-## Phased Roadmap
-
-- Phase 0: Spike
-
-  - Implement CLI skeleton tm autopilot with dry-run showing planned steps from a real task + subtasks.
-
-  - Detect test runner (package.json) and git state; render a preflight report.
-
-- Phase 1: Core Rails (State Machine & Orchestration)
-
-  - Implement WorkflowOrchestrator in tm-core as a **state machine** that tracks TDD phases per subtask.
-
-  - Orchestrator **guides** the current AI session (Claude Code/MCP client) rather than executing code itself.
-
-  - Add Git/Test adapters for status checks and validation (not direct execution).
-
-  - WorkflowOrchestrator API:
-    - `getNextWorkUnit(taskId)` → returns next phase to execute (RED/GREEN/COMMIT) with context
-    - `completeWorkUnit(taskId, subtaskId, phase, result)` → records completion and advances state
-    - `getRunState(taskId)` → returns current progress and resumability data
-
-  - MCP integration: expose work unit endpoints so Claude Code can query "what to do next" and report back.
-
-  - Branch/tag mapping via existing tag-management APIs.
-
-  - Run report persisted under .taskmaster/reports/runs/ with state checkpoints for resumability.
-
-- Phase 2: PR + Resumability
-
-  - Add gh PR creation with well-formed body using the run report.
-
-  - Introduce resumable checkpoints and --resume flag.
-
-  - Add coverage enforcement and optional lint/format step.
-
-- Phase 3: Extensibility + Guardrails
-
-  - Add support for basic pytest/go test adapters.
-
-  - Add safeguards: diff preview mode, manual confirm gates, aggressive minimal-change prompts.
-
-  - Optional: small TUI panel and extension panel leveraging the same run state file.
-
-## References (Repo)
-
-- Test Workflow: .cursor/rules/test_workflow.mdc
-
-- Git Workflow: .cursor/rules/git_workflow.mdc
-
-- CLI: apps/cli/src/commands/start.command.ts, apps/cli/src/ui/components/*.ts
-
-- Core Services: packages/tm-core/src/services/task-service.ts, task-execution-service.ts
-
-- Executors: packages/tm-core/src/executors/*
-
-- Git Utilities: scripts/modules/utils/git-utils.js
-
-- Tag Management: scripts/modules/task-manager/tag-management.js
-
- - Surgical Test Generator: .claude/agents/surgical-test-generator.md
-

.taskmaster/docs/prd-tm-start.txt

@@ -1,91 +0,0 @@
-<context>
-# Overview
-Add a new CLI command: `task-master start <task_id>` (alias: `tm start <task_id>`). This command hard-codes `claude-code` as the executor, fetches task details, builds a standardized prompt, runs claude-code, shows the result, checks for git changes, and auto-marks the task as done if successful.
-
-We follow the Commander class pattern, reuse task retrieval from `show` command flow. Extremely minimal for 1-hour hackathon timeline.
-
-# Core Features
-- `start` command (Commander class style) 
-- Hard-coded executor: `claude-code`
-- Standardized prompt designed for minimal changes following existing patterns
-- Shows claude-code output (no streaming)
-- Git status check for success detection
-- Auto-mark task done if successful
-
-# User Experience
-```
-task-master start 12
-```
-1) Fetches Task #12 details
-2) Builds standardized prompt with task context
-3) Runs claude-code with the prompt
-4) Shows output
-5) Checks git status for changes
-6) Auto-marks task done if changes detected
-</context>
-
-<PRD>
-# Technical Architecture
-
-- Command pattern:
-  - Create `apps/cli/src/commands/start.command.ts` modeled on [list.command.ts](mdc:apps/cli/src/commands/list.command.ts) and task lookup from [show.command.ts](mdc:apps/cli/src/commands/show.command.ts)
-
-- Task retrieval:
-  - Use `@tm/core` via `createTaskMasterCore` to get task by ID
-  - Extract: id, title, description, details
-
-- Executor (ultra-simple approach):
-  - Execute `claude "full prompt here"` command directly
-  - The prompt tells Claude to first run `tm show <task_id>` to get task details
-  - Then tells Claude to implement the code changes
-  - This opens Claude CLI interface naturally in the current terminal
-  - No subprocess management needed - just execute the command
-
-- Execution flow:
-  1) Validate `<task_id>` exists; exit with error if not
-  2) Build standardized prompt that includes instructions to run `tm show <task_id>`
-  3) Execute `claude "prompt"` command directly in terminal
-  4) Claude CLI opens, runs `tm show`, then implements changes
-  5) After Claude session ends, run `git status --porcelain` to detect changes
-  6) If changes detected, auto-run `task-master set-status --id=<task_id> --status=done`
-
-- Success criteria:
-  - Success = exit code 0 AND git shows modified/created files
-  - Print changed file paths; warn if no changes detected
-
-# Development Roadmap
-
-MVP (ship in ~1 hour):
-1) Implement `start.command.ts` (Commander class), parse `<task_id>`
-2) Validate task exists via tm-core 
-3) Build prompt that tells Claude to run `tm show <task_id>` then implement
-4) Execute `claude "prompt"` command, then check git status and auto-mark done
-
-# Risks and Mitigations
-- Executor availability: Error clearly if `claude-code` provider fails
-- False success: Git-change heuristic acceptable for hackathon MVP
-
-# Appendix
-
-**Standardized Prompt Template:**
-```
-You are an AI coding assistant with access to this repository's codebase.
-
-First, run this command to get the task details:
-tm show <task_id>
-
-Then implement the task with these requirements:
-- Make the SMALLEST number of code changes possible
-- Follow ALL existing patterns in the codebase (you have access to analyze the code)
-- Do NOT over-engineer the solution
-- Use existing files/functions/patterns wherever possible
-- When complete, print: COMPLETED: <brief summary of changes>
-
-Begin by running tm show <task_id> to understand what needs to be implemented.
-```
-
-**Key References:**
-- [list.command.ts](mdc:apps/cli/src/commands/list.command.ts) - Command structure
-- [show.command.ts](mdc:apps/cli/src/commands/show.command.ts) - Task validation
-- Node.js `child_process.exec()` - For executing `claude "prompt"` command
-</PRD>

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

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

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

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