task-master-ai/CHANGELOG.md

A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.

# task-master-ai

## 0.43.0

### Minor Changes

- [#1599](https://github.com/eyaltoledano/claude-task-master/pull/1599) [`e689fcf`](https://github.com/eyaltoledano/claude-task-master/commit/e689fcf2a20cada4a19ee31fed723b6f35f2c13d) Thanks [@triepod-ai](https://github.com/triepod-ai)! - Add MCPB bundle for single-click Claude Desktop installation
  - Added `manifest.json` for MCP Bundle (MCPB) specification v0.3
  - Added `.mcpbignore` to exclude development files from bundle
  - Added `icon.png` (512x512) for Claude Desktop display
  - Enables users to install Task Master MCP server directly in Claude Desktop without manual configuration

- [#1605](https://github.com/eyaltoledano/claude-task-master/pull/1605) [`efedc85`](https://github.com/eyaltoledano/claude-task-master/commit/efedc85cb1110a75748f3df0e530f3c9e27d2155) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add verbose output mode to loop command with `--verbose` flag
  - New `-v, --verbose` flag shows Claude's work in real-time (thinking, tool calls) rather than waiting until the iteration completes
  - New `--no-output` flag excludes full Claude output from iteration results to save memory
  - Improved error handling with proper validation for incompatible options (verbose + sandbox)

- [#1611](https://github.com/eyaltoledano/claude-task-master/pull/1611) [`c798639`](https://github.com/eyaltoledano/claude-task-master/commit/c798639d1a6b492de1b7cc82a28a13ddfba23eb8) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add optional `metadata` field to tasks for storing user-defined custom data

  Tasks and subtasks now support an optional `metadata` field that allows storing arbitrary JSON data such as:
  - External IDs (GitHub issues, Jira tickets, Linear issues)
  - Workflow data (sprints, story points, custom statuses)
  - Integration data (sync timestamps, external system references)
  - Custom tracking (UUIDs, version numbers, audit information)

  Key features:
  - **AI-Safe**: Metadata is preserved through all AI operations (update-task, expand, etc.) because AI schemas intentionally exclude this field
  - **Flexible Schema**: Store any JSON-serializable data without schema changes
  - **Backward Compatible**: The field is optional; existing tasks work without modification
  - **Subtask Support**: Both tasks and subtasks can have their own metadata
  - **MCP Tool Support**: Use `update_task` and `update_subtask` with the `metadata` parameter to update metadata (requires `TASK_MASTER_ALLOW_METADATA_UPDATES=true` in MCP server environment)

  Example usage:

  ```json
  {
    "id": 1,
    "title": "Implement authentication",
    "metadata": {
      "githubIssue": 42,
      "sprint": "Q1-S3",
      "storyPoints": 5
    }
  }
  ```

  MCP metadata update example:

  ```javascript
  // With TASK_MASTER_ALLOW_METADATA_UPDATES=true set in MCP env
  update_task({
    id: "1",
    metadata: '{"githubIssue": 42, "sprint": "Q1-S3"}',
  });
  ```

### Patch Changes

- [#1587](https://github.com/eyaltoledano/claude-task-master/pull/1587) [`0d628ca`](https://github.com/eyaltoledano/claude-task-master/commit/0d628ca9514f22607c0a6495b701e4cde743b45c) Thanks [@bjcoombs](https://github.com/bjcoombs)! - Add modifyJSON function for safer file updates

- [#1600](https://github.com/eyaltoledano/claude-task-master/pull/1600) [`712a078`](https://github.com/eyaltoledano/claude-task-master/commit/712a0789d6d584adf5dbb27732c783cd240014b2) Thanks [@esumerfd](https://github.com/esumerfd)! - Add --no-banner to suppress the startup banner.

## 0.42.0

### Minor Changes

- [#1533](https://github.com/eyaltoledano/claude-task-master/pull/1533) [`6c3a92c`](https://github.com/eyaltoledano/claude-task-master/commit/6c3a92c439d4573ff5046e3d251a4a26d85d0deb) Thanks [@bjcoombs](https://github.com/bjcoombs)! - Add --ready and --blocking filters to list command for identifying parallelizable tasks
  - Add `--ready` filter to show only tasks with satisfied dependencies (ready to work on)
  - Add `--blocking` filter to show only tasks that block other tasks
  - Combine `--ready --blocking` to find high-impact tasks (ready AND blocking others)
  - Add "Blocks" column to task table showing which tasks depend on each task
  - Blocks field included in JSON output for programmatic access
  - Add "Ready" column to `tags` command showing count of ready tasks per tag
  - Add `--ready` filter to `tags` command to show only tags with available work
  - Excludes deferred/blocked tasks from ready count (only actionable statuses)
  - Add `--all-tags` option to list ready tasks across all tags (use with `--ready`)
  - Tag column shown as first column when using `--all-tags` for easy scanning

### Patch Changes

- [#1569](https://github.com/eyaltoledano/claude-task-master/pull/1569) [`4cfde1c`](https://github.com/eyaltoledano/claude-task-master/commit/4cfde1c3d54b94701e0fcfc8dbdedbc3bbaf4339) Thanks [@bjcoombs](https://github.com/bjcoombs)! - Improve concurrency safety by adopting modifyJson pattern in file-storage
  - Refactor saveTasks, createTag, deleteTag, renameTag to use modifyJson for atomic read-modify-write operations
  - This prevents lost updates when multiple processes concurrently modify tasks.json
  - Complements the cross-process file locking added in PR #1566

- [#1566](https://github.com/eyaltoledano/claude-task-master/pull/1566) [`3cc6174`](https://github.com/eyaltoledano/claude-task-master/commit/3cc6174b471fc1ea7f12955095d0d35b4dc5904c) Thanks [@bjcoombs](https://github.com/bjcoombs)! - Fix race condition when multiple Claude Code windows write to tasks.json simultaneously
  - Add cross-process file locking to prevent concurrent write collisions
  - Implement atomic writes using temp file + rename pattern to prevent partial writes
  - Re-read file inside lock to get current state, preventing lost updates from stale snapshots
  - Add stale lock detection and automatic cleanup (10-second timeout)
  - Export `withFileLock` and `withFileLockSync` utilities for use by other modules

  This fix prevents data loss that could occur when multiple Task Master instances (e.g., multiple Claude Code windows) access the same tasks.json file concurrently.

- [#1576](https://github.com/eyaltoledano/claude-task-master/pull/1576) [`097c8ed`](https://github.com/eyaltoledano/claude-task-master/commit/097c8edcb0ca065218e9b51758ad370ac7475f1a) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve loop command error handling and use dangerously-skip-permissions
  - Add proper spawn error handling (ENOENT, EACCES) with actionable messages
  - Return error info from checkSandboxAuth and runInteractiveAuth instead of silent failures
  - Use --dangerously-skip-permissions for unattended loop execution
  - Fix null exit code masking issue

- [#1577](https://github.com/eyaltoledano/claude-task-master/pull/1577) [`e762e4f`](https://github.com/eyaltoledano/claude-task-master/commit/e762e4f64608a77d248ac8ce5eeb218000b51907) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Make Docker sandbox mode opt-in for loop command
  - Add `--sandbox` flag to `task-master loop` (default: use plain `claude -p`)
  - Preserve progress.txt between runs (append instead of overwrite)
  - Display execution mode in loop startup output

- [#1580](https://github.com/eyaltoledano/claude-task-master/pull/1580) [`940ab58`](https://github.com/eyaltoledano/claude-task-master/commit/940ab587e50cff43c3a2639bbbd210fdd577c3f1) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Update Codex CLI supported models to match current available models
  - Remove deprecated models: gpt-5, gpt-5-codex, gpt-5.1
  - Add gpt-5.2-codex as the current default model
  - Add gpt-5.1-codex-mini for faster, cheaper option
  - Keep gpt-5.1-codex-max and gpt-5.2

## 0.42.0-rc.0

### Minor Changes

- [#1533](https://github.com/eyaltoledano/claude-task-master/pull/1533) [`6c3a92c`](https://github.com/eyaltoledano/claude-task-master/commit/6c3a92c439d4573ff5046e3d251a4a26d85d0deb) Thanks [@bjcoombs](https://github.com/bjcoombs)! - Add --ready and --blocking filters to list command for identifying parallelizable tasks
  - Add `--ready` filter to show only tasks with satisfied dependencies (ready to work on)
  - Add `--blocking` filter to show only tasks that block other tasks
  - Combine `--ready --blocking` to find high-impact tasks (ready AND blocking others)
  - Add "Blocks" column to task table showing which tasks depend on each task
  - Blocks field included in JSON output for programmatic access
  - Add "Ready" column to `tags` command showing count of ready tasks per tag
  - Add `--ready` filter to `tags` command to show only tags with available work
  - Excludes deferred/blocked tasks from ready count (only actionable statuses)
  - Add `--all-tags` option to list ready tasks across all tags (use with `--ready`)
  - Tag column shown as first column when using `--all-tags` for easy scanning

### Patch Changes

- [#1569](https://github.com/eyaltoledano/claude-task-master/pull/1569) [`4cfde1c`](https://github.com/eyaltoledano/claude-task-master/commit/4cfde1c3d54b94701e0fcfc8dbdedbc3bbaf4339) Thanks [@bjcoombs](https://github.com/bjcoombs)! - Improve concurrency safety by adopting modifyJson pattern in file-storage
  - Refactor saveTasks, createTag, deleteTag, renameTag to use modifyJson for atomic read-modify-write operations
  - This prevents lost updates when multiple processes concurrently modify tasks.json
  - Complements the cross-process file locking added in PR #1566

- [#1566](https://github.com/eyaltoledano/claude-task-master/pull/1566) [`3cc6174`](https://github.com/eyaltoledano/claude-task-master/commit/3cc6174b471fc1ea7f12955095d0d35b4dc5904c) Thanks [@bjcoombs](https://github.com/bjcoombs)! - Fix race condition when multiple Claude Code windows write to tasks.json simultaneously
  - Add cross-process file locking to prevent concurrent write collisions
  - Implement atomic writes using temp file + rename pattern to prevent partial writes
  - Re-read file inside lock to get current state, preventing lost updates from stale snapshots
  - Add stale lock detection and automatic cleanup (10-second timeout)
  - Export `withFileLock` and `withFileLockSync` utilities for use by other modules

  This fix prevents data loss that could occur when multiple Task Master instances (e.g., multiple Claude Code windows) access the same tasks.json file concurrently.

- [#1576](https://github.com/eyaltoledano/claude-task-master/pull/1576) [`097c8ed`](https://github.com/eyaltoledano/claude-task-master/commit/097c8edcb0ca065218e9b51758ad370ac7475f1a) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve loop command error handling and use dangerously-skip-permissions
  - Add proper spawn error handling (ENOENT, EACCES) with actionable messages
  - Return error info from checkSandboxAuth and runInteractiveAuth instead of silent failures
  - Use --dangerously-skip-permissions for unattended loop execution
  - Fix null exit code masking issue

- [#1577](https://github.com/eyaltoledano/claude-task-master/pull/1577) [`e762e4f`](https://github.com/eyaltoledano/claude-task-master/commit/e762e4f64608a77d248ac8ce5eeb218000b51907) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Make Docker sandbox mode opt-in for loop command
  - Add `--sandbox` flag to `task-master loop` (default: use plain `claude -p`)
  - Preserve progress.txt between runs (append instead of overwrite)
  - Display execution mode in loop startup output

- [#1580](https://github.com/eyaltoledano/claude-task-master/pull/1580) [`940ab58`](https://github.com/eyaltoledano/claude-task-master/commit/940ab587e50cff43c3a2639bbbd210fdd577c3f1) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Update Codex CLI supported models to match current available models
  - Remove deprecated models: gpt-5, gpt-5-codex, gpt-5.1
  - Add gpt-5.2-codex as the current default model
  - Add gpt-5.1-codex-mini for faster, cheaper option
  - Keep gpt-5.1-codex-max and gpt-5.2

## 0.41.0

### Minor Changes

- [#1571](https://github.com/eyaltoledano/claude-task-master/pull/1571) [`c2d6c18`](https://github.com/eyaltoledano/claude-task-master/commit/c2d6c18a96fce5a2d5cb50bd1ae5d58ef577501c) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add loop command for automated task execution with Claude Code

  **New Features:**
  - `task-master loop` command that runs Claude Code in a Docker sandbox, executing one task per iteration based on the selected tag
  - Built-in presets for different workflows:
    - `default` - General task completion from the Task Master backlog
    - `test-coverage` - Find uncovered code and write meaningful tests
    - `linting` - Fix lint errors and type errors one by one
    - `duplication` - Find duplicated code and refactor into shared utilities
    - `entropy` - Find code smells and clean them up
  - Progress file tracking to maintain context across iterations (inside `.taskmaster/loop-progress.txt`)
    - Remember to delete this file between loops to not pollute the agent with bad context
  - Automatic completion detection via `<loop-complete>` and `<loop-blocked>` markers

### Patch Changes

- [#1556](https://github.com/eyaltoledano/claude-task-master/pull/1556) [`1befc6a`](https://github.com/eyaltoledano/claude-task-master/commit/1befc6a341babd825b8dd000513ffbf8a1620e62) Thanks [@TheLazyIndianTechie](https://github.com/TheLazyIndianTechie)! - fix: tolerate AI SDK versions without jsonSchema export

  Fallback to sanitized Zod schema handling when jsonSchema is unavailable, and
  align structured-output tests and registration perf thresholds to reduce CI
  failures.

  Also enforce sequential, unique subtask ids when regenerating subtasks during
  scope adjustment.

- [#1553](https://github.com/eyaltoledano/claude-task-master/pull/1553) [`226678b`](https://github.com/eyaltoledano/claude-task-master/commit/226678b93aa01d0e62c0fac852802e9955c7ebd7) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - fix: Remove .default() from Zod schemas to satisfy OpenAI strict JSON schema validation

  This fixes an issue where codex-cli provider (using OpenAI API) would fail with "Missing 'dependencies'" error during task expansion. OpenAI's structured outputs require all properties to be in the 'required' array, but Zod's .default() makes fields optional. The fix removes .default() from schemas and applies defaults at the application level instead.

- [#1543](https://github.com/eyaltoledano/claude-task-master/pull/1543) [`9a6fa1b`](https://github.com/eyaltoledano/claude-task-master/commit/9a6fa1bd2ab389097f1074fe4a4f779dee8180b6) Thanks [@triepod-ai](https://github.com/triepod-ai)! - feat: Add tool annotations for improved LLM tool understanding

  Added MCP tool annotations (readOnlyHint, destructiveHint, title) to all 12 tools to help LLMs better understand tool behavior and make safer decisions about tool execution.

## 0.40.1

### Patch Changes

- [#1523](https://github.com/eyaltoledano/claude-task-master/pull/1523) [`fc1a79f`](https://github.com/eyaltoledano/claude-task-master/commit/fc1a79f2565b0d8c24f009aec2c473a335262ae2) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Codex cli Validate reasoning effort against model capabilities
  - Add provider-level reasoning effort validation for OpenAI models
  - Automatically cap unsupported effort levels (e.g., 'xhigh' on gpt-5.1 and gpt-5 becomes 'high')

- [#1549](https://github.com/eyaltoledano/claude-task-master/pull/1549) [`98087ac`](https://github.com/eyaltoledano/claude-task-master/commit/98087acae91fad7345bdb4c253d4dfd0d584f81e) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve CLI startup speed by 2x

- [#1545](https://github.com/eyaltoledano/claude-task-master/pull/1545) [`a0007a3`](https://github.com/eyaltoledano/claude-task-master/commit/a0007a3575305c367c8561584aa0dbd181f5e1cc) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Smarter project root detection with boundary markers
  - Prevents Task Master from incorrectly detecting `.taskmaster` folders in your home directory when working inside a different project
  - Now stops at project boundaries (`.git`, `package.json`, lock files) instead of searching all the way up to the filesystem root
  - Adds support for monorepo markers (`lerna.json`, `nx.json`, `turbo.json`) and additional lock files (`bun.lockb`, `deno.lock`)

- [#1523](https://github.com/eyaltoledano/claude-task-master/pull/1523) [`fc1a79f`](https://github.com/eyaltoledano/claude-task-master/commit/fc1a79f2565b0d8c24f009aec2c473a335262ae2) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve json schemas for ai-related commands making it more compatible with openai models
  - Fixes #1541 #1542

- [#1542](https://github.com/eyaltoledano/claude-task-master/pull/1542) [`b817d6f`](https://github.com/eyaltoledano/claude-task-master/commit/b817d6f9f278c84785ec468f9b305e70c47266f6) Thanks [@mdimitrovg](https://github.com/mdimitrovg)! - Fixed vertex-ai authentication when using service account and vertex location env variable.

## 0.40.0

### Minor Changes

- [#1538](https://github.com/eyaltoledano/claude-task-master/pull/1538) [`a2d5639`](https://github.com/eyaltoledano/claude-task-master/commit/a2d563991dd8ad6b8a9b76d0d43eac7a6156dd97) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Added Gemini 3 Flash Preview model support for Google and Gemini CLI providers

- [#1535](https://github.com/eyaltoledano/claude-task-master/pull/1535) [`4d1ed20`](https://github.com/eyaltoledano/claude-task-master/commit/4d1ed20345083ab2ec1c7fc268c69379281a68ea) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add auto-detection for IDE profiles in rules command
  - `tm rules add` now opens interactive setup with detected IDEs pre-selected
  - `tm rules add -y` auto-detects and installs rules without prompting
  - Detects 13 IDEs: Cursor, Claude Code, Windsurf, VS Code, Roo, Cline, Kiro, Zed, Kilo, Trae, Gemini, OpenCode, Codex

- [#1526](https://github.com/eyaltoledano/claude-task-master/pull/1526) [`38c2c08`](https://github.com/eyaltoledano/claude-task-master/commit/38c2c08af1f8de729d5d2dab586ec4622445f2db) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add watch mode and compact output to list command
  - Add `-w/--watch` flag to continuously monitor task changes with real-time updates
  - Add `-c/--compact` flag for minimal task output format
  - Add `--no-header` flag to hide the command header
  - Support file-based watching via fs.watch for local tasks.json
  - Support API-based watching via Supabase Realtime for authenticated users
  - Display last sync timestamp and source in watch mode

### Patch Changes

- [#1538](https://github.com/eyaltoledano/claude-task-master/pull/1538) [`a2d5639`](https://github.com/eyaltoledano/claude-task-master/commit/a2d563991dd8ad6b8a9b76d0d43eac7a6156dd97) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improved model search in `task-master models --setup` to match both display names and model IDs

## 0.40.0-rc.0

### Minor Changes

- [#1538](https://github.com/eyaltoledano/claude-task-master/pull/1538) [`a2d5639`](https://github.com/eyaltoledano/claude-task-master/commit/a2d563991dd8ad6b8a9b76d0d43eac7a6156dd97) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Added Gemini 3 Flash Preview model support for Google and Gemini CLI providers

- [#1535](https://github.com/eyaltoledano/claude-task-master/pull/1535) [`4d1ed20`](https://github.com/eyaltoledano/claude-task-master/commit/4d1ed20345083ab2ec1c7fc268c69379281a68ea) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add auto-detection for IDE profiles in rules command
  - `tm rules add` now opens interactive setup with detected IDEs pre-selected
  - `tm rules add -y` auto-detects and installs rules without prompting
  - Detects 13 IDEs: Cursor, Claude Code, Windsurf, VS Code, Roo, Cline, Kiro, Zed, Kilo, Trae, Gemini, OpenCode, Codex

- [#1526](https://github.com/eyaltoledano/claude-task-master/pull/1526) [`38c2c08`](https://github.com/eyaltoledano/claude-task-master/commit/38c2c08af1f8de729d5d2dab586ec4622445f2db) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add watch mode and compact output to list command
  - Add `-w/--watch` flag to continuously monitor task changes with real-time updates
  - Add `-c/--compact` flag for minimal task output format
  - Add `--no-header` flag to hide the command header
  - Support file-based watching via fs.watch for local tasks.json
  - Support API-based watching via Supabase Realtime for authenticated users
  - Display last sync timestamp and source in watch mode

### Patch Changes

- [#1538](https://github.com/eyaltoledano/claude-task-master/pull/1538) [`a2d5639`](https://github.com/eyaltoledano/claude-task-master/commit/a2d563991dd8ad6b8a9b76d0d43eac7a6156dd97) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improved model search in `task-master models --setup` to match both display names and model IDs

## 0.39.0

### Minor Changes

- [#1521](https://github.com/eyaltoledano/claude-task-master/pull/1521) [`353e3bf`](https://github.com/eyaltoledano/claude-task-master/commit/353e3bffd6df528dc19f7c5790564d0dead14c6d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhanced task metadata display for remote/team mode tasks
  - Tasks now display rich implementation guidance in team mode including:
    - **Relevant Files**: Files to create, modify, or reference with descriptions
    - **Codebase Patterns**: Coding patterns and conventions to follow
    - **Existing Infrastructure**: Code and utilities to leverage
    - **Scope Boundaries**: What's in and out of scope for the task
    - **Implementation Approach**: Step-by-step guidance
    - **Technical Constraints**: Requirements and limitations
    - **Acceptance Criteria**: Definition of done checklist
    - **Skills & Category**: Task classification and required expertise
  - How to see the new task details:
    1. Create a brief on tryhamster.com
    2. Generate the plan of the brief
    3. View subtasks

- [#1525](https://github.com/eyaltoledano/claude-task-master/pull/1525) [`1c2228d`](https://github.com/eyaltoledano/claude-task-master/commit/1c2228dbb618e522798c4484b74c1508f13d61d6) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add tool search tool for Claude Code MCP server and enable deferred MCP loading
  - Added new tool search tool capabilities for the Taskmaster MCP in Claude Code
  - Running `task-master rules add claude` now automatically configures your shell (`~/.zshrc`, `~/.bashrc`, or PowerShell profile) with `ENABLE_EXPERIMENTAL_MCP_CLI=true` to enable deferred MCP loading
  - **Context savings**: Deferred loading saves ~16% of Claude Code's 200k context window (~33k tokens for Task Master alone). Savings apply to all MCP servers, so total savings may be higher depending on your setup.

### Patch Changes

- [#1310](https://github.com/eyaltoledano/claude-task-master/pull/1310) [`4b6570e`](https://github.com/eyaltoledano/claude-task-master/commit/4b6570e300eedb265af215c0ca6baeb772d42e4a) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix Azure OpenAI provider to use correct deployment-based URL format
  - Add Azure OpenAI documentation page <https://docs.task-master.dev/providers/azure>

## 0.39.0-rc.0

### Minor Changes

- [#1521](https://github.com/eyaltoledano/claude-task-master/pull/1521) [`353e3bf`](https://github.com/eyaltoledano/claude-task-master/commit/353e3bffd6df528dc19f7c5790564d0dead14c6d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhanced task metadata display for remote/team mode tasks
  - Tasks now display rich implementation guidance in team mode including:
    - **Relevant Files**: Files to create, modify, or reference with descriptions
    - **Codebase Patterns**: Coding patterns and conventions to follow
    - **Existing Infrastructure**: Code and utilities to leverage
    - **Scope Boundaries**: What's in and out of scope for the task
    - **Implementation Approach**: Step-by-step guidance
    - **Technical Constraints**: Requirements and limitations
    - **Acceptance Criteria**: Definition of done checklist
    - **Skills & Category**: Task classification and required expertise
  - How to see the new task details:
    1. Create a brief on tryhamster.com
    2. Generate the plan of the brief
    3. View subtasks

- [#1525](https://github.com/eyaltoledano/claude-task-master/pull/1525) [`1c2228d`](https://github.com/eyaltoledano/claude-task-master/commit/1c2228dbb618e522798c4484b74c1508f13d61d6) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add tool search tool for Claude Code MCP server and enable deferred MCP loading
  - Added new tool search tool capabilities for the Taskmaster MCP in Claude Code
  - Running `task-master rules add claude` now automatically configures your shell (`~/.zshrc`, `~/.bashrc`, or PowerShell profile) with `ENABLE_EXPERIMENTAL_MCP_CLI=true` to enable deferred MCP loading
  - **Context savings**: Deferred loading saves ~16% of Claude Code's 200k context window (~33k tokens for Task Master alone). Savings apply to all MCP servers, so total savings may be higher depending on your setup.

### Patch Changes

- [#1310](https://github.com/eyaltoledano/claude-task-master/pull/1310) [`4b6570e`](https://github.com/eyaltoledano/claude-task-master/commit/4b6570e300eedb265af215c0ca6baeb772d42e4a) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix Azure OpenAI provider to use correct deployment-based URL format
  - Add Azure OpenAI documentation page <https://docs.task-master.dev/providers/azure>

## 0.38.0

### Minor Changes

- [#1461](https://github.com/eyaltoledano/claude-task-master/pull/1461) [`9ee63e0`](https://github.com/eyaltoledano/claude-task-master/commit/9ee63e01db4308cf248be3855949c7cd86272b9b) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add operating mode filtering for slash commands and rules

  Solo mode and team mode now have distinct sets of commands and rules:
  - **Solo mode**: Local file-based storage commands (parse-prd, add-task, expand, etc.) plus common commands
  - **Team mode**: Team-specific commands (goham) plus common commands (show-task, list-tasks, help, etc.)

  Both modes share common commands for viewing and navigating tasks. The difference is:
  - Solo users get commands for local file management (PRD parsing, task expansion, dependencies)
  - Team users get Hamster cloud integration commands instead

  When switching modes (e.g., from solo to team), all existing TaskMaster commands and rules are automatically cleaned up before adding the new mode's files. This prevents orphaned commands/rules from previous modes.

  The operating mode is auto-detected from config or auth status, and can be overridden with `--mode=solo|team` flag on the `rules` command.

- [#1461](https://github.com/eyaltoledano/claude-task-master/pull/1461) [`9ee63e0`](https://github.com/eyaltoledano/claude-task-master/commit/9ee63e01db4308cf248be3855949c7cd86272b9b) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Taskmaster slash commands for:
  - Roo
  - Cursor
  - Codex
  - Gemini
  - Opencode

  Add them with `task-master rules add <provider>`

- [#1508](https://github.com/eyaltoledano/claude-task-master/pull/1508) [`69ac463`](https://github.com/eyaltoledano/claude-task-master/commit/69ac46351eac8e1c3f58b203b2a618bf6114c000) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Added support for new OpenAI models with reasoning effort configuration:
  - `gpt-5.1` (codex-cli & openai): supports none, low, medium, high reasoning
  - `gpt-5.1-codex-max` (codex-cli & openai): supports none, low, medium, high, xhigh reasoning
  - `gpt-5.2` (codex-cli & openai): supports none, low, medium, high, xhigh reasoning
  - `gpt-5.2-pro` (openai only): supports medium, high, xhigh reasoning

  Updated ai-sdk-provider-codex-cli dependency to ^0.7.0.

## 0.38.0-rc.1

### Minor Changes

- [#1461](https://github.com/eyaltoledano/claude-task-master/pull/1461) [`9ee63e0`](https://github.com/eyaltoledano/claude-task-master/commit/9ee63e01db4308cf248be3855949c7cd86272b9b) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add operating mode filtering for slash commands and rules

  Solo mode and team mode now have distinct sets of commands and rules:
  - **Solo mode**: Local file-based storage commands (parse-prd, add-task, expand, etc.) plus common commands
  - **Team mode**: Team-specific commands (goham) plus common commands (show-task, list-tasks, help, etc.)

  Both modes share common commands for viewing and navigating tasks. The difference is:
  - Solo users get commands for local file management (PRD parsing, task expansion, dependencies)
  - Team users get Hamster cloud integration commands instead

  When switching modes (e.g., from solo to team), all existing TaskMaster commands and rules are automatically cleaned up before adding the new mode's files. This prevents orphaned commands/rules from previous modes.

  The operating mode is auto-detected from config or auth status, and can be overridden with `--mode=solo|team` flag on the `rules` command.

- [#1461](https://github.com/eyaltoledano/claude-task-master/pull/1461) [`9ee63e0`](https://github.com/eyaltoledano/claude-task-master/commit/9ee63e01db4308cf248be3855949c7cd86272b9b) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Taskmaster slash commands for:
  - Roo
  - Cursor
  - Codex
  - Gemini
  - Opencode

  Add them with `task-master rules add <provider>`

## 0.38.0-rc.0

### Minor Changes

- [#1508](https://github.com/eyaltoledano/claude-task-master/pull/1508) [`69ac463`](https://github.com/eyaltoledano/claude-task-master/commit/69ac46351eac8e1c3f58b203b2a618bf6114c000) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Added support for new OpenAI models with reasoning effort configuration:
  - `gpt-5.1` (codex-cli & openai): supports none, low, medium, high reasoning
  - `gpt-5.1-codex-max` (codex-cli & openai): supports none, low, medium, high, xhigh reasoning
  - `gpt-5.2` (codex-cli & openai): supports none, low, medium, high, xhigh reasoning
  - `gpt-5.2-pro` (openai only): supports medium, high, xhigh reasoning

  Updated ai-sdk-provider-codex-cli dependency to ^0.7.0.

## 0.37.2

### Patch Changes

- [#1492](https://github.com/eyaltoledano/claude-task-master/pull/1492) [`071dfc6`](https://github.com/eyaltoledano/claude-task-master/commit/071dfc6be9abe30909157ea72e026036721cea1d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix login issues for users whose browsers or firewalls were blocking CLI authentication

- [#1491](https://github.com/eyaltoledano/claude-task-master/pull/1491) [`0e908be`](https://github.com/eyaltoledano/claude-task-master/commit/0e908be43af1075bae1fd7f6b7a6fad8a131dd56) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add `tm/` prefix to autopilot branch names
  - Team mode branches now follow the `tm/<org-slug>/task-<id>` naming convention for better organization.
  - Solves issue some users were having regarding not being able to start workflow on master Taskmaster tag

## 0.37.2

### Patch Changes

- [#1492](https://github.com/eyaltoledano/claude-task-master/pull/1492) [`071dfc6`](https://github.com/eyaltoledano/claude-task-master/commit/071dfc6be9abe30909157ea72e026036721cea1d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix login issues for users whose browsers or firewalls were blocking CLI authentication

- [#1491](https://github.com/eyaltoledano/claude-task-master/pull/1491) [`0e908be`](https://github.com/eyaltoledano/claude-task-master/commit/0e908be43af1075bae1fd7f6b7a6fad8a131dd56) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add `tm/` prefix to autopilot branch names
  - Team mode branches now follow the `tm/<org-slug>/task-<id>` naming convention for better organization.
  - Solves issue some users were having regarding not being able to start workflow on master Taskmaster tag

## 0.37.2-rc.0

### Patch Changes

- [#1492](https://github.com/eyaltoledano/claude-task-master/pull/1492) [`071dfc6`](https://github.com/eyaltoledano/claude-task-master/commit/071dfc6be9abe30909157ea72e026036721cea1d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix login issues for users whose browsers or firewalls were blocking CLI authentication

- [#1491](https://github.com/eyaltoledano/claude-task-master/pull/1491) [`0e908be`](https://github.com/eyaltoledano/claude-task-master/commit/0e908be43af1075bae1fd7f6b7a6fad8a131dd56) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add `tm/` prefix to autopilot branch names
  - Team mode branches now follow the `tm/<org-slug>/task-<id>` naming convention for better organization.
  - Solves issue some users were having regarding not being able to start workflow on master Taskmaster tag

## 0.37.1

### Patch Changes

- [#1477](https://github.com/eyaltoledano/claude-task-master/pull/1477) [`b0199f1`](https://github.com/eyaltoledano/claude-task-master/commit/b0199f1cfa643051f90406d69e90ea916d434e6a) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve auth-related error handling

- [#1478](https://github.com/eyaltoledano/claude-task-master/pull/1478) [`6ff330f`](https://github.com/eyaltoledano/claude-task-master/commit/6ff330f8c2bc6e534e0a883c770e8394d7ad5fa8) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Increase page size of brief selection (interactive cli setup)

## 0.37.1-rc.0

### Patch Changes

- [#1478](https://github.com/eyaltoledano/claude-task-master/pull/1478) [`6ff330f`](https://github.com/eyaltoledano/claude-task-master/commit/6ff330f8c2bc6e534e0a883c770e8394d7ad5fa8) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Increase page size of brief selection (interactive cli setup)

## 0.37.0

### Minor Changes

- [#1452](https://github.com/eyaltoledano/claude-task-master/pull/1452) [`4046b3c`](https://github.com/eyaltoledano/claude-task-master/commit/4046b3ca4479adf0239679eb5ba18b7b4aec0749) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add Hamster integration for `parse-prd` command

  Your tasks are only as good as the context behind them. Now when you run `parse-prd`, you can choose to bring your PRD to Hamster instead of parsing locally.

  **New Workflow Choice**
  - **Parse locally**: PRD becomes a task list in a local JSON file - great for quick prototyping and vibing solo
  - **Bring it to Hamster**: PRD becomes a living brief connected to your team, codebase, and agents

  **Why Hamster?**
  - Tasks live in a central place with real-time sync across your team
  - Collaborate on your PRD/brief together, generate tasks on Hamster, bring them into Taskmaster
  - No API keys needed - Hamster handles all AI inference, just need a Hamster account

  **Hamster Integration**
  - OAuth login flow when choosing Hamster (same as export command)
  - Create brief directly from PRD content with auto-generated title/description
  - Progress bar showing task generation phases (analyzing → generating → processing)
  - Invite teammates during brief creation
  - Auto-set context to new brief when complete

  **Quality of Life**
  - Clickable brief URL and team invite URL in terminal
  - Shows task count as they're generated
  - Graceful fallback if generation takes longer than expected

- [#1452](https://github.com/eyaltoledano/claude-task-master/pull/1452) [`4046b3c`](https://github.com/eyaltoledano/claude-task-master/commit/4046b3ca4479adf0239679eb5ba18b7b4aec0749) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Redesign `tm init` with clearer workflow selection and reduced noise

  Choose how you want to plan: Solo with Taskmaster or Together with Hamster. The new init flow guides you through setup with context-appropriate options and cleaner output.

  **New Workflow Selection**
  - Clear framing: "You need a plan before you execute. How do you want to build it?"
  - **Solo (Taskmaster)**: Parse PRD → structured tasks → AI agent executes with control
  - **Together (Hamster)**: Team writes brief → Hamster refines → aligned execution with Taskmaster

  **Cleaner Experience**
  - Optional AI IDE rules setup (Y/n prompt instead of always showing)
  - 15+ log messages moved to debug level - much less noise
  - Skip Git prompts when using Hamster (not needed for cloud storage)
  - Skip AI model configuration for Hamster (uses Hamster's AI)

  **Hamster Integration**
  - OAuth login flow when choosing Hamster workflow
  - Context-aware guidance based on your workflow choice

  **Quality of Life**
  - Run `tm rules --setup` anytime if you declined during init
  - Use `--yes` flag for fully non-interactive setup
  - Use `--rules cursor,windsurf` to specify rules upfront

- [#1452](https://github.com/eyaltoledano/claude-task-master/pull/1452) [`4046b3c`](https://github.com/eyaltoledano/claude-task-master/commit/4046b3ca4479adf0239679eb5ba18b7b4aec0749) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Introduce `tm export` command - bring Task Master to your team

  Share your task plans with teammates by exporting local tasks to collaborative briefs on Hamster. Select which tags to export, invite team members, and start collaborating instantly.

  **New `tm export` Command**
  - Export your local tasks to shareable team briefs
  - Hamster will reverse engineer your PRD based on your tasks (reverse parse prd!)
  - Select multiple tags to export in one go, import all tasks across tags to Hamster
  - Hamster will generate brief titles and descriptions from your task content
  - Automatically sets your CLI context to the new brief
  - All AI calls handled by Hamster, zero API keys needed - just a Hamster account!

  **Team Collaboration**
  - Invite teammates during export with `-I, --invite` flag
  - Add up to 10 team members by email
  - See invitation status: sent, already a member, or error

  **Quality of Life Improvements**
  - New `tm login` / `tm logout` shortcuts
  - Display ID shortcuts: `tm show ham31` now works (normalizes to HAM-31)
  - Better task rendering with proper HTML/Markdown support

- [#1452](https://github.com/eyaltoledano/claude-task-master/pull/1452) [`4046b3c`](https://github.com/eyaltoledano/claude-task-master/commit/4046b3ca4479adf0239679eb5ba18b7b4aec0749) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add simpler positional syntax and Hamster-aware UI improvements
  - **Simpler command syntax**: Use positional arguments without flags
    - `tm update-task 1 Added implementation` (no quotes needed for multi-word prompts)
    - `tm status 1 done` (new alias for set-status) or `tm set-status 1,1.1,2 in-progress`
    - `tm list done` or `tm list in-progress` or `tm list all` (shortcut for --with-subtasks)
  - **Hamster-aware help**: Context-specific command list when connected to Hamster
    - Shows only relevant commands for Hamster workflow
    - Beautiful boxed section headers with improved spacing
    - Clear usage examples with new positional syntax
    - Better visual alignment and cleaner formatting
  - **Progress indicators**: Added loading spinner to `update-task` when connected to Hamster
    - Shows "Updating task X on Hamster..." during AI processing
    - Cleaner, more responsive UX for long-running operations
  - **Improved context display**: Show 'Brief: [name]' instead of 'tag: [name]' when connected to Hamster
  - **Cleaner Hamster updates**: Simplified update display (removed redundant Mode/Prompt info)
  - **Smart messaging**: "NO TASKS AVAILABLE" warning only shows when literally no tasks exist
    - Removed misleading messages when tasks are just completed/in-progress/blocked
    - Better UX for filtered task lists
  - **Updated help everywhere**: Regular help menu now shows new positional argument syntax
    - All suggested actions updated across commands
    - Consistent syntax in all UI components
  - **Auto-detection**: Automatically detects Hamster connection for better UX
  - **Backward compatible**: All old flag syntax still works (`--id`, `--status`, etc.)

### Patch Changes

- [#1452](https://github.com/eyaltoledano/claude-task-master/pull/1452) [`4046b3c`](https://github.com/eyaltoledano/claude-task-master/commit/4046b3ca4479adf0239679eb5ba18b7b4aec0749) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add Sentry integration for error tracking and AI telemetry monitoring
  - **Sentry Integration**: Added comprehensive error tracking and AI operation monitoring using Sentry with Vercel AI SDK integration
  - **AI Telemetry**: All AI operations (generateText, streamText, generateObject, streamObject) now automatically track spans, token usage, prompts, and responses
  - **MCP Server Instrumentation**: Wrapped FastMCP server with `Sentry.wrapMcpServerWithSentry()` to automatically capture spans for all MCP tool interactions
  - **Privacy Controls**: Added `anonymousTelemetry` config option (default: true) allowing local storage users to opt out of telemetry
  - **Complete Coverage**: Telemetry enabled for all AI commands including parse-prd, expand, update-task, analyze-complexity, and research
  - **Internal Telemetry**: Sentry DSN is hardcoded internally for Task Master's telemetry (not user-configurable)
  - **Dual Initialization**: Automatic Sentry initialization in both CLI (scripts/dev.js) and MCP Server (mcp-server/src/index.js) with full MCP instrumentation

- [#1463](https://github.com/eyaltoledano/claude-task-master/pull/1463) [`55595f6`](https://github.com/eyaltoledano/claude-task-master/commit/55595f680c8b52b5421d3e0c7640bf2050efe44f) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix package issue in earlier rc

## 0.36.0-rc.3

### Minor Changes

- [#1452](https://github.com/eyaltoledano/claude-task-master/pull/1452) [`4046b3c`](https://github.com/eyaltoledano/claude-task-master/commit/4046b3ca4479adf0239679eb5ba18b7b4aec0749) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add Hamster integration for `parse-prd` command

  Your tasks are only as good as the context behind them. Now when you run `parse-prd`, you can choose to bring your PRD to Hamster instead of parsing locally.

  **New Workflow Choice**
  - **Parse locally**: PRD becomes a task list in a local JSON file - great for quick prototyping and vibing solo
  - **Bring it to Hamster**: PRD becomes a living brief connected to your team, codebase, and agents

  **Why Hamster?**
  - Tasks live in a central place with real-time sync across your team
  - Collaborate on your PRD/brief together, generate tasks on Hamster, bring them into Taskmaster
  - No API keys needed - Hamster handles all AI inference, just need a Hamster account

  **Hamster Integration**
  - OAuth login flow when choosing Hamster (same as export command)
  - Create brief directly from PRD content with auto-generated title/description
  - Progress bar showing task generation phases (analyzing → generating → processing)
  - Invite teammates during brief creation
  - Auto-set context to new brief when complete

  **Quality of Life**
  - Clickable brief URL and team invite URL in terminal
  - Shows task count as they're generated
  - Graceful fallback if generation takes longer than expected

- [#1452](https://github.com/eyaltoledano/claude-task-master/pull/1452) [`4046b3c`](https://github.com/eyaltoledano/claude-task-master/commit/4046b3ca4479adf0239679eb5ba18b7b4aec0749) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Redesign `tm init` with clearer workflow selection and reduced noise

  Choose how you want to plan: Solo with Taskmaster or Together with Hamster. The new init flow guides you through setup with context-appropriate options and cleaner output.

  **New Workflow Selection**
  - Clear framing: "You need a plan before you execute. How do you want to build it?"
  - **Solo (Taskmaster)**: Parse PRD → structured tasks → AI agent executes with control
  - **Together (Hamster)**: Team writes brief → Hamster refines → aligned execution with Taskmaster

  **Cleaner Experience**
  - Optional AI IDE rules setup (Y/n prompt instead of always showing)
  - 15+ log messages moved to debug level - much less noise
  - Skip Git prompts when using Hamster (not needed for cloud storage)
  - Skip AI model configuration for Hamster (uses Hamster's AI)

  **Hamster Integration**
  - OAuth login flow when choosing Hamster workflow
  - Context-aware guidance based on your workflow choice

  **Quality of Life**
  - Run `tm rules --setup` anytime if you declined during init
  - Use `--yes` flag for fully non-interactive setup
  - Use `--rules cursor,windsurf` to specify rules upfront

- [#1452](https://github.com/eyaltoledano/claude-task-master/pull/1452) [`4046b3c`](https://github.com/eyaltoledano/claude-task-master/commit/4046b3ca4479adf0239679eb5ba18b7b4aec0749) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Introduce `tm export` command - bring Task Master to your team

  Share your task plans with teammates by exporting local tasks to collaborative briefs on Hamster. Select which tags to export, invite team members, and start collaborating instantly.

  **New `tm export` Command**
  - Export your local tasks to shareable team briefs
  - Hamster will reverse engineer your PRD based on your tasks (reverse parse prd!)
  - Select multiple tags to export in one go, import all tasks across tags to Hamster
  - Hamster will generate brief titles and descriptions from your task content
  - Automatically sets your CLI context to the new brief
  - All AI calls handled by Hamster, zero API keys needed - just a Hamster account!

  **Team Collaboration**
  - Invite teammates during export with `-I, --invite` flag
  - Add up to 10 team members by email
  - See invitation status: sent, already a member, or error

  **Quality of Life Improvements**
  - New `tm login` / `tm logout` shortcuts
  - Display ID shortcuts: `tm show ham31` now works (normalizes to HAM-31)
  - Better task rendering with proper HTML/Markdown support

- [#1452](https://github.com/eyaltoledano/claude-task-master/pull/1452) [`4046b3c`](https://github.com/eyaltoledano/claude-task-master/commit/4046b3ca4479adf0239679eb5ba18b7b4aec0749) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add simpler positional syntax and Hamster-aware UI improvements
  - **Simpler command syntax**: Use positional arguments without flags
    - `tm update-task 1 Added implementation` (no quotes needed for multi-word prompts)
    - `tm status 1 done` (new alias for set-status) or `tm set-status 1,1.1,2 in-progress`
    - `tm list done` or `tm list in-progress` or `tm list all` (shortcut for --with-subtasks)
  - **Hamster-aware help**: Context-specific command list when connected to Hamster
    - Shows only relevant commands for Hamster workflow
    - Beautiful boxed section headers with improved spacing
    - Clear usage examples with new positional syntax
    - Better visual alignment and cleaner formatting
  - **Progress indicators**: Added loading spinner to `update-task` when connected to Hamster
    - Shows "Updating task X on Hamster..." during AI processing
    - Cleaner, more responsive UX for long-running operations
  - **Improved context display**: Show 'Brief: [name]' instead of 'tag: [name]' when connected to Hamster
  - **Cleaner Hamster updates**: Simplified update display (removed redundant Mode/Prompt info)
  - **Smart messaging**: "NO TASKS AVAILABLE" warning only shows when literally no tasks exist
    - Removed misleading messages when tasks are just completed/in-progress/blocked
    - Better UX for filtered task lists
  - **Updated help everywhere**: Regular help menu now shows new positional argument syntax
    - All suggested actions updated across commands
    - Consistent syntax in all UI components
  - **Auto-detection**: Automatically detects Hamster connection for better UX
  - **Backward compatible**: All old flag syntax still works (`--id`, `--status`, etc.)

### Patch Changes

- [#1452](https://github.com/eyaltoledano/claude-task-master/pull/1452) [`4046b3c`](https://github.com/eyaltoledano/claude-task-master/commit/4046b3ca4479adf0239679eb5ba18b7b4aec0749) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add Sentry integration for error tracking and AI telemetry monitoring
  - **Sentry Integration**: Added comprehensive error tracking and AI operation monitoring using Sentry with Vercel AI SDK integration
  - **AI Telemetry**: All AI operations (generateText, streamText, generateObject, streamObject) now automatically track spans, token usage, prompts, and responses
  - **MCP Server Instrumentation**: Wrapped FastMCP server with `Sentry.wrapMcpServerWithSentry()` to automatically capture spans for all MCP tool interactions
  - **Privacy Controls**: Added `anonymousTelemetry` config option (default: true) allowing local storage users to opt out of telemetry
  - **Complete Coverage**: Telemetry enabled for all AI commands including parse-prd, expand, update-task, analyze-complexity, and research
  - **Internal Telemetry**: Sentry DSN is hardcoded internally for Task Master's telemetry (not user-configurable)
  - **Dual Initialization**: Automatic Sentry initialization in both CLI (scripts/dev.js) and MCP Server (mcp-server/src/index.js) with full MCP instrumentation

- [#1463](https://github.com/eyaltoledano/claude-task-master/pull/1463) [`55595f6`](https://github.com/eyaltoledano/claude-task-master/commit/55595f680c8b52b5