- Introduced a new pipeline service to manage custom workflow steps that execute after a feature is marked "In Progress".
- Added API endpoints for configuring, saving, adding, updating, deleting, and reordering pipeline steps.
- Enhanced the UI to support pipeline settings, including a dialog for managing steps and integration with the Kanban board.
- Updated the application state management to handle pipeline configurations per project.
- Implemented dynamic column generation in the Kanban board to display pipeline steps between "In Progress" and "Waiting Approval".
- Added documentation for the new pipeline feature, including usage instructions and configuration details.
This feature allows for a more structured workflow, enabling automated processes such as code reviews and testing after feature implementation.
Add Model Context Protocol (MCP) server integration to extend AI agent
capabilities with external tools. This allows users to configure MCP
servers (stdio, SSE, HTTP) in global settings and have agents use them.
Note: MCP servers are currently configured globally. Per-project MCP
server configuration is planned for a future update.
Features:
- New MCP Servers settings section with full CRUD operations
- Import/Export JSON configs (Claude Code format compatible)
- Configurable permission settings:
- Auto-approve MCP tools (bypass permission prompts)
- Unrestricted tools (allow all tools when MCP enabled)
- Refresh button to reload from settings file
Implementation:
- Added MCPServerConfig and MCPToolInfo types
- Added store actions for MCP server management
- Updated claude-provider to use configurable MCP permissions
- Updated sdk-options factory functions for MCP support
- Added settings helpers for loading MCP configs
The sandbox configuration was set in createChatOptions() and
createAutoModeOptions(), but was never passed to the ClaudeProvider.
This caused the sandbox to never actually be enabled.
Changes:
- Add sandbox field to ExecuteOptions interface
- Pass sandbox config from AgentService to provider
- Pass sandbox config from AutoModeService to provider
- Forward sandbox config in ClaudeProvider to SDK options
Now the sandbox configuration from settings is properly used.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add a global setting to enable/disable sandbox mode for Claude Agent SDK.
This allows users to control sandbox behavior based on their authentication
setup and system compatibility.
Changes:
- Add enableSandboxMode to GlobalSettings (default: true)
- Add sandbox mode checkbox in Claude settings UI
- Wire up setting through app store and settings service
- Update createChatOptions and createAutoModeOptions to use setting
- Add getEnableSandboxModeSetting helper function
- Remove hardcoded sandbox configuration from ClaudeProvider
- Add detailed logging throughout agent execution flow
The sandbox mode requires API key or OAuth token authentication. Users
experiencing issues with CLI-only auth can disable it in settings.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Introduced a new utility function to filter out CLAUDE.md from context files when autoLoadClaudeMd is enabled, enhancing clarity and preventing duplication.
- Updated AgentService and AutoModeService to utilize the new filtering function, streamlining context file management.
- Improved documentation for the new utility, detailing its purpose and usage in context file handling.
- Updated both services to conditionally load context files while excluding CLAUDE.md when autoLoadClaudeMd is enabled, preventing duplication.
- Improved the structure and clarity of the context files prompt, emphasizing the importance of following project-specific rules and conventions.
- Ensured consistent handling of context file loading across different methods in both services.
- Updated both services to conditionally load CLAUDE.md based on the autoLoadClaudeMd setting, preventing duplication.
- Improved clarity in comments regarding the loading process of context files.
- Ensured consistent retrieval of the autoLoadClaudeMd setting across different methods.
- Removed the private method for getting the autoLoadClaudeMd setting from AgentService and AutoModeService.
- Updated both services to utilize the new settings helper for retrieving the autoLoadClaudeMd setting, improving code reusability and clarity.
- Adjusted error handling in the settings helper to throw errors instead of returning false when the settings service is unavailable.
- Updated API routes to accept an optional settings service for loading the autoLoadClaudeMd setting.
- Introduced a new settings helper utility for retrieving project-specific settings.
- Enhanced feature generation and spec generation processes to utilize the autoLoadClaudeMd setting.
- Refactored relevant route handlers to support the new settings integration across various endpoints.
- Introduced a new setting to enable automatic loading of CLAUDE.md files from project-specific directories.
- Updated relevant services and components to support the new setting, including the AgentService and AutoModeService.
- Added UI controls for managing the auto-load setting in the settings view.
- Enhanced SDK options to incorporate settingSources for CLAUDE.md loading.
- Updated global and project settings interfaces to include autoLoadClaudeMd property.
- Introduced a new utility function `loadContextFiles` to load project-specific context files from the `.automaker/context/` directory, enhancing agent prompts with project rules and guidelines.
- Updated `AgentService` and `AutoModeService` to utilize the new context loading functionality, combining context prompts with existing system prompts for improved agent performance.
- Added comprehensive documentation on the context files system, including usage examples and metadata structure, to facilitate better understanding and implementation.
- Removed redundant context loading logic from `AutoModeService`, streamlining the codebase.
These changes aim to improve the agent's contextual awareness and adherence to project-specific conventions.
This commit updates various modules to utilize the secure file system operations from the secureFs module instead of the native fs module. Key changes include:
- Replaced fs imports with secureFs in multiple route handlers and services to enhance security and consistency in file operations.
- Added centralized validation for working directories in the sdk-options module to ensure all AI model invocations are secure.
These changes aim to improve the security and maintainability of file handling across the application.
This commit introduces several improvements to the security and file handling mechanisms across the application. Key changes include:
- Updated the Dockerfile to pin the GitHub CLI version for reproducible builds.
- Refactored the secure file system operations to ensure consistent path validation and type handling.
- Removed legacy path management functions and streamlined the allowed paths logic in the security module.
- Enhanced route handlers to validate path parameters against the ALLOWED_ROOT_DIRECTORY, improving security against unauthorized access.
- Updated the settings service to focus solely on the Anthropic API key, removing references to Google and OpenAI keys.
These changes aim to enhance security, maintainability, and clarity in the codebase.
Tests: All unit tests passing.
This commit replaces direct file system operations with a secure file system adapter to enhance security by enforcing path validation. The changes include:
- Replaced `fs` imports with `secureFs` in various services and utilities.
- Updated file operations in `agent-service`, `auto-mode-service`, `feature-loader`, and `settings-service` to use the secure file system methods.
- Ensured that all file I/O operations are validated against the ALLOWED_ROOT_DIRECTORY.
This refactor aims to prevent unauthorized file access and improve overall security posture.
Tests: All unit tests passing.
🤖 Generated with Claude Code
Removed all references to OPENAI_API_KEY and GOOGLE_API_KEY since only
Claude (Anthropic) provider is implemented. These were placeholder references
for future providers that don't exist yet.
Changes:
- Removed OPENAI_API_KEY and GOOGLE_API_KEY from docker-compose.yml
- Removed from .env and .env.example files
- Updated setup/routes/store-api-key.ts to only support anthropic
- Updated setup/routes/delete-api-key.ts to only support anthropic
- Updated setup/routes/api-keys.ts to only return anthropic key status
- Updated models/routes/providers.ts to only list anthropic provider
- Updated auto-mode-service.ts error message to only reference ANTHROPIC_API_KEY
Backend test results: 653/653 passing ✅🤖 Generated with Claude Code
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
This commit consolidates directory security from two environment variables
(WORKSPACE_DIR, ALLOWED_PROJECT_DIRS) into a single ALLOWED_ROOT_DIRECTORY variable
while maintaining backward compatibility.
Changes:
- Re-enabled path validation in security.ts (was previously disabled)
- Implemented isPathAllowed() to check ALLOWED_ROOT_DIRECTORY with DATA_DIR exception
- Added backward compatibility for legacy ALLOWED_PROJECT_DIRS and WORKSPACE_DIR
- Implemented path traversal protection via isPathWithinDirectory() helper
- Added PathNotAllowedError custom exception for security violations
- Updated all FS route endpoints to validate paths and return 403 on violation
- Updated template clone endpoint to validate project paths
- Updated workspace config endpoints to use ALLOWED_ROOT_DIRECTORY
- Fixed stat() response property access bug in project-init.ts
- Updated security tests to expect actual validation behavior
Security improvements:
- Path validation now enforced at all layers (routes, project init, agent services)
- appData directory (DATA_DIR) always allowed for settings/credentials
- Backward compatible with existing ALLOWED_PROJECT_DIRS/WORKSPACE_DIR configurations
- Protection against path traversal attacks
Backend test results: 654/654 passing ✅🤖 Generated with Claude Code
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
- Updated 150+ files to import from @automaker/* packages
- Server imports now use @automaker/utils, @automaker/platform, @automaker/types, @automaker/model-resolver, @automaker/dependency-resolver, @automaker/git-utils
- UI imports now use @automaker/dependency-resolver and @automaker/types
- Deleted duplicate dependency-resolver files (222 lines eliminated)
- Updated dependency-resolver to use ES modules for Vite compatibility
- Added type annotation fix in auto-mode-service.ts
- Updated feature-loader to re-export Feature type from @automaker/types
- Both server and UI builds successfully verified
Phase 1 of server refactoring complete.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Resolved conflict in apps/ui/tests/worktree-integration.spec.ts:
- Kept assertion verifying worktreePath is undefined (consistent with pattern)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Updated branchName assignment to use nullish coalescing, ensuring that unassigned features are correctly set to null instead of an empty string. This change improves the handling of feature states during the update process.
- Consolidated imports in session-manager.tsx for cleaner code.
- Improved state initialization formatting for better readability.
- Updated board-view.tsx to enhance feature management, including the use of refs to track running tasks and prevent unnecessary effect re-runs.
- Added affectedFeatureCount prop to DeleteWorktreeDialog for better user feedback on feature assignments.
- Refactored useBoardActions to ensure worktrees are created when features are added or updated, improving overall workflow efficiency.
Context files from .automaker/context/ (CLAUDE.md, CODE_QUALITY.md, etc.)
are now passed as system prompt instead of prepending to user prompt.
This ensures the agent follows project-specific rules like package manager
preferences (pnpm vs npm) and coding conventions.
Changes:
- Add getContextDir() utility to automaker-paths.ts
- Add loadContextFiles() method to load .md/.txt files from context dir
- Pass context as systemPrompt in executeFeature() and followUpFeature()
- Add debug logging to confirm system prompt is provided
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When executeFeatureWithContext calls executeFeature with a continuation
prompt, skip the context existence check to avoid the loop:
executeFeature -> resumeFeature -> executeFeatureWithContext -> executeFeature
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When executeFeatureWithContext calls executeFeature with a continuation
prompt, skip the context existence check to avoid the loop:
executeFeature -> resumeFeature -> executeFeatureWithContext -> executeFeature
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Refactored DialogContent component to use forwardRef for better integration with refs.
- Enhanced auto mode service by introducing an auto loop for processing features concurrently.
- Updated error handling and feature management logic to streamline operations.
- Cleaned up code formatting and improved readability across various components and services.
- Added new RadioGroup and Switch components for better UI interaction.
- Introduced BranchSelector for improved branch selection in feature dialogs.
- Updated Autocomplete and BranchAutocomplete components to handle error states.
- Refactored feature management to archive verified features instead of deleting them.
- Enhanced worktree handling by removing worktreePath from features, relying on branchName instead.
- Improved auto mode functionality by integrating branch management and worktree updates.
- Cleaned up unused code and optimized existing logic for better performance.
- Introduced TaskProgressPanel to display task execution status in the AgentOutputModal.
- Enhanced useAutoMode hook to emit events for task start, completion, and phase completion.
- Updated AutoModeEvent type to include new task-related events.
- Implemented task parsing from generated specifications to track progress accurately.
- Improved auto mode service to handle task progress updates and emit relevant events.
- Introduced PlanApprovalDialog for reviewing and approving feature plans.
- Added state management for pending plan approvals and loading states.
- Enhanced BoardView to handle plan approval actions, including approve and reject functionalities.
- Updated KanbanCard and KanbanBoard components to include buttons for viewing and approving plans.
- Integrated plan approval logic into the auto mode service, allowing for user feedback and plan edits.
- Updated app state to manage default plan approval settings and integrate with existing feature workflows.
- Introduced a new TodoListRenderer component to display parsed todo items with status indicators and colors.
- Implemented a parseTodoContent function to extract todo items from TodoWrite JSON content.
- Enhanced LogEntryItem to conditionally render todo items when a TodoWrite entry is detected, improving log entry clarity and usability.
- Updated UI to visually differentiate between todo item statuses, enhancing user experience in task tracking.
- Introduced support for <summary> tags in log entries, allowing for better organization and parsing of summary content.
- Updated the detectEntryType function to recognize <summary> tags as a preferred format for summaries.
- Implemented summary accumulation logic to handle content between <summary> and </summary> tags.
- Modified the prompt in auto-mode service to instruct users to wrap their summaries in <summary> tags for consistency in log output.
- Added tool category icons and colors for log entries based on their metadata, improving visual differentiation.
- Implemented search functionality and filters for log entry types and tool categories, allowing users to customize their view.
- Enhanced log entry parsing to include tool-specific summaries and file paths, providing more context in the logs.
- Introduced a clear filters button to reset search and category filters, improving user experience.
- Updated the log viewer UI to accommodate new features, including a sticky header for better accessibility.
- Removed the saveOutput function from AgentOutputModal to streamline state management, ensuring local state updates without direct file writes.
- Introduced a debounced file writing mechanism in the auto-mode service to handle incremental updates to agent output, improving performance and reliability.
- Enhanced error handling during file writes to prevent execution interruptions and ensure all content is saved correctly.
- Added a new PlanningMode feature to manage default planning strategies for features.
- Updated the FeatureDefaultsSection to include a dropdown for selecting the default planning mode.
- Enhanced AddFeatureDialog and EditFeatureDialog to support planning mode selection and state management.
- Introduced PlanningModeSelector component for better user interaction with planning modes.
- Updated app state management to include default planning mode and related specifications.
- Refactored various UI components to ensure compatibility with new planning mode features.
- Modified the resumeFeature method across multiple files to accept an optional useWorktrees parameter, defaulting to false for improved control over worktree usage.
- Updated related hooks and service methods to ensure consistent handling of the new parameter.
- Enhanced server route logic to reflect the change, ensuring worktrees are only utilized when explicitly enabled.
- Introduced a new Autocomplete component for improved user experience in selecting options across various UI components.
- Refactored BranchAutocomplete and CategoryAutocomplete to utilize the new Autocomplete component, streamlining code and enhancing maintainability.
- Updated Playwright configuration to support mock agent functionality during CI/CD, allowing for simulated API interactions without real calls.
- Added comprehensive end-to-end tests for feature lifecycle, ensuring robust validation of the complete feature management process.
- Enhanced auto-mode service to support mock responses, improving testing efficiency and reliability.
- Updated the worktree creation and retrieval logic to resolve paths to absolute for improved cross-platform compatibility.
- Ensured that provided worktree paths are validated and resolved correctly, preventing issues on different operating systems.
- Refactored existing functions to consistently return absolute paths, enhancing reliability across Windows, macOS, and Linux environments.
