- Restricted CORS to localhost origins to prevent remote code execution (RCE) attacks.
- Updated MCP server configuration handling to enforce security warnings when adding or importing servers.
- Introduced a SecurityWarningDialog to inform users about potential risks associated with server commands and configurations.
- Ensured that only serverId is accepted for testing server connections, preventing arbitrary command execution.
These changes improve the overall security posture of the MCP server management and usage.
Security improvements:
- Mask sensitive values in URLs (api_key, token, auth, secret, etc.)
- Prevents accidental API key leaks when sharing screen or screenshots
Performance guidance:
- Show warning banner when total MCP tools exceed 80
- Warns users that high tool count may degrade AI model performance
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Only auto-expand servers when user manually clicks Test button.
Auto-test on mount now keeps servers collapsed to avoid clutter
when there are many MCP servers configured.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
CodeRabbit identified dead code - the else blocks were unreachable
since validation ensures serverId or serverConfig is truthy.
Simplified to ternary expression.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Introduced JSON editing for individual and global MCP server configurations.
- Added functionality to open JSON edit dialogs for specific servers and all servers collectively.
- Implemented validation for JSON input to ensure correct server configuration.
- Enhanced server testing logic to allow silent testing without toast notifications.
- Updated UI to include buttons for editing JSON configurations and improved user experience.
This update streamlines server management and configuration, allowing for more flexible and user-friendly interactions.
- Add MCPTestService for testing MCP server connections
- Support stdio, SSE, and HTTP transport types
- Implement workaround for SSE headers bug (SDK Issue #436)
- Create API routes for /api/mcp/test and /api/mcp/tools
- Add API client methods for MCP operations
- Create MCPToolsList component with collapsible schema display
- Add Test button to MCP servers section with status indicators
- Add Headers field for HTTP/SSE servers
- Add Environment Variables field for stdio servers
- Fix text overflow in tools list display
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Introduced comprehensive unit tests for the pipeline routes, covering handlers for getting, saving, adding, updating, deleting, and reordering steps.
- Added tests for the pipeline service, ensuring correct behavior for methods like getting and saving pipeline configurations, adding, updating, and deleting steps, as well as reordering them.
- Implemented error handling tests to verify graceful degradation in case of missing parameters or service failures.
- Enhanced test coverage for the `getNextStatus` and `getStep` methods to ensure accurate status transitions and step retrieval.
These tests improve the reliability of the pipeline feature by ensuring that all critical functionalities are validated against expected behaviors.
- 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 tests for getMCPServersFromSettings()
- Add tests for getMCPPermissionSettings()
- Cover all server types (stdio, sse, http)
- Test error handling and edge cases
- Increases branch coverage from 54.91% to 56.59%
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
- Removed the delay mechanism for starting newly created features, simplifying the process.
- Updated the logic to capture existing feature IDs before adding a new feature, allowing for immediate identification of the newly created feature.
- Enhanced error handling to notify users if the feature could not be started automatically.
Update waitForContextFile, selectContextFile, and waitForFileContentToLoad
helpers to use Playwright's expect().toPass() with retry intervals, handling
race conditions between API calls completing and UI re-rendering. Also add
waitForNetworkIdle after dialog closes in context-file-management test.
Removed all debug console.log statements from agent-service.ts to avoid
polluting production logs. This addresses code review feedback from
gemini-code-assist.
Removed debug logs for:
- sendMessage() entry and session state
- Event emissions (started, message, stream, complete)
- Provider execution
- SDK session ID capture
- Tool use detection
- Queue processing
- emitAgentEvent() calls
Kept console.error logs for actual errors (session not found, execution
errors, etc.) as they are useful for troubleshooting.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Updated tests to reflect changes made to sandbox mode implementation:
1. Changed permissionMode expectation from 'acceptEdits' to 'default'
- ClaudeProvider now uses 'default' permission mode
2. Renamed test "should enable sandbox by default" to "should pass sandbox configuration when provided"
- Sandbox is no longer enabled by default in the provider
- Provider now forwards sandbox config only when explicitly provided via ExecuteOptions
3. Updated error handling test expectations
- Now expects two console.error calls with new format
- First call: '[ClaudeProvider] ERROR: executeQuery() error during execution:'
- Second call: '[ClaudeProvider] ERROR stack:' with stack trace
All 32 tests in claude-provider.test.ts now pass.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add comprehensive test coverage for sandbox mode configuration:
- Added tests for enableSandboxMode=false for both createChatOptions and createAutoModeOptions
- Added tests for enableSandboxMode not provided for both functions
- Updated existing tests to pass enableSandboxMode=true where sandbox assertions exist
This addresses the broken test assertions identified by coderabbit-ai review.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
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>
The default value should be 'true' to match the defaults in
libs/types/src/settings.ts and apps/ui/src/store/app-store.ts.
🤖 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>
- Replaced theme-specific scrollbar styles with a universal approach using CSS variables for better maintainability.
- Moved theme-specific scrollbar overrides from `global.css` to their respective theme files (`retro.css`, `red.css`)
- Enhanced the configureThrottling function to prevent changes to maxConcurrency while operations are in flight.
- Added comprehensive unit tests for secure-fs throttling and retry logic, ensuring correct behavior and configuration.
- Removed outdated secure-fs test file and replaced it with a new, updated version to improve test coverage.
- Adjusted the test to reflect the addition of queue state file reading, increasing the expected number of file read calls from 2 to 3.
- Updated comments for clarity regarding the file reading process in the agent-service tests.
- Added concurrency limiting using p-limit to prevent ENFILE/EMFILE errors.
- Introduced retry logic with exponential backoff for transient file descriptor errors.
- Enhanced secure-fs with new functions for configuring throttling and monitoring active/pending operations.
- Added unit tests for throttling and retry logic to ensure reliability.
- Introduced useOSDetection hook to determine the user's operating system.
- Updated FileBrowserDialog to utilize the OS detection for displaying the correct keyboard shortcut (⌘ or Ctrl) based on the detected OS.
- Replaced inline entry mapping with a memoized entryItems component for improved performance.
- Clarified keydown event handling comments to enhance understanding of ESC key behavior in relation to modal interactions.
- Updated keydown event logic to prevent search activation when input fields or contenteditable elements are focused.
- Enhanced ESC key handling to ensure parent modal does not close when search is open.
- Adjusted dependencies in useEffect to include entries length for better state management.
