- Add 4 launch options matching dev.mjs (Web, Electron, Docker Dev, Electron+Docker)
- Add arrow key navigation in menu with visual selection indicator
- Add cross-platform port conflict detection and resolution (Windows/Unix)
- Add Docker container detection with Stop/Restart/Attach/Cancel options
- Add Electron process detection when switching between modes
- Add centered, styled output for Docker build progress
- Add HUSKY=0 to docker-compose files to prevent permission errors
- Fix Windows/Git Bash compatibility (platform detection, netstat/taskkill)
- Fix bash arithmetic issue with set -e causing script to hang
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The 'local' keyword can only be used inside functions. Line 423 had
'local timeout_count=0' in the main script body which caused a bash error.
Removed the unused variable declaration.
Fixes: bash error 'local: can only be used in a function'
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Major improvements to start-automaker.sh launcher script:
**Architecture & Code Quality:**
- Organized into logical sections with clear separators (8 sections)
- Extracted all magic numbers into named constants at top
- Added comprehensive comments throughout
**Functionality:**
- Dynamic version extraction from package.json (no manual updates)
- Pre-flight checks: validates Node.js, npm, tput installed
- Platform detection: warns on Windows/unsupported systems
- Terminal size validation: checks min 70x20, displays warning if too small
- Input timeout: 30-second auto-timeout for hands-free operation
- History tracking: remembers last selected mode in ~/.automaker_launcher_history
**User Experience:**
- Added --help flag with comprehensive usage documentation
- Added --version flag showing version, Node.js, Bash info
- Added --check-deps flag to verify project dependencies
- Added --no-colors flag for terminals without color support
- Added --no-history flag to disable history tracking
- Enhanced cleanup function: restores cursor + echo, better signal handling
- Better error messages with actionable remediation steps
- Improved exit experience: "Goodbye! See you soon." message
**Robustness:**
- Real initialization checks (validates node_modules, build artifacts)
- Spinner uses frame counting instead of infinite loop (max 1.6s)
- Proper signal trap handling (EXIT, INT, TERM)
- Error recovery: respects --no-colors in pre-flight checks
**File Management:**
- Renamed from "start automaker.sh" to "start-automaker.sh" for consistency
- Made script more portable with SCRIPT_DIR detection
**Documentation:**
- Added section to README.md: "Interactive TUI Launcher"
- Documented all launch modes and options with examples
- Added feature list, history file location, usage tips
- Updated table of contents with TUI launcher section
Fixes: #511 (CI test failures resolved)
Improvements: Better UX for new users, production-ready error handling
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Add a beautiful terminal user interface (TUI) script that provides an
interactive menu for launching Automaker in different modes:
- [1] Web Browser mode (localhost:3007)
- [2] Desktop App (Electron)
- [3] Desktop + Debug (Electron with DevTools)
- [Q] Exit
Features:
- ASCII art logo with gradient colors
- Centered, responsive layout that adapts to terminal size
- Animated spinner during launch sequence
- Cross-shell compatibility (bash/zsh)
- Clean exit handling with cursor restoration
This provides a more user-friendly alternative to remembering
npm commands, especially for new users getting started with
the project.
- Introduced a new ImportExportDialog component for managing settings import and export via JSON.
- Integrated JsonSyntaxEditor for editing JSON settings with syntax highlighting.
- Updated SettingsView to include the import/export dialog and associated state management.
- Enhanced SettingsHeader with an import/export button for easy access.
These changes aim to improve user experience by allowing seamless transfer of settings between installations.
- Introduced server log level configuration and HTTP request logging settings, allowing users to control the verbosity of server logs and enable or disable request logging at runtime.
- Added an Event Hook Service to execute custom actions based on system events, supporting shell commands and HTTP webhooks.
- Enhanced the UI with new sections for managing server logging preferences and event hooks, including a dialog for creating and editing hooks.
- Updated global settings to include server log level and request logging options, ensuring persistence across sessions.
These changes aim to improve debugging capabilities and provide users with customizable event-driven actions within the application.
- Updated the default setting for autoLoadClaudeMd from false to true in the global settings. This change aims to enhance user experience by automatically loading ClaudeMd, streamlining the workflow for users.
- Added functionality to save, clear, and load backlog plans within the application.
- Introduced a new API endpoint for clearing saved backlog plans.
- Enhanced the backlog plan dialog to allow users to review and apply changes to their features.
- Integrated dependency management features in the UI, allowing users to select parent and child dependencies for features.
- Improved the graph view with options to manage plans and visualize dependencies effectively.
- Updated the sidebar and settings to include provider visibility toggles for better user control over model selection.
These changes aim to enhance the user experience by providing robust backlog management capabilities and improving the overall UI for feature planning.
- Added a helper function to map priority levels to badge variants in the IdeationDashboard.
- Improved UI elements in SuggestionCard for better spacing and visual hierarchy.
- Updated PromptCategoryGrid and PromptList components with enhanced hover effects and layout adjustments for a more responsive design.
- Refined button styles and interactions for better user experience across components.
These changes aim to improve the overall usability and aesthetics of the ideation view.
- Introduced a new button in the IdeationHeader for discarding all ideas when in dashboard mode.
- Implemented state management for discard readiness and count in IdeationView.
- Added confirmation dialog for discarding ideas in IdeationDashboard.
- Enhanced bulk action readiness checks to include discard operations.
This update improves user experience by allowing bulk discarding of ideas with confirmation, ensuring actions are intentional.
- Ensure the context menu closes consistently after the confirmation dialog, regardless of user action.
- Reset confirmation state upon dialog closure to prevent unintended interactions.
- Prevent context menu from closing when a confirmation dialog is open.
- Add success toast notification upon project removal.
- Refactor event handlers to account for dialog state, improving user experience.
- auto-mode-service-planning.test.ts: Add taskExecutionPrompts argument
to buildFeaturePrompt calls, update test for implementation instructions
- claude-usage-service.test.ts: Skip deprecated Mac tests (service now
uses PTY for all platforms), rename Windows tests to PTY tests, update
to use process.cwd() instead of home directory
- claude-provider.test.ts: Add missing model parameter to environment
variable passthrough tests
All tests now pass (1093 passed, 23 skipped).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Split prompt-customization-section.tsx into focused modules:
- types.ts (51 lines) - Type definitions
- tab-configs.ts (448 lines) - Configuration data for all tabs
- components.tsx (159 lines) - Reusable Banner, PromptField, PromptFieldList
- prompt-customization-section.tsx (176 lines) - Main component
Benefits:
- Main component reduced from ~810 to 176 lines
- Clear separation of concerns
- Easier to find and modify specific parts
- Configuration data isolated for easy updates
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace repetitive JSX with TAB_CONFIGS array defining all tabs and fields
- Create reusable Banner component for info/warning banners
- Create PromptFieldList component for rendering fields from config
- Support nested sections (like Auto Mode's Template Prompts section)
- Reduce file from ~950 lines to ~810 lines (-15% code)
Benefits:
- Adding new prompt tabs/fields is now declarative (just add to config)
- Consistent structure enforced by TypeScript interfaces
- Much easier to maintain and extend
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create PromptTabContent reusable component in prompt-customization-section.tsx
- Update all tabs (Agent, Commit Message, Title Generation, Ideation, App Spec,
Context Description, Suggestions, Task Execution) to use the new component
- Add {{count}} placeholder to DEFAULT_SUGGESTIONS_SYSTEM_PROMPT for dynamic
suggestion count
Addresses PR review comments from Gemini.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update auto-mode-service.ts to use centralized Task Execution prompts
from settings, making all 9 task execution prompts customizable via UI:
- buildFeaturePrompt: uses implementationInstructions and
playwrightVerificationInstructions from settings
- buildTaskPrompt: uses taskPromptTemplate with variable substitution
- buildPipelineStepPrompt: updated to pass prompts through
- executeFeatureWithContext: uses resumeFeatureTemplate
- resolvePlanApproval recovery: uses continuationAfterApprovalTemplate
- Multi-agent continuation: uses continuationAfterApprovalTemplate
- recordLearningsFromFeature: uses learningExtractionSystemPrompt
and learningExtractionUserPromptTemplate
All 12 prompt categories are now fully customizable from the UI.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix inline type imports in defaults.ts (move to top-level imports)
- Update ideation-service.ts to use centralized prompts from settings
- Update generate-title.ts to use centralized prompts
- Update validate-issue.ts to use centralized prompts
- Clean up validation-schema.ts (prompts already centralized)
- Minor server index cleanup
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add 4 new prompt type interfaces (AppSpecPrompts, ContextDescriptionPrompts,
SuggestionsPrompts, TaskExecutionPrompts) with resolved types
- Add default prompts for all new categories to @automaker/prompts/defaults.ts
- Add merge functions for new prompt categories in merge.ts
- Update settings-helpers.ts getPromptCustomization() to return all 12 categories
- Update server routes (generate-spec, generate-features-from-spec, describe-file,
describe-image, generate-suggestions) to use centralized prompts
- Add 4 new tabs in prompt customization UI (App Spec, Context, Suggestions, Tasks)
- Fix Ideation tab layout using grid-cols-4 for even distribution
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added functionality for bulk verifying features in the BoardView, allowing users to mark multiple features as verified at once.
- Introduced a selection target mechanism to differentiate between 'backlog' and 'waiting_approval' features during selection mode.
- Updated the KanbanCard and SelectionActionBar components to support the new selection target logic, improving user experience for bulk actions.
- Enhanced the UI to provide appropriate actions based on the current selection target, including verification options for waiting approval features.
- Add provider icon (Anthropic/OpenAI) that displays based on active tab
- Icon color reflects usage status (green/orange/red)
- Progress bar and stale indicator update dynamically when switching tabs
- Shows Claude metrics when Claude tab is active, Codex metrics when Codex tab is active
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
- Added support for real-time task status updates using WebSocket events, allowing the Kanban card to reflect current task progress accurately.
- Introduced a new state for fresh planSpec data fetched from the API to ensure the agent info panel displays up-to-date task information.
- Updated the effectiveTodos calculation to prioritize fresh planSpec data and incorporate real-time status, improving task display accuracy.
- Enhanced the logic to listen for relevant WebSocket events and update task statuses accordingly, ensuring synchronization with the agent output modal.
- Reduced the maximum height of the task progress panel from 300px to 200px for better UI consistency.
- Introduced a new `effectiveTodos` calculation in the agent info panel to correctly display tasks from `planSpec` when available, ensuring accurate task counts and statuses.
- Updated references to use `effectiveTodos` instead of the original `agentInfo.todos` for task display logic in the agent info panel.
- Adjusted the height of various modal components to align with the new task progress panel height.
The merge handler previously hardcoded branch names as `feature/${featureId}`
and worktree paths as `.worktrees/${featureId}`, which failed for auto-generated
branches (e.g., `feature/v0.11.0rc-1768413895104-31pa`) and custom worktrees.
Changes:
- Server handler now accepts branchName and worktreePath directly from the UI
- Added branch existence validation before attempting merge
- Updated merge dialog with 2-step confirmation (type "merge" to confirm)
- Removed feature branch naming restriction - any branch can now be merged
- Updated API types and client to pass correct parameters
Closes#408
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The branch listing logic now correctly shows remote branches (e.g., "origin/main") even if a local branch with the same base name exists, since users need remote branches as PR base targets. Also extracted duplicate state reset logic in create-pr-dialog into a reusable function.
- Updated the list-branches endpoint to accept an optional parameter for including remote branches.
- Implemented logic to fetch and deduplicate remote branches alongside local branches.
- Modified the CreatePRDialog component to utilize the updated API for branch selection, allowing users to select from both local and remote branches.
Address PR review comment - use process.cwd() for Windows too instead of
USERPROFILE/homedir fallback for consistency.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Use node-pty on all platforms instead of expect on macOS for more reliable PTY handling
- Use process.cwd() as working directory (project dir is likely already trusted)
- Add detection for new trust prompt text variants ("Ready to code here", "permission to work")
- Add specific error handling for trust prompt pending state
- Show helpful UI message when trust prompt needs manual approval
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
