- Introduced VITE_APP_MODE variable in multiple files to manage application modes.
- Updated dev.mjs and docker-compose.dev.yml to set different modes for development.
- Enhanced type definitions in vite-env.d.ts to include VITE_APP_MODE options.
- Modified AutomakerLogo component to display version suffix based on the current app mode.
- Improved OS detection logic in use-os-detection.ts to utilize Electron's platform information.
- Updated ElectronAPI interface to expose platform information.
These changes provide better control over application behavior based on the mode, enhancing the development experience.
* memory
* feat: add smart memory selection with task context
- Add taskContext parameter to loadContextFiles for intelligent file selection
- Memory files are scored based on tag matching with task keywords
- Category name matching (e.g., "terminals" matches terminals.md) with 4x weight
- Usage statistics influence scoring (files that helped before rank higher)
- Limit to top 5 files + always include gotchas.md
- Auto-mode passes feature title/description as context
- Chat sessions pass user message as context
This prevents loading 40+ memory files and killing context limits.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: enhance auto-mode service and context loader
- Improved context loading by adding task context for better memory selection.
- Updated JSON parsing logic to handle various formats and ensure robust error handling.
- Introduced file locking mechanisms to prevent race conditions during memory file updates.
- Enhanced metadata handling in memory files, including validation and sanitization.
- Refactored scoring logic for context files to improve selection accuracy based on task relevance.
These changes optimize memory file management and enhance the overall performance of the auto-mode service.
* refactor: enhance learning extraction and formatting in auto-mode service
- Improved the learning extraction process by refining the user prompt to focus on meaningful insights and structured JSON output.
- Updated the LearningEntry interface to include additional context fields for better documentation of decisions and patterns.
- Enhanced the formatLearning function to adopt an Architecture Decision Record (ADR) style, providing richer context for recorded learnings.
- Added detailed logging for better traceability during the learning extraction and appending processes.
These changes aim to improve the quality and clarity of learnings captured during the auto-mode service's operation.
* feat: integrate stripProviderPrefix utility for model ID handling
- Added stripProviderPrefix utility to various routes to ensure providers receive bare model IDs.
- Updated model references in executeQuery calls across multiple files, enhancing consistency in model ID handling.
- Introduced memoryExtractionModel in settings for improved learning extraction tasks.
These changes streamline the model ID processing and enhance the overall functionality of the provider interactions.
* feat: enhance error handling and server offline management in board actions
- Improved error handling in the handleRunFeature and handleStartImplementation functions to throw errors for better caller management.
- Integrated connection error detection and server offline handling, redirecting users to the login page when the server is unreachable.
- Updated follow-up feature logic to include rollback mechanisms and improved user feedback for error scenarios.
These changes enhance the robustness of the board actions by ensuring proper error management and user experience during server connectivity issues.
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: webdevcody <webdevcody@gmail.com>
- Fix disposed response object in Playwright route handler
- Add git user config to prevent 'empty ident' errors
- Increase server startup timeout and improve debugging
- Fix YAML indentation in E2E workflow
Resolves:
- 'Response has been disposed' error in open-existing-project test
- Git identity configuration issues in CI
- Backend server startup timing issues
- Combined CLI disconnection markers with OpenCode support
- Added OpenCode auth/deauth routes and API methods
- Resolved merge conflicts between feature branch and upstream v0.9.0rc
- Fix Claude, Codex, and Cursor auth handlers to check if CLI is already authenticated
- Use same detection logic as each provider's internal checkAuth/codexAuthIndicators()
- For Codex: Check for API keys and auth files before requiring manual login
- For Cursor: Check for env var and credentials files before requiring manual auth
- For Claude: Check for cached auth tokens, settings, and credentials files
- If CLI is already authenticated: Just reconnect by removing disconnected marker
- If CLI needs auth: Tell user to manually run login command
- This prevents timeout errors when login commands can't run in non-interactive mode
- Refactored ProvidersSetupStep component to improve the UI and streamline provider status checks for Claude, Cursor, Codex, and OpenCode.
- Introduced auto-verification for CLI authentication and improved error handling for authentication states.
- Added loading indicators for provider status checks and enhanced user feedback for installation and authentication processes.
- Updated setup store to manage verification states and ensure accurate representation of provider statuses.
These changes enhance the user experience by providing clearer feedback and a more efficient setup process for AI providers.
- Updated unit tests for OpenCode provider to include new authentication indicators.
- Refactored ProvidersSetupStep component by removing unnecessary UI elements for better clarity.
- Improved board background persistence tests by utilizing a setup function for initializing app state.
- Enhanced settings synchronization tests to ensure proper handling of login and app state.
These changes improve the testing framework and user interface for OpenCode integration, ensuring a smoother setup and authentication process.
- Added OpenCode authentication status check to the OpencodeProvider class.
- Introduced OpenCodeAuthStatus interface to manage authentication states.
- Updated detectInstallation method to include authentication status in the response.
- Created ProvidersSetupStep component to consolidate provider setup UI, including Claude, Cursor, Codex, and OpenCode.
- Refactored setup view to streamline navigation and improve user experience.
- Enhanced OpenCode CLI integration with updated installation paths and authentication checks.
This commit enhances the setup process by allowing users to configure and authenticate multiple AI providers, improving overall functionality and user experience.
- Added OpenCode model selection to AddFeatureDialog and EditFeatureDialog.
- Introduced ProfileTypeahead component for improved profile selection.
- Updated model constants to include OpenCode models and integrated them into the PhaseModelSelector.
- Enhanced planning mode options with new UI elements for OpenCode.
- Refactored existing components to streamline model handling and improve user experience.
This commit expands the functionality of the feature dialogs, allowing users to select and manage OpenCode models effectively.
- Implemented OpenCode CLI installation and authentication status check.
- Added new route for OpenCode status in setup routes.
- Updated HttpApiClient to include method for fetching OpenCode status.
- Enhanced system paths to include OpenCode's default installation directories.
This commit introduces functionality to check the installation and authentication status of the OpenCode CLI, improving integration with the overall system.
- Removed dependency on getElectronAPI and directly accessed window.electronAPI for retrieving the documents path in Electron mode.
- Added handling for web mode to return null when the documents path cannot be accessed.
- Included logging for the resolved documents path to aid in debugging.
Addresses PR feedback to reduce duplicated code in scanAgentsDirectory
by introducing an FsAdapter interface that abstracts the differences
between systemPaths (user directory) and secureFs (project directory).
Changes:
- Extract parseAgentContent helper for parsing agent file content
- Add FsAdapter interface with exists, readdir, and readFile methods
- Create createSystemPathAdapter for user-level paths
- Create createSecureFsAdapter for project-level paths
- Refactor scanAgentsDirectory to use a single loop with the adapter
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Resolved conflict in agent-service.ts by keeping both:
- agents parameter for custom subagents (from our branch)
- thinkingLevel and reasoningEffort parameters (from v0.9.0rc)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Moves prefix stripping from individual providers to AgentService/IdeationService
and adds validation to ensure providers receive bare model IDs. This prevents
bugs like the Codex CLI receiving "codex-gpt-5.1-codex-max" instead of the
expected "gpt-5.1-codex-max".
- Add validateBareModelId() helper with fail-fast validation
- Add originalModel field to ExecuteOptions for logging
- Update all providers to validate model has no prefix
- Centralize prefix stripping in service layer
- Remove redundant prefix stripping from individual providers
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
The verifySession() function was not including the X-API-Key header
when making requests to /api/settings/status, causing Electron mode
to fail authentication on app startup despite having a valid API key.
This resulted in users seeing "You've been logged out" screen
immediately after launching the Electron app.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add codex- prefix support in model resolver
- Fix modelSupportsThinking() to properly detect provider types
- Update CODEX_MODEL_PREFIXES to include codex- prefix
- Add 'codex-' prefix to all Codex CLI model IDs
- Add 'cursor-' prefix to Cursor CLI GPT model IDs
- Update provider-utils.ts to use prefix-based matching
- Update UI components to use prefixed model IDs
- Fix model routing to prevent Cursor picking up Codex models
- Update isCursorModel to exclude ALL Codex models from Cursor routing
- Check against CODEX_MODEL_CONFIG_MAP for comprehensive exclusion
- Includes: gpt-5.2-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5.2, gpt-5.1
- Also excludes overlapping models like gpt-5.2 and gpt-5.1 that exist in both maps
- Update test to expect CodexProvider for gpt-5.2 (correct behavior)
This ensures ALL Codex CLI models route to Codex provider, not Cursor.
Previously only gpt-5.1-codex-* and gpt-5.2-codex-* were excluded.
- Fix isCursorModel to exclude Codex-specific models (gpt-5.1-codex-*, gpt-5.2-codex-*)
- These models should route to Codex provider, not Cursor provider
- Add CODEX_YOLO_FLAG constant for --dangerously-bypass-approvals-and-sandbox
- Always use YOLO flag in codex-provider for full permissions
- Simplify codex CLI args to minimal set with YOLO flag
- Update tests to reflect new behavior with YOLO flag
This fixes the bug where selecting a Codex model (e.g., gpt-5.1-codex-max)
was incorrectly spawning cursor-agent instead of codex exec.
The root cause was:
1. Cursor provider had higher priority (10) than Codex (5)
2. isCursorModel() returned true for Codex models in CURSOR_MODEL_MAP
3. Models like gpt-5.1-codex-max routed to Cursor instead of Codex
The fix:
1. isCursorModel now excludes Codex-specific model IDs
2. Codex always uses --dangerously-bypass-approvals-and-sandbox flag
- Remove SANDBOX_OPTIONS and APPROVAL_OPTIONS from codex-settings.tsx
- Remove Select components for sandbox mode and approval policy
- Remove codexSandboxMode and codexApprovalPolicy from CodexSettingsProps interface
- Update codex-settings-tab.tsx to pass only simplified props
- Codex now always runs with full permissions (--dangerously-bypass-approvals-and-sandbox)
The UI no longer shows sandbox or approval settings since Codex always uses full permissions.
- Always use CODEX_YOLO_FLAG (--dangerously-bypass-approvals-and-sandbox) for Codex
- Remove all conditional logic - no sandbox/approval config, no config overrides
- Simplify codex-provider.ts to always run Codex in full-permissions mode
- Codex always gets: full access, no approvals, web search enabled, images enabled
- Update services to apply full-permission settings automatically for Codex models
- Remove sandbox and approval controls from UI settings page
- Update tests to reflect new behavior (some pre-existing tests disabled/updated)
Note: 3 pre-existing tests disabled/skipped due to old behavior expectations (require separate PR to update)
- Add ReasoningEffortSelector component for UI selection
- Integrate reasoning effort in feature creation/editing dialogs
- Add reasoning effort support to phase model selector
- Update agent service and board actions to handle reasoning effort
- Add reasoning effort fields to feature and settings types
- Update model selector and agent info panel with reasoning effort display
- Enhance agent context parser for reasoning effort processing
Reasoning effort allows fine-tuned control over Codex model reasoning
capabilities, providing options from 'none' to 'xhigh' for different
task complexity requirements.
- Fix Codex profiles showing as 'Claude Sonnet' in UI
- Add proper Codex model display in profile cards and selectors
- Add useEffect to sync profile form data when editing profiles
- Update provider badges to show 'Codex' with OpenAI icon
- Enhance profile selection validation across feature dialogs
- Add getCodexModelLabel support to display functions
The issue was that profile display functions only handled Claude and Cursor
providers, causing Codex profiles to fallback to 'sonnet' display.
- Try OpenAI API if API key is available
- Parse rate limit info from Codex CLI responses
- Extract plan type from Codex auth file
- Provide helpful configuration message when usage unavailable
- Deleted the worktree integration test file to streamline the test suite and remove obsolete tests. This change helps maintain focus on relevant test cases and improves overall test management.
- Updated the logic in the createListHandler to ensure that the branch name is correctly assigned, especially for the main worktree when it may be missing.
- Added checks to handle cases where the worktree directory might not exist, ensuring that removed worktrees are accurately tracked.
- Enhanced the final worktree entry handling to account for scenarios where the output does not end with a blank line, improving robustness.
- Introduced a new npm script "test:ui" for running UI tests in the apps/ui workspace.
- Removed unnecessary login screen handling from the worktree integration test to streamline the test flow.
- Added useRef to manage AbortController for retry requests in the LoginView component.
- Implemented logic to abort any ongoing retry requests before initiating a new server check, improving error handling and user experience during login attempts.
- Changed the E2E settings to enable the use of worktrees for better test isolation.
- Modified the test repository initialization to explicitly set the initial branch to 'main', ensuring compatibility across different git versions and avoiding CI environment discrepancies.
- Removed the redundant call to ignore empty array overwrite for 'enabledCodexModels' in the SettingsService.
- Reformatted the description of the 'Heavy Task' profile in the E2E fixture setup script for better readability.
- Updated Playwright configuration to explicitly unset ALLOWED_ROOT_DIRECTORY for unrestricted testing paths.
- Improved E2E fixture setup script to reset server settings to a known state, ensuring test isolation.
- Enhanced error handling in ContextView and WelcomeView components to reset state and provide user feedback on failures.
- Updated tests to ensure proper navigation and visibility checks during logout processes, improving reliability.
- Added safeguards to prevent overwriting non-empty arrays with empty arrays during global settings updates, specifically for the 'projects' field.
- Implemented logging for updates to assist in diagnosing accidental wipes of critical settings.
- Updated tests to verify that projects are preserved during logout transitions and that theme changes are ignored if a project wipe is attempted.
- Enhanced the settings synchronization logic to ensure safe handling during authentication state changes.
- Added a new utility for checking Codex CLI authentication status using the 'codex login status' command.
- Integrated the authentication check into the CodexProvider's installation detection and authentication methods.
- Updated Codex CLI status display in the UI to reflect authentication status and method.
- Enhanced error handling and logging for better debugging during authentication checks.
- Refactored related components to ensure consistent handling of authentication across the application.
- Updated the 'Add Context Image' test to simplify file verification by relying on UI visibility instead of disk checks.
- Enhanced the 'Feature Manual Review Flow' test with better project setup and API interception to ensure consistent test conditions.
- Improved the 'AI Profiles' test by replacing arbitrary timeouts with dynamic checks for profile count.
- Refined the 'Project Creation' and 'Open Existing Project' tests to ensure proper project visibility and settings management during tests.
- Added mechanisms to prevent settings hydration from restoring previous project states, ensuring tests run in isolation.
- Removed unused test image from fixtures to clean up the repository.
- Created combined UsagePopover component with tab switching between providers
- Added Codex usage API endpoint and service (returns not available message)
- Updated BoardHeader to show single usage button for both providers
- Enhanced type definitions for Codex usage with primary/secondary rate limits
- Wired up Codex usage API in HTTP client
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Added `skipSandboxWarning` option to project setup functions to streamline testing.
- Implemented logic to disable the splash screen during tests by setting `automaker-splash-shown` in sessionStorage.
- Introduced a new package.json for a test project and added a test image to the fixtures for improved testing capabilities.
- Added a new function `waitForSplashScreenToDisappear` to manage splash screen visibility, ensuring it does not block user interactions.
- Integrated splash screen checks in various navigation functions and interaction methods to enhance user experience by waiting for the splash screen to disappear before proceeding.
- Updated test setup to disable the splash screen during tests for consistent testing behavior.
- Added additional cloud storage path patterns for macOS and Linux to the checkSandboxCompatibility function, ensuring better compatibility with sandbox environments.
- Revised the login view to simplify the initial server/session check logic, removing unnecessary ref guard and improving responsiveness during component unmounting.
- Changed the event type from 'thread.completed' to 'turn.completed' in the CODEX_EVENT_TYPES constant and its usage within the CodexProvider class.
- This update aligns the event handling with the intended functionality, ensuring correct event processing.
