- Replaced dynamic import of the query function with a call to the new Simple Query Service for improved clarity and maintainability.
- Streamlined the response handling by directly utilizing the result from the simple query, enhancing code readability.
- Updated the prompt and options structure to align with the new service's requirements, ensuring consistent behavior in learning extraction.
- Modified tests to navigate directly to the dashboard instead of the welcome view, ensuring a smoother project selection process.
- Updated project name verification to check against the sidebar button instead of multiple elements.
- Added logic to expand the sidebar if collapsed, improving visibility for project names during tests.
- Adjusted test assertions to reflect changes in the UI structure, including the introduction of the dashboard view.
- Rename FAILURE_COOLDOWN to FAILURE_COOLDOWN_MS with explicit calculation
- Add SUCCESS_CACHE_MS constant to replace magic number 300000
- Use multiplication (30 * 1000, 5 * 60 * 1000) to make units explicit
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When Codex is not connected/authenticated, the /api/codex/models endpoint
returns 503. The fetchCodexModels function had no cooldown after failures,
causing infinite retries when navigating to the Settings screen.
Added codexModelsLastFailedAt state to track failed fetch attempts and
skip retries for 30 seconds after a failure. This prevents the infinite
loop while still allowing periodic retry attempts.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Introduced a new Simple Query Service to streamline basic AI queries, allowing for structured JSON outputs.
- Updated existing routes to utilize the new service, replacing direct SDK calls with a unified interface for querying.
- Enhanced provider handling in various routes, including generate-spec, generate-features-from-spec, and validate-issue, to support both Claude and Cursor models seamlessly.
- Added structured output support for improved response handling and error management across the application.
- Eliminated the getPriorityDisplay function and the PriorityBadge component from the ListRow implementation.
- Removed the pipelineConfig prop from ListRowProps interface.
- Cleaned up the code to streamline the ListRow component, focusing on essential features.
- Added validation to check if the specified worktree path exists before generating commit messages.
- Implemented a check to ensure the worktree path is a valid git repository by verifying the presence of the .git directory.
- Improved error handling by returning appropriate responses for invalid paths and non-git repositories.
- Added a new section in the UI for customizing commit message prompts.
- Integrated a system prompt for AI-generated commit messages, allowing users to define their own instructions.
- Updated the backend to merge custom prompts with default settings for commit message generation.
- Enhanced the commit message generation logic to utilize the effective system prompt based on user settings.
- Implemented a new endpoint to generate commit messages based on git diffs.
- Updated worktree routes to include the AI commit message generation functionality.
- Enhanced the UI to support automatic generation of commit messages when the commit dialog opens, based on user settings.
- Added settings for enabling/disabling AI-generated commit messages and configuring the model used for generation.
Integrate Claude Haiku to automatically generate commit messages when
committing worktree changes. Shows a sparkle animation while generating
and auto-populates the commit message field.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Sidebar now uses overlay pattern on mobile (fixed position when open)
- Added backdrop overlay that dismisses sidebar on tap
- Made collapse toggle button visible on all screen sizes
- Made project options menu visible on all screen sizes
Previously the sidebar was forced to collapsed width (w-16) on mobile
even when sidebarOpen was true, and the toggle/options buttons were
hidden with `hidden lg:flex`.
- Introduced a flag to track if a branch was successfully deleted, improving response clarity.
- Updated the response structure to include the new branchDeleted flag.
- Enhanced projectPath validation in init-script to ensure it is a non-empty string before processing.
Add enabledOpencodeModels and opencodeDefaultModel to the settings
migration to ensure they are properly persisted like Cursor settings.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace busy-wait loop in refreshModels with Promise-based approach
- Remove duplicate error logging in opencode-models.ts handlers
- Fix multi-slash parsing in provider-icon.tsx (only handle exactly one slash)
- Use dynamic icon resolution for selected OpenCode model in trigger
- Fix misleading comment about merge precedence (static takes precedence)
- Add enabledOpencodeModels and opencodeDefaultModel to settings sync
- Add clarifying comments about session-only dynamic model settings
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Convert execFileSync to async execFile in fetchModelsFromCli and
fetchAuthenticatedProviders to avoid blocking the event loop
- Remove unused opencode-dynamic-providers.tsx component
- Use regex for more robust model ID validation in parseModelsOutput
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add icon detection for dynamic OpenCode provider models (provider/model format)
- Support zai-coding-plan, github-copilot, google, xai, and other providers
- Detect model type from name (glm, claude, gpt, gemini, grok, etc.)
- Fix React.useMemo → useMemo to resolve "React is not defined" error
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update error event interface to handle nested error objects with
name/data/message structure from OpenCode CLI
- Extract meaningful error messages from provider errors in normalizeEvent
- Add error type handling in executeWithProvider to throw errors with
actual provider messages instead of returning empty response
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update isOpencodeModel() to detect dynamic models with provider/model format
(e.g., github-copilot/gpt-4o, google/gemini-2.5-pro, zai-coding-plan/glm-4.7)
- Update resolveModelString() to recognize and pass through OpenCode models
- Update enhance route to route OpenCode models to OpenCode provider
- Fix OpenCode CLI command format: use --format json (not stream-json)
- Remove unsupported -q and - flags from CLI arguments
- Update normalizeEvent() to handle actual OpenCode JSON event format
- Add dynamic model configuration UI with provider grouping
- Cache providers and models in app store for snappier navigation
- Show authenticated providers in OpenCode CLI status card
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added WorktreeSettingsDialog and PlanSettingsDialog components to manage worktree branch settings.
- Integrated new settings into BoardHeader for toggling worktree branch usage in feature creation.
- Updated AddFeatureDialog to utilize selected worktree branch for custom mode.
- Introduced new state management in app-store for handling worktree branch preferences.
These changes improve user control over feature creation workflows by allowing branch selection based on the current worktree context.
- Removed unused properties and state management from the EmptyStateCard component for cleaner code.
- Updated the EMPTY_STATE_CONFIGS to remove exampleCard entries, streamlining the empty state configuration.
- Enhanced the primary action handling in the EmptyStateCard for improved functionality.
- Updated sidebar component to include a mobile overlay backdrop when open.
- Adjusted visibility of logo and footer elements based on sidebar state.
- Improved layout and spacing for various components within the sidebar for better usability on different screen sizes.
- Refined styles for buttons and project selectors to enhance visual consistency and responsiveness.
- Updated apply handler to accept an optional branchName from the request body.
- Modified BoardView and BacklogPlanDialog components to pass currentBranch to the apply API.
- Enhanced ElectronAPI and HttpApiClient to include branchName in the apply method.
This change allows users to specify a branch when applying backlog plans, improving flexibility in feature management.
