- 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>
Implement per-project theme override capability in the Discord-like layout:
- Add theme submenu to project context menu with live preview
- Reuse existing theme constants and useThemePreview hook from sidebar
- Extract reusable ThemeButton and ThemeColumn components (DRY principle)
- Replace magic z-index values with named constants
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Problem:
- OpenRouter dynamic models only appeared after visiting settings page
- PhaseModelSelector (used in Add/Edit Feature dialogs) only fetched Codex models
- dynamicOpencodeModels remained empty until OpencodeSettingsTab mounted
Solution:
- Add fetchOpencodeModels() action to app-store mirroring fetchCodexModels pattern
- Add state tracking: opencodeModelsLoading, opencodeModelsError, timestamps
- Call fetchOpencodeModels() in PhaseModelSelector useEffect on mount
- Use same caching strategy: 5min success cache, 30sec failure cooldown
Files changed:
- apps/ui/src/store/app-store.ts
- Add OpenCode model loading state properties
- Add fetchOpencodeModels action with error handling & caching
- apps/ui/src/components/views/settings-view/model-defaults/phase-model-selector.tsx
- Add opencodeModelsLoading, fetchOpencodeModels to store hook
- Add useEffect to fetch OpenCode models on mount
Result:
- OpenRouter models now appear in Add/Edit Feature dialogs immediately
- No need to visit settings page first
- Consistent with Codex model loading behavior
CLI-based providers (OpenCode, etc.) only accept a single prompt via
stdin/args and don't support separate system/user message channels like
Claude SDK. When systemPrompt is passed to these providers, it was
silently dropped, causing:
- BacklogPlan JSON parsing failures with OpenCode/GPT-5.2 (missing
"output ONLY JSON" formatting instruction)
- Loss of critical formatting/schema instructions for structured outputs
This fix adds embedSystemPromptIntoPrompt() method to CliProvider base
class that:
- Prepends systemPrompt to the user prompt before CLI execution
- Handles both string and array prompts (vision support)
- Handles both string systemPrompt and SystemPromptPreset objects
- Uses standard \n\n---\n\n separator (consistent with codebase)
- Sets systemPrompt to undefined to prevent double-injection
Benefits OpencodeProvider immediately (uses base executeQuery).
CursorProvider still uses manual workarounds (overrides executeQuery).
Fixes the immediate BacklogPlan + OpenCode bug while maintaining
backward compatibility with existing Cursor workarounds.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Updated create-pr.ts to improve commit error handling and logging.
- Enhanced project-switcher.tsx with new folder opening functionality and state management for project setup.
- Expanded icon-picker.tsx to include a comprehensive list of icons organized by category.
- Replaced dialog components with popover components for auto mode and plan settings, improving UI responsiveness.
- Refactored board-view components to streamline feature management and enhance user experience.
- Removed outdated dialog components and replaced them with popover alternatives for better accessibility.
These changes aim to improve the overall usability and functionality of the project management interface.
- Fix handleResolveConflicts to use origin/${worktree.branch} instead of
hardcoded origin/main for pull and resolve conflicts
- Add defaultBaseBranch prop to CreatePRDialog to use selected branch
- Fix branchCardCounts to use primary worktree branch as default
- Enable PR status and Address PR Comments for main branch tab
- Add automatic PR detection from GitHub for branches without stored metadata
This allows users working on release branches (like v0.11.0rc) to properly
pull from their branch's remote and see PR status for any branch.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Resolved conflict in worktree-panel.tsx by combining imports:
- DevServerLogsPanel from this branch
- WorktreeMobileDropdown, WorktreeActionsDropdown, BranchSwitchDropdown from v0.11.0rc
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add the ability to view dev server logs in a dedicated panel with:
- Real-time log streaming via WebSocket events
- ANSI color support using xterm.js
- Scrollback buffer (50KB) for log history on reconnect
- Output throttling to prevent UI flooding
- "View Logs" option in worktree dropdown menu
Server changes:
- Add scrollback buffer and event emission to DevServerService
- Add GET /api/worktree/dev-server-logs endpoint
- Add dev-server:started, dev-server:output, dev-server:stopped events
UI changes:
- Add reusable XtermLogViewer component
- Add DevServerLogsPanel dialog component
- Add useDevServerLogs hook for WebSocket subscription
Closes#462
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Modified command arguments in tests to include '--add-dir' for better context.
- Updated error messages for authentication and timeout scenarios to provide clearer guidance.
- Adjusted timer values in tests to align with implementation delays, ensuring accurate simulation of usage data retrieval.
- Reformatted the fullAccess and chat tool presets in sdk-options.ts for better readability.
- Simplified the return statement in icon-picker.tsx for cleaner code.
- Removed the board-background-persistence.spec.ts test file as it is no longer needed.
- Introduced custom icon functionality for projects, allowing users to upload and manage their own icons.
- Updated Project and ProjectRef types to include customIconPath.
- Enhanced the ProjectSwitcher component to display custom icons alongside preset icons.
- Added EditProjectDialog for inline editing of project details, including icon uploads.
- Improved AppearanceSection to support custom icon uploads and display.
- Updated sidebar and project switcher UI for better user experience and accessibility.
Implements #469
- Skip learning extraction when ANTHROPIC_API_KEY is not available
- Add reasoningEffort parameter to simpleQuery for Codex model configuration
- Add stdinData support to spawnProcess for CLI stdin input
- Update UI API types for model override with reasoning support
- Support Codex and OpenCode models in issue validation
- Add reasoningEffort parameter for Codex model configuration
- Update validation logic to use structured output for Claude/Codex
- Update UI hooks and types for multi-provider model selection
- Add OpenAI API key storage to store-api-key handler
- Include Google/OpenAI key status in credentials API responses
- Add unified ModelId type for Claude, Codex, Cursor, OpenCode, and dynamic providers
- Update PhaseModelEntry to support all provider model types
When an OpenAI API key is stored in settings or environment, use SDK mode
instead of CLI mode. This bypasses the MCP transport layer which was
failing with 'TokenRefreshFailed' errors due to OAuth token issues.
The SDK uses the API key directly via @openai/codex-sdk, avoiding the
OAuth token refresh mechanism that was causing mid-execution failures.
