When a user explicitly passes a model override (e.g., model: "sonnet"),
the code was only fetching credentials without resolving the model alias.
This caused API calls to fail because the Claude API expects full model
strings like "claude-sonnet-4-20250514", not aliases like "sonnet".
The other code branches (settings-based and fallback) correctly called
resolvePhaseModel(), but the explicit override branch was missing this.
This fix adds the resolvePhaseModel() call to ensure model aliases are
properly resolved before being sent to the API.
* feat: refactor Claude API Profiles to Claude Compatible Providers
- Rename ClaudeApiProfile to ClaudeCompatibleProvider with models[] array
- Each ProviderModel has mapsToClaudeModel field for Claude tier mapping
- Add providerType field for provider-specific icons (glm, minimax, openrouter)
- Add thinking level support for provider models in phase selectors
- Show all mapped Claude models per provider model (e.g., "Maps to Haiku, Sonnet, Opus")
- Add Bulk Replace feature to switch all phases to a provider at once
- Hide Bulk Replace button when no providers are enabled
- Fix project-level phaseModelOverrides not persisting after refresh
- Fix deleting last provider not persisting (remove empty array guard)
- Add getProviderByModelId() helper for all SDK routes
- Update all routes to pass provider config for provider models
- Update terminology from "profiles" to "providers" throughout UI
- Update documentation to reflect new provider system
* fix: atomic writer race condition and bulk replace reset to defaults
1. AtomicWriter Race Condition Fix (libs/utils/src/atomic-writer.ts):
- Changed temp file naming from Date.now() to Date.now() + random hex
- Uses crypto.randomBytes(4).toString('hex') for uniqueness
- Prevents ENOENT errors when multiple concurrent writes happen
within the same millisecond
2. Bulk Replace "Anthropic Direct" Reset (both dialogs):
- When selecting "Anthropic Direct", now uses DEFAULT_PHASE_MODELS
- Properly resets thinking levels and other settings to defaults
- Added thinkingLevel to the change detection comparison
- Affects both global and project-level bulk replace dialogs
* fix: update tests for new model resolver passthrough behavior
1. model-resolver tests:
- Unknown models now pass through unchanged (provider model support)
- Removed expectations for warnings on unknown models
- Updated case sensitivity and edge case tests accordingly
- Added tests for provider-like model names (GLM-4.7, MiniMax-M2.1)
2. atomic-writer tests:
- Updated regex to match new temp file format with random suffix
- Format changed from .tmp.{timestamp} to .tmp.{timestamp}.{hex}
* refactor: simplify getPhaseModelWithOverrides calls per code review
Address code review feedback on PR #629:
- Make settingsService parameter optional in getPhaseModelWithOverrides
- Function now handles undefined settingsService gracefully by returning defaults
- Remove redundant ternary checks in 4 call sites:
- apps/server/src/routes/context/routes/describe-file.ts
- apps/server/src/routes/context/routes/describe-image.ts
- apps/server/src/routes/worktree/routes/generate-commit-message.ts
- apps/server/src/services/auto-mode-service.ts
- Remove unused DEFAULT_PHASE_MODELS imports where applicable
* test: fix server tests for provider model passthrough behavior
- Update model-resolver.test.ts to expect unknown models to pass through
unchanged (supports ClaudeCompatibleProvider models like GLM-4.7)
- Remove warning expectations for unknown models (valid for providers)
- Add missing getCredentials and getGlobalSettings mocks to
ideation-service.test.ts for settingsService
* fix: address code review feedback for model providers
- Honor thinkingLevel in generate-commit-message.ts
- Pass claudeCompatibleProvider in ideation-service.ts for provider models
- Resolve provider configuration for model overrides in generate-suggestions.ts
- Update "Active Profile" to "Active Provider" label in project-claude-section
- Use substring instead of deprecated substr in api-profiles-section
- Preserve provider enabled state when editing in api-profiles-section
* fix: address CodeRabbit review issues for Claude Compatible Providers
- Fix TypeScript TS2339 error in generate-suggestions.ts where
settingsService was narrowed to 'never' type in else branch
- Use DEFAULT_PHASE_MODELS per-phase defaults instead of hardcoded
'sonnet' in settings-helpers.ts
- Remove duplicate eventHooks key in use-settings-migration.ts
- Add claudeCompatibleProviders to localStorage migration parsing
and merging functions
- Handle canonical claude-* model IDs (claude-haiku, claude-sonnet,
claude-opus) in project-models-section display names
This resolves the CI build failures and addresses code review feedback.
* fix: skip broken list-view-priority E2E test and add Priority column label
- Skip list-view-priority.spec.ts with TODO explaining the infrastructure
issue: setupRealProject only sets localStorage but server settings
take precedence with localStorageMigrated: true
- Add 'Priority' label to list-header.tsx for the priority column
(was empty string, now shows proper header text)
- Increase column width to accommodate the label
The E2E test issue is that tests create features in a temp directory,
but the server loads from the E2E Test Project fixture path set in
setup-e2e-fixtures.mjs. Needs infrastructure fix to properly switch
projects or create features through UI instead of on disk.
* feat: add Claude API provider profiles for alternative endpoints
Add support for managing multiple Claude-compatible API endpoints
(z.AI GLM, AWS Bedrock, etc.) through provider profiles in settings.
Features:
- New ClaudeApiProfile type with base URL, API key, model mappings
- Pre-configured z.AI GLM template with correct model names
- Profile selector in Settings > Claude > API Profiles
- Clean switching between profiles and direct Anthropic API
- Immediate persistence to prevent data loss on restart
Profile support added to all execution paths:
- Agent service (chat)
- Ideation service
- Auto-mode service (feature agents, enhancements)
- Simple query service (title generation, descriptions, etc.)
- Backlog planning, commit messages, spec generation
- GitHub issue validation, suggestions
Environment variables set when profile is active:
- ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN/API_KEY
- ANTHROPIC_DEFAULT_HAIKU/SONNET/OPUS_MODEL
- API_TIMEOUT_MS, CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC
Ensure running details are cleared when generation completes or fails, preventing state leaks.
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
- 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.
* 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>
- Introduced a new function, buildThinkingOptions, to handle the conversion of ThinkingLevel to maxThinkingTokens for the Claude SDK.
- Updated existing SDK option creation functions to incorporate thinking options, ensuring that maxThinkingTokens are included based on the specified thinking level.
- Enhanced the settings service to support migration of phase models to include thinking levels, improving compatibility with new configurations.
- Added comprehensive tests for thinking level integration and migration logic, ensuring robust functionality across the application.
This update significantly improves the SDK's configurability and performance by allowing for more nuanced control over reasoning capabilities.
- Import isCursorModel to detect Cursor models
- For Cursor: embed systemPrompt in userPrompt with explicit instructions
- Add "DO NOT write any files" directive for Cursor models
- Prevents Cursor from writing plan to files instead of returning JSON
- Matches pattern used by github validation (validate-issue.ts)
Cursor doesn't support systemPrompt separation like Claude SDK,
so we need to combine prompts and add explicit instructions to
prevent it from using Write/Edit tools and creating files.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Change debug logs to info/warn so they're always visible
- Log when result message is received from Cursor
- Log lengths of both msg.result and accumulated responseText
- Log which source is being used (result vs accumulated)
- Log empty response error for better diagnostics
- Add response preview logging on parse failure
This will help diagnose why Cursor parsing is failing by showing:
1. Whether result messages are being received
2. What content lengths we're working with
3. Whether response text is empty or has content
4. What the actual response looks like when parsing fails
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Switch from extractJson to extractJsonWithArray for 'changes' field
- Validates that 'changes' is an array, not just that it exists
- Add debug logging for response length and preview on parse failure
- Add debug logging when receiving result from Cursor provider
- Matches pattern used by suggestions feature
- Helps diagnose parsing issues with better error context
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Add handler for type=result messages in stream processing
- Cursor provider sends final accumulated text in msg.result
- Backlog plan was only handling assistant messages
- Now matches pattern used by github validation and suggestions
- Fixes "cursor cli parsing failed" error
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Merges latest main branch changes including:
- MCP server support and configuration
- Pipeline configuration system
- Prompt customization settings
- GitHub issue comments in validation
- Auth middleware improvements
- Various UI/UX improvements
All Cursor CLI features preserved:
- Multi-provider support (Claude + Cursor)
- Model override capabilities
- Phase model configuration
- Provider tabs in settings
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update parseAndCreateFeatures and parsePlanResponse to use the shared
extractJson/extractJsonWithArray utilities instead of manual regex
parsing for more robust and consistent JSON extraction from AI responses.
- parse-and-create-features.ts: Use extractJsonWithArray for features
- generate-plan.ts: Use extractJson with requiredKey for backlog plans
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a readOnly option to ExecuteOptions that controls whether the
Cursor CLI runs with --force flag (allows edits) or without (suggest-only).
Read-only routes now pass readOnly: true:
- generate-spec.ts, generate-features-from-spec.ts (we write files ourselves)
- validate-issue.ts, generate-suggestions.ts (analysis only)
- describe-file.ts, describe-image.ts (description only)
- generate-plan.ts, enhance.ts (text generation only)
Routes that implement features (auto-mode-service, agent-service) keep
the default (readOnly: false) to allow file modifications.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Read model from settings.phaseModels.backlogPlanningModel instead of
hardcoded 'sonnet' fallback. Still supports per-call override via model
parameter. Falls back to DEFAULT_PHASE_MODELS if settings unavailable.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add comprehensive prompt customization system allowing users to customize
all AI prompts (Auto Mode, Agent Runner, Backlog Plan, Enhancement) through
the Settings UI.
## Features
### Core Customization System
- New TypeScript types for prompt customization with enabled flag
- CustomPrompt interface with value and enabled state
- Prompts preserved even when disabled (no data loss)
- Merged prompt system (custom overrides defaults when enabled)
- Persistent storage in ~/.automaker/settings.json
### Settings UI
- New "Prompt Customization" section in Settings
- 4 tabs: Auto Mode, Agent, Backlog Plan, Enhancement
- Toggle-based editing (read-only default → editable custom)
- Dynamic textarea height based on prompt length (120px-600px)
- Visual state indicators (Custom/Default labels)
### Warning System
- Critical prompt warnings for Backlog Plan (JSON format requirement)
- Field-level warnings when editing critical prompts
- Info banners for Auto Mode planning markers
- Color-coded warnings (blue=info, amber=critical)
### Backend Integration
- Auto Mode service loads prompts from settings
- Agent service loads prompts from settings
- Backlog Plan service loads prompts from settings
- Enhancement endpoint loads prompts from settings
- Settings sync includes promptCustomization field
### Files Changed
- libs/types/src/prompts.ts - Type definitions
- libs/prompts/src/defaults.ts - Default prompt values
- libs/prompts/src/merge.ts - Merge utilities
- apps/ui/src/components/views/settings-view/prompts/ - UI components
- apps/server/src/lib/settings-helpers.ts - getPromptCustomization()
- All service files updated to use customizable prompts
## Technical Details
Prompt storage format:
```json
{
"promptCustomization": {
"autoMode": {
"planningLite": {
"value": "Custom prompt text...",
"enabled": true
}
}
}
}
```
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
