- Replaced hardcoded model string with dynamic resolution for the analysis model, allowing for future flexibility.
- Enhanced error handling to provide specific authentication failure messages based on the model type, improving user feedback.
This change streamlines the model selection process and improves error clarity for users.
Fixed 4 TypeScript errors:
- fs.ts: Removed duplicate 'os' import (lines 8 and 10)
- spec-regeneration.ts: Removed dead code checking for impossible error type (2 occurrences)
The error type checks were comparing msg.type to "error", but the SDK type union
does not include "error" as a valid message type. Errors are properly handled
in the catch blocks, so these checks were unreachable dead code.
All TypeScript compilation now passes cleanly.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Created 5 new utility modules in apps/server/src/lib/ to eliminate ~320 lines of duplicated code:
- image-handler.ts: Centralized image processing (MIME types, base64, content blocks)
- prompt-builder.ts: Standardized prompt building with image attachments
- model-resolver.ts: Model alias resolution and provider routing
- conversation-utils.ts: Conversation history processing for providers
- error-handler.ts: Error classification and user-friendly messages
Updated services and providers to use shared utilities:
- agent-service.ts: -51 lines (removed duplicate image handling, model logic)
- auto-mode-service.ts: -75 lines (removed MODEL_MAP, duplicate utilities)
- claude-provider.ts: -10 lines (uses conversation-utils)
- codex-provider.ts: -5 lines (uses conversation-utils)
Added comprehensive documentation:
- docs/server/utilities.md: Complete reference for all 9 lib utilities
- docs/server/providers.md: Provider architecture guide with examples
Benefits:
- Single source of truth for critical business logic
- Improved maintainability and testability
- Consistent behavior across services and providers
- Better documentation for future development
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Implements a flexible provider pattern that supports both Claude Agent SDK
and OpenAI Codex CLI, enabling future expansion to other AI providers
(Cursor, OpenCode, etc.) with minimal changes.
## Architecture Changes
### New Provider System
- Created provider abstraction layer with BaseProvider interface
- Model-based routing: model prefix determines provider
- `gpt-*`, `o*` → CodexProvider (subprocess CLI)
- `claude-*`, `opus/sonnet/haiku` → ClaudeProvider (SDK)
- Providers implement common ExecuteOptions interface
### New Files Created
- `providers/types.ts` - Shared interfaces (ExecuteOptions, ProviderMessage, etc.)
- `providers/base-provider.ts` - Abstract base class
- `providers/claude-provider.ts` - Claude Agent SDK wrapper
- `providers/codex-provider.ts` - Codex CLI subprocess executor
- `providers/codex-cli-detector.ts` - Installation & auth detection
- `providers/codex-config-manager.ts` - TOML config management
- `providers/provider-factory.ts` - Model-based provider routing
- `lib/subprocess-manager.ts` - Reusable subprocess utilities
## Features Implemented
### Codex CLI Integration
- Spawns Codex CLI as subprocess with JSONL output
- Converts Codex events to Claude SDK-compatible format
- Supports both `codex login` and OPENAI_API_KEY auth methods
- Handles: reasoning, messages, commands, todos, file changes
- Extracts text from content blocks for non-vision CLI
### Conversation History
- Added conversationHistory support to ExecuteOptions
- ClaudeProvider: yields previous messages to SDK
- CodexProvider: prepends history as text context
- Follow-up prompts maintain full conversation context
### Image Upload Support
- Images embedded as base64 for vision models
- Image paths appended to prompt text for Read tool access
- Auto-mode: copies images to feature folder
- Follow-up: combines original + new images
- Updates feature.json with image metadata
### Session Model Persistence
- Added `model` field to Session and SessionMetadata
- Sessions remember model preference across interactions
- API endpoints accept model parameter
- Auto-mode respects feature's model setting
## Modified Files
### Services
- `agent-service.ts`:
- Added conversation history building
- Uses ProviderFactory instead of direct SDK calls
- Appends image paths to prompts
- Added model parameter and persistence
- `auto-mode-service.ts`:
- Removed OpenAI model block restriction
- Uses ProviderFactory for all models
- Added image support in buildFeaturePrompt
- Follow-up: loads context, copies images, updates feature.json
- Returns to waiting_approval after follow-up
### Routes
- `agent.ts`: Added model parameter to /send endpoint
- `sessions.ts`: Added model field to create/update
- `models.ts`: Added Codex models (gpt-5.2, gpt-5.1-codex*)
### Configuration
- `.env.example`: Added OPENAI_API_KEY and CODEX_CLI_PATH
- `.gitignore`: Added provider-specific ignores
## Bug Fixes
- Fixed image path resolution (relative → absolute)
- Fixed Codex empty prompt when images attached
- Fixed follow-up status management (in_progress → waiting_approval)
- Fixed follow-up images not appearing in prompt text
- Removed OpenAI model restrictions in auto-mode
## Testing Notes
- Codex CLI authentication verified with both methods
- Image uploads work for both Claude (vision) and Codex (Read tool)
- Follow-up prompts maintain full context
- Conversation history persists across turns
- Model switching works per-session
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Introduced a new DeleteSessionDialog component for confirming session deletions.
- Integrated the delete session dialog into the SessionManager component, allowing users to delete sessions with a confirmation prompt.
- Updated the UI to handle session deletion more intuitively, enhancing user experience.
- Refactored existing delete confirmation logic to utilize the new DeleteConfirmDialog component for consistency across the application.
- Introduced the GPT-5.2 model with advanced coding capabilities across various components.
- Added a new button in ProfilesView to refresh default profiles, enhancing user experience.
- Updated CodexSetupStep to clarify authentication requirements and added commands for verifying login status.
- Enhanced utility functions to recognize the new GPT-5.2 model in the application.
Resolved conflict in http-api-client.ts by adopting the server-side
file browser dialog approach from fs/ui branch.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added .automaker/ to .gitignore to prevent tracking of the entire directory.
- Deleted outdated files including app_spec.txt, categories.json, memory.md, clean-code.md, and gemini.md from the .automaker context.
- Enhanced the mcp-server-factory.js and spec-regeneration-service.js to enforce status management for new features, ensuring they default to "backlog" and clarifying status handling in comments.
- Introduced a new file browsing endpoint in fs.ts to improve directory navigation while maintaining security constraints.
- Introduced a new FileBrowserProvider to manage file browsing state and functionality.
- Added FileBrowserDialog component for user interface to navigate and select directories.
- Updated Home component to utilize the file browser context and provide global access.
- Enhanced HttpApiClient to use the new file browser for directory and file selection.
- Implemented server-side route for browsing directories, including drive detection on Windows.
- Replaced prompt-based directory input with a web-based directory picker in HttpApiClient.
- Added server endpoint for resolving directory paths based on directory name and file structure.
- Enhanced error handling and logging for directory and file selection processes.
- Updated file picker to validate file existence with the server for better user feedback.
- Added .automaker/images/ to .gitignore to prevent tracking of generated images.
- Deleted obsolete agent-output.md and feature.json files related to removed "Agent Tools" feature.
- Introduced a new script for uploading build artifacts to R2 and updating releases.json.
- Enhanced GitHub Actions workflow to include artifact uploads for different platforms.
- Relocated the button from the bottom sidebar to the header next to the AutoMaker logo.
- Updated the button to be a compact icon-only version with a tooltip on hover.
- Adjusted the header layout to accommodate the new button placement.
- Removed the old button from the sidebar to streamline the UI.
- Removed unused Electron API methods and simplified the main process.
- Introduced a new workspace picker modal for improved project selection.
- Enhanced error handling for authentication issues across various components.
- Updated UI styles for dark mode support and added new CSS variables.
- Refactored session management to utilize a centralized API access method.
- Added server routes for workspace management, including directory listing and configuration checks.
- Added new scripts for server development and full application startup in package.json.
- Enhanced project management by checking for existing projects to avoid duplicates.
- Improved API integration with better error handling and connection checks in the Electron API.
- Updated UI components to reflect changes in project and session management.
- Refactored authentication status display to include more detailed information on methods used.
