Implemented three-layer defense mechanism to prevent AI-generated code from breaking the codebase:
- Layer 1: AGENTS.md with universal AI agent instructions
- Layer 2: Husky pre-commit hooks with test file checking
- Layer 3: GitHub Actions CI with TypeScript, ESLint, tests, and coverage
Includes design document, test infrastructure, and coverage thresholds.
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Detailed step-by-step plan for adding inline agent switcher to
MessageInput with backend support and toast notifications.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Design for inline agent switcher in MessageInput that allows
switching the current session's agent mid-conversation.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add unit and integration tests covering core business logic:
- SessionStore: 18 tests for session persistence and management
- Conductor: 13 tests for session orchestration and agent lifecycle
- IPC Handlers: 19 tests for main-renderer communication
- Agent check: 10 tests for agent detection utilities
Tests achieve 31.74% overall coverage with focus on critical paths. Includes Vitest configuration, mock setup, and test utilities.
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Design for adding a file tree browser in the right panel showing
the current session's working directory with context menu support.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
