- Add testing methodology and mouse-first architecture docs to CLAUDE.md
- Harden safety.py with Unicode NFKC normalization, newline injection
detection, and 10K character length limit
- Create screen_state.py for detecting BIOS, lock screen, desktop, sleep
states via screenshot hash analysis and OCR keyword matching
- Integrate ScreenStateDetector into agent.py run_task() loop
- Centralize desktop/app keyword constants in screen_state.py
- Add 47 new unit tests (test_screen_state, test_mouse_ops, test_safety
edge cases)
- Migrate test_integration.py cleanup code from combo keys to mouse_ops
- Fix pre-existing test_shortcut_action test to match blocked behavior
- Add project evaluation table to CLAUDE.md known limitations
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
qiuruiandClaude Opus 4.6
5b50a6b1d3