Optimization:
- Cache mean phase per frame in ring buffer for O(1) Doppler access
- Sliding window (last 64 frames) instead of full history traversal
- Doppler FFT: 253.9us -> 44.9us per frame (5.7x faster)
- Full pipeline: 719.2us -> 254.2us per frame (2.8x faster)
Trust kill switch:
- ./verify: one-command proof replay with SHA-256 hash verification
- Enhanced verify.py with source provenance, feature inspection, --audit
- Makefile with verify/verify-verbose/verify-audit targets
- New hash: 0b82bd45e836e5a99db0494cda7795832dda0bb0a88dac65a2bab0e949950ee0
Benchmark fix:
- NN inference_bench.rs uses MockBackend instead of calling forward()
which now correctly errors when no weights are loaded
https://claude.ai/code/session_01Ki7pvEZtJDvqJkmyn6B714
- csi_processor.py: Replace np.random.rand(10) Doppler placeholder with
real temporal phase-difference FFT extraction from CSI history buffer.
Returns zeros (not random) when insufficient history frames available.
- csi_extractor.py: Replace np.random.rand() fallbacks in ESP32 and
Atheros parsers with proper data parsing (ESP32) and explicit error
raising (Atheros). Add CSIExtractionError for clear failure reporting
instead of silent random data substitution.
These are the two most critical mock eliminations identified in ADR-011.
https://claude.ai/code/session_01Ki7pvEZtJDvqJkmyn6B714
Claude