GOAP Agent 6 output: ESP32 CSI capabilities (52/114 subcarriers), 16-node
mesh topology with 120 edges, TDM synchronized sensing (3ms slots),
computational budget (Stoer-Wagner uses 0.07% of one core), channel hopping,
power analysis (0.44W/node), dual-core firmware architecture, and edge vs
server computing with 100x data reduction on-device.
Part of RF Topological Sensing research swarm (12 agents).
https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv
GOAP Agent 1 output: Graph-theoretic foundations covering max-flow/min-cut
for RF (Ford-Fulkerson, Stoer-Wagner, Karger), RF as dynamic graph with
CSI coherence weights, topological change detection via Fiedler vector and
Cheeger inequality, dynamic graph algorithms, comparison to classical RF
sensing, formal mathematical framework, and 9 open research questions.
Part of RF Topological Sensing research swarm (12 agents).
https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv
GOAP Agent 7 output: 1,226-line document covering SimCLR/MoCo/BYOL for CSI,
AETHER-Topo dual-head extension, coherence boundary detection with multi-scale
analysis, delta-driven updates (2-12x efficiency), self-supervised pre-training
protocol, triplet networks for 5-state edge classification, and MERIDIAN
cross-environment transfer with EWC continual learning.
Part of RF Topological Sensing research swarm (12 agents).
https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv
GOAP Agent 4 output: 896-line SOTA document covering Graph Transformers
(Graphormer, SAN, GPS, TokenGT), Temporal Graph Transformers (TGN, TGAT,
DyRep), ViT for RF spectrograms, transformer-based mincut prediction,
positional encoding for RF graphs, foundation models for RF sensing, and
efficient edge deployment with INT8 quantization.
Part of RF Topological Sensing research swarm (10 agents).
https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv
- Add create_collector() factory function that auto-detects platform and never raises
- Add LinuxWifiCollector.is_available() classmethod for probe-without-exception
- Refactor ws_server.py to use create_collector(), removing ~30 lines of duplicated platform detection
- Add 10 unit tests covering all platform paths and edge cases
- Add ADR-049 documenting the cross-platform detection and fallback chain
Docker, WSL, and headless users now get SimulatedCollector automatically
with a clear WARNING log instead of a RuntimeError crash.
Closes#148Closes#155
Co-Authored-By: claude-flow <ruv@ruv.net>
The ambient light color 0x446688 (dark blue-gray) was too dim to produce
visible brightness changes. Changed to 0xccccdd (bright neutral) with 5x
multiplier. Bumped SETTINGS_VERSION to force fresh defaults.
Co-Authored-By: claude-flow <ruv@ruv.net>
The ambient light was initialized with intensity * 3.0 but the slider
and preset callbacks set raw value without the multiplier, making the
setting appear to do nothing.
Co-Authored-By: claude-flow <ruv@ruv.net>
Add environment-tuned activity classification that learns from labeled
ESP32 CSI recordings, replacing brittle static thresholds.
- Adaptive classifier: 15-feature logistic regression trained from JSONL
recordings (variance, motion band, subcarrier stats: skew, kurtosis,
entropy, IQR). Trains in <1s, persists as JSON, auto-loads on restart.
- Three-stage signal smoothing: adaptive baseline subtraction (α=0.003),
EMA + trimmed-mean median filter (21-frame window), hysteresis debounce
(4 frames). Motion classification now stable across seconds, not frames.
- Vital signs stabilization: outlier rejection (±8 BPM HR, ±2 BPM BR),
trimmed mean, dead-band (±2 BPM HR), EMA α=0.02. HR holds steady for
10+ seconds instead of jumping 50 BPM every frame.
- Observatory auto-detect: always probes /health on startup, connects
WebSocket to live ESP32 data automatically.
- New API endpoints: POST /api/v1/adaptive/train, GET /adaptive/status,
POST /adaptive/unload for runtime model management.
- Updated user guide with Observatory, adaptive classifier tutorial,
signal smoothing docs, and new troubleshooting entries.
- Add branch = main to each submodule in .gitmodules
- Add GitHub Actions workflow that checks every 6 hours for
upstream updates and opens a PR automatically
Co-Authored-By: claude-flow <ruv@ruv.net>
Replace `declare -A` (associative array, requires Bash 4+) with
a standard indexed array. macOS ships Bash 3.2 due to GPLv3
licensing, so `declare -A` fails with "invalid option".
Fixes#134
Co-Authored-By: claude-flow <ruv@ruv.net>
Replace unsafe `torch.load(path)` with `torch.load(path,
map_location=self.device, weights_only=True)` to prevent
pickle deserialization RCE (trailofbits.python.pickles-in-pytorch).
weights_only=True disables pickle entirely for model loading,
which is the PyTorch-recommended mitigation (available since 1.13).
Also adds map_location for correct CPU/GPU device mapping.
Closes#106
Co-Authored-By: claude-flow <ruv@ruv.net>
- Add intro explaining DDD purpose and bounded context overview table
- Add Edge Intelligence bounded context (#7) for on-device sensing
- Add ubiquitous language terms: Edge Tier, WASM Module
- Fix frame rate 20 Hz -> 28 Hz (measured on hardware)
- Link each context to its source files and ADRs
- Add NVS configuration table and invariants for edge processing
- Create docs/ddd/README.md introducing all 3 domain models
- Update main README docs table to link to DDD index
Co-Authored-By: claude-flow <ruv@ruv.net>
Claude
rUv