frank/ruvnet--RuView
1
0
Fork 0
mirror of https://github.com/ruvnet/RuView synced 2026-07-20 17:03:24 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
v1721
ruvnet--RuView/CLAUDE.md
T
rUv 17471e93ff ADR-152: WiFi-Pose SOTA 2026 intake — WiFlow-STD benchmark, Rust integrations, ADR-153 802.11bf layer, efficiency frontier (#1008) 
* feat(calibration): NodeGeometry transceiver-geometry recording (ADR-152 §2.1.1)

PerceptAlign-motivated geometry capture at enrollment: per-node optional
records (position, antenna orientation, inter-node distances, acquisition
method) — recorded when known, never required. Event-sourced via
EnrollmentEvent::GeometryRecorded (latest recording wins); persisted on
SpecialistBank with serde defaults so pre-ADR-152 bank JSON loads cleanly
(fixture-proven, and geometry-free banks serialize byte-shape-identical
to the old schema); threaded through MultiNodeMixture as data only — the
learned geometry embeddings and algorithmic fusion use are §2.1.2,
deliberately deferred until the ADR-151 P6 LoRA heads exist.

Geometry recorded from now on means banks captured today remain usable
for layout-conditioned training later — you can't retroactively add
geometry to data you didn't record.

8 new tests (3 geometry, 2 anchor, 2 bank, 1 multistatic) + full-loop
extension (2-node geometry, one tape-measured + one unknown, surviving
the bank JSON round-trip the runtime loads from). 50/50 calibration
(both feature configs) + 23 CLI tests green.

Co-Authored-By: RuFlo <ruv@ruv.net>

* feat(training): two-checkerboard camera↔room calibration for ADR-079 labels (ADR-152 §2.1.3)

Defends the camera-supervised pipeline against PerceptAlign's
"coordinate overfitting": MediaPipe keypoints were emitted in raw camera
coordinates with no shared frame and no transceiver-geometry metadata —
the exact label shape that memorizes deployment layout and collapses
cross-layout.

- scripts/calibrate-camera-room.py + calibration_lib.py: OpenCV
  two-checkerboard calibration → versioned bundle JSON (intrinsics,
  camera→room extrinsics, checkerboard spec, transceiver geometry,
  sha256 calibration_id). Intrinsics resolve from file > cache >
  multi-view computation > loud-warning 2-view fallback.
- collect-ground-truth.py --calibration <bundle>: every sample gains
  keypoints_room (unit bearing rays from the camera center in the room
  frame — documented projective alignment; raw image coords preserved
  so training chooses), camera_origin_room, calibration_id, and the
  transceiver geometry stamp. Without the flag, output is byte-identical
  to before (tested) + a one-line ADR-152 warning.

Design finding (recorded for ADR-152): a single planar checkerboard's
corner grid is centrosymmetric — the reversed corner ordering fits a
ghost camera pose with IDENTICAL reprojection error, so per-board flip
disambiguation is mathematically ill-posed. solve_two_board_extrinsics
solves the joint wall+floor set over all 4 flip combinations, where the
minimum is unique — an independent reason the TWO-checkerboard method is
required, beyond what PerceptAlign states.

15 headless pytest tests green (synthetic corners: extrinsics recovery
incl. ghost resolution, bundle round-trip + hash stability, ray
transforms w/ distortion + cross-resolution, no-calibration byte
identity).

Co-Authored-By: RuFlo <ruv@ruv.net>

* feat(benchmarks): WiFlow-STD reproduction harness + measurement (a) results (ADR-152 §2.2)

Shipped checkpoint REFUTED (0.08% PCK@20, wrong keypoint normalization);
6 reproducibility defects documented (broken imports, corrupted dataset
tail with float32-max garbage that NaN-poisons fp16 BatchNorm, unreachable
test phase). After repairs, retraining with upstream defaults reproduces
96.09% PCK@20 full-test / 96.61% corruption-free (published 97.25%) on
RTX 5080. Claims graded MEASURED-EQUIVALENT; 2.23M params + ~0.055 GFLOPs
verified. Third-party code/weights/data stay out of tree (gitignored).

Co-Authored-By: claude-flow <ruv@ruv.net>

* feat: ADR-152 Rust integrations + ADR-153 802.11bf protocol model

- calibration: GeometryEmbedding — 32-slot permutation-invariant NodeGeometry
  featurization for future LoRA-head conditioning (ADR-152 §2.1.2); derived
  SpecialistBank::geometry_embedding() accessor; 59 tests
- train: MaePretrainConfig + patchify/random-mask with UNSW measured recipe
  (80% masking, (30,3) patches; ADR-152 §2.3, arXiv 2511.18792); strict
  no-truncate/no-NaN policy; proptest properties
- train: WiFlowStdModel — tch-gated port of the verified ~96%-PCK@20
  WiFlow-STD architecture (ADR-152 §2.2 beyond-SOTA); ungated param formula
  pinned to 2,225,042; 15/17-keypoint support; 239 crate tests
- hardware: ieee80211bf forward-compatibility protocol model (ADR-153):
  SpecProfile gates, SensingCapabilities negotiation, required ConsentMode,
  session FSM, SensingTransport + SimTransport + OpportunisticCsiBridge;
  full acceptance checklist covered; 156+4 tests
- deps: ruvector bumps per ADR-152 §2.6 survey (mincut/solver 2.0.6,
  attention 2.1.0, gnn 2.2.0); vendor/ruvector synced to a083bd77f
- docs: ADR-153 accepted; ADR-152 §2.2 status, §2.4 amendment, §2.6 added

Workspace: 162 test suites green (--no-default-features); Python proof PASS.
Known pre-existing flake: homecore-api env_empty_falls_back_to_defaults
(unserialized env-var mutation) — untouched, follow-up.

Co-Authored-By: claude-flow <ruv@ruv.net>

* docs: CHANGELOG + CLAUDE.md entries for ADR-152 integrations and ADR-153

Co-Authored-By: claude-flow <ruv@ruv.net>

* fix(train): repair tch-backend bit-rot — gated path compiles and tests run again

Mechanical API refresh against current tch: Vec::from(Tensor) -> try_from
(+ explicit flatten), numel() usize cast, Rem/div ops -> remainder() /
divide_scalar_mode(floor) — the latter fixed a silent true-division bug in
heatmap argmax decoding; clamp(1.0, f64::MAX) -> clamp_min (torch 2.x scalar
overflow panic); petgraph EdgeRef import; missing EvalMetrics and
verify_checkpoint_dir APIs that tests documented. wiflow_std roundtrip test
uses safetensors (.pt _save_parameters roundtrip broken in torch 2.11
Windows). Gated: 349 passed (incl. all 20 wiflow_std); ungated: unchanged.
Known pre-existing: gaussian-heatmap convention mismatch (2 tests), proof
seed race under parallel threads — documented, deliberate follow-ups.

Co-Authored-By: claude-flow <ruv@ruv.net>

* feat(train): WiFlow-STD PyTorch->tch weight import + numerical parity proof

export_to_safetensors.py maps the retrained checkpoint (295 tensors -> 248
mapped, param sum exactly 2,225,042; num_batches_tracked dropped) into a
tch-loadable safetensors plus a deterministic parity fixture. Gated #[ignore]
integration test loads it strictly and asserts forward-pass agreement:
max abs diff 1.192e-7 on the seed-42 fixture. dump_variable_names test makes
the tch name layout authoritative. Zero architecture discrepancies found.

Co-Authored-By: claude-flow <ruv@ruv.net>

* fix: workflow-review findings — BN gamma init, ThresholdParams serde, init docs

Concurrent validation workflow (2 review lanes + adversarial verification,
13 agents): 5 confirmed findings, 3 refuted. Fixes:
- wiflow_std: pin BatchNorm gamma to 1.0 (tch default draws Uniform(0,1) —
  silently halves activations in from-scratch training; loaded checkpoints
  unaffected, parity re-verified after the change)
- wiflow_std: document the conv-init divergences vs the reference's
  effective kaiming_normal(fan_out) re-init (from-scratch dynamics only)
- ieee80211bf: ThresholdParams deserialization validates via try_from so
  the <=100 invariant holds for untrusted payloads (+ rejection test)

Benchmarks (release, ruvzen): GeometryEmbedding 1.84us/call (542k/s),
MAE tokenization 7.38us/window (135k/s), 802.11bf FSM 8.9M events/s —
nothing suspicious.

Co-Authored-By: claude-flow <ruv@ruv.net>

* docs(adr): ADR-152 §2.1.4 gate resolved — PerceptAlign repo MIT, dataset on HF

Co-Authored-By: claude-flow <ruv@ruv.net>

* feat(benchmarks): edge optimization measured + measurement (b) blocked + 92.9% retraction

Edge optimization (ADR-152 optimize track): ONNX Runtime fp32 is the CPU
latency win (3.2 ms/window, ~3.4x faster than torch, parity 2.4e-7); ORT
dynamic int8 reaches 2.44 MB (paper's ~2.2 MB claim plausible only via
conv-capable toolchains; -0.16pt PCK@20, +18% MPJPE, 2x slower); torch
dynamic quant converts 0% of this conv-only model; fp16 halves storage free
but is slower on CPU.

Measurement (b) BLOCKED-ON-DATA: only 1,077 paired ESP32 windows exist
(stop rule <2k). Forensic recheck of the surviving April holdout RETRACTS
the ADR-079 '92.9% PCK@20' figure: constant-output model, absolute (not
torso) threshold, 69 near-static frames — mean predictor scores 100% under
that protocol; torso-PCK@20 is 19.1%. Corroborates PR #535. Stale citations
removed from user-guide, readme-details, ADR-152 §2.1.3; no-citation rule
extended to ADR-079 accuracy claims. Unblock: >=2k-window multi-pose paired
session + torso-PCK re-baseline.

Co-Authored-By: claude-flow <ruv@ruv.net>

* docs(user-guide): corrected camera-supervised collection tutorial

Step 0 CSI-rate check + session-length math (window yield = frames/20 —
the May session's 8x under-delivery was a ~12 Hz CSI rate, not an aligner
bug); two-checkerboard calibration step (ADR-152 §2.1.3); pose-variety and
confidence guidance; torso-normalized PCK + temporal-split + pred-variance
eval protocol (lessons from the 92.9% retraction); scale presets re-keyed
to realistic window counts.

Co-Authored-By: claude-flow <ruv@ruv.net>

* feat(benchmarks): static PTQ int8 (calibrated) results + overnight capture script

Conv-only static QDQ beats dynamic int8 on accuracy (PCK@20 96.61-96.63%
vs 96.52%, MPJPE +10% vs +18% over fp32) at ~equal size/latency; all-ops
QDQ strictly worse (int8 activations through attention glue). Entropy
calibration verified bit-identical to MinMax on this data. Deployment:
ONNX fp32 for speed (3.2ms), static conv-only QDQ for smallest (2.53MB).

Also: scripts/overnight-empty-capture.py — segmented UDP CSI recorder for
empty-room baselines (no glob collisions, detach-safe).

Co-Authored-By: claude-flow <ruv@ruv.net>

* feat(benchmarks): measurement (b) MEASURED — optimization transfer only, mean-pose baseline wins

WiFlow-STD fine-tuned on 2,046 fresh single-room ESP32 paired windows
(temporal 70/15/15, 70->540 adapter, K=17): pretrained-init 65% PCK@20 vs
scratch 0% (optimization transfer) but frozen-trunk ~0% (no feature
transfer), and NOTHING beats the mean-pose baseline (95.9% PCK@20 —
single subject, near-static normalized coords). Honesty gates held: pred
std 0.0113 (non-constant model) but mean-baseline dominance means no
citable CSI->pose capability from this data. ADR-152 open question 1
answered partially; definitive answer needs multi-subject/position data.

Two new aligner findings: heterogeneous csi_shape with silent zero-padding
(~20%), and extractCsiMatrix's transposed shape label (frame-major data,
[nSc, nFrames] label) — fixes pending.

Co-Authored-By: claude-flow <ruv@ruv.net>

* feat(benchmarks): efficiency sweep MEASURED — half model dominates full reference

Compact WiFlow-STD variants on the same data/split/protocol: half (843,834
params, 0.38x) strictly dominates the 2.23M reference (PCK@20 96.62 vs
96.61, PCK@50 99.47 vs 99.11, MPJPE 0.00898 vs 0.0094) — the published
architecture is over-parameterized for its own benchmark. quarter (338k)
96.05%; tiny (56,290 params, 1/39.5) holds 94.11% — a ~220KB fp32 edge
candidate. In-domain caveats recorded; cross-domain untested.

Co-Authored-By: claude-flow <ruv@ruv.net>

* feat(train): compact WiFlow-STD presets in Rust + tiny edge artifact (ADR-152)

WiFlowStdConfig gains half()/quarter()/tiny() mirroring the overnight sweep
exactly: TcnGroupsMode (Fixed/Gcd/Depthwise), input_pw_groups, derived
stride schedule and decoder-mid (all default to upstream behavior; legacy
serde JSON unaffected). Param formulas pin to trained ground truth first
try: 843,834 / 338,600 / 56,290; default 2,225,042 pin and 1.192e-7 parity
unchanged. 248 tests green.

Tiny edge artifact (tiny_edge_bench.py): ONNX fp32 = 295 KB, 0.66 ms/win
(~1,500/s CPU), 94.11% PCK@20 (matches sweep clean-test exactly; parity
1.49e-7). Static int8 is a bad trade at this scale (-1.43pt, +19% MPJPE,
-16% size, slower) — recorded as negative result. Export note: width-16
breaks AdaptiveAvgPool((15,1)) TorchScript export; replaced by exact
mean+matmul equivalent, proven by parity.

Co-Authored-By: claude-flow <ruv@ruv.net>

* fix: resolve all 10 confirmed code-review findings (7-angle review, 20/20 verified)

wiflow_std: min_feature_width (default 15) replaces the keypoints->stride
coupling — for_keypoints(17) now provably builds the trained [2,2,2,2]
graph and pools 15->17, matching the validated Python protocol (pinned by
tests); param_count() total on invalid configs; random_mask returns Result
and rejects non-finite/out-of-range ratios; trainer checkpoints switched
to safetensors (.pt VarStore roundtrip broken on Windows torch 2.11).

ieee80211bf: SBP proxy now re-triggers instances and relays reports via
Action::RelaySbpReport -> SensingFrame::SbpReport (clients consume via
their existing path); missed_instances reset on success = consecutive
semantics; SessionTable gains a guarded SBP entry point + unknown-id drop
counter; initiator-role sessions reject inbound setup/SBP requests
(RejectedNotSupported) closing the idle hijack; StartSetup/StartSbp
outside Idle return InvalidStateForCommand; SBP validation unified
through evaluate_setup with a 1:1 SetupStatus->SbpStatus mapping.
events.rs split out to honor the 500-line cap.

calibration/cli: enrollment geometry now actually reaches trained banks —
both production call sites attach .with_geometry; --geometry flag on
train-room and POST /enroll/geometry + train-body geometry on
calibrate-serve give production a recording surface; geometry-free banks
log the ADR-152 §2.1.2 note.

benchmarks: corruption masks committed as ground truth (unregenerable
after in-place cleaning; verified bit-identical regeneration from the
pristine copy) + generate_corruption_masks.py producer; _bench_common.py
dedups the 5x-copied shim/evaluate/seed/remap (post-refactor PCK@20
re-verified equal to the last digit); remote scripts get the mmap patch;
tiny_edge --calib validated multiple-of-64; onnx_bench --help no longer
executes (and overwrote) the export — artifact restored byte-exact.

Workspace: 2,963 tests passed, 0 failed; Python proof PASS.

Co-Authored-By: claude-flow <ruv@ruv.net>

* ci: build workspace tests without debuginfo — runner disk exhaustion

The combined 38-crate debug target exceeds the GitHub runner's disk
('final link failed: No space left on device'); the same tree measured
151GB locally with full debuginfo. CARGO_PROFILE_{DEV,TEST}_DEBUG=0
shrinks the target ~5-10x; debuginfo serves no purpose in CI test runs.

Co-Authored-By: claude-flow <ruv@ruv.net>
2026-06-11 17:02:23 -04:00

409 lines
19 KiB
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# Claude Code Configuration — WiFi-DensePose + Claude Flow V3
## Project: wifi-densepose
WiFi-based human pose estimation using Channel State Information (CSI).
Dual codebase: Python v1 (`v1/`) and Rust port (`v2/`).
### Key Rust Crates
| Crate | Description |
|-------|-------------|
| `wifi-densepose-core` | Core types, traits, error types, CSI frame primitives |
| `wifi-densepose-signal` | SOTA signal processing + RuvSense multistatic sensing (16 modules) |
| `wifi-densepose-nn` | Neural network inference (ONNX, PyTorch, Candle backends) |
| `wifi-densepose-train` | Training pipeline with ruvector integration + ruview_metrics; MAE pretraining recipe (`mae.rs`, ADR-152 §2.3) + WiFlow-STD port (`wiflow_std/`, tch-gated) |
| `wifi-densepose-mat` | Mass Casualty Assessment Tool — disaster survivor detection |
| `wifi-densepose-hardware` | ESP32 aggregator, TDM protocol, channel hopping firmware; `ieee80211bf/` 802.11bf forward-compat protocol model (ADR-153) |
| `wifi-densepose-ruvector` | RuVector v2.0.4 integration + cross-viewpoint fusion (5 modules) |
| `wifi-densepose-wasm` | WebAssembly bindings for browser deployment |
| `wifi-densepose-cli` | CLI tool (`wifi-densepose` binary) — `calibrate`/`calibrate-serve`/`enroll`/`train-room`/`room-watch` + MAT (MAT gated behind the `mat` feature; build `--no-default-features` for the aarch64/appliance calibration binary) |
| `wifi-densepose-calibration` | ADR-151 per-room calibration & specialist training — `baseline → enroll → extract → train` → bank of small specialists (presence/posture/breathing/heartbeat/restlessness/anomaly) + multistatic fusion; pure Rust, edge-deployable |
| `wifi-densepose-sensing-server` | Lightweight Axum server for WiFi sensing UI |
| `wifi-densepose-wifiscan` | Multi-BSSID WiFi scanning (ADR-022) |
| `wifi-densepose-vitals` | ESP32 CSI-grade vital sign extraction (ADR-021) |
| `nvsim` | Deterministic NV-diamond magnetometer pipeline simulator (ADR-089) — standalone leaf, WASM-ready |
| `vendor/rvcsi` (submodule) | **rvCSI** — edge RF sensing runtime (ADR-095/096): 9 crates (`rvcsi-core`/`-dsp`/`-events`/`-adapter-file`/`-adapter-nexmon`/`-ruvector`/`-runtime`/`-node`/`-cli`). Lives in its own repo ([github.com/ruvnet/rvcsi](https://github.com/ruvnet/rvcsi)), vendored here under `vendor/rvcsi`, published to crates.io as `rvcsi-* 0.3.x` and to npm as `@ruv/rvcsi`. Not a `v2/` workspace member — depend on the published crates (or the submodule's `crates/rvcsi-*` paths). Normalized `CsiFrame`/`CsiWindow`/`CsiEvent` schema, validate-before-FFI, reusable DSP, typed confidence-scored events, the napi-c Nexmon shim (real nexmon_csi `.pcap` from a Raspberry Pi 5 / 4 / 3B+ — BCM43455c0), the napi-rs SDK, the `rvcsi` CLI, a Claude Code plugin. |
| `ruview-swarm` | Drone swarm control system (ADR-148) — hierarchical-mesh topology, Raft consensus, MARL, CSI sensing payload, MAVLink/PX4 compat, Ruflo AI-agent integration |
### RuvSense Modules (`signal/src/ruvsense/`)
| Module | Purpose |
|--------|---------|
| `multiband.rs` | Multi-band CSI frame fusion, cross-channel coherence |
| `phase_align.rs` | Iterative LO phase offset estimation, circular mean |
| `multistatic.rs` | Attention-weighted fusion, geometric diversity |
| `coherence.rs` | Z-score coherence scoring, DriftProfile |
| `coherence_gate.rs` | Accept/PredictOnly/Reject/Recalibrate gate decisions |
| `pose_tracker.rs` | 17-keypoint Kalman tracker with AETHER re-ID embeddings |
| `field_model.rs` | SVD room eigenstructure, perturbation extraction |
| `tomography.rs` | RF tomography, ISTA L1 solver, voxel grid |
| `longitudinal.rs` | Welford stats, biomechanics drift detection |
| `intention.rs` | Pre-movement lead signals (200-500ms) |
| `cross_room.rs` | Environment fingerprinting, transition graph |
| `gesture.rs` | DTW template matching gesture classifier |
| `adversarial.rs` | Physically impossible signal detection, multi-link consistency |
| `cir.rs` | ADR-134 CSI→CIR via ISTA L1 sparse recovery (NeumannSolver warm-start) |
| `calibration.rs` | ADR-135 empty-room baseline (Welford amplitude + von Mises phase, drift trigger) |
### Cross-Viewpoint Fusion (`ruvector/src/viewpoint/`)
| Module | Purpose |
|--------|---------|
| `attention.rs` | CrossViewpointAttention, GeometricBias, softmax with G_bias |
| `geometry.rs` | GeometricDiversityIndex, Cramer-Rao bounds, Fisher Information |
| `coherence.rs` | Phase phasor coherence, hysteresis gate |
| `fusion.rs` | MultistaticArray aggregate root, domain events |
### RuVector v2.0.4 Integration (ADR-016 complete, ADR-017 proposed)
All 5 ruvector crates integrated in workspace:
- `ruvector-mincut` → `metrics.rs` (DynamicPersonMatcher) + `subcarrier_selection.rs`
- `ruvector-attn-mincut` → `model.rs` (apply_antenna_attention) + `spectrogram.rs`
- `ruvector-temporal-tensor` → `dataset.rs` (CompressedCsiBuffer) + `breathing.rs`
- `ruvector-solver` → `subcarrier.rs` (sparse interpolation 114→56) + `triangulation.rs`
- `ruvector-attention` → `model.rs` (apply_spatial_attention) + `bvp.rs`
### Architecture Decisions
43 ADRs in `docs/adr/` (ADR-001 through ADR-043). Key ones:
- ADR-014: SOTA signal processing (Accepted)
- ADR-015: MM-Fi + Wi-Pose training datasets (Accepted)
- ADR-016: RuVector training pipeline integration (Accepted — complete)
- ADR-017: RuVector signal + MAT integration (Proposed — next target)
- ADR-024: Contrastive CSI embedding / AETHER (Accepted)
- ADR-027: Cross-environment domain generalization / MERIDIAN (Accepted)
- ADR-028: ESP32 capability audit + witness verification (Accepted)
- ADR-029: RuvSense multistatic sensing mode (Proposed)
- ADR-030: RuvSense persistent field model (Proposed)
- ADR-031: RuView sensing-first RF mode (Proposed)
- ADR-032: Multistatic mesh security hardening (Proposed)
- ADR-148: Drone swarm control system / `ruview-swarm` (In Progress)
- ADR-152: WiFi-Pose SOTA 2026 intake — geometry conditioning, WiFlow-STD benchmark (measurement (a) complete: claims MEASURED-EQUIVALENT at ~96% PCK@20), MAE recipe (Proposed; §2.1–2.3, 2.6 implemented)
- ADR-153: IEEE 802.11bf-2025 forward-compatibility protocol model (Accepted — amends ADR-152 §2.4)
### Supported Hardware
| Device | Port | Chip | Role | Cost |
|--------|------|------|------|------|
| ESP32-S3 (8MB flash) | COM9 (ruvzen, was COM7) | Xtensa dual-core | WiFi CSI sensing node | ~$9 |
| ESP32-S3 SuperMini (4MB) | — | Xtensa dual-core | WiFi CSI (compact) | ~$6 |
| ESP32-C6 + Seeed MR60BHA2 | COM12 (ruvzen, was COM4) | RISC-V + 60 GHz FMCW | mmWave HR/BR/presence + WiFi CSI | ~$15 |
| HLK-LD2410 | — | 24 GHz FMCW | Presence + distance | ~$3 |
**Not supported:** ESP32 (original), ESP32-C3 — single-core, can't run CSI DSP pipeline.
### Build & Test Commands (this repo)
```bash
# Rust — full workspace tests (1,031+ tests, ~2 min)
cd v2
cargo test --workspace --no-default-features
# Rust — single crate check (no GPU needed)
cargo check -p wifi-densepose-train --no-default-features
# Python — deterministic proof verification (SHA-256)
python archive/v1/data/proof/verify.py
# Python — test suite
cd archive/v1 && python -m pytest tests/ -x -q
```
### ESP32 Firmware Build (Windows — Python subprocess required)
```bash
# Build 8MB firmware (real WiFi CSI mode, no mocks)
# See CLAUDE.local.md for the full Python subprocess command
# Key: must strip MSYSTEM env vars for ESP-IDF v5.4 on Git Bash
# Build 4MB firmware
cp sdkconfig.defaults.4mb sdkconfig.defaults
# then same build process
# Flash to COM7
# [python, idf_py, '-p', 'COM7', 'flash']
# Provision WiFi
python firmware/esp32-csi-node/provision.py --port COM7 \
--ssid "YourWiFi" --password "secret" --target-ip 192.168.1.20
# Monitor serial
python -m serial.tools.miniterm COM7 115200
```
### Firmware Release Process
1. Build 8MB from `sdkconfig.defaults.template` (no mock)
2. Build 4MB from `sdkconfig.defaults.4mb` (no mock)
3. Save 6 binaries: `esp32-csi-node.bin`, `bootloader.bin`, `partition-table.bin`, `ota_data_initial.bin`, `esp32-csi-node-4mb.bin`, `partition-table-4mb.bin`
4. Tag: `git tag v0.X.Y-esp32 && git push origin v0.X.Y-esp32`
5. Release: `gh release create v0.X.Y-esp32 <binaries> --title "..." --notes-file ...`
6. Verify on real hardware (COM7) before publishing
7. **CRITICAL:** Always test with real WiFi CSI, not mock mode — mock missed the Kconfig threshold bug
### Crate Publishing Order
Crates must be published in dependency order:
1. `wifi-densepose-core` (no internal deps)
2. `wifi-densepose-vitals` (no internal deps)
3. `wifi-densepose-wifiscan` (no internal deps)
4. `wifi-densepose-hardware` (no internal deps)
5. `wifi-densepose-signal` (depends on core)
6. `wifi-densepose-nn` (no internal deps, workspace only)
7. `wifi-densepose-ruvector` (no internal deps, workspace only)
8. `wifi-densepose-train` (depends on signal, nn)
9. `wifi-densepose-mat` (depends on core, signal, nn)
10. `wifi-densepose-wasm` (depends on mat)
11. `wifi-densepose-sensing-server` (depends on wifiscan)
12. `wifi-densepose-cli` (depends on mat)
### Validation & Witness Verification (ADR-028)
**After any significant code change, run the full validation:**
```bash
# 1. Rust tests — must be 1,031+ passed, 0 failed
cd v2
cargo test --workspace --no-default-features
# 2. Python proof — must print VERDICT: PASS
cd ..
python archive/v1/data/proof/verify.py
# 3. Generate witness bundle (includes both above + firmware hashes)
bash scripts/generate-witness-bundle.sh
# 4. Self-verify the bundle — must be 7/7 PASS
cd dist/witness-bundle-ADR028-*/
bash VERIFY.sh
```
**If the Python proof hash changes** (e.g., numpy/scipy version update):
```bash
# Regenerate the expected hash, then verify it passes
python archive/v1/data/proof/verify.py --generate-hash
python archive/v1/data/proof/verify.py
```
**Witness bundle contents** (`dist/witness-bundle-ADR028-<sha>.tar.gz`):
- `WITNESS-LOG-028.md` — 33-row attestation matrix with evidence per capability
- `ADR-028-esp32-capability-audit.md` — Full audit findings
- `proof/verify.py` + `expected_features.sha256` — Deterministic pipeline proof
- `test-results/rust-workspace-tests.log` — Full cargo test output
- `firmware-manifest/source-hashes.txt` — SHA-256 of all 7 ESP32 firmware files
- `crate-manifest/versions.txt` — All 15 crates with versions
- `VERIFY.sh` — One-command self-verification for recipients
**Key proof artifacts:**
- `archive/v1/data/proof/verify.py` — Trust Kill Switch: feeds reference signal through production pipeline, hashes output
- `archive/v1/data/proof/expected_features.sha256` — Published expected hash
- `archive/v1/data/proof/sample_csi_data.json` — 1,000 synthetic CSI frames (seed=42)
- `docs/WITNESS-LOG-028.md` — 11-step reproducible verification procedure
- `docs/adr/ADR-028-esp32-capability-audit.md` — Complete audit record
### Branch
Default branch: `main`
Active feature branch: `ruvsense-full-implementation` (PR #77)
---
## Behavioral Rules (Always Enforced)
- Do what has been asked; nothing more, nothing less
- NEVER create files unless they're absolutely necessary for achieving your goal
- ALWAYS prefer editing an existing file to creating a new one
- NEVER proactively create documentation files (*.md) or README files unless explicitly requested
- NEVER save working files, text/mds, or tests to the root folder
- Never continuously check status after spawning a swarm — wait for results
- ALWAYS read a file before editing it
- NEVER commit secrets, credentials, or .env files
## File Organization
- NEVER save to root folder — use the directories below
- `docs/adr/` — Architecture Decision Records (43 ADRs)
- `docs/ddd/` — Domain-Driven Design models
- `v2/crates/` — Rust workspace crates (15 crates)
- `v2/crates/wifi-densepose-signal/src/ruvsense/` — RuvSense multistatic modules (14 files)
- `v2/crates/wifi-densepose-ruvector/src/viewpoint/` — Cross-viewpoint fusion (5 files)
- `v2/crates/wifi-densepose-hardware/src/esp32/` — ESP32 TDM protocol
- `firmware/esp32-csi-node/main/` — ESP32 C firmware (channel hopping, NVS config, TDM)
- `archive/v1/src/` — Python source (core, hardware, services, api)
- `archive/v1/data/proof/` — Deterministic CSI proof bundles
- `.claude-flow/` — Claude Flow coordination state (committed for team sharing)
- `.claude/` — Claude Code settings, agents, memory (committed for team sharing)
## Project Architecture
- Follow Domain-Driven Design with bounded contexts
- Keep files under 500 lines
- Use typed interfaces for all public APIs
- Prefer TDD London School (mock-first) for new code
- Use event sourcing for state changes
- Ensure input validation at system boundaries
### Project Config
- **Topology**: hierarchical-mesh
- **Max Agents**: 15
- **Memory**: hybrid
- **HNSW**: Enabled
- **Neural**: Enabled
## Pre-Merge Checklist
Before merging any PR, verify each item applies and is addressed:
1. **Rust tests pass** — `cargo test --workspace --no-default-features` (1,031+ passed, 0 failed)
2. **Python proof passes** — `python archive/v1/data/proof/verify.py` (VERDICT: PASS)
3. **README.md** — Update platform tables, crate descriptions, hardware tables, feature summaries if scope changed
4. **CLAUDE.md** — Update crate table, ADR list, module tables, version if scope changed
5. **CHANGELOG.md** — Add entry under `[Unreleased]` with what was added/fixed/changed
6. **User guide** (`docs/user-guide.md`) — Update if new data sources, CLI flags, or setup steps were added
7. **ADR index** — Update ADR count in README docs table if a new ADR was created
8. **Witness bundle** — Regenerate if tests or proof hash changed: `bash scripts/generate-witness-bundle.sh`
9. **Docker Hub image** — Only rebuild if Dockerfile, dependencies, or runtime behavior changed
10. **Crate publishing** — Only needed if a crate is published to crates.io and its public API changed
11. **`.gitignore`** — Add any new build artifacts or binaries
12. **Security audit** — Run security review for new modules touching hardware/network boundaries
## Build & Test
```bash
# Build
npm run build
# Test
npm test
# Lint
npm run lint
```
- ALWAYS run tests after making code changes
- ALWAYS verify build succeeds before committing
## Security Rules
- NEVER hardcode API keys, secrets, or credentials in source files
- NEVER commit .env files or any file containing secrets
- Always validate user input at system boundaries
- Always sanitize file paths to prevent directory traversal
- Run `npx @claude-flow/cli@latest security scan` after security-related changes
## Concurrency: 1 MESSAGE = ALL RELATED OPERATIONS
- All operations MUST be concurrent/parallel in a single message
- Use Claude Code's Task tool for spawning agents, not just MCP
- ALWAYS batch ALL todos in ONE TodoWrite call (5-10+ minimum)
- ALWAYS spawn ALL agents in ONE message with full instructions via Task tool
- ALWAYS batch ALL file reads/writes/edits in ONE message
- ALWAYS batch ALL Bash commands in ONE message
## Swarm Orchestration
- MUST initialize the swarm using CLI tools when starting complex tasks
- MUST spawn concurrent agents using Claude Code's Task tool
- Never use CLI tools alone for execution — Task tool agents do the actual work
- MUST call CLI tools AND Task tool in ONE message for complex work
### 3-Tier Model Routing (ADR-026)
| Tier | Handler | Latency | Cost | Use Cases |
|------|---------|---------|------|-----------|
| **1** | Agent Booster (WASM) | <1ms | $0 | Simple transforms (var→const, add types) — Skip LLM |
| **2** | Haiku | ~500ms | $0.0002 | Simple tasks, low complexity (<30%) |
| **3** | Sonnet/Opus | 2-5s | $0.003-0.015 | Complex reasoning, architecture, security (>30%) |
- Always check for `[AGENT_BOOSTER_AVAILABLE]` or `[TASK_MODEL_RECOMMENDATION]` before spawning agents
- Use Edit tool directly when `[AGENT_BOOSTER_AVAILABLE]`
## Swarm Configuration & Anti-Drift
- ALWAYS use hierarchical topology for coding swarms
- Keep maxAgents at 6-8 for tight coordination
- Use specialized strategy for clear role boundaries
- Use `raft` consensus for hive-mind (leader maintains authoritative state)
- Run frequent checkpoints via `post-task` hooks
- Keep shared memory namespace for all agents
```bash
npx @claude-flow/cli@latest swarm init --topology hierarchical --max-agents 8 --strategy specialized
```
## Swarm Execution Rules
- ALWAYS use `run_in_background: true` for all agent Task calls
- ALWAYS put ALL agent Task calls in ONE message for parallel execution
- After spawning, STOP — do NOT add more tool calls or check status
- Never poll TaskOutput or check swarm status — trust agents to return
- When agent results arrive, review ALL results before proceeding
## V3 CLI Commands
### Core Commands
| Command | Subcommands | Description |
|---------|-------------|-------------|
| `init` | 4 | Project initialization |
| `agent` | 8 | Agent lifecycle management |
| `swarm` | 6 | Multi-agent swarm coordination |
| `memory` | 11 | AgentDB memory with HNSW search |
| `task` | 6 | Task creation and lifecycle |
| `session` | 7 | Session state management |
| `hooks` | 17 | Self-learning hooks + 12 workers |
| `hive-mind` | 6 | Byzantine fault-tolerant consensus |
### Quick CLI Examples
```bash
npx @claude-flow/cli@latest init --wizard
npx @claude-flow/cli@latest agent spawn -t coder --name my-coder
npx @claude-flow/cli@latest swarm init --v3-mode
npx @claude-flow/cli@latest memory search --query "authentication patterns"
npx @claude-flow/cli@latest doctor --fix
```
## Available Agents (60+ Types)
### Core Development
`coder`, `reviewer`, `tester`, `planner`, `researcher`
### Specialized
`security-architect`, `security-auditor`, `memory-specialist`, `performance-engineer`
### Swarm Coordination
`hierarchical-coordinator`, `mesh-coordinator`, `adaptive-coordinator`
### GitHub & Repository
`pr-manager`, `code-review-swarm`, `issue-tracker`, `release-manager`
### SPARC Methodology
`sparc-coord`, `sparc-coder`, `specification`, `pseudocode`, `architecture`
## Memory Commands Reference
```bash
# Store (REQUIRED: --key, --value; OPTIONAL: --namespace, --ttl, --tags)
npx @claude-flow/cli@latest memory store --key "pattern-auth" --value "JWT with refresh" --namespace patterns
# Search (REQUIRED: --query; OPTIONAL: --namespace, --limit, --threshold)
npx @claude-flow/cli@latest memory search --query "authentication patterns"
# List (OPTIONAL: --namespace, --limit)
npx @claude-flow/cli@latest memory list --namespace patterns --limit 10
# Retrieve (REQUIRED: --key; OPTIONAL: --namespace)
npx @claude-flow/cli@latest memory retrieve --key "pattern-auth" --namespace patterns
```
## Quick Setup
```bash
claude mcp add claude-flow -- npx -y @claude-flow/cli@latest
npx @claude-flow/cli@latest daemon start
npx @claude-flow/cli@latest doctor --fix
```
## Claude Code vs CLI Tools
- Claude Code's Task tool handles ALL execution: agents, file ops, code generation, git
- CLI tools handle coordination via Bash: swarm init, memory, hooks, routing
- NEVER use CLI tools as a substitute for Task tool agents
## Support
- Documentation: https://github.com/ruvnet/claude-flow
- Issues: https://github.com/ruvnet/claude-flow/issues
Reference in New Issue View Git Blame Copy Permalink