Pure conversion from our wire-format `MdnsService` to the
`mdns_sd::ServiceInfo` shape the responder daemon consumes. No
socket binding, no daemon registration yet — that lands next iter
as a `runtime::spawn_mdns_responder(info)` JoinHandle returning
helper, same shape as `runtime::spawn_publisher`.
* `MdnsService::to_service_info(hostname, ipv4) ->
Result<ServiceInfo, mdns_sd::Error>`
* `mdns-sd = "0.11"` added — aligned with the workspace pin from
wifi-densepose-desktop so the lockfile doesn't fork dalek-like
surfaces.
3 new tests:
* to_service_info_carries_service_type_and_port — locks that
`_ruview-ha._tcp` (with or without mdns-sd's trailing-dot
normalisation) and the control port round-trip through the
conversion
* to_service_info_propagates_txt_records — every locked TXT
key from iter 4 (cog_id, mqtt_port, privacy, proto, node_id,
cog_version) reachable via `get_property_val_str` on the
converted ServiceInfo
* to_service_info_does_not_silently_drop_caller_hostname —
locks the caller-side responsibility for the .local. suffix.
mdns-sd 0.11 accepts bare hostnames (verified empirically by
initial test expecting it to reject — it didn't), so the
wrapper layer must do the trailing-dot dance. Documenting
that via a named test catches future bumps where the lib
starts mutating the value.
63/63 cog tests green (60 → 63).
ADR-116 P4 now ⁶⁄₇: ✅ mDNS record-builder, ✅ chain, ✅ JSONL, ✅
file persistence, ✅ Ed25519 signing, ✅ ServiceInfo conversion;
⏳ daemon register + embedded broker.
Co-Authored-By: claude-flow <ruv@ruv.net>
Closes the cryptographic-attestation gap in ADR-116 §2.2: every
witness event can now be signed by the Seed's Ed25519 key, with
verify available to any auditor holding the public key.
Module shape (`src/witness_signing.rs`, kept separate from
`witness::` so the hash chain stays usable without dalek linked
in — important for the wasm32 audit-verifier variant we'll ship
later):
* sign_event(event, &SigningKey) -> Signature
* verify_signature(event, &Signature, &VerifyingKey)
-> Result<(), SignatureVerifyError>
* signature_to_hex / signature_from_hex (128-char lowercase,
matches the witness hex convention)
* SignatureVerifyError::Invalid
* SignatureParseError::{Length, Hex}
Key design point: signature covers the SAME canonical bytes
witness::hash_event hashes. That means:
1. A signed event commits to the entire event content (kind,
payload, timestamp, seq, prev_hash) — no field can be
retroactively changed without invalidating both the hash AND
the signature.
2. The signature implicitly commits to the event's *chain
position* via prev_hash — splicing a signed event into a
different chain breaks verification.
Adds `ed25519-dalek = "2.1"` to cog-ha-matter (already in
workspace via ruv-neural, version kept aligned).
9 new tests:
* sign_and_verify_round_trip
* verify_rejects_signature_under_wrong_key
* verify_rejects_tampered_event (mutate payload after sign)
* verify_rejects_event_with_wrong_prev_hash (splice attack)
* signature_hex_round_trip
* signature_from_hex_rejects_wrong_length
* signature_from_hex_rejects_non_hex
* signature_is_deterministic_for_same_event_and_key
(locks Ed25519's determinism — catches future accidental
swap to a randomized scheme)
* different_events_produce_different_signatures
60/60 cog tests green (51 → 60). Key management is intentionally
out of scope here — the cog runtime reads the Seed's key from the
Cognitum control plane's secure store (separate concern).
ADR-116 P4 now ⁵⁄₆: ✅ mDNS record, ✅ chain, ✅ JSONL, ✅ file
persistence, ✅ Ed25519 signing; ⏳ responder + embedded broker.
Co-Authored-By: claude-flow <ruv@ruv.net>
Closes the witness audit-bundle surface. The hash-chain primitive
+ JSONL serializer from earlier iters only handled one event at a
time; this lands the file-stream surface that operations actually
need:
* `WitnessChain::write_jsonl(&mut impl Write) -> io::Result<()>`
— streams every event as one line + `\n`, empty chain writes
zero bytes
* `WitnessChain::read_jsonl(impl BufRead) -> Result<WitnessChain,
WitnessReadError>` — parses event-by-event AND runs chain-level
`verify()` on the loaded chain, catching reordered or replayed
prefixes that per-event hashing alone misses
Critical security property: `read_jsonl` calls `WitnessChain::verify`
on the loaded chain BEFORE returning Ok. A forged bundle assembled
from two valid chains pasted together would slip past the
per-event hash check (each event's `this_hash` is internally
consistent) but the cross-event `prev_hash` linkage detects the
seam. Test `read_jsonl_chain_verify_catches_reordered_events`
locks this — swap two events in a 2-event bundle, see Verify error.
Error surface (new `WitnessReadError` enum):
* `Io { line_no, msg }` — read failure mid-stream
* `Parse { line_no, source }` — per-event from_jsonl_line failure
* `Verify { source }` — chain-level verify failure
`line_no` is 1-indexed so an auditor sees the same number their
text editor shows. Blank lines tolerated for hand-edited bundles.
7 new tests:
* empty chain writes zero bytes
* write→read round-trips a 3-event chain
* exactly N newlines for N events; trailing newline present
* blank lines / leading newline tolerated
* parse error surfaces with correct line_no
* reordered events caught by chain-level verify
* no-trailing-newline still loads the final event
51/51 cog tests green (44 → 51).
Co-Authored-By: claude-flow <ruv@ruv.net>
Third P4 sub-unit: serialize/parse for the witness hash chain so
audit bundles can be written to disk and replayed.
Wire shape (one record per line, alphabetical field order locked):
{"kind":"...","payload_hex":"...","prev_hash":"...","seq":N,
"this_hash":"...","timestamp_unix_s":N}
Why alphabetical field order: auditors archive whole bundles and
hash them. A rebuild that reordered fields would silently
invalidate every archival hash — locking the order is what makes
the JSONL stable across compiler / serde-json upgrades.
Why hex everywhere: human-greppable, monospace-friendly, no base64
ambiguity, no Vec<u8> JSON-array ugliness. Same convention as
ADR-101's `binary_sha256`.
Critically, `from_jsonl_line` RE-VERIFIES `this_hash` against
the canonical bytes derived from the parsed fields. A tampered
bundle fires `WitnessParseError::HashMismatch` BEFORE the event
loads — the parser is itself an auditor.
New surfaces:
* `WitnessHash::from_hex` (with structured length/parse errors)
* `WitnessEvent::to_jsonl_line`, `from_jsonl_line`
* `WitnessParseError` enum: Json | MissingField | WrongType |
HashLength | HashHex | PayloadHex | PayloadLength | HashMismatch
* private `hex_encode` / `hex_decode` helpers (no `hex` crate dep)
10 new tests:
* jsonl round-trip preserves all fields
* jsonl line has no embedded \n / \r (one record per line)
* jsonl field order is alphabetical (byte-stable archival)
* parser rejects tampered payload via HashMismatch
* parser rejects non-hex characters in hash
* parser rejects missing field
* hex encode/decode round-trip across empty / single byte / 0xff /
UTF-8 / arbitrary bytes
* hex decode rejects odd-length input
* WitnessHash::from_hex round-trip
* WitnessHash::from_hex rejects wrong length
44/44 cog tests green (34 → 44).
ADR-116 P4 row enumerates 4 sub-units now: ✅ mDNS record-builder,
✅ witness chain primitive, ✅ witness JSONL persistence,
⏳ responder + embedded broker + Ed25519 signing.
Co-Authored-By: claude-flow <ruv@ruv.net>
Second P4 unit: an append-only SHA-256 hash chain for tamper-evident
audit logging. ADR-116 §2.2 promised this for healthcare /
education / shared-housing deployments — this lands the primitive
with no key dependency so the next iter can layer Ed25519 signing
on top without touching the chain itself.
Module shape:
* `WitnessHash([u8; 32])` newtype + `WitnessHash::GENESIS` sentinel
* `WitnessEvent { seq, prev_hash, ts, kind, payload, this_hash }`
— once committed, every field is immutable
* `WitnessChain` — `append`, `tip`, `verify`, `events`
* `canonical_bytes` — length-prefixed serialization that prevents
the classic concatenation forgery
(`abc|def` ≠ `ab|cdef`)
* `WitnessVerifyError` — auditor-friendly error with `at: usize`
on every variant (SeqGap, PrevHashMismatch, HashMismatch)
13 new tests covering both happy path and active tampering:
* genesis hash all-zeros
* empty chain tip is genesis
* canonical bytes length-prefixed (anti-forgery)
* canonical bytes start with prev_hash (wire-format lock)
* append links to prev_hash
* seq monotonic from 0
* verify passes on clean chain
* verify catches tampered payload (fires HashMismatch)
* verify catches broken prev_hash link
* verify catches seq gap
* hash hex is 64 lowercase chars
* first event prev_hash == GENESIS (auditor anchor)
* different payloads → different hashes
Hash-chain over Merkle is the right tradeoff for the cog's event
rate (a few/min steady, dozens during a fall) — linear scan is
fine and we save the Merkle complexity for a future tier when
chains span days.
34/34 cog tests green (21 → 34).
ADR-116 P4 row updated to enumerate the three P4 sub-units shipped /
pending: (a) mDNS record-builder ✅, (b) witness hash-chain ✅, (c)
responder + embedded broker + Ed25519 signing pending.
Co-Authored-By: claude-flow <ruv@ruv.net>
Opens P4 with the smallest extractable unit: a pure builder that
produces the wire-format `MdnsService` the responder will publish
next iter. Splitting the record-builder from the responder lets
us:
* lock the TXT-record surface with named unit tests so drift
between the cog and the HA-side YAML auto-discovery binding
fires a test instead of silently breaking deployments,
* swap the responder library (mdns-sd / zeroconf / pnet) without
touching content,
* include the advertisement in `--print-manifest` for Seed
integration tests that can't boot tokio.
TXT surface (sorted, RFC 6763):
| cog_id | "ha-matter" |
| cog_version | CARGO_PKG_VERSION |
| node_id | identity.node_id |
| mqtt_port | u16 stringified |
| privacy | "1" | "0" |
| proto | "ruview-ha/1" |
9 new tests:
* service_type locked to `_ruview-ha._tcp`
* instance_name carries node_id
* control_port advertises the *control plane*, not MQTT
* privacy flag is "1"/"0" (HA config flow reads it byte-stable)
* proto version locked to ruview-ha/1 (bump is deliberate)
* cog_id in TXT matches crate constant
* txt_records sorted for byte-stable mDNS responses
* **PII leak guard**: TXT must NOT carry hr_bpm, br_bpm, pose_*,
keypoint, ssid, lat, lon, mac, rssi — broadcasts in cleartext
so a future "let's add hr_bpm for convenience" patch fires
here, not in a privacy incident.
* required-keys lock — adding is fine, removing/renaming breaks
every deployed Seed.
21/21 cog tests green (12 → 21).
ADR-116 P4 flipped pending → in progress, with the responder /
embedded broker / witness chain enumerated as the remaining P4
sub-units.
Co-Authored-By: claude-flow <ruv@ruv.net>
P3 closes the publisher wiring loop. `main.rs` now:
1. builds `PublisherInputs` from CLI args via the pure helper
extracted last iter,
2. opens a `broadcast::channel::<VitalsSnapshot>(256)`,
3. calls `runtime::spawn_publisher(inputs, rx)` — a thin
wrapper around ADR-115's `publisher::spawn` that owns the
`Arc<MqttConfig>` wrap,
4. holds the tx side so the channel stays open until P3.5
wires the sensing-server bridge,
5. awaits Ctrl-C or unexpected publisher exit (logged at WARN).
Two new tests:
* `spawn_publisher_returns_live_handle_without_broker` — proves
the wiring compiles and the rumqttc event loop survives an
unreachable broker (it retries internally; we abort the handle
inside 100 ms). Catches breakage from a future refactor that
accidentally pre-validates host reachability.
* `default_state_channel_capacity_is_reasonable` — locks the
`DEFAULT_STATE_CHANNEL_CAPACITY = 256` default; a regression to
e.g. 1 would surface here instead of as a dropped frame in
production under bursty multi-Seed federation.
12/12 cog-ha-matter tests green (10 → 12).
ADR-116 phase table: P3 flipped from "in progress" to ✅ wiring done,
with the P3.5 follow-up (sensing-server `/v1/snapshot` WS bridge)
explicitly named.
Co-Authored-By: claude-flow <ruv@ruv.net>
Adds `runtime::build_publisher_inputs(host, port, privacy, identity)` —
the side-effect-free helper that turns the cog's CLI surface into the
`(MqttConfig, OwnedDiscoveryBuilder)` pair ADR-115's `publisher::spawn`
consumes. Keeps the tokio runtime wiring out of the pure unit so the
mDNS responder + Seed control plane (P4) can build the same inputs
from different sources without going through clap.
8 new tests lock the wire-format invariants:
* host/port round-trip into MqttConfig
* privacy_mode propagation (P1 dossier item 7, FDA Jan 2026)
* discovery_prefix defaults to "homeassistant"
* discovery carries node_id + sw_version + friendly_name
* via_device advertises COG_ID (ADR-101/102 device-registry shape)
* client_id includes node_id (lesson from ADR-115 iter 45-48 session
takeover post-mortem — two publishers sharing a client_id loop)
* tls defaults to Off for v1 LAN-only (lock against silent enablement)
* default_identity carries CARGO_PKG_VERSION + PID for uniqueness
Plus the existing 2 manifest tests → 10/10 green
(`cargo test -p cog-ha-matter --no-default-features --lib`).
Also lands the deep-researcher dossier (`docs/research/ADR-116-ha-...`)
that the ADR §3+§4 reference — it was produced last iter but only the
ADR was committed; this puts the source-of-truth into the tree so the
ADR's "8 sections, 30+ citations" claim is actually verifiable.
P3 status in the ADR phase table flipped from "pending" to "in progress"
with the helper named; next iter tokio::spawns publisher::run(...) in
main.rs and registers the mDNS responder.
Co-Authored-By: claude-flow <ruv@ruv.net>
Sets up docs/research/sota-2026-05-22/ as the autonomous-research
output dir, with PROGRESS.md as the canonical 15-vector research
agenda spanning spatial intelligence, RF features, RSSI-only, and
exotic/long-horizon verticals. Cron d6e5c473 (*/10 * * * *) picks
threads from this file and self-terminates at 2026-05-22 08:00 ET.
First concrete contribution this tick — R5 subcarrier saliency:
* examples/research-sota/r5_subcarrier_saliency.py: pure-numpy port
of the count cog's Conv1d encoder + count head, computes per-
subcarrier input×gradient saliency via central-difference. 128
samples × 56 subcarriers × 2 forward passes/subcarrier ≈ ~3 s on
CPU, no GPU or framework dependency.
* docs/research/sota-2026-05-22/R5-subcarrier-saliency.md: research
note with motivation, method, novelty argument, and the first
measured ranking. Top-8 subcarriers for cog-person-count v0.0.2:
[41, 52, 30, 31, 10, 35, 2, 38]. Max/mean ratio 2.85x.
* v2/crates/cog-person-count/cog/artifacts/saliency.json: machine-
readable per-subcarrier saliency + top-K lists, so future-tick
experiments (retrain at K=8/16/32) consume it without re-running.
Key insight from the first measurement: top-8 saliency is *band-
spread* (indices span 2-52), not concentrated. This directly raises
R8's (RSSI-only) feasibility ceiling, because RSSI is a band-
aggregate — it retains the integral of a band-spread signal. First-
order estimate: RSSI-only should hit ~60% of full-CSI accuracy for
the count task. R7 (adversarial defence) inherits a concrete defender-
priority list: corroborate these 8 subcarriers across nodes.
This commit is the first of many short, focused contributions over
the next ~12 hours. PROGRESS.md is the canonical pointer for the
next tick to pick up the next thread.
* chore: stage v0.0.2 artifacts + temperature scalar for build pipeline
Stages count_v1.{safetensors,onnx,temperature,train_results.json}
ahead of the build/sign/upload step. This commit is a momentary
side-effect — the next commit will refresh the per-arch manifests
with the new binary SHAs once ruvultra finishes the cross-build.
The .temperature file holds the calibration scalar from LBFGS over the
held-out conf logits. The Rust cog will read it post-load and divide
conf_logits by it before sigmoid, exactly matching the Python eval.
* feat(cog-person-count): v0.0.2 — K-fold validated, label smoothing + early stop + temp scale
The v0.0.1 "65.1% but class-1=0%" result was an unlucky temporal split
that let a degenerate "always predict 0" classifier hit eval acc =
class-0 fraction. 5-fold stratified random CV proved the architecture
actually learns ~57.1% class-1 accuracy under fair splits — a real,
modestly useful signal.
v0.0.2 ships a retrained model that:
* **Splits randomly (seed=42) 80/20** instead of temporally — eliminates
the trailing-window-class-imbalance cheat.
* **Class-balanced sampler** (multinomial with replacement, weighted by
inverse class frequency) — per-batch expected counts are equal
regardless of dataset distribution.
* **Label smoothing 0.1** on the cross-entropy — reduces confidence
saturation that drove v0.0.1's all-or-nothing predictions.
* **Early stopping** with patience=20 — stops at epoch 29 instead of
overfitting through 400.
* **Temperature scaling** of the conf head — LBFGS fits a scalar T on
held-out conf logits; ships as a count_v1.temperature sidecar so the
Rust cog can divide conf_logits by T before sigmoid.
Numbers on the same data:
| Metric | v0.0.1 | v0.0.2 | K-fold (5x100) |
|------------------|--------|--------|----------------|
| Overall acc | 65.1% | 62.3% | 62.2% ± 1.9% |
| Class 0 acc | 100% | 86.2% | 67.4% |
| Class 1 acc | 0% | 34.3% | 57.1% ✓ |
| MAE | 0.349 | 0.377 | 0.378 |
| Spearman | 0.023 | 0.013 | 0.160 |
Class-1 accuracy 0 → 34.3% is the headline win. Net acc moves slightly
because we stopped cheating on class 0. K-fold's 57% says there's
headroom remaining; reaching it needs more independent splits (== more
data), not more training tricks.
Confidence calibration didn't move. Temperature scaling alone can't fix
a confidence head trained against a noisy argmax==truth indicator over
a 62%-accurate classifier — the head's training signal is the issue,
not its post-hoc transform. The honest fix is multi-room data (#645),
not another calibration knob.
Live on cognitum-v0 at /var/lib/cognitum/apps/person-count/ — health
reports candle-cpu backend, count = 1 (was 0 in v0.0.1) on synthetic
zero input.
Files changed:
* scripts/train-count.py — adds --k-fold (no sklearn dep, hand-rolled
stratified splits with deterministic shuffle) and --v2 paths.
* v2/.../cog/artifacts/count_v1.safetensors (392 KB, new sha
32996433…) + count_v1.onnx (16 KB) + count_v1.temperature (0.9262
scalar) + count_train_results.json (full epoch trace).
* v2/.../cog/artifacts/manifests/{arm,x86_64}/manifest.json bumped to
version 0.0.2 with the new weights_sha256 + caveats.
* docs/benchmarks/person-count-cog.md — appends a v0.0.2 section
with the K-fold diagnostic table and honest-read paragraph.
GCS:
gs://cognitum-apps/cogs/arm/cog-person-count-count_v1.safetensors
refreshed (binaries unchanged — load weights via mmap at runtime).
The arm + x86_64 manifests committed in #696 referenced the binaries
built before #697 wired the `run` subcommand. Rebuilt + re-signed +
re-uploaded to GCS, and re-deployed to cognitum-v0:
arm sha 15c2fbac…7728ea5 (3,807,456 B, up from 2,168,816 — added Tokio runtime)
x86_64 sha 051614ce…cc8388b3 (4,502,960 B, up from 2,615,528)
Both re-signed Ed25519 with COGNITUM_OWNER_SIGNING_KEY. Manifests
now match the binaries published at gs://cognitum-apps/cogs/{arm,
x86_64}/cog-person-count-* and the binary installed at
/var/lib/cognitum/apps/person-count/ on cognitum-v0.
Phase 4 of ADR-103. Adds the long-running polling loop so the cog's
fourth verb (`run`) does real work, completing the ADR-100 runtime
contract end-to-end:
cog-person-count version → "person-count 0.3.0"
cog-person-count manifest → JSON skeleton
cog-person-count health → loads weights + 1-shot infer + emit
cog-person-count run --config → long-running per-frame emit ← THIS
What ships:
* src/runtime.rs (new) — `run_loop` polls sensing_url every poll_ms,
slides a [56, 20] CSI window, runs InferenceEngine::infer, emits
publisher::person_count events. Same shape as
cog-pose-estimation::runtime — fetch_frame extracts amplitudes
from `snapshot.nodes[0].amplitude[]`, fails open on connect errors
with a WARN log rather than crashing.
* src/lib.rs — registers the runtime module.
* src/main.rs — cmd_run now loads RunConfig from a JSON file, builds
the InferenceEngine (with weights if cfg.model_path is set,
otherwise auto-discover), emits a run.started event, and hands off
to the Tokio multi-thread runtime's block_on(run_loop). Single-node
fusion is a no-op for N=1 today; v0.2.0 will append predictions
from sibling nodes and call fusion::fuse_confidence_weighted before
emit.
Verified locally:
cargo check -p cog-person-count --no-default-features → clean
cargo test -p cog-person-count → 15/15 pass (no regressions)
cargo build -p cog-person-count --release → 2.36 MB unchanged
./cog-person-count run --config bad-config.json:
line 1: {"event":"run.started","fields":{"cog":"person-count",
"sensing_url":"http://127.0.0.1:9999/...",poll_ms:100,
"model_path":"(auto-discover)"}}
line 2: WARN sensing-server fetch failed
error=Connection Failed: Connect error: actively refused
(loop alive — exits cleanly on SIGTERM, no crash, no NaN)
Also adds a "Relationship to the in-process score_to_person_count
heuristic" section to cog/README.md explaining the dual-emitter
design (sensing-server keeps emitting the PR #491 slot heuristic;
the cog runs out-of-process and emits person.count events from the
learned model). Operators choose by installing the cog or not — no
sensing-server rebuild required.
ADR-103 §"Migration" status:
1. Land ADR + scaffold ........... done (#693, #694)
2. Train count_v1 ................ done (#695)
3. Cross-compile + sign + GCS .... done (#696)
4. Server-side wiring ............ done — out-of-process design
means no rewire needed; this
cog is the wiring.
5. v0.2.0 multi-room + LoRA ...... data-bound (#645)
Phase 3 of ADR-103. Cross-compiled aarch64 + x86_64 on ruvultra, signed
with COGNITUM_OWNER_SIGNING_KEY (Ed25519), uploaded to GCS, and live-
installed on the cognitum-v0 Pi 5 alongside cog-pose-estimation.
Real-hardware bench on cognitum-v0:
./cog-person-count-arm health
→ backend=candle-cpu, count=0, confidence=0.49, p95=[0,7]
30 sequential health invocations: 0.276 s → 9.2 ms/invocation cold
Compares to cog-pose-estimation's 8.4 ms — count cog is ~10% slower
because the dual-head (count softmax + confidence sigmoid) does ~2x
the work after the shared encoder.
GCS release artifacts (publicly downloadable, SHA-verified):
arm/cog-person-count-arm 2,168,816 B
sha: 36bc0bb0...0d47b507b3c3
sig: R/00xdzHriyr/2r...JK+a6k71NDg== (Ed25519)
x86_64/cog-person-count-x86_64 2,615,528 B
sha: 76cdd1ec...3923 7392b01db
sig: QB+8cnGSMQmu...ZtTNIQ2rDg== (Ed25519)
arm/cog-person-count-count_v1.safetensors 392,088 B
sha: dacb0551...e6e04ff56d15c3a65a9ff
Live install at /var/lib/cognitum/apps/person-count/ on cognitum-v0
matches the layout of every other installed cog (anomaly-detect,
seizure-detect, pose-estimation): cog-person-count-arm binary,
count_v1.safetensors weights, manifest.json, config.json.
Adds:
* v2/.../cog/artifacts/manifests/{arm,x86_64}/manifest.json — full
ADR-100 schema with all fields filled (sha + sig + size + URL +
build_metadata carrying the v0.0.1 honest training caveats).
* docs/benchmarks/person-count-cog.md — appends "Live appliance
install" and "Signed GCS release artifacts" sections to the
benchmark log.
Honest v0.0.1 caveat still applies (class-1 accuracy 0% on the held-
out tail of the single-session training data) — same data-bound
limit as pose_v1. The shipped artifact is the *vehicle*; production-
quality accuracy follows from multi-room paired data per ADR-103's
v0.2.0 plan + #645.
Phase 2 of ADR-103: trained count head on the existing 1,077 paired
samples (the same data that produced pose_v1 yesterday).
Honest result: 65.1% eval accuracy / 100% within ±1 / MAE 0.349 on
the held-out time-window. Per-class: 100% on "empty room" / 0% on
"1 person". The model overfit by epoch 100 (train_acc → 1.0,
eval_loss climbed 0.67 → 7.8) and the "best" checkpoint is the
snapshot that happened to predict the eval window's class
distribution (140/215 = 65.1%, matches eval_acc exactly). Confidence
head Spearman = 0.023 ⇒ uncalibrated. Same data-bound failure mode
as pose_v1 (#645), bounded by single-session training data; same
fix path (multi-room).
What v0.0.1 still validates end-to-end:
* PyTorch → safetensors → Candle Rust loads cleanly on first try.
`cog-person-count health` reports `backend: candle-cpu` and emits
real per-frame predictions instead of the stub backend's hard-coded
{1 person, 0 confidence}. Architecture parity between train-count.py
and src/inference.rs::CountNet is bit-exact.
* ONNX export bit-clean (16 KB, opset 18, dynamic batch axis).
* Training wall time: 5.6 s for 400 epochs on RTX 5080.
* Binary size unchanged (2.36 MB stripped), model loads via mmap at
runtime.
This commit ships:
* scripts/align-ground-truth.js: extended to emit n_persons_mode +
n_persons_max per window so the training pipeline has count
labels. Backwards-compatible (additive fields).
* scripts/train-count.py: new — mirrors CountNet architecture
exactly, loads paired.jsonl, trains 400 epochs with
CE+BCE+Brier loss, exports safetensors + ONNX + per-epoch JSON.
* v2/.../cog/artifacts/{count_v1.safetensors,count_v1.onnx,
count_train_results.json}: the trained artifacts.
* v2/.../cog/README.md: Status table updated with the v0.0.1 numbers
+ an Honest Caveat section explaining the data-bound result.
* docs/benchmarks/person-count-cog.md: new — full v0.0.1 benchmark
log mirroring the format docs/benchmarks/pose-estimation-cog.md
established. Includes comparison to ADR-103 v0.1.0 acceptance
gates and per-class breakdown.
Still pending:
* `run` subcommand wiring (long-running polling loop, same as pose)
* Cross-compile + sign + GCS upload (mirror of pose cog pipeline)
* Live install on cognitum-v0
* v0.2.0: re-train on multi-room data, LoRA per-room adapters,
Stoer-Wagner min-cut clip in fusion stage
First implementation PR for ADR-103. Same incremental shape that
ADR-101 used: scaffold the cog crate, ship a stub-backend release
that satisfies the runtime contract + 15 tests + measured cold-start,
then follow up with the trained count_v1.safetensors in a separate PR.
What ships:
* v2/crates/cog-person-count/ — new workspace member.
- Cargo.toml: candle-core/candle-nn 0.9 (cpu default, cuda feature
opt-in), safetensors, ureq, sha2 — same dep shape as the pose cog
but minus wifi-densepose-train (this cog has no training-side
consumer, so the dep tree is materially smaller → 2.36 MB
binary vs the pose cog's 4.5 MB).
- src/inference.rs: CountNet (Conv1d 56→64→128→128 encoder + count
head Linear(128→64→8)+softmax + confidence head
Linear(128→32→1)+sigmoid). Stub backend returns
`{1-person, 0-confidence}` honestly when no safetensors present.
- src/fusion.rs: fuse_confidence_weighted() — Bayesian product of
per-node distributions with confidence-weighted log-sum, plus
fuse_with_mincut_clip() hook for the v0.2.0 Stoer-Wagner
upper-bound (`ruvector-mincut` dep lands when min-cut graph
builder is ready). Confidences floored at 1e-3 and probs floored
at 1e-9 before logs — no NaN propagation.
- src/publisher.rs: emits {count, confidence, count_p95_low,
count_p95_high, n_nodes, probs} per ADR-103 §"Output".
- src/main.rs: full ADR-100 four-verb CLI (version|manifest|health
|run). The `run` subcommand explicitly returns "wiring pending
v0.0.1" so the in-process library API is the v0.0.1-clean
integration path.
- tests/smoke.rs (8 tests) + fusion::tests (7 tests, in-lib) — 15
total, all green. Cover stub-backend behaviour, wrong-shape
rejection, fusion math (empty / single / agreement / high-conf
override / normalisation), p95-range correctness, and min-cut
clip semantics.
- cog/{manifest.template.json, config.schema.json, README.md} +
cog/artifacts/ placeholder dir.
* v2/Cargo.toml: registers the new workspace member.
Verified locally:
cargo check -p cog-person-count --no-default-features → clean
cargo test -p cog-person-count --no-default-features → 8/8 pass
cargo test -p cog-person-count --lib → 7/7 pass
cargo build -p cog-person-count --release → 2.36 MB binary
./cog-person-count version → "person-count 0.3.0"
./cog-person-count manifest → JSON skeleton
./cog-person-count health → backend:stub,
count:1, conf:0,
p95:[1,1]
Cold-start: 30 sequential `health` invocations → 53.3 ms/invocation
(vs cog-pose-estimation's 76.2 ms — smaller dep tree)
cog/README.md adds:
* Security section — six-row threat table covering safetensor mmap
trust, non-finite outputs, sensing fetch failures, fusion
divide-by-zero / log-of-zero, min-cut degenerate cases, and stdout
spoofing.
* Performance / optimization section — binary size, release profile
(already opt-level=3 / lto=fat / codegen-units=1 / strip=true at
workspace level), cold-start comparison table, projected warm-path
latency budget.
Still pending (separate PRs, ADR-103 §"Migration"):
* Train count_v1.safetensors on the existing 1,077 paired samples
with `n_persons` labels (Candle on RTX 5080, same script that
produced pose_v1.safetensors yesterday).
* `run` subcommand wiring (long-running polling loop, same shape as
cog-pose-estimation::runtime).
* Cross-compile + sign + GCS upload (mirror of cog-pose-estimation
release pipeline).
* Server-side `csi.rs::score_to_person_count` call-site rewire to
consume this cog when installed; falls back to PR #491's heuristic
when not.
* feat(edge-registry): ADR-102 — surface Cognitum cog catalog via /api/v1/edge/registry
Adds a new sensing-server endpoint that fetches and caches the canonical
Cognitum app registry at
https://storage.googleapis.com/cognitum-apps/app-registry.json (105 cogs
across 11 categories as of v2.1.0). RuView previously had no live
awareness of the catalog — the README's capability table was hand-
curated and went stale as Cognitum shipped new cogs (the registry was
last updated 6 days ago).
ADR:
* docs/adr/ADR-102-edge-module-registry.md — full design, response
shape, configuration flags, failure modes, and a 12-row security
review covering SSRF, response inflation, ?refresh abuse, stale-serve
semantics, TLS, cache poisoning, JSON-panic resistance, etc.
Code:
* v2/.../edge_registry.rs — EdgeRegistry struct + UreqFetcher +
MockFetcher trait + 7 unit tests. RwLock<Option<CachedEntry>> with
stale-on-error fallback. MAX_PAYLOAD_BYTES=8 MiB, 10s wire timeout.
* v2/.../main.rs — constructs Option<Arc<EdgeRegistry>> at startup,
registers GET /api/v1/edge/registry handler, wires Extension layer.
Handler runs the blocking ureq fetch via tokio::task::spawn_blocking
so the async runtime stays free.
* v2/.../cli.rs / main.rs Args — three new flags (per user request to
"allow the registry to be disabled or changed"):
--edge-registry-url <URL> (env RUVIEW_EDGE_REGISTRY_URL)
--edge-registry-ttl-secs <N> (env RUVIEW_EDGE_REGISTRY_TTL_SECS)
--no-edge-registry (env RUVIEW_NO_EDGE_REGISTRY)
When --no-edge-registry is set or the URL is empty, the endpoint
returns 404.
Cargo.toml: adds ureq (rustls), sha2, thiserror as direct deps.
README:
* New collapsed "🧩 Edge Module Catalog" section with the full 105-cog
table generated from the registry, grouped by category with practical
one-line descriptions (e.g. "Spots irregular heartbeats and abnormal
heart rhythms", "Detects walking problems and scores fall risk").
Links to https://seed.cognitum.one/store and the local appliance
/cogs page. Sits between the HF model section and How It Works.
Tests (7/7 pass):
first_call_hits_upstream_and_caches
ttl_expiry_triggers_refetch
force_refresh_bypasses_fresh_cache
stale_serve_on_upstream_failure_after_cached_success
no_cache_no_upstream_returns_error
upstream_invalid_json_is_treated_as_error
upstream_sha256_is_deterministic
Security highlights (full review in ADR-102 §"Security review"):
- The registry is metadata-only; per-cog binary signatures (ADR-100)
remain the trust root for installs. A compromised registry can
mislead a human reader but cannot ship malicious binaries.
- 8 MiB cap + 10s timeout + Option<Arc<...>> via Extension layer means
the endpoint can't be used to exhaust memory or pin tokio threads.
- Stale-on-error responses carry an explicit `stale: true` field so
upstream outages are visible to consumers rather than silently
masked.
- Endpoint sits behind the existing RUVIEW_API_TOKEN bearer gate when
set, otherwise unauthenticated (registry contents are public anyway).
* chore: refresh Cargo.lock for ureq/sha2/thiserror deps added by ADR-102
Issue #640 (PCK gap follow-up) was deleted upstream after the cog v0.0.1
PRs landed today. Re-opened as #645 with the same context plus the
new measured v0.0.1 numbers (PCK@20 3.0%, PCK@50 18.5%, MPJPE 0.093).
This patch updates the three files in main that still pointed at the
dead #640 to point at #645 instead — ADR-101, the cog README, and the
benchmark log.
Adds the x86_64-unknown-linux-gnu binary uploaded to
gs://cognitum-apps/cogs/x86_64/, signed with the same Ed25519
COGNITUM_OWNER_SIGNING_KEY as the arm release. Together with the
already-shipped arm artifact, the cog now ships natively for both
target architectures the Cognitum fleet supports.
x86_64 release:
sha256: a434739a24415b34e1aff50e5e1c3c32e568db96af473bbb3e5ecc9b95fe71fa
signature: pNNuxhgM18PztN8BSZdfw5oAShG2pV3na5T/q2QdlJWX/5FJgo4QTiUCbcTAxI2Uiva8VURSOlRzMU3xoQPqCQ==
size: 4,548,856 bytes
cold-start: 5.4 ms / invocation on ruvultra (RTX 5080, NVMe)
Reorganizes manifests under cog/artifacts/manifests/{arm,x86_64}/
so each arch carries its own manifest with the matching binary_sha256
and signature — same layout the release pipeline will use for the
future hailo8 / hailo10 variants.
Updates docs/benchmarks/pose-estimation-cog.md with the cross-arch
cold-start table:
Windows (x86_64) 76.2 ms
ruvultra (x86_64) 5.4 ms <- this release
Pi 5 (aarch64) 8.4 ms
Verified via anonymous GCS download + SHA round-trip — identical to
local build.
Hailo HEF remains the only pending arch, still blocked on Hailo SDK
provisioning to a self-hosted runner.
* feat(cog-pose-estimation): scaffold first Cog from this repo (ADR-100 + ADR-101)
Adds the foundation for the pose-estimation Cog that ships from this
repo into Cognitum V0 appliances. Companion ADR-225 + crate land in
cognitum-one/v0-appliance.
ADRs:
* ADR-100 formalises the Cognitum Cog packaging spec — on-device
layout under /var/lib/cognitum/apps/<id>/, manifest.json schema
(incl. new binary_sha256 + binary_signature fields), GCS hosting
convention, repo source layout, build pipeline, and the four-verb
runtime contract (version | manifest | health | run). Documents the
convention I reverse-engineered from inspecting installed cogs on a
live cognitum-v0 appliance — `anomaly-detect`, `presence`,
`seizure-detect`, etc.
* ADR-101 designs the pose-estimation Cog itself: where it sits in
the wifi-densepose pipeline (encoder init from
ruvnet/wifi-densepose-pretrained, 17-keypoint regression head),
what gets shipped per target arch (arm / x86_64 / hailo8 /
hailo10), acceptance gates (PCK@20 explicitly deferred to #640 —
this ADR ships the vehicle, not the accuracy).
Crate v2/crates/cog-pose-estimation/:
* Cargo.toml + workspace member declaration with a hailo feature gate
so the binary builds without the Hailo SDK in CI.
* main.rs implements the four-verb CLI exactly per ADR-100.
* config.rs / manifest.rs / publisher.rs / inference.rs / runtime.rs —
small modules, each <100 lines.
* publisher.rs emits ADR-100 structured JSON events.
* inference.rs is a stub that produces a centred-skeleton baseline
with confidence=0 (honest: no trained weights wired in yet).
* runtime.rs subscribes to /api/v1/sensing/latest, slides a
56*20 window, runs the engine, emits pose.frame events.
* cog/manifest.template.json + cog/config.schema.json define the
release artifact + runtime config schemas.
* cog/Makefile holds build / sign / upload targets.
* tests/smoke.rs covers manifest roundtrip + engine I/O surface.
Verified locally:
* cargo check -p cog-pose-estimation: clean.
* cargo test -p cog-pose-estimation: 4/4 pass.
* ./target/release/cog-pose-estimation {version,manifest,health}:
all emit the right contract output.
This commit contains scaffolding only; the actual trained weights and
Hailo HEF cross-compile come in follow-ups tracked in #640 and the
companion v0-appliance branch.
* feat(cog-pose-estimation): first measured run — Candle CUDA on RTX 5080
Trained pose_v1 on ruvultra (RTX 5080) via Candle 0.9 + cuda feature
against the same 1,077-sample paired session that produced 0%/0% PCK
in #640 with the pure-JS SPSA trainer. First real numbers:
PCK@20 = 3.0% (up from 0.0%)
PCK@50 = 18.5% (up from 0.0%)
MPJPE = 0.093 (down from 0.66, ~7x improvement)
400 epochs in 2.1 s wall time, full-batch, ~5 ms/epoch. Loss curve
0.181 -> 0.014 over the run, eval 0.010. Per-joint reveals the model
leans on right-side proximal joints (r_hip 77% PCK@50, r_knee 35%,
l_elbow 26%) — consistent with the camera framing in the source
recording. Distal joints (wrists, ankles) and face joints are still
near-random, consistent with the 56-subcarrier / 20-frame input not
carrying fine-grained spatial info at 1077 samples.
This commit:
* Adds v2/crates/cog-pose-estimation/cog/artifacts/{pose_v1.safetensors,
train_results.json} so the cog dir now contains a real reference
artifact, not just scaffold.
* Updates cog/README.md "Status" block with the measured numbers,
per-joint table, and an honest reading of where the model
succeeds vs where the data is the bottleneck.
* Adds docs/benchmarks/pose-estimation-cog.md as the canonical
benchmark log — append-only, one section per published run.
* Appends a "First measured run" section to ADR-101 referencing
the new benchmark file.
Still pending in the follow-up:
* Wire pose_v1.safetensors into src/inference.rs (replace stub).
* ONNX export (Candle lacks a writer — needs external conversion).
* Hailo HEF cross-compile + cluster deploy.
The data-bound gap to PCK@20 >= 35% is tracked in #640.
* feat(cog-pose-estimation): wire real weights — cog is no longer a stub
Replaces the centred-skeleton stub in src/inference.rs with a real
Candle-based loader that reads cog/artifacts/pose_v1.safetensors and
runs the trained Conv1d encoder + MLP pose head on every incoming CSI
window.
What changes:
* src/inference.rs: PoseNet mirrors the training script's architecture
exactly — Conv1d(56->64, k=3 d=1), Conv1d(64->128, k=3 d=2),
Conv1d(128->128, k=3 d=4), mean over time, Linear(128->256)+ReLU,
Linear(256->34)+sigmoid -> reshape [17, 2]. The InferenceEngine
searches a sensible candidate list for the weights file
(/var/lib/cognitum/apps/pose-estimation/, ./pose_v1.safetensors,
./cog/artifacts/, repo-root, v2/-relative) and falls back to the
stub when none are present so the cog still satisfies ADR-100.
* Cargo.toml: adds candle-core 0.9 + candle-nn 0.9 (no-default-features,
CPU build by default) + safetensors 0.4. New `cuda` feature opt-in
for GPU inference on hosts that have it. Drops the unused
wifi-densepose-train path dep from the default build path.
* src/main.rs + src/publisher.rs: health.ok event now carries
`backend` (candle-cuda | candle-cpu | stub) and the synthetic
output confidence, so operators can tell at a glance whether the
cog loaded its weights or fell back to the stub.
* tests/smoke.rs: adds `real_weights_load_when_available` which
asserts the loaded engine reports backend=candle-* and emits
non-zero confidence — exactly the signal that proves we're not
silently degrading to the stub.
Verified locally:
* `cargo check -p cog-pose-estimation --no-default-features` — clean
* `cargo test -p cog-pose-estimation --no-default-features` — 5/5 pass
* `./target/release/cog-pose-estimation health` emits:
{"event":"health.ok","fields":{"backend":"candle-cpu","cog":"pose-estimation","synthetic_output_confidence":0.185}}
— 0.185 is the published PCK@50 from cog/artifacts/train_results.json,
emitted by the real Candle inference path (would be 0.0 if it had
fallen back to the stub).
The cog now runs the trained pose_v1 model end-to-end. Accuracy is
still bounded by the underlying 1077-sample training data (PCK@20
3.0%, PCK@50 18.5% per docs/benchmarks/pose-estimation-cog.md) — that
gap is data-bound and tracked in #640. ONNX export + Hailo HEF
cross-compile remain follow-ups.
* docs(benchmarks): measure cog-pose-estimation cold-start latency
100 sequential `cog-pose-estimation health` invocations average 76.2 ms
each on a Windows x86_64 host using the `candle-cpu` backend. Each
invocation re-loads pose_v1.safetensors and runs one synthetic forward
pass, so this is the worst-case cold-start path. Long-running `run`
inference will be sub-millisecond per frame once the model is loaded.
Updates the benchmarks doc accordingly.
* feat(cog-pose-estimation): ONNX export — pose_v1.onnx + scripts/export-onnx.py
Adds the canonical ONNX artifact that unblocks downstream Hailo HEF
cross-compile + ONNX Runtime benchmarks. Generated on ruvultra (torch
2.12.0 + CUDA), 12,059 bytes, opset 18, dynamic batch axis.
* scripts/export-onnx.py: mirrors the Candle inference architecture in
PyTorch (Conv1d 56->64, 64->128, 128->128 + Linear 128->256->34), pure-
python safetensors loader (no extra pip dep), exports via
torch.onnx.export, then verifies via onnx.checker.check_model and
numerical parity against the torch reference.
* Verified parity vs torch: max |torch - onnx| = 8.94e-8 (1e-5
threshold). Effectively bit-perfect.
* v2/crates/cog-pose-estimation/cog/artifacts/pose_v1.onnx — the
artifact itself, 12 KB.
* docs/benchmarks/pose-estimation-cog.md — adds an ONNX export
section with the verification numbers.
Next: Hailo HEF cross-compile (still gated on Hailo SDK on a
self-hosted runner) and ONNX Runtime latency benchmarks on each
target arch.
* feat(cog-pose-estimation): release v0.0.1 — signed aarch64 binary on GCS
End-to-end deploy: cross-compiled to aarch64-unknown-linux-gnu on
ruvultra, ran via qemu-aarch64-static, then smoke-tested on a real
cognitum-v0 Pi 5. Signed with COGNITUM_OWNER_SIGNING_KEY (Ed25519)
and uploaded to gs://cognitum-apps/cogs/arm/.
Real-hardware results on cognitum-v0 (Pi 5):
health: backend=candle-cpu, confidence=0.185, real weights loaded
30x sequential `health`: 0.251 s total -> 8.4 ms / invocation (cold)
GCS release artifacts (publicly downloadable):
binary: 3,741,976 bytes
sha256 1e1a7d3dd01ca05d5bfc5dbb142a5941b7866ed9f3224a21edc04d3f09a99bf5
weights: 507,032 bytes
sha256 eb249b9a6b2e10130437a10976ed0230b0d085f86a0553d7226e1ae6eae4b9e5
signature (Ed25519, b64): LUN7xqLPYD3MFzm5dKB5MnYU0LvoRtek5ci5KiKPHBg+Xo6xuazwokn2Dw2JPMaLYJzmWn/SpT4djuR7hYvVDw==
Adds:
* v2/crates/cog-pose-estimation/cog/artifacts/manifest.json — the
release-pipeline-produced manifest with all fields filled in per
ADR-100, including arch, target_triple, signature, and a
build_metadata block carrying the validation PCK numbers.
* docs/benchmarks/pose-estimation-cog.md — new sections covering
the real Pi 5 smoke (8.4 ms cold-start) and the signed GCS
release artifacts.
Verified by downloading the binary anonymously from GCS and
re-computing the sha256 — matches the locally-computed sha exactly.
Signature decoded to the expected 64-byte Ed25519 length.
Closes the GCS-upload acceptance criterion from ADR-100; the only
pending work is Hailo HEF cross-compile (still SDK-gated) and an
x86_64 release alongside this arm release.
* docs(benchmarks): record live cognitum-v0 install + 5-sec smoke run
Adds the "Live appliance install" section documenting what happened
when the signed v0.0.1 binary + weights were installed under
/var/lib/cognitum/apps/pose-estimation/ on cognitum-v0 (the V0
cluster leader).
* Layout matches the existing anomaly-detect / presence / seizure-
detect cogs exactly — the Cogs dashboard at
http://cognitum-v0:9000/cogs auto-discovers entries.
* `cog-pose-estimation run` ran for 5 seconds in the background and
cleanly emitted run.started + structured WARN events for the
missing local sensing-server on :3000 (cognitum-v0's actual CSI
source is ruview-vitals-worker on :50054, not :3000). No crashes,
no NaN, no leaks.
* Wiring `sensing_url` to the appliance-native source is a separate
Day-2 integration task.
#613 fixed adaptive_classifier.rs:94 (the IQR sort) and called the audit
done, but the grep used `partial_cmp(b).unwrap()` as a literal and missed
seven additional production sites that use comparator variants:
adaptive_classifier.rs:205 AdaptiveModel::classify() argmax over softmax
probs — same per-frame hot path as #611.
NaN flows through normalise → logits → softmax
and still reaches this site even after the
IQR fix.
adaptive_classifier.rs:480 train() argmax (training accuracy loop)
adaptive_classifier.rs:500 train() per-class argmax
main.rs:2446, 2449 count_persons_mincut variance source/sink select
csi.rs:602, 605 count_persons_mincut variance source/sink select
(duplicate of main.rs logic in csi.rs)
For the variance-select sites, note that the *outer* `unwrap_or((0, &0))`
only catches an empty iterator — it cannot rescue a panic raised inside
the comparator. A single NaN in `variances[]` still aborts the process.
Same fix as #613: swap `.unwrap()` for `.unwrap_or(std::cmp::Ordering::Equal)`
inside the comparator closure. Pure behavioural change, no API surface.
Re-audit of the remaining `partial_cmp(...).unwrap()` matches in v2/:
they are all inside `#[cfg(test)]` / `#[test]` blocks (spectrogram.rs:269,
depth.rs:234, connectivity.rs:477, vital_signs.rs:737) where inputs are
controlled and panic-on-NaN is acceptable.
Integrating @schwarztim's PR #491 into main on their behalf — their fork has
fallen too far behind for a clean rebase (the PR's commit graph dropped
silently during `git rebase origin/main`), so applying as a merge from the
fork head to preserve the diff cleanly.
What this lands:
- `RollingP95` adaptive normaliser for the person-count feature scaling.
Streaming P95 over a 600-sample / ~30 s sliding window. Cold-start
(<60 samples) falls back to the legacy denominators (variance/300,
motion_band_power/250, spectral_power/500) so day-0 behaviour is
preserved on every deployment.
- `RuntimeConfig` struct + `load_runtime_config` / `save_runtime_config`
persisted to `data/config.json`. Exposes `dedup_factor` via REST so
multi-node deployments can tune cluster-deduplication without a rebuild,
including an auto-tune endpoint that derives optimal dedup from a known
person count (calibration mode).
- `compute_person_score()` now takes &AppStateInner alongside &FeatureInfo
so the adaptive denominators are reachable. All 3 call sites updated.
- New `AppStateInner` fields: `p95_variance`, `p95_motion_band_power`,
`p95_spectral_power`, `dedup_factor`, `data_dir`.
Closes#491. Directly addresses:
- #499 (double skeletons, multi-node) — the slot-clustering problem this
PR's adaptive normaliser was designed to fix
- #519 Bug 1 (ghost person detection on edge-tier 1 & 2 multi-node)
- #496 (person count over-reporting on single-room single-person)
Verified locally:
- cargo check -p wifi-densepose-sensing-server --no-default-features: 1.0s
- cargo test -p wifi-densepose-sensing-server --no-default-features --lib:
233/233 passed in 25.0s
Co-authored-by: @schwarztim
Co-Authored-By: claude-flow <ruv@ruv.net>
Reported by @ArnonEnbar with a complete reproduction.
broadcast_tick_task() re-emits the cached `latest_update` every tick so
pose WS clients keep getting data even when ESP32 pauses between
frames. The `source` field of that cached update was set to "esp32" at
the moment a fresh ESP32 frame was last decoded (main.rs:3885, :4136).
After the ESP32 loses power or network, no fresh frame is decoded —
the cached `latest_update` is still re-broadcast every tick with the
stale source: "esp32" baked in. UI's "Sensing" tab keeps showing
"LIVE — ESP32 HARDWARE Connected" with frozen vitals/features/
classification re-broadcast indefinitely. REST `/health` correctly
reports source: "esp32:offline" (via effective_source(), which checks
last_esp32_frame elapsed time against ESP32_OFFLINE_TIMEOUT=5s) — but
the WS broadcast path was the one consumer that didn't call it.
Fix: clone the cached update per tick, overwrite source with
s.effective_source(), then serialize and broadcast. UI now switches to
"esp32:offline" on the same 5s budget as the REST surface.
cargo build -p wifi-densepose-sensing-server --no-default-features:
17s, no errors (1 pre-existing unused-import warning unchanged).
Reported by @bannned-bit. Five endpoints in
v2/crates/wifi-densepose-sensing-server embedded user-controlled
identifiers in format!() paths with no sanitization:
recording.rs POST /api/v1/recording/start (session_name)
recording.rs GET /api/v1/recording/download/:id (id)
recording.rs DELETE /api/v1/recording/delete/:id (id)
model_manager.rs POST /api/v1/models/load (model_id)
training_api.rs load_recording_frames (dataset_ids[])
Each unauthenticated caller could:
- READ arbitrary files via ../../etc/passwd, ../../.env, etc.
- WRITE attacker-controlled JSONL via recording/start
- LOAD attacker-controlled .rvf model files
- DELETE arbitrary files the server process can touch
New `path_safety` module exports `safe_id(&str) -> Result<&str, PathSafetyError>`
that enforces the rejection envelope BEFORE any user input reaches a
format!() that builds a path:
- Allowed character set: [A-Za-z0-9._-]
- Reject leading '.' (rules out '.', '..', '.env', hidden files)
- Reject empty strings
- Reject anything > 64 bytes
- Reject all whitespace, path separators, null bytes, non-ASCII
Applied at all 5 sites. Errors return 400 Bad Request (download) /
status:"error" JSON (others) — not panics.
9 unit tests in path_safety::tests cover:
- accepts simple alphanumeric / hyphen / underscore / dot
- rejects empty, leading dot, path separators ('/', '\'),
null byte, whitespace, shell specials, non-ASCII (including
fullwidth slash U+FF0F), too-long, boundary at MAX_ID_LEN
test result: ok. 9 passed; 0 failed
cargo build -p wifi-densepose-sensing-server --no-default-features: 33s
Fix-marker RuView#615 in scripts/fix-markers.json prevents removing the
guard at any of the 5 call sites. CHANGELOG entry under [Unreleased] /
Security documents the patched endpoints and the rejection envelope.
Severity: critical per reporter — five remotely-reachable paths to read,
write, or delete arbitrary files. Hot per-request paths, not edge cases.
Reported by @bannned-bit. v2/crates/wifi-densepose-sensing-server/src/
adaptive_classifier.rs:94 did:
sorted.sort_by(|a, b| a.partial_cmp(b).unwrap());
f64::partial_cmp returns None on NaN, so `.unwrap()` panics. CSI data
from real ESP32 hardware can produce NaN (silent DSP div-by-zero,
empty buffer, etc.), and this code path runs on every frame in the
classify() hot path — a single NaN frame kills the entire sensing
server process.
Fix swaps for unwrap_or(Ordering::Equal), matching the pattern the
same file already uses at lines 149-150 and 155 (those sites were
already NaN-safe; this site was an oversight).
Scoped audit: greped the v2/ tree for `partial_cmp(b).unwrap()`. The
other 3 hits are in #[cfg(test)] blocks (spectrogram.rs:269,
depth.rs:234, connectivity.rs:477) where panic-on-NaN is acceptable
because test inputs are controlled. Only adaptive_classifier.rs:94
was a production-path crash.
Severity: critical per reporter — runtime panic on real-world data.
Patch: 1-line behavioural change + comment.
Each of these crates was a single-line doc-comment placeholder:
v2/crates/wifi-densepose-api/src/lib.rs: //! WiFi-DensePose REST API (stub)
v2/crates/wifi-densepose-db/src/lib.rs: //! WiFi-DensePose database layer (stub)
v2/crates/wifi-densepose-config/src/lib.rs: //! WiFi-DensePose configuration (stub)
with empty [dependencies] in their Cargo.toml and zero references from any
source file or Cargo.toml in the workspace (verified by `grep -rln
wifi-densepose-api/-db/-config` across `v2/`). They were reserved early for
an envisioned REST/database/config split that never materialised.
The functionality these would have provided is covered today by:
- REST/WS: wifi-densepose-sensing-server (Axum)
- Config: per-crate config + CLI args in sensing-server and desktop
- DB: no persistent state; system is real-time
Removal prevents `cargo` from listing dead crates, shipping empty published
artifacts to crates.io, or wasting reviewer attention. If any of these names
is needed in the future, reintroduce them with a real implementation.
Per the issue reporter (@bannned-bit / Matad0r) #578 explicitly listed
"OR be removed from workspace members until implementation starts" as an
acceptable resolution.
Updated:
- `v2/Cargo.toml`: drop the three members (with inline comment explaining why)
- `v2/Cargo.lock`: regenerated by cargo check
- `CLAUDE.md`: drop the three rows from the crate table and the publishing
order list
- `CHANGELOG.md`: add an `[Unreleased] / Removed` entry
Verified:
- `cd v2 && cargo check --workspace --no-default-features` -> finished
in 48s, no errors (warnings unchanged)
* v2: pin Rust 1.89 for sensing-server dependency chain
ruvector-core 2.0.5, hnsw_rs 0.3.4, and mmap-rs 0.7 require newer Cargo/rustc
than 1.82 (edition2024 manifest, is_multiple_of, stable avx512f target_feature
on x86_64). Add v2/rust-toolchain.toml so cargo build -p
wifi-densepose-sensing-server picks a compatible toolchain.
Signed-off-by: Chaitanya Tata <chaitanya@dotstarconsulting.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* sensing-server: default UI path for cwd v2/ and coalesce fallbacks
The previous default ../../ui resolves to a non-existent directory when
the binary is run from v2/ (common), so /ui/* returned 404 and the
dashboard appeared broken. Default to ../ui and try ../ui, ./ui,
../../ui when the configured path is missing.
Signed-off-by: Chaitanya Tata <chaitanya@dotstarconsulting.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Signed-off-by: Chaitanya Tata <chaitanya@dotstarconsulting.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
The sensing-server binds to 127.0.0.1 by default with no `Host` header
validation on either router. A foreign page can lower its DNS TTL,
re-resolve to 127.0.0.1 after the browser has accepted the origin, and
then read live pose + vital signs from /api/v1/* + /ws/sensing as
same-origin against the attacker's hostname. When `RUVIEW_API_TOKEN` is
unset (the documented LAN-mode default from #443/#547) the attacker
can also drive state-mutating POSTs (recording/start, models/load,
adaptive/train, calibration/start, sona/activate).
Defense: a small `host_validation` axum middleware that pins the `Host`
header to a configurable allowlist. The loopback names (`localhost`,
`127.0.0.1`, `[::1]`, each with or without a port) are always in the
set, so default 127.0.0.1 deployments keep working from the local
browser without any configuration change. Operators who bind to a
routable address extend the set with one or more `--allowed-host`
flags or a comma-separated `SENSING_ALLOWED_HOSTS` env var.
Reverse-proxy deployments that already canonicalise `Host` opt out
with `--disable-host-validation`.
The layer is wired into both the dedicated WebSocket router on
`--ws-port` (8765) and the main HTTP router on `--http-port` (8080),
so /ws/sensing on either listener is covered. Rejection responses are
`421 Misdirected Request` (the correct status for a request that
arrived at a server that does not consider the supplied `Host`
authoritative); missing `Host` is `400 Bad Request`.
CWE-346 (Origin Validation Error), CWE-350 (Reliance on Reverse DNS).
Severity: high.
Tests: 13 new unit tests on the middleware (loopback defaults,
case-insensitivity, IPv6 bracketing, port stripping, env-var/CLI
merge, foreign-host rejection on /health + /ws/*, disabled-allowlist
escape hatch). Full suite: 220/220 pass under
`cargo test -p wifi-densepose-sensing-server --no-default-features`.
Co-authored-by: Aeon <aeon@aaronjmars.com>
process_frame computed arithmetic mean + variance on phase values from
atan2(), which are wrapped to (-pi, pi]. Phases close across the +/-pi
discontinuity produced ~pi^2 variance instead of ~1e-6, feeding wrap
noise into the heart-rate FFT buffer.
Replace inline math with a standard circular variance helper
(1 - mean resultant length). Add 4 unit tests, one through the
production path of process_frame.
Closes#593
Three threads in this commit:
1) Per-frame attractor analysis (default analyze_every_n: 8 → 1).
The I5 benchmark put per-frame update at 0.012 ms p99 — 83× under D4's
1 ms budget. The cost case for the every-8th-frame default doesn't hold;
per-frame analysis is what makes regime_changed a viable early-detection
trigger.
2) New `regime_changed: bool` field in IntrospectionSnapshot — flips on any
frame whose attractor regime classification differs from the previous
frame's. Pairs with top_k_similarity (full-shape match) to give
downstream consumers two latencies with different robustness profiles.
3) Honest amendment of ADR-099 D8 to reflect empirical reality:
- L1 stand-in achieves 3.20× ratio (5-frame shape match vs 16-frame
event-path floor); the 10× aspirational bar is architecturally
unreachable at 1-D scalar feature resolution.
- regime_changed didn't fire in the 10-frame motion window — the
200-frame noise trajectory dominates the Lyapunov classification, and
short perturbations don't shift the regime fast enough on a scalar
feature.
- Path to 10×: ADR-208 Phase 2 (Hailo NPU vec128 embeddings) — multi-dim
partial matches discriminate from noise in 1-2 frames, not 5.
- Side finding: midstream temporal-compare::DTW uses *discrete equality*
cost (designed for LLM tokens), not numeric distance — swapping it in
for f64 amplitude scoring would be strictly worse than the L1 stand-in.
A numeric DTW is a separate concern (hand-roll or new crate).
- Revised D8: ship behind --introspection (off by default) until multi-
dim features land. Per-frame update budget IS met (0.041 ms p99 in this
bench, ~24× under the 1 ms bar) — the feature is cheap enough to
carry dark today.
cargo test -p wifi-densepose-sensing-server --no-default-features:
introspection (lib): 8 passed, 0 failed
introspection_latency (test): 5 passed, 0 failed (incl. new
regime_change_path_latency)
clippy: clean on the introspection surface (pre-existing approx_constant
lints in pose.rs / main.rs unchanged).
Co-Authored-By: claude-flow <ruv@ruv.net>
I5. Measures the architectural latency floor of the introspection path
vs. the window-aggregated event path, plus the per-frame update cost.
Result on this run:
ADR-099 D8 floor ratio : 3.20× (16 frames / 5 frames)
D8 target ≥10× — NOT YET MET on the host-side
L1 stand-in scoring; I6 closes the gap.
ADR-099 D4 update p50/p99 : 0.001 ms / 0.012 ms (~83× under the 1 ms
budget on a desktop runner; even with thermal
throttling on a Pi 5 we have orders of
magnitude of headroom).
Regime after 200 frames : Idle, lyapunov=-2.32, confidence=1.0
(attractor analyzer is firing as designed).
The D8 gap is structural to the current scoring: signature_score() uses a
length-normalised L1 over the trailing window, which requires roughly the
full signature length of in-shape frames before crossing
promotion_threshold. Closing it is the I6 work — swap in the real
midstreamer-temporal-compare DTW (partial-match scoring) and/or surface
the attractor's regime-change as an *earlier* trigger than full signature
match.
The latency-ratio test asserts a regression bar (≥3.0×) on the L1 baseline,
prints the D8 ratio + whether it's met, and explicitly defers the ≥10×
target to I6 in the docstring. Better empirical reporting than a flag that
silently fails until tuned.
ESP32 sanity (independent of the benchmark): COM7 device alive at csi_collector
cb #84500 (~30 min uptime), len=128/256 HT20/HT40, ch5, RSSI swings -44 to
-79 (= real motion in the room). UDP target still unreachable from this
host per the earlier diagnosis; that's a deployment fix, not a measurement
gate.
Co-Authored-By: claude-flow <ruv@ruv.net>
I3 (per ADR-099). Three changes in main.rs:
1) AppStateInner: + intro: IntrospectionState + intro_tx: broadcast::Sender<String>
(256-slot ring, same shape as the existing tx).
2) ESP32 frame path: after the global frame_history push, before the
per-node mutable borrow of s.node_states, compute the per-frame derived
feature (mean amplitude across subcarriers), call s.intro.update(ts_ns,
feature), and broadcast the snapshot JSON to s.intro_tx. Placement is
deliberate — between the global state's mutable touch and the per-node
&mut so borrow-checking stays linear; ns is borrowed *after* the tap
completes its s.intro / s.intro_tx access.
3) Routes:
ws_introspection_handler → /ws/introspection
api_introspection_snapshot → /api/v1/introspection/snapshot
Same Axum + tokio::sync::broadcast pattern as ws_sensing_handler,
subscribed against s.intro_tx. Wrapped by the bearer-auth middleware
already on /api/v1/* — orchestrator probes and unauthenticated /ws/sensing
reachers continue to land on the existing topic.
Verified:
cargo build -p wifi-densepose-sensing-server --no-default-features ✓
cargo test -p wifi-densepose-sensing-server --no-default-features
lib: 207 passed, 0 failed (199 pre-tap + 8 introspection)
integration suites: 70, 8, 16, 18 passed, 0 failed
cargo clippy: clean on the introspection surface (pre-existing warnings
on -core / -ruvector / -signal unchanged).
Co-Authored-By: claude-flow <ruv@ruv.net>
ruv
OrbisAI Security
Rahul
Winter Lau
dependabot[bot]
Chaitanya Tata
Timothy Schwarz
@aaronjmars
Akhilesh Arora