style(sparse-attn): cargo fmt over crate sources after no_std refactor

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

ADR-183 Tier 1-3 complete: vitals worker + CSI LoRA embedder + CPU en…

…coder path

- Separability ratio 4.515× (target ≥2×): PASS
- p99 embed latency 0.002ms (target <12ms): PASS
- Smoke test 38/38 PASS
- All cluster nodes deployed: cognitum-v0/cluster-1/2/3
- Release: cognitum-one/v0-appliance v0.1.0-csi-lora

ruvllm Pi 5 + Hailo HAT cluster — ADR-179 SOTA

ruvector-hailo backend v0.2.0 (iter 227)

Branch hailo-backend snapshot at iter 227. NPU acceleration is the
production default since iter 163 (~70 embeds/sec/worker, p50=55-57 ms,
9.6× over cpu-fallback on cognitum-v0 / Pi 5 + AI HAT+).

Two arcs of work since v0.1.0-iter156b:

Arc 1 — security/hardening (iters 174-213):
  8-layer DoS gate stack (byte caps, stream cap, RPC timeout,
  CVE-2023-44487, keepalive, batch cap, rate-limit per-item),
  HEF sha256 pin, SEGV-on-shutdown fix, HailoRT FFI 2s timeout,
  retry short-circuit on terminal errors, OOM-bounded operator-path
  file reads, client TLS flag plumbing, fakeworker DoS-gate parity.

Arc 2 — ADR-178 integration gap analysis (iters 215-227):
  EmbeddingProvider impl on both hailo embedders + workspace
  rejoin (Gap B), ruvllm-bridge deploy artifacts (Gap A),
  csi-bridge docs disambiguation (Gap C short-term),
  hailo-cluster-as-provider example (Gap D short-term),
  ADR-167 stale-stratigraphy collapsed (Gap F),
  install-bridge.sh → install-mmwave-bridge.sh rename (Gap H).

Verification:
  cargo build --workspace --release: clean (3m49s)
  cargo check --workspace: clean
  cluster lib + integration tests --features tls: 23 suites green
  hailo lib tests: 21 default + 22 cpu-fallback + 7 tokenizer pass
  cargo deny check on both crates: advisories/bans/licenses/sources ok
  cargo audit --deny warnings (with iter-224 ignores): exit 0
  Pi cognitum-v0 deployed + bit-identical embed verified
    (vec_head=0.0181,-0.0220,0.0451,0.0159 unchanged)

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

perf(hailo): cache + NPU bench — 15.86M embeds/sec on cache hits (ite…

…r 168)

Iter-165 leftover #9 closed. Re-ran cluster-bench against the same
Pi 5 NPU worker, this time exercising the iter-108 LRU cache at the
cluster coordinator:

  cold (unique keys):                 70.2 embeds/sec  p50=56ms
  mixed (keyspace=2048, cache=1024):  74.7 embeds/sec  p50=55ms  hit=5.9%
  hot   (keyspace=32,   cache=1024):  15.86 M emb/sec  p50<1µs   hit=100%

The hot-path 15.86M figure is real — the cluster coordinator returns
already-served vectors in-process without touching the gRPC stack
or the NPU. For repeat-text workloads (RAG over a stable corpus,
ruvllm context prefix sharing, search query autocomplete) this is
the actual throughput an application sees.

Even at 5.9% hit rate (mostly-unique workload) the cache adds a
small ~6% throughput improvement. The operator-facing recommendation
is to enable --cache=N at any deploy where the same texts are
embedded more than once. ADR-176 status table + measurements
section updated with the three-row bench.

Pi worker stopped post-bench; the iter-156b HEF stays at
/var/lib/ruvector-hailo/models/all-minilm-l6-v2/model.hef ready for
the next start.

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

ruvllm-esp32 v0.3.0-rc2 — portable stdio for all 5 variants

ruvllm-esp32 v0.3.0-rc1 — ADR-165+166 (workflow + VFS fixes)

v2.2.0 — Performance batch: delete_edges_batch, zero-copy insert_batc…

…h, FloatArray, has_edge, MicroLoRA persistence

chore: Update attention NAPI-RS binaries for all platforms

  Built from commit 86f671a

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc
  - wasm

  🤖 Generated by GitHub Actions

chore: Update NAPI-RS binaries for all platforms

  Built from commit 84f202f

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc

  🤖 Generated by GitHub Actions