mirror of https://github.com/ruvnet/RuView synced 2026-06-09 10:13:17 +00:00

Files

T

ruv 8ff7c2c35a feat(plugins): RuView Claude Code + Codex marketplace plugin

Add `plugins/ruview` — an end-to-end toolkit for working with RuView
(WiFi-DensePose) from Claude Code, mirrored as Codex prompts.

Marketplace: `plugins/.claude-plugin/marketplace.json` (one plugin, `ruview`).

Skills (9): ruview-quickstart, ruview-hardware-setup, ruview-configure,
ruview-applications, ruview-model-training, ruview-advanced-sensing,
ruview-cli-api, ruview-mmwave, ruview-verify — shell-first (cargo / python /
idf.py / docker / node), no claude-flow MCP dependency.

Commands (7): /ruview-start, /ruview-flash, /ruview-provision, /ruview-app,
/ruview-train, /ruview-advanced, /ruview-verify.

Agents (3): ruview-onboarding-guide, ruview-config-engineer,
ruview-training-engineer.

Codex mirror: codex/AGENTS.md + codex/README.md + codex/prompts/*.md (full
command parity, enforced by scripts/smoke.sh).

Docs: docs/adrs/0001-ruview-plugin-contract.md (Proposed). Verification:
scripts/smoke.sh (13 structural checks). Provisioning docs reflect the full
`provision.py` flag set (TDM mesh, edge tiers, vitals, hop channels, Cognitum
Seed, swarm intervals) and the issue #391 NVS-namespace-replace gotcha.

Verified: `claude plugin validate` (plugin + marketplace), loads via
`claude --plugin-dir`, smoke 13/13, and confirmed against an attached ESP32-S3
on COM8 running the RuView CSI firmware (live adaptive_ctrl + csi_collector
serial output).

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

2026-05-11 17:39:16 -04:00

1.7 KiB

Raw Blame History

description, argument-hint

description	argument-hint
Train a RuView model — camera-free WiFlow pose, camera-supervised pose (92.9% PCK@20), RuVector embeddings, domain generalization, local SNN, with optional GPU on GCloud.	[camera-free\|camera-supervised\|embeddings\|domain-gen\|snn\|gpu] [--epochs N]

/ruview-train

Train, fine-tune, evaluate, or publish a RuView model.

Invoke the ruview-model-training skill.
Pick the track from $ARGUMENTS; if empty, ask which:
- camera-free (Track A) — cargo run -p wifi-densepose-sensing-server -- --pretrain --dataset data/csi/ --pretrain-epochs 50 then -- --train --dataset data/mmfi/ --epochs 100 --save-rvf model.rvf. ~84 s on M4 Pro, modest accuracy.
- camera-supervised (Track B, ADR-079) — python scripts/collect-ground-truth.py, python scripts/collect-training-data.py, node scripts/align-ground-truth.js, then train on data/paired/, eval with node scripts/eval-wiflow.js. ~19 min, 92.9% PCK@20. Needs data/pose_landmarker_lite.task.
- embeddings (Track C, AETHER ADR-024) — wifi-densepose-train + wifi-densepose-ruvector; -- --model model.rvf --embed, -- --build-index env.
- domain-gen (Track D, MERIDIAN ADR-027) / snn (Track E) — node scripts/snn-csi-processor.js --port 5006; cognitum-seed-pretraining tutorial.
- gpu — gcloud config set project cognitum-20260110; bash scripts/gcloud-train.sh --gpu l4 --hours 2 (or --gpu a100 --sweep, --dry-run to smoke-test). VM auto-deletes unless --keep-vm.
After training: cd v2 && cargo test --workspace --no-default-features, python archive/v1/data/proof/verify.py. To publish: python scripts/publish-huggingface.py.
Hand off to /ruview-verify for the witness bundle.

1.7 KiB Raw Blame History

/ruview-train

1.7 KiB

Raw Blame History