Files

rUv 9bbe95648c feat: ADR-024 Contrastive CSI Embedding Model — all 7 phases (#52 )

Full implementation of Project AETHER — Contrastive CSI Embedding Model.

## Phases Delivered
1. ProjectionHead (64→128→128) + L2 normalization
2. CsiAugmenter (5 physically-motivated augmentations)
3. InfoNCE contrastive loss + SimCLR pretraining
4. FingerprintIndex (4 index types: env, activity, temporal, person)
5. RVF SEG_EMBED (0x0C) + CLI integration
6. Cross-modal alignment (PoseEncoder + InfoNCE)
7. Deep RuVector: MicroLoRA, EWC++, drift detection, hard-negative mining, SEG_LORA

## Stats
- 276 tests passing (191 lib + 51 bin + 16 rvf + 18 vitals)
- 3,342 additions across 8 files
- Zero unsafe/unwrap/panic/todo stubs
- ~55KB INT8 model for ESP32 edge deployment

Also fixes deprecated GitHub Actions (v3→v4) and adds feat/* branch CI triggers.

Closes #50

2026-03-01 01:44:38 -05:00

3.6 KiB

Raw Blame History

wifi-densepose-db

Database persistence layer for the WiFi-DensePose pose estimation system.

Overview

wifi-densepose-db implements the DataStore trait defined in wifi-densepose-core, providing persistent storage for CSI frames, pose estimates, scan sessions, and alert history. The intended backends are SQLx for relational storage (PostgreSQL and SQLite) and Redis for real-time caching and pub/sub.

Status: This crate is currently a stub. The intended API surface is documented below.

Planned Features

Dual backend -- PostgreSQL for production deployments, SQLite for single-node and embedded use. Selectable at compile time via feature flags.
Redis caching -- Connection-pooled Redis for low-latency pose estimate lookups, session state, and pub/sub event distribution.
Migrations -- Embedded SQL migrations managed by SQLx, applied automatically on startup.
Repository pattern -- Typed repository structs (PoseRepository, SessionRepository, AlertRepository) implementing the core DataStore trait.
Connection pooling -- Configurable pool sizes via sqlx::PgPool / sqlx::SqlitePool.
Transaction support -- Scoped transactions for multi-table writes (e.g., survivor detection plus alert creation).
Time-series optimisation -- Partitioned tables and retention policies for high-frequency CSI frame storage.

Planned feature flags

Flag	Default	Description
`postgres`	no	Enable PostgreSQL backend
`sqlite`	yes	Enable SQLite backend
`redis`	no	Enable Redis caching layer

Quick Start

// Intended usage (not yet implemented)
use wifi_densepose_db::{Database, PoseRepository};
use wifi_densepose_core::PoseEstimate;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    let db = Database::connect("sqlite://data/wifi-densepose.db").await?;
    db.run_migrations().await?;

    let repo = PoseRepository::new(db.pool());

    // Store a pose estimate
    repo.insert(&pose_estimate).await?;

    // Query recent poses
    let recent = repo.find_recent(10).await?;
    println!("Last 10 poses: {:?}", recent);

    Ok(())
}

Planned Schema

-- Core tables
CREATE TABLE csi_frames (
    id          UUID PRIMARY KEY,
    session_id  UUID NOT NULL,
    timestamp   TIMESTAMPTZ NOT NULL,
    subcarriers BYTEA NOT NULL,
    antenna_id  INTEGER NOT NULL
);

CREATE TABLE pose_estimates (
    id          UUID PRIMARY KEY,
    frame_id    UUID REFERENCES csi_frames(id),
    timestamp   TIMESTAMPTZ NOT NULL,
    keypoints   JSONB NOT NULL,
    confidence  REAL NOT NULL
);

CREATE TABLE scan_sessions (
    id          UUID PRIMARY KEY,
    started_at  TIMESTAMPTZ NOT NULL,
    ended_at    TIMESTAMPTZ,
    config      JSONB NOT NULL
);

Crate	Role
`wifi-densepose-core`	`DataStore` trait definition
`wifi-densepose-config`	Database connection configuration
`wifi-densepose-api`	REST API (consumer)
`wifi-densepose-mat`	Disaster detection (consumer)
`wifi-densepose-signal`	CSI signal processing

License

MIT OR Apache-2.0

3.6 KiB Raw Blame History