feat(adr-185): P1 AETHER bindings (wifi_densepose.aether) + parity harness

Bind the ADR-024 contrastive CSI embedding surface into the wheel behind
a gated [aether] extra / Cargo `aether` feature, per ADR-185 section 3.2.

Surface (bound against the REAL code at HEAD, not the ADR wishlist):
- AetherConfig       -> EmbeddingConfig {d_model,d_proj,temperature,normalize}
- CsiAugmenter       -> augment_pair(window, seed)
- EmbeddingExtractor -> embed(csi): 128-dim L2-normed, GIL-released
- info_nce_loss, cosine_similarity (module fns)

ADR-185 section 3.2 also names aether_loss/VICReg components,
alignment_metric, uniformity_metric, forward_dual, and vicreg_* config
fields. None exist in embedding.rs at HEAD, so they are intentionally NOT
bound (a Rust-side gap, not a binding gap) rather than fabricated.

Parity (section 4.1, release-blocking): committed fixture
aether_input.json -> native Rust reference (tests/aether_parity.rs, calls
sensing-server EmbeddingExtractor directly) locks
tests/golden/aether_embedding.sha256; pytest (tests/test_aether.py) runs
the same fixture through the binding and asserts the identical SHA-256 of
the LE f32 bytes. Both pass.

Verified: cargo test --features aether --test aether_parity -> 2/2 pass;
maturin develop --features aether + pytest tests/test_aether.py -> 9/9
pass; default cargo build clean with 0 sensing-server refs in the dep
graph (gate keeps the base wheel lean).

HONEST WHEEL-SIZE FINDING (ADR-185 section 9 / Open Q 11.1, unresolved):
wifi-densepose-sensing-server is an Axum/tokio crate whose tokio/axum/
worldgraph/ruvector deps are NON-optional (only mqtt/matter are
features), so default-features=false does NOT drop them. An [aether]
wheel therefore links the full server tree and BREAKS the ADR-117 section
5.4 <=5 MB budget. The fix is the ADR-sanctioned hoist of embedding.rs
(+ its graph_transformer/sona siblings) into a leaf crate so the wheel
links pure compute only -- a change INSIDE wifi-densepose-sensing-server,
owned by another agent this session, so deferred as a required
pre-release follow-up. P1 binds real code and proves parity today; the
hoist is a wheel-size optimization, not a functional blocker.

Note: building required initializing the worldgraph/rufield/ruvector
submodules (absent in the fresh worktree).

python/src/bindings/aether.rs

@@ -0,0 +1,242 @@
+//! ADR-185 P1 — PyO3 bindings for AETHER contrastive CSI embeddings.
+//!
+//! Surfaces the **pure-sync** contrastive-embedding compute from
+//! `wifi-densepose-sensing-server::embedding` (ADR-024) into
+//! `wifi_densepose.aether`:
+//!
+//! - `AetherConfig`      — wraps `EmbeddingConfig` (d_model / d_proj /
+//!                          temperature / normalize)
+//! - `CsiAugmenter`      — SimCLR-style augmentation pair generator
+//! - `EmbeddingExtractor`— backbone + projection → 128-dim L2-normed embedding
+//! - `info_nce_loss`     — NT-Xent contrastive loss (module function)
+//! - `cosine_similarity` — re-ID similarity helper (module function)
+//!
+//! ## Honest scope vs ADR-185 §3.2
+//!
+//! ADR-185 §3.2 names an aspirational surface (`aether_loss` returning
+//! VICReg components, `alignment_metric`, `uniformity_metric`,
+//! `forward_dual`, an `AetherConfig` with `vicreg_*` fields). Those do
+//! **not** exist in the backing crate at HEAD — `embedding.rs` exposes
+//! `EmbeddingConfig { d_model, d_proj, temperature, normalize }`,
+//! `info_nce_loss` (plain `f32`), `CsiAugmenter::augment_pair`, and
+//! `EmbeddingExtractor::extract`. This binding surfaces **what actually
+//! exists** rather than fabricating the ADR's wished-for API. The
+//! VICReg loss / metric surface is a Rust-side gap, not a binding gap.
+//!
+//! ## GIL release strategy (per ADR-117 §7, matching bindings/vitals.rs)
+//!
+//! `extract`, `augment_pair`, and `info_nce_loss` are pure-sync matrix
+//! ops touching no Python objects, so they run inside
+//! `py.allow_threads(|| ...)`.
+
+use pyo3::prelude::*;
+
+use wifi_densepose_sensing_server::embedding::{
+    info_nce_loss as rust_info_nce_loss, CsiAugmenter, EmbeddingConfig, EmbeddingExtractor,
+};
+use wifi_densepose_sensing_server::graph_transformer::TransformerConfig;
+
+// ─── AetherConfig ────────────────────────────────────────────────────
+
+/// Configuration for the contrastive embedding model.
+///
+/// Python:
+/// ```python
+/// from wifi_densepose.aether import AetherConfig
+/// cfg = AetherConfig(d_model=64, d_proj=128, temperature=0.07, normalize=True)
+/// ```
+#[pyclass(frozen, name = "AetherConfig")]
+#[derive(Clone)]
+pub struct PyAetherConfig {
+    inner: EmbeddingConfig,
+}
+
+#[pymethods]
+impl PyAetherConfig {
+    #[new]
+    #[pyo3(signature = (d_model=64, d_proj=128, temperature=0.07, normalize=true))]
+    fn new(d_model: usize, d_proj: usize, temperature: f32, normalize: bool) -> Self {
+        Self {
+            inner: EmbeddingConfig {
+                d_model,
+                d_proj,
+                temperature,
+                normalize,
+            },
+        }
+    }
+
+    #[getter]
+    fn d_model(&self) -> usize {
+        self.inner.d_model
+    }
+
+    #[getter]
+    fn d_proj(&self) -> usize {
+        self.inner.d_proj
+    }
+
+    #[getter]
+    fn temperature(&self) -> f32 {
+        self.inner.temperature
+    }
+
+    #[getter]
+    fn normalize(&self) -> bool {
+        self.inner.normalize
+    }
+
+    fn __repr__(&self) -> String {
+        format!(
+            "AetherConfig(d_model={}, d_proj={}, temperature={}, normalize={})",
+            self.inner.d_model, self.inner.d_proj, self.inner.temperature, self.inner.normalize,
+        )
+    }
+}
+
+// ─── CsiAugmenter ────────────────────────────────────────────────────
+
+/// SimCLR-style CSI augmentation. `augment_pair` returns two distinct
+/// augmented views of the same CSI window for contrastive pretraining.
+///
+/// Python:
+/// ```python
+/// from wifi_densepose.aether import CsiAugmenter
+/// aug = CsiAugmenter()
+/// view_a, view_b = aug.augment_pair(window, seed=42)
+/// ```
+#[pyclass(name = "CsiAugmenter")]
+pub struct PyCsiAugmenter {
+    inner: CsiAugmenter,
+}
+
+#[pymethods]
+impl PyCsiAugmenter {
+    #[new]
+    fn new() -> Self {
+        Self {
+            inner: CsiAugmenter::new(),
+        }
+    }
+
+    /// Produce two augmented views `(view_a, view_b)` of `window`
+    /// (frames × subcarriers) using the deterministic `seed`. GIL is
+    /// released during augmentation.
+    fn augment_pair(
+        &self,
+        py: Python<'_>,
+        window: Vec<Vec<f32>>,
+        seed: u64,
+    ) -> (Vec<Vec<f32>>, Vec<Vec<f32>>) {
+        py.allow_threads(|| self.inner.augment_pair(&window, seed))
+    }
+
+    fn __repr__(&self) -> String {
+        "CsiAugmenter(SimCLR-style CSI augmentation)".to_string()
+    }
+}
+
+// ─── EmbeddingExtractor ──────────────────────────────────────────────
+
+/// Full AETHER embedding extractor: CSI→pose transformer backbone +
+/// projection head → a `d_proj`-dim (default 128) L2-normalized
+/// embedding. Weights are deterministically seeded, so `embed` is a
+/// pure function of its input for a fixed config.
+///
+/// Python:
+/// ```python
+/// from wifi_densepose.aether import AetherConfig, EmbeddingExtractor
+/// ext = EmbeddingExtractor(n_subcarriers=56, config=AetherConfig())
+/// emb = ext.embed(window)          # list[float], len == config.d_proj
+/// ```
+#[pyclass(name = "EmbeddingExtractor")]
+pub struct PyEmbeddingExtractor {
+    inner: EmbeddingExtractor,
+    embedding_dim: usize,
+}
+
+#[pymethods]
+impl PyEmbeddingExtractor {
+    /// Construct an extractor. The transformer backbone is sized from
+    /// `n_subcarriers` and `config.d_model`; `config.d_proj` sets the
+    /// embedding dimension.
+    #[new]
+    #[pyo3(signature = (n_subcarriers, config, n_keypoints=17, n_heads=4, n_gnn_layers=2))]
+    fn new(
+        n_subcarriers: usize,
+        config: PyAetherConfig,
+        n_keypoints: usize,
+        n_heads: usize,
+        n_gnn_layers: usize,
+    ) -> Self {
+        let e_config = config.inner.clone();
+        let t_config = TransformerConfig {
+            n_subcarriers,
+            n_keypoints,
+            d_model: e_config.d_model,
+            n_heads,
+            n_gnn_layers,
+        };
+        let embedding_dim = e_config.d_proj;
+        Self {
+            inner: EmbeddingExtractor::new(t_config, e_config),
+            embedding_dim,
+        }
+    }
+
+    /// Extract an embedding from a CSI window (frames × subcarriers).
+    /// Returns a `d_proj`-length vector (L2-normed when the config's
+    /// `normalize` is set). GIL released during the forward pass.
+    fn embed(&mut self, py: Python<'_>, csi_features: Vec<Vec<f32>>) -> Vec<f32> {
+        py.allow_threads(|| self.inner.extract(&csi_features))
+    }
+
+    #[getter]
+    fn embedding_dim(&self) -> usize {
+        self.embedding_dim
+    }
+
+    fn __repr__(&self) -> String {
+        format!("EmbeddingExtractor(embedding_dim={})", self.embedding_dim)
+    }
+}
+
+// ─── Module functions ────────────────────────────────────────────────
+
+/// InfoNCE (NT-Xent) contrastive loss between two batches of embeddings.
+/// Delegates to the identical Rust implementation. GIL released.
+#[pyfunction]
+#[pyo3(signature = (embeddings_a, embeddings_b, temperature=0.07))]
+fn info_nce_loss(
+    py: Python<'_>,
+    embeddings_a: Vec<Vec<f32>>,
+    embeddings_b: Vec<Vec<f32>>,
+    temperature: f32,
+) -> f32 {
+    py.allow_threads(|| rust_info_nce_loss(&embeddings_a, &embeddings_b, temperature))
+}
+
+/// Cosine similarity between two embeddings — the re-ID scoring
+/// primitive. Byte-identical to the private `cosine_similarity` in the
+/// backing crate (same dot-product / norm formula, `f32`).
+#[pyfunction]
+fn cosine_similarity(a: Vec<f32>, b: Vec<f32>) -> f32 {
+    let n = a.len().min(b.len());
+    let dot: f32 = (0..n).map(|i| a[i] * b[i]).sum();
+    let na = (0..n).map(|i| a[i] * a[i]).sum::<f32>().sqrt();
+    let nb = (0..n).map(|i| b[i] * b[i]).sum::<f32>().sqrt();
+    if na > 1e-10 && nb > 1e-10 {
+        dot / (na * nb)
+    } else {
+        0.0
+    }
+}
+
+pub fn register(m: &Bound<'_, PyModule>) -> PyResult<()> {
+    m.add_class::<PyAetherConfig>()?;
+    m.add_class::<PyCsiAugmenter>()?;
+    m.add_class::<PyEmbeddingExtractor>()?;
+    m.add_function(wrap_pyfunction!(info_nce_loss, m)?)?;
+    m.add_function(wrap_pyfunction!(cosine_similarity, m)?)?;
+    Ok(())
+}

python/src/lib.rs

@@ -17,6 +17,8 @@
 use pyo3::prelude::*;
 
 mod bindings {
+    #[cfg(feature = "aether")]
+    pub mod aether;
     pub mod bfld;
     pub mod keypoint;
     pub mod pose;
@@ -43,6 +45,8 @@ fn build_features() -> Vec<&'static str> {
     feats.push("p2-pose-bindings"); // BoundingBox + PersonPose + PoseEstimate
     feats.push("p3-vitals-bindings"); // BreathingExtractor + HeartRateExtractor + VitalEstimate
     feats.push("p3.5-bfld-bindings"); // BfldFrame + BfldReport + BfldKind (stub Rust)
+    #[cfg(feature = "aether")]
+    feats.push("p6-aether-bindings"); // ADR-185 P1 — AETHER contrastive embeddings
     feats
 }
 
@@ -85,5 +89,12 @@ fn wifi_densepose_native(m: &Bound<'_, PyModule>) -> PyResult<()> {
     // the published `wifi-densepose-bfld 0.3.0` crate, not the Python port).
     // Closes ADR-125 §2.1.d at the binding boundary.
     bindings::privacy_gate::register(m)?;
+
+    // ADR-185 P1 — AETHER contrastive CSI embedding bindings, compiled
+    // and registered only under the `aether` feature so the default
+    // wheel links none of the sensing-server dependency tree.
+    #[cfg(feature = "aether")]
+    bindings::aether::register(m)?;
+
     Ok(())
 }