"""
Face embedding clustering using DBSCAN with cosine distance.

Called by the periodic `recluster_faces` Celery task (PR7).
"""
import logging

import numpy as np
from sklearn.cluster import DBSCAN

logger = logging.getLogger(__name__)


def cluster_faces(
    embeddings: np.ndarray,
    eps: float = 0.35,
    min_samples: int = 2,
) -> np.ndarray:
    """Cluster face embeddings using DBSCAN with cosine metric.

    Args:
        embeddings: (N, D) float32 array of L2-normalized face embeddings.
        eps: Maximum cosine distance between two samples to be in the
             same neighborhood. Lower = tighter clusters.
        min_samples: Minimum cluster size.

    Returns:
        (N,) int array of cluster labels. -1 = noise / unclustered.
    """
    if len(embeddings) < min_samples:
        return np.full(len(embeddings), -1, dtype=int)

    db = DBSCAN(eps=eps, min_samples=min_samples, metric="cosine")
    labels = db.fit_predict(embeddings)

    n_clusters = len(set(labels) - {-1})
    n_noise = (labels == -1).sum()
    logger.info(
        "Face clustering: %d embeddings → %d clusters, %d noise",
        len(embeddings), n_clusters, n_noise,
    )
    return labels