feat: cron jobs — daily summary, speaker clustering, clip purge

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

app/cron/cluster_unknowns.py

@@ -0,0 +1,64 @@
+import sqlite3
+import numpy as np
+from app.shared.config import Settings
+from app.pipeline.recognition import unpack_embedding, cosine_similarity
+
+
+def cluster_unknown_speakers(settings: Settings, db: sqlite3.Connection) -> None:
+    """
+    Groups unknown/ambiguous utterances from the last 7 days by voice similarity.
+    Assigns speaker_id from an existing 'Unknown #N' speaker or creates a new one.
+    Threshold: 0.70 cosine similarity.
+    """
+    CLUSTER_THRESHOLD = 0.70
+
+    rows = db.execute("""
+        SELECT id, embedding FROM utterances
+        WHERE match_status IN ('unknown', 'ambiguous')
+          AND embedding IS NOT NULL
+          AND date(start_time) >= date('now', '-7 days')
+        ORDER BY start_time ASC
+    """).fetchall()
+
+    if not rows:
+        return
+
+    clusters: list = []
+    cluster_centroids: list = []
+
+    for row in rows:
+        emb = unpack_embedding(row["embedding"])
+        best_cluster = None
+        best_sim = 0.0
+        for i, centroid in enumerate(cluster_centroids):
+            sim = cosine_similarity(emb, centroid)
+            if sim > best_sim and sim >= CLUSTER_THRESHOLD:
+                best_sim = sim
+                best_cluster = i
+        if best_cluster is not None:
+            clusters[best_cluster].append(row["id"])
+            n = len(clusters[best_cluster])
+            cluster_centroids[best_cluster] = (
+                (cluster_centroids[best_cluster] * (n - 1) + emb) / n
+            )
+        else:
+            clusters.append([row["id"]])
+            cluster_centroids.append(emb)
+
+    for i, cluster in enumerate(clusters):
+        if len(cluster) < 2:
+            continue
+        name = f"Unknown #{i + 1}"
+        existing = db.execute("SELECT id FROM speakers WHERE name=?", (name,)).fetchone()
+        if existing:
+            speaker_id = existing["id"]
+        else:
+            cur = db.execute("INSERT INTO speakers (name) VALUES (?)", (name,))
+            db.commit()
+            speaker_id = cur.lastrowid
+        for utt_id in cluster:
+            db.execute(
+                "UPDATE utterances SET speaker_id=?, match_status='ambiguous' WHERE id=?",
+                (speaker_id, utt_id),
+            )
+    db.commit()