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()

app/cron/daily_summary.py

@@ -0,0 +1,48 @@
+import sqlite3
+import httpx
+from app.shared.config import Settings
+
+
+def generate_daily_summary(date: str, settings: Settings, db: sqlite3.Connection) -> None:
+    rows = db.execute("""
+        SELECT u.start_time, u.transcript, r.name as room_name, s.name as speaker_name
+        FROM utterances u
+        JOIN rooms r ON u.room_id = r.id
+        LEFT JOIN speakers s ON u.speaker_id = s.id
+        WHERE date(u.start_time) = ?
+        ORDER BY u.start_time ASC
+    """, (date,)).fetchall()
+
+    if not rows:
+        return
+
+    lines = [
+        f"[{r['room_name']} {r['start_time']}] {r['speaker_name'] or 'Unknown'}: {r['transcript']}"
+        for r in rows
+    ]
+    context = "\n".join(lines)
+
+    prompt = (
+        f"Summarize the following household conversations from {date} in 2-4 sentences. "
+        f"Focus on key decisions, activities, and topics discussed. Do not transcribe verbatim.\n\n"
+        f"{context}"
+    )
+
+    resp = httpx.post(
+        f"{settings.ollama_url}/api/chat",
+        json={
+            "model": settings.ollama_model,
+            "messages": [{"role": "user", "content": prompt}],
+            "stream": False,
+        },
+        timeout=120.0,
+    )
+    resp.raise_for_status()
+    summary = resp.json()["message"]["content"]
+
+    db.execute(
+        "INSERT INTO daily_summaries (date, summary_text) VALUES (?,?) "
+        "ON CONFLICT(date) DO UPDATE SET summary_text=?, generated_at=CURRENT_TIMESTAMP",
+        (date, summary, summary),
+    )
+    db.commit()

app/cron/main.py

@@ -0,0 +1,35 @@
+import time
+from datetime import datetime, timezone, timedelta
+
+from app.shared.config import get_settings
+from app.shared.database import get_db, init_schema
+from app.cron.daily_summary import generate_daily_summary
+from app.cron.cluster_unknowns import cluster_unknown_speakers
+from app.cron.purge_clips import purge_old_clips
+
+
+def run_nightly(settings, db):
+    yesterday = (datetime.now(timezone.utc) - timedelta(days=1)).strftime("%Y-%m-%d")
+    today = datetime.now(timezone.utc).strftime("%Y-%m-%d")
+    generate_daily_summary(yesterday, settings, db)
+    cluster_unknown_speakers(settings, db)
+    purge_old_clips(today, settings, db)
+
+
+def main():
+    settings = get_settings()
+    init_schema(settings)
+    db = get_db(settings)
+
+    while True:
+        now = datetime.now(timezone.utc)
+        next_midnight = now.replace(hour=0, minute=0, second=0, microsecond=0)
+        if next_midnight <= now:
+            next_midnight += timedelta(days=1)
+        sleep_secs = (next_midnight - now).total_seconds()
+        time.sleep(sleep_secs)
+        run_nightly(settings, db)
+
+
+if __name__ == "__main__":
+    main()

app/cron/purge_clips.py

@@ -0,0 +1,31 @@
+import sqlite3
+from datetime import datetime, timedelta
+from pathlib import Path
+from app.shared.config import Settings
+
+
+def purge_old_clips(today: str, settings: Settings, db: sqlite3.Connection) -> None:
+    cutoff = datetime.strptime(today, "%Y-%m-%d") - timedelta(days=settings.clip_retention_days)
+    clips_root = Path(settings.clips_dir)
+    if not clips_root.exists():
+        return
+    for date_dir in clips_root.iterdir():
+        if not date_dir.is_dir():
+            continue
+        try:
+            dir_date = datetime.strptime(date_dir.name, "%Y-%m-%d")
+        except ValueError:
+            continue
+        if dir_date < cutoff:
+            for wav in date_dir.glob("*.wav"):
+                wav.unlink()
+            try:
+                date_dir.rmdir()
+            except OSError:
+                pass
+    cutoff_str = cutoff.strftime("%Y-%m-%d")
+    db.execute(
+        "UPDATE utterances SET audio_clip_path=NULL WHERE date(start_time) < ?",
+        (cutoff_str,),
+    )
+    db.commit()

tests/test_cron.py

@@ -0,0 +1,71 @@
+import pytest
+import os
+from datetime import datetime, timezone
+from pathlib import Path
+from unittest.mock import MagicMock
+
+
+def _seed_utterances(db, room_id, count=3):
+    for i in range(count):
+        db.execute(
+            "INSERT INTO utterances (room_id, transcript, match_status, start_time, end_time) VALUES (?,?,?,?,?)",
+            (room_id, f"utterance {i}", "unknown",
+             "2026-05-27 10:00:00", "2026-05-27 10:00:03"),
+        )
+    db.commit()
+
+
+def test_daily_summary_inserts_row(mocker, settings, db):
+    db.execute("INSERT INTO rooms (name) VALUES (?)", ("Kitchen",))
+    db.commit()
+    room = db.execute("SELECT id FROM rooms WHERE name='Kitchen'").fetchone()
+    _seed_utterances(db, room["id"])
+
+    mock_post = mocker.patch("app.cron.daily_summary.httpx.post")
+    mock_post.return_value.json.return_value = {"message": {"content": "Busy day."}}
+    mock_post.return_value.raise_for_status = MagicMock()
+
+    from app.cron.daily_summary import generate_daily_summary
+    generate_daily_summary("2026-05-27", settings, db)
+
+    row = db.execute("SELECT * FROM daily_summaries WHERE date='2026-05-27'").fetchone()
+    assert row is not None
+    assert row["summary_text"] == "Busy day."
+
+
+def test_daily_summary_skips_if_no_utterances(mocker, settings, db):
+    mock_post = mocker.patch("app.cron.daily_summary.httpx.post")
+    from app.cron.daily_summary import generate_daily_summary
+    generate_daily_summary("2026-05-27", settings, db)
+    mock_post.assert_not_called()
+
+
+def test_purge_clips_deletes_old_files(settings, db, tmp_path):
+    from app.cron.purge_clips import purge_old_clips
+
+    clips_dir = tmp_path / "clips"
+    old_dir = clips_dir / "2026-04-01"
+    old_dir.mkdir(parents=True)
+    old_file = old_dir / "1.wav"
+    old_file.write_bytes(b"\x00" * 100)
+
+    new_dir = clips_dir / "2026-05-27"
+    new_dir.mkdir(parents=True)
+    new_file = new_dir / "2.wav"
+    new_file.write_bytes(b"\x00" * 100)
+
+    # Create a settings with clips_dir pointing to tmp
+    from app.shared.config import Settings
+    settings_override = Settings(
+        db_path=settings.db_path,
+        clips_dir=str(clips_dir),
+        clip_retention_days=30,
+        speaches_url=settings.speaches_url,
+        ollama_url=settings.ollama_url,
+        livekit_api_key=settings.livekit_api_key,
+        livekit_api_secret=settings.livekit_api_secret,
+    )
+
+    purge_old_clips("2026-05-28", settings_override, db)
+    assert not old_file.exists()
+    assert new_file.exists()