feat: frigate-notify v2 (modular app, CLIP recognition) + clip-service

Splits the single main.py into config/database/models/routes/vision/recognition/
ollama_client/cleanup modules, adds a web UI, and introduces clip-service for
CLIP (ViT-L-14) embeddings.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

compose/hf-pdocker-01/clip-service/docker-compose.yml

@@ -0,0 +1,19 @@
+services:
+  clip-service:
+    image: clip-service:latest
+    container_name: clip-service
+    restart: unless-stopped
+    network_mode: host
+    mem_limit: 3G
+    memswap_limit: 3G
+    healthcheck:
+      test: ["CMD-SHELL", "curl -sf http://localhost:5200/health || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 180s
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"

compose/hf-pdocker-01/frigate-notify/Dockerfile

@@ -9,6 +9,8 @@ RUN pip install --no-cache-dir -r requirements.txt
 
 COPY app/ .
 
+RUN mkdir -p /data
+
 EXPOSE 5199
 
 CMD ["python", "-u", "main.py"]

compose/hf-pdocker-01/frigate-notify/app/cleanup.py

@@ -0,0 +1,35 @@
+"""Automatic event cleanup based on retention settings."""
+
+import asyncio
+import logging
+
+from database import get_connection
+
+logger = logging.getLogger(__name__)
+
+
+async def cleanup_old_events():
+    """Delete events older than the configured retention period. Runs hourly."""
+    while True:
+        try:
+            conn = get_connection()
+            row = conn.execute(
+                "SELECT value FROM settings WHERE key='event_retention_days'"
+            ).fetchone()
+            days = int(row["value"]) if row else 90
+
+            result = conn.execute(
+                "DELETE FROM events WHERE created_at < datetime('now', ? || ' days')",
+                (f"-{days}",),
+            )
+            conn.commit()
+            if result.rowcount > 0:
+                logger.info(
+                    "Cleaned up %d events older than %d days",
+                    result.rowcount,
+                    days,
+                )
+        except Exception:
+            logger.exception("Cleanup failed")
+
+        await asyncio.sleep(3600)

compose/hf-pdocker-01/frigate-notify/app/config.py

@@ -0,0 +1,56 @@
+"""Centralized configuration for frigate-notify v2."""
+
+import os
+
+
+class Config:
+    """Application configuration read from environment variables."""
+
+    # MQTT
+    MQTT_HOST: str = os.environ.get("MQTT_HOST", "192.168.86.192")
+    MQTT_PORT: int = int(os.environ.get("MQTT_PORT", "1883"))
+
+    # Frigate
+    FRIGATE_URL: str = os.environ.get("FRIGATE_URL", "http://192.168.86.192:5000")
+
+    # Matrix
+    MATRIX_HOMESERVER: str = os.environ.get(
+        "MATRIX_HOMESERVER", "http://192.168.86.192:8008"
+    )
+    MATRIX_ACCESS_TOKEN: str = os.environ.get("MATRIX_ACCESS_TOKEN", "")
+    MATRIX_ROOM_ID: str = os.environ.get("MATRIX_ROOM_ID", "")
+
+    # Vision - CLIP service
+    CLIP_SERVICE_URL: str = os.environ.get(
+        "CLIP_SERVICE_URL", "http://192.168.86.150:5200"
+    )
+
+    # Vision - Ollama
+    OLLAMA_URL: str = os.environ.get("OLLAMA_URL", "http://192.168.86.150:11434")
+    OLLAMA_MODEL: str = os.environ.get("OLLAMA_MODEL", "llava:13b")
+
+    # Recognition thresholds
+    RECOGNITION_THRESHOLD_HIGH: float = float(
+        os.environ.get("RECOGNITION_THRESHOLD_HIGH", "0.85")
+    )
+    RECOGNITION_THRESHOLD_LOW: float = float(
+        os.environ.get("RECOGNITION_THRESHOLD_LOW", "0.60")
+    )
+
+    # Filtering
+    ALLOWED_LABELS: set = set(
+        os.environ.get("ALLOWED_LABELS", "person,car,dog,cat,bird").split(",")
+    )
+    MIN_SCORE: float = float(os.environ.get("MIN_SCORE", "0.7"))
+    RATE_LIMIT_SECONDS: int = int(os.environ.get("RATE_LIMIT_SECONDS", "60"))
+    DEDUP_WINDOW_SECONDS: int = int(os.environ.get("DEDUP_WINDOW_SECONDS", "30"))
+
+    # Server
+    SERVER_HOST: str = os.environ.get("SERVER_HOST", "0.0.0.0")
+    SERVER_PORT: int = int(os.environ.get("SERVER_PORT", "5199"))
+
+    # Database
+    DB_PATH: str = os.environ.get("DB_PATH", "/data/frigate-notify.db")
+
+
+config = Config()

compose/hf-pdocker-01/frigate-notify/app/database.py

@@ -0,0 +1,109 @@
+"""SQLite database schema and connection management for frigate-notify v2."""
+
+import logging
+import sqlite3
+import threading
+
+logger = logging.getLogger(__name__)
+
+# Thread-local storage for database connections
+_local = threading.local()
+
+_db_path: str = "/data/frigate-notify.db"
+
+
+def set_db_path(path: str) -> None:
+    """Set the database path. Closes any existing connection first."""
+    global _db_path
+    close_connection()
+    _db_path = path
+
+
+def get_connection() -> sqlite3.Connection:
+    """Get a thread-local database connection with WAL mode and foreign keys enabled."""
+    if not hasattr(_local, "connection") or _local.connection is None:
+        conn = sqlite3.connect(_db_path)
+        conn.execute("PRAGMA journal_mode=WAL")
+        conn.execute("PRAGMA foreign_keys=ON")
+        conn.row_factory = sqlite3.Row
+        _local.connection = conn
+    return _local.connection
+
+
+def close_connection() -> None:
+    """Close the thread-local database connection if one exists."""
+    if hasattr(_local, "connection") and _local.connection is not None:
+        _local.connection.close()
+        _local.connection = None
+
+
+def init_db() -> None:
+    """Create all tables and default settings."""
+    conn = get_connection()
+    cursor = conn.cursor()
+
+    cursor.executescript(
+        """
+        CREATE TABLE IF NOT EXISTS known_objects (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            name TEXT NOT NULL,
+            type TEXT NOT NULL CHECK(type IN ('person', 'vehicle', 'pet')),
+            action TEXT NOT NULL DEFAULT 'quiet' CHECK(action IN ('quiet', 'suppress', 'alert')),
+            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+            updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+        );
+
+        CREATE TABLE IF NOT EXISTS embeddings (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            known_object_id INTEGER NOT NULL,
+            embedding BLOB NOT NULL,
+            snapshot_url TEXT,
+            thumbnail BLOB,
+            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+            FOREIGN KEY (known_object_id) REFERENCES known_objects(id) ON DELETE CASCADE
+        );
+
+        CREATE TABLE IF NOT EXISTS events (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            frigate_event_id TEXT UNIQUE NOT NULL,
+            camera TEXT NOT NULL,
+            label TEXT NOT NULL,
+            score REAL NOT NULL,
+            snapshot BLOB,
+            embedding BLOB,
+            match_status TEXT NOT NULL DEFAULT 'unreviewed'
+                CHECK(match_status IN ('known', 'unknown', 'ambiguous', 'unreviewed')),
+            matched_object_id INTEGER,
+            match_confidence REAL,
+            ai_description TEXT,
+            notified INTEGER NOT NULL DEFAULT 0,
+            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+            FOREIGN KEY (matched_object_id) REFERENCES known_objects(id) ON DELETE SET NULL
+        );
+
+        CREATE TABLE IF NOT EXISTS settings (
+            key TEXT PRIMARY KEY,
+            value TEXT NOT NULL
+        );
+
+        CREATE INDEX IF NOT EXISTS idx_events_created_at ON events(created_at);
+        CREATE INDEX IF NOT EXISTS idx_events_match_status ON events(match_status);
+        CREATE INDEX IF NOT EXISTS idx_events_camera ON events(camera);
+        CREATE INDEX IF NOT EXISTS idx_embeddings_known_object_id ON embeddings(known_object_id);
+        """
+    )
+
+    # Insert default settings if they don't exist
+    defaults = {
+        "vision_backend": "haiku",
+        "recognition_enabled": "false",
+        "event_retention_days": "90",
+    }
+    for key, value in defaults.items():
+        cursor.execute(
+            "INSERT OR IGNORE INTO settings (key, value) VALUES (?, ?)",
+            (key, value),
+        )
+
+    conn.commit()
+    logger.info("Database initialized at %s", _db_path)

compose/hf-pdocker-01/frigate-notify/app/main.py

@@ -1,3 +1,5 @@
+"""frigate-notify v2 — FastAPI application with MQTT listener."""
+
 import asyncio
 import json
 import logging
@@ -6,29 +8,28 @@ import signal
 import sys
 import time
 from collections import defaultdict
-from http.server import HTTPServer, BaseHTTPRequestHandler
+from contextlib import asynccontextmanager
+from pathlib import Path
 from threading import Thread
 
 import aiohttp
 import anthropic
 import paho.mqtt.client as mqtt
+import uvicorn
+from fastapi import FastAPI
+from fastapi.responses import FileResponse, JSONResponse
+from fastapi.staticfiles import StaticFiles
 
-from vision import analyze_snapshot
+from config import config
+from database import close_connection, get_connection, init_db, set_db_path
 from matrix_client import MatrixClient
-
+from routes.events import router as events_router
-# --- Configuration ---
+from routes.known_objects import router as known_objects_router
-MQTT_HOST = os.environ.get("MQTT_HOST", "192.168.86.192")
+from routes.settings import router as settings_router
-MQTT_PORT = int(os.environ.get("MQTT_PORT", "1883"))
+from ollama_client import OllamaClient
-FRIGATE_URL = os.environ.get("FRIGATE_URL", "http://192.168.86.192:5000")
+from recognition import recognize_event, get_clip_embedding, embedding_to_bytes
-MATRIX_HOMESERVER = os.environ.get("MATRIX_HOMESERVER", "http://192.168.86.192:8008")
+from vision import get_description
-MATRIX_ACCESS_TOKEN = os.environ["MATRIX_ACCESS_TOKEN"]
+from cleanup import cleanup_old_events
-MATRIX_ROOM_ID = os.environ["MATRIX_ROOM_ID"]
-HEALTH_PORT = int(os.environ.get("HEALTH_PORT", "5199"))
-
-ALLOWED_LABELS = {"person", "car", "dog", "cat", "bird"}
-MIN_SCORE = 0.7
-RATE_LIMIT_SECONDS = 60
-DEDUP_WINDOW_SECONDS = 30
 
 # --- Logging ---
 logging.basicConfig(
@@ -44,46 +45,12 @@ last_notify_per_camera: defaultdict[str, float] = defaultdict(float)
 events_processed = 0
 last_event_time: str | None = None
 mqtt_connected = False
-
+mqtt_client_instance: mqtt.Client | None = None
-
-# --- Health endpoint ---
-class HealthHandler(BaseHTTPRequestHandler):
-    protocol_version = "HTTP/1.1"
-
-    def do_GET(self):
-        if self.path == "/health":
-            body = json.dumps(
-                {
-                    "status": "ok",
-                    "mqtt_connected": mqtt_connected,
-                    "events_processed": events_processed,
-                    "last_event": last_event_time,
-                }
-            )
-            encoded = body.encode()
-            self.send_response(200)
-            self.send_header("Content-Type", "application/json")
-            self.send_header("Content-Length", str(len(encoded)))
-            self.end_headers()
-            self.wfile.write(encoded)
-        else:
-            self.send_response(404)
-            self.end_headers()
-
-    def log_message(self, format, *args):
-        pass  # suppress access logs
-
-
-def start_health_server():
-    server = HTTPServer(("0.0.0.0", HEALTH_PORT), HealthHandler)
-    thread = Thread(target=server.serve_forever, daemon=True)
-    thread.start()
-    logger.info("Health server started on port %d", HEALTH_PORT)
 
 
 # --- Snapshot fetching ---
 async def fetch_snapshot(event_id: str) -> bytes | None:
-    url = f"{FRIGATE_URL}/api/events/{event_id}/snapshot.jpg"
+    url = f"{config.FRIGATE_URL}/api/events/{event_id}/snapshot.jpg"
     try:
         async with aiohttp.ClientSession() as session:
             async with session.get(url) as resp:
@@ -103,7 +70,8 @@ async def fetch_snapshot(event_id: str) -> bytes | None:
 
 # --- Event processing ---
 async def process_event(
-    event_data: dict, claude: anthropic.Anthropic, matrix: MatrixClient
+    event_data: dict, claude: anthropic.Anthropic, matrix: MatrixClient,
+    ollama_client: OllamaClient = None,
 ):
     global events_processed, last_event_time
 
@@ -119,27 +87,30 @@ async def process_event(
     has_snapshot = after.get("has_snapshot", False)
 
     # --- Filtering ---
-    if label not in ALLOWED_LABELS:
+    if label not in config.ALLOWED_LABELS:
         return
-    if score < MIN_SCORE:
+    if score < config.MIN_SCORE:
         return
     if not has_snapshot:
         return
 
     # Dedup
     now = time.time()
-    if event_id in recent_events and now - recent_events[event_id] < DEDUP_WINDOW_SECONDS:
+    if (
+        event_id in recent_events
+        and now - recent_events[event_id] < config.DEDUP_WINDOW_SECONDS
+    ):
         return
     recent_events[event_id] = now
 
     # Rate limit per camera
-    if now - last_notify_per_camera[camera] < RATE_LIMIT_SECONDS:
+    if now - last_notify_per_camera[camera] < config.RATE_LIMIT_SECONDS:
         logger.info("Rate limited: %s on %s", label, camera)
         return
     last_notify_per_camera[camera] = now
 
     # Cleanup old dedup entries
-    cutoff = now - DEDUP_WINDOW_SECONDS * 2
+    cutoff = now - config.DEDUP_WINDOW_SECONDS * 2
     for eid in [k for k, v in recent_events.items() if v < cutoff]:
         del recent_events[eid]
 
@@ -150,18 +121,84 @@ async def process_event(
     # --- Fetch snapshot ---
     snapshot = await fetch_snapshot(event_id)
 
-    # --- AI analysis ---
+    # --- Recognition ---
+    match_status = "unreviewed"
+    matched_id = None
+    match_conf = 0.0
+    matched_name = None
+
+    # Check if recognition is enabled
+    recognition_enabled = False
+    try:
+        conn = get_connection()
+        row = conn.execute("SELECT value FROM settings WHERE key='recognition_enabled'").fetchone()
+        if row:
+            recognition_enabled = row["value"].lower() == "true"
+    except Exception:
+        pass
+
+    if recognition_enabled and snapshot:
+        match_status, matched_id, match_conf, matched_name = await recognize_event(
+            snapshot, ollama_client
+        )
+        # Store embedding with event
+        embedding = await get_clip_embedding(snapshot)
+        if embedding:
+            embedding_blob = embedding_to_bytes(embedding)
+            try:
+                conn = get_connection()
+                conn.execute(
+                    "UPDATE events SET embedding=?, match_status=?, matched_object_id=?, match_confidence=? WHERE frigate_event_id=?",
+                    (embedding_blob, match_status, matched_id, match_conf, event_id),
+                )
+                conn.commit()
+            except Exception:
+                logger.exception("Failed to update event recognition")
+
+        # If known, check action - skip notification for quiet/suppress
+        if match_status == "known" and matched_id:
+            conn = get_connection()
+            obj = conn.execute("SELECT action FROM known_objects WHERE id=?", (matched_id,)).fetchone()
+            if obj and obj["action"] in ("quiet", "suppress"):
+                logger.info("Known object '%s' (%s), skipping notification", matched_name, obj["action"])
+                events_processed += 1
+                last_event_time = time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime())
+                return
+
+    # --- AI description ---
+    vision_backend = "haiku"
+    try:
+        conn = get_connection()
+        row = conn.execute("SELECT value FROM settings WHERE key='vision_backend'").fetchone()
+        if row:
+            vision_backend = row["value"]
+    except Exception:
+        pass
+
     description = None
     if snapshot:
-        description = analyze_snapshot(claude, snapshot)
+        description = await get_description(snapshot, vision_backend, claude, ollama_client)
     if not description:
         description = f"{label.capitalize()} detected on {camera}."
 
+    # --- Store event in database ---
+    try:
+        conn = get_connection()
+        conn.execute(
+            """INSERT OR IGNORE INTO events
+               (frigate_event_id, camera, label, score, snapshot, match_status, ai_description, notified)
+               VALUES (?, ?, ?, ?, ?, ?, ?, 1)""",
+            (event_id, camera, label, score, snapshot, match_status, description),
+        )
+        conn.commit()
+    except Exception:
+        logger.exception("Failed to store event %s in database", event_id)
+
     # --- Format message ---
     score_pct = int(score * 100)
     ts = time.strftime("%I:%M:%S %p", time.localtime())
     date_str = time.strftime("%b %d, %Y", time.localtime())
-    frigate_link = f"{FRIGATE_URL}/review?id={event_id}"
+    frigate_link = f"{config.FRIGATE_URL}/review?id={event_id}"
 
     plain = (
         f"{camera} - {label.capitalize()} - {score_pct}%\n"
@@ -195,7 +232,8 @@ def create_mqtt_client(
     loop: asyncio.AbstractEventLoop,
     claude: anthropic.Anthropic,
     matrix: MatrixClient,
-):
+    ollama_client: OllamaClient = None,
+) -> mqtt.Client:
     global mqtt_connected
 
     def on_connect(client, userdata, flags, reason_code, properties):
@@ -213,7 +251,7 @@ def create_mqtt_client(
         try:
             payload = json.loads(msg.payload)
             asyncio.run_coroutine_threadsafe(
-                process_event(payload, claude, matrix), loop
+                process_event(payload, claude, matrix, ollama_client), loop
             )
         except json.JSONDecodeError:
             logger.warning("Invalid JSON on %s", msg.topic)
@@ -227,33 +265,99 @@ def create_mqtt_client(
     return client
 
 
-# --- Main ---
+def start_mqtt(loop: asyncio.AbstractEventLoop) -> None:
-def main():
+    """Start MQTT client in a background thread."""
-    logger.info("Starting frigate-notify")
+    global mqtt_client_instance
 
     claude = anthropic.Anthropic()
-    matrix = MatrixClient(MATRIX_HOMESERVER, MATRIX_ACCESS_TOKEN, MATRIX_ROOM_ID)
+    matrix = MatrixClient(
+        config.MATRIX_HOMESERVER,
+        config.MATRIX_ACCESS_TOKEN,
+        config.MATRIX_ROOM_ID,
+    )
+    ollama_client = OllamaClient(config.OLLAMA_URL, config.OLLAMA_MODEL)
 
-    loop = asyncio.new_event_loop()
+    mqtt_client_instance = create_mqtt_client(loop, claude, matrix, ollama_client)
-    loop_thread = Thread(target=loop.run_forever, daemon=True)
+    mqtt_client_instance.connect(config.MQTT_HOST, config.MQTT_PORT)
-    loop_thread.start()
 
-    start_health_server()
+    thread = Thread(target=mqtt_client_instance.loop_forever, daemon=True)
-
+    thread.start()
-    mqtt_client = create_mqtt_client(loop, claude, matrix)
+    logger.info("MQTT client started in background thread")
-    mqtt_client.connect(MQTT_HOST, MQTT_PORT)
-
-    def shutdown(signum, frame):
-        logger.info("Shutting down...")
-        mqtt_client.disconnect()
-        loop.call_soon_threadsafe(loop.stop)
-        sys.exit(0)
-
-    signal.signal(signal.SIGTERM, shutdown)
-    signal.signal(signal.SIGINT, shutdown)
-
-    mqtt_client.loop_forever()
 
 
+# --- FastAPI lifespan ---
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    """Startup and shutdown logic for the FastAPI application."""
+    logger.info("Starting frigate-notify v2")
+
+    # Initialize database
+    set_db_path(config.DB_PATH)
+    init_db()
+
+    # Start MQTT listener in background
+    loop = asyncio.get_event_loop()
+    start_mqtt(loop)
+
+    # Start periodic event cleanup
+    asyncio.create_task(cleanup_old_events())
+
+    yield
+
+    # Shutdown
+    logger.info("Shutting down frigate-notify v2")
+    if mqtt_client_instance:
+        mqtt_client_instance.disconnect()
+    close_connection()
+
+
+# --- FastAPI app ---
+app = FastAPI(
+    title="frigate-notify",
+    version="2.0.0",
+    lifespan=lifespan,
+)
+
+# Include API routers
+app.include_router(events_router)
+app.include_router(known_objects_router)
+app.include_router(settings_router)
+
+# Mount static files directory
+static_dir = Path(__file__).parent / "static"
+static_dir.mkdir(exist_ok=True)
+app.mount("/static", StaticFiles(directory=str(static_dir)), name="static")
+
+
+@app.get("/health")
+async def health():
+    """Health check endpoint."""
+    return {
+        "status": "ok",
+        "version": "2.0.0",
+        "mqtt_connected": mqtt_connected,
+        "events_processed": events_processed,
+        "last_event": last_event_time,
+    }
+
+
+@app.get("/")
+async def index():
+    """Serve the web UI index page."""
+    index_path = static_dir / "index.html"
+    if index_path.exists():
+        return FileResponse(str(index_path))
+    return JSONResponse(
+        {"message": "frigate-notify v2", "docs": "/docs"},
+        status_code=200,
+    )
+
+
+# --- Entrypoint ---
 if __name__ == "__main__":
-    main()
+    uvicorn.run(
+        "main:app",
+        host=config.SERVER_HOST,
+        port=config.SERVER_PORT,
+        log_level="info",
+    )

compose/hf-pdocker-01/frigate-notify/app/models.py

@@ -0,0 +1,95 @@
+"""Pydantic models for frigate-notify v2 API."""
+
+from datetime import datetime
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+# --- Known Objects ---
+
+
+class KnownObjectCreate(BaseModel):
+    """Request model for creating a known object."""
+
+    name: str = Field(..., min_length=1, max_length=255)
+    type: str = Field(..., pattern="^(person|vehicle|pet)$")
+    action: str = Field(default="quiet", pattern="^(quiet|suppress|alert)$")
+
+
+class KnownObjectUpdate(BaseModel):
+    """Request model for updating a known object."""
+
+    name: Optional[str] = Field(default=None, min_length=1, max_length=255)
+    type: Optional[str] = Field(default=None, pattern="^(person|vehicle|pet)$")
+    action: Optional[str] = Field(default=None, pattern="^(quiet|suppress|alert)$")
+
+
+class KnownObjectResponse(BaseModel):
+    """Response model for a known object."""
+
+    id: int
+    name: str
+    type: str
+    action: str
+    created_at: str
+    updated_at: str
+
+
+# --- Events ---
+
+
+class TagEventRequest(BaseModel):
+    """Request model for tagging an event with a known object.
+
+    Either provide known_object_id to link to an existing object,
+    or provide name + type to create a new known object.
+    """
+
+    known_object_id: Optional[int] = None
+    name: Optional[str] = Field(default=None, min_length=1, max_length=255)
+    type: Optional[str] = Field(default=None, pattern="^(person|vehicle|pet)$")
+
+
+class EventResponse(BaseModel):
+    """Response model for an event."""
+
+    id: int
+    frigate_event_id: str
+    camera: str
+    label: str
+    score: float
+    has_snapshot: bool = False
+    snapshot_base64: Optional[str] = None
+    match_status: str
+    matched_object_id: Optional[int] = None
+    matched_object_name: Optional[str] = None
+    match_confidence: Optional[float] = None
+    ai_description: Optional[str] = None
+    notified: bool
+    created_at: str
+
+
+# --- Settings ---
+
+
+class SettingsResponse(BaseModel):
+    """Response model for application settings."""
+
+    vision_backend: str
+    recognition_enabled: bool
+    event_retention_days: int
+
+
+# --- Stats ---
+
+
+class StatsResponse(BaseModel):
+    """Response model for application statistics."""
+
+    total_events: int = 0
+    known_matches: int = 0
+    unknown_events: int = 0
+    unreviewed: int = 0
+    known_objects_count: int = 0
+    events_today: int = 0

compose/hf-pdocker-01/frigate-notify/app/ollama_client.py

@@ -0,0 +1,132 @@
+"""Ollama vision LLM client for frigate-notify v2."""
+
+import base64
+import logging
+
+import aiohttp
+
+logger = logging.getLogger(__name__)
+
+
+class OllamaClient:
+    """Client for Ollama vision models (e.g., llava)."""
+
+    def __init__(self, base_url: str, model: str):
+        self.base_url = base_url.rstrip("/")
+        self.model = model
+
+    async def analyze_image(self, image_bytes: bytes, prompt: str) -> str | None:
+        """Send an image to Ollama for analysis.
+
+        Args:
+            image_bytes: Raw image bytes (JPEG).
+            prompt: Text prompt for the vision model.
+
+        Returns:
+            Response text or None on failure.
+        """
+        b64 = base64.b64encode(image_bytes).decode("utf-8")
+        payload = {
+            "model": self.model,
+            "prompt": prompt,
+            "images": [b64],
+            "stream": False,
+            "options": {"num_predict": 200},
+        }
+        try:
+            async with aiohttp.ClientSession() as session:
+                async with session.post(
+                    f"{self.base_url}/api/generate",
+                    json=payload,
+                    timeout=aiohttp.ClientTimeout(total=30),
+                ) as resp:
+                    if resp.status == 200:
+                        data = await resp.json()
+                        text = data.get("response", "").strip()
+                        logger.info(
+                            "Ollama analysis complete: %d chars", len(text)
+                        )
+                        return text if text else None
+                    body = await resp.text()
+                    logger.error(
+                        "Ollama analyze_image failed %s: %s", resp.status, body
+                    )
+        except Exception:
+            logger.exception("Ollama analyze_image request failed")
+        return None
+
+    async def compare_images(
+        self,
+        image_bytes: bytes,
+        reference_bytes: bytes,
+        object_name: str,
+    ) -> bool | None:
+        """Compare two images to determine if they show the same object/person.
+
+        Args:
+            image_bytes: The new event image bytes.
+            reference_bytes: The reference (known) image bytes.
+            object_name: Name of the known object for context.
+
+        Returns:
+            True if same, False if different, None on failure/inconclusive.
+        """
+        b64_new = base64.b64encode(image_bytes).decode("utf-8")
+        b64_ref = base64.b64encode(reference_bytes).decode("utf-8")
+        prompt = (
+            f"Look at these two images. The first image is from a security camera. "
+            f"The second image is a reference photo of '{object_name}'. "
+            f"Are these the same person/vehicle/animal? "
+            f"Answer with ONLY 'yes' or 'no'."
+        )
+        payload = {
+            "model": self.model,
+            "prompt": prompt,
+            "images": [b64_new, b64_ref],
+            "stream": False,
+            "options": {"num_predict": 200},
+        }
+        try:
+            async with aiohttp.ClientSession() as session:
+                async with session.post(
+                    f"{self.base_url}/api/generate",
+                    json=payload,
+                    timeout=aiohttp.ClientTimeout(total=30),
+                ) as resp:
+                    if resp.status == 200:
+                        data = await resp.json()
+                        text = data.get("response", "").strip().lower()
+                        logger.info("Ollama compare result: %s", text)
+                        if "yes" in text.split()[:3]:
+                            return True
+                        if "no" in text.split()[:3]:
+                            return False
+                        logger.warning(
+                            "Ollama compare inconclusive: %s", text
+                        )
+                        return None
+                    body = await resp.text()
+                    logger.error(
+                        "Ollama compare_images failed %s: %s",
+                        resp.status,
+                        body,
+                    )
+        except Exception:
+            logger.exception("Ollama compare_images request failed")
+        return None
+
+    async def is_available(self) -> bool:
+        """Check if Ollama is reachable and responding.
+
+        Returns:
+            True if Ollama responds with HTTP 200, False otherwise.
+        """
+        try:
+            async with aiohttp.ClientSession() as session:
+                async with session.get(
+                    f"{self.base_url}/api/tags",
+                    timeout=aiohttp.ClientTimeout(total=3),
+                ) as resp:
+                    return resp.status == 200
+        except Exception:
+            return False

compose/hf-pdocker-01/frigate-notify/app/recognition.py

@@ -0,0 +1,232 @@
+"""Recognition pipeline using CLIP embeddings with Ollama vision fallback."""
+
+import base64
+import logging
+import struct
+from typing import Optional
+
+import aiohttp
+import numpy as np
+
+from config import config
+from database import get_connection
+from ollama_client import OllamaClient
+
+logger = logging.getLogger(__name__)
+
+
+def embedding_to_bytes(embedding: list[float]) -> bytes:
+    """Pack a float32 embedding list into bytes for SQLite storage.
+
+    Args:
+        embedding: List of float values (typically 768-dimensional).
+
+    Returns:
+        Packed bytes (len(embedding) * 4 bytes).
+    """
+    return struct.pack(f"{len(embedding)}f", *embedding)
+
+
+def bytes_to_embedding(data: bytes) -> np.ndarray:
+    """Unpack bytes back into a float32 numpy array.
+
+    Args:
+        data: Packed bytes from embedding_to_bytes().
+
+    Returns:
+        Numpy array of float32 values.
+    """
+    count = len(data) // 4
+    values = struct.unpack(f"{count}f", data)
+    return np.array(values, dtype=np.float32)
+
+
+async def get_clip_embedding(image_bytes: bytes) -> list[float] | None:
+    """Get CLIP embedding for an image from the clip-service sidecar.
+
+    Args:
+        image_bytes: Raw image bytes (JPEG).
+
+    Returns:
+        List of float embedding values, or None on failure.
+    """
+    b64 = base64.b64encode(image_bytes).decode("utf-8")
+    try:
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{config.CLIP_SERVICE_URL}/embed",
+                json={"image": b64},
+                timeout=aiohttp.ClientTimeout(total=10),
+            ) as resp:
+                if resp.status == 200:
+                    data = await resp.json()
+                    embedding = data.get("embedding")
+                    if embedding:
+                        logger.info(
+                            "CLIP embedding received: %d dimensions",
+                            len(embedding),
+                        )
+                        return embedding
+                    logger.warning("CLIP response missing embedding field")
+                else:
+                    body = await resp.text()
+                    logger.error(
+                        "CLIP embed failed %s: %s", resp.status, body
+                    )
+    except Exception:
+        logger.exception("CLIP embedding request failed")
+    return None
+
+
+async def find_best_match(
+    query_embedding: list[float],
+) -> tuple[int | None, float, str | None]:
+    """Find the best matching known object for a query embedding.
+
+    Loads all embeddings from the database, computes cosine similarity,
+    groups by known_object_id and takes the max score per object.
+
+    Args:
+        query_embedding: The query embedding to match against.
+
+    Returns:
+        Tuple of (best_object_id, best_score, best_name).
+        Returns (None, 0.0, None) if no embeddings exist.
+    """
+    conn = get_connection()
+    cursor = conn.execute(
+        """
+        SELECT e.id, e.known_object_id, e.embedding, ko.name
+        FROM embeddings e
+        JOIN known_objects ko ON e.known_object_id = ko.id
+        """
+    )
+    rows = cursor.fetchall()
+
+    if not rows:
+        return (None, 0.0, None)
+
+    query_vec = np.array(query_embedding, dtype=np.float32)
+    query_norm = np.linalg.norm(query_vec)
+    if query_norm == 0:
+        return (None, 0.0, None)
+    query_vec = query_vec / query_norm
+
+    # Group scores by known_object_id, keeping max per object
+    best_per_object: dict[int, tuple[float, str]] = {}
+
+    for row in rows:
+        stored_vec = bytes_to_embedding(row["embedding"])
+        stored_norm = np.linalg.norm(stored_vec)
+        if stored_norm == 0:
+            continue
+        stored_vec = stored_vec / stored_norm
+
+        similarity = float(np.dot(query_vec, stored_vec))
+        obj_id = row["known_object_id"]
+        obj_name = row["name"]
+
+        if obj_id not in best_per_object or similarity > best_per_object[obj_id][0]:
+            best_per_object[obj_id] = (similarity, obj_name)
+
+    if not best_per_object:
+        return (None, 0.0, None)
+
+    best_id = max(best_per_object, key=lambda k: best_per_object[k][0])
+    best_score, best_name = best_per_object[best_id]
+
+    return (best_id, best_score, best_name)
+
+
+async def recognize_event(
+    image_bytes: bytes,
+    ollama_client: Optional[OllamaClient] = None,
+) -> tuple[str, int | None, float, str | None]:
+    """Full recognition pipeline for a Frigate event image.
+
+    Steps:
+        1. Get CLIP embedding for the image.
+        2. Find the best matching known object.
+        3. High confidence (>= threshold_high): return "known".
+        4. Low confidence (< threshold_low): return "unknown".
+        5. Ambiguous range: use Ollama vision LLM to confirm/deny.
+        6. If LLM unavailable or inconclusive: return "ambiguous".
+        7. If no embedding could be obtained: return "unreviewed".
+
+    Args:
+        image_bytes: Raw image bytes (JPEG).
+        ollama_client: Optional OllamaClient for ambiguous case fallback.
+
+    Returns:
+        Tuple of (match_status, object_id, score, object_name).
+        match_status is one of: "known", "unknown", "ambiguous", "unreviewed".
+    """
+    # Step 1: Get CLIP embedding
+    embedding = await get_clip_embedding(image_bytes)
+    if embedding is None:
+        logger.warning("Could not get CLIP embedding, returning unreviewed")
+        return ("unreviewed", None, 0.0, None)
+
+    # Step 2: Find best match
+    best_id, best_score, best_name = await find_best_match(embedding)
+
+    # No embeddings in DB at all
+    if best_id is None:
+        return ("unknown", None, 0.0, None)
+
+    high_threshold = config.RECOGNITION_THRESHOLD_HIGH
+    low_threshold = config.RECOGNITION_THRESHOLD_LOW
+
+    # Step 3: High confidence match
+    if best_score >= high_threshold:
+        logger.info(
+            "High confidence match: %s (%.3f)", best_name, best_score
+        )
+        return ("known", best_id, best_score, best_name)
+
+    # Step 4: Low confidence - clearly not a match
+    if best_score < low_threshold:
+        logger.info("Low confidence, no match (%.3f)", best_score)
+        return ("unknown", None, best_score, None)
+
+    # Step 5: Ambiguous range - try Ollama vision LLM
+    if ollama_client is not None:
+        logger.info(
+            "Ambiguous score %.3f for %s, trying Ollama comparison",
+            best_score,
+            best_name,
+        )
+        # Get a reference thumbnail from the embeddings table
+        conn = get_connection()
+        cursor = conn.execute(
+            """
+            SELECT thumbnail FROM embeddings
+            WHERE known_object_id = ? AND thumbnail IS NOT NULL
+            LIMIT 1
+            """,
+            (best_id,),
+        )
+        ref_row = cursor.fetchone()
+        if ref_row and ref_row["thumbnail"] is not None:
+            result = await ollama_client.compare_images(
+                image_bytes, ref_row["thumbnail"], best_name
+            )
+            if result is True:
+                logger.info(
+                    "Ollama confirmed match: %s (%.3f)",
+                    best_name,
+                    best_score,
+                )
+                return ("known", best_id, best_score, best_name)
+            elif result is False:
+                logger.info(
+                    "Ollama denied match: %s (%.3f)", best_name, best_score
+                )
+                return ("unknown", None, best_score, None)
+            # result is None: inconclusive, fall through to ambiguous
+
+    # Step 6: LLM unavailable or inconclusive
+    logger.info(
+        "Ambiguous match: %s (%.3f)", best_name, best_score
+    )
+    return ("ambiguous", best_id, best_score, best_name)

compose/hf-pdocker-01/frigate-notify/app/requirements.txt

@@ -1,3 +1,7 @@
 paho-mqtt==2.1.0
 anthropic>=0.40.0
 aiohttp>=3.9.0
+fastapi>=0.115.0
+uvicorn[standard]>=0.34.0
+python-multipart>=0.0.18
+numpy>=1.26.0

compose/hf-pdocker-01/frigate-notify/app/routes/events.py

@@ -0,0 +1,226 @@
+"""Event API endpoints for frigate-notify v2."""
+
+import base64
+import logging
+from typing import Optional
+
+from fastapi import APIRouter, HTTPException, Query
+from fastapi.responses import Response
+
+from database import get_connection
+from models import EventResponse, TagEventRequest
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/api/events", tags=["events"])
+
+
+@router.get("", response_model=list[EventResponse])
+async def list_events(
+    camera: Optional[str] = Query(default=None),
+    label: Optional[str] = Query(default=None),
+    status: Optional[str] = Query(default=None),
+    limit: int = Query(default=50, ge=1, le=500),
+    offset: int = Query(default=0, ge=0),
+):
+    """List events with optional filters and pagination.
+
+    Returns events without snapshot/embedding BLOBs but with has_snapshot bool.
+    Joins to known_objects for matched_object_name.
+    """
+    conn = get_connection()
+
+    query = """
+        SELECT
+            e.id, e.frigate_event_id, e.camera, e.label, e.score,
+            CASE WHEN e.snapshot IS NOT NULL THEN 1 ELSE 0 END AS has_snapshot,
+            e.match_status, e.matched_object_id,
+            ko.name AS matched_object_name,
+            e.match_confidence, e.ai_description, e.notified, e.created_at
+        FROM events e
+        LEFT JOIN known_objects ko ON e.matched_object_id = ko.id
+    """
+    conditions = []
+    params: list = []
+
+    if camera:
+        conditions.append("e.camera = ?")
+        params.append(camera)
+    if label:
+        conditions.append("e.label = ?")
+        params.append(label)
+    if status:
+        conditions.append("e.match_status = ?")
+        params.append(status)
+
+    if conditions:
+        query += " WHERE " + " AND ".join(conditions)
+
+    query += " ORDER BY e.created_at DESC LIMIT ? OFFSET ?"
+    params.extend([limit, offset])
+
+    cursor = conn.execute(query, params)
+    rows = cursor.fetchall()
+
+    return [
+        EventResponse(
+            id=row["id"],
+            frigate_event_id=row["frigate_event_id"],
+            camera=row["camera"],
+            label=row["label"],
+            score=row["score"],
+            has_snapshot=bool(row["has_snapshot"]),
+            match_status=row["match_status"],
+            matched_object_id=row["matched_object_id"],
+            matched_object_name=row["matched_object_name"],
+            match_confidence=row["match_confidence"],
+            ai_description=row["ai_description"],
+            notified=bool(row["notified"]),
+            created_at=row["created_at"],
+        )
+        for row in rows
+    ]
+
+
+@router.get("/{event_id}", response_model=EventResponse)
+async def get_event(event_id: int):
+    """Get a single event detail. Includes base64-encoded snapshot if exists."""
+    conn = get_connection()
+    cursor = conn.execute(
+        """
+        SELECT
+            e.id, e.frigate_event_id, e.camera, e.label, e.score,
+            e.snapshot,
+            CASE WHEN e.snapshot IS NOT NULL THEN 1 ELSE 0 END AS has_snapshot,
+            e.match_status, e.matched_object_id,
+            ko.name AS matched_object_name,
+            e.match_confidence, e.ai_description, e.notified, e.created_at
+        FROM events e
+        LEFT JOIN known_objects ko ON e.matched_object_id = ko.id
+        WHERE e.id = ?
+        """,
+        (event_id,),
+    )
+    row = cursor.fetchone()
+    if not row:
+        raise HTTPException(status_code=404, detail="Event not found")
+
+    snapshot_b64 = None
+    if row["snapshot"] is not None:
+        snapshot_b64 = base64.b64encode(row["snapshot"]).decode("ascii")
+
+    return EventResponse(
+        id=row["id"],
+        frigate_event_id=row["frigate_event_id"],
+        camera=row["camera"],
+        label=row["label"],
+        score=row["score"],
+        has_snapshot=bool(row["has_snapshot"]),
+        snapshot_base64=snapshot_b64,
+        match_status=row["match_status"],
+        matched_object_id=row["matched_object_id"],
+        matched_object_name=row["matched_object_name"],
+        match_confidence=row["match_confidence"],
+        ai_description=row["ai_description"],
+        notified=bool(row["notified"]),
+        created_at=row["created_at"],
+    )
+
+
+@router.get("/{event_id}/snapshot")
+async def get_event_snapshot(event_id: int):
+    """Return raw JPEG snapshot for an event. 404 if no snapshot."""
+    conn = get_connection()
+    cursor = conn.execute(
+        "SELECT snapshot FROM events WHERE id = ?",
+        (event_id,),
+    )
+    row = cursor.fetchone()
+    if not row:
+        raise HTTPException(status_code=404, detail="Event not found")
+    if row["snapshot"] is None:
+        raise HTTPException(status_code=404, detail="No snapshot available")
+
+    return Response(content=row["snapshot"], media_type="image/jpeg")
+
+
+@router.post("/{event_id}/tag")
+async def tag_event(event_id: int, body: TagEventRequest):
+    """Tag an event as a known object.
+
+    Either provide known_object_id to link to an existing object,
+    or provide name + type to create a new known object.
+    If the event has an embedding, store it in the embeddings table.
+    """
+    conn = get_connection()
+
+    # Verify event exists
+    cursor = conn.execute(
+        "SELECT id, embedding FROM events WHERE id = ?",
+        (event_id,),
+    )
+    event_row = cursor.fetchone()
+    if not event_row:
+        raise HTTPException(status_code=404, detail="Event not found")
+
+    known_object_id = body.known_object_id
+
+    if known_object_id is not None:
+        # Verify the known object exists
+        cursor = conn.execute(
+            "SELECT id FROM known_objects WHERE id = ?",
+            (known_object_id,),
+        )
+        if not cursor.fetchone():
+            raise HTTPException(status_code=404, detail="Known object not found")
+    elif body.name and body.type:
+        # Create a new known object
+        cursor = conn.execute(
+            "INSERT INTO known_objects (name, type) VALUES (?, ?)",
+            (body.name, body.type),
+        )
+        known_object_id = cursor.lastrowid
+        conn.commit()
+    else:
+        raise HTTPException(
+            status_code=400,
+            detail="Must provide either known_object_id or both name and type",
+        )
+
+    # If event has an embedding, store it in the embeddings table
+    if event_row["embedding"] is not None:
+        conn.execute(
+            "INSERT INTO embeddings (known_object_id, embedding) VALUES (?, ?)",
+            (known_object_id, event_row["embedding"]),
+        )
+
+    # Update event
+    conn.execute(
+        """UPDATE events
+           SET match_status = 'known',
+               matched_object_id = ?,
+               match_confidence = 1.0
+           WHERE id = ?""",
+        (known_object_id, event_id),
+    )
+    conn.commit()
+
+    return {"status": "ok", "matched_object_id": known_object_id}
+
+
+@router.post("/{event_id}/dismiss")
+async def dismiss_event(event_id: int):
+    """Set event match_status to 'unknown'."""
+    conn = get_connection()
+
+    cursor = conn.execute("SELECT id FROM events WHERE id = ?", (event_id,))
+    if not cursor.fetchone():
+        raise HTTPException(status_code=404, detail="Event not found")
+
+    conn.execute(
+        "UPDATE events SET match_status = 'unknown' WHERE id = ?",
+        (event_id,),
+    )
+    conn.commit()
+
+    return {"status": "ok"}

compose/hf-pdocker-01/frigate-notify/app/routes/known_objects.py

@@ -0,0 +1,177 @@
+"""Known objects API endpoints for frigate-notify v2."""
+
+import logging
+from typing import Optional
+
+from fastapi import APIRouter, HTTPException, Query
+from fastapi.responses import Response
+
+from database import get_connection
+from models import KnownObjectResponse, KnownObjectUpdate
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/api/known-objects", tags=["known-objects"])
+
+
+@router.get("")
+async def list_known_objects(
+    type: Optional[str] = Query(default=None, pattern="^(person|vehicle|pet)$"),
+):
+    """List all known objects with embedding_count. Optional type filter."""
+    conn = get_connection()
+
+    query = """
+        SELECT
+            ko.id, ko.name, ko.type, ko.action,
+            ko.created_at, ko.updated_at,
+            COUNT(e.id) AS embedding_count
+        FROM known_objects ko
+        LEFT JOIN embeddings e ON ko.id = e.known_object_id
+    """
+    params: list = []
+
+    if type:
+        query += " WHERE ko.type = ?"
+        params.append(type)
+
+    query += " GROUP BY ko.id ORDER BY ko.name"
+
+    cursor = conn.execute(query, params)
+    rows = cursor.fetchall()
+
+    return [
+        {
+            "id": row["id"],
+            "name": row["name"],
+            "type": row["type"],
+            "action": row["action"],
+            "created_at": row["created_at"],
+            "updated_at": row["updated_at"],
+            "embedding_count": row["embedding_count"],
+        }
+        for row in rows
+    ]
+
+
+@router.get("/{object_id}")
+async def get_known_object(object_id: int):
+    """Get a single known object with list of its embeddings (id, created_at only)."""
+    conn = get_connection()
+
+    cursor = conn.execute(
+        "SELECT id, name, type, action, created_at, updated_at FROM known_objects WHERE id = ?",
+        (object_id,),
+    )
+    row = cursor.fetchone()
+    if not row:
+        raise HTTPException(status_code=404, detail="Known object not found")
+
+    # Get embeddings list
+    emb_cursor = conn.execute(
+        "SELECT id, created_at FROM embeddings WHERE known_object_id = ? ORDER BY created_at",
+        (object_id,),
+    )
+    embeddings = [
+        {"id": e["id"], "created_at": e["created_at"]} for e in emb_cursor.fetchall()
+    ]
+
+    return {
+        "id": row["id"],
+        "name": row["name"],
+        "type": row["type"],
+        "action": row["action"],
+        "created_at": row["created_at"],
+        "updated_at": row["updated_at"],
+        "embeddings": embeddings,
+    }
+
+
+@router.get("/{object_id}/thumbnails/{embedding_id}")
+async def get_embedding_thumbnail(object_id: int, embedding_id: int):
+    """Return raw JPEG thumbnail from embeddings table."""
+    conn = get_connection()
+
+    cursor = conn.execute(
+        "SELECT thumbnail FROM embeddings WHERE id = ? AND known_object_id = ?",
+        (embedding_id, object_id),
+    )
+    row = cursor.fetchone()
+    if not row:
+        raise HTTPException(status_code=404, detail="Embedding not found")
+    if row["thumbnail"] is None:
+        raise HTTPException(status_code=404, detail="No thumbnail available")
+
+    return Response(content=row["thumbnail"], media_type="image/jpeg")
+
+
+@router.put("/{object_id}")
+async def update_known_object(object_id: int, body: KnownObjectUpdate):
+    """Update name/type/action for a known object. Sets updated_at."""
+    conn = get_connection()
+
+    cursor = conn.execute(
+        "SELECT id FROM known_objects WHERE id = ?",
+        (object_id,),
+    )
+    if not cursor.fetchone():
+        raise HTTPException(status_code=404, detail="Known object not found")
+
+    updates = []
+    params: list = []
+
+    if body.name is not None:
+        updates.append("name = ?")
+        params.append(body.name)
+    if body.type is not None:
+        updates.append("type = ?")
+        params.append(body.type)
+    if body.action is not None:
+        updates.append("action = ?")
+        params.append(body.action)
+
+    if not updates:
+        raise HTTPException(status_code=400, detail="No fields to update")
+
+    updates.append("updated_at = CURRENT_TIMESTAMP")
+    params.append(object_id)
+
+    conn.execute(
+        f"UPDATE known_objects SET {', '.join(updates)} WHERE id = ?",
+        params,
+    )
+    conn.commit()
+
+    # Return the updated object
+    cursor = conn.execute(
+        "SELECT id, name, type, action, created_at, updated_at FROM known_objects WHERE id = ?",
+        (object_id,),
+    )
+    row = cursor.fetchone()
+
+    return KnownObjectResponse(
+        id=row["id"],
+        name=row["name"],
+        type=row["type"],
+        action=row["action"],
+        created_at=row["created_at"],
+        updated_at=row["updated_at"],
+    )
+
+
+@router.delete("/{object_id}")
+async def delete_known_object(object_id: int):
+    """Delete a known object. Embeddings cascade delete automatically."""
+    conn = get_connection()
+
+    cursor = conn.execute(
+        "SELECT id FROM known_objects WHERE id = ?",
+        (object_id,),
+    )
+    if not cursor.fetchone():
+        raise HTTPException(status_code=404, detail="Known object not found")
+
+    conn.execute("DELETE FROM known_objects WHERE id = ?", (object_id,))
+    conn.commit()
+
+    return {"status": "ok"}

compose/hf-pdocker-01/frigate-notify/app/routes/settings.py

@@ -0,0 +1,78 @@
+"""Settings and stats API endpoints for frigate-notify v2."""
+
+import logging
+from datetime import date
+
+from fastapi import APIRouter
+
+from config import config
+from database import get_connection
+from models import StatsResponse
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/api", tags=["settings"])
+
+
+@router.get("/settings")
+async def get_settings():
+    """Return all settings from DB plus runtime config values."""
+    conn = get_connection()
+    cursor = conn.execute("SELECT key, value FROM settings")
+    db_settings = {row["key"]: row["value"] for row in cursor.fetchall()}
+
+    # Merge with runtime config values
+    return {
+        **db_settings,
+        "recognition_threshold_high": config.RECOGNITION_THRESHOLD_HIGH,
+        "recognition_threshold_low": config.RECOGNITION_THRESHOLD_LOW,
+        "rate_limit_seconds": config.RATE_LIMIT_SECONDS,
+        "allowed_labels": list(config.ALLOWED_LABELS),
+        "min_score": config.MIN_SCORE,
+    }
+
+
+@router.put("/settings")
+async def update_settings(body: dict):
+    """Accept dict body, upsert each key/value into settings table."""
+    conn = get_connection()
+    for key, value in body.items():
+        conn.execute(
+            "INSERT INTO settings (key, value) VALUES (?, ?) "
+            "ON CONFLICT(key) DO UPDATE SET value = excluded.value",
+            (key, str(value)),
+        )
+    conn.commit()
+    return {"status": "ok"}
+
+
+@router.get("/stats", response_model=StatsResponse)
+async def get_stats():
+    """Return event and object counts."""
+    conn = get_connection()
+
+    total = conn.execute("SELECT COUNT(*) FROM events").fetchone()[0]
+    known = conn.execute(
+        "SELECT COUNT(*) FROM events WHERE match_status = 'known'"
+    ).fetchone()[0]
+    unknown = conn.execute(
+        "SELECT COUNT(*) FROM events WHERE match_status = 'unknown'"
+    ).fetchone()[0]
+    unreviewed = conn.execute(
+        "SELECT COUNT(*) FROM events WHERE match_status = 'unreviewed'"
+    ).fetchone()[0]
+    objects_count = conn.execute("SELECT COUNT(*) FROM known_objects").fetchone()[0]
+    today = date.today().isoformat()
+    events_today = conn.execute(
+        "SELECT COUNT(*) FROM events WHERE DATE(created_at) = ?",
+        (today,),
+    ).fetchone()[0]
+
+    return StatsResponse(
+        total_events=total,
+        known_matches=known,
+        unknown_events=unknown,
+        unreviewed=unreviewed,
+        known_objects_count=objects_count,
+        events_today=events_today,
+    )

compose/hf-pdocker-01/frigate-notify/app/static/app.js

@@ -0,0 +1,578 @@
+// Frigate Alerts - Web UI
+(function () {
+    'use strict';
+
+    let currentView = 'dashboard';
+    let currentTagEventId = null;
+    let refreshTimer = null;
+    let knownObjectsCache = [];
+
+    // --- Initialization ---
+
+    document.addEventListener('DOMContentLoaded', () => {
+        setupNavigation();
+        setupTagModal();
+        loadView('dashboard');
+        loadStats();
+    });
+
+    // --- Navigation ---
+
+    function setupNavigation() {
+        document.querySelectorAll('.sidebar-item').forEach(item => {
+            item.addEventListener('click', (e) => {
+                e.preventDefault();
+                const view = item.dataset.view;
+                loadView(view);
+            });
+        });
+    }
+
+    function setActiveNav(view) {
+        document.querySelectorAll('.sidebar-item').forEach(item => {
+            item.classList.toggle('active', item.dataset.view === view);
+        });
+    }
+
+    // --- View Router ---
+
+    function loadView(view) {
+        currentView = view;
+        setActiveNav(view);
+        clearAutoRefresh();
+
+        switch (view) {
+            case 'dashboard':
+                loadDashboard();
+                startAutoRefresh();
+                break;
+            case 'review':
+                loadReview();
+                startAutoRefresh();
+                break;
+            case 'known':
+                loadKnown();
+                break;
+            case 'settings':
+                loadSettings();
+                break;
+        }
+    }
+
+    // --- Auto Refresh ---
+
+    function startAutoRefresh() {
+        refreshTimer = setInterval(() => {
+            if (currentView === 'dashboard') {
+                loadDashboard();
+            } else if (currentView === 'review') {
+                loadReview();
+            }
+            loadStats();
+        }, 30000);
+    }
+
+    function clearAutoRefresh() {
+        if (refreshTimer) {
+            clearInterval(refreshTimer);
+            refreshTimer = null;
+        }
+    }
+
+    // --- Dashboard View ---
+
+    function loadDashboard() {
+        const content = document.getElementById('main-content');
+        content.innerHTML = '<div class="loading">Loading events</div>';
+
+        fetch('/api/events?limit=50')
+            .then(r => r.json())
+            .then(events => {
+                if (!events.length) {
+                    content.innerHTML = `
+                        <h1>Dashboard</h1>
+                        <div class="empty-state">
+                            <p>No events recorded yet.</p>
+                            <p>Events will appear here when Frigate detects objects.</p>
+                        </div>`;
+                    return;
+                }
+                content.innerHTML = `
+                    <div class="page-header">
+                        <h1>Dashboard</h1>
+                    </div>
+                    <div class="filters">
+                        <select id="filter-camera" onchange="window._applyFilters()">
+                            <option value="">All Cameras</option>
+                        </select>
+                        <select id="filter-label" onchange="window._applyFilters()">
+                            <option value="">All Labels</option>
+                        </select>
+                        <select id="filter-status" onchange="window._applyFilters()">
+                            <option value="">All Statuses</option>
+                            <option value="known">Known</option>
+                            <option value="unknown">Unknown</option>
+                            <option value="ambiguous">Ambiguous</option>
+                            <option value="unreviewed">Unreviewed</option>
+                        </select>
+                    </div>
+                    <div id="events-list"></div>`;
+
+                populateFilterOptions(events);
+                renderEvents(events);
+            })
+            .catch(err => {
+                content.innerHTML = `<h1>Dashboard</h1><div class="empty-state"><p>Error loading events: ${err.message}</p></div>`;
+            });
+    }
+
+    function populateFilterOptions(events) {
+        const cameras = [...new Set(events.map(e => e.camera).filter(Boolean))].sort();
+        const labels = [...new Set(events.map(e => e.label).filter(Boolean))].sort();
+
+        const cameraSelect = document.getElementById('filter-camera');
+        const labelSelect = document.getElementById('filter-label');
+
+        if (cameraSelect) {
+            cameras.forEach(c => {
+                const opt = document.createElement('option');
+                opt.value = c;
+                opt.textContent = c;
+                cameraSelect.appendChild(opt);
+            });
+        }
+
+        if (labelSelect) {
+            labels.forEach(l => {
+                const opt = document.createElement('option');
+                opt.value = l;
+                opt.textContent = l;
+                labelSelect.appendChild(opt);
+            });
+        }
+    }
+
+    // Expose filter function globally for inline onchange handlers
+    window._applyFilters = function () {
+        const camera = document.getElementById('filter-camera')?.value || '';
+        const label = document.getElementById('filter-label')?.value || '';
+        const status = document.getElementById('filter-status')?.value || '';
+
+        let url = '/api/events?limit=50';
+        if (camera) url += `&camera=${encodeURIComponent(camera)}`;
+        if (label) url += `&label=${encodeURIComponent(label)}`;
+        if (status) url += `&status=${encodeURIComponent(status)}`;
+
+        fetch(url)
+            .then(r => r.json())
+            .then(events => renderEvents(events))
+            .catch(err => console.error('Filter error:', err));
+    };
+
+    function renderEvents(events) {
+        const container = document.getElementById('events-list');
+        if (!container) return;
+
+        if (!events.length) {
+            container.innerHTML = '<div class="empty-state"><p>No events match the current filters.</p></div>';
+            return;
+        }
+
+        container.innerHTML = events.map(event => `
+            <div class="event-card" data-event-id="${event.id}">
+                <img src="/api/events/${event.id}/snapshot"
+                     onerror="this.style.display='none'"
+                     alt="${event.label || 'snapshot'}">
+                <div class="event-info">
+                    <div class="event-header">
+                        <span>
+                            <span class="event-camera">${escapeHtml(event.camera || 'unknown')}</span>
+                            <span class="event-label"> &mdash; ${escapeHtml(event.label || 'unknown')}</span>
+                            <span class="event-score">(${(event.score * 100).toFixed(0)}%)</span>
+                        </span>
+                        <span class="badge badge-${event.match_status || 'unreviewed'}">${event.match_status || 'unreviewed'}</span>
+                    </div>
+                    <div class="event-time">${formatTime(event.created_at)}</div>
+                    ${event.ai_description ? `<div class="event-description">${escapeHtml(event.ai_description)}</div>` : ''}
+                    ${event.matched_object_name ? `<div class="event-label">Identified as: <strong>${escapeHtml(event.matched_object_name)}</strong></div>` : ''}
+                    <div class="event-actions">
+                        <button class="btn btn-primary btn-sm" onclick="window._tagEvent('${event.id}')">Tag</button>
+                        <button class="btn btn-sm" onclick="window._dismissEvent('${event.id}')">Dismiss</button>
+                    </div>
+                </div>
+            </div>
+        `).join('');
+    }
+
+    // --- Review View ---
+
+    function loadReview() {
+        const content = document.getElementById('main-content');
+        content.innerHTML = '<div class="loading">Loading review queue</div>';
+
+        fetch('/api/events?limit=50&status=unreviewed')
+            .then(r => r.json())
+            .then(events => {
+                if (!events.length) {
+                    content.innerHTML = `
+                        <h1>Review Queue</h1>
+                        <div class="empty-state">
+                            <p>No events to review.</p>
+                            <p>All events have been reviewed or dismissed.</p>
+                        </div>`;
+                    return;
+                }
+                content.innerHTML = `
+                    <div class="page-header">
+                        <h1>Review Queue</h1>
+                        <span>${events.length} event${events.length !== 1 ? 's' : ''} to review</span>
+                    </div>
+                    <div id="events-list"></div>`;
+                renderEvents(events);
+            })
+            .catch(err => {
+                content.innerHTML = `<h1>Review Queue</h1><div class="empty-state"><p>Error loading events: ${err.message}</p></div>`;
+            });
+    }
+
+    // --- Known Objects View ---
+
+    function loadKnown() {
+        const content = document.getElementById('main-content');
+        content.innerHTML = '<div class="loading">Loading known objects</div>';
+
+        fetch('/api/known-objects')
+            .then(r => r.json())
+            .then(objects => {
+                knownObjectsCache = objects;
+
+                if (!objects.length) {
+                    content.innerHTML = `
+                        <h1>Known Objects</h1>
+                        <div class="empty-state">
+                            <p>No known objects registered.</p>
+                            <p>Tag events from the Dashboard to add known objects.</p>
+                        </div>`;
+                    return;
+                }
+
+                content.innerHTML = `
+                    <div class="page-header">
+                        <h1>Known Objects</h1>
+                        <span>${objects.length} object${objects.length !== 1 ? 's' : ''}</span>
+                    </div>
+                    <div class="known-grid">
+                        ${objects.map(obj => `
+                            <div class="known-card" data-object-id="${obj.id}">
+                                <h4>${escapeHtml(obj.name)}</h4>
+                                <span class="type-badge">${escapeHtml(obj.type)}</span>
+                                <div class="embedding-count">${obj.embedding_count || 0} embedding${(obj.embedding_count || 0) !== 1 ? 's' : ''}</div>
+                                ${obj.samples && obj.samples.length ? `
+                                    <div class="known-card-samples">
+                                        ${obj.samples.map(s => `<img src="${s}" onerror="this.style.display='none'" alt="sample">`).join('')}
+                                    </div>
+                                ` : ''}
+                                <div class="known-card-actions">
+                                    <button class="btn btn-danger btn-sm" onclick="window._deleteKnownObject('${obj.id}', '${escapeHtml(obj.name)}')">Delete</button>
+                                </div>
+                            </div>
+                        `).join('')}
+                    </div>`;
+            })
+            .catch(err => {
+                content.innerHTML = `<h1>Known Objects</h1><div class="empty-state"><p>Error loading objects: ${err.message}</p></div>`;
+            });
+    }
+
+    // --- Settings View ---
+
+    function loadSettings() {
+        const content = document.getElementById('main-content');
+        content.innerHTML = '<div class="loading">Loading settings</div>';
+
+        fetch('/api/settings')
+            .then(r => r.json())
+            .then(settings => {
+                content.innerHTML = `
+                    <h1>Settings</h1>
+                    <div class="settings-form">
+                        <div class="settings-section">
+                            <h3>Vision Analysis</h3>
+                            <div class="form-group">
+                                <label>Vision Backend</label>
+                                <select id="setting-vision-backend">
+                                    <option value="haiku" ${settings.vision_backend === 'haiku' ? 'selected' : ''}>Claude Haiku</option>
+                                    <option value="ollama" ${settings.vision_backend === 'ollama' ? 'selected' : ''}>Ollama (Local)</option>
+                                    <option value="both" ${settings.vision_backend === 'both' ? 'selected' : ''}>Both (Haiku + Ollama)</option>
+                                </select>
+                                <div class="help-text">Which AI backend to use for snapshot analysis</div>
+                            </div>
+                        </div>
+
+                        <div class="settings-section">
+                            <h3>Recognition</h3>
+                            <div class="form-group">
+                                <label class="checkbox-label">
+                                    <input type="checkbox" id="setting-recognition-enabled" ${settings.recognition_enabled ? 'checked' : ''}>
+                                    Enable object recognition
+                                </label>
+                                <div class="help-text">Match detected objects against known objects database</div>
+                            </div>
+                        </div>
+
+                        <div class="settings-section">
+                            <h3>Data Retention</h3>
+                            <div class="form-group">
+                                <label>Event Retention (days)</label>
+                                <input type="number" id="setting-retention-days" value="${settings.event_retention_days || 30}" min="1" max="365">
+                                <div class="help-text">How long to keep event records and snapshots</div>
+                            </div>
+                        </div>
+
+                        <div class="form-group">
+                            <button class="btn btn-primary" onclick="window._saveSettings()">Save Settings</button>
+                        </div>
+                    </div>`;
+            })
+            .catch(err => {
+                content.innerHTML = `<h1>Settings</h1><div class="empty-state"><p>Error loading settings: ${err.message}</p></div>`;
+            });
+    }
+
+    window._saveSettings = function () {
+        const settings = {
+            vision_backend: document.getElementById('setting-vision-backend').value,
+            recognition_enabled: document.getElementById('setting-recognition-enabled').checked,
+            event_retention_days: parseInt(document.getElementById('setting-retention-days').value, 10)
+        };
+
+        fetch('/api/settings', {
+            method: 'PUT',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify(settings)
+        })
+            .then(r => {
+                if (!r.ok) throw new Error('Failed to save settings');
+                return r.json();
+            })
+            .then(() => showToast('Settings saved', 'success'))
+            .catch(err => showToast('Error: ' + err.message, 'error'));
+    };
+
+    // --- Stats ---
+
+    function loadStats() {
+        fetch('/api/stats')
+            .then(r => r.json())
+            .then(stats => {
+                const el = document.getElementById('stats-summary');
+                if (!el) return;
+
+                el.innerHTML = `
+                    <div class="stat-item">
+                        <span>Total Events</span>
+                        <span class="stat-value">${stats.total_events || 0}</span>
+                    </div>
+                    <div class="stat-item">
+                        <span>Unreviewed</span>
+                        <span class="stat-value">${stats.unreviewed || 0}</span>
+                    </div>
+                    <div class="stat-item">
+                        <span>Known</span>
+                        <span class="stat-value">${stats.known_matches || 0}</span>
+                    </div>
+                    <div class="stat-item">
+                        <span>Unknown</span>
+                        <span class="stat-value">${stats.unknown_events || 0}</span>
+                    </div>
+                    <div class="stat-item">
+                        <span>Known Objects</span>
+                        <span class="stat-value">${stats.known_objects_count || 0}</span>
+                    </div>`;
+            })
+            .catch(() => {
+                // Stats are non-critical, silently fail
+            });
+    }
+
+    // --- Tag Modal ---
+
+    function setupTagModal() {
+        document.getElementById('tag-cancel').addEventListener('click', closeTagModal);
+        document.getElementById('tag-save').addEventListener('click', saveTag);
+
+        document.getElementById('tag-existing-object').addEventListener('change', (e) => {
+            const newFields = document.getElementById('tag-new-fields');
+            newFields.style.display = e.target.value ? 'none' : 'block';
+        });
+
+        // Close modal on backdrop click
+        document.getElementById('tag-modal').addEventListener('click', (e) => {
+            if (e.target === document.getElementById('tag-modal')) {
+                closeTagModal();
+            }
+        });
+
+        // Close modal on Escape key
+        document.addEventListener('keydown', (e) => {
+            if (e.key === 'Escape') closeTagModal();
+        });
+    }
+
+    window._tagEvent = function (eventId) {
+        currentTagEventId = eventId;
+
+        // Show snapshot in modal
+        const snapshotContainer = document.getElementById('tag-modal-snapshot');
+        snapshotContainer.innerHTML = `<img src="/api/events/${eventId}/snapshot" onerror="this.style.display='none'" alt="snapshot">`;
+
+        // Load known objects for dropdown
+        fetch('/api/known-objects')
+            .then(r => r.json())
+            .then(objects => {
+                knownObjectsCache = objects;
+                const select = document.getElementById('tag-existing-object');
+                select.innerHTML = '<option value="">-- Create new --</option>';
+                objects.forEach(obj => {
+                    const opt = document.createElement('option');
+                    opt.value = obj.id;
+                    opt.textContent = `${obj.name} (${obj.type})`;
+                    select.appendChild(opt);
+                });
+            })
+            .catch(() => { });
+
+        // Reset form
+        document.getElementById('tag-name').value = '';
+        document.getElementById('tag-type').value = 'person';
+        document.getElementById('tag-new-fields').style.display = 'block';
+        document.getElementById('tag-existing-object').value = '';
+
+        document.getElementById('tag-modal').classList.remove('hidden');
+    };
+
+    function closeTagModal() {
+        document.getElementById('tag-modal').classList.add('hidden');
+        currentTagEventId = null;
+    }
+
+    function saveTag() {
+        if (!currentTagEventId) return;
+
+        const existingId = document.getElementById('tag-existing-object').value;
+        let body;
+
+        if (existingId) {
+            body = { known_object_id: existingId };
+        } else {
+            const name = document.getElementById('tag-name').value.trim();
+            const type = document.getElementById('tag-type').value;
+            if (!name) {
+                showToast('Please enter a name', 'error');
+                return;
+            }
+            body = { name: name, type: type };
+        }
+
+        fetch(`/api/events/${currentTagEventId}/tag`, {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify(body)
+        })
+            .then(r => {
+                if (!r.ok) throw new Error('Failed to tag event');
+                return r.json();
+            })
+            .then(() => {
+                showToast('Event tagged successfully', 'success');
+                closeTagModal();
+                loadView(currentView);
+                loadStats();
+            })
+            .catch(err => showToast('Error: ' + err.message, 'error'));
+    }
+
+    // --- Event Actions ---
+
+    window._dismissEvent = function (eventId) {
+        fetch(`/api/events/${eventId}/dismiss`, {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' }
+        })
+            .then(r => {
+                if (!r.ok) throw new Error('Failed to dismiss event');
+                return r.json();
+            })
+            .then(() => {
+                showToast('Event dismissed', 'success');
+                // Remove card from DOM for immediate feedback
+                const card = document.querySelector(`.event-card[data-event-id="${eventId}"]`);
+                if (card) {
+                    card.style.opacity = '0';
+                    card.style.transition = 'opacity 0.3s';
+                    setTimeout(() => card.remove(), 300);
+                }
+                loadStats();
+            })
+            .catch(err => showToast('Error: ' + err.message, 'error'));
+    };
+
+    // --- Known Object Actions ---
+
+    window._deleteKnownObject = function (objectId, name) {
+        if (!confirm(`Delete known object "${name}"? This cannot be undone.`)) return;
+
+        fetch(`/api/known-objects/${objectId}`, {
+            method: 'DELETE'
+        })
+            .then(r => {
+                if (!r.ok) throw new Error('Failed to delete object');
+                return r.json();
+            })
+            .then(() => {
+                showToast(`Deleted "${name}"`, 'success');
+                loadKnown();
+                loadStats();
+            })
+            .catch(err => showToast('Error: ' + err.message, 'error'));
+    };
+
+    // --- Utilities ---
+
+    function escapeHtml(str) {
+        if (!str) return '';
+        const div = document.createElement('div');
+        div.textContent = str;
+        return div.innerHTML;
+    }
+
+    function formatTime(timestamp) {
+        if (!timestamp) return '';
+        const date = new Date(timestamp);
+        const now = new Date();
+        const diffMs = now - date;
+        const diffMins = Math.floor(diffMs / 60000);
+        const diffHours = Math.floor(diffMs / 3600000);
+        const diffDays = Math.floor(diffMs / 86400000);
+
+        if (diffMins < 1) return 'Just now';
+        if (diffMins < 60) return `${diffMins}m ago`;
+        if (diffHours < 24) return `${diffHours}h ago`;
+        if (diffDays < 7) return `${diffDays}d ago`;
+
+        return date.toLocaleDateString() + ' ' + date.toLocaleTimeString([], { hour: '2-digit', minute: '2-digit' });
+    }
+
+    function showToast(message, type) {
+        const toast = document.createElement('div');
+        toast.className = `toast toast-${type}`;
+        toast.textContent = message;
+        document.body.appendChild(toast);
+        setTimeout(() => {
+            toast.style.opacity = '0';
+            toast.style.transition = 'opacity 0.3s';
+            setTimeout(() => toast.remove(), 300);
+        }, 3000);
+    }
+
+})();

compose/hf-pdocker-01/frigate-notify/app/static/index.html

@@ -0,0 +1,61 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Frigate Alerts</title>
+    <link rel="stylesheet" href="/static/style.css">
+</head>
+<body>
+    <nav id="sidebar">
+        <div class="sidebar-header">
+            <h2>Frigate Alerts</h2>
+        </div>
+        <div class="sidebar-section">
+            <a href="#" class="sidebar-item active" data-view="dashboard">Dashboard</a>
+            <a href="#" class="sidebar-item" data-view="review">Review Queue</a>
+            <a href="#" class="sidebar-item" data-view="known">Known Objects</a>
+            <a href="#" class="sidebar-item" data-view="settings">Settings</a>
+        </div>
+        <div class="sidebar-section sidebar-stats">
+            <div id="stats-summary"></div>
+        </div>
+    </nav>
+    <main id="content">
+        <div id="main-content"></div>
+    </main>
+
+    <div id="tag-modal" class="modal hidden">
+        <div class="modal-content">
+            <h3>Tag as Known Object</h3>
+            <div id="tag-modal-snapshot"></div>
+            <div class="form-group">
+                <label>Existing object:</label>
+                <select id="tag-existing-object">
+                    <option value="">-- Create new --</option>
+                </select>
+            </div>
+            <div id="tag-new-fields">
+                <div class="form-group">
+                    <label>Name:</label>
+                    <input type="text" id="tag-name" placeholder="e.g., Jeremy, Blue F-150, Max">
+                </div>
+                <div class="form-group">
+                    <label>Type:</label>
+                    <select id="tag-type">
+                        <option value="person">Person</option>
+                        <option value="vehicle">Vehicle</option>
+                        <option value="pet">Pet</option>
+                    </select>
+                </div>
+            </div>
+            <div class="modal-actions">
+                <button id="tag-save" class="btn btn-primary">Save</button>
+                <button id="tag-cancel" class="btn">Cancel</button>
+            </div>
+        </div>
+    </div>
+
+    <script src="/static/app.js"></script>
+</body>
+</html>

compose/hf-pdocker-01/frigate-notify/app/static/style.css

@@ -0,0 +1,534 @@
+* {
+    margin: 0;
+    padding: 0;
+    box-sizing: border-box;
+}
+
+body {
+    font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+    background: #1a1a2e;
+    color: #e0e0e0;
+    display: flex;
+    min-height: 100vh;
+}
+
+/* Sidebar */
+#sidebar {
+    width: 220px;
+    background: #16213e;
+    padding: 20px 0;
+    position: fixed;
+    height: 100vh;
+    overflow-y: auto;
+}
+
+.sidebar-header {
+    padding: 0 20px 20px;
+    border-bottom: 1px solid #0f3460;
+}
+
+.sidebar-header h2 {
+    color: #00b4d8;
+    font-size: 1.2em;
+}
+
+.sidebar-section {
+    padding: 10px 0;
+}
+
+.sidebar-item {
+    display: block;
+    padding: 10px 20px;
+    color: #a0a0a0;
+    text-decoration: none;
+    transition: all 0.2s;
+}
+
+.sidebar-item:hover {
+    background: #0f3460;
+    color: #fff;
+}
+
+.sidebar-item.active {
+    background: #0f3460;
+    color: #00b4d8;
+    border-left: 3px solid #00b4d8;
+}
+
+.sidebar-stats {
+    padding: 20px;
+    font-size: 0.85em;
+    color: #888;
+}
+
+/* Main content */
+#content {
+    margin-left: 220px;
+    flex: 1;
+    padding: 20px;
+}
+
+/* Page headers */
+h1 {
+    margin-bottom: 20px;
+}
+
+.page-header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-bottom: 20px;
+}
+
+/* Filters */
+.filters {
+    display: flex;
+    gap: 10px;
+    margin-bottom: 20px;
+    flex-wrap: wrap;
+}
+
+.filters select,
+.filters input {
+    padding: 6px 10px;
+    background: #16213e;
+    border: 1px solid #0f3460;
+    color: #e0e0e0;
+    border-radius: 4px;
+}
+
+.filters select:focus,
+.filters input:focus {
+    outline: none;
+    border-color: #00b4d8;
+}
+
+/* Event cards */
+.event-card {
+    background: #16213e;
+    border-radius: 8px;
+    padding: 15px;
+    margin-bottom: 15px;
+    display: flex;
+    gap: 15px;
+    transition: border-color 0.2s;
+    border: 1px solid transparent;
+}
+
+.event-card:hover {
+    border-color: #0f3460;
+}
+
+.event-card img {
+    width: 160px;
+    height: 120px;
+    object-fit: cover;
+    border-radius: 4px;
+    background: #1a1a2e;
+}
+
+.event-info {
+    flex: 1;
+}
+
+.event-header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-bottom: 8px;
+}
+
+.event-camera {
+    font-weight: bold;
+    color: #00b4d8;
+}
+
+.event-label {
+    color: #a0a0a0;
+}
+
+.event-score {
+    color: #888;
+    font-size: 0.85em;
+}
+
+.event-description {
+    color: #ccc;
+    margin: 8px 0;
+    font-size: 0.9em;
+    line-height: 1.4;
+}
+
+.event-time {
+    color: #666;
+    font-size: 0.8em;
+    margin-bottom: 6px;
+}
+
+.event-actions {
+    margin-top: 10px;
+    display: flex;
+    gap: 8px;
+}
+
+/* Status badges */
+.badge {
+    padding: 3px 10px;
+    border-radius: 12px;
+    font-size: 0.8em;
+    font-weight: bold;
+}
+
+.badge-known {
+    background: #2d6a4f;
+    color: #95d5b2;
+}
+
+.badge-unknown {
+    background: #9a4c1a;
+    color: #f4a261;
+}
+
+.badge-ambiguous {
+    background: #7c6f09;
+    color: #ffd166;
+}
+
+.badge-unreviewed {
+    background: #444;
+    color: #aaa;
+}
+
+/* Buttons */
+.btn {
+    padding: 6px 14px;
+    border: none;
+    border-radius: 4px;
+    cursor: pointer;
+    font-size: 0.85em;
+    transition: all 0.2s;
+    color: #ccc;
+    background: #2a2a4a;
+}
+
+.btn:hover {
+    background: #3a3a5a;
+    color: #fff;
+}
+
+.btn-primary {
+    background: #0f3460;
+    color: #fff;
+}
+
+.btn-primary:hover {
+    background: #00b4d8;
+}
+
+.btn-danger {
+    background: #7c2929;
+    color: #fff;
+}
+
+.btn-danger:hover {
+    background: #c0392b;
+}
+
+.btn-sm {
+    padding: 4px 10px;
+    font-size: 0.8em;
+}
+
+/* Modal */
+.modal {
+    position: fixed;
+    top: 0;
+    left: 0;
+    width: 100%;
+    height: 100%;
+    background: rgba(0, 0, 0, 0.7);
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    z-index: 1000;
+}
+
+.modal.hidden {
+    display: none;
+}
+
+.modal-content {
+    background: #16213e;
+    border-radius: 8px;
+    padding: 25px;
+    width: 450px;
+    max-width: 90vw;
+}
+
+.modal-content h3 {
+    margin-bottom: 15px;
+    color: #00b4d8;
+}
+
+.modal-actions {
+    display: flex;
+    gap: 10px;
+    justify-content: flex-end;
+    margin-top: 15px;
+}
+
+#tag-modal-snapshot {
+    margin-bottom: 15px;
+}
+
+#tag-modal-snapshot img {
+    width: 100%;
+    max-height: 200px;
+    object-fit: cover;
+    border-radius: 4px;
+}
+
+/* Form elements */
+.form-group {
+    margin-bottom: 12px;
+}
+
+.form-group label {
+    display: block;
+    margin-bottom: 4px;
+    color: #a0a0a0;
+    font-size: 0.9em;
+}
+
+.form-group input,
+.form-group select {
+    width: 100%;
+    padding: 8px 10px;
+    background: #1a1a2e;
+    border: 1px solid #0f3460;
+    color: #e0e0e0;
+    border-radius: 4px;
+}
+
+.form-group input:focus,
+.form-group select:focus {
+    outline: none;
+    border-color: #00b4d8;
+}
+
+.form-group input[type="checkbox"] {
+    width: auto;
+    margin-right: 8px;
+}
+
+.form-group .checkbox-label {
+    display: flex;
+    align-items: center;
+    cursor: pointer;
+}
+
+.form-group .help-text {
+    font-size: 0.8em;
+    color: #666;
+    margin-top: 4px;
+}
+
+/* Known objects grid */
+.known-grid {
+    display: grid;
+    grid-template-columns: repeat(auto-fill, minmax(250px, 1fr));
+    gap: 15px;
+}
+
+.known-card {
+    background: #16213e;
+    border-radius: 8px;
+    padding: 15px;
+    border: 1px solid transparent;
+    transition: border-color 0.2s;
+}
+
+.known-card:hover {
+    border-color: #0f3460;
+}
+
+.known-card h4 {
+    color: #00b4d8;
+    margin-bottom: 5px;
+}
+
+.known-card .type-badge {
+    font-size: 0.8em;
+    color: #a0a0a0;
+    text-transform: capitalize;
+}
+
+.known-card .embedding-count {
+    font-size: 0.8em;
+    color: #666;
+    margin-top: 6px;
+}
+
+.known-card .known-card-actions {
+    margin-top: 10px;
+    display: flex;
+    gap: 8px;
+}
+
+.known-card .known-card-samples {
+    display: flex;
+    gap: 5px;
+    margin-top: 10px;
+    overflow-x: auto;
+}
+
+.known-card .known-card-samples img {
+    width: 60px;
+    height: 60px;
+    object-fit: cover;
+    border-radius: 4px;
+    background: #1a1a2e;
+}
+
+/* Settings */
+.settings-form {
+    max-width: 600px;
+}
+
+.settings-form .form-group {
+    margin-bottom: 15px;
+}
+
+.settings-section {
+    margin-bottom: 30px;
+}
+
+.settings-section h3 {
+    color: #00b4d8;
+    margin-bottom: 15px;
+    padding-bottom: 8px;
+    border-bottom: 1px solid #0f3460;
+}
+
+/* Stats in sidebar */
+.stat-item {
+    display: flex;
+    justify-content: space-between;
+    margin-bottom: 8px;
+}
+
+.stat-value {
+    color: #00b4d8;
+    font-weight: bold;
+}
+
+/* Empty state */
+.empty-state {
+    text-align: center;
+    color: #666;
+    padding: 60px 20px;
+}
+
+.empty-state p {
+    margin-top: 10px;
+    font-size: 0.9em;
+}
+
+/* Loading spinner */
+.loading {
+    text-align: center;
+    padding: 40px;
+    color: #666;
+}
+
+.loading::after {
+    content: '';
+    display: inline-block;
+    width: 20px;
+    height: 20px;
+    border: 2px solid #0f3460;
+    border-top-color: #00b4d8;
+    border-radius: 50%;
+    animation: spin 0.8s linear infinite;
+    margin-left: 10px;
+    vertical-align: middle;
+}
+
+@keyframes spin {
+    to { transform: rotate(360deg); }
+}
+
+/* Toast notifications */
+.toast {
+    position: fixed;
+    bottom: 20px;
+    right: 20px;
+    padding: 12px 20px;
+    border-radius: 6px;
+    color: #fff;
+    font-size: 0.9em;
+    z-index: 2000;
+    animation: slideIn 0.3s ease-out;
+}
+
+.toast-success {
+    background: #2d6a4f;
+}
+
+.toast-error {
+    background: #7c2929;
+}
+
+@keyframes slideIn {
+    from {
+        transform: translateY(20px);
+        opacity: 0;
+    }
+    to {
+        transform: translateY(0);
+        opacity: 1;
+    }
+}
+
+/* Responsive */
+@media (max-width: 768px) {
+    #sidebar {
+        width: 100%;
+        height: auto;
+        position: relative;
+    }
+
+    .sidebar-section {
+        display: flex;
+        flex-wrap: wrap;
+    }
+
+    .sidebar-item {
+        padding: 8px 15px;
+    }
+
+    .sidebar-stats {
+        display: none;
+    }
+
+    #content {
+        margin-left: 0;
+    }
+
+    body {
+        flex-direction: column;
+    }
+
+    .event-card {
+        flex-direction: column;
+    }
+
+    .event-card img {
+        width: 100%;
+        height: auto;
+    }
+
+    .known-grid {
+        grid-template-columns: 1fr;
+    }
+}

compose/hf-pdocker-01/frigate-notify/app/vision.py

@@ -1,7 +1,11 @@
 import base64
 import logging
+from typing import Optional
+
 import anthropic
 
+from ollama_client import OllamaClient
+
 logger = logging.getLogger(__name__)
 
 PROMPT = (
@@ -40,3 +44,66 @@ def analyze_snapshot(client: anthropic.Anthropic, image_bytes: bytes) -> str | N
     except Exception:
         logger.exception("Claude Vision API failed")
         return None
+
+
+async def analyze_snapshot_ollama(
+    ollama_client: OllamaClient, image_bytes: bytes
+) -> str | None:
+    """Send a snapshot to Ollama vision model for description.
+
+    Args:
+        ollama_client: Configured OllamaClient instance.
+        image_bytes: Raw image bytes (JPEG).
+
+    Returns:
+        Description string or None on failure.
+    """
+    return await ollama_client.analyze_image(image_bytes, PROMPT)
+
+
+async def get_description(
+    image_bytes: bytes,
+    vision_backend: str,
+    claude_client: Optional[anthropic.Anthropic] = None,
+    ollama_client: Optional[OllamaClient] = None,
+) -> str | None:
+    """Get a scene description using the configured vision backend.
+
+    Args:
+        image_bytes: Raw image bytes (JPEG).
+        vision_backend: One of "haiku", "ollama", or "both".
+            "both" tries Ollama first, falls back to Haiku.
+        claude_client: Anthropic client (required for "haiku" and "both").
+        ollama_client: OllamaClient instance (required for "ollama" and "both").
+
+    Returns:
+        Description string or None if all backends fail.
+    """
+    if vision_backend == "ollama":
+        if ollama_client is None:
+            logger.error("Ollama backend selected but no client provided")
+            return None
+        return await analyze_snapshot_ollama(ollama_client, image_bytes)
+
+    if vision_backend == "haiku":
+        if claude_client is None:
+            logger.error("Haiku backend selected but no client provided")
+            return None
+        return analyze_snapshot(claude_client, image_bytes)
+
+    if vision_backend == "both":
+        # Try Ollama first, fall back to Haiku
+        if ollama_client is not None:
+            result = await analyze_snapshot_ollama(ollama_client, image_bytes)
+            if result is not None:
+                return result
+            logger.info("Ollama failed, falling back to Haiku")
+
+        if claude_client is not None:
+            return analyze_snapshot(claude_client, image_bytes)
+
+        logger.error("Both backend selected but no clients provided")
+        return None
+
+    logger.error("Unknown vision backend: %s", vision_backend)
+    return None

compose/hf-pdocker-01/frigate-notify/docker-compose.yml

@@ -12,8 +12,8 @@ services:
       - MQTT_HOST=192.168.86.192
       - MQTT_PORT=1883
       - MATRIX_HOMESERVER=http://192.168.86.192:8008
-      - CLIP_SERVICE_URL=http://192.168.86.196:5200
+      - CLIP_SERVICE_URL=http://localhost:5200
-      - OLLAMA_URL=http://192.168.86.196:11434
+      - OLLAMA_URL=http://192.168.86.150:11434
       - OLLAMA_MODEL=llava:13b
       - DB_PATH=/data/frigate-notify.db
     volumes:

compose/hf-pdocker-01/frigate/docker-compose.yml

@@ -13,8 +13,11 @@ services:
       - /mnt/docker-data/configs/frigate/config:/config
       - /mnt/frigate-recordings:/media/frigate
       - /etc/localtime:/etc/localtime:ro
+    tmpfs:
+      - /tmp/cache:size=4G
     devices:
       - /dev/dri:/dev/dri
+      - /dev/bus/usb:/dev/bus/usb
     mem_limit: 12G
     memswap_limit: 12G
     healthcheck: