feat: SQLite persistence, non-blocking inference, modular frontend

Backend:
- Persist alert events and robot delivery counters in SQLite (data/app.db,
  YOLO_DB_PATH override); EventStore keeps its interface, DeliveryStatsStore
  uses read/write-through UPSERT; in-memory fallback remains for standalone
  AlertManager use
- Serve /api/detect from a sync endpoint and serialize YOLO inference with a
  lock, so concurrent requests no longer block the event loop
- Unify single-image and session detection: requests without session_id
  share the fixed single-image session and run full frame confirmation
- Store UTC Z-suffixed timestamps for sortable string comparison; close
  executor and database on shutdown via FastAPI lifespan

Frontend:
- Split app.js into ES modules (main.js + modules/{dom,api,ui,charts,store}
  + views/{dashboard,inspection,events,robots,robotCards}), no build step
- Escape all server data interpolated into innerHTML; guard missing
  event.classes; replace lazy element ID list with memoized qs()
- Remove hardcoded fake stats (trend badge, device donut segment)

Docs:
- Rewrite README: accurate weight policy (only trained best.pt committed,
  no Git LFS), SQLite persistence, single-worker note, data asset inventory
- Align models/pretrained/README.md with actual files; add YOLO_DB_PATH to
  .env.example; add persistence unit tests; ruff clean

.env.example

@@ -4,6 +4,9 @@ YOLO_IMGSZ=768
 YOLO_CONF=0.40
 YOLO_IOU=0.45
 
+# SQLite 数据库路径（事件与机器人投递统计持久化）。
+YOLO_DB_PATH=data/app.db
+
 # 企业微信群机器人，可留空。
 WECHAT_WEBHOOK_URL=