feat: persistent monitor_enabled flag + auto-start keepalive on boot

Makes live monitoring (and therefore alerting) genuinely 24/7 and
restart-surviving, instead of runtime-only keepalive.

- NL43Config.monitor_enabled (default True) + migrate_add_monitor_enabled.py.
- On startup, auto-start keepalive monitors for every monitor_enabled +
  tcp_enabled unit — so feeds/alerts resume after a restart with no manual step.
- /monitor/start and /monitor/stop now PERSIST monitor_enabled (start=True,
  stop=False) in addition to applying keepalive at runtime, so the toggle
  sticks. Roster output includes monitor_enabled for the admin UI to read.

On by default: configure a unit -> it's monitored 24/7 unless toggled off.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

app/main.py

@@ -38,6 +38,25 @@ async def lifespan(app: FastAPI):
     await poller.start()
     logger.info("Background poller started")
 
+    # Auto-start keepalive live monitors for units configured for 24/7 monitoring
+    # (monitor_enabled). This is what keeps alerting running unattended across
+    # restarts — without it a feed only runs while someone has the live view open.
+    try:
+        from app.monitor import monitor_manager
+        from app.database import SessionLocal
+        from app.models import NL43Config
+        db = SessionLocal()
+        try:
+            units = db.query(NL43Config).filter_by(monitor_enabled=True, tcp_enabled=True).all()
+            for cfg in units:
+                m = await monitor_manager.get(cfg.unit_id)
+                await m.set_keepalive(True)
+                logger.info(f"Auto-started keepalive monitor for {cfg.unit_id}")
+        finally:
+            db.close()
+    except Exception as e:
+        logger.error(f"Failed to auto-start monitors: {e}")
+
     yield  # Application runs
 
     # Shutdown

app/models.py

@@ -23,6 +23,10 @@ class NL43Config(Base):
     poll_interval_seconds = Column(Integer, nullable=True, default=60)  # Polling interval (10-3600 seconds)
     poll_enabled = Column(Boolean, default=True)  # Enable/disable background polling for this device
 
+    # Live monitor (fan-out DOD feed). Keepalive runs it 24/7 even with no viewer,
+    # which is what makes alerting continuous. On by default; toggleable from the UI.
+    monitor_enabled = Column(Boolean, default=True)
+
 
 class NL43Status(Base):
     """

app/routers.py

@@ -295,22 +295,32 @@ async def monitor_stream(websocket: WebSocket, unit_id: str):
 
 
 @router.post("/{unit_id}/monitor/start")
-async def monitor_start(unit_id: str):
+async def monitor_start(unit_id: str, db: Session = Depends(get_db)):
-    """Keep the device's feed running even with no browser attached, so alerting
+    """Enable 24/7 keepalive monitoring: persist monitor_enabled and start the feed
-    evaluates continuously. Runtime-only (resets on restart)."""
+    now, so alerting evaluates continuously even with no viewer. Survives restarts
+    (auto-started on boot from the persisted flag)."""
+    cfg = db.query(NL43Config).filter_by(unit_id=unit_id).first()
+    if cfg:
+        cfg.monitor_enabled = True
+        db.commit()
     from app.monitor import monitor_manager
     monitor = await monitor_manager.get(unit_id)
     await monitor.set_keepalive(True)
-    return {"status": "ok", "unit_id": unit_id, "running": monitor.running, "keepalive": True}
+    return {"status": "ok", "unit_id": unit_id, "monitor_enabled": True, "running": monitor.running}
 
 
 @router.post("/{unit_id}/monitor/stop")
-async def monitor_stop(unit_id: str):
+async def monitor_stop(unit_id: str, db: Session = Depends(get_db)):
-    """Drop the keep-alive; the feed stops once no browser subscribers remain."""
+    """Disable keepalive monitoring: persist monitor_enabled=False and drop the
+    keepalive (the feed stops once no browser subscribers remain)."""
+    cfg = db.query(NL43Config).filter_by(unit_id=unit_id).first()
+    if cfg:
+        cfg.monitor_enabled = False
+        db.commit()
     from app.monitor import monitor_manager
     monitor = await monitor_manager.get(unit_id)
     await monitor.set_keepalive(False)
-    return {"status": "ok", "unit_id": unit_id, "keepalive": False}
+    return {"status": "ok", "unit_id": unit_id, "monitor_enabled": False}
 
 
 @router.get("/_monitor/status")
@@ -501,6 +511,7 @@ def get_roster(db: Session = Depends(get_db)):
             "web_enabled": cfg.web_enabled,
             "poll_enabled": cfg.poll_enabled,
             "poll_interval_seconds": cfg.poll_interval_seconds,
+            "monitor_enabled": cfg.monitor_enabled,
             "status": None
         }
 

migrate_add_monitor_enabled.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+"""
+Migration: add monitor_enabled column to nl43_config.
+
+Controls whether the live fan-out DOD monitor is kept alive 24/7 for a unit
+(which is what makes alerting continuous). Defaults to enabled. Run once per DB.
+"""
+
+import sqlite3
+import sys
+from pathlib import Path
+
+DB_PATH = Path(__file__).parent / "data" / "slmm.db"
+
+
+def migrate():
+    if not DB_PATH.exists():
+        print(f"Database not found at {DB_PATH}")
+        print("No migration needed - database will be created with new schema")
+        return
+
+    conn = sqlite3.connect(DB_PATH)
+    cursor = conn.cursor()
+    try:
+        cursor.execute("PRAGMA table_info(nl43_config)")
+        columns = [row[1] for row in cursor.fetchall()]
+
+        if "monitor_enabled" in columns:
+            print("✓ monitor_enabled column already exists, no migration needed")
+            return
+
+        print("Adding monitor_enabled column (default enabled)...")
+        # SQLite stores booleans as 0/1; default 1 = enabled.
+        cursor.execute("ALTER TABLE nl43_config ADD COLUMN monitor_enabled BOOLEAN DEFAULT 1")
+        conn.commit()
+        print("✓ Added monitor_enabled column")
+        print("\n✓ Migration completed successfully!")
+
+    except Exception as e:
+        conn.rollback()
+        print(f"✗ Migration failed: {e}", file=sys.stderr)
+        sys.exit(1)
+    finally:
+        conn.close()
+
+
+if __name__ == "__main__":
+    migrate()