fix non-alerting of overdue hosts

hbd/server/udp.py

@@ -171,6 +171,24 @@ def dicttos(ID, d):
 DROPOVERDUE = 7 * 24 * 3600  # seconds before an overdue host becomes UNKNOWN
 
 
+def _set_connectivity_alert(host, afam, level_name):
+    """Update (or clear) a connectivity alert_state entry for a host/address-family.
+
+    level_name is "CRITICAL", "WARNING", or "OK".  "OK" removes the entry so
+    that recovered hosts don't clutter the Alerts Dashboard.
+    """
+    from .threshold import AlertState, AlertLevel
+    metric_path = f"connectivity.{afam}"
+    level = getattr(AlertLevel, level_name, AlertLevel.OK)
+    if level == AlertLevel.OK:
+        host.alert_states.pop(metric_path, None)
+        return
+    if metric_path not in host.alert_states:
+        host.alert_states[metric_path] = AlertState(metric_path)
+    state = host.alert_states[metric_path]
+    state.update(level, level_name)
+
+
 def _make_timer_callbacks(uname, host, ctx):
     """Return (on_overdue, on_unknown) async callbacks for connection timer logic.
 
@@ -182,6 +200,7 @@ def _make_timer_callbacks(uname, host, ctx):
 
     async def on_unknown(connection):
         connection.newstate(connection.__class__.UNKNOWN, connection.lastbeat)
+        # Keep connectivity alert active when host transitions to unknown
         if msg_to_websockets:
             msg_to_websockets("host", host.stateinfo())
 
@@ -196,6 +215,8 @@ def _make_timer_callbacks(uname, host, ctx):
             uname,
             notify_mod.Notification(title=f"[CRITICAL] {uname}", body=msg, level="CRITICAL"),
         )
+        # Track in alert_states so the Alerts Dashboard shows this
+        _set_connectivity_alert(host, connection.afam, "CRITICAL")
         if threshold_checker:
             threshold_checker.check_value(
                 host_name=uname,
@@ -410,6 +431,8 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
     if conn.getstate() != hbdcls.Connection.UP:
         lasts = conn.state
         d = conn.newstate(hbdcls.Connection.UP, now)
+        # Clear connectivity alert now that the host is back up
+        _set_connectivity_alert(host, conn.afam, "OK")
         # Don't log/notify RECOVER for a brand-new host seen for the first time —
         # it was never down, it just hasn't been seen before.
         if not newh:
@@ -436,6 +459,7 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
             notify_mod.Notification(title=f"[INFO] {uname}", body=m, level="INFO"),
         )
         conn.newstate(hbdcls.Connection.DOWN, now)
+        _set_connectivity_alert(host, conn.afam, "CRITICAL")
 
     if interval > 0:
         host.interval = interval