Fix service status

status-service/monitors.py

@@ -184,7 +184,8 @@ class ServiceMonitor:
         self,
         service_name: str,
         result: tuple,
-        now: datetime
+        now: datetime,
+        suppress_alerts: bool = False
     ):
         """Process check result with DB persistence and alerting."""
         if isinstance(result, Exception):
@@ -221,13 +222,14 @@ class ServiceMonitor:
         if stats["total_checks"] > 0:
             svc.uptime_percent = stats["uptime_percent"]
 
-        # Handle incident tracking and alerting
+        # Handle incident tracking and alerting (skip alerts during grace period)
         if is_down and not was_down:
             # Service just went down
             svc.last_incident = now
             incident_id = create_incident(service_name, status.value, message)
-            await alert_service_down(service_name, svc.display_name, message)
-            mark_incident_notified(incident_id)
+            if not suppress_alerts:
+                await alert_service_down(service_name, svc.display_name, message)
+                mark_incident_notified(incident_id)
 
         elif not is_down and was_down:
             # Service recovered
@@ -236,7 +238,8 @@ class ServiceMonitor:
                 started_at = datetime.fromisoformat(open_incident["started_at"])
                 downtime_minutes = int((now - started_at).total_seconds() / 60)
                 resolve_incident(service_name)
-                await alert_service_recovered(service_name, svc.display_name, downtime_minutes)
+                if not suppress_alerts:
+                    await alert_service_recovered(service_name, svc.display_name, downtime_minutes)
 
     async def check_all_services(
         self,
@@ -244,7 +247,8 @@ class ServiceMonitor:
         frontend_url: str,
         bot_url: str,
         external_url: str = "",
-        public_url: str = ""
+        public_url: str = "",
+        suppress_alerts: bool = False
     ):
         """Check all services concurrently."""
         now = datetime.now()
@@ -262,7 +266,7 @@ class ServiceMonitor:
         # Process results
         service_names = ["backend", "database", "frontend", "bot", "external"]
         for i, service_name in enumerate(service_names):
-            await self._process_check_result(service_name, results[i], now)
+            await self._process_check_result(service_name, results[i], now, suppress_alerts)
 
         # Check SSL certificate (if public URL is HTTPS)
         if public_url and public_url.startswith("https://"):
@@ -270,7 +274,15 @@ class ServiceMonitor:
 
         self.last_check = now
 
-    def get_all_statuses(self) -> dict[str, ServiceStatus]:
+    def get_all_statuses(self, period_hours: int = 24) -> dict[str, ServiceStatus]:
+        """Get all service statuses with data for specified period."""
+        # Update historical data for requested period
+        for name, svc in self.services.items():
+            svc.latency_history = get_latency_history(name, hours=period_hours)
+            svc.avg_latency_24h = get_avg_latency(name, hours=period_hours)
+            stats = get_uptime_stats(name, hours=period_hours)
+            if stats["total_checks"] > 0:
+                svc.uptime_percent = stats["uptime_percent"]
         return self.services
 
     def get_overall_status(self) -> Status: