ops(multiplayer): add control-plane alert rules

deploy/observability/prometheus-rules.yaml

@@ -0,0 +1,54 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: cosmic-clash-control-plane
+  namespace: cosmic-clash
+  labels:
+    app.kubernetes.io/name: cosmic-clash
+    app.kubernetes.io/component: observability
+spec:
+  groups:
+    - name: cosmic-clash.control-plane
+      rules:
+        - alert: CosmicClashControlPlaneAPIP95High
+          expr: |
+            histogram_quantile(
+              0.95,
+              sum by (le, operation) (
+                rate(cosmic_clash_api_latency_seconds_bucket[5m])
+              )
+            ) > 0.25
+          for: 5m
+          labels:
+            severity: page
+            owner: api
+          annotations:
+            summary: Cosmic Clash control-plane API p95 latency is high
+            description: >-
+              The 5-minute p95 latency for operation {{ $labels.operation }}
+              has exceeded the 250 ms API SLO for 5 minutes.
+            runbook_url: https://example.invalid/cosmic-clash/runbooks/control-plane-api
+        - alert: CosmicClashControlPlaneAPI5xxHigh
+          expr: |
+            (
+              sum by (operation) (
+                rate(cosmic_clash_api_requests_total{status="5xx"}[5m])
+              )
+              /
+              clamp_min(
+                sum by (operation) (
+                  rate(cosmic_clash_api_requests_total[5m])
+                ),
+                0.001
+              )
+            ) > 0.01
+          for: 5m
+          labels:
+            severity: page
+            owner: api
+          annotations:
+            summary: Cosmic Clash control-plane API 5xx rate is high
+            description: >-
+              The 5-minute 5xx ratio for operation {{ $labels.operation }}
+              has exceeded 1 percent for 5 minutes.
+            runbook_url: https://example.invalid/cosmic-clash/runbooks/control-plane-api