fix(prometheus): bump memory limit from 1Gi to 2Gi due to OOM

fix(litellm): add resource limits (512Mi/1Gi) to prevent unbounded memory consumption

litellm/litellm.yaml

@@ -112,6 +112,13 @@ spec:
         env:
         - name: STORE_MODEL_IN_DB
           value: "True"
+        resources:
+          requests:
+            memory: "512Mi"
+            cpu: "250m"
+          limits:
+            memory: "1Gi"
+            cpu: "500m"
       volumes:
         - name: config-volume
           configMap:

monitoring/prometheus-deployment.yaml

@@ -15,10 +15,9 @@ spec:
       labels:
         app: prometheus
     spec:
-      # Target the nucbox (amd64, 24Gi RAM) which is the only node with enough memory for Prometheus.
+      # Prevent scheduling on Raspberry Pi due to resource requirements (512Mi-1Gi memory, 500m-1000m CPU)
       nodeSelector:
-        kubernetes.io/os: linux
+        hardware: high-memory
-        kubernetes.io/arch: amd64
       serviceAccountName: prometheus
       containers:
         - name: prometheus
@@ -40,10 +39,10 @@ spec:
               mountPath: /prometheus
           resources:
             requests:
-              memory: "512Mi"
+              memory: "1Gi"
               cpu: "500m"
             limits:
-              memory: "1Gi"
+              memory: "2Gi"
               cpu: "1000m"
       volumes:
         - name: prometheus-config