fix(helm): require the metrics server before rendering the gateway ServiceMonitor

The http port serves /metrics/ behind virtual-key auth, so a ServiceMonitor
pointed at it only collects 401s and the RPM/TPM HPA metrics never appear

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

helm/litellm-helm/values.yaml

@@ -260,8 +260,10 @@ keda:
   # carry: KEDA divides the release-wide rate by it to pick the replica count.
   # The queries select samples by the release namespace and the `job` label the
   # chart's ServiceMonitor produces (the metrics Service name), so enable
-  # serviceMonitor below. Tokens are counted at completion, so TPM trails long
-  # streams. serverAddress is required once either target is set.
+  # serviceMonitor below together with metricsServer: the http port serves
+  # /metrics/ behind virtual-key auth and answers an unauthenticated scrape
+  # with 401. Tokens are counted at completion, so TPM trails long streams.
+  # serverAddress is required once either target is set.
   prometheus:
     serverAddress: ""
     requestsPerMinute: ""

helm/litellm/templates/gateway/servicemonitor.yaml

@@ -1,4 +1,7 @@
 {{- if and .Values.gateway.enabled .Values.gateway.serviceMonitor.enabled }}
+{{- if not .Values.gateway.metricsServer.enabled }}
+{{- fail "gateway.serviceMonitor.enabled requires gateway.metricsServer.enabled: the http port serves /metrics/ behind virtual-key auth, so an unauthenticated scrape gets 401" }}
+{{- end }}
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
@@ -17,7 +20,7 @@ spec:
     matchNames:
       - {{ .Release.Namespace | quote }}
   endpoints:
-    - port: {{ ternary "metrics" "http" .Values.gateway.metricsServer.enabled }}
+    - port: metrics
       path: /metrics/
       interval: {{ .Values.gateway.serviceMonitor.interval }}
       scrapeTimeout: {{ .Values.gateway.serviceMonitor.scrapeTimeout }}

helm/litellm/tests/hpa_workload_metrics_tests.yaml

@@ -141,13 +141,22 @@ tests:
       - hasDocuments:
           count: 0
 
-  - it: scrapes each gateway pod through the http port when the metrics sidecar is off
+  - it: refuses a ServiceMonitor without the metrics server, whose http port needs a bearer token
+    template: gateway/servicemonitor.yaml
+    set:
+      gateway.serviceMonitor.enabled: true
+    asserts:
+      - failedTemplate:
+          errorPattern: gateway.serviceMonitor.enabled requires gateway.metricsServer.enabled
+
+  - it: scrapes each gateway pod through the metrics port
     template: gateway/servicemonitor.yaml
     release:
       name: rel
       namespace: llm
     set:
       gateway.serviceMonitor.enabled: true
+      gateway.metricsServer.enabled: true
       gateway.serviceMonitor.labels:
         release: kube-prometheus-stack
     asserts:
@@ -169,22 +178,19 @@ tests:
       - equal:
           path: spec.endpoints
           value:
-            - port: http
+            - port: metrics
               path: /metrics/
               interval: 15s
               scrapeTimeout: 10s
               scheme: http
 
-  - it: scrapes the metrics sidecar port when the metrics server is on
+  - it: honours a custom scrape interval
     template: gateway/servicemonitor.yaml
     set:
       gateway.serviceMonitor.enabled: true
       gateway.serviceMonitor.interval: 30s
       gateway.metricsServer.enabled: true
     asserts:
-      - equal:
-          path: spec.endpoints[0].port
-          value: metrics
       - equal:
           path: spec.endpoints[0].interval
           value: 30s

helm/litellm/values.yaml

@@ -285,8 +285,8 @@ gateway:
       limits:
         memory: 512Mi
   # Prometheus Operator ServiceMonitor for the gateway pods. Scrapes the
-  # `<gateway>-metrics` Service when metricsServer is enabled, otherwise the
-  # gateway Service on the http port. Either way every pod is its own scrape
+  # `<gateway>-metrics` Service, so it requires metricsServer above (the http
+  # port serves /metrics/ behind virtual-key auth). Every pod is its own scrape
   # target, so the samples carry the `pod` label the per-pod autoscaling
   # queries below group by.
   serviceMonitor: