apiVersion: http.keda.sh/v1alpha1
kind: HTTPScaledObject
metadata:
  name: openclaw-brain-a100-scaling
  namespace: customer1
spec:
  # The host header the interceptor should match
  host: openclaw-brain-service.customer1.svc.cluster.local   # ← important

  # Target to scale + routing info (old style)
  scaleTargetRef:
    deployment: openclaw-brain-vllm          # your Deployment name
    service: openclaw-brain-service          # your Service name
    port: 8000                                 # ← change if your container port is different (e.g. 8080, 11434 for vLLM, etc.)

  # Replica settings
  replicas:
    min: 0
    max: 1

  # Scaling metric - best for "wake on first request" use case
  targetPendingRequests: 1

  # Cooldown before scaling down (15 minutes idle)
  scaledownPeriod: 900