apiVersion: http.keda.sh/v1alpha1
kind: HTTPScaledObject
metadata:
  name: openclaw-brain-a100-scaling
  namespace: customer1
spec:
  hosts:
    - a100-vllm.internal.cluster # Replace with actual internal routing host if needed
  scaleTargetRef:
    name: openclaw-brain-vllm
    kind: Deployment
    apiVersion: apps/v1
    service: openclaw-brain-service
    port: 8000
  replicas:
    min: 0
    max: 1
  scaledownPeriod: 900 # 15 minutes of idle time before scaling to zero