apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: llm-gateway
  namespace: llm-gateway
  labels:
    app: llm-gateway
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: llm-gateway

  minReplicas: 3
  maxReplicas: 20

  behavior:
    scaleDown:
      stabilizationWindowSeconds: 300
      policies:
      - type: Percent
        value: 50
        periodSeconds: 60
      - type: Pods
        value: 2
        periodSeconds: 60
      selectPolicy: Min
    scaleUp:
      stabilizationWindowSeconds: 0
      policies:
      - type: Percent
        value: 100
        periodSeconds: 30
      - type: Pods
        value: 4
        periodSeconds: 30
      selectPolicy: Max

  metrics:
  # CPU-based scaling
  - type: Resource
    resource:
      name: cpu
      target:
        type: Utilization
        averageUtilization: 70

  # Memory-based scaling
  - type: Resource
    resource:
      name: memory
      target:
        type: Utilization
        averageUtilization: 80

  # Custom metrics (requires metrics-server and custom metrics API)
  # - type: Pods
  #   pods:
  #     metric:
  #       name: http_requests_per_second
  #     target:
  #       type: AverageValue
  #       averageValue: "1000"