---
# HorizontalPodAutoscalers for neuron-prod
# Single Legion node today — minReplicas=1 prevents unnecessary idle waste.
# When GCP GKE is live these minimums should go to 2 for HA.
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: neuron-mcp-hpa
  namespace: neuron-prod
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: neuron-mcp-blue
  minReplicas: 1
  maxReplicas: 6
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 65
    - type: Resource
      resource:
        name: memory
        target:
          type: Utilization
          averageUtilization: 80
  behavior:
    scaleDown:
      stabilizationWindowSeconds: 300  # Don't thrash — wait 5m before scaling down
      policies:
        - type: Pods
          value: 1
          periodSeconds: 120
    scaleUp:
      stabilizationWindowSeconds: 30
      policies:
        - type: Pods
          value: 2
          periodSeconds: 60
---
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: neuron-rest-hpa
  namespace: neuron-prod
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: neuron-rest
  minReplicas: 1
  maxReplicas: 4
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 65
    - type: Resource
      resource:
        name: memory
        target:
          type: Utilization
          averageUtilization: 80
  behavior:
    scaleDown:
      stabilizationWindowSeconds: 300
    scaleUp:
      stabilizationWindowSeconds: 30
---
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: neuron-marketing-hpa
  namespace: neuron-prod
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: neuron-marketing
  # minReplicas=1 to match the file's own convention (see header comment).
  # Kubernetes only allows minReplicas=0 when at least one Object or External
  # metric is configured (queue depth, custom signal, etc.); with only a
  # Resource (CPU) metric, scale-to-zero is rejected and the whole HPA is
  # invalid — which was blocking neuron-prod's Argo CD sync.
  minReplicas: 1
  maxReplicas: 8
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 70
  behavior:
    scaleDown:
      stabilizationWindowSeconds: 120
    scaleUp:
      stabilizationWindowSeconds: 15