{{- if .Values.autoscaling.enabled }}
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: {{ include "litellm.fullname" . }}
  labels:
    {{- include "litellm.labels" . | nindent 4 }}
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: {{ include "litellm.fullname" . }}
  minReplicas: {{ .Values.autoscaling.minReplicas }}
  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
  {{- if .Values.autoscaling.behavior }}
  behavior:
    {{- toYaml .Values.autoscaling.behavior | nindent 4 }}
  {{- end }}
  metrics:
    {{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
    {{- if and .Values.collector.enabled .Values.collector.scaleOnProxyContainerCpu }}
    - type: ContainerResource
      containerResource:
        name: cpu
        container: {{ include "litellm.name" . }}
        target:
          type: Utilization
          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
    {{- else }}
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
    {{- end }}
    {{- end }}
    {{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
    - type: Resource
      resource:
        name: memory
        target:
          type: Utilization
          averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
    {{- end }}
    {{- with .Values.autoscaling.targetRequestsPerSecond }}
    - type: Pods
      pods:
        metric:
          name: litellm_requests_per_second
        target:
          type: AverageValue
          averageValue: {{ toJson . | trimAll "\"" | quote }}
    {{- end }}
    {{- with .Values.autoscaling.targetTokensPerSecond }}
    - type: Pods
      pods:
        metric:
          name: litellm_tokens_per_second
        target:
          type: AverageValue
          averageValue: {{ toJson . | trimAll "\"" | quote }}
    {{- end }}
{{- end }}