---
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  creationTimestamp: "2026-10-31T00:32:49Z"
  labels:
    gateway.istio.io/managed: openshift.io-gateway-controller-v1
    gateway.networking.k8s.io/gateway-class-name: openshift-ai-inference
    gateway.networking.k8s.io/gateway-name: openshift-ai-inference
  managedFields:
  - apiVersion: autoscaling/v2
    fieldsType: FieldsV1
    fieldsV1:
      f:metadata:
        f:annotations: {}
        f:labels:
          f:gateway.istio.io/managed: {}
          f:gateway.networking.k8s.io/gateway-class-name: {}
          f:gateway.networking.k8s.io/gateway-name: {}
        f:ownerReferences:
          k:{"uid":"3665c6a7-caeb-4fe8-b18b-4a05cdf7a704"}: {}
      f:spec:
        f:maxReplicas: {}
        f:minReplicas: {}
        f:scaleTargetRef:
          f:apiVersion: {}
          f:kind: {}
          f:name: {}
    manager: openshift.io/gateway-controller/v1
    operation: Apply
    time: "2026-10-31T00:32:49Z"
  - apiVersion: autoscaling/v2
    fieldsType: FieldsV1
    fieldsV1:
      f:status:
        f:conditions:
          .: {}
          k:{"type":"AbleToScale"}:
            .: {}
            f:lastTransitionTime: {}
            f:message: {}
            f:reason: {}
            f:status: {}
            f:type: {}
          k:{"type":"ScalingActive"}:
            .: {}
            f:lastTransitionTime: {}
            f:message: {}
            f:reason: {}
            f:status: {}
            f:type: {}
          k:{"type":"ScalingLimited"}:
            .: {}
            f:lastTransitionTime: {}
            f:message: {}
            f:reason: {}
            f:status: {}
            f:type: {}
        f:currentMetrics: {}
        f:currentReplicas: {}
        f:desiredReplicas: {}
    manager: kube-controller-manager
    operation: Update
    subresource: status
    time: "2026-10-31T02:32:22Z"
  name: openshift-ai-inference-openshift-ai-inference
  namespace: openshift-ingress
  ownerReferences:
  - apiVersion: gateway.networking.k8s.io/v1beta1
    kind: Gateway
    name: openshift-ai-inference
    uid: 3665c6a7-caeb-4fe8-b18b-4a05cdf7a704
  resourceVersion: "176403"
  uid: f696a3df-016e-40bf-a6a4-559dd1f74364
spec:
  maxReplicas: 10
  metrics:
  - resource:
      name: cpu
      target:
        averageUtilization: 80
        type: Utilization
    type: Resource
  minReplicas: 1
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: openshift-ai-inference-openshift-ai-inference
status:
  conditions:
  - lastTransitionTime: "2026-10-31T00:33:04Z"
    message: the HPA controller was able to get the target's current scale
    reason: SucceededGetScale
    status: "True"
    type: AbleToScale
  - lastTransitionTime: "2026-10-31T02:32:22Z"
    message: 'the HPA was unable to compute the replica count: failed to get cpu utilization:
      unable to get metrics for resource cpu: unable to fetch metrics from resource
      metrics API: the server is currently unable to handle the request (get pods.metrics.k8s.io)'
    reason: FailedGetResourceMetric
    status: "False"
    type: ScalingActive
  - lastTransitionTime: "2026-10-31T00:33:50Z"
    message: the desired count is within the acceptable range
    reason: DesiredWithinRange
    status: "False"
    type: ScalingLimited
  currentMetrics:
  - type: ""
  currentReplicas: 1
  desiredReplicas: 1