litellm/helm/litellm-helm/tests/hpa_tests.yaml

suite: "hpa"
templates:
  - hpa.yaml
tests:
  - it: "renders behavior when set"
    set:
      autoscaling.enabled: true
      autoscaling.behavior:
        scaleUp:
          stabilizationWindowSeconds: 60
          policies:
            - type: Pods
              value: 2
              periodSeconds: 60
        scaleDown:
          stabilizationWindowSeconds: 90
          policies:
            - type: Pods
              value: 1
              periodSeconds: 60
    asserts:
      - isKind: { of: HorizontalPodAutoscaler }
      - equal: { path: spec.behavior.scaleUp.stabilizationWindowSeconds, value: 60 }
      - equal: { path: spec.behavior.scaleDown.stabilizationWindowSeconds, value: 90 }

  - it: "does not render behavior when not set"
    set:
      autoscaling.enabled: true
    asserts:
      - isKind: { of: HorizontalPodAutoscaler }
      - isNull: { path: spec.behavior }

  - it: "scales on cpu at the documented 60 percent by default"
    set:
      autoscaling.enabled: true
    asserts:
      - isKind: { of: HorizontalPodAutoscaler }
      - equal: { path: "spec.metrics[0].resource.name", value: cpu }
      - equal: { path: "spec.metrics[0].resource.target.type", value: Utilization }
      - equal: { path: "spec.metrics[0].resource.target.averageUtilization", value: 60 }

  - it: "does not scale on memory by default"
    set:
      autoscaling.enabled: true
    asserts:
      - lengthEqual: { path: spec.metrics, count: 1 }

  - it: "honours an explicit cpu target override"
    set:
      autoscaling.enabled: true
      autoscaling.targetCPUUtilizationPercentage: 75
    asserts:
      - equal: { path: "spec.metrics[0].resource.target.averageUtilization", value: 75 }

  - it: "renders a memory metric only when a memory target is set"
    set:
      autoscaling.enabled: true
      autoscaling.targetMemoryUtilizationPercentage: 80
    asserts:
      - lengthEqual: { path: spec.metrics, count: 2 }
      - equal: { path: "spec.metrics[1].resource.name", value: memory }
      - equal: { path: "spec.metrics[1].resource.target.averageUtilization", value: 80 }

  - it: "renders no workload metrics by default"
    set:
      autoscaling.enabled: true
      autoscaling.targetMemoryUtilizationPercentage: 80
    asserts:
      - lengthEqual: { path: spec.metrics, count: 2 }
      - notContains: { path: spec.metrics, content: { type: Pods }, any: true }

  - it: "adds a requests-per-second Pods metric after the cpu metric"
    set:
      autoscaling.enabled: true
      autoscaling.targetRequestsPerSecond: 90
    asserts:
      - lengthEqual: { path: spec.metrics, count: 2 }
      - equal: { path: "spec.metrics[0].resource.name", value: cpu }
      - equal:
          path: "spec.metrics[1]"
          value:
            type: Pods
            pods:
              metric: { name: litellm_requests_per_second }
              target: { type: AverageValue, averageValue: "90" }

  - it: "adds a tokens-per-second Pods metric on its own"
    set:
      autoscaling.enabled: true
      autoscaling.targetTokensPerSecond: 6M
    asserts:
      - lengthEqual: { path: spec.metrics, count: 2 }
      - equal:
          path: "spec.metrics[1]"
          value:
            type: Pods
            pods:
              metric: { name: litellm_tokens_per_second }
              target: { type: AverageValue, averageValue: "6M" }
      - notContains:
          path: spec.metrics
          content: { type: Pods, pods: { metric: { name: litellm_requests_per_second } } }
          any: true

  - it: "renders requests, tokens, cpu and memory metrics together"
    set:
      autoscaling.enabled: true
      autoscaling.targetMemoryUtilizationPercentage: 80
      autoscaling.targetRequestsPerSecond: 90
      autoscaling.targetTokensPerSecond: 6000000
    asserts:
      - lengthEqual: { path: spec.metrics, count: 4 }
      - equal: { path: "spec.metrics[0].resource.name", value: cpu }
      - equal: { path: "spec.metrics[1].resource.name", value: memory }
      - equal: { path: "spec.metrics[2].pods.metric.name", value: litellm_requests_per_second }
      - equal: { path: "spec.metrics[2].pods.target.averageValue", value: "90" }
      - equal: { path: "spec.metrics[3].pods.metric.name", value: litellm_tokens_per_second }
      - equal: { path: "spec.metrics[3].pods.target.averageValue", value: "6000000" }

  - it: "scales on workload metrics alone when the cpu target is cleared"
    set:
      autoscaling.enabled: true
      autoscaling.targetCPUUtilizationPercentage: null
      autoscaling.targetRequestsPerSecond: 90
      autoscaling.targetTokensPerSecond: 6000000
    asserts:
      - lengthEqual: { path: spec.metrics, count: 2 }
      - notContains: { path: spec.metrics, content: { type: Resource }, any: true }
      - equal: { path: "spec.metrics[0].pods.metric.name", value: litellm_requests_per_second }
      - equal: { path: "spec.metrics[1].pods.metric.name", value: litellm_tokens_per_second }
      - notMatchRegexRaw: { pattern: per_minute }

  - it: "ignores the per-minute keys, which the chart never shipped"
    set:
      autoscaling.enabled: true
      autoscaling.targetRequestsPerMinute: 5400
      autoscaling.targetTokensPerMinute: 360000000
    asserts:
      - lengthEqual: { path: spec.metrics, count: 1 }
      - notContains: { path: spec.metrics, content: { type: Pods }, any: true }

  - it: "renders no hpa when autoscaling is disabled"
    asserts:
      - hasDocuments: { count: 0 }