suite: "keda"
templates:
  - keda.yaml
release:
  name: rel
  namespace: llm
tests:
  - it: "renders no scaled object by default"
    asserts:
      - hasDocuments: { count: 0 }

  - it: "passes user triggers through and adds no prometheus triggers by default"
    set:
      keda.enabled: true
      keda.triggers:
        - type: cpu
          metricType: Utilization
          metadata: { value: "60" }
    asserts:
      - isKind: { of: ScaledObject }
      - equal:
          path: spec.triggers
          value:
            - type: cpu
              metricType: Utilization
              metadata: { value: "60" }

  - it: "scales on release-wide requests per second divided by the per-replica target"
    set:
      keda.enabled: true
      keda.prometheus.serverAddress: http://prometheus-operated.monitoring.svc:9090
      keda.prometheus.requestsPerSecond: 90
    asserts:
      - lengthEqual: { path: spec.triggers, count: 1 }
      - equal:
          path: "spec.triggers[0]"
          value:
            type: prometheus
            metadata:
              serverAddress: http://prometheus-operated.monitoring.svc:9090
              threshold: "90"
              query: sum(rate(litellm_proxy_total_requests_metric_total{namespace="llm",job="rel-litellm"}[1m]))

  - it: "scales on tokens per second on its own"
    set:
      keda.enabled: true
      keda.prometheus.serverAddress: http://prom:9090
      keda.prometheus.tokensPerSecond: 6000000
    asserts:
      - lengthEqual: { path: spec.triggers, count: 1 }
      - equal: { path: "spec.triggers[0].type", value: prometheus }
      - equal: { path: "spec.triggers[0].metadata.threshold", value: "6000000" }
      - equal:
          path: "spec.triggers[0].metadata.query"
          value: sum(rate(litellm_total_tokens_metric_total{namespace="llm",job="rel-litellm"}[1m]))

  - it: "appends requests and tokens triggers after user triggers and selects the metrics service job"
    set:
      keda.enabled: true
      metricsServer.enabled: true
      keda.triggers:
        - type: cpu
          metricType: Utilization
          metadata: { value: "60" }
      keda.prometheus.serverAddress: http://prom:9090
      keda.prometheus.requestsPerSecond: 90
      keda.prometheus.tokensPerSecond: 6000000
    asserts:
      - lengthEqual: { path: spec.triggers, count: 3 }
      - equal: { path: "spec.triggers[0].type", value: cpu }
      - equal: { path: "spec.triggers[1].metadata.threshold", value: "90" }
      - equal:
          path: "spec.triggers[1].metadata.query"
          value: sum(rate(litellm_proxy_total_requests_metric_total{namespace="llm",job="rel-litellm-metrics"}[1m]))
      - equal: { path: "spec.triggers[2].metadata.threshold", value: "6000000" }
      - equal:
          path: "spec.triggers[2].metadata.query"
          value: sum(rate(litellm_total_tokens_metric_total{namespace="llm",job="rel-litellm-metrics"}[1m]))
      - notMatchRegexRaw: { pattern: "\\* *60|per_minute|PerMinute" }

  - it: "ignores the per-minute keys, which the chart never shipped"
    set:
      keda.enabled: true
      keda.prometheus.serverAddress: http://prom:9090
      keda.prometheus.requestsPerMinute: 5400
      keda.prometheus.tokensPerMinute: 360000000
    asserts:
      - isKind: { of: ScaledObject }
      - isNullOrEmpty: { path: spec.triggers }

  - it: "refuses a workload target without a prometheus server address"
    set:
      keda.enabled: true
      keda.prometheus.requestsPerSecond: 90
    asserts:
      - failedTemplate:
          errorMessage: keda.prometheus.serverAddress is required when keda.prometheus.requestsPerSecond or tokensPerSecond is set

  - it: "yields to the hpa when both autoscalers are enabled"
    set:
      autoscaling.enabled: true
      keda.enabled: true
      keda.prometheus.serverAddress: http://prom:9090
      keda.prometheus.requestsPerSecond: 90
    asserts:
      - hasDocuments: { count: 0 }