config:
  target: "http://localhost:8080"
  phases:
    - duration: 30
      arrivalRate: 10
      name: "Warm up"
    - duration: 60
      arrivalRate: 50
      name: "Load test - 50 concurrent"
    - duration: 60
      arrivalRate: 100
      name: "Load test - 100 concurrent"
    - duration: 60
      arrivalRate: 200
      name: "Stress test"
  plugins:
    expect: {}
  processor: "./processors.js"

scenarios:
  - name: "Chat Completions (Non-streaming)"
    flow:
      - post:
          url: "/v1/chat/completions"
          headers:
            Authorization: "Bearer {{ $processEnvironment.API_KEY }}"
            Content-Type: "application/json"
          json:
            model: "gpt-4"
            messages:
              - role: "user"
                content: "Hello, how are you?"
            max_tokens: 100
            stream: false

  - name: "Chat Completions (Streaming)"
    weight: 3
    flow:
      - post:
          url: "/v1/chat/completions"
          headers:
            Authorization: "Bearer {{ $processEnvironment.API_KEY }}"
            Content-Type: "application/json"
          json:
            model: "gpt-4"
            messages:
              - role: "user"
                content: "Count from 1 to 10"
            stream: true