server:
  listen: "127.0.0.1:41091"
bootstrap:
  listen: "0.0.0.0:18080"
  artifact_dir: "artifacts"
logging:
  level: "error"
refresh:
  enabled: false
  listen: "127.0.0.1:19093"
openai:
  enabled: true
  listen: "127.0.0.1:41355"
  provider_id: "test-provider"
  adapter: "openai_compat"
  target: ""
a2a:
  listen: "0.0.0.0:8081"
metrics:
  port: 0
models:
  - id: "qwen3.6:35b"
    display_name: "Qwen Base"
    providers:
      prov-a: "served-qwen"
nodes:
  - id: "node-1"
    alias: "n1"
    token: "tok-1"
    adapters:
      openai_compat_instances:
        - name: "vllm-gpu"
          enabled: true
          provider: "vllm"
          endpoint: "http://127.0.0.1:8000/v1"
    providers:
      - id: "prov-a"
        type: "vllm"
        category: "api"
        adapter: "vllm-gpu"
        models: ["served-qwen"]
        health: "available"
        capacity: 2
        max_queue: 4
        queue_timeout_ms: 5000