model_governance:
  profiles:
    default:
      provider: oci_openai
      model: openai.gpt-4.1
      temperature: 0.2
      max_tokens: 2048

    router:
      provider: oci_openai
      model: openai.gpt-4.1
      temperature: 0
      max_tokens: 500

    judge:
      provider: oci_openai
      model: openai.gpt-4.1
      temperature: 0
      max_tokens: 800

  operation_profiles:
    router.intent: router
    agent.final_answer: default
    judge.response_quality: judge

  policies:
    tenants:
      default:
        allowed_providers:
          - oci_openai
          - oci_sdk
          - mock
        allowed_profiles:
          - default
          - router
          - judge

rate_limits:
  default:
    requests_per_minute: 600
  channels:
    whatsapp:
      requests_per_minute: 120
    web:
      requests_per_minute: 300
  agents:
    telecom_contas:
      requests_per_minute: 180

backend_headers:
  propagate_model_policy: true
  propagate_trace_context: true

evaluation:
  enabled: true
  sample_rate: 1.0