# Optional file. If this file is absent, the backend keeps using .env exactly as before.
# If present, each inference point can override provider/model/params.
# Recommendation: set provider explicitly in every profile to avoid ambiguity.
profiles:
  default:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0.2
    max_tokens: 2048

  # Workflow/routing
  supervisor:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0
    max_tokens: 700

  processing_interruption_classifier:
    provider: oci_openai
    model: openai.gpt-4.1-mini
    temperature: 0
    max_tokens: 8
    timeout_seconds: 5

  router:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0
    max_tokens: 768

  # Safety / evaluation
  guardrail:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0
    max_tokens: 600

  grl:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0
    max_tokens: 700

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

  # RAG
  rag_rewriter:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0
    max_tokens: 300

  rag_compressor:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0
    max_tokens: 1200

  rag_generation:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0.1
    max_tokens: 1800

  # Memory / operations
  summary_memory:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0.1
    max_tokens: 1200

  noc:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0
    max_tokens: 700

  # Agent-specific overrides
  billing_agent:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0.2

  product_agent:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0.2

  backoffice_agent:
    provider: oci_openai
    model: openai.gpt-4.1
    temperature: 0.2

  mcp_parameter_extraction:
    provider: oci_openai
    model: openai.gpt-4.1-mini
    temperature: 0
    max_tokens: 80
    timeout_seconds: 5