version: v0.1

listeners:
  egress_traffic:
    address: 0.0.0.0
    port: 12000
    message_format: openai
    timeout: 30s

llm_providers:

  # OpenAI Models
  - model: openai/gpt-5-2025-08-07
    routing_preferences:
      - name: code generation
        description: generating new code snippets, functions, or boilerplate based on user prompts or requirements

  - model: openai/gpt-4.1-2025-04-14
    access_key: $OPENAI_API_KEY
    routing_preferences:
      - name: code understanding
        description: understand and explain existing code snippets, functions, or libraries

  # Anthropic Models
  - model: anthropic/claude-3-5-sonnet-20241022
    access_key: $ANTHROPIC_API_KEY

  - model: anthropic/claude-3-haiku-20240307
    access_key: $ANTHROPIC_API_KEY

  # Azure OpenAI Models
  - model: azure_openai/gpt-5-mini
    access_key: $AZURE_API_KEY
    base_url: https://katanemo.openai.azure.com

  # Ollama Models
  - model: ollama/llama3.1
    base_url: http://host.docker.internal:11434


# Model aliases - friendly names that map to actual provider names
model_aliases:
  # Alias for summarization tasks -> fast/cheap model
  arch.summarize.v1:
    target: gpt-4.1-2025-04-14

  # Alias for creative tasks -> Claude model
  arch.creative.v1:
    target: claude-3-5-sonnet-20241022

  # Alias for quick responses -> fast model
  arch.fast.v1:
    target: claude-3-haiku-20240307

  chat-model:
    target: claude-3-5-sonnet-20241022