# LLM backend: "local" or "lmstudio"
llm:
  backend: local        # change to "lmstudio" to use LM Studio instead
  max_cache_tokens: 4096  # max KV-cache size per session (tokens); 0 to disable caching

  system_prompt: >-
    You are a helpful voice assistant. 
    Keep your responses extremely concise but natural for spoken conversation.
    Do not use markdown, bullet points, code blocks, emojis, or any formatting that doesn't work in speech.

  # Settings used only when backend = "lmstudio"
  lmstudio:
    url: http://host.docker.internal:1234   # host.docker.internal resolves to your PC from inside Docker
    model: ""           # leave empty to use whatever model LM Studio has loaded