Function requestBodyFor

requestBodyFor(
    chat: {
        apiKeyEnv?: string;
        baseURL: string;
        model: string;
        reasoning: "none" | "default";
        replyShape: "server" | "prompt";
    },
): (body: Record<string, unknown>) => Record<string, unknown>
Adjusts each request for the server. With thinking off it also sends the switch Qwen models read through their chat template (enable_thinking: false), which MLX needs and Ollama ignores. When Kizuki checks reply shapes itself, the shape the server would ignore is left out.
Parameters
- chat: {
      apiKeyEnv?: string;
      baseURL: string;
      model: string;
      reasoning: "none" | "default";
      replyShape: "server" | "prompt";
  }
  - OptionalapiKeyEnv?: string
    
    The name of the environment variable that holds the API key. The key itself is never saved.
  - baseURL: string
  - model: string
  - reasoning: "none" | "default"
    
    none turns thinking off, which is faster on small local models. default leaves it to the model.
  - replyShape: "server" | "prompt"
    
    How replies are kept in the right shape. server: the server enforces it (Ollama, OpenAI). prompt: Kizuki describes the shape in the prompt and checks the reply itself, for servers that ignore it (MLX).
Returns (body: Record<string, unknown>) => Record<string, unknown>
- Defined in lib/model.ts:24