interface ChatRequestMessage {
    appSource?: string;
    chat_template_kwargs?: Record<string, unknown>;
    frequency_penalty?: number;
    jobID: string;
    max_tokens?: number;
    messages: ChatMessage[];
    min_p?: number;
    model: string;
    presence_penalty?: number;
    repetition_penalty?: number;
    response_format?: ChatResponseFormat;
    sogni_tool_execution?: boolean;
    sogni_tools?: SogniToolsMode;
    stop?: string | string[];
    stream?: boolean;
    taskProfile?: "general" | "coding" | "reasoning";
    temperature?: number;
    tokenType?: "sogni" | "spark";
    tool_choice?: ToolChoice;
    tools?: ToolDefinition[];
    top_k?: number;
    top_p?: number;
    type: "llm";
}

Properties

appSource?: string
chat_template_kwargs?: Record<string, unknown>

Per-request chat template arguments (e.g. { enable_thinking: false } for llama.cpp).

frequency_penalty?: number
jobID: string
max_tokens?: number
messages: ChatMessage[]
min_p?: number
model: string
presence_penalty?: number
repetition_penalty?: number
response_format?: ChatResponseFormat

Per-request structured-output constraint (OpenAI-compatible).

sogni_tool_execution?: boolean
sogni_tools?: SogniToolsMode
stop?: string | string[]
stream?: boolean
taskProfile?: "general" | "coding" | "reasoning"
temperature?: number
tokenType?: "sogni" | "spark"
tool_choice?: ToolChoice
tools?: ToolDefinition[]
top_k?: number
top_p?: number
type: "llm"