mlx-bun library API
    Preparing search index...

    Interface RenderOptions

    interface RenderOptions {
        addGenerationPrompt?: boolean;
        enableThinking?: boolean;
        preserveThinking?: boolean;
        reasoningEffort?: "xhigh" | "medium" | "low";
        tools?: ToolDefinition[] | null;
    }
    Index
    addGenerationPrompt? enableThinking? preserveThinking? reasoningEffort? tools?
    addGenerationPrompt?: boolean
    enableThinking?: boolean
    preserveThinking?: boolean

    Keep think blocks from historical assistant turns in the rendered prompt (Qwen3.8 preserve_thinking, template default true — better prompt-cache reuse and agent-trace continuity). Only passed when the template reads it.

    reasoningEffort?: "xhigh" | "medium" | "low"

    Template-level reasoning depth (Qwen3.8: xhigh|medium|low — the template RAISES on other values, so callers must map OpenAI levels first and only set this for templates that read it; see ChatTemplate.readsReasoningEffort).

    tools?: ToolDefinition[] | null

    Settings
    Member Visibility

    On This Page
    Properties