/**
 * Streaming parser that splits `<think>…</think>` (and `<thinking>…</thinking>`)
 * tags embedded in a model's text output into separate text / thinking segments.
 *
 * Problem: reasoning models like nemotron, deepseek-r1, qwq emit their chain of
 * thought inline in the text content field — not via the Anthropic `thinking`
 * block nor the OpenAI `reasoning_content` field. If we don't split these,
 * the literal `<think>` tags and the full reasoning leak into the answer UI
 * and into conversation history (wasting context on future turns).
 *
 * Usage:
 *   const s = new ThinkTagStripper();
 *   for (const seg of s.push(chunk)) emit(seg);
 *   for (const seg of s.flush()) emit(seg);
 *
 * Handles tags split across chunk boundaries by holding a small suffix.
 */
export type Segment = {
    type: 'text' | 'thinking';
    text: string;
};
export declare class ThinkTagStripper {
    private mode;
    private pending;
    push(chunk: string): Segment[];
    flush(): Segment[];
}