LLM 429 レート制限 & ワーカー並列数計算ツール

クォータ使用率 & ボトルネック診断

// Full-jitter exponential backoff + Retry-After guard (google/gemini-4-hydrogen)
export async function callWithRateLimitGuard<T>(
  fn: () => Promise<Response>,
  maxRetries = 5,
  baseDelayMs = 500,
  maxDelayMs = 30_000
): Promise<T> {
  for (let attempt = 0; attempt <= maxRetries; attempt++) {
    const res = await fn();
    if (res.status !== 429 && res.status < 500) {
      return (await res.json()) as T;
    }
    if (attempt === maxRetries) {
      throw new Error(`LLM quota exhausted (HTTP ${res.status}) after ${maxRetries} retries`);
    }
    const retryAfterSec = Number(res.headers.get('retry-after'));
    const ceiling = Math.min(maxDelayMs, baseDelayMs * 2 ** attempt);
    const sleepMs = Number.isFinite(retryAfterSec) && retryAfterSec > 0
      ? retryAfterSec * 1000
      : Math.floor(Math.random() * ceiling);
    await new Promise((r) => setTimeout(r, sleepMs));
  }
  throw new Error('Unreachable');
}