API Rate Limit Handler

function getRetryDelay(
  response: Response,
  attempt: number,
  maxDelayMs = 60_000
): number {
  // Prefer upstream hints
  const retryAfter = response.headers.get("Retry-After");
  if (retryAfter) {
    const seconds = Number(retryAfter);
    if (Number.isFinite(seconds) && seconds >= 0) {
      return Math.min(seconds * 1000, maxDelayMs);
    }
    // HTTP-date format
    const date = new Date(retryAfter).getTime();
    if (Number.isFinite(date)) {
      return Math.min(Math.max(0, date - Date.now()), maxDelayMs);
    }
  }

  // GitHub documents x-ratelimit-reset as Unix epoch seconds.
  const githubReset = Number(response.headers.get("x-ratelimit-reset"));
  if (Number.isFinite(githubReset)) {
    return Math.min(
      Math.max(0, githubReset * 1000 - Date.now()),
      maxDelayMs
    );
  }

  // Fallback: capped exponential backoff with full jitter.
  const cap = Math.min(1000 * 2 ** attempt, maxDelayMs);
  return Math.floor(Math.random() * cap);
}

async function fetchWithRetry(
  url: string,
  options: RequestInit,
  maxRetries = 3,
  maxElapsedMs = 120_000,
  retryNonIdempotent = false
): Promise<Response> {
  const startedAt = Date.now();
  const method = (options.method ?? "GET").toUpperCase();
  const replaySafe = ["GET", "HEAD", "OPTIONS", "PUT", "DELETE"].includes(method)
    || retryNonIdempotent;

  for (let attempt = 0; attempt <= maxRetries; attempt++) {
    const response = await fetch(url, options);

    if (response.ok) return response;

    // Terminal errors — do not retry
    if ([400, 401, 403, 404, 422].includes(response.status)) {
      throw new Error(`Terminal error ${response.status}: ${response.statusText}`);
    }

    if (!replaySafe) {
      throw new Error(
        `${method} was not retried because replay safety was not explicitly established`
      );
    }

    // Retryable — but exhausted attempts
    if (attempt === maxRetries) {
      throw new Error(`Failed after ${maxRetries} retries: ${response.status}`);
    }

    const remaining = maxElapsedMs - (Date.now() - startedAt);
    const delay = Math.min(getRetryDelay(response, attempt), remaining);
    if (delay <= 0) {
      throw new Error(`Retry deadline exceeded after ${maxElapsedMs}ms`);
    }

    // Release the connection before waiting when the body is not needed.
    await response.body?.cancel();
    console.warn(
      `Request failed (${response.status}), retrying in ${Math.round(delay)}ms (attempt ${attempt + 1}/${maxRetries})`
    );
    await new Promise(resolve => setTimeout(resolve, delay));
  }

  throw new Error("Unreachable");
}

class TokenBucket {
  private tokens: number;
  private lastRefill: number;
  private queue: Promise<void> = Promise.resolve();

  constructor(
    private maxTokens: number,
    private refillRate: number // tokens per second
  ) {
    this.tokens = maxTokens;
    this.lastRefill = Date.now();
  }

  async acquire(): Promise<void> {
    const ticket = this.queue.then(() => this.acquireOnce());
    this.queue = ticket.catch(() => undefined);
    return ticket;
  }

  private async acquireOnce(): Promise<void> {
    this.refill();
    if (this.tokens < 1) {
      const waitMs = ((1 - this.tokens) / this.refillRate) * 1000;
      await new Promise(resolve => setTimeout(resolve, waitMs));
      this.refill();
    }
    this.tokens -= 1;
  }

  private refill(): void {
    const now = Date.now();
    const elapsed = (now - this.lastRefill) / 1000;
    this.tokens = Math.min(this.maxTokens, this.tokens + elapsed * this.refillRate);
    this.lastRefill = now;
  }
}

// Usage: limit to 60 requests/minute
const limiter = new TokenBucket(60, 1);

async function rateLimitedFetch(url: string, options: RequestInit) {
  await limiter.acquire();
  return fetchWithRetry(url, options);
}

const response = await fetchWithRetry(
  "https://api.github.com/repos/OWNER/REPO",
  {
    method: "GET",
    headers: {
      "Accept": "application/vnd.github+json",
      "Authorization": `Bearer ${githubToken}`,
    },
  },
  3
);

import time
import random
import httpx

def fetch_with_retry(url: str, max_retries: int = 3, **kwargs) -> httpx.Response:
    for attempt in range(max_retries + 1):
        response = httpx.request("GET", url, **kwargs)

        if response.is_success:
            return response

        if response.status_code in (400, 401, 403, 404, 422):
            response.raise_for_status()

        if attempt == max_retries:
            response.raise_for_status()

        # Parse Retry-After or compute backoff
        retry_after = response.headers.get("retry-after")
        if retry_after and retry_after.isdigit():
            delay = int(retry_after)
        else:
            delay = min(2 ** attempt + random.uniform(0, 1), 60)

        print(f"Retrying in {delay:.1f}s (attempt {attempt + 1}/{max_retries})")
        time.sleep(delay)

    raise RuntimeError("Unreachable")