6.5 Errors and Rate Limits

import time
import random

def call_with_retry(client, max_retries=3, **kwargs):
    for attempt in range(max_retries):
        try:
            return client.chat.completions.create(**kwargs)
        except Exception as e:
            if "429" in str(e):
                # 指数退避 + 随机抖动
                wait_time = (2 ** attempt) + random.uniform(0, 1)
                print(f"限流，{wait_time:.1f}秒后重试...")
                time.sleep(wait_time)
            elif "502" in str(e) or "503" in str(e):
                # 上游故障，快速重试
                time.sleep(1)
            else:
                raise e
    raise Exception("超过最大重试次数")