HHAPI 请求超时排查：推荐超时时长配置与网络诊断方法

import os
import openai

client = openai.OpenAI(
    api_key=os.environ.get("HHAPI_API_KEY"),
    base_url="<API_BASE_URL>/v1",
    # 非流式请求：建议设置 60 秒以上
    timeout=60.0
)

# 流式请求：建议设置 120 秒以上
# 也可针对单次调用单独设置超时
stream_client = openai.OpenAI(
    api_key=os.environ.get("HHAPI_API_KEY"),
    base_url="<API_BASE_URL>/v1",
    timeout=120.0
)

with stream_client.chat.completions.stream(
    model="<MODEL_ID>",
    messages=[{"role": "user", "content": "写一篇 1000 字的文章"}],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

import OpenAI from "openai";

// 非流式请求：建议 60 秒以上
const client = new OpenAI({
  apiKey: process.env.HHAPI_API_KEY,
  baseURL: "<API_BASE_URL>/v1",
  timeout: 60 * 1000, // 单位：毫秒
});

// 流式请求：建议 120 秒以上
const streamClient = new OpenAI({
  apiKey: process.env.HHAPI_API_KEY,
  baseURL: "<API_BASE_URL>/v1",
  timeout: 120 * 1000,
});

const stream = await streamClient.chat.completions.create({
  model: "<MODEL_ID>",
  messages: [{ role: "user", content: "写一篇 1000 字的文章" }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}