当前位置：首页 > news >正文

Portkey-AI gateway 的一次“假压缩头”翻车的完整排障记：由 httpx 解压异常引发的根因分析

news 2025/8/18 13:04:27

笔者最近在本地搭建了Portkey AI Gateway（模型路由网关），然后按照文档中的方式进行测试。

在这里插入图片描述
结果发现，网关能够接收到请求，但是Python测试的程序却运行报错。

在这里插入图片描述
Python代码报错信息如下：

Traceback (most recent call last):File "F:\pytorch310\lib\site-packages\httpx\_decoders.py", line 97, in decodereturn self.decompressor.decompress(data)
zlib.error: Error -3 while decompressing data: incorrect header checkThe above exception was the direct cause of the following exception:Traceback (most recent call last):File "F:\pytorch310\lib\site-packages\portkey_ai\_vendor\openai\_base_client.py", line 989, in requestresponse = self._client.send(File "F:\pytorch310\lib\site-packages\httpx\_client.py", line 928, in sendraise excFile "F:\pytorch310\lib\site-packages\httpx\_client.py", line 922, in sendresponse.read()File "F:\pytorch310\lib\site-packages\httpx\_models.py", line 881, in readself._content = b"".join(self.iter_bytes())File "F:\pytorch310\lib\site-packages\httpx\_models.py", line 898, in iter_bytesdecoded = decoder.decode(raw_bytes)File "F:\pytorch310\lib\site-packages\httpx\_decoders.py", line 99, in decoderaise DecodingError(str(exc)) from exc
httpx.DecodingError: Error -3 while decompressing data: incorrect header checkThe above exception was the direct cause of the following exception:Traceback (most recent call last):File "E:\PycharmProjects\PortkeyAIProject\test.py", line 10, in <module>response = client.chat.completions.create(File "F:\pytorch310\lib\site-packages\portkey_ai\api_resources\apis\chat_complete.py", line 183, in createreturn self.normal_create(File "F:\pytorch310\lib\site-packages\portkey_ai\api_resources\apis\chat_complete.py", line 126, in normal_createresponse = self.openai_client.with_raw_response.chat.completions.create(File "F:\pytorch310\lib\site-packages\portkey_ai\_vendor\openai\_legacy_response.py", line 364, in wrappedreturn cast(LegacyAPIResponse[R], func(*args, **kwargs))File "F:\pytorch310\lib\site-packages\portkey_ai\_vendor\openai\_utils\_utils.py", line 287, in wrapperreturn func(*args, **kwargs)File "F:\pytorch310\lib\site-packages\portkey_ai\_vendor\openai\resources\chat\completions\completions.py", line 925, in createreturn self._post(File "F:\pytorch310\lib\site-packages\portkey_ai\_vendor\openai\_base_client.py", line 1259, in postreturn cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))File "F:\pytorch310\lib\site-packages\portkey_ai\_vendor\openai\_base_client.py", line 1021, in requestraise APIConnectionError(request=request) from err
openai.APIConnectionError: Connection error.

然后笔者定位到报错位置，发现是gzip解码时出现了问题。

在这里插入图片描述

症状是 incorrect header check，最终定位到网关在响应里带了 Content-Encoding: gzip 头，但实体其实是明文 JSON（即“假压缩头”）。任何会自动解压的客户端（httpx/Portkey SDK 等）都会在读取阶段失败。

要想在根源上修复这个问题，需要在网关/反代上保证“头与实体一致”——不压就删 Content-Encoding；压了就只压一层并设置正确的头。可是这个网关是直接运行起来的开源项目，所以笔者只好想了一个临时的办法来解决这个问题：客户端用 httpx.stream(...).iter_raw() 读原始字节并手动解析。

复现与第一轮尝试

1) 最初用 Portkey SDK 直连 provider

from portkey_ai import Portkey
client = Portkey(provider="dashscope", Authorization="Bearer <key>")
client.chat.completions.create(model="qwen-plus", messages=[...])

现象：httpx.DecodingError。
直觉：解压阶段挂了 → 看压缩相关头部。

2) 改走本地网关 `base_url`

Portkey(base_url="http://localhost:8787/v1")

这时 Portkey 的 provider= 参数不会自动变成网关能识别的路由头，于是网关返回：

400 {'status': 'failure', 'message': 'Either x-portkey-config or x-portkey-provider header is required'}

结论：走自托管网关必须用请求头指明路由（x-portkey-provider）。

我们补上头之后，仍旧遇到 DecodingError。说明不仅是路由问题，压缩/头部也有坑。

关键破局：跳过自动解压，直看“线上的原始字节”

为排除客户端自动行为干扰，直接用 httpx.stream(...).iter_raw()：

import httpx, jsonGATEWAY = "http://localhost:8787/v1"
payload = {"model": "qwen-plus", "messages": [{"role": "user", "content": "Hello"}]}
headers = {"x-portkey-provider": "dashscope","Authorization": "Bearer <your_secret_key>","Accept-Encoding": "identity","Content-Type": "application/json",
}with httpx.stream("POST", f"{GATEWAY}/chat/completions", json=payload, headers=headers, timeout=30) as r:print("status =", r.status_code)print("Content-Encoding =", r.headers.get("content-encoding"))raw = b"".join(r.iter_raw())  # ★ 不做解压，拿“线上的原始字节”print("raw len =", len(raw))print("raw head =", raw[:80])# 如果服务端其实是明文 JSON（却错误地带了 Content-Encoding）try:print("as text ->", raw[:200].decode("utf-8"))except Exception:  # 如果真的是 gzip，可自行解压看import gzip, iotry:txt = gzip.GzipFile(fileobj=io.BytesIO(raw)).read().decode("utf-8")print("as gzip json ->", txt[:200])except Exception as e:print("manual decode failed:", e)

实际输出（核心证据）：

status = 200
Content-Encoding = gzip
raw len = 448
raw head = b'{"choices":[{"message":{"role":"assistant","content":"Hi there! \xd9\xa9(\xe2\x97\x95\xe2\x80\xbf\xe2\x97\x95\xef\xbd\xa1)'
as text -> {"choices":[{"message":{"role":"assistant","content":"Hi there! ٩(◕‿◕｡)۶ How can I assist you today?"},"finish_reason":"stop","index":0,"logprobs":null}],"object":"chat.completion","usage":{

结论：服务端响应头声称 gzip，但实体实际上是明文 JSON。
这就是“假压缩头”。httpx/SDK 看到 Content-Encoding: gzip 会尝试解压，结果自然报 incorrect header check。