超时问题

[AmShadows]

经常爆这个错误，换了模型也是，基模api本身没设置超时，而且LLM 基础参数请求超时（毫秒）设置150000，但是会提示50s这种不一致的情况（50s好像是上次配置的，但是已经更新150000了还是会出现50s），有时候超时200s也会报错，我在chatbox测试基模的回显是非常快的。

docker搭建，源代码用了项目java-sec-code，本地基模用了qwen，然后30个文件就停止完成了。

📈 ZIP任务 4c92fed2-abb2-4480-8139-9e56a09e398e: 进度 30/64
INFO:openai._base_client:Retrying request to /chat/completions in 0.447964 seconds
INFO:openai._base_client:Retrying request to /chat/completions in 0.836777 seconds

Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm._turn_on_debug()'.

ERROR:app.services.llm.service:Custom prompt analysis failed: LiteLLM (qwen) API调用失败: 请求超时 (50s)。建议：
1. 检查网络连接是否正常
2. 尝试增加超时时间
3. 验证API端点是否正确
Traceback (most recent call last):
❌ ZIP任务分析文件失败 (java-sec-code-master/src/main/java/org/joychou/mapper/UserMapper.java): LiteLLM (qwen) API调用失败: 请求超时 (50s)。建议：
1. 检查网络连接是否正常
2. 尝试增加超时时间
3. 验证API端点是否正确
  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/custom_httpx/aiohttp_transport.py", line 60, in map_aiohttp_exceptions
    yield
  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/custom_httpx/aiohttp_transport.py", line 274, in handle_async_request
    response = await self._make_aiohttp_request(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/custom_httpx/aiohttp_transport.py", line 240, in _make_aiohttp_request
    response = await client_session.request(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/aiohttp/client.py", line 1510, in __aenter__
    self._resp: _RetType = await self._coro
                           ^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/aiohttp/client.py", line 779, in _request
    resp = await handler(req)
           ^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/aiohttp/client.py", line 757, in _connect_and_send_request
    await resp.start(conn)
  File "/app/.venv/lib/python3.12/site-packages/aiohttp/client_reqrep.py", line 539, in start
    message, payload = await protocol.read()  # type: ignore[union-attr]
                       ^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/aiohttp/streams.py", line 680, in read
    await self._waiter
aiohttp.client_exceptions.SocketTimeoutError: Timeout on reading data from socket

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1529, in request
    response = await self._client.send(
               ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/httpx/_client.py", line 1629, in send
    response = await self._send_handling_auth(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/httpx/_client.py", line 1657, in _send_handling_auth
    response = await self._send_handling_redirects(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/httpx/_client.py", line 1694, in _send_handling_redirects
    response = await self._send_single_request(request)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/httpx/_client.py", line 1730, in _send_single_request
    response = await transport.handle_async_request(request)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/custom_httpx/aiohttp_transport.py", line 273, in handle_async_request
    with map_aiohttp_exceptions():
         ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/contextlib.py", line 158, in __exit__
    self.gen.throw(value)
  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/custom_httpx/aiohttp_transport.py", line 74, in map_aiohttp_exceptions
    raise mapped_exc(message) from exc
httpx.ReadTimeout: Timeout on reading data from socket

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 836, in acompletion
    headers, response = await self.make_openai_chat_completion_request(
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/litellm/litellm_core_utils/logging_utils.py", line 190, in async_wrapper
    result = await func(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 458, in make_openai_chat_completion_request
    raise e
  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 437, in make_openai_chat_completion_request
    await openai_aclient.chat.completions.with_raw_response.create(
  File "/app/.venv/lib/python3.12/site-packages/openai/_legacy_response.py", line 381, in wrapped
    return cast(LegacyAPIResponse[R], await func(*args, **kwargs))
                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 2678, in create
    return await self._post(
           ^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1794, in post
    return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1547, in request
    raise APITimeoutError(request=request) from err
openai.APITimeoutError: Request timed out.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/app/.venv/lib/python3.12/site-packages/litellm/main.py", line 607, in acompletion
    response = await init_response
               ^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 883, in acompletion
    raise OpenAIError(
litellm.llms.openai.common_utils.OpenAIError: Request timed out. - timeout value=50.0, time taken=151.3 seconds

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/app/app/services/llm/adapters/litellm_adapter.py", line 171, in complete
    return await self.retry(lambda: self._send_request(request))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/app/services/llm/base_adapter.py", line 123, in retry
    raise error
  File "/app/app/services/llm/base_adapter.py", line 116, in retry
    return await fn()
           ^^^^^^^^^^
  File "/app/app/services/llm/adapters/litellm_adapter.py", line 240, in _send_request
    response = await litellm.acompletion(**kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/litellm/utils.py", line 1646, in wrapper_async
    raise e
  File "/app/.venv/lib/python3.12/site-packages/litellm/utils.py", line 1492, in wrapper_async
    result = await original_function(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/litellm/main.py", line 626, in acompletion
    raise exception_type(
          ^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2340, in exception_type
    raise e
  File "/app/.venv/lib/python3.12/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 317, in exception_type
    raise Timeout(
litellm.exceptions.Timeout: litellm.Timeout: APITimeoutError - Request timed out. Error_str: Request timed out. - timeout value=50.0, time taken=151.3 seconds

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/app/app/services/llm/service.py", line 964, in analyze_code_with_custom_prompt
    response = await adapter.complete(request)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/app/services/llm/adapters/litellm_adapter.py", line 173, in complete
    self.handle_error(error, f"LiteLLM ({self.config.provider.value}) API调用失败")
  File "/app/app/services/llm/base_adapter.py", line 102, in handle_error
    raise LLMError(
app.services.llm.types.LLMError: LiteLLM (qwen) API调用失败: 请求超时 (50s)。建议：
1. 检查网络连接是否正常
2. 尝试增加超时时间
3. 验证API端点是否正确

[lintsinghua]

关于超时配置不生效的问题：

从日志中看到 timeout value=50.0，但用户已配置 150000ms。这说明配置保存后，Agent 运行时未正确读取用户配置的超时值。

当前版本已支持在系统配置页面设置超时参数（首Token超时、流式超时、Agent总超时等），请更新到最新版本后重新配置。

如果更新后仍有问题，请提供：

1. 系统配置页面的超时配置截图
2. 使用的 Docker 镜像版本