[Insight Engine Streamlit App] 研究过程中发生错误: Your request was blocked.

[lxs-w]

错误信息

研究过程中发生错误: Your request was blocked.

错误详情

Traceback (most recent call last):
  File "/app/SingleEngineApp/insight_engine_streamlit_app.py", line 149, in execute_research
    agent._generate_report_structure(query)
  File "/app/SingleEngineApp/../InsightEngine/agent.py", line 417, in _generate_report_structure
    self.state = report_structure_node.mutate_state(state=self.state)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/SingleEngineApp/../InsightEngine/nodes/report_structure_node.py", line 204, in mutate_state
    raise e
  File "/app/SingleEngineApp/../InsightEngine/nodes/report_structure_node.py", line 185, in mutate_state
    report_structure = self.run(input_data, **kwargs)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/SingleEngineApp/../InsightEngine/nodes/report_structure_node.py", line 65, in run
    raise e
  File "/app/SingleEngineApp/../InsightEngine/nodes/report_structure_node.py", line 55, in run
    response = self.llm_client.stream_invoke_to_string(SYSTEM_PROMPT_REPORT_STRUCTURE, self.query)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/SingleEngineApp/../InsightEngine/llms/base.py", line 148, in stream_invoke_to_string
    for chunk in self.stream_invoke(system_prompt, user_prompt, **kwargs):
  File "/app/SingleEngineApp/../InsightEngine/llms/base.py", line 132, in stream_invoke
    raise e
  File "/app/SingleEngineApp/../InsightEngine/llms/base.py", line 118, in stream_invoke
    stream = self.client.chat.completions.create(
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_utils/_utils.py", line 286, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/resources/chat/completions/completions.py", line 1156, in create
    return self._post(
           ^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1259, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1047, in request
    raise self._make_status_error_from_response(err.response) from None
openai.APIStatusError: Your request was blocked.

环境信息

• 应用: Insight Engine Streamlit App
• 时间: 2025-11-19 05:27:10

[dosubot[bot]]

这个 “Your request was blocked” 错误通常和 OpenAI API 配置有关，比如 API key 无效、模型名或 base URL 配置错误、API 账号被限流/封禁，或者网络无法访问 API。常见排查方法如下：

1. 检查 .env 或环境变量里的 INSIGHT_ENGINE_API_KEY、INSIGHT_ENGINE_MODEL_NAME、INSIGHT_ENGINE_BASE_URL 是否填写正确，base URL 不能带 /chat/completions 等多余路径，只能是 https://api.openai.com/v1 这类根路径，否则会被 API 拒绝请求（参考）。
2. 确认 API key 有效且有权限访问目标模型，部分模型需要专门申请权限（参考）。
3. 检查是否触发了并发/频率限制，比如同一个 key 被多个 agent 并发使用，或者组织额度用尽，都会导致请求被 block（参考）。
4. 如果你在国内，确认网络能正常访问 base URL，有时需要代理/VPN（参考）。
5. 配置修改后务必重启服务，确保新参数生效。

可以在日志里加一行 print(self.llm_client.get_model_info())，确认实际用的模型和 API base 是你期望的。如果配置没问题，也可以用 curl 或 Postman 手动请求 base URL，看能否返回 200，进一步定位是网络、配置还是服务商问题。

如果近期刚升级过 BettaFish，注意新版 LLM 接口已切换为流式调用，部分错误会直接抛出并记录日志，便于定位（相关代码实现）。

To reply, just mention @dosu.

---

^{How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other}   

[DoiiarX]

可能是被API供应商封了，例如在不受许可的地区访问openai的api。openai和cluade都有严重的地区政策。