bytedance/deer-flow

`write_file` 写入长报告时 LLM 流式超时/断连，输出到页面正常

Open

#3189 opened on May 24, 2026

View on GitHub
 (2 comments) (0 reactions) (1 assignee)Python (67,767 stars) (9,005 forks)batch import
help wanted

Description

背景

执行调研/分析任务时，Agent 将完整报告通过 write_file 工具一次性写入文件。报告内容较长，LLM 需要在单次流式响应中生成整个 content 参数。

现象

写入文件时报错，两种错误交替出现：

错误 1（在config.yaml中配置 stream_chunk_timeout 前）

  File "/app/backend/.venv/lib/python3.12/site-packages/langchain_openai/chat_models/base.py", line 3361, in _astream
    async for chunk in super()._astream(*args, **kwargs):
  File "/app/backend/.venv/lib/python3.12/site-packages/langchain_openai/chat_models/base.py", line 1838, in _astream
    async for chunk in _astream_with_chunk_timeout(
  File "/app/backend/.venv/lib/python3.12/site-packages/langchain_openai/chat_models/_client_utils.py", line 665, in _astream_with_chunk_timeout
    raise StreamChunkTimeoutError(
langchain_openai.chat_models._client_utils.StreamChunkTimeoutError: No streaming chunk received for 120.0s (model=mimo-v2.5, chunks_received=58). The connection may be alive at the TCP layer but is not producing content. Tune or disable via the `stream_chunk_timeout` constructor kwarg (set to None or 0 to disable) or the `LANGCHAIN_OPENAI_STREAM_CHUNK_TIMEOUT_S` env var. See also `http_socket_options` for the kernel-level TCP timeout that catches dead TCP peers.

错误 2（配置 stream_chunk_timeout: 300 后）

2026-05-24 02:45:11 - deerflow.agents.middlewares.llm_error_handling_middleware - WARNING - Transient LLM error on attempt 1/3; retrying in 1000ms: peer closed connection without sending complete message body (incomplete chunked read)

复现条件

  • 场景：Agent 执行 write_file(content="完整报告")，单次工具调用 content 参数很大时
  • 正常场景：同样内容让 LLM 直接输出到页面（对话式输出），正常完成
  • 多环境验证：本地电脑（家庭宽带）和公司服务器（数据中心）均出现过
  • 多模型验证：不同 LLM 提供方均出现过

已尝试的修复

  • 配置 stream_chunk_timeout: 300：无效，只是把报错从"客户端超时"变成"服务器断连"
  • 重启家庭路由器：暂时有效，但公司服务器环境同样出现

求助问题

  1. 是否有更好的方式处理长报告写入？是否考虑在工具层面支持自动分块？
  2. 是否可以在 Skill 提示词中引导 LLM 分章节追加写入（append=True），避免单次生成超长 content，但有些情况下调研任务并没有通过Skill执行，所以系统提示词层面引导？
  3. create_chat_model 中是否需要设置默认的 stream_chunk_timeout 和 httpx timeout 值？
  4. 社区是否有类似经验，长流式响应的最佳实践是什么？

Contributor guide

Tech stack
python
Domain
backendtooling
Issue type
bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
blocked
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
basic knowledge of LLM streamingpython asynclangchainfile I/O in agent tools
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
45
Research direction
Investigate the write file tool implementation in the deer flow codebase to understand how the content is passed to the LLM. Consider implementing automatic chunking of long content before writing to the file, or adjust the LLM call to handle large responses. Also review the create chat model configuration for default timeout settings and examine the langchain openai library's streaming behavior. Consult community best practices for handling long streaming responses in LLM agents.