langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

Two print in one step: When use for step in graph.stream #738

New Issue
Closed
opened 2026-02-20 17:41:31 -05:00 by yindo · 1 comment
yindo commented 2026-02-20 17:41:31 -05:00
Owner
Copy Link
Copy Source

Originally created by @Xiaoshouzhen on GitHub (Jun 24, 2025).

Checked other resources

  • This is a bug, not a usage question. For questions, please use GitHub Discussions.
  • I added a clear and detailed title that summarizes the issue.
  • I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
  • I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.

Example Code

builder = StateGraph(State)
builder.add_edge(START, "coordinator")
builder.add_node("coordinator", coordinator_node)
builder.add_node("planner", planner_node)
builder.add_node("supervisor", supervisor_node)
builder.add_node("data_gatherer", data_gatherer_node)
# builder.add_node("reporter", data_gatherer)
# builder.add_edge("reporter", )
g = builder.compile()
#
input = "哪天的生产质量较差？"
st = State(messages=[HumanMessage(content=input)],
           TEAM_MEMBERS=TEAM_MEMBERS,
           next="",
           full_plan="",
           deep_thinking_mode=False,
           search_before_planning=False,
           next_description="",
           query_data=[])

for step, met in g.stream(
        st,
        stream_mode="values",
        subgraphs=True
):

    met["messages"][-1].pretty_print()

Error Message and Stack Trace (if applicable)

Description

i use graph.stream(include a subgraph), i expect the out of stream is one time, but the process out is Two time, i receive follow out, the question is the same out will print again when next node update messages.

add: I use command method to update messages,like this:

def supervisor_node(state: State) -> Command[Literal["data_gatherer"]]:
    messages = apply_prompt_template("supervisor", state)
    response = get_llm(0.7).with_structured_output(Router).invoke(messages)
    goto = response["next"]
    task = response["task_description"]
    if goto == "FINISH":
        goto = "__end__"
    return Command(
        update={
            "next": goto,
            "next_description": task
        },
        goto=goto,

    )

System Info

================================== Ai Message ==================================
Name: planner
{
"thought": "用户询问哪一天的生产质量较差，需要分析生产数据以识别质量问题发生的日期。",
"title": "分析生产质量差异并定位问题日期",
"steps": [
{
"agent_name": "data_gatherer",
"title": "收集全量生产数据",
"description": "从数据库提取所有生产记录，包括生产日期、产品批次、质检结果、缺陷类型及数量等核心字段。确保覆盖近3年的完整数据集。",
"note": "需包含时间维度、质量指标和生产参数的原始数据"
},
{
"agent_name": "organizer",
"title": "结构化生产质量数据",
"description": "按日期粒度整理数据，计算每日合格率、缺陷密度、客户投诉率等关键质量指标，建立标准化时间序列数据库。",
"note": "需消除数据冗余并补充缺失值"
},
{
"agent_name": "analyzer",
"title": "识别异常质量波动",
"description": "运用统计过程控制（SPC）方法分析每日质量指标，结合趋势分析和假设检验定位显著偏离正常范围的日期。",
"note": "需考虑季节性因素和生产规模变化"
},
{
"agent_name": "reporter",
"title": "生成质量异常报告",
"description": "输出包含问题日期列表、关键缺陷类型、可能影响因素及改善建议的正式分析报告。",
"note": "需用可视化图表展示异常波动点"
}
]
}
================================== Ai Message ==================================
Name: planner
{
"thought": "用户询问哪一天的生产质量较差，需要分析生产数据以识别质量问题发生的日期。",
"title": "分析生产质量差异并定位问题日期",
"steps": [
{
"agent_name": "data_gatherer",
"title": "收集全量生产数据",
"description": "从数据库提取所有生产记录，包括生产日期、产品批次、质检结果、缺陷类型及数量等核心字段。确保覆盖近3年的完整数据集。",
"note": "需包含时间维度、质量指标和生产参数的原始数据"
},
{
"agent_name": "organizer",
"title": "结构化生产质量数据",
"description": "按日期粒度整理数据，计算每日合格率、缺陷密度、客户投诉率等关键质量指标，建立标准化时间序列数据库。",
"note": "需消除数据冗余并补充缺失值"
},
{
"agent_name": "analyzer",
"title": "识别异常质量波动",
"description": "运用统计过程控制（SPC）方法分析每日质量指标，结合趋势分析和假设检验定位显著偏离正常范围的日期。",
"note": "需考虑季节性因素和生产规模变化"
},
{
"agent_name": "reporter",
"title": "生成质量异常报告",
"description": "输出包含问题日期列表、关键缺陷类型、可能影响因素及改善建议的正式分析报告。",
"note": "需用可视化图表展示异常波动点"
}
]
}

Originally created by @Xiaoshouzhen on GitHub (Jun 24, 2025). ### Checked other resources - [x] This is a bug, not a usage question. For questions, please use GitHub Discussions. - [x] I added a clear and detailed title that summarizes the issue. - [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example). - [x] I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue. ### Example Code ```python builder = StateGraph(State) builder.add_edge(START, "coordinator") builder.add_node("coordinator", coordinator_node) builder.add_node("planner", planner_node) builder.add_node("supervisor", supervisor_node) builder.add_node("data_gatherer", data_gatherer_node) # builder.add_node("reporter", data_gatherer) # builder.add_edge("reporter", ) g = builder.compile() # input = "哪天的生产质量较差？" st = State(messages=[HumanMessage(content=input)], TEAM_MEMBERS=TEAM_MEMBERS, next="", full_plan="", deep_thinking_mode=False, search_before_planning=False, next_description="", query_data=[]) for step, met in g.stream( st, stream_mode="values", subgraphs=True ): met["messages"][-1].pretty_print() ``` ### Error Message and Stack Trace (if applicable) ```shell ``` ### Description i use graph.stream(include a subgraph), i expect the out of stream is one time, but the process out is Two time, i receive follow out, the question is the same out will print again when next node update messages. add: I use command method to update messages,like this: ```python def supervisor_node(state: State) -> Command[Literal["data_gatherer"]]: messages = apply_prompt_template("supervisor", state) response = get_llm(0.7).with_structured_output(Router).invoke(messages) goto = response["next"] task = response["task_description"] if goto == "FINISH": goto = "__end__" return Command( update={ "next": goto, "next_description": task }, goto=goto, ) ``` ### System Info ================================== Ai Message ================================== Name: planner { "thought": "用户询问哪一天的生产质量较差，需要分析生产数据以识别质量问题发生的日期。", "title": "分析生产质量差异并定位问题日期", "steps": [ { "agent_name": "data_gatherer", "title": "收集全量生产数据", "description": "从数据库提取所有生产记录，包括生产日期、产品批次、质检结果、缺陷类型及数量等核心字段。确保覆盖近3年的完整数据集。", "note": "需包含时间维度、质量指标和生产参数的原始数据" }, { "agent_name": "organizer", "title": "结构化生产质量数据", "description": "按日期粒度整理数据，计算每日合格率、缺陷密度、客户投诉率等关键质量指标，建立标准化时间序列数据库。", "note": "需消除数据冗余并补充缺失值" }, { "agent_name": "analyzer", "title": "识别异常质量波动", "description": "运用统计过程控制（SPC）方法分析每日质量指标，结合趋势分析和假设检验定位显著偏离正常范围的日期。", "note": "需考虑季节性因素和生产规模变化" }, { "agent_name": "reporter", "title": "生成质量异常报告", "description": "输出包含问题日期列表、关键缺陷类型、可能影响因素及改善建议的正式分析报告。", "note": "需用可视化图表展示异常波动点" } ] } ================================== Ai Message ================================== Name: planner { "thought": "用户询问哪一天的生产质量较差，需要分析生产数据以识别质量问题发生的日期。", "title": "分析生产质量差异并定位问题日期", "steps": [ { "agent_name": "data_gatherer", "title": "收集全量生产数据", "description": "从数据库提取所有生产记录，包括生产日期、产品批次、质检结果、缺陷类型及数量等核心字段。确保覆盖近3年的完整数据集。", "note": "需包含时间维度、质量指标和生产参数的原始数据" }, { "agent_name": "organizer", "title": "结构化生产质量数据", "description": "按日期粒度整理数据，计算每日合格率、缺陷密度、客户投诉率等关键质量指标，建立标准化时间序列数据库。", "note": "需消除数据冗余并补充缺失值" }, { "agent_name": "analyzer", "title": "识别异常质量波动", "description": "运用统计过程控制（SPC）方法分析每日质量指标，结合趋势分析和假设检验定位显著偏离正常范围的日期。", "note": "需考虑季节性因素和生产规模变化" }, { "agent_name": "reporter", "title": "生成质量异常报告", "description": "输出包含问题日期列表、关键缺陷类型、可能影响因素及改善建议的正式分析报告。", "note": "需用可视化图表展示异常波动点" } ] }
yindo added the bugpending labels 2026-02-20 17:41:31 -05:00
yindo closed this issue 2026-02-20 17:41:31 -05:00
yindo commented 2026-02-20 17:41:32 -05:00
Author
Owner
Copy Link
Copy Source

@sydney-runkle commented on GitHub (Jun 27, 2025):

I believe you can use subgraphs=False to fix this. Please open a new issue with a MRE if you'd like further assistance.

@sydney-runkle commented on GitHub (Jun 27, 2025): I believe you can use `subgraphs=False` to fix this. Please open a new issue with a MRE if you'd like further assistance.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label bug pending
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#738
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?