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

The node is followed by one conditional_edges, and the state update is returned at the node. As a result, conditional_edges are updated twice after the return #323

New Issue
Closed
opened 2026-02-20 17:36:42 -05:00 by yindo · 2 comments
yindo commented 2026-02-20 17:36:42 -05:00
Owner
Copy Link
Copy Source

Originally created by @Panda-eat-meat on GitHub (Nov 27, 2024).

Checked other resources

  • I added a very descriptive title to this issue.
  • I searched the LangGraph/LangChain documentation with the integrated search.
  • I used the GitHub search to find a similar question and didn't find it.
  • I am sure that this is a bug in LangGraph/LangChain rather than my code.
  • I am sure this is better as an issue rather than a GitHub discussion, since this is a LangGraph bug and not a design question.

Example Code

# code likes like this

def add_message(left_message, right_message):
    print("add_message: ", left_message, right_message)
    if isinstance(left_message, list) and isinstance(right_message, list):
        left_message.extend(right_message)
    elif isinstance(left_message, list):
        left_message.append(right_message)
    else:
        left_message = right_message
    print("add_message end: ", left_message)
    return left_message



class MainState(TypedDict):
    history_diag: Annotated[List[Union[UserMessage, SystemMessage, str, int]], add_message]



async def build_graph(self):
    ********some node************

    self.workflow.add_node("node 1", self.node_1)
    self.workflow.add_node("daozhen_node_get_next_question_wrap", self.node_get_next_question_wrap)
    self.workflow.add_edge("daozhen_node_get_next_question", "daozhen_node_get_next_question_wrap")

    self.workflow.add_conditional_edges("daozhen_node_get_next_question_wrap", self.edge_conditional_res_route, ["node 1","node 2"])
    return self



async def edge_conditional_res_route(self, state: MainState):
    if is_end or jump_out:
        return "node 1"
    else:
        return "node 2"



async def node_get_next_question_wrap(self, state: MainState):
    append_message = [1, 2]
    return {"history_diag": append_message}



async def node_1(self, state: MainState):
    print(state["history_diag"])
    # get [1, 2, 1, 2], bug just update once

Error Message and Stack Trace (if applicable)

No response

Description

One node is called node1. Following the node, conditional_edges returns to update one field of the state. As a result, conditional_edges returns are updated twice. But if I insert a node between node1 and conditional_edges that doesn't return anything, it won't repeat

System Info

macbook m3

lang version:
langchain 0.3.7
langchain-anthropic 0.2.3
langchain-core 0.3.15
langchain-text-splitters 0.3.2
langgraph 0.2.53
langgraph-checkpoint 2.0.6
langgraph-checkpoint-postgres 2.0.2
langgraph-sdk 0.1.35
langsmith 0.1.137

Originally created by @Panda-eat-meat on GitHub (Nov 27, 2024). ### Checked other resources - [X] I added a very descriptive title to this issue. - [X] I searched the [LangGraph](https://langchain-ai.github.io/langgraph/)/LangChain documentation with the integrated search. - [X] I used the GitHub search to find a similar question and didn't find it. - [X] I am sure that this is a bug in LangGraph/LangChain rather than my code. - [X] I am sure this is better as an issue [rather than a GitHub discussion](https://github.com/langchain-ai/langgraph/discussions/new/choose), since this is a LangGraph bug and not a design question. ### Example Code ```python # code likes like this def add_message(left_message, right_message): print("add_message: ", left_message, right_message) if isinstance(left_message, list) and isinstance(right_message, list): left_message.extend(right_message) elif isinstance(left_message, list): left_message.append(right_message) else: left_message = right_message print("add_message end: ", left_message) return left_message class MainState(TypedDict): history_diag: Annotated[List[Union[UserMessage, SystemMessage, str, int]], add_message] async def build_graph(self): ********some node************ self.workflow.add_node("node 1", self.node_1) self.workflow.add_node("daozhen_node_get_next_question_wrap", self.node_get_next_question_wrap) self.workflow.add_edge("daozhen_node_get_next_question", "daozhen_node_get_next_question_wrap") self.workflow.add_conditional_edges("daozhen_node_get_next_question_wrap", self.edge_conditional_res_route, ["node 1","node 2"]) return self async def edge_conditional_res_route(self, state: MainState): if is_end or jump_out: return "node 1" else: return "node 2" async def node_get_next_question_wrap(self, state: MainState): append_message = [1, 2] return {"history_diag": append_message} async def node_1(self, state: MainState): print(state["history_diag"]) # get [1, 2, 1, 2], bug just update once ``` ### Error Message and Stack Trace (if applicable) _No response_ ### Description One node is called node1. Following the node, conditional_edges returns to update one field of the state. As a result, conditional_edges returns are updated twice. But if I insert a node between node1 and conditional_edges that doesn't return anything, it won't repeat ### System Info macbook m3 lang version: langchain 0.3.7 langchain-anthropic 0.2.3 langchain-core 0.3.15 langchain-text-splitters 0.3.2 langgraph 0.2.53 langgraph-checkpoint 2.0.6 langgraph-checkpoint-postgres 2.0.2 langgraph-sdk 0.1.35 langsmith 0.1.137
yindo added the invalid label 2026-02-20 17:36:42 -05:00
yindo closed this issue 2026-02-20 17:36:43 -05:00
yindo commented 2026-02-20 17:36:43 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Jan 14, 2025):

Please provide a minimal reproducible example https://stackoverflow.com/help/minimal-reproducible-example

@vbarda commented on GitHub (Jan 14, 2025): Please provide a minimal reproducible example https://stackoverflow.com/help/minimal-reproducible-example
yindo commented 2026-02-20 17:36:43 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Jan 29, 2025):

Closing due to inactivity

@vbarda commented on GitHub (Jan 29, 2025): Closing due to inactivity
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 invalid
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#323
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?