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

Tool execution issues or React agent issues？ #621

New Issue
Closed
opened 2026-02-20 17:41:00 -05:00 by yindo · 2 comments
yindo commented 2026-02-20 17:41:00 -05:00
Owner
Copy Link
Copy Source

Originally created by @imliinyi on GitHub (May 14, 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

class TestNode(BaseNode):
    def __init__(self, llm: ChatOpenAI, system_prompt: str):
        self.tools = python_repl_tool
        self.test_agent = create_react_agent(
            llm,
            tools=[self.tools],
            prompt=system_prompt
        )

    def node(self, state: CodeMessageState) -> Command[Literal["code_generate_node", "check_node", END]]:
        """处理测试节点逻辑"""
        code = state.code
        print("=====TEST NODE RUN=====")
        result = self.test_agent.invoke(state)
        goto = self.get_next_node(result["messages"][-1])
        result["messages"][-1] = HumanMessage(
            content=result["messages"][-1].content,
            name="tester"
        )
        return Command(
            update={
                "messages": result["messages"],
                "code": code,
            },
            goto=goto
        )

Error Message and Stack Trace (if applicable)

=====TEST NODE RUN=====
Python REPL can execute arbitrary code. Use with caution.

=====TEST NODE RUN=====
=====END=====

Description

When I execute this node once, it can always run the python_depl_tool tool, but when I run it in bulk, there is a high probability that it will not use the python_depl_tool tool. That's why？The second time, he did not use the python_depl_tool tool

System Info

langchain_core: 0.3.59
langchain: 0.3.25
langchain_community: 0.3.23
langsmith: 0.3.24
langchain_experimental: 0.3.4
langchain_openai: 0.3.16
langchain_text_splitters: 0.3.8
langgraph_sdk: 0.1.61

Originally created by @imliinyi on GitHub (May 14, 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 class TestNode(BaseNode): def __init__(self, llm: ChatOpenAI, system_prompt: str): self.tools = python_repl_tool self.test_agent = create_react_agent( llm, tools=[self.tools], prompt=system_prompt ) def node(self, state: CodeMessageState) -> Command[Literal["code_generate_node", "check_node", END]]: """处理测试节点逻辑""" code = state.code print("=====TEST NODE RUN=====") result = self.test_agent.invoke(state) goto = self.get_next_node(result["messages"][-1]) result["messages"][-1] = HumanMessage( content=result["messages"][-1].content, name="tester" ) return Command( update={ "messages": result["messages"], "code": code, }, goto=goto ) ``` ### Error Message and Stack Trace (if applicable) ```shell =====TEST NODE RUN===== Python REPL can execute arbitrary code. Use with caution. =====TEST NODE RUN===== =====END===== ``` ### Description When I execute this node once, it can always run the python_depl_tool tool, but when I run it in bulk, there is a high probability that it will not use the python_depl_tool tool. That's why？The second time, he did not use the python_depl_tool tool ### System Info > langchain_core: 0.3.59 > langchain: 0.3.25 > langchain_community: 0.3.23 > langsmith: 0.3.24 > langchain_experimental: 0.3.4 > langchain_openai: 0.3.16 > langchain_text_splitters: 0.3.8 > langgraph_sdk: 0.1.61
yindo added the question label 2026-02-20 17:41:00 -05:00
yindo closed this issue 2026-02-20 17:41:00 -05:00
yindo commented 2026-02-20 17:41:00 -05:00
Author
Owner
Copy Link
Copy Source

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

This is most likely an issue with the LLM you're using. LangGraph's prebuilt create_react_agent doesn't have any specific logic for determining whether to use a tool - it's up to the underlying LLM to determine this. Please provide more details if you still think there is some issue specifically w/ LangGraph, otherwise will close the issue

@vbarda commented on GitHub (May 14, 2025): This is most likely an issue with the LLM you're using. LangGraph's prebuilt `create_react_agent` doesn't have any specific logic for determining whether to use a tool - it's up to the underlying LLM to determine this. Please provide more details if you still think there is some issue specifically w/ LangGraph, otherwise will close the issue
yindo commented 2026-02-20 17:41:00 -05:00
Author
Owner
Copy Link
Copy Source

@imliinyi commented on GitHub (May 15, 2025):

This is most likely an issue with the LLM you're using. LangGraph's prebuilt create_react_agent doesn't have any specific logic for determining whether to use a tool - it's up to the underlying LLM to determine this. Please provide more details if you still think there is some issue specifically w/ LangGraph, otherwise will close the issue

Got It

@imliinyi commented on GitHub (May 15, 2025): > This is most likely an issue with the LLM you're using. LangGraph's prebuilt `create_react_agent` doesn't have any specific logic for determining whether to use a tool - it's up to the underlying LLM to determine this. Please provide more details if you still think there is some issue specifically w/ LangGraph, otherwise will close the issue Got It
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 question
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#621
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?