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

Agent always calling tool even if not needed #164

New Issue
Closed
opened 2026-02-20 17:30:01 -05:00 by yindo · 2 comments
yindo commented 2026-02-20 17:30:01 -05:00
Owner
Copy Link
Copy Source

Originally created by @tomaszbk on GitHub (Aug 1, 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

result =app.invoke(
   {"messages": [HumanMessage(content="what is your name?")]}, stream_mode=False)

Error Message and Stack Trace (if applicable)

No response

Description

The following prompt that the model receives: "Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.\n\nRespond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables." forces the agent to use a tool, even if I just send hello to the agent. It should say "if you require to use a tool" or something to make it optional

System Info

langchain==0.2.11
langchain-community==0.2.10
langchain-core==0.2.24
langchain-experimental==0.0.63
langchain-ollama==0.1.0
langchain-text-splitters==0.2.2
langchainhub==0.1.20
Windows
python 3.11.7

Originally created by @tomaszbk on GitHub (Aug 1, 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 result =app.invoke( {"messages": [HumanMessage(content="what is your name?")]}, stream_mode=False) ``` ### Error Message and Stack Trace (if applicable) _No response_ ### Description The following prompt that the model receives: "Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.\n\nRespond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}. Do not use variables." forces the agent to use a tool, even if I just send hello to the agent. It should say "if you require to use a tool" or something to make it optional ### System Info langchain==0.2.11 langchain-community==0.2.10 langchain-core==0.2.24 langchain-experimental==0.0.63 langchain-ollama==0.1.0 langchain-text-splitters==0.2.2 langchainhub==0.1.20 Windows python 3.11.7
yindo closed this issue 2026-02-20 17:30:01 -05:00
yindo commented 2026-02-20 17:30:01 -05:00
Author
Owner
Copy Link
Copy Source

@hwchase17 commented on GitHub (Aug 1, 2024):

this seems like a prompting issue and not anything related to langgraph? where are you getting that prompt from? we dont have any built in prompts

@hwchase17 commented on GitHub (Aug 1, 2024): this seems like a prompting issue and not anything related to langgraph? where are you getting that prompt from? we dont have any built in prompts
yindo commented 2026-02-20 17:30:01 -05:00
Author
Owner
Copy Link
Copy Source

@tomaszbk commented on GitHub (Aug 1, 2024):

I checked the internals and you were right, I htink it is ollama that adds that so you could use tools with it

@tomaszbk commented on GitHub (Aug 1, 2024): I checked the internals and you were right, I htink it is ollama that adds that so you could use tools with 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
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#164
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?