I’ve noticed an issue with N8N and tool calling using AI agents.
If the same tool is called multiple time for a single “input” from the user, the response of the tool is always the same regardless of the input.
Call 1
Call 2
I’ve tested other tools like Jira and I ran into the same issue.
Currently Version 1.66.0 (self hosted)
It looks like your topic is missing some important information. Could you provide the following if applicable.
Hi @davidpp,
Welcome to the community 
Could you share your workflow or parts of it?
Ensure to copy your n8n workflow and paste it in the code block, that is in between the pairs of triple backticks, which also could be achieved by clicking </> (preformatted text) in the editor and pasting in your workflow.
```
<your workflow>
```
Make sure that you’ve removed any sensitive information from your workflow and include dummy data or pinned data as much as you can!
Hi!
I just updated to latest (1.88), created a temporary flow using Jira as a tool and was still able to reproduce. (Flow below).
I forgot to specify, this is a read operation, but if I were to do a “write” operation using Jira, it would just create three issues re-using the same cached payload from the first tool calling too.
I am facing same issues with AI Agent node with tool agent. Did anyone got it fixed ?
Same thing here with many tool calling of sub-workflows.
I have the same problem with a sub-workflow.
Has anyone looked at this yet?
Hey all. What version are you on? I think we had a bug in an older version that should now be fixed. Otherwise we’d need to look into this again.
I have the problem on a version 1.80.3 Self-Hosted and on a version 1.77.4 Cloud.
Okay, after Update to 1.80.5 it works like a charm 
Thanks for pointing out the version update!
Phew. Glad to hear that. Thanks for the heads up.
This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.
