Bug Found
I was setting up a new workflow and noticed that Assistants I created through the OpenAI node’s “Create an Assistant” operation were not having their Temperature and Top P (optional options) being set correctly.
It seems no matter what I set the values to, the result is an Assistant created with both values set to 1.
(I am able to correctly set those values with a later OpenAI node set to “Update an Assistant” operation.)
I suppose this could be a bug on OpenAI’s side, not n8n’s, or perhaps the n8n node is not sending the values correctly?
I was noticed it with OpenAI’s “GPT-4.1-NANO” model, but have not tested it with other models (there are just so many now).
Example workflow to reproduce:
Information on my n8n setup
- n8n version: 1.89.2
- Database (default: SQLite): ? (haven’t set anything, so probably default)
- n8n EXECUTIONS_PROCESS setting (default: own, main): default
- Running n8n via (Docker, npm, n8n cloud, desktop app): Self-hosted via Docker desktop
- Operating system: macOS 13.7.4