AI Agent Crashes n8n Cloud Pro2 instance

Describe the problem/error/question

I was using OpenAI > Analyse Image node and everything was working fine. But it doesn’t support o3 or any newer models. So I switched to the AI Agent so I could use o3 and Gemini Pro.

Since switching to this new AI Agent Node type, executions crash the instance and force it to reboot.

So I upgraded from Pro1 to Pro2 instance. Now it doesn’t crash but it does hang the entire instance during processing ~2minutes.

As a further step I cut this process out into a subworkflow to improve memory efficiency - same result. I am passing in a 1 MB file. The parent workflow only consists of 10-15 nodes. and the subworkflow is another 10.

What is the error message (if any)?

Workspace hangs/freezes for duration of execution.

Please share your workflow

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

Share the output returned by the last node

Information on your n8n setup

  • n8n version: 1.95.3,
  • Database (default: SQLite):
  • n8n EXECUTIONS_PROCESS setting (default: own, main):
  • Running n8n via (Docker, npm, n8n cloud, desktop app): n8n Cloud
  • Operating system: