When llm are working, how to manually halt

[fendaLzx]

[jonigl]

Hey @fendaLzx, thanks for reaching out!

I’ve just released v0.23.0, which adds the ability to manually stop model generation by simply pressing a during a run.

🔗 https://github.com/jonigl/mcp-client-for-ollama/releases/tag/v0.23.0

Here’s a quick demo of how it works:

You can upgrade with:

pip install --upgrade mcp-client-for-ollama
# or
pip install mcp-client-for-ollama==0.23.0

Would love to hear if this solves the issue for you!

Cheers!