Thinking tokens are present in the Ollama output

[tannisroot]

trafficstars

The problem

When using the "reasoning" model qwq:latest with support for tools in Ollama, it does work, however, output contains the "thinking" section, contained within <think> section, that should be omitted and not presented to the user.

What version of Home Assistant Core has the issue?

core-2025.3.0

What was the last working version of Home Assistant Core?

No response

What type of installation are you running?

Home Assistant Container

Integration causing the issue

Ollama

Link to integration documentation on our website

https://www.home-assistant.io/integrations/ollama/

Diagnostics information

No response

Example YAML snippet

Anything in the logs that might be useful for us?

Additional information

No response