Disable thinking mode for models used through Ollama like qwen3:0.6b

[BrayanMnz]

Please do a quick search on GitHub issues first, the feature you are about to request might have already been requested.

Expected Behavior

The ollama team has added thinking support to the cli and the api.
See: ollama/ollama#10584

This parameter allows to control the output of the "thinking" process of the model

Current Behavior

At this moment, there is no way to manage the thinking parameter from the Spring AI Ollama API.

Context

Adding this, will give us the ability to use thinking models, and get just the "output" without the thinking phase of the model.

[BrayanMnz]

Hi team - I am looking forward on contributing the changes for making this possible, I do appreciate any help with the onboarding process for me, to be able to contribute to the project.

Regards,

[sunyuhan1998]

Hi @BrayanMnz , Thanks for the report!I've pushed a PR: #3386 before this to add that support, and it's currently sitting in the 1.1.X milestone

[BrayanMnz]

That's great, the changes LGTM @sunyuhan1998
Hopefully they will be integrated soon in the project.

This #3386 address my concern, closing this.