Issues with qwen3:32b, llama4:16x17b, gpt-oss:20b

Up until recently, the Ollama Python library worked with all models that I downloaded, but now I run into issues with some of the newer models:

For reference, here is how I call Ollama:

    response = ollama.generate(
        model=llm_engine,
        prompt=query,
        stream=False,
        format=response_model.model_json_schema(),
        options={"temperature": 0.0, "top_k": 1, "num_ctx": num_ctx},
        images=images,
    )

(1) Minor -- qwen3:32b responds only in "thinking" instead of "response":

Instead of just using response["response"], I now need to use

response_text = (response["response"] or response["thinking"] or "").strip()

since qwen3:32b consistently responds in response["thinking"] and leaves response["response"] blank.

(2) Major -- llama4:16x17b and gpt-oss:20b don't seem to provide any response:

Here is the response I got from invoking gpt-oss:20b:

model='gpt-oss:20b' created_at='2025-11-03T09:07:14.833064Z' done=True done_reason='stop' total_duration=11868059417 load_duration=3789110375 prompt_eval_count=2640 prompt_eval_duration=7464908083 eval_count=7 eval_duration=371895000 response='' thinking=None context=[...]

Apologies in advance if I'm doing something wrong.

Many thanks
Wolfram

I am running Ollama's Python client version 0.6.0 and Ollama version 0.12.9.

Start by reproducing the reported ollama.generate call with qwen3:32b, llama4:16x17b, and gpt-oss:20b using Ollama Python client 0.6.0 and Ollama 0.12.9. Compare the returned response and thinking fields across the affected models; done means the cause and expected client behavior are established and covered by an appropriate regression test or documented resolution.