Handle additional message content in ollama client

[szaman19]

Enables models to store thinking tokens from model clients

Problem

The BaseAgent and AssistantAgent clients using Ollama OllamaChatCompletionClient don't report thinking tokens when using run(task). Only the content field of the tool call is checked for thought, but ollama may also return the thinking tokens in the thinking field. This PR updates the check in the _ollama_client to also check the thinking field.

As a result:

result = await agent.task()

print(result.thinking)  # This is maybe empty even with a reasoning model 

Changes

• python/packages/autogen-ext/src/autogen_ext/models/ollama/_ollama_client.py - Lines 678-679

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.