Flash Thinking tokens as streaming output.

[nikhilsinghal005]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

ChatGoogleGenerativeAI(
            model=model_name,
            temperature=temperature,
            max_tokens=max_tokens,
            streaming=True,
            stream_usage=True,
            thinking_config = {'include_thoughts': True}

        )    tried this but it is not working for me.

Description

I'm trying to get the thinking tokens using the langchain and from langchain_google_genai import ChatGoogleGenerativeAI
. But i am only receiving only the output tokens not the thoughts that it generates.

System Info

[nikhilsinghal005]

@sbusso @jarib @zeke @deepblue anyone please @staticmethod
def create_thinking_vertex_ai_client(model_name="gemini-2.0-flash-thinking-exp", temperature=0.1, max_tokens=4000):
"""Create a new Vertex AI client instance with working thinking mode"""
return ChatGoogleGenerativeAI(
model=model_name,
temperature=temperature,
max_tokens=max_tokens,
streaming=True,
google_api_key='xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx',
http_options={'api_version':'v1alpha'},
model_kwargs={
'thinking_config': {'include_thoughts': True}
}
) i tried this also

[sbusso]

@nikhilsinghal005 hi

[wxxedu]

Any updates?