Langchain branch and langgraph migration

[kientv]

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

runnable_branch = RunnableBranch(
            (lambda msg: is_function_calling(msg), partial_func | tool_chain | StrOutputParser()),
            StrOutputParser()
        )

        response_synthesizer = (prompt | llm | runnable_branch | StrOutputParser()).with_config(
            run_name="SynthesizerFunctionResponse",
        )

Description

ERROR: Error during async streaming: 'code'
code is in the path of API passing from OpenAPI spec

My questions is:

1. With langchain, How to separate branch for function calling and none function calling (partial_func is callable return tool_message, tool_chain is llm return AI_messsage).
2. With langgraph. How to handle OpenAPI function authentication. In langchain, I use partial_func (route_func) to call API with auth and header.

System Info

langchain==0.3.23
langchain-anthropic==0.3.5
langchain-community==0.3.21
langchain-core==0.3.51
langchain-google-genai==2.0.10
langchain-google-vertexai==2.0.20
langchain-openai==0.3.12
langchain-qdrant==0.2.0
langchain-text-splitters==0.3.8