langgraph-supervisor causes Gemini LLM invocation issues — "contents not specified" error

[iaavas]

I'm encountering an issue while using the langgraph-supervisor library in conjunction with Google's Gemini model (via LangChain). The error I'm seeing is:

langchain_google_genai.chat_models.ChatGoogleGenerativeAIError: Invalid argument provided to Gemini: 400 * GenerateContentRequest.contents: contents is not specified 

After investigating, I found:

• When the LLM is invoked directly (outside of langgraph-supervisor), the Gemini model works fine.
• However, when used within the langgraph-supervisor, Gemini throws the above error, which indicates that an empty content field is being passed at some point.
• This suggests that the supervisor may be invoking the agent even when no new message or content is passed, leading Gemini to reject the call.

Reproducible Code:

from langchain_google_genai import ChatGoogleGenerativeAI
from langgraph_supervisor import create_supervisor
from langgraph.prebuilt import create_react_agent
from langchain_core.messages import HumanMessage
from config import GEMINI_API_KEY


model = ChatGoogleGenerativeAI(
            model="gemini-1.5-flash",
            temperature=0.7,
            google_api_key=GEMINI_API_KEY,

        )


# Create specialized agents

def add(a: float, b: float) -> float:
    """Add two numbers."""
    return a + b

def multiply(a: float, b: float) -> float:
    """Multiply two numbers."""
    return a * b

def web_search(query: str) -> str:
    """Search the web for information."""
    return (
        "Here are the headcounts for each of the FAANG companies in 2024:\n"
        "1. **Facebook (Meta)**: 67,317 employees.\n"
        "2. **Apple**: 164,000 employees.\n"
        "3. **Amazon**: 1,551,000 employees.\n"
        "4. **Netflix**: 14,000 employees.\n"
        "5. **Google (Alphabet)**: 181,269 employees."
    )

math_agent = create_react_agent(
    model=model,
    tools=[add, multiply],
    name="math_expert",
    prompt="You are a math expert. Always use one tool at a time."
)

research_agent = create_react_agent(
    model=model,
    tools=[web_search],
    name="research_expert",
    prompt="You are a world class researcher with access to web search. Do not do any math."
)

# Create supervisor workflow
workflow = create_supervisor(
    [research_agent, math_agent],
    model=model,
    prompt=(
        "You are a team supervisor managing a research expert and a math expert. "
        "For current events, use research_agent. "
        "For math problems, use math_agent."
    )
)

# Compile and run
app = workflow.compile()
result = app.invoke({
    "messages": [
        {
            "role": "user",
            "content": "what's the combined headcount of the FAANG companies in 2024?"
        }
    ]
})
print(result)

[vbarda]

can you provide a trace or a full list of messages that you are passing to the gemini api?