Not able to call tool correctly when execute multi agent node parallel way.

[iam1492]

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

class State(TypedDict):
    messages: Annotated[list[AnyMessage], add_messages]
    
openai = ChatOpenAI (
    model= "gpt-4o-mini"
)

tools = [get_financial_statement]
llm_with_tool = openai.bind_tools(tools)

financial_tool_node = ToolNode(tools)

def create_agent_node(state, system_prompt, has_tool=False):
    human_messages = [msg for msg in state["messages"] if isinstance(msg, HumanMessage)]
    other_messages = [msg for msg in state["messages"] 
                     if not isinstance(msg, HumanMessage) and not isinstance(msg, SystemMessage)]
    system_messages = [SystemMessage(content=system_prompt)]
    messages = system_messages + human_messages + other_messages
    
    if has_tool:
        message = llm_with_tool.invoke(messages)
    else:
        message = openai.invoke(messages)
    
    return {
        "messages": [message]
    }
    
researcher = lambda state: create_agent_node(state, system_prompt=stock_researcher_prompt)
financial_analyst = lambda state: create_agent_node(state, system_prompt=stock_fianacial_analyst_1_prompt, has_tool=True)
financial_analyst_2 = lambda state: create_agent_node(state, system_prompt=stock_financial_analyst_2_prompt)
financial_advisor = lambda state: create_agent_node(state, system_prompt=stock_financial_advisor_prompt)
hedge_fund_manager = lambda state: create_agent_node(state, system_prompt=hedge_fund_manager_prompt)

builder = StateGraph(State)
builder.add_node("researcher", researcher)
builder.add_node("financial_analyst", financial_analyst)
builder.add_node("financial_tool_node", financial_tool_node)
builder.add_node("financial_analyst_2", financial_analyst_2)
builder.add_node("financial_advisor", financial_advisor)
builder.add_node("hedge_fund_manager", hedge_fund_manager)

builder.add_edge(START, "researcher")
builder.add_edge("researcher", "financial_analyst")
builder.add_edge("researcher", "financial_analyst_2")

def my_tools_condition(
    state: Union[list[AnyMessage], dict[str, Any], BaseModel],
    messages_key: str = "messages",
) -> Literal["financial_tool_node", "__end__"]:
    
    if isinstance(state, list):
        ai_message = state[-1]
    elif isinstance(state, dict) and (messages := state.get(messages_key, [])):
        ai_message = messages[-1]
    elif messages := getattr(state, messages_key, []):
        ai_message = messages[-1]
    else:
        raise ValueError(f"No messages found in input state to tool_edge: {state}")
    if hasattr(ai_message, "tool_calls") and len(ai_message.tool_calls) > 0:
        return "financial_tool_node"
    return "__end__"

builder.add_conditional_edges("financial_analyst", my_tools_condition)
builder.add_edge("financial_tool_node", "financial_analyst")
builder.add_edge(["financial_analyst", "financial_analyst_2"], "financial_advisor")
builder.add_edge("financial_advisor", "hedge_fund_manager")
builder.add_edge("hedge_fund_manager", END)

app = builder.compile()

Description

Hi I'm very beginner with langgraph.
I saw some of tutorial's from website and youtube and try to migrate my crewai project to langgraph.
What I want to achieve is running parallel node with binding tool.
But when I trying to run with initial message then I always have same error.

openai.BadRequestError: Error code: 400 - {'error': {'message': "An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'. The following tool_call_ids did not have response messages: call_eKBRwc2Sb60wtUlZkbZrC9VB", 'type': 'invalid_request_error', 'param': 'messages.[4].role', 'code': None}}      
During task with name 'financial_advisor' and id '0c6a1ae5-5895-93d9-3bae-34948274390f'

And when I saw langsmith log. My financial tool node has empty message.
What I expect is STEP like this:
financial_analysis -> call tool(financial_tool_node) -> fianancial_analysis with result-> financial advisor.
Here is my mermaid graph and I suspect that financial advisor node start before my financial_tool_node finish it's work.

Here is my langsmith log

System Info

System Information

OS: Windows
OS Version: 10.0.26100
Python Version: 3.13.2 (tags/v3.13.2:4f8bb39, Feb 4 2025, 15:23:48) [MSC v.1942 64 bit (AMD64)]

Package Information

langchain_core: 0.3.47
langsmith: 0.3.18
langchain_anthropic: 0.3.10
langchain_google_genai: 2.1.0
langchain_openai: 0.3.9
langgraph_sdk: 0.1.58

Optional packages not installed

langserve

Other Dependencies

anthropic<1,>=0.49.0: Installed. No version info available.
filetype: 1.2.0
google-ai-generativelanguage: 0.6.17
httpx: 0.28.1
jsonpatch<2.0,>=1.33: Installed. No version info available.
langchain-core<1.0.0,>=0.3.45: Installed. No version info available.
langsmith-pyo3: Installed. No version info available.
langsmith<0.4,>=0.1.125: Installed. No version info available.
openai-agents: Installed. No version info available.
openai<2.0.0,>=1.66.3: Installed. No version info available.
opentelemetry-api: Installed. No version info available.
opentelemetry-exporter-otlp-proto-http: Installed. No version info available.
opentelemetry-sdk: Installed. No version info available.
orjson: 3.10.15
packaging: 24.2
packaging<25,>=23.2: Installed. No version info available.
pydantic: 2.10.6
pydantic<3.0.0,>=2.5.2;: Installed. No version info available.
pydantic<3.0.0,>=2.7.4: Installed. No version info available.
pydantic<3.0.0,>=2.7.4;: Installed. No version info available.
pytest: Installed. No version info available.
PyYAML>=5.3: Installed. No version info available.
requests: 2.32.3
requests-toolbelt: 1.0.0
rich: Installed. No version info available.
tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available.
tiktoken<1,>=0.7: Installed. No version info available.
typing-extensions>=4.7: Installed. No version info available.
zstandard: 0.23.0

[iam1492]

I just found out that when I make [financial_analyst and financial_tool_node] to a SubGraph, the project works well.
Is it because of different super step issue?
Thanks!

[iam1492]

Move this q&a to langgraph discussion