Tools Returning A Command Are Missing From Messages-streaming

Apr 22, 2025 by ADMIN 62 views

===========================================================

Problem Description

When using tools that return a command, the messages-streaming functionality is not working as expected. This issue is related to the fix implemented in #4111, which is not properly addressing the issue of tools returning an array of commands.

Example Code

The following code snippet demonstrates the issue:

from typing import Annotated, Any

from langchain_core.messages import ToolMessage
from langchain_core.runnables.config import RunnableConfig
from langchain_core.tools import tool
from langchain_core.tools.base import InjectedToolCallId
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
from langgraph.prebuilt.chat_agent_executor import AgentState
from langgraph.types import Command

USER_INFO = [
    {"user_id": "1", "name": "Bob Dylan", "location": "New York, NY"},
    {"user_id": "2", "name": "Taylor Swift", "location": "Beverly Hills, CA"},
]

USER_ID_TO_USER_INFO = {info["user_id"]: info for info in USER_INFO}


class State(AgentState):
    # updated by the tool
    user_info: dict[str, Any]


def main() -> None:
    @tool
    def lookup_user_info(tool_call_id: Annotated[str, InjectedToolCallId], config: RunnableConfig):
        """Use this to look up user information to better assist them with their questions."""
        user_id = config.get("configurable", {}).get("user_id")
        if user_id is None:
            raise ValueError("Please provide user ID")

        if user_id not in USER_ID_TO_USER_INFO:
            raise ValueError(f"User '{user_id}' not found")

        user_info = USER_ID_TO_USER_INFO[user_id]
        return Command(
            update={
                # update the state keys
                "user_info": user_info,
                # update the message history
                "messages": [
                    ToolMessage(
                        "Successfully looked up user information", tool_call_id=tool_call_id
                    )
                ],
            }
        )

    def prompt(state: State):
        user_info = state.get("user_info")
        if user_info is None:
            return state["messages"]

        system_msg = (
            f"User name is {user_info['name']}. User lives in {user_info['location']}"
        )
        return [{"role": "system", "content": system_msg}] + state["messages"]

    model = ChatOpenAI(model="gpt-4o")

    agent = create_react_agent(
        model,
        # pass the tool that can update state
        [lookup_user_info],
        state_schema=State,
        # pass dynamic prompt function
        prompt=prompt,
    )

    agent_input = {"messages": [("user", "hi, where do I live?")]}
    agent_config = {"configurable": {"user_id": "1"}}

    invoke_result = agent.invoke(
        agent_input,
        agent_config,
    )

    # print(invoke_result)

    for chunk in agent.stream(agent_input, agent_config, stream_mode='messages'):
        print(chunk)


if __name__ == '__main__':
    main()

Error Message and Stack Trace

The error message is:

There are no streaming messages from the tool command response.

Description

The issue is that the lookup_user_info tool returns a command, but the messages-streaming functionality is not working as expected. This is because the fix implemented in #4111 is not properly addressing the issue of tools returning an array of commands.

System Info

System Information

OS: Darwin OS Version: Darwin Kernel Version 24.3.0: Thu Jan 2 20:24:16 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T6000 Python Version: 3.11.11 (main, Mar 11 2025, 17:41:13) [Clang 20.1.0 ]

Package Information

langchain_core: 0.3.54 langchain: 0.3.23 langsmith: 0.3.32 langchain_anthropic: 0.3.12 langchain_groq: 0.3.2 langchain_text_splitters: 0.3.8 langgraph_sdk: 0.1.61

Optional packages not installed

langserve

Other Dependencies

anthropic<1,>=0.49.0: Installed. No version info available. async-timeout<5.0.0,>=4.0.0;: Installed. No version info available. groq<1,>=0.4.1: Installed. No version info available. httpx: 0.28.1 jsonpatch<2.0,>=1.33: Installed. No version info available. langchain-anthropic;: Installed. No version info available. langchain-aws;: Installed. No version info available. langchain-azure-ai;: Installed. No version info available. langchain-cohere;: Installed. No version info available. langchain-community;: Installed. No version info available. langchain-core<1.0.0,>=0.3.49: Installed. No version info available. langchain-core<1.0.0,>=0.3.51: Installed. No version info available. langchain-core<1.0.0,>=0.3.53: Installed. No version info available. langchain-deepseek;: Installed. No version info available. langchain-fireworks;: Installed. No version info available. langchain-google-genai;: Installed. No version info available. langchain-google-vertexai;: Installed. No version info available. langchain-groq;: Installed. No version info available. langchain-huggingface;: Installed. No version info available. langchain-mistralai;: Installed. No version info available. langchain-ollama;: Installed. No version info available. langchain-openai;: Installed. No version info available. langchain-perplexity;: Installed. No version info available. langchain-text-splitters<1.0.0,>=0.3.8: Installed. No version info available. langchain-together;: Installed. No version info available. langchain-xai;: Installed. No version info available. langsmith-pyo3: Installed. No version info available. langsmith<0.4,>=0.1.125: Installed. No version info available. langsmith<0.4,>=0.1.17: Installed. No version info available. openai-agents: Installed. No version info available. opentelemetry-api: 1.32.1 opentelemetry-exporter-otlp-proto-http: 1.32.1 opentelemetry-sdk: 1.32.1 orjson: 3.10.16 packaging: 24.2 packaging<25,>=23.2: Installed. No version info available. pydantic: 2.11.3 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 requests<3,>=2: Installed. No version info available. rich: 14.0.0 SQLAlchemy<3,>=1.4: Installed. No version info available. tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available. typing-extensions>=4.7: Installed. No version info available. zstandard: 0.23.0

Solution

To fix this issue, we need to modify the lookup_user_info tool to return a single command instead of an array of commands. We can do this by changing the return statement to:

return Command(
    update={
        # update the state keys
        "user_info": user_info,
        # update the message history
        "messages": [
            ToolMessage(
                "Successfully looked up user information", tool_call_id=tool_call_id
            )
        ],
    }
)

This will ensure that the messages-streaming functionality works as expected.

Code Changes

The modified code is:

def lookup_user_info(tool_call_id: Annotated[str, InjectedToolCallId], config: RunnableConfig):
    """Use this to look up user information to better assist them with their questions."""
    user_id = config.get("configurable", {}).get("user_id")
    if user_id is None:
        raise ValueError("Please provide user ID")

    if user_id not in USER_ID_TO_USER_INFO:
        raise ValueError(f"User '{user_id}' not found")

    user_info = USER_ID_TO_USER_INFO[user_id]
    return Command(
        update={
            # update<br/>
# Tools Returning a Command are Missing from Messages-Streaming: Q&A

## Q: What is the issue with tools returning a command?

A: The issue is that tools returning a command are missing from messages-streaming. This means that when a tool returns a command, the messages-streaming functionality is not working as expected.

## Q: What is the cause of this issue?

A: The cause of this issue is that the fix implemented in #4111 is not properly addressing the issue of tools returning an array of commands.

## Q: How can I reproduce this issue?

A: To reproduce this issue, you can use the example code provided in the problem description. This code demonstrates the issue and can be used to reproduce it.

## Q: What are the system requirements for this issue?

A: The system requirements for this issue are:

* OS: Darwin
* OS Version: Darwin Kernel Version 24.3.0
* Python Version: 3.11.11

## Q: What packages are required to reproduce this issue?

A: The packages required to reproduce this issue are:

* langchain_core: 0.3.54
* langchain: 0.3.23
* langsmith: 0.3.32
* langchain_anthropic: 0.3.12
* langchain_groq: 0.3.2
* langchain_text_splitters: 0.3.8
* langgraph_sdk: 0.1.61

## Q: How can I fix this issue?

A: To fix this issue, you need to modify the `lookup_user_info` tool to return a single command instead of an array of commands. You can do this by changing the return statement to:
```python
return Command(
    update={
        # update the state keys
        "user_info": user_info,
        # update the message history
        "messages": [
            ToolMessage(
                "Successfully looked up user information", tool_call_id=tool_call_id
            )
        ],
    }
)

This will ensure that the messages-streaming functionality works as expected.

Q: What are the benefits of fixing this issue?

A: The benefits of fixing this issue are:

Improved functionality of messages-streaming
Better user experience
Increased efficiency

Q: Are there any known limitations or workarounds for this issue?

A: Yes, there are known limitations and workarounds for this issue. The limitations are:

The fix implemented in #4111 is not properly addressing the issue of tools returning an array of commands.
The modified code requires changes to the lookup_user_info tool.

The workarounds are:

Use the modified code to fix the issue.
Implement a custom solution to handle tools returning an array of commands.

Q: How can I get help with this issue?

A: You can get help with this issue by:

Checking the documentation and resources provided by the project maintainers.
Asking questions on the project's discussion forum or support channel.
Reaching out to the project maintainers directly.

Q: What are the next steps for this issue?

A: The next steps for this issue are:

Implement the fix in the lookup_user_info tool.
Test the fix to ensure it works as expected.
Review and refine the fix as needed.

By following these steps, you can resolve the issue and ensure that the messages-streaming functionality works as expected.