Cannot use Enums for node names

[laurencejennings]

Checked other resources

• This is a bug, not a usage question. For questions, please use GitHub Discussions.
• I added a clear and detailed title that summarizes the issue.
• I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
• I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.

Example Code

from enum import Enum
from langchain_core.messages import HumanMessage
from langgraph.graph import StateGraph, START, END
from langgraph.prebuilt import create_react_agent

from typing import Literal
from typing_extensions import TypedDict

from langchain_openai import ChatOpenAI
from langgraph.graph import MessagesState, END
from langgraph.types import Command

class Members(Enum):
    researcher="researcher"
    coder="coder"

members = [Members.researcher, Members.coder]
# Our team supervisor is an LLM node. It just picks the next agent to process
# and decides when the work is completed
options = members + ["FINISH"]

system_prompt = (
    "You are a supervisor tasked with managing a conversation between the"
    f" following workers: {members}. Given the following user request,"
    " respond with the worker to act next. Each worker will perform a"
    " task and respond with their results and status. When finished,"
    " respond with FINISH."
)


class Router(TypedDict):
    """Worker to route to next. If no workers needed, route to FINISH."""

    next: Literal[*options]


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


def supervisor_node(state: MessagesState) -> Command[Literal[*members, "__end__"]]:
    messages = [
        {"role": "system", "content": system_prompt},
    ] + state["messages"]
    response = llm.with_structured_output(Router).invoke(messages)
    goto = response["next"]
    if goto == "FINISH":
        goto = END

    return Command(goto=goto)
research_agent = create_react_agent(
    llm, tools=[], state_modifier="You are a researcher. DO NOT do any math."
)


def research_node(state: MessagesState) -> Command[Literal["supervisor"]]:
    result = research_agent.invoke(state)
    return Command(
        update={
            "messages": [
                HumanMessage(content=result["messages"][-1].content, name="researcher")
            ]
        },
        goto="supervisor",
    )


# NOTE: THIS PERFORMS ARBITRARY CODE EXECUTION, WHICH CAN BE UNSAFE WHEN NOT SANDBOXED
code_agent = create_react_agent(llm, tools=[])


def code_node(state: MessagesState) -> Command[Literal["supervisor"]]:
    result = code_agent.invoke(state)
    return Command(
        update={
            "messages": [
                HumanMessage(content=result["messages"][-1].content, name="coder")
            ]
        },
        goto="supervisor",
    )


builder = StateGraph(MessagesState)
builder.add_edge(START, "supervisor")
builder.add_node("supervisor", supervisor_node)
builder.add_node("researcher", research_node)
builder.add_node("coder", code_node)
graph = builder.compile()

Error Message and Stack Trace (if applicable)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[4], line 90
     88 builder.add_node("researcher", research_node)
     89 builder.add_node("coder", code_node)
---> 90 graph = builder.compile()

File ~/projects/ditto/poc/assignments/venv/lib/python3.11/site-packages/langgraph/graph/state.py:510, in StateGraph.compile(self, checkpointer, store, interrupt_before, interrupt_after, debug)
    507 interrupt_after = interrupt_after or []
    509 # validate the graph
--> 510 self.validate(
    511     interrupt=(
    512         (interrupt_before if interrupt_before != "*" else []) + interrupt_after
    513         if interrupt_after != "*"
    514         else []
    515     )
    516 )
    518 # prepare output channels
    519 output_channels = (
    520     "__root__"
    521     if len(self.schemas[self.output]) == 1
   (...)
    527     ]
    528 )

File ~/projects/ditto/poc/assignments/venv/lib/python3.11/site-packages/langgraph/graph/graph.py:405, in Graph.validate(self, interrupt)
    403 for target in all_targets:
    404     if target not in self.nodes and target != END:
--> 405         raise ValueError(f"Found edge ending at unknown node `{target}`")
    406 # validate interrupts
    407 if interrupt:

ValueError: Found edge ending at unknown node `Members.coder`

Description

I'm trying to use an Enum for my node/agent names to make the code more maintainable, but it seems the graph is looking for a node with the actual name of the enum variable not the value.

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 22.5.0: Mon Apr 24 20:51:50 PDT 2023; root:xnu-8796.121.2~5/RELEASE_X86_64
Python Version: 3.11.6 (v3.11.6:8b6ee5ba3b, Oct 2 2023, 11:18:21) [Clang 13.0.0 (clang-1300.0.29.30)]

Package Information

langchain_core: 0.3.29
langchain: 0.3.9
langchain_community: 0.3.8
langsmith: 0.1.147
langchain_openai: 0.2.10
langchain_text_splitters: 0.3.2
langgraph_sdk: 0.1.48

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.11.11
async-timeout: Installed. No version info available.
dataclasses-json: 0.6.7
httpx: 0.28.1
httpx-sse: 0.4.0
jsonpatch: 1.33
langsmith-pyo3: Installed. No version info available.
numpy: 1.26.4
openai: 1.59.3
orjson: 3.10.13
packaging: 24.2
pydantic: 2.10.4
pydantic-settings: 2.7.1
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.35
tenacity: 9.0.0
tiktoken: 0.8.0
typing-extensions: 4.12.2

[vbarda]

hm, i can't reproduce the exact issue you're running, but i would recommend using StrEnum instead of Enum. if you still want to use enums. let me know if this resolves it

[gbaian10]

You can try the following two methods.

class Members(str, Enum):
    ....

or

from enum import StrEnum
class Members(StrEnum):
    ...

[vbarda]

@laurencejennings does this resolve your issue?