langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

Command do not render graph if nodes are defined within a class. #391

New Issue
Closed
opened 2026-02-20 17:39:53 -05:00 by yindo · 3 comments
yindo commented 2026-02-20 17:39:53 -05:00
Owner
Copy Link
Copy Source

Originally created by @SergioG-M on GitHub (Jan 9, 2025).

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

import random

from langgraph.graph import START, StateGraph
from langgraph.types import Command
from typing_extensions import Literal, TypedDict


# Define graph state
class State(TypedDict):
    foo: str


# Define the nodes


class MyGraph:
    def node_a(self, state: State) -> Command[Literal["node_b", "node_c"]]:
        print("Called A")
        value = random.choice(["a", "b"])
        # this is a replacement for a conditional edge function
        if value == "a":
            goto = "node_b"
        else:
            goto = "node_c"

        # note how Command allows you to BOTH update the graph state AND route to the next node
        return Command(
            # this is the state update
            update={"foo": value},
            # this is a replacement for an edge
            goto=goto,
        )

    # Nodes B and C are unchanged

    def node_b(self, state: State):
        print("Called B")
        return {"foo": state["foo"] + "b"}

    def node_c(self, state: State):
        print("Called C")
        return {"foo": state["foo"] + "c"}

    def build_graph(self):
        builder = StateGraph(State)
        builder.add_edge(START, "node_a")
        builder.add_node("node_a", self.node_a)
        builder.add_node("node_b", self.node_b)
        builder.add_node("node_c", self.node_c)
        # NOTE: there are no edges between nodes A, B and C!

        graph = builder.compile()
        return graph


from IPython.display import display, Image

graph = MyGraph().build_graph()

display(Image(graph.get_graph().draw_mermaid_png()))

Error Message and Stack Trace (if applicable)

No response

Description

When using command inside a class the edges are not rendered. It works if nodes are outside (or probably if static methods?)
I adapted this code: https://langchain-ai.github.io/langgraph/how-tos/command/#define-graph
And the generated graph is this:

image

System Info

langgraph version 0.2.61

Originally created by @SergioG-M on GitHub (Jan 9, 2025). ### Checked other resources - [x] This is a bug, not a usage question. For questions, please use GitHub Discussions. - [X] I added a clear and detailed title that summarizes the issue. - [X] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example). - [X] 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 ```python import random from langgraph.graph import START, StateGraph from langgraph.types import Command from typing_extensions import Literal, TypedDict # Define graph state class State(TypedDict): foo: str # Define the nodes class MyGraph: def node_a(self, state: State) -> Command[Literal["node_b", "node_c"]]: print("Called A") value = random.choice(["a", "b"]) # this is a replacement for a conditional edge function if value == "a": goto = "node_b" else: goto = "node_c" # note how Command allows you to BOTH update the graph state AND route to the next node return Command( # this is the state update update={"foo": value}, # this is a replacement for an edge goto=goto, ) # Nodes B and C are unchanged def node_b(self, state: State): print("Called B") return {"foo": state["foo"] + "b"} def node_c(self, state: State): print("Called C") return {"foo": state["foo"] + "c"} def build_graph(self): builder = StateGraph(State) builder.add_edge(START, "node_a") builder.add_node("node_a", self.node_a) builder.add_node("node_b", self.node_b) builder.add_node("node_c", self.node_c) # NOTE: there are no edges between nodes A, B and C! graph = builder.compile() return graph from IPython.display import display, Image graph = MyGraph().build_graph() display(Image(graph.get_graph().draw_mermaid_png())) ``` ### Error Message and Stack Trace (if applicable) _No response_ ### Description When using command inside a class the edges are not rendered. It works if nodes are outside (or probably if static methods?) I adapted this code: https://langchain-ai.github.io/langgraph/how-tos/command/#define-graph And the generated graph is this: ![image](https://github.com/user-attachments/assets/d3a850b5-802f-4bc1-a2a1-37c2c8d0d5d7) ### System Info langgraph version 0.2.61
yindo closed this issue 2026-02-20 17:39:53 -05:00
yindo commented 2026-02-20 17:39:53 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Jan 9, 2025):

I can reproduce the issue, will look into it

@vbarda commented on GitHub (Jan 9, 2025): I can reproduce the issue, will look into it
yindo commented 2026-02-20 17:39:53 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Jan 14, 2025):

Fixed in #3032

@vbarda commented on GitHub (Jan 14, 2025): Fixed in #3032
yindo commented 2026-02-20 17:39:53 -05:00
Author
Owner
Copy Link
Copy Source

@luhodaan commented on GitHub (Jul 30, 2025):

Hi,
I'm experiencing the same issue described in this thread, but with LangGraph 0.3.1. The edges are still not being rendered when using Command within class methods.
Environment:

LangGraph version: 0.3.1
Python version: 3.11.6
OS: Windows 11

Real-world impact:
I have a multi-step agent with conditional routing based on LLM tool calls and structured outputs. The graph works perfectly but all Command-inferred edges are invisible, making it impossible to understand the flow in LangGraph Studio.

Could we please reopen this issue?

I attach a simplified example of my graph and what I mean:

from langgraph.types import Command
from typing import Literal

def evaluate_user_query(state, llm_instance) -> Command[Literal["tables_or_rdf", "END"]]:
   evaluation_result = llm_instance.with_structured_output(QueryEvaluation).invoke(state["messages"])
   
   goto = "tables_or_rdf" if evaluation_result.is_valid else "END"
   return Command(update={"query_evaluation": evaluation_result}, goto=goto)

def tables_or_rdf(state, llm_instance, list_tables_tool, brick_explore_tool) -> Command[Literal["list_tables_tool", "brick_explore_tool", "END"]]:
   llm_with_tools = llm_instance.bind_tools([list_tables_tool, brick_explore_tool])
   response = llm_with_tools.invoke(state["messages"])
   
   goto = "END"
   if hasattr(response, 'tool_calls') and response.tool_calls:
       tool_name = response.tool_calls[0].get("name")
       if tool_name == "brick_explore_tool":
           goto = "brick_explore_tool"
       elif tool_name in ["list_tables_tool", "sql_db_list_tables"]:
           goto = "list_tables_tool"
   
   return Command(update={"messages": [response]}, goto=goto)

def generate_query(state, llm_instance, run_query_tool, brick_explore_tool) -> Command[Literal["check_query","brick_explore_tool", "END"]]:
   llm_with_tools = llm_instance.bind_tools([run_query_tool, brick_explore_tool])
   response = llm_with_tools.invoke(state["messages"])

   goto = "END"
   if hasattr(response, 'tool_calls') and response.tool_calls:
       tool_call = response.tool_calls[0]
       if tool_call.get("name") == "sql_db_query":
           goto = "check_query"
       elif tool_call.get("name") == "brick_explore_tool":
           goto = "brick_explore_tool"

   return Command(update={"messages": [response]}, goto=goto)

class MyGraph:
   def build_graph(self):
       workflow = StateGraph(MessagesState)
       workflow.add_node("evaluate_user_query", self.evaluate_user_query)
       workflow.add_node("tables_or_rdf", self.tables_or_rdf)
       workflow.add_node("generate_query", self.generate_query)
       workflow.add_node("list_tables_tool", list_tables_node)
       workflow.add_node("brick_explore_tool", brick_explore_node)
       workflow.add_node("check_query", self.check_query)
       
       workflow.add_edge(START, "evaluate_user_query")
       workflow.add_edge("list_tables_tool", "generate_query")
       workflow.add_edge("check_query", "run_query")
       
       return workflow.compile()
@luhodaan commented on GitHub (Jul 30, 2025): Hi, I'm experiencing the same issue described in this thread, but with LangGraph 0.3.1. The edges are still not being rendered when using Command within class methods. Environment: LangGraph version: 0.3.1 Python version: 3.11.6 OS: Windows 11 Real-world impact: I have a multi-step agent with conditional routing based on LLM tool calls and structured outputs. The graph works perfectly but all Command-inferred edges are invisible, making it impossible to understand the flow in LangGraph Studio. **Could we please reopen this issue?** I attach a simplified example of my graph and what I mean: ``` from langgraph.types import Command from typing import Literal def evaluate_user_query(state, llm_instance) -> Command[Literal["tables_or_rdf", "END"]]: evaluation_result = llm_instance.with_structured_output(QueryEvaluation).invoke(state["messages"]) goto = "tables_or_rdf" if evaluation_result.is_valid else "END" return Command(update={"query_evaluation": evaluation_result}, goto=goto) def tables_or_rdf(state, llm_instance, list_tables_tool, brick_explore_tool) -> Command[Literal["list_tables_tool", "brick_explore_tool", "END"]]: llm_with_tools = llm_instance.bind_tools([list_tables_tool, brick_explore_tool]) response = llm_with_tools.invoke(state["messages"]) goto = "END" if hasattr(response, 'tool_calls') and response.tool_calls: tool_name = response.tool_calls[0].get("name") if tool_name == "brick_explore_tool": goto = "brick_explore_tool" elif tool_name in ["list_tables_tool", "sql_db_list_tables"]: goto = "list_tables_tool" return Command(update={"messages": [response]}, goto=goto) def generate_query(state, llm_instance, run_query_tool, brick_explore_tool) -> Command[Literal["check_query","brick_explore_tool", "END"]]: llm_with_tools = llm_instance.bind_tools([run_query_tool, brick_explore_tool]) response = llm_with_tools.invoke(state["messages"]) goto = "END" if hasattr(response, 'tool_calls') and response.tool_calls: tool_call = response.tool_calls[0] if tool_call.get("name") == "sql_db_query": goto = "check_query" elif tool_call.get("name") == "brick_explore_tool": goto = "brick_explore_tool" return Command(update={"messages": [response]}, goto=goto) class MyGraph: def build_graph(self): workflow = StateGraph(MessagesState) workflow.add_node("evaluate_user_query", self.evaluate_user_query) workflow.add_node("tables_or_rdf", self.tables_or_rdf) workflow.add_node("generate_query", self.generate_query) workflow.add_node("list_tables_tool", list_tables_node) workflow.add_node("brick_explore_tool", brick_explore_node) workflow.add_node("check_query", self.check_query) workflow.add_edge(START, "evaluate_user_query") workflow.add_edge("list_tables_tool", "generate_query") workflow.add_edge("check_query", "run_query") return workflow.compile() ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#391
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?