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

[PR #255] [CLOSED] Implement Enum-Based Declarations for Graph Nodes #1335

New Issue
Closed
opened 2026-02-20 17:44:29 -05:00 by yindo · 0 comments
yindo commented 2026-02-20 17:44:29 -05:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/langgraph/pull/255
Author: @Undertone0809
Created: 4/1/2024
Status: ❌ Closed

Base: main ← Head: zeeland/add-graph-node-enum-support

📝 Commits (2)

  • 0b73086 Add graph add_node enum type support
  • 755a24a Merge branch 'main' into zeeland/add-graph-node-enum-support

📊 Changes

3 files changed (+49 additions, -18 deletions)

View changed files

📝 examples/plan-and-execute/plan-and-execute.ipynb (+16 -10)
📝 langgraph/graph/graph.py (+25 -6)
📝 langgraph/graph/state.py (+8 -2)

📄 Description

Summary

  • Replaced string-based node definitions with enums in plan-and-execute.ipynb for better readability and fewer errors.
  • Updated graph.py and state.py to accept enums in graph operations, enhancing code maintainability.
  • Added conversion logic for enum to string in affected methods, ensuring backward compatibility.

Original:

from langgraph.graph import StateGraph, END

workflow = StateGraph(PlanExecute)

# Add the plan node
workflow.add_node("planner", plan_step)

# Add the execution step
workflow.add_node("agent", execute_step)

# Add a replan node
workflow.add_node("replan", replan_step)

workflow.set_entry_point("planner")

# From plan we go to agent
workflow.add_edge("planner", "agent")

# From agent, we replan
workflow.add_edge("agent", "replan")

workflow.add_conditional_edges(
    "replan",
    # Next, we pass in the function that will determine which node is called next.
    should_end,
    {
        # If `tools`, then we call the tool node.
        True: END,
        False: "agent",
    },
)

# Finally, we compile it!
# This compiles it into a LangChain Runnable,
# meaning you can use it as you would any other runnable
app = workflow.compile()

After:

from langgraph.graph import StateGraph, END
from enum import Enum

class NodeType(Enum):
    PLAN = "planner"
    EXECUTE = "agent"
    REPLAN = "replan"

workflow = StateGraph(PlanExecute)

# Add the plan node
workflow.add_node(NodeType.PLAN, plan_step)

# Add the execution step
workflow.add_node(NodeType.EXECUTE, execute_step)

# Add a replan node
workflow.add_node(NodeType.REPLAN, replan_step)

workflow.set_entry_point(NodeType.PLAN)

# From plan we go to agent
workflow.add_edge(NodeType.PLAN, NodeType.EXECUTE)

# From agent, we replan
workflow.add_edge(NodeType.EXECUTE, NodeType.REPLAN)

workflow.add_conditional_edges(
    NodeType.REPLAN,
    # Next, we pass in the function that will determine which node is called next.
    should_end,
    {
        # If `tools`, then we call the tool node.
        True: END,
        False: NodeType.EXECUTE,
    },
)

# Finally, we compile it!
# This compiles it into a LangChain Runnable,
# meaning you can use it as you would any other runnable
app = workflow.compile()

Reason for changes:

Adopting enum-based node declarations enhances code clarity and standardizes data types, reducing the likelihood of errors due to misspelled strings. This approach streamlines development and maintenance processes by providing a more structured and error-resistant method for defining nodes within the codebase.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/langgraph/pull/255 **Author:** [@Undertone0809](https://github.com/Undertone0809) **Created:** 4/1/2024 **Status:** ❌ Closed **Base:** `main` ← **Head:** `zeeland/add-graph-node-enum-support` --- ### 📝 Commits (2) - [`0b73086`](https://github.com/langchain-ai/langgraph/commit/0b73086a60d220be1ac01b070bec2bb8ed0d22f1) Add graph add_node enum type support - [`755a24a`](https://github.com/langchain-ai/langgraph/commit/755a24a9d958b9b81856a547cc490f43e8b51b84) Merge branch 'main' into zeeland/add-graph-node-enum-support ### 📊 Changes **3 files changed** (+49 additions, -18 deletions) <details> <summary>View changed files</summary> 📝 `examples/plan-and-execute/plan-and-execute.ipynb` (+16 -10) 📝 `langgraph/graph/graph.py` (+25 -6) 📝 `langgraph/graph/state.py` (+8 -2) </details> ### 📄 Description ## Summary - Replaced string-based node definitions with enums in plan-and-execute.ipynb for better readability and fewer errors. - Updated graph.py and state.py to accept enums in graph operations, enhancing code maintainability. - Added conversion logic for enum to string in affected methods, ensuring backward compatibility. Original: ```python from langgraph.graph import StateGraph, END workflow = StateGraph(PlanExecute) # Add the plan node workflow.add_node("planner", plan_step) # Add the execution step workflow.add_node("agent", execute_step) # Add a replan node workflow.add_node("replan", replan_step) workflow.set_entry_point("planner") # From plan we go to agent workflow.add_edge("planner", "agent") # From agent, we replan workflow.add_edge("agent", "replan") workflow.add_conditional_edges( "replan", # Next, we pass in the function that will determine which node is called next. should_end, { # If `tools`, then we call the tool node. True: END, False: "agent", }, ) # Finally, we compile it! # This compiles it into a LangChain Runnable, # meaning you can use it as you would any other runnable app = workflow.compile() ``` After: ```python from langgraph.graph import StateGraph, END from enum import Enum class NodeType(Enum): PLAN = "planner" EXECUTE = "agent" REPLAN = "replan" workflow = StateGraph(PlanExecute) # Add the plan node workflow.add_node(NodeType.PLAN, plan_step) # Add the execution step workflow.add_node(NodeType.EXECUTE, execute_step) # Add a replan node workflow.add_node(NodeType.REPLAN, replan_step) workflow.set_entry_point(NodeType.PLAN) # From plan we go to agent workflow.add_edge(NodeType.PLAN, NodeType.EXECUTE) # From agent, we replan workflow.add_edge(NodeType.EXECUTE, NodeType.REPLAN) workflow.add_conditional_edges( NodeType.REPLAN, # Next, we pass in the function that will determine which node is called next. should_end, { # If `tools`, then we call the tool node. True: END, False: NodeType.EXECUTE, }, ) # Finally, we compile it! # This compiles it into a LangChain Runnable, # meaning you can use it as you would any other runnable app = workflow.compile() ``` ## Reason for changes: Adopting enum-based node declarations enhances code clarity and standardizes data types, reducing the likelihood of errors due to misspelled strings. This approach streamlines development and maintenance processes by providing a more structured and error-resistant method for defining nodes within the codebase. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-20 17:44:29 -05:00
yindo closed this issue 2026-02-20 17:44:29 -05:00
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 pull-request
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#1335
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?