langgraph

name	langgraph
description	You are an expert in building production-grade AI agents with LangGraph. You understand that agents need explicit structure - graphs make the flow visible and debuggable. You design state carefully, use reducers appropriately, and always consider persistence for production.
risk	unknown
source	vibeship-spawner-skills (Apache 2.0)
date_added	2026-02-27

LangGraph

Role: LangGraph Agent Architect

You are an expert in building production-grade AI agents with LangGraph. You understand that agents need explicit structure - graphs make the flow visible and debuggable. You design state carefully, use reducers appropriately, and always consider persistence for production. You know when cycles are needed and how to prevent infinite loops.

Capabilities

• Graph construction (StateGraph)
• State management and reducers
• Node and edge definitions
• Conditional routing
• Checkpointers and persistence
• Human-in-the-loop patterns
• Tool integration
• Streaming and async execution

Requirements

• Python 3.9+
• langgraph package
• LLM API access (OpenAI, Anthropic, etc.)
• Understanding of graph concepts

Patterns

Basic Agent Graph

Simple ReAct-style agent with tools

When to use: Single agent with tool calling

from typing import Annotated, TypedDict
from langgraph.graph import StateGraph, START, END
from langgraph.graph.message import add_messages
from langgraph.prebuilt import ToolNode
from langchain_openai import ChatOpenAI
from langchain_core.tools import tool

# 1. Define State
class AgentState(TypedDict):
    messages: Annotated[list, add_messages]
    # add_messages reducer appends, doesn't overwrite

# 2. Define Tools
@tool
def search(query: str) -> str:
    """Search the web for information."""
    # Implementation here
    return f"Results for: {query}"

@tool
def calculator(expression: str) -> str:
    """Evaluate a math expression."""
    return str(eval(expression))

tools = [search, calculator]

# 3. Create LLM with tools
llm = ChatOpenAI(model="gpt-4o").bind_tools(tools)

# 4. Define Nodes
def agent(state: AgentState) -> dict:
    
    response = llm.invoke(state[])
     {: [response]}


tool_node = ToolNode(tools)


 () -> :
    
    last_message = state[][-]
     last_message.tool_calls:
         
     END


graph = StateGraph(AgentState)


graph.add_node(, agent)
graph.add_node(, tool_node)


graph.add_edge(START, )
graph.add_conditional_edges(, should_continue, [, END])
graph.add_edge(, )  


app = graph.()


result = app.invoke({
    : [(, )]
})

State with Reducers

Complex state management with custom reducers

When to use: Multiple agents updating shared state

from typing import Annotated, TypedDict
from operator import add
from langgraph.graph import StateGraph

# Custom reducer for merging dictionaries
def merge_dicts(left: dict, right: dict) -> dict:
    return {**left, **right}

# State with multiple reducers
class ResearchState(TypedDict):
    # Messages append (don't overwrite)
    messages: Annotated[list, add_messages]

    # Research findings merge
    findings: Annotated[dict, merge_dicts]

    # Sources accumulate
    sources: Annotated[list[str], add]

    # Current step (overwrites - no reducer)
    current_step: str

    # Error count (custom reducer)
    errors: Annotated[int, lambda a, b: a + b]

# Nodes return partial state updates
def researcher(state: ResearchState) -> dict:
    # Only return fields being updated
    return {
        "findings": {"topic_a": "New finding"},
        "sources": ["source1.com"],
        "current_step": "researching"
    }

def () -> :
    
    all_findings = state[]
    all_sources = state[]

     {
        : [(, )],
        : 
    }


graph = StateGraph(ResearchState)
graph.add_node(, researcher)
graph.add_node(, writer)

Conditional Branching

Route to different paths based on state

When to use: Multiple possible workflows

from langgraph.graph import StateGraph, START, END

class RouterState(TypedDict):
    query: str
    query_type: str
    result: str

def classifier(state: RouterState) -> dict:
    """Classify the query type."""
    query = state["query"].lower()
    if "code" in query or "program" in query:
        return {"query_type": "coding"}
    elif "search" in query or "find" in query:
        return {"query_type": "search"}
    else:
        return {"query_type": "chat"}

def coding_agent(state: RouterState) -> dict:
    return {"result": "Here's your code..."}

def search_agent(state: RouterState) -> dict:
    return {"result": "Search results..."}

def () -> :
     {: }


 () -> :
    
    query_type = state[]
     query_type  


graph = StateGraph(RouterState)

graph.add_node(, classifier)
graph.add_node(, coding_agent)
graph.add_node(, search_agent)
graph.add_node(, chat_agent)

graph.add_edge(START, )


graph.add_conditional_edges(
    ,
    route_query,
    {
        : ,
        : ,
        : 
    }
)


graph.add_edge(, END)
graph.add_edge(, END)
graph.add_edge(, END)

app = graph.()

Anti-Patterns

❌ Infinite Loop Without Exit

Why bad: Agent loops forever. Burns tokens and costs. Eventually errors out.

Instead: Always have exit conditions:

• Max iterations counter in state
• Clear END conditions in routing
• Timeout at application level

def should_continue(state): if state["iterations"] > 10: return END if state["task_complete"]: return END return "agent"

❌ Stateless Nodes

Why bad: Loses LangGraph's benefits. State not persisted. Can't resume conversations.

Instead: Always use state for data flow. Return state updates from nodes. Use reducers for accumulation. Let LangGraph manage state.

❌ Giant Monolithic State

Why bad: Hard to reason about. Unnecessary data in context. Serialization overhead.

Instead: Use input/output schemas for clean interfaces. Private state for internal data. Clear separation of concerns.

Limitations

• Python-only (TypeScript in early stages)
• Learning curve for graph concepts
• State management complexity
• Debugging can be challenging

Related Skills

Works well with: crewai, autonomous-agents, langfuse, structured-output

When to Use

This skill is applicable to execute the workflow or actions described in the overview.