How to gate paid tool calls in LangGraph

1. Why this guide matters

LangGraph shines when you want explicit nodes, edges and state transitions. That makes it a great place to attach spend governance before a paid tool node fires.

This pattern adds a decision node that asks NORNR first and routes the graph based on the returned status.

2. Install what you need

pip install agentpay langgraph

This guide uses the hosted NORNR path at https://nornr.com, so you can validate the decision flow without standing up the full local stack first.

3. Create the governed wallet

from agentpay import Wallet

wallet = Wallet.create(
    owner="graph-agent",
    daily_limit=80,
    require_approval_above=30,
    base_url="https://nornr.com",
)

This wallet is the mandate. It sets the budget and review threshold before the framework-specific workflow is allowed to continue.

4. Apply it in the workflow

from typing import TypedDict
from langgraph.graph import StateGraph, END

class FlowState(TypedDict):
    question: str
    decision: dict | None

def check_budget(state: FlowState):
    decision = wallet.pay(
        amount=18.00,
        to="openai",
        purpose="paid tool call",
    )
    return {"decision": decision}

def route_after_budget(state: FlowState):
    status = (state.get("decision") or {}).get("status")
    return "paid_tool" if status == "approved" else "hold"

graph = StateGraph(FlowState)
graph.add_node("check_budget", check_budget)
graph.add_conditional_edges("check_budget", route_after_budget, {"paid_tool": "paid_tool", "hold": END})

The key pattern stays the same across frameworks: ask NORNR for a decision first, then let the expensive or externally billable step run only if policy says yes.

5. What to expect

• approved means the workflow can continue immediately inside its mandate.
• queued means the request crossed an approval threshold and should wait for review.
• rejected means policy did not allow the action to proceed.

That three-way split is what makes the pattern useful: low-risk work stays fast, higher-risk work becomes reviewable, and clearly out-of-policy work never leaves the workflow.

6. Where to go next

• Hosted quickstart
• Control room
• Guides library