Spend controls for LangGraph ToolNode calls

LangGraph executes tools through ToolNode. Paybond hooks that boundary with awrapToolCall — spend verify before side-effecting tools execute, then auto-evidence after success. Model inference stays on your provider client.

Adapter reference: /docs/kit/langgraph.

• awrapToolCall before ToolNode

  Harbor authorize runs before side-effecting tools execute in your StateGraph.

• Auto-evidence

  Hooks finalize spend and submit signed evidence after paid tool success.

• Policy budgets

  Versioned YAML caps per-call and intent spend for long-lived graphs.

• TypeScript and Python

  Same langgraph adapter on npm and pip (paybond-kit[langgraph]).

Why Paybond (not just LangGraph checks)?

LangGraph tool nodes and host approvals do not enforce a spend limit, a per-operation permission check (capability token), or a signed completion receipt tied to a spend agreement (intent).

How it works

3-minute quickstart

Smoke the langgraph adapter sandbox contract:

paybond login
paybond agent demo langgraph smoke \
  --operation paid-tool \
  --requested-spend-cents 100 \
  --evidence-preset cost_and_completion \
  --format table

paybond login
paybond agent demo langgraph smoke \
  --operation paid-tool \
  --requested-spend-cents 100 \
  --evidence-preset cost_and_completion \
  --format table

When the smoke succeeds you should see:

• ✓ Spend approved
• ✓ Tool completed
• ✓ Evidence verified (cost_and_completion)

What success looks like

Scaffold

paybond init agent-middleware --framework langgraph --out paybond-langgraph.ts
paybond policy init --preset travel --out paybond.policy.yaml

paybond init agent-middleware --framework langgraph --out paybond-langgraph.ts
paybond policy init --preset travel --out paybond.policy.yaml

Or the full wizard:

paybond init --solution travel --max-spend-usd 500 --framework langgraph --non-interactive

paybond init --solution travel --max-spend-usd 500 --framework langgraph --non-interactive

Wire middleware

import { Paybond } from "@paybond/kit";

const paybond = await Paybond.open({ apiKey: process.env.PAYBOND_API_KEY! });

const { awrapToolCall, createToolNode } = await paybond.agent({
  policy: "travel",
  framework: "langgraph",
  tools: [bookHotelTool, searchWebTool],
});

const node = createToolNode!([bookHotelTool, searchWebTool], { awrapToolCall });
// Add node to your StateGraph

import { Paybond } from "@paybond/kit";

const paybond = await Paybond.open({ apiKey: process.env.PAYBOND_API_KEY! });

const { awrapToolCall, createToolNode } = await paybond.agent({
  policy: "travel",
  framework: "langgraph",
  tools: [bookHotelTool, searchWebTool],
});

const node = createToolNode!([bookHotelTool, searchWebTool], { awrapToolCall });
// Add node to your StateGraph

Install extras: pip install "paybond-kit[langgraph]".

Manual hook wiring

When you already bound a PaybondAgentRun:

from langgraph.prebuilt import ToolNode
from paybond_kit.langgraph_hooks import paybond_awrap_tool_call

node = ToolNode(tools, awrap_tool_call=paybond_awrap_tool_call(run))

import { paybondAwrapToolCall, paybondToolNode } from "@paybond/kit/langgraph";

const node = paybondToolNode(tools, run);

Approval holds: when Paybond returns an approval hold, surface it to operators, approve in the tenant console, then retry with the same operation, amount, metadata, and approvalToken. Hard denials must not execute the tool.

Production checklist

Works with

Ready to test?

Related guides

• Agent middleware — run binding and policy hot-reload
• Agent policy-as-code — long-lived graphs with GitOps YAML
• Approve AWS spending with agents — aws preset and LangGraph

Developer reference: /docs/kit/langgraph.