Vercel AI Chatbot

What it does

This example demonstrates the @grantex/vercel-ai integration by building scope-enforced tools with the Vercel AI SDK:

Register an agent and obtain a grant token via the sandbox flow
Create scoped tools using createGrantexTool with Zod schemas for typed parameters (calendar:read, email:send)
Wrap tools with withAuditLogging to automatically log every execution to the Grantex audit trail
Invoke tools via generateText (if OPENAI_API_KEY is set) or directly
Demonstrate GrantexScopeError — attempting to create a tool with storage:delete (a scope not in the grant) throws a GrantexScopeError with requiredScope and grantedScopes properties
Inspect the audit trail to see the logged actions

Start the local Grantex stack from the repository root:

docker compose up --build

In a separate terminal, run the example:

cd examples/vercel-ai-chatbot
npm install
npm start

To use a real LLM with generateText instead of direct tool invocation, set OPENAI_API_KEY:

OPENAI_API_KEY=sk-... npm start

Without OPENAI_API_KEY (direct invocation):

Agent registered: ag_01HXYZ...
Grant token received, grantId: grnt_01HXYZ...
Tools created: read_calendar, send_email
Audit logging attached

--- Invoking tools directly (no OPENAI_API_KEY set) ---
Calendar result: {"date":"today","events":[{"title":"Team standup","time":"9:00 AM"},{"title":"Design review","time":"2:00 PM"}]}
Email result: {"sent":true,"to":"alice@example.com","subject":"Today's events","bodyLength":49}

--- Testing scope enforcement ---
GrantexScopeError caught:
  Required scope:  storage:delete
  Granted scopes:  calendar:read, email:send

--- Audit trail ---
  [success] read_calendar — 2026-02-28T12:00:00.000Z
  [success] send_email — 2026-02-28T12:00:01.000Z

Done! Vercel AI integration demo complete.

Variable	Default	Description
`GRANTEX_URL`	`http://localhost:3001`	Base URL of the Grantex auth service
`GRANTEX_API_KEY`	`sandbox-api-key-local`	API key. Use a sandbox key for auto-approval
`OPENAI_API_KEY`	(none)	Optional. Set to use `generateText` with a real LLM