Chat SDK now supports Vercel Connect
The Chat SDK now integrates with Vercel Connect for secure credential management, eliminating the need to manually store or rotate tokens. New adapter helpers for Slack, GitHub, and Linear use OIDC token validation and short-lived tokens for both inbound and outbound bot calls.
You can now use to manage credentials for your bots, with no tokens or signing secrets to store or rotate yourself.Vercel ConnectChat SDK
The new subpath provides adapter helpers for Slack, GitHub, and Linear. Each helper takes a connector UID and returns a config you spread into the matching adapter factory.@vercel/connect/chat
Outbound bot calls use a function-form token field backed by , so each API request gets a fresh, short-lived token that Vercel Connect rotates for you.getToken
Inbound use a that validates the OIDC token Connect attaches to forwarded events, eliminating the need for a .triggerswebhookVerifiersigningSecret
Read the to set up your first connector with Chat SDK or follow the to build your own Slackbot with Vercel Connect.documentationknowledge base guide
Source: original entry ↗
More from Vercel
Follow Vercel to get its new changes in your feed and email digest.
Skip sending request bodies to Routing Middleware
Vercel now allows you to skip sending client request bodies to Routing Middleware via the skipMiddlewareRequestBody configuration option, reducing middleware invocation costs and improving time to first byte for requests with large bodies.
Vercel Sandbox creation now returns ready sandbox
Vercel Sandbox instances are now ready to run commands and access files immediately upon creation completion. The Sandbox.create() method now waits for snapshot restoration to finish before resolving, eliminating delays on the first command or file operation.
Step 5 Preview now available on AI Gateway
StepFun's Step 5 Preview model is now available on Vercel's AI Gateway, supporting text and image input with a 1M-token context window optimized for agentic coding, professional knowledge work, and financial analysis. The model can be accessed via the unified AI Gateway API for tracking usage, cost management, and performance optimization.