Vercel shipped [email protected] on 2026-09-30 (compare): optional SSE heartbeats keep idle UI message streams open; prune all tool content when retaining zero trailing messages; ignore pending tool approvals superseded by user messages; preserve partial reasoning tags at streamed text ends. Build migrates tsup→tsdown with gateway/provider/utils bumps.

Key Takeaways

Vercel AI SDK ai@7.0.123: idle SSE heartbeats; prune tool content when retaining zero messages; user messages supersede pending tool approvals
🖼️Official Media
Click to view high-res
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

🔬

In-Depth Technical Analysis

Background

Agent/chat UIs lose idle SSE behind proxies, leave tool content when retain=0, and stall when user messages supersede pending tool approvals. [email protected] targets those runtime edges.

What shipped

[[email protected]](https://github.com/vercel/ai/releases/tag/[email protected]): optional SSE heartbeats; prune tool content at retain=0; ignore superseded approvals; preserve partial reasoning tags; tsup→tsdown + gateway/provider/utils bumps. Compare.

Benchmarks

No official SWE-bench numbers. Anchors: publish 2026-09-30T02:21:24Z, npm [email protected]. Measure your own idle-stream and approval regressions.

Get started

npm i [email protected]. Docs: https://ai-sdk.dev/docs/introduction

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

Up NextVercel AI SDK: `@ai-sdk/openai` 3.0.121 / 2.0.132 add native GPT-6.1 Sol support
Read Now→