RepoJournal
Vercel

@vercel

Next.js + the Vercel platform — frontend infrastructure for the web

Pick a date

  1. Tue 5 may
  2. Wed 6 may
  3. Thu 7 may
  4. Fri 8 may
  5. Sat 9 may
  6. Sun 10 may
  7. Mon 11 may
  8. Tue 12 may
  9. Wed 13 may
  10. Thu 14 may
  11. Fri 15 may
  12. Sat 16 may
  13. Sun 17 may
  14. Mon 18 may
  15. Tue 19 may
  16. Wed 20 may
  17. Thu 21 may
  18. Sat 23 may
  19. Sun 24 may
  20. Mon 25 may
  21. Tue 26 may
  22. Wed 27 may
  23. Thu 28 may
  24. Fri 29 may
  25. Sat 30 may
  26. Sun 31 may
  27. Mon 1 jun
  28. Mon 8 jun
  29. Tue 9 jun
  30. Today 10 jun

The Wire · Showcase

VERCEL AI FIXES XAI PROVIDER BUGS BREAKING MULTI-STEP TOOL CALLING

By RepoJournal · Filed · About Vercel

Grok reasoning models are failing 4-12% of the time on continuation steps, and Vercel AI just shipped two fixes that surface the actual errors and stop duplicate reasoning events from tanking requests.

The XAI provider in Vercel AI was silently breaking multi-step tool calls with grok-4.3 and grok-4.20-reasoning [1]. Every reasoning summary part event fired a new reasoning-start marker, which meant when XAI split a reasoning block across multiple parts, Vercel AI sent duplicate markers that violated XAI's API contract. That's been fixed [2]. In parallel, error reporting was completely broken [3]. XAI 4xx failures surfaced as generic "Bad Request" messages while the real error detail lived buried in responseBody, making debugging impossible [4]. Now errors properly parse XAI's actual response schema and bubble up the real message. On the Turborepo side, v2.9.15-canary.3 hit a doc aliasing snag but shipped critical cache fixes [5], while the standalone Vercel CLI fixed its own update check routing [6]. The AI package is holding in pre-release mode and waiting on the next changeset merge [7].

Action items

References

  1. [1] fix(provider/xai): dedupe reasoning-start on multi-summary-part responses to prevent xai 400s on continuations ↗ vercel/ai
  2. [2] fix(provider/xai): dedupe reasoning-start on multi-summary-part responses to prevent xai 400s on continuations (#15334) vercel/ai
  3. [3] fix(provider/xai): surface full xai error detail in APICallError.message ↗ vercel/ai
  4. [4] fix(provider/xai): surface full xai error detail in APICallError.message (#15338) vercel/ai
  5. [5] release(turborepo): 2.9.15-canary.3 ↗ vercel/turborepo
  6. [6] [FIX] Fixing a single deployment error ↗ vercel/vercel
  7. [7] Version Packages (canary) ↗ vercel/ai

FAQ

What changed in Vercel on May 17, 2026?
Grok reasoning models are failing 4-12% of the time on continuation steps, and Vercel AI just shipped two fixes that surface the actual errors and stop duplicate reasoning events from tanking requests.
What should Vercel teams do about it?
Upgrade @vercel/ai if using XAI providers with reasoning models before next deploy • Update standalone Vercel CLI to fix self-update checks • Monitor Turborepo canary for stable 2.9.15 release
Which Vercel repositories shipped on May 17, 2026?
vercel/ai, vercel/turborepo, vercel/vercel

Related across the cluster

For your repos

The showcase is a teaser.
Your wire is the product.

Same engine. Different stack. Below: what changes when the wire is yours.

Showcase wire

  • •14 famous open source orgs
  • •One wire per day
  • •Public, generic
  • •Read on the web, when you remember

Your wire

  • →Up to 1,500 of your repos - orgs, deps, vendors
  • →Morning and evening briefs
  • →Action items routed to your team
  • →Slack delivery, email, breaking-news CVE alerts

Want a hands-on demo first? Ask a current user for an invite link.