RepoJournal
Vercel

@vercel

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

Keep up with Vercel in about 3 minutes a day: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

One email a day. Unsubscribe in one click.

Pick a date

Topics: JavaScript Full archive →

The Wire · Showcase

PHOTON SETUP FIXED, AI SDK PATCHES REASONING TOKEN EDGE CASE

By RepoJournal · Filed · About Vercel

Eve's Photon integration now correctly detects dedicated projects and skips redundant registration, while the AI SDK patches a token-counting bug hitting reasoning models on Baseten.

Photon setup in Eve [1] now inspects for existing dedicated projects before registering operators, displaying the least-loaded line for dedicated projects and keeping the existing flow for shared users. This lands alongside Kybernesis Arcana's addition to Eve's official extension gallery [2], which brings memory and workspace isolation to managed workspaces via `eve add extension/arcana`. The test suite hardened against scenario observation races [3]. Across the AI SDK, the openai-compatible provider [6] patches a critical token-counting bug: when reasoning models report `completion_tokens_details.reasoning_tokens` greater than `completion_tokens` (observed with Baseten serving reasoning workloads that hit the length stop mid-reasoning), the text token share is now clamped to 0 rather than going negative. The fix rolls forward into Vercel [4], Together AI [5], Moonshot AI [7], and Hugging Face [8] adapters. On the chat desk, Google Chat attachment downloads now send `alt=media` to the media endpoint [9], fixing a bug where the adapter returned metadata instead of file bytes and failed with a bare 400. Workflow adds opt-in WebSocket transport for event writes [10], defaulting to HTTP and gated behind `WORKFLOW_EVENTS_TRANSPORT=ws` until confidence builds.

One email a day. Unsubscribe in one click.

Action items

References

  1. [1] fix(setup): show dedicated Photon numbers ↗ vercel/eve
  2. [2] feat(docs): add Kybernesis Arcana memory extension ↗ vercel/eve
  3. [3] test(eve): remove scenario observation races (#1878) vercel/eve
  4. [4] @ai-sdk/vercel@3.0.28 ↗ vercel/ai
  5. [5] @ai-sdk/togetherai@3.0.29 ↗ vercel/ai
  6. [6] @ai-sdk/openai-compatible@3.0.28 ↗ vercel/ai
  7. [7] @ai-sdk/moonshotai@3.0.31 ↗ vercel/ai
  8. [8] @ai-sdk/huggingface@2.0.28 ↗ vercel/ai
  9. [9] fix(gchat): send alt=media when downloading attachments by resourceName ↗ vercel/chat
  10. [10] Add WebSocket transport for step-execution event writes (opt-in) ↗ vercel/workflow

Quick answers

What shipped in Vercel on August 10, 2026?
Eve's Photon integration now correctly detects dedicated projects and skips redundant registration, while the AI SDK patches a token-counting bug hitting reasoning models on Baseten. In total, 7 commits, 8 pull requests, and 10 releases landed.
Who contributed to Vercel on August 10, 2026?
6 developers shipped this update, including OwenKephart, cmpadden, Chad Hietala, github-actions[bot], codybuell, and shalabhc.
What were the notable Vercel updates?
fix(setup): show dedicated Photon numbers, feat(docs): add Kybernesis Arcana memory extension, and test(eve): remove scenario observation races (#1878).

More from @vercel

Daily updates, in your inbox

Follow Vercel

Keep up with Vercel in about 3 minutes a day: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

or

One email a day. Unsubscribe in one click. Read a past issue →

Elsewhere on the wire

Want every project, not just this one?