Follow Discord
Sweep 12 Nov 2026 · 20:38Z Build v2.1.323 540 read Stable v2.1.311 Latest v2.1.322 Next v2.1.323 Feeds RSS JSON llms.txt llms-full.txt Unofficial
The last run did not finish v2.1.323 no changelog was produced for this release

Claude Code v2.1.281 ·

Advisor standby fallback now requires the org to be entitled to the model

The standby advisor model is now used only if your organisation is known to serve that model

You'll notice Improvements
JSON All of v2.1.281
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
AdvisorArea: what it touches
ImprovementsKind: in v2.1.281,
ImprovementsSection of the release
What

The advisor is a second model Claude Code can consult, and a standby advisor model is used when the main choice is unavailable. Claude Code now checks the first matching standby model against the models your organisation has access to. This check applies only when you connect directly to Anthropic.

If your organisation is not known to serve that model, no standby is used. Claude Code writes a line to its debug log (a detailed record for troubleshooting) instead of falling back to that model.

Why

This stops Claude Code from falling back to an advisor model your organisation cannot use.

See this entry in the whole of v2.1.281 →

Feedback