Follow Discord
Sweep 10 Nov 2026 · 02:18Z Build v2.1.322 539 read Stable v2.1.311 Latest v2.1.322 Next v2.1.322 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.280 ·

Cloud code-review failure guidance now varies by reason

Failed cloud /code-review runs now show tailored guidance based on why they failed instead of one generic message

Group of 2 You'll notice Improvements
JSON All of v2.1.280
You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
Code ReviewArea: what it touches
ImprovementsKind: in v2.1.280,
ImprovementsSection of the release

What

  • The failure message shown when a cloud /code-review run fails no longer always tells the user to retry /code-review ultra or fall back to local review. It now branches on the specific failure reason, such as session_archived, stopped_remotely, or session_not_found, only recommending the ultra/local retry for a subset of causes.
  • Whether a poll that repeatedly gets 404s is treated as session_not_found versus just a timeout is now controlled by a remote-config flag, tengu_breezy_diffie.

Why

This gives clearer, more accurate next steps when a cloud code review fails, instead of always pointing to the same generic retry advice regardless of the actual cause.

Read from
Names in the bundle/code-review ultra
Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Added since A small documentation edit on Code Review touched a line naming /code-review ultra after this was published. Ultrareview requires authentication with a claude.ai account and is not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, or to organizations with Zero Data Retention enabled or with the [HIPAA configuration… code-review see the edit
Confirmed since Anthropic's documentation has since written up /code-review ultra, on Find bugs with ultrareview. `claude -p '/code-review ultra'` doesn't get you the findings, so use `claude ultrareview` in scripts. The `-p` run launches the cloud review and exits without waiting for it. When the review would bill usage credits, the `-p` run stops wi… ultrareview see the edit
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up /code-review ultra, on Find bugs with ultrareview.

See this entry in the whole of v2.1.280 →

Feedback