Follow Discord
Sweep 01 Oct 2026 · 17:27Z Build v2.1.287 508 read Stable v2.1.285 Latest v2.1.287 Next v2.1.287 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.286 ·

Artifact comment writes get their own permission path

Artifact comments get a separate commentWrite permission, allowed in turns not started by a human, and unasked writes are now tracked

Group of 2 You'll notice Improvements
JSON All of v2.1.286
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
ArtifactsArea: what it touches
ImprovementsKind: in v2.1.286,
ImprovementsSection of the release

What

Artifacts are documents Claude can create and share, and they can have comments. Writing a comment now has its own permission flag, commentWrite, instead of relying only on routineWrite.

  • The permission check for artifact writes now passes commentWrite and records approval for comment writes separately from routine writes.
  • When a turn was not started by a human, commentWrite set to true is let through by the same branch that already allowed routineWrite.
  • Two new telemetry events, usage data sent back to Anthropic, fire when a comment is written or published without being asked for.
  • Separately, the options used for model requests gain accessFallbackModel.

Why

Comments on artifacts can now be written in turns that no person started, such as automated runs. Comments written without being asked for are now counted.

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtWhat turns this permission on, and which feature it belongs to, is not known.

See this entry in the whole of v2.1.286 →

Feedback