Follow Discord
Sweep 06 Nov 2026 · 01:32Z Build v2.1.319 537 read Stable v2.1.311 Latest v2.1.318 Next v2.1.319 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.274 ·

Artifacts can route documents to a Claude Docs connector, with auto_open adjusted accordingly

Artifacts now hand document creation off to a connected Claude Docs connector when available, and auto_open guidance was updated to match

Group of 4 You'll notice Improvements
JSON All of v2.1.274
You'll noticeTier: how much it should matter to you
4Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
ArtifactsArea: what it touches
ImprovementsKind: in v2.1.274,
What probably matters to youSection of the release

What

  • When a first-party connector for reading and writing documents (Claude Docs) is attached, the artifacts flow now routes document creation to that connector or its skill instead of creating an Artifact, falling back to the normal quickstart flow otherwise.
  • A validation rule that used to block the auto_open: "after_first_write" option under a certain tool-availability condition has been removed from artifact publishing.
  • The instructions Claude sees when starting a new Artifact now explicitly say auto_open: "after_first_write" should never be used for a type whose content is written through a connector, such as a Claude Docs document.
  • The description of the auto_open parameter on the artifact-creation tool was simplified, dropping an extra sentence that used to appear only when a certain feature flag was on.

Why This avoids opening an artifact automatically for content that is actually being created through a connector like Claude Docs, keeping the auto-open behavior consistent with where the content is really going.

See this entry in the whole of v2.1.274 →

Feedback