{"version":"2.1.271","anchor":"artifact-comment-auto-reply-is-now-grounded-in-the-artifact","canonical_anchor":"artifact-comment-auto-reply-is-now-grounded-in-the-artifact","heading":"Artifact comment auto-reply is now grounded in the artifact's live page source","tier":"notice","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.271\/e\/artifact-comment-auto-reply-is-now-grounded-in-the-artifact","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.271","markdown":"### Artifact comment auto-reply is now grounded in the artifact's live page source\n\nAuto-replies to artifact comments now read the artifact's actual page content first\n\n**What**\n\nWhen Claude Code composes an automatic reply to a comment thread on an artifact (a generated piece of content like a webpage), it now fetches the current HTML of that artifact's page and includes it, truncated and marked as untrusted, in the prompt it uses to write the reply. A new check now catches and discards replies that simply echo that fenced content back instead of actually responding to it. Prompt caching is also conditionally enabled for this reply path.\n\n**Why**\n\nThis grounds automatic replies in what the artifact page actually shows, rather than letting Claude guess, and prevents low-quality replies that just parrot the input back.\n\n- Area: Artifacts\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}