{"version":"2.1.265","anchor":"self-edit-consent-for-artifact-live-replies-now-tracks-expli","canonical_anchor":"self-edit-consent-for-artifact-live-replies-now-tracks-expli","heading":"Self-edit consent for artifact live replies now tracks explicit allow, not just decline","tier":"internal","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265\/e\/self-edit-consent-for-artifact-live-replies-now-tracks-expli","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265","markdown":"### Self-edit consent for artifact live replies now tracks explicit allow, not just decline\n\nConsent tracking for live artifact replies now distinguishes an explicit allow from a decline\n\n**What**\n\nWhen a live artifact session (a shared, interactive Claude Code output) asks for consent to send replies, Claude Code now records an `allowed: true` flag on the pending consent entry when you explicitly grant it. An entry is only moved to `declined` if it wasn't already marked as allowed.\n\n**Why**\n\nThis prevents an explicit \"allow\" from later being incorrectly overwritten or reported as a decline, making consent state for artifact replies more reliable.\n\n- Area: Artifacts\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}