{"version":"2.1.280","anchor":"new-refusal-guidance-text-for-irrecoverable-artifact-read-er","canonical_anchor":"new-refusal-guidance-text-for-irrecoverable-artifact-read-er","heading":"New refusal-guidance text for irrecoverable artifact read errors","tier":"notice","area":"Artifacts","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/new-refusal-guidance-text-for-irrecoverable-artifact-read-er","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### New refusal-guidance text for irrecoverable artifact read errors\n\nClaude Code now tells the model not to retry an artifact read when the failure is unrecoverable\n\n**What**\n\nWhen an artifact (a file-like object Claude Code can read) fails to load with one of several specific error codes \u2014 the agent wasn't added, the agent doesn't own it, access needs to be requested, or the artifact is gone \u2014 Claude Code now shows a fixed instruction telling the model not to retry the read, and instead to tell the user the artifact couldn't be read and continue without it.\n\n**Why**\n\nThis stops Claude from repeatedly retrying a read that can never succeed, and ensures the user is informed promptly instead of the model silently looping.\n\n- Area: Artifacts\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5"}