{"version":"2.1.224","anchor":"feedback-tool-now-covers-claude-s-own-behaviour-not-just-pro","canonical_anchor":"feedback-tool-now-covers-claude-s-own-behaviour-not-just-pro","heading":"Feedback tool now covers Claude's own behaviour, not just product bugs","tier":"notice","area":"Feedback","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.224\/e\/feedback-tool-now-covers-claude-s-own-behaviour-not-just-pro","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.224","markdown":"### Feedback tool now covers Claude's own behaviour, not just product bugs\n\nClaude will now offer to draft feedback when it itself goes wrong in your session.\n\n**What**\n\nThe built-in feedback drafting tool used to be scoped to Claude Code the product. It now explicitly handles model-behaviour reports too, and will offer to draft one when Claude itself goes wrong in the session: retracting a confident answer, stopping short of the task, declining something reasonable, spawning too many subagents, tone problems, over-questioning, or scope creep.\n\n**Details**\n\n- Report fields are unchanged: type, title, details, area, failure_mode, task_category.\n\n**Evidence**\n\n`draft product or model-behavior feedback report queue`\n\n- Area: Feedback\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 3\/5"}