{"version":"2.1.321","anchor":"auto-mode-classifier-new-turn-ended-block-message-and-hook","canonical_anchor":"auto-mode-classifier-new-turn-ended-block-message-and-hook","heading":"Auto mode can block a call because the turn ended, with new wording","tier":"notice","area":"Auto Mode","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.321\/e\/auto-mode-classifier-new-turn-ended-block-message-and-hook","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.321","markdown":"### Auto mode can block a call because the turn ended, with new wording\n\nAuto mode has a new block reason for when the turn has ended, an extra check before allowing a call, and no longer blames a hook\n\n**Unclear.** What makes auto mode use the new turn-ended block, and what its extra check looks at, is not stated.\n\n**What**\n\nAuto mode is a permission mode in which Claude Code reviews each action itself instead of asking you. A tool call is a single action, such as running a command. Changes to how auto mode decides:\n\n- It can now block a call with a \"turn ended\" reason, which has its own message.\n\n- It runs an extra check before allowing a call.\n\n- When it cannot reach a verdict, the message now says another call in the response \"was changed after auto mode reviewed it\". It used to say the call was changed \"by a hook\", an automated script you can set to run around Claude's actions.\n\n**Why**\n\nYou may see different wording when auto mode blocks an action. The message no longer points at hooks as the cause.\n\n- Area: Auto Mode\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}