{"version":"2.1.269","anchor":"new-structured-pauseretrystop-classification-for-autonomou","canonical_anchor":"new-structured-pauseretrystop-classification-for-autonomou","heading":"New structured pause\/retry\/stop classification for autonomous 'goal' turns, with user-facing pause messages","tier":"notice","area":"Goal Mode","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269\/e\/new-structured-pauseretrystop-classification-for-autonomou","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269","markdown":"### New structured pause\/retry\/stop classification for autonomous 'goal' turns, with user-facing pause messages\n\nAutonomous 'goal' turns get structured pause\/retry\/stop handling with clear 'Goal paused' messages\n\n**What**\n\nWhen you set a goal with `\/goal`, Claude keeps working across turns until the goal is met or clears for another reason. The logic that decides what happens when a goal-driven turn is interrupted has been rewritten from a simple reason string into a structured classification covering retrying, pausing, or stopping, for cases like API errors, rate limiting, usage limits, a hook (an automated check) ending the turn, or a goal-check outcome. Each case now shows a specific message, such as \"Goal paused \u00b7 the API rejected the last request \u00b7 send a message to continue, or run \/goal clear\".\n\n**Why**\n\nThis makes it clearer why an autonomous goal run stopped or paused, and tells you exactly what to do next instead of leaving you to guess.\n\n- Area: Goal Mode\n- Names: `\/goal`\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 3\/5"}