{"version":"2.1.315","anchor":"spawned-loop-memory-withdrawal-attachment","canonical_anchor":"spawned-loop-memory-withdrawal-attachment","heading":"New kind of context about memory for loops started by Claude Code","tier":"internal","area":"Memory","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.315\/e\/spawned-loop-memory-withdrawal-attachment","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.315","markdown":"### New kind of context about memory for loops started by Claude Code\n\nClaude Code has a new kind of attached context about withdrawing memory from a loop it has started\n\n**Unclear.** What this attachment tells the model, and when it is sent, is not stated.\n\n**What**\n\nClaude Code has a new kind of attachment, which is extra information added to the conversation alongside your messages. It concerns memory being withdrawn from a loop that Claude Code has spawned, meaning a repeating task it started itself.\n\n**Why**\n\nIt gives these loops a new piece of context to work with.\n\n- Area: Memory\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}