{"version":"2.1.286","anchor":"memory-recall-selector-falls-back-to-other-models-when-the-a","canonical_anchor":"memory-recall-selector-falls-back-to-other-models-when-the-a","heading":"Memory recall tries another model when the first one refuses","tier":"notice","area":"Memory","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286\/e\/memory-recall-selector-falls-back-to-other-models-when-the-a","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286","markdown":"### Memory recall tries another model when the first one refuses\n\nWhen the model picking relevant memories refuses a request, Claude Code now tries the next model on a list instead of giving up\n\n**Unclear.** Which models are on the candidate list is not stated.\n\n**What**\n\nMemory recall is the step where Claude Code picks which of your saved memories are relevant to the current conversation. It uses a model to make that choice.\n\nThat step used to send a single request, and if it failed, the failure was only recorded. It now works through a list of candidate models. If one refuses the request, Claude Code logs a warning and tries the next. It records whether it had to fall back to another model, and separately records when every model on the list refused.\n\n**Why**\n\nMemory recall is less likely to fail quietly when a model refuses the request, so relevant memories are more likely to reach Claude.\n\n- Area: Memory\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5"}