{"version":"2.1.305","anchor":"notice-when-a-subagent-fell-back-to-another-model","canonical_anchor":"notice-when-a-subagent-fell-back-to-another-model","heading":"Subagent results say when the agent switched to a backup model","tier":"notice","area":"Subagents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/notice-when-a-subagent-fell-back-to-another-model","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305","markdown":"### Subagent results say when the agent switched to a backup model\n\nWhen a subagent had to switch to a backup model because its first model could not be used, its result now starts with a warning saying so\n\n**What**\n\nA subagent is a helper agent that Claude starts to handle part of a task and that reports back with a result. When a subagent's model cannot be used, it can switch to a backup model from its fallback model chain.\n\nWhen that happens, the subagent's result now begins with a warning naming the model it switched to and saying that its earlier model could not be used.\n\n**Why**\n\nYou can now tell when a subagent ran on a different model than the one it started with, instead of the switch going unnoticed.\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}