{"version":"2.1.286","anchor":"fallback-model-switch-warns-about-a-smaller-context-window","canonical_anchor":"fallback-model-switch-warns-about-a-smaller-context-window","heading":"Switching to a fallback model now warns when the context window shrinks","tier":"notice","area":"Model Fallback","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286\/e\/fallback-model-switch-warns-about-a-smaller-context-window","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286","markdown":"### Switching to a fallback model now warns when the context window shrinks\n\nWhen Claude Code falls back to a model with a smaller context window, the notice shows both sizes and suggests `\/clear` or a larger fallback\n\n**Unclear.** It is not clear whether this notice is shown to everyone or only when some setting allows it.\n\n**What**\n\nClaude Code can switch to a fallback model, a backup from your fallback list, when the model you picked cannot be used. Each model has a context window, which is how much of the conversation it can hold at once. When the fallback model has a smaller context window than the one it replaces, Claude Code now says so.\n\n- The notice gains a line showing the change, in the form \"context window X \u2192 Y tokens\".\n\n- A follow-up message explains that Claude Code fell back to another model and suggests choosing a fallback model with a larger context window, or using `\/clear` to start a new conversation with empty context.\n\n- It also suggests putting a model that supports a 1M-token context window in the fallback list.\n\n**Why**\n\nWithout this, a long conversation could suddenly seem to lose earlier details after a fallback, with no hint why. The notice explains the loss and points to ways to avoid it.\n\n- Area: Model Fallback\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 1\/5"}