{"version":"2.1.323","anchor":"unknown-model-window-warning-no-longer-suggests-appending-1","canonical_anchor":"unknown-model-window-warning-no-longer-suggests-appending-1","heading":"Unknown-model warning now suggests \/autocompact instead of adding [1m]","tier":"use","area":"Models","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323\/e\/unknown-model-window-warning-no-longer-suggests-appending-1","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323","markdown":"### Unknown-model warning now suggests \/autocompact instead of adding [1m]\n\nThe warning for an unrecognised model no longer says to add [1m] and now suggests \/autocompact for 1M-token windows\n\n**What**\n\nWhen Claude Code does not recognise your model name, such as an alias from a gateway, it shows a notice about the context window (how much text the model can hold at once) it assumes. That notice changed:\n\n- It no longer suggests adding `[1m]` to the model name to get a 1 million token window\n\n- When the assumed window is 1 million tokens or more, it suggests setting a smaller auto-compact window with `\/autocompact`\n\nThe notice still suggests setting `CLAUDE_CODE_MAX_CONTEXT_TOKENS` to the model's real window. Setting `CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT=1` works as before.\n\n**Why**\n\nIf you use a model Claude Code does not recognise, the advice in the warning is different. With a large assumed window, it now points you to `\/autocompact`, which sets how full the context gets before Claude Code compacts it automatically.\n\n- Area: Models\n- Names: `\/autocompact`\n- Tier: Use it now\n- Useful: 2\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}