{"version":"2.1.300","anchor":"autocompact-telemetry-expanded-and-the-high-token-warning-m","canonical_anchor":"autocompact-telemetry-expanded-and-the-high-token-warning-m","heading":"\/autocompact warns about high token usage only for larger windows","tier":"notice","area":"Compaction","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.300\/e\/autocompact-telemetry-expanded-and-the-high-token-warning-m","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.300","markdown":"### `\/autocompact` warns about high token usage only for larger windows\n\nThe high-token-usage warning in `\/autocompact` now shows only when the chosen window is bigger than the auto window for your model\n\n**What**\n\n`\/autocompact` sets the auto-compact window: how full the context window gets before Claude Code compacts automatically. When you set your own size instead of `auto`, it could warn \"Overriding auto may result in high token usage, especially when resuming long sessions.\" That warning now shows only when the size you choose is larger than the auto window for your model.\n\nThe usage report the command sends now also includes the model, the previous size and where it came from, the new size, whether it was overridden, and the route taken.\n\n**Why**\n\nYou are warned about extra token use only when your choice can actually raise it, not when you pick a smaller window.\n\n- Area: Compaction\n- Names: `\/autocompact`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}