{"version":"2.1.283","anchor":"desktop-auto-compact-window-cap-is-now-driven-by-the-tengu","canonical_anchor":"desktop-auto-compact-window-cap-is-now-driven-by-the-tengu","heading":"Claude Desktop can cap the auto-compact window on 1M-context models","tier":"soon","area":"Compaction","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.283\/e\/desktop-auto-compact-window-cap-is-now-driven-by-the-tengu","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.283","markdown":"### Claude Desktop can cap the auto-compact window on 1M-context models\n\nIn Claude Desktop, auto-compact on 1M-context models can now be capped at a 600k or 500k window by a server-side setting\n\n**What**\n\nAuto-compact summarizes older parts of a conversation when it grows too long for the model's context window, which is how much text the model can take in at once. A cap on that window, which previously could never apply, can now be set from the server. It is only considered when all of these hold:\n\n- `CLAUDE_CODE_ENTRYPOINT` is `claude-desktop`\n\n- auto-compact is enabled\n\n- the model natively supports a context window of at least 1M tokens\n\nA value of \"600k\" or \"500k\" limits the window to 600,000 or 500,000 tokens. The built-in default is empty, so no cap applies unless the server sends a value.\n\n**Why**\n\nDesktop users on 1M-context models could see compaction start earlier if the server applies the cap to their account.\n\n- Flag `tengu_goofy_jellyfish`: Not enough to say (read for one account on one subscription tier against v2.1.283; this account: no value returned, anonymous baseline: no value returned, compiled default: not a boolean we can read) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.\n- Area: Compaction\n- Tier: Nothing to try yet\n- Useful: 3\/5\n- Signal: 3\/5"}