{"version":"2.1.323","anchor":"per-model-capability-facts-now-feed-beta-and-effort-decision","canonical_anchor":"per-model-capability-facts-now-feed-beta-and-effort-decision","heading":"What each model supports can now be set from the server","tier":"internal","area":"Models","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323\/e\/per-model-capability-facts-now-feed-beta-and-effort-decision","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323","markdown":"### What each model supports can now be set from the server\n\nClaude Code now reads per-model capability details from server-sent data, which override its built-in checks on features like effort\n\n**What**\n\nClaude Code decides some behaviour based on what the current model supports, such as whether it accepts a per-turn effort level or tools added mid-conversation. Those decisions used to rely on checks built into Claude Code that look at the model's name. Claude Code now reads a set of capability details for each model from data the server sends, and those override the built-in checks. The `\/compact` context window display uses the same details.\n\n**Why**\n\nWhat a model is treated as supporting can be changed from the server without an update to Claude Code.\n\n- Area: Models\n- Names: `\/compact`\n- Tier: Under the hood\n- Useful: 3\/5\n- Signal: 4\/5\n- Scope: individual\n- Heads-up: no"}