{"version":"2.1.280","anchor":"context-usage-metadata-reporting-reworked-to-reduce-flicker","canonical_anchor":"context-usage-metadata-reporting-reworked-to-reduce-flicker","heading":"Context-usage metadata reporting reworked to reduce flicker\/inaccuracy","tier":"notice","area":"Context Usage","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/context-usage-metadata-reporting-reworked-to-reduce-flicker","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### Context-usage metadata reporting reworked to reduce flicker\/inaccuracy\n\nContext-usage reporting now waits briefly for a real token count instead of always estimating\n\n**What**\n\nThe reporting of context-window usage (how much of the model's available context has been used) has been rewritten around a new shared component that tracks both measured and estimated token counts. It adds a `reportAtTurnEnd` step that, at the end of a turn, waits briefly for a real measured token count before reporting; if that wait times out, it falls back to an estimate instead.\n\n**Why**\n\nPreviously reported usage numbers could flicker between estimated and measured values or be briefly inaccurate. Waiting for a real count when possible, with a timeout fallback, should make usage indicators (such as a status bar) more stable and accurate without introducing a noticeable delay.\n\n- Area: Context Usage\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}