{"version":"2.1.281","anchor":"context-usage-reports-carry-a-compact-boundary-id-stripped","canonical_anchor":"context-usage-reports-carry-a-compact-boundary-id-stripped","heading":"Context-usage reports carry a compact-boundary id, stripped for some sessions","tier":null,"area":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281\/e\/context-usage-reports-carry-a-compact-boundary-id-stripped","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281","markdown":"### Context-usage reports carry a compact-boundary id, stripped for some sessions\n\nContext-usage reports can now name the compaction point they were measured after, except in some sessions\n\n**Unclear.** The finding does not say what a `foreign` or `noHistoryBackfill` session is from a user's point of view.\n\n**What**\n\nClaude Code reports how full the context window is, meaning how much of the model's working memory the conversation uses. That report can now include `after_boundary`, the ID of the compact-boundary message at the start of the conversation. A compact boundary marks where an earlier part of the conversation was replaced by a summary.\n\n- An estimate taken after a boundary is skipped until a measured value has been written\n\n- The context meter uses an estimate only if it belongs to the same boundary as the measured value, and keeps the measured value's other fields\n\n- `after_boundary` is left out for sessions with `noHistoryBackfill` or `foreign` set\n\n**Why**\n\nThe context meter is less likely to mix a figure from before a compaction with one from after it."}