{"version":"2.1.281","anchor":"context-total-now-counts-categories-plus-the-api-measured-m","canonical_anchor":"context-total-now-counts-categories-plus-the-api-measured-m","heading":"\/context total now counts categories plus the API-measured message remainder","tier":null,"area":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281\/e\/context-total-now-counts-categories-plus-the-api-measured-m","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281","markdown":"### \/context total now counts categories plus the API-measured message remainder\n\nThe \/context total is now the sum of its non-deferred categories plus the API-measured message remainder, not the raw API input count\n\n**Unclear.** The finding does not say how 'non-deferred' categories are chosen or how large the difference from the old total tends to be.\n\n**What**\n\n`\/context` shows how much of the context window is in use. The context window is the amount of text the model can take in at once, measured in tokens (small chunks of text). When usage figures from the API are available, the total it shows is now calculated differently. The API is the service Claude Code sends requests to.\n\n- Now: the total is the sum of the non-deferred categories plus the remaining message tokens measured by the API.\n\n- Before: the total was the raw input token count the API reported.\n\n**Why**\n\nThe headline number is now built from the same categories the breakdown lists, so the total and its parts line up. The number may differ from what earlier versions showed for a similar conversation."}