{"version":"2.1.281","anchor":"token-usage-attachment-computes-the-context-window-different","canonical_anchor":"token-usage-attachment-computes-the-context-window-different","heading":"Token-usage attachment computes the context window differently","tier":null,"area":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281\/e\/token-usage-attachment-computes-the-context-window-different","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281","markdown":"### Token-usage attachment computes the context window differently\n\nThe `token_usage` attachment now converts the model through an extra step before working out the context window\n\n**Unclear.** The finding does not say what the extra step does or which models it affects.\n\n**What**\n\nWhen `CLAUDE_CODE_ENABLE_TOKEN_USAGE_ATTACHMENT` is set, Claude Code adds a `token_usage` attachment, which is a note telling the model how much of its context window it has used. The context window is how much text the model can hold at once. Before working out that total, Claude Code now passes the model name through an extra conversion step.\n\n**Why**\n\nThe total in this note may now come out differently for some models."}