{"version":"2.1.232","anchor":"context-returns-a-structured-breakdown-of-token-usage","canonical_anchor":"context-returns-a-structured-breakdown-of-token-usage","heading":"\/context returns a structured breakdown of token usage","tier":"notice","area":"Context","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232\/e\/context-returns-a-structured-breakdown-of-token-usage","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232","markdown":"### \/context returns a structured breakdown of token usage\n\n\/context now attaches exact machine-readable token numbers alongside its rendered report.\n\n**What**\n\nThe `\/context` command now attaches machine-readable usage data to its message alongside the text, so the context report carries exact numbers rather than only rendered output.\n\n**Details**\n\n- The payload includes the model, `total_tokens`, `raw_max_tokens`, a percentage, and an optional over-limit block giving how many tokens over and of what kind.\n- Separate breakdowns for categories, MCP tools, memory files and agents.\n- Each category is classified by a new helper as free, buffer, deferred or used.\n- The field flows through to the transcript and to the assistant message yielded to the caller. No such field existed in the previous build.\n\n**Evidence**\n\n`raw_max_tokens`\n\n- Area: Context\n- Names: `\/context`\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}