{"version":"2.1.232","anchor":"context-returns-machine-readable-usage-alongside-the-table","canonical_anchor":"context-returns-machine-readable-usage-alongside-the-table","heading":"\/context returns machine-readable usage alongside the table","tier":"notice","area":"Context","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232\/e\/context-returns-machine-readable-usage-alongside-the-table","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232","markdown":"### \/context returns machine-readable usage alongside the table\n\nThe \/context report now includes structured totals plus per-tool, per-memory, per-agent and per-skill breakdowns.\n\n**What**\n\nThe context report now carries a structured payload as well as the usual markdown table: model, total tokens, the model's raw maximum, percentage used, and breakdowns by category, MCP tool, memory file, agent and skill.\n\n**Details**\n\n- When you are over the window there is an extra section giving how many tokens over you are and which kind of limit was hit: the model's own believed limit, or the smaller window Claude Code compacts against.\n- A matching schema with full descriptions was added to the stream-JSON type definitions. The schema shape existed before; the code that fills it in is new.\n\n**Evidence**\n\n`Structured twin of the \/context report`, `over_limit`\n\n- Area: Context\n- Names: `\/context`\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}