{"version":"2.1.267","anchor":"auto-mode-safety-classifier-gets-hard-sizenode-budgets-on-o","canonical_anchor":"auto-mode-safety-classifier-gets-hard-sizenode-budgets-on-o","heading":"Auto-mode safety classifier gets hard size\/node budgets on output schemas","tier":"internal","area":"Auto Mode","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.267\/e\/auto-mode-safety-classifier-gets-hard-sizenode-budgets-on-o","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.267","markdown":"### Auto-mode safety classifier gets hard size\/node budgets on output schemas\n\nAuto mode's safety classifier now enforces separate hard limits on a tool schema's size and nesting depth\n\n**What**\n\nWhen Claude Code's auto mode decides whether a tool call needs your approval, it feeds the tool's output schema to a safety classifier. That schema is now checked against two separate hard limits, one on how many nodes it can expand into and one on its total byte size, each raising its own error when exceeded, instead of a single overall length check.\n\n**Why**\n\nThis makes the safety classifier used in auto mode harder to overwhelm with an unusually large or deeply nested tool schema, since either limit alone can now stop an oversized schema before it reaches the classifier.\n\n- Area: Auto Mode\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}