{"version":"2.1.269","anchor":"refined-detection-of-safeguards-api-errors-to-avoid-false","canonical_anchor":"refined-detection-of-safeguards-api-errors-to-avoid-false","heading":"Refined detection of 'safeguards' API errors to avoid false positives","tier":"notice","area":"Permissions","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269\/e\/refined-detection-of-safeguards-api-errors-to-avoid-false","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269","markdown":"### Refined detection of 'safeguards' API errors to avoid false positives\n\nFewer false positives when detecting Anthropic API 'safeguards' errors\n\n**What**\n\nWhen Claude Code checks whether a 400 error from Anthropic's API is a \"safeguards\" trip (a safety check that blocked a request), it now also checks the error message against a new pattern matching a specific structured field path, and excludes matches. It does this by first trimming the error down to just its first line before comparing.\n\n**Why**\n\nThis avoids incorrectly classifying certain error messages as safeguards trips when they aren't, which should make error handling and any related messaging more accurate.\n\n- Area: Permissions\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5"}