{"version":"2.1.248","anchor":"first-error-in-a-failed-run-is-handled-separately","canonical_anchor":"first-error-in-a-failed-run-is-handled-separately","heading":"First error in a failed run is handled separately","tier":"internal","area":"Error Handling","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248\/e\/first-error-in-a-failed-run-is-handled-separately","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248","markdown":"### First error in a failed run is handled separately\n\nThe first error of a failed run is now handled distinctly from later ones.\n\n**What**\n\nWhen a run ends in an execution error, the collected errors now pass through a helper in a \"first\" mode so the first error is treated distinctly from the rest before being reported. The retry cap and its telemetry are unchanged.\n\n**Details**\n\n- `MAX_STRUCTURED_OUTPUT_RETRIES` is still honoured as an environment override.\n\n**Evidence**\n\n`error_max_structured_output_retries`\n\n- Area: Error Handling\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}