{"version":"2.1.234","anchor":"new-cli-api-error-event-when-api-retries-are-exhausted","canonical_anchor":"new-cli-api-error-event-when-api-retries-are-exhausted","heading":"New cli_api_error event when API retries are exhausted","tier":"internal","area":"Telemetry","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.234\/e\/new-cli-api-error-event-when-api-retries-are-exhausted","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.234","markdown":"### New `cli_api_error` event when API retries are exhausted\n\nAn API call that fails every retry now records attempts, timing, model and route.\n\n**What**\n\nAn API call that fails after all retries now emits an error-level telemetry event recording the attempt count, the duration with and without retries, whether it fell back to non-streaming, the client request id, the model, the query source and the route.\n\n**Evidence**\n\n`did_fallback_to_non_streaming`\n\n- Area: Telemetry\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 2\/5"}