diff --git a/backend/crates/gateway-api/tests/openai/responses/http.rs b/backend/crates/gateway-api/tests/openai/responses/http.rs index ce4e576be..b11a7a2f4 100644 --- a/backend/crates/gateway-api/tests/openai/responses/http.rs +++ b/backend/crates/gateway-api/tests/openai/responses/http.rs @@ -2164,13 +2164,14 @@ async fn streaming_upstream_wire_failure_should_not_be_rewritten_as_a_gateway_er #[tokio::test] async fn streaming_upstream_error_event_should_be_translated_to_response_failed_for_sse() { - for (error_type, code, client_code, kind, client_status) in [ + for (error_type, code, client_code, kind, client_status, keeps_retry_after) in [ ( "service_unavailable_error", "server_is_overloaded", "server_error", ProviderErrorKind::UpstreamCapacityUnavailable, 503, + false, ), ( "rate_limit_error", @@ -2178,13 +2179,14 @@ async fn streaming_upstream_error_event_should_be_translated_to_response_failed_ "turn_rate_limit_exceeded", ProviderErrorKind::RateLimited, 429, + true, ), ] { let trace = Arc::new(Trace::default()); let error_data = json!({ "type": "error", "status": 429, - "headers": {"Retry-After": "24"}, + "headers": {"Retry-After": "24", "retry-after-ms": "24000", "x-request-id": "req_test"}, "error": { "type": error_type, "code": code, @@ -2254,6 +2256,31 @@ async fn streaming_upstream_error_event_should_be_translated_to_response_failed_ .find(|event| event.event.as_deref() == Some("response.failed")) .expect("translated response.failed event"); let failed: Value = serde_json::from_str(&failed.data).expect("response.failed JSON"); + let mut expected = json!({ + "type": "response.failed", + "status": client_status, + "headers": {"x-request-id": "req_test"}, + "response": { + "id": "resp_test", + "model": "public-model", + "status": "failed", + "error": { + "type": error_type, + "code": client_code, + "message": "Our servers are currently overloaded. Please try again later.", + "param": null, + "future_error_field": {"keep": true} + }, + "future_response_field": {"keep": true} + }, + "sequence_number": 2, + "future_event_field": {"keep": true} + }); + if keeps_retry_after { + expected["headers"]["Retry-After"] = json!("24"); + expected["headers"]["retry-after-ms"] = json!("24000"); + expected["response"]["error"]["headers"] = json!({"retry-after": "24"}); + } assert_eq!( ( @@ -2262,32 +2289,8 @@ async fn streaming_upstream_error_event_should_be_translated_to_response_failed_ body.contains("event: error\n"), body.ends_with("data: [DONE]\n\n"), ), - ( - json!({ - "type": "response.failed", - "status": client_status, - "headers": {"Retry-After": "24"}, - "response": { - "id": "resp_test", - "model": "public-model", - "status": "failed", - "error": { - "type": error_type, - "code": client_code, - "message": "Our servers are currently overloaded. Please try again later.", - "param": null, - "future_error_field": {"keep": true}, - "headers": {"retry-after": "24"} - }, - "future_response_field": {"keep": true} - }, - "sequence_number": 2, - "future_event_field": {"keep": true} - }), - 1, - false, - true, - ) + (expected, 1, false, true), + "{code}" ); } }