fix(gateway): fail over model-not-found responses

backend/internal/handler/openai_gateway_credential_failover_test.go

@@ -128,6 +128,44 @@ func TestOpenAICapacityFailoverExhaustionPreservesMessageAsServerError(t *testin
 	})
 }
 
+func TestOpenAIManagedSingleAccountModelNotFoundExhaustionPreservesStructured400(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	recorder := httptest.NewRecorder()
+	c, _ := gin.CreateTestContext(recorder)
+	body := []byte(`{"error":{"type":"invalid_request_error","code":"model_not_found","param":"model","message":"The requested model is unavailable on this account"}}`)
+
+	(&OpenAIGatewayHandler{}).handleFailoverExhausted(c, &service.UpstreamFailoverError{
+		StatusCode:   http.StatusBadRequest,
+		ResponseBody: body,
+	}, false)
+
+	require.Equal(t, http.StatusBadRequest, recorder.Code)
+	require.Equal(t, "invalid_request_error", gjson.Get(recorder.Body.String(), "error.type").String())
+	require.Equal(t, "model_not_found", gjson.Get(recorder.Body.String(), "error.code").String())
+	require.Equal(t, "model", gjson.Get(recorder.Body.String(), "error.param").String())
+	require.Equal(t, "The requested model is unavailable on this account", gjson.Get(recorder.Body.String(), "error.message").String())
+}
+
+func TestOpenAIManagedModelNotFoundExhaustionSanitizesMessage(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	recorder := httptest.NewRecorder()
+	c, _ := gin.CreateTestContext(recorder)
+	body := []byte(`{"error":{"code":"model_not_found","message":"Model not found; inspect https://upstream.example/debug?access_token=super-secret-value&model=x"}}`)
+
+	(&OpenAIGatewayHandler{}).handleFailoverExhausted(c, &service.UpstreamFailoverError{
+		StatusCode:   http.StatusBadRequest,
+		ResponseBody: body,
+	}, false)
+
+	require.Equal(t, http.StatusBadRequest, recorder.Code)
+	require.NotContains(t, recorder.Body.String(), "super-secret-value")
+	require.Contains(t, gjson.Get(recorder.Body.String(), "error.message").String(), "access_token=***")
+	recorded, ok := c.Get(service.OpsUpstreamErrorMessageKey)
+	require.True(t, ok)
+	require.NotContains(t, recorded, "super-secret-value")
+	require.Contains(t, recorded, "access_token=***")
+}
+
 func TestResponsesFailoverExhaustedAfterForwardedTerminalMarksOpsWithoutDuplicateFrame(t *testing.T) {
 	gin.SetMode(gin.TestMode)
 	recorder := httptest.NewRecorder()

backend/internal/handler/openai_gateway_handler.go

@@ -3311,6 +3311,12 @@ func (h *OpenAIGatewayHandler) handleFailoverExhausted(c *gin.Context, failoverE
 	}
 	statusCode := failoverErr.StatusCode
 	responseBody := failoverErr.ResponseBody
+	if statusCode == http.StatusBadRequest && service.IsOpenAICompatibleModelNotFound400(responseBody) && !streamStarted {
+		upstreamMsg := service.SanitizeUpstreamErrorMessage(service.ExtractUpstreamErrorMessage(responseBody))
+		service.SetOpsUpstreamError(c, statusCode, upstreamMsg, "")
+		service.WriteOpenAIUpstreamClientError(c, statusCode, responseBody, upstreamMsg)
+		return
+	}
 	if service.IsOpenAISilentRefusalErrorBody(responseBody) {
 		service.SetOpsUpstreamError(c, statusCode, service.OpenAISilentRefusalClientMessage(), "")
 		h.handleStreamingAwareError(c, http.StatusBadGateway, "upstream_error", service.OpenAISilentRefusalClientMessage(), streamStarted)