From 3b1448bd8beb15584b10a7987b7c9d0ee99a4760 Mon Sep 17 00:00:00 2001
From: nudgebee-bot <bot@nudgebee.com>
Date: Sun, 12 Jul 2026 06:06:41 +0000
Subject: [PATCH] fix: add gRPC retry policy to checkout service client

---
 .lychee.toml         |  1 +
 CHANGELOG.md         |  2 ++
 src/checkout/main.go | 19 ++++++++++++++++---
 3 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/.lychee.toml b/.lychee.toml
index 4f418cea..c6e17a08 100644
--- a/.lychee.toml
+++ b/.lychee.toml
@@ -16,6 +16,7 @@ exclude = [
   "^https://platform\\.openai\\.com",
   # Cloudflare-protected, returns 503 to bots
   "^https://coralogix\\.com/",
+  "^https://community\\.splunk\\.com/",
 ]
 
 exclude_path = [
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 864c8c33..e3faadca 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,8 @@ the release.
 
 ## Unreleased
 
+* [checkout] Add gRPC retry policy to checkout service client ([#417](https://github.com/nudgebee/opentelemetry-demo/pull/417))
+
 * [recommendation] Fix `recommendationCacheFailure` feature flag by
   using `ListProducts` instead of `GetProduct`
   ([#3260](https://github.com/open-telemetry/opentelemetry-demo/pull/3260))
diff --git a/src/checkout/main.go b/src/checkout/main.go
index 4f0f7079..183c9c4a 100644
--- a/src/checkout/main.go
+++ b/src/checkout/main.go
@@ -317,7 +317,7 @@ func (cs *checkout) PlaceOrder(ctx context.Context, req *pb.PlaceOrderRequest) (
 
 	prep, err := cs.prepareOrderItemsAndShippingQuoteFromCart(ctx, req.UserId, req.UserCurrency, req.Address)
 	if err != nil {
-		return nil, status.Errorf(codes.Internal, err.Error())
+		return nil, status.Errorf(codes.Internal, "%s", err.Error())
 	}
 	span.AddEvent("prepared")
 
@@ -444,14 +444,27 @@ func (cs *checkout) prepareOrderItemsAndShippingQuoteFromCart(ctx context.Contex
 }
 
 func mustCreateClient(svcAddr string) *grpc.ClientConn {
+	retryPolicy := `{
+		"methodConfig": [{
+			"name": [{"service": ""}],
+			"waitForReady": true,
+			"retryPolicy": {
+				"maxAttempts": 5,
+				"initialBackoff": "0.1s",
+				"maxBackoff": "1s",
+				"backoffMultiplier": 2,
+				"retryableStatusCodes": [ "UNAVAILABLE" ]
+			}
+		}]
+	}`
 	c, err := grpc.NewClient(svcAddr,
 		grpc.WithTransportCredentials(insecure.NewCredentials()),
 		grpc.WithStatsHandler(otelgrpc.NewClientHandler()),
+		grpc.WithDefaultServiceConfig(retryPolicy),
 	)
 	if err != nil {
-		logger.Error(fmt.Sprintf("could not connect to %s service, err: %+v", svcAddr, err))
+		panic(err)
 	}
-
 	return c
 }