From 3470c91e3a6777ffac2ffa56d04ace5b65454c81 Mon Sep 17 00:00:00 2001
From: JamBalaya56562 <jambalaya.pyoncafe@outlook.jp>
Date: Sun, 31 May 2026 19:54:51 +0900
Subject: [PATCH] ci: fix recurring Verify Examples workflow failures

The "Verify Examples" workflow had been failing on every run. Log
analysis across many runs surfaced three independent root causes:

1. validate job: nextjs-zip and remix-zip pinned the EOL runtime
   nodejs20.x (deprecated 2026-04-30), so `sam validate --lint` matched
   cfn-lint rule W2531 and failed every run. Bumped both to nodejs22.x.
   EOL deprecations are intentionally left to fail CI so example runtimes
   get updated promptly when they age out.

2. test-image(fasthtml) / test-zip(fasthtml-zip): requirements.txt left
   python-fasthtml unpinned. Newer releases (>=0.14.0) dropped `Card` from
   fasthtml.common, so the app raised `NameError: name 'Card' is not
   defined` and returned HTTP 500. Pinned to ==0.13.4 (latest release that
   still exports Card and installs cleanly on python:3.12-slim). Verified
   end-to-end: the real app's index route now returns HTTP 200.

3. test-image/test-zip build steps: intermittent `toomanyrequests: Rate
   exceeded` while sam build pulled base images from public.ecr.aws.
   Wrapped both `sam build` invocations in a 3-attempt retry loop.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 .github/workflows/examples.yaml            | 40 ++++++++++++++++++++--
 examples/fasthtml-zip/app/requirements.txt |  2 +-
 examples/fasthtml/app/requirements.txt     |  2 +-
 examples/nextjs-zip/template.yaml          |  2 +-
 examples/remix-zip/template.yaml           |  2 +-
 5 files changed, 42 insertions(+), 6 deletions(-)

diff --git a/.github/workflows/examples.yaml b/.github/workflows/examples.yaml
index 392eec8b..0c196a5e 100644
--- a/.github/workflows/examples.yaml
+++ b/.github/workflows/examples.yaml
@@ -119,7 +119,25 @@ jobs:
 
       - name: Build
         working-directory: examples/${{ matrix.example }}
-        run: sam build
+        run: |
+          # Retry to tolerate transient registry rate limits (toomanyrequests: Rate
+          # exceeded). public.ecr.aws throttles unauthenticated pulls at ~1 req/s per
+          # source IP, and the matrix runs many jobs from shared runner IPs, so bursts
+          # collide. Exponential backoff with random jitter desynchronizes retries
+          # across jobs to avoid a thundering herd re-colliding on the same boundary.
+          max_attempts=5
+          attempt=1
+          while true; do
+            if sam build; then exit 0; fi
+            if [ "$attempt" -ge "$max_attempts" ]; then
+              echo "sam build failed after ${max_attempts} attempts"
+              exit 1
+            fi
+            delay=$(( 10 * 2 ** (attempt - 1) + RANDOM % 16 ))   # ~10/20/40/80s + 0-15s jitter
+            echo "sam build failed (attempt ${attempt}/${max_attempts}), retrying in ${delay}s..."
+            sleep "$delay"
+            attempt=$(( attempt + 1 ))
+          done
 
       - name: Start local API and verify
         working-directory: examples/${{ matrix.example }}
@@ -201,7 +219,25 @@ jobs:
 
       - name: Build
         working-directory: examples/${{ matrix.example }}
-        run: sam build
+        run: |
+          # Retry to tolerate transient registry rate limits (toomanyrequests: Rate
+          # exceeded). public.ecr.aws throttles unauthenticated pulls at ~1 req/s per
+          # source IP, and the matrix runs many jobs from shared runner IPs, so bursts
+          # collide. Exponential backoff with random jitter desynchronizes retries
+          # across jobs to avoid a thundering herd re-colliding on the same boundary.
+          max_attempts=5
+          attempt=1
+          while true; do
+            if sam build; then exit 0; fi
+            if [ "$attempt" -ge "$max_attempts" ]; then
+              echo "sam build failed after ${max_attempts} attempts"
+              exit 1
+            fi
+            delay=$(( 10 * 2 ** (attempt - 1) + RANDOM % 16 ))   # ~10/20/40/80s + 0-15s jitter
+            echo "sam build failed (attempt ${attempt}/${max_attempts}), retrying in ${delay}s..."
+            sleep "$delay"
+            attempt=$(( attempt + 1 ))
+          done
 
       - name: Inject local layer into build output
         working-directory: examples/${{ matrix.example }}
diff --git a/examples/fasthtml-zip/app/requirements.txt b/examples/fasthtml-zip/app/requirements.txt
index 3a46ffff..8afeaefa 100644
--- a/examples/fasthtml-zip/app/requirements.txt
+++ b/examples/fasthtml-zip/app/requirements.txt
@@ -1 +1 @@
-python-fasthtml
+python-fasthtml==0.13.4
diff --git a/examples/fasthtml/app/requirements.txt b/examples/fasthtml/app/requirements.txt
index 3a46ffff..8afeaefa 100644
--- a/examples/fasthtml/app/requirements.txt
+++ b/examples/fasthtml/app/requirements.txt
@@ -1 +1 @@
-python-fasthtml
+python-fasthtml==0.13.4
diff --git a/examples/nextjs-zip/template.yaml b/examples/nextjs-zip/template.yaml
index c6ae6e3f..5b79bf9f 100644
--- a/examples/nextjs-zip/template.yaml
+++ b/examples/nextjs-zip/template.yaml
@@ -16,7 +16,7 @@ Resources:
       CodeUri: app/
       MemorySize: 256
       Handler: run.sh
-      Runtime: nodejs20.x
+      Runtime: nodejs22.x
       Architectures:
         - x86_64
       Environment:
diff --git a/examples/remix-zip/template.yaml b/examples/remix-zip/template.yaml
index eb10fccc..6a45c8a1 100644
--- a/examples/remix-zip/template.yaml
+++ b/examples/remix-zip/template.yaml
@@ -16,7 +16,7 @@ Resources:
     Properties:
       CodeUri: .
       Handler: run.sh
-      Runtime: nodejs20.x
+      Runtime: nodejs22.x
       MemorySize: 1024
       Architectures:
         - x86_64