From 62c5e17eecb07718e7f53d74dc108cae952650fb Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Thu, 25 Jun 2026 17:05:35 +0000
Subject: [PATCH] fix: retry transient failures in container metadata fetch

- Add `withRetry` helper to docker-registry.js that retries up to 2 times
  on transient errors (timeout, ECONNRESET, ECONNREFUSED, ETIMEDOUT,
  ENOTFOUND, HTTP 5xx) with linear backoff (2s, 4s)
- Wrap `getImageConfig` with `withRetry` so registry timeouts no longer
  fail the metadata endpoint on the first attempt
- Improve frontend error message to hint the user can click
  "Fetch metadata" to retry manually if all retries are exhausted

Closes #385
---
 .../pages/containers/ContainerFormPage.tsx    |  3 +-
 create-a-container/utils/docker-registry.js   | 33 +++++++++++++++++++
 2 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/create-a-container/client/src/pages/containers/ContainerFormPage.tsx b/create-a-container/client/src/pages/containers/ContainerFormPage.tsx
index 87ec7ebe..548d0123 100644
--- a/create-a-container/client/src/pages/containers/ContainerFormPage.tsx
+++ b/create-a-container/client/src/pages/containers/ContainerFormPage.tsx
@@ -229,7 +229,8 @@ export function ContainerFormPage() {
       }
       setMetadataMsg(`Loaded metadata: ${added} port(s) discovered.`);
     },
-    onError: (err: ApiError) => setMetadataMsg(err.message),
+    onError: (err: ApiError) =>
+      setMetadataMsg(`${err.message} — Use "Fetch metadata" to try again.`),
   });
 
   // Tracks the last image we auto-fetched so blurring the custom-image input
diff --git a/create-a-container/utils/docker-registry.js b/create-a-container/utils/docker-registry.js
index ef61bfe3..ef110386 100644
--- a/create-a-container/utils/docker-registry.js
+++ b/create-a-container/utils/docker-registry.js
@@ -153,6 +153,35 @@ async function authenticatedFetchJson(url, headers = {}) {
   }
 }
 
+/**
+ * Retry an async operation on transient failures (timeout, network error, 5xx).
+ * @param {Function} fn - Async function to execute
+ * @param {number} maxRetries - Number of additional attempts after the first failure
+ * @param {number} retryDelay - Base delay in ms between attempts (doubles each retry)
+ * @returns {Promise} Resolved value of fn
+ */
+async function withRetry(fn, maxRetries = 2, retryDelay = 2000) {
+  let lastError;
+  for (let attempt = 0; attempt <= maxRetries; attempt++) {
+    try {
+      return await fn();
+    } catch (err) {
+      lastError = err;
+      if (attempt === maxRetries) break;
+      const isTransient =
+        err.message.includes('timeout') ||
+        err.message.includes('ECONNRESET') ||
+        err.message.includes('ECONNREFUSED') ||
+        err.message.includes('ETIMEDOUT') ||
+        err.message.includes('ENOTFOUND') ||
+        /HTTP 5\d\d/.test(err.message);
+      if (!isTransient) throw err;
+      await new Promise((resolve) => setTimeout(resolve, retryDelay * (attempt + 1)));
+    }
+  }
+  throw lastError;
+}
+
 /**
  * Check if a template is a Docker image reference (contains '/')
  * @param {string} template - The template string
@@ -242,6 +271,10 @@ async function getImageDigest(registry, repo, tag) {
  * @returns {Promise<object>} Image config object
  */
 async function getImageConfig(registry, repo, tag) {
+  return withRetry(() => _getImageConfig(registry, repo, tag));
+}
+
+async function _getImageConfig(registry, repo, tag) {
   const registryHost = registry === 'docker.io' ? 'registry-1.docker.io' : registry;
   
   // First, fetch the manifest to get the config digest