From 35f7bc92cda09fc73246e75ed0925d9c89825661 Mon Sep 17 00:00:00 2001
From: kireto <kireto@oblachno.com>
Date: Wed, 26 Aug 2026 14:27:57 +0000
Subject: [PATCH] DEVX-164: fix: increase HTTP 500 retry count to 5 with longer
 backoff and visible logging

---
 docs/specs/DEVX-164.md        | 34 ++++++++++++++++++++++++++++++++++
 src/devx/tools/build_image.py | 12 ++++++++++--
 src/devx/translations.json    |  8 ++++++++
 3 files changed, 52 insertions(+), 2 deletions(-)
 create mode 100644 docs/specs/DEVX-164.md

diff --git a/docs/specs/DEVX-164.md b/docs/specs/DEVX-164.md
new file mode 100644
index 0000000..efc8079
--- /dev/null
+++ b/docs/specs/DEVX-164.md
@@ -0,0 +1,34 @@
+# DEVX-164: Increase HTTP 500 retry count and backoff for docker push
+
+## Problem
+The HTTP 500 retry logic (DEVX-162, DEVX-163) works correctly — 3 retry
+attempts are made. But all 3 attempts fail because the Gitea registry's
+"offset mismatch" race condition needs more than ~15s to recover. The
+current backoff is 5s-20s with 3 attempts (total ~15s of waiting).
+
+## Approach
+Increase retry count from 3 to 5 and backoff from 5-20s to 10-60s,
+giving the registry up to ~2 minutes to recover. Add visible logging
+between retry attempts so the CI logs show the retry happening.
+
+REQ-1: Increase retry count from 3 to 5
+REQ-2: Increase backoff from 5-20s to 10-60s exponential
+REQ-3: Add visible logging between retry attempts (click.echo)
+REQ-4: All tests pass with 100% coverage
+
+## Test Plan
+- Unit tests verify retry count and backoff parameters
+- Unit tests verify logging output on retry
+- Manual: trigger build-images workflow and verify retries visible in logs
+
+## Deploy Plan
+- Merge to master
+
+## Rollback Plan
+- Revert the merge commit
+
+## Acceptance Criteria
+- [x] REQ-1: Increase retry count from 3 to 5
+- [x] REQ-2: Increase backoff from 5-20s to 10-60s exponential
+- [x] REQ-3: Add visible logging between retry attempts (click.echo)
+- [x] REQ-4: All tests pass with 100% coverage
diff --git a/src/devx/tools/build_image.py b/src/devx/tools/build_image.py
index a9ee410..8e808d6 100644
--- a/src/devx/tools/build_image.py
+++ b/src/devx/tools/build_image.py
@@ -315,9 +315,17 @@ def push_image(
         click.echo(f"Pushing {ft}...")
 
         @retry(
-            stop=stop_after_attempt(3),
-            wait=wait_exponential(multiplier=5, min=5, max=20),
+            stop=stop_after_attempt(5),
+            wait=wait_exponential(multiplier=10, min=10, max=60),
             retry=retry_if_exception_type(PushHTTP500Error),
+            before_sleep=lambda retry_state: click.echo(
+                _(
+                    "  HTTP 500 from registry, retrying in {wait:.0f}s (attempt {attempt}/5)...",
+                    wait=retry_state.next_action.sleep if retry_state.next_action else 0,
+                    attempt=retry_state.attempt_number + 1,
+                ),
+                err=True,
+            ),
             reraise=True,
         )
         def _attempt(_cmd: list[str] = cmd) -> subprocess.CompletedProcess[str]:
diff --git a/src/devx/translations.json b/src/devx/translations.json
index 06f356c..811c753 100644
--- a/src/devx/translations.json
+++ b/src/devx/translations.json
@@ -5152,5 +5152,13 @@
     "pl": "PR has 'refactoring' label — size check bypassed.",
     "ru": "PR has 'refactoring' label — size check bypassed.",
     "zh": "PR has 'refactoring' label — size check bypassed."
+  },
+  "  HTTP 500 from registry, retrying in {wait:.0f}s (attempt {attempt}/5)...": {
+    "en": "HTTP 500 from registry, retrying in {wait:.0f}s (attempt {attempt}/5)...",
+    "bg": "  HTTP 500 от регистъра, повторен опит след {wait:.0f}с (опит {attempt}/5)...",
+    "de": "  HTTP 500 vom Registry, Wiederholung in {wait:.0f}s (Versuch {attempt}/5)...",
+    "pl": "  HTTP 500 z rejestru, ponawianie za {wait:.0f}s (próba {attempt}/5)...",
+    "ru": "  HTTP 500 от реестра, повтор через {wait:.0f}с (попытка {attempt}/5)...",
+    "zh": "  注册表返回 HTTP 500，{wait:.0f}秒后重试（第{attempt}/5次尝试）..."
   }
 }