From b13009b4159f1c1e84b3307b9fa611e80d54c35f Mon Sep 17 00:00:00 2001
From: Kurdistan Tech Ministry <info@pezkuwichain.io>
Date: Sun, 26 Apr 2026 01:52:23 +0300
Subject: [PATCH] ci: retry test jobs once on runner_system_failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

VPS2 Docker daemon crashed mid-run, killing test-partition-1/2 and
leaving wasm-check/test-no-try-runtime-2 with 404 exec errors. None
of these were test failures — all were runner infrastructure failures.

retry: max: 1, when: runner_system_failure retries only on runner
crashes, never on actual test failures. Correct safeguard for
multi-runner setups where any VPS can restart unexpectedly.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 .gitlab-ci.yml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index 3e479738..9f935c81 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -292,6 +292,9 @@ cargo-audit:
     - echo "CARGO_TARGET_DIR=$CARGO_TARGET_DIR (disk $(df -h /cache/cargo-target | tail -1 | awk '{print $3 "/" $2 " used, " $4 " free"}'))"
   cache: []
   timeout: 150m
+  retry:
+    max: 1
+    when: runner_system_failure
   rules:
     - if: $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH
     - if: $CI_PIPELINE_SOURCE == "schedule"