From d70a76298a34a744bc3495b3528da032d3783e38 Mon Sep 17 00:00:00 2001
From: Alexandre <44178713+alexbelgium@users.noreply.github.com>
Date: Thu, 13 Aug 2026 11:55:05 +0200
Subject: [PATCH] fix(ci): retry a failed add-on build once before
 auto-reverting the push (#2971)

A single failing matrix leg in the builder reverts the entire push, so any
transient error inside a build silently undoes a good version bump.

Observed on zoneminder 1.38.4 (run 31678876409, attempt 1): the aarch64 leg
failed after 44 s inside the ha_autoapps.sh layer with

  curl: (92) HTTP/2 stream 1 was not closed cleanly: REFUSED_STREAM (err 7)
  gzip: stdin: unexpected end of file
  tar: Error is not recoverable: exiting now

while the amd64 leg built and pushed 1.38.4 to GHCR. revert-on-failure then
pushed 0ee26fc72 reverting the bump; a manual re-run of the same source went
fully green. Because that re-run flips the run conclusion to success, these
incidents do not even show up in run-conclusion statistics.

The build-image step is now run tolerantly (continue-on-error) and repeated
once when the first attempt fails. Only a second failure reaches
revert-on-failure, so genuinely broken add-ons are still reverted, one build
later than before.

The retry is unconditional rather than gated on the log text looking
transient: BuildKit reformats error strings and registry/runner failures
spell themselves many different ways, so a text classifier would eventually
stop reverting real breakage. It is also cheap - the add-ons that fail
deterministically on every push (ente, comixed, binance-trading-bot) each
fail in 16-34 s.

Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
---
 .github/workflows/onpush_builder.yaml | 44 +++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/.github/workflows/onpush_builder.yaml b/.github/workflows/onpush_builder.yaml
index 134ce45d2d..b2949204e9 100644
--- a/.github/workflows/onpush_builder.yaml
+++ b/.github/workflows/onpush_builder.yaml
@@ -285,8 +285,52 @@ jobs:
             echo "${{ matrix.arch }} is not a valid architecture for ${{ matrix.addon }}, skipping build."
           fi
 
+      # A single failing leg here auto-reverts the whole push (revert-on-failure
+      # below), so a transient error inside the build - a truncated download in
+      # a RUN layer, a registry hiccup - silently undoes a perfectly good
+      # version bump. Seen on zoneminder 1.38.4 (run 31678876409): the aarch64
+      # leg died on "curl: (92) HTTP/2 stream 1 was not closed cleanly:
+      # REFUSED_STREAM", the commit was reverted, and a manual re-run of the
+      # identical source then went green. (A lost runner or a cancelled job is
+      # not covered by this - no later step gets to run at all.)
+      #
+      # So: build once tolerantly, and only let a second failure reach the
+      # revert. A genuinely broken add-on fails twice and is still reverted,
+      # one build later. Retrying is unconditional rather than gated on the
+      # log text looking "transient" - BuildKit reformats error strings and
+      # registry/runner failures spell themselves a dozen ways, so classifying
+      # by log text would silently stop reverting real breakage. It is also
+      # cheap: the add-ons that fail deterministically on every push each fail
+      # in 16-34 s.
       - name: Build ${{ matrix.addon }} add-on
+        id: build
         if: steps.info.outputs.build_arch == 'true' && steps.info.outputs.has_dockerfile == 'true'
+        continue-on-error: true
+        uses: home-assistant/builder/actions/build-image@2026.06.0
+        with:
+          arch: ${{ matrix.arch }}
+          cache-gha: "false"
+          cache-gha-scope: ${{ matrix.addon }}-${{ matrix.arch }}
+          context: ./${{ matrix.addon }}
+          file: ${{ steps.info.outputs.dockerfile }}
+          image: ${{ steps.info.outputs.image }}
+          image-tags: |
+            ${{ steps.info.outputs.version }}
+            latest
+          version: ${{ steps.info.outputs.version }}
+          push: "true"
+          cosign: "false"
+          container-registry-password: ${{ secrets.GITHUB_TOKEN }}
+          labels: ${{ steps.info.outputs.labels }}
+          build-args: ${{ steps.info.outputs.build_args }}
+
+      # Keep these inputs identical to the first attempt above - this step is
+      # that attempt, run a second time, and nothing else. There is deliberately
+      # no pause in between: re-running the earlier layers already spaces the
+      # two network windows apart, and a sleep step would only add somewhere
+      # else for the retry to be skipped from.
+      - name: Build ${{ matrix.addon }} add-on (retry after failed attempt)
+        if: steps.build.outcome == 'failure'
         uses: home-assistant/builder/actions/build-image@2026.06.0
         with:
           arch: ${{ matrix.arch }}