From 681654233ed62097e8558010a85878a154095e4d Mon Sep 17 00:00:00 2001
From: Niek Otten <not@respellion.nl>
Date: Thu, 23 Jul 2026 16:41:57 +0200
Subject: [PATCH] ci: parallelise jobs at runner capacity >1, keep the two
 heavy jobs apart (closes #127)

The six jobs have no data dependencies, so they now schedule concurrently on the
capacity-2 runner. Guard against the two memory-heavy jobs (mutation + verify-stack)
co-scheduling and re-triggering the e2e OOM (#126): order verify-stack after mutation
via needs, with if: !cancelled() so it still runs when the ratchet fails. Add a
concurrency group so a new push supersedes the previous run instead of wasting a slot.

closes #127
---
 .gitea/workflows/ci.yaml | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/.gitea/workflows/ci.yaml b/.gitea/workflows/ci.yaml
index 4ec07a3..84e9f79 100644
--- a/.gitea/workflows/ci.yaml
+++ b/.gitea/workflows/ci.yaml
@@ -9,6 +9,12 @@ on:
 permissions:
   contents: read
 
+# Supersede stale runs: a new push to the same branch/PR cancels the previous run, so the runner's
+# concurrency slots aren't spent on commits nobody is waiting for (refs #127).
+concurrency:
+  group: ci-${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 # Self-hosted runner — see docs/runbooks/ci.md for the runner setup.
 # `uses:` are absolute, tag-pinned URLs (CLAUDE.md §8.7 / §15).
 
@@ -129,12 +135,20 @@ jobs:
           path: services/bff/StrykerOutput/**/reports/mutation-report.html
           if-no-files-found: warn
 
-  # One stage for every check that needs the live stack. On the single self-hosted
-  # runner jobs run sequentially, so booting OpenZaak once (instead of once per job)
-  # is the cheapest layout (issue #58). No setup-dotnet: the ACL test runs in a built
-  # image and everything reaches services by container IP. Needs Docker + egress
+  # One stage for every check that needs the live stack. Booting OpenZaak once (instead
+  # of once per job) is the cheapest layout (issue #58). No setup-dotnet: the ACL test runs
+  # in a built image and everything reaches services by container IP. Needs Docker + egress
   # (base images, nuget, selectielijst.openzaak.nl).
+  #
+  # `needs: [mutation]` is NOT a data dependency — it serialises the two memory-heavy jobs so
+  # they never co-schedule now the runner has capacity >1. A concurrent Stryker run + full-stack
+  # bring-up + Playwright browser on one host is what OOMs the e2e (commit d5e5fa2, #126). The
+  # light .NET/frontend jobs have no `needs`, so they still parallelise up to runner capacity.
+  # `if: !cancelled()` keeps verify-stack running even when the mutation ratchet fails (so we don't
+  # lose its signal) while still honouring run cancellation from the concurrency group above.
   verify-stack:
+    needs: [mutation]
+    if: ${{ !cancelled() }}
     runs-on: ubuntu-latest
     steps:
       - uses: https://github.com/actions/checkout@v4
-- 
2.54.0