From b4437dcee4b49499be629d9b6e38eb195ccaeb24 Mon Sep 17 00:00:00 2001
From: Diego Rodrigues de Sa e Souza
 <8016841+diegosouzapw@users.noreply.github.com>
Date: Sun, 7 Jun 2026 14:57:29 -0300
Subject: [PATCH] fix(ci): stop the E2E shard from being cancelled mid-run
 (timeout headroom) (#3387)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The heaviest E2E shard (5/6 — responsive viewport matrix + studio/smoke) overran
the job's 20m timeout-minutes because each shard re-runs `npm run build` (~5m)
before Playwright, then runs ~24 serial tests with retries:2. The job was killed
(CANCELLED mid-run, 'Terminate orphan process') instead of any test failing.

- Bump test-e2e timeout-minutes 20 -> 35 (cumulative build+tests headroom).
- Lower the Playwright per-test timeout 600s -> 180s so a genuine hang fails fast
  and visibly (a clear per-test timeout) instead of silently eating the job budget.
---
 .github/workflows/ci.yml | 6 +++++-
 playwright.config.ts     | 6 +++++-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index d0f34d467e..ac3cdab2ce 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -500,7 +500,11 @@ jobs:
   test-e2e:
     name: E2E Tests (${{ matrix.shard }}/6)
     runs-on: ubuntu-latest
-    timeout-minutes: 20
+    # 20m was too tight for the heaviest shard: each shard re-runs `npm run build`
+    # (~5m) before Playwright, so a slow shard's tests + build overran 20m and the
+    # job was cancelled mid-run. 35m gives headroom; the per-test cap in
+    # playwright.config.ts bounds any genuine hang to a fast, visible failure.
+    timeout-minutes: 35
     needs: build
     strategy:
       fail-fast: false
diff --git a/playwright.config.ts b/playwright.config.ts
index 5263e2643a..072fb79a0f 100644
--- a/playwright.config.ts
+++ b/playwright.config.ts
@@ -25,7 +25,11 @@ export default defineConfig({
     "**/skills-marketplace.spec.ts",
   ],
   fullyParallel: false,
-  timeout: 600_000,
+  // Per-test cap. 600s was high enough that one hung test (× retries) could
+  // exhaust the e2e job's wall-clock budget, so the GitHub job hit its
+  // timeout-minutes and was CANCELLED mid-run instead of the test failing fast.
+  // 180s is generous for a UI flow yet bounds a hang to a clear per-test failure.
+  timeout: 180_000,
   forbidOnly: !!process.env.CI,
   retries: process.env.CI ? 2 : 0,
   workers: 1,