Merge pull request #736 from MBombeck/ci/e2e-shards

Run the browser suite as two shards

.github/workflows/e2e.yml

@@ -15,9 +15,19 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  e2e:
+  # The suite outgrew the runner the same way the integration suite did: the
+  # single job passed at ~18 minutes against a 20-minute cap, and the settings
+  # geometry measurements pushed it over. Same remedy, split rather than raise:
+  # two Playwright shards, each with its own database and production build, and
+  # a gate job below that carries the exact name branch protection requires.
+  shard:
     runs-on: ubuntu-latest
     timeout-minutes: 20
+    strategy:
+      fail-fast: false
+      matrix:
+        shard: [1, 2]
+    name: e2e shard ${{ matrix.shard }}/2
     services:
       postgres:
         image: postgres:16-alpine
@@ -87,7 +97,7 @@ jobs:
       # chart-runtime boundary (a duplicated ~92 KB gz recharts chunk).
       - run: pnpm bundle-check
 
-      - run: pnpm exec playwright test
+      - run: pnpm exec playwright test --shard=${{ matrix.shard }}/2
         env:
           E2E_BASE_URL: http://localhost:3000
 
@@ -95,7 +105,23 @@ jobs:
         if: always()
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
-          name: playwright-report
+          name: playwright-report-shard-${{ matrix.shard }}
           path: playwright-report/
           retention-days: 7
           if-no-files-found: ignore
+
+  # Branch protection requires a check named exactly "e2e". This job carries
+  # that name and answers for both shards: it fails when any shard failed or
+  # was cancelled, so a half-green matrix cannot satisfy the gate.
+  e2e:
+    runs-on: ubuntu-latest
+    needs: shard
+    if: always()
+    timeout-minutes: 5
+    steps:
+      - name: Every shard finished green
+        run: |
+          if [ "${{ needs.shard.result }}" != "success" ]; then
+            echo "shard result: ${{ needs.shard.result }}"
+            exit 1
+          fi

scripts/__tests__/ci-determinism.test.ts

@@ -77,14 +77,19 @@ describe("Playwright CI determinism", () => {
     const workflow = parse(
       readRepoFile(".github/workflows/e2e.yml"),
     ) as Workflow;
-    const upload = workflow.jobs.e2e?.steps?.find((step) =>
+    // The suite runs as a shard matrix since the single job outgrew its
+    // timeout; the running job is `shard`, while `e2e` is the gate that
+    // carries the required check name and runs no browser. The report
+    // therefore lives on the shard job, named per shard so the two
+    // artifacts cannot clobber each other.
+    const upload = workflow.jobs.shard?.steps?.find((step) =>
       step.uses?.startsWith("actions/upload-artifact@"),
     );
 
     expect(upload).toBeDefined();
     expect(upload?.if).toBe("always()");
     expect(upload?.with).toMatchObject({
-      name: "playwright-report",
+      name: "playwright-report-shard-${{ matrix.shard }}",
       path: "playwright-report/",
       "retention-days": 7,
       "if-no-files-found": "ignore",
@@ -95,7 +100,7 @@ describe("Playwright CI determinism", () => {
     const workflow = parse(
       readRepoFile(".github/workflows/e2e.yml"),
     ) as Workflow;
-    const env = workflow.jobs.e2e?.env;
+    const env = workflow.jobs.shard?.env;
 
     expect(env?.API_TOKEN_HMAC_KEY).toMatch(/^[0-9a-f]{64}$/);
     expect(env?.SESSION_COOKIE_SECURE).toBe("false");