Replace privilegedescalation-dev with headlamp-dev in E2E scripts and workflow

Co-Authored-By: Paperclip <noreply@paperclip.ing>

.github/workflows/e2e.yaml

@@ -10,14 +10,94 @@ on:
 permissions:
   contents: read
 
+# Only one E2E run at a time: the shared E2E_RELEASE (headlamp-e2e) in
+# headlamp-dev cannot be shared across concurrent runs.
+# cancel-in-progress: false (queue, don't cancel) — cancelling in-flight
+# runs may skip the if: always() teardown, leaving dangling cluster resources.
 concurrency:
   group: e2e-${{ github.repository }}
   cancel-in-progress: false
 
+env:
+  E2E_NAMESPACE: headlamp-dev
+  E2E_RELEASE: headlamp-e2e
+  # Pin to a known-good Headlamp version. Using :latest is risky because
+  # the tag can change between CI runs, causing flaky failures when a newer
+  # image is pulled on some nodes but not others (IfNotPresent pull policy).
+  # Update this when Headlamp is upgraded in production (kube-system).
+  HEADLAMP_VERSION: v0.40.1
+
 jobs:
   e2e:
-    uses: privilegedescalation/.github/.github/workflows/plugin-e2e.yaml@main
-    with:
-      node-version: '22'
-      headlamp-version: v0.40.1
-      e2e-namespace: headlamp-dev
+    runs-on: runners-privilegedescalation
+    timeout-minutes: 15
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v6
+        with:
+          node-version: '22'
+          cache: 'npm'
+
+      - name: Setup kubectl
+        uses: azure/setup-kubectl@v4
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Build plugin
+        run: npx @kinvolk/headlamp-plugin build
+
+      - name: Deploy E2E Headlamp instance
+        run: scripts/deploy-e2e-headlamp.sh
+
+      - name: Load E2E environment
+        run: |
+          if [ -f .env.e2e ]; then
+            cat .env.e2e >> "$GITHUB_ENV"
+          else
+            echo "::error::deploy-e2e-headlamp.sh did not produce .env.e2e"
+            exit 1
+          fi
+
+      - name: Install Playwright browsers
+        run: npx playwright install --with-deps chromium
+
+      - name: Run E2E tests
+        run: npm run e2e
+        env:
+          HEADLAMP_URL: ${{ env.HEADLAMP_URL }}
+          HEADLAMP_TOKEN: ${{ env.HEADLAMP_TOKEN }}
+
+      - name: Collect deployment diagnostics on failure
+        if: failure()
+        run: |
+          echo "=== Pod state ==="
+          kubectl get pods -n "$E2E_NAMESPACE" -l "app.kubernetes.io/instance=$E2E_RELEASE" 2>&1 || true
+          echo "=== Pod describe ==="
+          kubectl describe pods -n "$E2E_NAMESPACE" -l "app.kubernetes.io/instance=$E2E_RELEASE" 2>&1 || true
+          echo "=== Recent namespace events ==="
+          kubectl get events -n "$E2E_NAMESPACE" --sort-by='.lastTimestamp' 2>&1 | tail -20 || true
+
+      - name: Teardown E2E instance
+        if: always()
+        run: scripts/teardown-e2e-headlamp.sh
+
+      - name: Upload Playwright report
+        uses: actions/upload-artifact@v7
+        if: failure()
+        with:
+          name: playwright-report
+          path: playwright-report/
+          retention-days: 7
+
+      - name: Upload test results
+        uses: actions/upload-artifact@v7
+        if: failure()
+        with:
+          name: test-results
+          path: test-results/
+          retention-days: 7

package.json

@@ -45,7 +45,6 @@
   "overrides": {
     "tar": "^7.5.11",
     "undici": "^7.24.3",
-    "lodash": ">=4.18.0",
-    "elliptic": ">=6.6.1"
+    "lodash": ">=4.18.0"
   }
 }

scripts/deploy-e2e-headlamp.sh

@@ -59,15 +59,10 @@ kubectl create configmap headlamp-intel-gpu-plugin \
   --from-file=package.json="$REPO_ROOT/package.json"
 
 # --- Tear down any existing E2E deployment for a clean start ---
-# Deleting the Deployment forces a fresh pod (new ReplicaSet) regardless of
-# whether the pod spec changed. The ServiceAccount is also deleted for a clean
-# token state. The Service is NOT deleted — leaving it in place avoids an
-# Endpoints UID race (FailedToUpdateEndpoint) that causes DNS resolution
-# failures. kubectl apply below upserts the Service in-place, and the new
-# pod's IP is added to the existing Endpoints automatically.
 echo ""
 echo "Removing any existing E2E deployment (clean-start)..."
 kubectl delete deployment "${E2E_RELEASE}" -n "$E2E_NAMESPACE" --ignore-not-found --wait
+kubectl delete service "${E2E_RELEASE}" -n "$E2E_NAMESPACE" --ignore-not-found --wait
 kubectl delete serviceaccount "${E2E_RELEASE}" -n "$E2E_NAMESPACE" --ignore-not-found --wait
 
 # --- Deploy Headlamp via kubectl apply ---