From 2eea2dc34869d0ecdaef050caed8c7d1c8dab5a7 Mon Sep 17 00:00:00 2001
From: Chris Farhood <chris@farhood.org>
Date: Thu, 14 May 2026 04:29:07 +0000
Subject: [PATCH] chore: remove dead E2E infrastructure per CTO decision
 (aff63c4)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

E2E approach is dead — removed from main in aff63c4. These files
re-introduced broken E2E infrastructure that will fail CI on every
uat→main promotion.

Removing:
- .github/workflows/e2e.yaml
- deployment/e2e-ci-runner-rbac.yaml
- scripts/deploy-e2e-headlamp.sh
- scripts/teardown-e2e-headlamp.sh

Co-Authored-By: Paperclip <noreply@paperclip.ing>
---
 .github/workflows/e2e.yaml         | 103 ---------------
 deployment/e2e-ci-runner-rbac.yaml |  12 --
 scripts/deploy-e2e-headlamp.sh     | 206 -----------------------------
 scripts/teardown-e2e-headlamp.sh   |  41 ------
 4 files changed, 362 deletions(-)
 delete mode 100644 .github/workflows/e2e.yaml
 delete mode 100644 deployment/e2e-ci-runner-rbac.yaml
 delete mode 100755 scripts/deploy-e2e-headlamp.sh
 delete mode 100755 scripts/teardown-e2e-headlamp.sh

diff --git a/.github/workflows/e2e.yaml b/.github/workflows/e2e.yaml
deleted file mode 100644
index 37f33a9..0000000
--- a/.github/workflows/e2e.yaml
+++ /dev/null
@@ -1,103 +0,0 @@
-name: E2E Tests
-
-on:
-  push:
-    branches: [main]
-  pull_request:
-    branches: [main]
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-# Only one E2E run at a time: the shared E2E_RELEASE (headlamp-e2e) in
-# privilegedescalation-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-${{ github.repository }}
-  cancel-in-progress: false
-
-env:
-  E2E_NAMESPACE: privilegedescalation-dev
-  E2E_RELEASE: headlamp-e2e
-  # Pin to a known-good Headlamp version. Using :latest is risky because
-  # the tag can change between CI runs, causing flaky failures when a newer
-  # image is pulled on some nodes but not others (IfNotPresent pull policy).
-  # Update this when Headlamp is upgraded in production (kube-system).
-  HEADLAMP_VERSION: v0.40.1
-
-jobs:
-  e2e:
-    runs-on: runners-privilegedescalation
-    timeout-minutes: 15
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: '22'
-          cache: 'npm'
-
-      - name: Setup kubectl
-        uses: azure/setup-kubectl@v4
-
-      - name: Install dependencies
-        run: npm ci
-
-      - name: Build plugin
-        run: npx @kinvolk/headlamp-plugin build
-
-      - name: Deploy E2E Headlamp instance
-        run: scripts/deploy-e2e-headlamp.sh
-
-      - name: Load E2E environment
-        run: |
-          if [ -f .env.e2e ]; then
-            cat .env.e2e >> "$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
diff --git a/deployment/e2e-ci-runner-rbac.yaml b/deployment/e2e-ci-runner-rbac.yaml
deleted file mode 100644
index 4f5aa3c..0000000
--- a/deployment/e2e-ci-runner-rbac.yaml
+++ /dev/null
@@ -1,12 +0,0 @@
----
-# RBAC for the GitHub Actions CI runner to manage E2E Headlamp instances.
-# CI-only test fixture — NOT for production use.
-#
-# This file is a REFERENCE ONLY. The canonical manifest lives in:
-#   privilegedescalation/infra/base/rbac/e2e-ci-runner-headlamp-rbac.yaml
-#
-# The infra repo is managed by Flux GitOps and is the source of truth.
-# Do not apply this file directly — it is kept here for developer reference only.
-#
-# E2E resources run in `privilegedescalation-dev` — nothing persists beyond a test run.
-# RBAC is managed via Flux from privilegedescalation/infra — do not apply manually.
diff --git a/scripts/deploy-e2e-headlamp.sh b/scripts/deploy-e2e-headlamp.sh
deleted file mode 100755
index b8c93c2..0000000
--- a/scripts/deploy-e2e-headlamp.sh
+++ /dev/null
@@ -1,206 +0,0 @@
-#!/usr/bin/env bash
-# deploy-e2e-headlamp.sh
-#
-# Deploys a stock Headlamp instance with the intel-gpu plugin loaded via
-# a ConfigMap volume mount. No custom Docker images — the plugin is built
-# in CI and injected as a ConfigMap.
-#
-# E2E resources are deployed to the `headlamp-plugins-e2e` namespace. Nothing
-# persists beyond the test run — teardown cleans up all created resources.
-#
-# Prerequisites:
-#   - Plugin built (dist/ exists with plugin-main.js + package.json)
-#   - kubectl configured with cluster access
-# RBAC is managed via Flux from privilegedescalation/infra/base/rbac/e2e-ci-runner-headlamp-rbac.yaml.
-# The infra repo is the source of truth — do not apply this file directly.
-# Apply RBAC first: kubectl apply -f privilegedescalation/infra/base/rbac/e2e-ci-runner-headlamp-rbac.yaml
-#
-# Environment:
-#   E2E_NAMESPACE     — namespace for E2E Headlamp (default: headlamp-plugins-e2e)
-#   E2E_RELEASE       — release/resource name prefix (default: headlamp-e2e)
-#   HEADLAMP_VERSION  — Headlamp image tag (default: latest)
-set -euo pipefail
-
-REPO_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
-DIST_DIR="$REPO_ROOT/dist"
-
-E2E_NAMESPACE="${E2E_NAMESPACE:-headlamp-plugins-e2e}"
-E2E_RELEASE="${E2E_RELEASE:-headlamp-e2e}"
-HEADLAMP_VERSION="${HEADLAMP_VERSION:-latest}"
-
-if [ ! -d "$DIST_DIR" ]; then
-  echo "ERROR: dist/ not found. Run 'npm run build' first." >&2
-  exit 1
-fi
-
-# --- Preflight: verify RBAC before touching the cluster ---
-echo "Checking RBAC permissions in namespace '${E2E_NAMESPACE}'..."
-if ! kubectl auth can-i delete configmaps -n "$E2E_NAMESPACE" --quiet 2>/dev/null; then
-  echo "ERROR: Missing RBAC — cannot delete configmaps in namespace '${E2E_NAMESPACE}'." >&2
-  echo "  Apply RBAC first: kubectl apply -f privilegedescalation/infra/base/rbac/e2e-ci-runner-headlamp-rbac.yaml" >&2
-  exit 1
-fi
-
-echo "=== E2E Headlamp Deployment ==="
-echo "  Image:     ghcr.io/headlamp-k8s/headlamp:${HEADLAMP_VERSION}"
-echo "  Namespace: $E2E_NAMESPACE"
-echo "  Release:   $E2E_RELEASE"
-
-# --- Create ConfigMap from built plugin ---
-echo ""
-echo "Creating ConfigMap with plugin files..."
-
-# Delete existing ConfigMap if present (idempotent redeploy)
-kubectl delete configmap headlamp-intel-gpu-plugin \
-  -n "$E2E_NAMESPACE" --ignore-not-found
-
-# Create ConfigMap from dist/ contents and package.json
-kubectl create configmap headlamp-intel-gpu-plugin \
-  -n "$E2E_NAMESPACE" \
-  --from-file="$DIST_DIR" \
-  --from-file=package.json="$REPO_ROOT/package.json"
-
-# --- Tear down any existing E2E deployment for a clean start ---
-echo ""
-echo "Removing any existing E2E deployment (clean-start)..."
-kubectl delete deployment "${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 ---
-echo ""
-echo "Deploying Headlamp E2E instance..."
-
-kubectl apply -f - <<EOF
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: ${E2E_RELEASE}
-  namespace: ${E2E_NAMESPACE}
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: ${E2E_RELEASE}
-  namespace: ${E2E_NAMESPACE}
-  labels:
-    app.kubernetes.io/name: headlamp
-    app.kubernetes.io/instance: ${E2E_RELEASE}
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: headlamp
-      app.kubernetes.io/instance: ${E2E_RELEASE}
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: headlamp
-        app.kubernetes.io/instance: ${E2E_RELEASE}
-    spec:
-      serviceAccountName: ${E2E_RELEASE}
-      automountServiceAccountToken: true
-      securityContext: {}
-      containers:
-        - name: headlamp
-          image: ghcr.io/headlamp-k8s/headlamp:${HEADLAMP_VERSION}
-          imagePullPolicy: IfNotPresent
-          securityContext:
-            runAsNonRoot: true
-            privileged: false
-            runAsUser: 100
-            runAsGroup: 101
-          args:
-            - "-in-cluster"
-            - "-in-cluster-context-name=main"
-            - "-plugins-dir=/headlamp/plugins"
-          ports:
-            - name: http
-              containerPort: 4466
-              protocol: TCP
-          readinessProbe:
-            httpGet:
-              path: /
-              port: http
-            initialDelaySeconds: 5
-            periodSeconds: 5
-            failureThreshold: 6
-          livenessProbe:
-            httpGet:
-              path: /
-              port: http
-            initialDelaySeconds: 10
-            periodSeconds: 10
-          volumeMounts:
-            - name: intel-gpu-plugin
-              mountPath: /headlamp/plugins/headlamp-intel-gpu
-              readOnly: true
-      volumes:
-        - name: intel-gpu-plugin
-          configMap:
-            name: headlamp-intel-gpu-plugin
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: ${E2E_RELEASE}
-  namespace: ${E2E_NAMESPACE}
-  labels:
-    app.kubernetes.io/name: headlamp
-    app.kubernetes.io/instance: ${E2E_RELEASE}
-spec:
-  type: ClusterIP
-  selector:
-    app.kubernetes.io/name: headlamp
-    app.kubernetes.io/instance: ${E2E_RELEASE}
-  ports:
-    - name: http
-      port: 80
-      targetPort: http
-      protocol: TCP
-EOF
-
-echo "Waiting for rollout..."
-kubectl rollout status "deployment/${E2E_RELEASE}" \
-  -n "$E2E_NAMESPACE" --timeout=120s
-
-# --- Generate a service URL for tests ---
-SVC_URL="http://${E2E_RELEASE}.${E2E_NAMESPACE}.svc.cluster.local"
-
-# --- Wait for DNS and HTTP reachability ---
-echo ""
-echo "Waiting for ${SVC_URL} to be reachable..."
-ATTEMPTS=0
-MAX_ATTEMPTS=24  # 24 × 5s = 120s max
-until curl -sf --max-time 5 "${SVC_URL}" -o /dev/null 2>/dev/null; do
-  ATTEMPTS=$((ATTEMPTS + 1))
-  if [ "$ATTEMPTS" -ge "$MAX_ATTEMPTS" ]; then
-    echo "ERROR: ${SVC_URL} not reachable after $((MAX_ATTEMPTS * 5))s" >&2
-    exit 1
-  fi
-  echo "  [${ATTEMPTS}/${MAX_ATTEMPTS}] not yet reachable, retrying in 5s..."
-  sleep 5
-done
-echo ""
-echo "E2E Headlamp is ready at: ${SVC_URL}"
-echo "  export HEADLAMP_URL=${SVC_URL}"
-
-# --- Generate a token for test auth ---
-echo ""
-echo "Creating service account token for E2E auth..."
-kubectl create serviceaccount headlamp-e2e-test \
-  -n "$E2E_NAMESPACE" --dry-run=client -o yaml | kubectl apply -f -
-
-TOKEN=$(kubectl create token headlamp-e2e-test -n "$E2E_NAMESPACE" --duration=1h 2>/dev/null || echo "")
-if [ -n "$TOKEN" ]; then
-  echo "  export HEADLAMP_TOKEN=<generated>"
-  echo ""
-  echo "HEADLAMP_URL=${SVC_URL}" > "$REPO_ROOT/.env.e2e"
-  echo "HEADLAMP_TOKEN=${TOKEN}" >> "$REPO_ROOT/.env.e2e"
-  echo "Wrote .env.e2e with HEADLAMP_URL and HEADLAMP_TOKEN"
-else
-  echo "  WARNING: Could not generate token. Set HEADLAMP_TOKEN manually or use OIDC."
-fi
-
-echo ""
-echo "E2E deployment complete."
diff --git a/scripts/teardown-e2e-headlamp.sh b/scripts/teardown-e2e-headlamp.sh
deleted file mode 100755
index 1af461e..0000000
--- a/scripts/teardown-e2e-headlamp.sh
+++ /dev/null
@@ -1,41 +0,0 @@
-#!/usr/bin/env bash
-# teardown-e2e-headlamp.sh
-#
-# Tears down the dedicated E2E Headlamp instance deployed by deploy-e2e-headlamp.sh.
-#
-# RBAC is managed via Flux from privilegedescalation/infra/base/rbac/e2e-ci-runner-headlamp-rbac.yaml.
-# The infra repo is the source of truth — do not apply this file directly.
-#
-# Environment:
-#   E2E_NAMESPACE  — namespace to clean up (default: headlamp-plugins-e2e)
-#   E2E_RELEASE    — release/resource name prefix (default: headlamp-e2e)
-set -euo pipefail
-
-REPO_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
-
-E2E_NAMESPACE="${E2E_NAMESPACE:-headlamp-plugins-e2e}"
-E2E_RELEASE="${E2E_RELEASE:-headlamp-e2e}"
-
-echo "=== E2E Headlamp Teardown ==="
-echo "  Namespace: $E2E_NAMESPACE"
-echo "  Release:   $E2E_RELEASE"
-
-echo "Removing Headlamp Deployment, Service, and ServiceAccount..."
-kubectl delete deployment "${E2E_RELEASE}" -n "$E2E_NAMESPACE" --ignore-not-found
-kubectl delete service "${E2E_RELEASE}" -n "$E2E_NAMESPACE" --ignore-not-found
-kubectl delete serviceaccount "${E2E_RELEASE}" -n "$E2E_NAMESPACE" --ignore-not-found
-
-echo "Cleaning up ConfigMap..."
-kubectl delete configmap headlamp-intel-gpu-plugin -n "$E2E_NAMESPACE" --ignore-not-found
-
-echo "Cleaning up test service account..."
-kubectl delete serviceaccount headlamp-e2e-test -n "$E2E_NAMESPACE" --ignore-not-found
-
-# Clean up .env.e2e if present
-if [ -f "$REPO_ROOT/.env.e2e" ]; then
-  rm "$REPO_ROOT/.env.e2e"
-  echo "Removed .env.e2e"
-fi
-
-echo ""
-echo "E2E teardown complete."