From 175d3ec6a2ddb9d2f4bf758c8e8ac615ce711ba4 Mon Sep 17 00:00:00 2001
From: Gandalf the Greybeard <gandalf@privilegedescalation.github>
Date: Tue, 24 Mar 2026 16:40:30 +0000
Subject: [PATCH] fix(e2e): clean-delete existing deployment before redeploy
 for guaranteed fresh pod
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

kubectl apply without prior deletion patches in place: if the pod spec is
unchanged between runs, no rollout is triggered and a potentially degraded
pod from a prior run keeps serving. This caused the auth.setup.ts timeout
(waiting for the "use a token" button) even when no concurrent runs were
present — the headlamp-e2e pod was in an inconsistent state from a previous
run that didn't tear down cleanly.

Changes:
- deploy-e2e-headlamp.sh: delete Deployment, Service, and ServiceAccount
  (with --wait) before applying, guaranteeing a fresh pod each run
- auth.setup.ts: add explicit waitFor({ state: 'visible', timeout: 15_000 })
  before the "use a token" button click, so failures surface at 15 s with a
  clear locator error rather than silently timing out at 60 s

Fixes the pre-existing infra issue blocking PR#110.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 e2e/auth.setup.ts              |  8 ++++++--
 scripts/deploy-e2e-headlamp.sh | 10 ++++++++++
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/e2e/auth.setup.ts b/e2e/auth.setup.ts
index 2bc6d1d..2b4ecb9 100644
--- a/e2e/auth.setup.ts
+++ b/e2e/auth.setup.ts
@@ -45,8 +45,12 @@ async function authenticateWithToken(page: Page, token: string): Promise<void> {
   await page.waitForURL(/\/(login|token)$/);
 
   if (page.url().includes('/login')) {
-    // OIDC login page — click "use a token" to reach token auth
-    await page.getByRole('button', { name: /use a token/i }).click();
+    // OIDC login page — click "use a token" to reach token auth.
+    // Wait explicitly before clicking so failures surface at 15 s
+    // with a clear message rather than silently timing out at 60 s.
+    const useTokenBtn = page.getByRole('button', { name: /use a token/i });
+    await useTokenBtn.waitFor({ state: 'visible', timeout: 15_000 });
+    await useTokenBtn.click();
     await page.waitForURL('**/token');
   }
 
diff --git a/scripts/deploy-e2e-headlamp.sh b/scripts/deploy-e2e-headlamp.sh
index 6186d5a..1b19583 100755
--- a/scripts/deploy-e2e-headlamp.sh
+++ b/scripts/deploy-e2e-headlamp.sh
@@ -58,6 +58,16 @@ kubectl create configmap headlamp-polaris-plugin \
   --from-file="$DIST_DIR" \
   --from-file=package.json="$REPO_ROOT/package.json"
 
+# --- Tear down any existing E2E deployment for a clean start ---
+# kubectl apply without prior deletion only patches in-place: if the pod spec is
+# unchanged between runs, no new rollout is triggered and a degraded pod keeps
+# serving. Delete first to guarantee a fresh pod regardless of prior state.
+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..."
-- 
2.52.0