fix hermes liveness probe

platform-engineer/cron-seed.yaml

@@ -24,18 +24,37 @@ spec:
       restartPolicy: OnFailure
       containers:
       - name: seed
-        image: bitnami/kubectl:1.35
+        # alpine is tiny and always available; we install curl + download the
+        # right-arch kubectl binary at runtime (bitnami/kubectl tags are
+        # inconsistent across versions, so we avoid depending on them).
+        image: alpine:3.20
         command: ["sh", "-c"]
         args:
         - |
           set -e
+
+          # Install curl, then download kubectl for this node's architecture.
+          apk add --no-cache curl
+          ARCH=$(uname -m)
+          case "$ARCH" in
+            x86_64)   KARCH=amd64 ;;
+            aarch64)  KARCH=arm64 ;;
+            armv7l)   KARCH=arm ;;
+            *) echo "unsupported arch: $ARCH" >&2; exit 1 ;;
+          esac
+          echo "Downloading kubectl for linux/$KARCH ..."
+          curl -fsSL -o /usr/local/bin/kubectl \
+            "https://dl.k8s.io/release/v1.35.0/bin/linux/${KARCH}/kubectl"
+          chmod +x /usr/local/bin/kubectl
+          kubectl version --client
+
           echo "Waiting for hermes pod to be Ready..."
           kubectl -n platform-engineer wait --for=condition=Ready pod -l app=hermes --timeout=300s || true
 
           POD=$(kubectl -n platform-engineer get pod -l app=hermes -o jsonpath='{.items[0].metadata.name}')
           echo "Using pod: $POD"
 
-          exists() { kubectl -n platform-engineer exec "$POD" -- hermes cron list 2>/dev/null | grep -qi "name=$1\| $1 "; }
+          exists() { kubectl -n platform-engineer exec "$POD" -- hermes cron list 2>/dev/null | grep -qi " $1 "; }
 
           create() {
             name="$1"; schedule="$2"; deliver="$3"; prompt="$4"

platform-engineer/deployment.yaml

@@ -128,12 +128,17 @@ spec:
             memory: "2Gi"
             cpu: "1000m"
         livenessProbe:
-          httpGet:
+          # Probe the dashboard port (9119, always enabled via HERMES_DASHBOARD=1
-            path: /health
+          # and binds 0.0.0.0). The gateway API on 8642 is off by default
-            port: 8642
+          # (API_SERVER_ENABLED not set), so 9119 is the reliable liveness signal.
-          initialDelaySeconds: 60
+          # s6 auto-restarts the gateway itself; this probe only catches a wedged
+          # container.
+          tcpSocket:
+            port: 9119
+          initialDelaySeconds: 90
           periodSeconds: 30
-          failureThreshold: 3
+          timeoutSeconds: 5
+          failureThreshold: 5
         securityContext:
           allowPrivilegeEscalation: false