dist/entrypoint.sh

@@ -16,28 +16,26 @@ echo "[entrypoint] Starting k3s server (embedded soul-demo orchestrator)..."
 # --disable metrics-server: saves ~50MB RAM
 # --write-kubeconfig-mode=644: allow non-root reads
 # --data-dir: use the pre-chowned dir
+# --flannel-iface=eth0: explicitly set the network interface.
+#   Cloud Run gen2 provides eth0 but k3s default IP detection walks the routing
+#   table looking for a default route, which fails in Cloud Run's network sandbox.
+#   Pinning to eth0 bypasses that detection and lets k3s bind correctly.
 k3s server \
   --disable traefik \
   --disable servicelb \
   --disable metrics-server \
   --write-kubeconfig-mode=644 \
   --data-dir /var/lib/rancher/k3s \
-  --node-name soul-node &
+  --node-name soul-node \
+  --flannel-iface=eth0 &
 
 K3S_PID=$!
 
-echo "[entrypoint] Waiting for k3s to become ready..."
+# Start neuron-web immediately — do NOT block on k3s becoming ready.
-until k3s kubectl get nodes --no-headers 2>/dev/null | grep -q "Ready"; do
+# Cloud Run's startup probe requires port 8080 to be listening within the
-  sleep 2
+# startup timeout. k3s may take 30-60s to initialise; blocking here causes
-done
+# probe failures and container termination before neuron-web ever starts.
-echo "[entrypoint] k3s ready. soul-demo Deployment will be applied automatically from manifests."
+# soul-demo becomes available asynchronously once k3s is ready. neuron-web
-
+# handles soul-demo being temporarily unavailable gracefully.
-# Wait for soul-demo pod to be Running before starting neuron-web
+echo "[entrypoint] Starting neuron-web on port ${PORT:-8080} (k3s initialising in background)..."
-echo "[entrypoint] Waiting for soul-demo pod..."
-until k3s kubectl get pods -l app=soul-demo --no-headers 2>/dev/null | grep -q "Running"; do
-  sleep 3
-done
-echo "[entrypoint] soul-demo is running."
-
-echo "[entrypoint] Starting neuron-web on port ${PORT:-8080}..."
 exec /usr/local/bin/neuron-web