cluster recovery: fix resource limits and node1 memory

- nvidia quota: requests.memory 8Gi → 12Gi (unblock cuda-validator)
- calibre: startup probe initial_delay 60→120s, timeout 1→5s,
  wait_for_rollout=false (DOCKER_MODS install takes 10+ min)
- immich ML: memory 2Gi → 4Gi (OOMKilled loading CLIP models)

Also done outside TF (not in this commit):
- node1 VM: 16 GiB → 24 GiB RAM (Proxmox)
- tigera-operator: kubectl patch 128→256Mi
- nvidia-driver-daemonset: kubectl patch 1→4Gi memory
- kyverno reports-controller: kubectl patch 128→256Mi
- CNPG operator: kubectl rollout restart

stacks/calibre/main.tf

@@ -138,6 +138,7 @@ module "nfs_stacks_config" {
 # }
 
 resource "kubernetes_deployment" "calibre-web-automated" {
+  wait_for_rollout = false # DOCKER_MODS install takes 10+ min on every container start
   metadata {
     name      = "calibre-web-automated"
     namespace = kubernetes_namespace.calibre.metadata[0].name
@@ -205,7 +206,8 @@ resource "kubernetes_deployment" "calibre-web-automated" {
               path = "/"
               port = 8083
             }
-            initial_delay_seconds = 60
+            initial_delay_seconds = 120
+            timeout_seconds       = 5
             period_seconds        = 15
             failure_threshold     = 56
           }

stacks/immich/main.tf

@@ -513,10 +513,10 @@ resource "kubernetes_deployment" "immich-machine-learning" {
           resources {
             requests = {
               cpu    = "100m"
-              memory = "2Gi"
+              memory = "4Gi"
             }
             limits = {
-              memory = "2Gi"
+              memory = "4Gi"
               "nvidia.com/gpu" = "1"
             }
           }

stacks/platform/modules/nvidia/main.tf

@@ -27,7 +27,7 @@ resource "kubernetes_resource_quota" "nvidia_quota" {
     hard = {
       "limits.memory"   = "48Gi"
       "requests.cpu"    = "8"
-      "requests.memory" = "8Gi"
+      "requests.memory" = "12Gi"
       pods              = "40"
     }
   }