feat: hermes auto-update cron with staggered offsets (+10min per node)

host_vars/artemis.yml

@@ -29,3 +29,6 @@ hermes_config:
   provider: openrouter
   model: openai/gpt-4o-mini
   context_length: 128000
+
+# Hermes auto-update offset (minutes from hour mark)
+hermes_update_offset: 0

host_vars/bones.yml

@@ -25,3 +25,6 @@ ollama_models:
 # Node-specific vars
 bones_storage: "256GB SSD"
 jvm_heap: "512m"
+
+# Hermes auto-update offset (minutes from hour mark)
+hermes_update_offset: 30

host_vars/hulkbuster.yml

@@ -6,9 +6,11 @@ gpu_type: nvidia
 gpu_model: "RTX 4070"
 vram_mb: 12282
 
-# GPU-specific tools (not drivers — Mark44 uses proprietary NVIDIA package)
+# GPU-specific packages
 extra_packages:
-  - nvtop                     # GPU monitoring
+  - nvidia-driver             # NVIDIA driver (if not already installed via proprietary)
+  - cuda-toolkit              # CUDA toolkit for ML workloads
+  - nvtop                     # GPU monitoring (better than nvidia-smi for live view)
   - nethogs                   # Network per-process monitoring
   - iotop                     # I/O per-process monitoring
 
@@ -17,6 +19,7 @@ ollama_models:
   - gemma4:e4b               # Already pulled — keep it
   - qwen2.5-coder:14b        # Primary coding model
   - qwen2.5:14b             # General purpose large model
+  - mistral:7b               # Fallback fast model
 
 # Services
 managed_services:
@@ -30,3 +33,6 @@ managed_services:
 # Ollama port override (standard)
 ollama_port: 11434
 open_webui_port: 8080
+
+# Hermes auto-update offset (minutes from hour mark)
+hermes_update_offset: 10

host_vars/mark5.yml

@@ -28,3 +28,6 @@ managed_services:
 
 # Ollama port
 ollama_port: 11434
+
+# Hermes auto-update offset (minutes from hour mark)
+hermes_update_offset: 20

host_vars/nebuchadnezzar.yml

@@ -0,0 +1,3 @@
+
+# Hermes auto-update offset (minutes from hour mark)
+hermes_update_offset: 40