Switch all Ollama models to gemma3n:e4b on node-197 GPU

Bake-off results: gemma3n:e4b (80.6% cmd match, 100% safety, 5.9s)
outperforms qwen3-coder:30b on all metrics. Updated paper, shrink,
and langgraph gateway configs. Frees steel141 for LoRA training.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

mc_aigod_paper.json

@@ -5,9 +5,9 @@
   "rcon_host": "127.0.0.1",
   "rcon_port": 25577,
   "rcon_password": "REDACTED_RCON",
-  "ollama_url": "http://192.168.0.141:11434",
-  "model": "gemma3:12b",
-  "command_model": "qwen3-coder:30b",
+  "ollama_url": "http://192.168.0.179:11434",
+  "model": "gemma3n:e4b",
+  "command_model": "gemma3n:e4b",
   "temperature": 0.85,
   "max_tokens": 700,
   "use_langgraph_gateway": true,