Update configuration and documentation for LLM support and local watchdog

- Added `ollama-models.yaml` to .gitignore and implemented logic to copy it in gpu-rent.ps1 and gpu-rent.sh.
- Enhanced env.example to include new variables for LLM runtime options and local watchdog configuration.
- Updated CLI commands to support LLM options during setup and execution, including new flags for Ollama and llama.cpp.
- Improved documentation in cli.md and README.md to reflect changes in LLM integration and local watchdog functionality.
- Adjusted architecture and decisions documentation to clarify the role of LLMs and local watchdog in the system.

tests/test_tunnel_watch.py

@@ -1,4 +1,4 @@
-from gpu_rent.tunnel import decide_watch
+from gpu_rent.tunnel import decide_watch, tunnel_forwards
 
 
 def test_decide_ok_active():
@@ -25,3 +25,25 @@ def test_decide_exit_error():
 def test_decide_exit_missing():
     d = decide_watch(None, tunnel_alive=False)
     assert d.kind == "exit"
+
+
+def test_tunnel_forwards_swarm_only(monkeypatch):
+    class Cfg:
+        swarmui_local_port = 17801
+        llm_runtime = "none"
+        ollama_local_port = 17811
+        llamacpp_local_port = 17812
+
+    monkeypatch.setattr("gpu_rent.tunnel.load_state", lambda: type("S", (), {"notes": {}})())
+    assert tunnel_forwards(Cfg()) == [(17801, 7801)]
+
+
+def test_tunnel_forwards_ollama(monkeypatch):
+    class Cfg:
+        swarmui_local_port = 17801
+        llm_runtime = "ollama"
+        ollama_local_port = 17811
+        llamacpp_local_port = 17812
+
+    monkeypatch.setattr("gpu_rent.tunnel.load_state", lambda: type("S", (), {"notes": {}})())
+    assert tunnel_forwards(Cfg()) == [(17801, 7801), (17811, 11434)]