Refactor LLM configuration to remove llamacpp support

- Removed references to llamacpp from configuration files, scripts, and documentation, streamlining the LLM setup process to focus solely on Ollama.
- Updated environment variables and paths to eliminate llamacpp-related entries, ensuring clarity in the configuration.
- Adjusted CLI commands and help messages to reflect the removal of llamacpp, enhancing user experience and reducing confusion.
- Revised documentation to provide clear guidance on using Ollama exclusively, including updates to setup instructions and runtime options.

tests/test_llm_only.py

@@ -15,13 +15,12 @@ def test_parse_enable_swarmui_workload(monkeypatch):
 def test_tunnel_forwards_llm_only(monkeypatch):
     class Cfg:
         swarmui_local_port = 17801
-        llm_runtime = "llamacpp"
+        llm_runtime = "ollama"
         enable_swarmui = False
         ollama_local_port = 17811
-        llamacpp_local_port = 17812
 
     monkeypatch.setattr("gpu_rent.tunnel.load_state", lambda: type("S", (), {"notes": {}})())
-    assert tunnel_forwards(Cfg()) == [(17812, 8080)]
+    assert tunnel_forwards(Cfg()) == [(17811, 11434)]
 
 
 def test_access_links_llm_only(monkeypatch):
@@ -29,10 +28,9 @@ def test_access_links_llm_only(monkeypatch):
 
     class Cfg:
         swarmui_local_port = 17801
-        llm_runtime = "llamacpp"
+        llm_runtime = "ollama"
         enable_swarmui = False
         ollama_local_port = 17811
-        llamacpp_local_port = 17812
 
     monkeypatch.setattr(
         "gpu_rent.access_card.load_state",
@@ -40,5 +38,5 @@ def test_access_links_llm_only(monkeypatch):
     )
     labels = [x.label for x in collect_access_links(Cfg(), tunneled=True)]
     assert "SwarmUI UI" not in labels
-    assert "llama.cpp" in labels
+    assert "Ollama API" in labels
     assert mcp_snippet_lines(Cfg())[0].startswith("#")