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_verify_stack.py

@@ -7,19 +7,18 @@ class _Cfg:
     llm_runtime = "none"
     swarmui_local_port = 17801
     ollama_local_port = 17811
-    llamacpp_local_port = 17812
 
 
 def test_expected_services_swarm_only():
-    assert _expected_services(_Cfg()) == (True, False, False)
+    assert _expected_services(_Cfg()) == (True, False)
 
 
 def test_expected_services_llm_only():
     class C:
         enable_swarmui = False
-        llm_runtime = "llamacpp"
+        llm_runtime = "ollama"
 
-    assert _expected_services(C()) == (False, False, True)
+    assert _expected_services(C()) == (False, True)
 
 
 def test_verify_stack_local_empty_when_nothing():
@@ -28,7 +27,6 @@ def test_verify_stack_local_empty_when_nothing():
         llm_runtime = "none"
         swarmui_local_port = 17801
         ollama_local_port = 17811
-        llamacpp_local_port = 17812
 
     logs: list[str] = []
     assert verify_stack_local(C(), logs.append, timeout=0.1) == []
@@ -40,7 +38,6 @@ def test_verify_stack_local_fails_closed_port(monkeypatch):
         llm_runtime = "ollama"
         swarmui_local_port = 17801
         ollama_local_port = 17999
-        llamacpp_local_port = 17812
 
     monkeypatch.setattr(
         "gpu_rent.ready._tcp_ok", lambda port, host="127.0.0.1", timeout=0.8: False
@@ -157,7 +154,7 @@ def test_verify_gpu_env_llm_only_skips_torch_requirement(monkeypatch):
 
     class C:
         enable_swarmui = False
-        llm_runtime = "llamacpp"
+        llm_runtime = "ollama"
 
     payload = {
         "ok": True,