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.

src/gpu_rent/config.py

@@ -16,10 +16,12 @@ from gpu_rent.paths import (
     extensions_manifest_path,
     migrate_legacy_if_needed,
     models_manifest_path,
+    ollama_models_manifest_path,
     runtime_dir,
     vars_path,
 )
 from gpu_rent.varsfile import apply_vars_file
+from gpu_rent.llm_runtime import normalize_runtime
 
 
 def _as_bool(value: str | None, default: bool) -> bool:
@@ -80,6 +82,11 @@ class Config:
     swarmui_image: str
     update_git: bool
 
+    llm_runtime: str
+    ollama_models_manifest: Path
+    ollama_local_port: int
+    llamacpp_local_port: int
+
     default_flavor_id: str
     flavor_preference: tuple[str, ...]
     flavor_fallback: bool
@@ -146,6 +153,15 @@ def load_config(*, require_auth: bool = True) -> Config:
         (os.environ.get("EXTENSIONS_MANIFEST") or "").strip()
         or str(extensions_manifest_path())
     ).expanduser()
+    ollama_manifest = Path(
+        (os.environ.get("OLLAMA_MODELS_MANIFEST") or "").strip()
+        or str(ollama_models_manifest_path())
+    ).expanduser()
+
+    try:
+        llm_runtime = normalize_runtime(os.environ.get("LLM_RUNTIME"))
+    except ValueError:
+        llm_runtime = "none"
 
     def _dir(env_name: str, folder: str) -> Path:
         raw = (os.environ.get(env_name) or "").strip()
@@ -187,6 +203,10 @@ def load_config(*, require_auth: bool = True) -> Config:
         swarmui_local_port=_as_int(os.environ.get("SWARMUI_LOCAL_PORT"), 17801),
         swarmui_image=(os.environ.get("SWARMUI_IMAGE") or "").strip(),
         update_git=_as_bool(os.environ.get("UPDATE_GIT"), True),
+        llm_runtime=llm_runtime,
+        ollama_models_manifest=ollama_manifest,
+        ollama_local_port=_as_int(os.environ.get("OLLAMA_LOCAL_PORT"), 17811),
+        llamacpp_local_port=_as_int(os.environ.get("LLAMACPP_LOCAL_PORT"), 17812),
         default_flavor_id=(os.environ.get("DEFAULT_FLAVOR_ID") or "").strip(),
         flavor_preference=_csv(
             os.environ.get("FLAVOR_PREFERENCE"),