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/remote/idle_killer.py

@@ -88,6 +88,46 @@ def swarm_busy(swarm_url: str, timeout: float = 8.0) -> tuple[bool, str]:
     return False, f"idle backend={bstat}"
 
 
+def llm_busy(timeout: float = 3.0) -> tuple[bool, str]:
+    """Ollama pull / loaded models or llama.cpp with a model count as busy."""
+    if (DATA / ".gpu-rent-ollama-pulling").is_file():
+        return True, "ollama pulling"
+    ctx = ssl.create_default_context()
+    # Ollama: any running model
+    try:
+        req = urllib.request.Request("http://127.0.0.1:11434/api/ps", method="GET")
+        with urllib.request.urlopen(req, timeout=timeout, context=ctx) as resp:
+            data = json.loads(resp.read().decode("utf-8"))
+        models = data.get("models") or []
+        if models:
+            names = ",".join(str(m.get("name") or "?") for m in models[:3])
+            return True, f"ollama running {names}"
+    except (urllib.error.URLError, urllib.error.HTTPError, TimeoutError, json.JSONDecodeError, OSError):
+        pass
+    # llama.cpp OpenAI models endpoint — if server up and lists a model, treat lightly:
+    # only busy if /health ok AND we recently had activity is hard; use loaded via props.
+    try:
+        req = urllib.request.Request("http://127.0.0.1:8080/health", method="GET")
+        with urllib.request.urlopen(req, timeout=timeout, context=ctx) as resp:
+            if getattr(resp, "status", 200) == 200:
+                # Server alive with a model is OK for idle unless slots busy — skip kill only
+                # when props show n_slots_in_use if available.
+                try:
+                    req2 = urllib.request.Request("http://127.0.0.1:8080/props", method="GET")
+                    with urllib.request.urlopen(req2, timeout=timeout, context=ctx) as resp2:
+                        props = json.loads(resp2.read().decode("utf-8"))
+                    in_use = int(props.get("total_slots") or 0) - int(
+                        props.get("available_slots") or props.get("total_slots") or 0
+                    )
+                    if in_use > 0:
+                        return True, f"llamacpp slots_in_use={in_use}"
+                except Exception:
+                    pass
+    except (urllib.error.URLError, urllib.error.HTTPError, TimeoutError, OSError):
+        pass
+    return False, "llm idle"
+
+
 def keystone_token(creds: dict) -> tuple[str, str]:
     """Return (token, compute_url)."""
     auth = {
@@ -189,6 +229,12 @@ def main() -> int:
         log(f"busy: {detail}")
         return 0
 
+    llm_is_busy, llm_detail = llm_busy()
+    if llm_is_busy:
+        write_ts(IDLE_SINCE, None)
+        log(f"busy: {llm_detail}")
+        return 0
+
     idle_minutes = float(creds.get("idle_minutes") or 30)
     since = read_ts(IDLE_SINCE)
     if since is None: