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/ollama_pull.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+"""Pull Ollama models from a JSON list. Stdlib only. Runs on the VM."""
+from __future__ import annotations
+
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+JOBS = Path("/tmp/gpu-rent-ollama-models.json")
+MARKER = Path("/mnt/swarm_data/.gpu-rent-ollama-pulling")
+
+
+def listed() -> set[str]:
+    try:
+        out = subprocess.check_output(["ollama", "list"], text=True, stderr=subprocess.DEVNULL)
+    except (subprocess.CalledProcessError, FileNotFoundError):
+        return set()
+    names: set[str] = set()
+    for i, line in enumerate(out.splitlines()):
+        if i == 0 and line.lower().startswith("name"):
+            continue
+        parts = line.split()
+        if parts:
+            names.add(parts[0])
+            # also bare name without tag
+            names.add(parts[0].split(":")[0])
+    return names
+
+
+def main() -> int:
+    if not JOBS.is_file():
+        print("no jobs file", file=sys.stderr)
+        return 1
+    models = json.loads(JOBS.read_text(encoding="utf-8"))
+    if not isinstance(models, list) or not models:
+        print("ollama pull: пустой список — skip")
+        return 0
+    have = listed()
+    MARKER.parent.mkdir(parents=True, exist_ok=True)
+    MARKER.write_text("1\n", encoding="utf-8")
+    failed = 0
+    try:
+        for i, name in enumerate(models, 1):
+            name = str(name).strip()
+            if not name:
+                continue
+            bare = name.split(":")[0]
+            if name in have or bare in have:
+                # Prefer exact tag match when possible
+                exact = any(h == name or h.startswith(name + ":") or name.startswith(h) for h in have)
+                if name in have or exact:
+                    print(f"[{i}/{len(models)}] уже есть {name}")
+                    continue
+            print(f"[{i}/{len(models)}] ollama pull {name}")
+            try:
+                subprocess.check_call(["ollama", "pull", name])
+            except subprocess.CalledProcessError as exc:
+                failed += 1
+                print(f"FAIL pull {name}: {exc}", file=sys.stderr)
+    finally:
+        MARKER.unlink(missing_ok=True)
+    if failed:
+        return 1
+    print("ollama pull ok")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())