Refactor LLM runtime handling and enhance CLI documentation

- Updated `resolve_llm_runtime` to prioritize live configuration over legacy notes, ensuring accurate runtime resolution.
- Enhanced `tunnel_forwards` to prefer current configuration for LLM runtime, improving tunnel setup logic.
- Improved idle-killer logic to handle stale markers and provide clearer warnings in the status output.
- Updated CLI documentation in `cli.md` to reflect changes in command behavior and runtime handling.
- Enhanced tests to validate new runtime resolution logic and ensure proper handling of configuration states.

src/gpu_rent/remote/ollama_pull.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import json
 import subprocess
 import sys
+import time
 from pathlib import Path
 
 JOBS = Path("/tmp/gpu-rent-ollama-models.json")
@@ -12,6 +13,7 @@ MARKER = Path("/mnt/swarm_data/.gpu-rent-ollama-pulling")
 
 
 def listed() -> set[str]:
+    """Exact tags from `ollama list` (NAME column), e.g. qwen2.5:7b."""
     try:
         out = subprocess.check_output(["ollama", "list"], text=True, stderr=subprocess.DEVNULL)
     except (subprocess.CalledProcessError, FileNotFoundError):
@@ -23,11 +25,21 @@ def listed() -> set[str]:
         parts = line.split()
         if parts:
             names.add(parts[0])
-            # also bare name without tag
-            names.add(parts[0].split(":")[0])
     return names
 
 
+def already_have(have: set[str], wanted: str) -> bool:
+    """Exact tag match only — qwen2.5:3b must not satisfy qwen2.5:7b."""
+    if wanted in have:
+        return True
+    # ollama list sometimes omits :latest
+    if ":" not in wanted and f"{wanted}:latest" in have:
+        return True
+    if wanted.endswith(":latest") and wanted.rsplit(":", 1)[0] in have:
+        return True
+    return False
+
+
 def main() -> int:
     if not JOBS.is_file():
         print("no jobs file", file=sys.stderr)
@@ -38,23 +50,20 @@ def main() -> int:
         return 0
     have = listed()
     MARKER.parent.mkdir(parents=True, exist_ok=True)
-    MARKER.write_text("1\n", encoding="utf-8")
+    MARKER.write_text(f"{int(time.time())}\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
+            if already_have(have, name):
+                print(f"[{i}/{len(models)}] уже есть {name}")
+                continue
             print(f"[{i}/{len(models)}] ollama pull {name}")
             try:
                 subprocess.check_call(["ollama", "pull", name])
+                have.add(name)
             except subprocess.CalledProcessError as exc:
                 failed += 1
                 print(f"FAIL pull {name}: {exc}", file=sys.stderr)