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.

tests/test_ollama_pull.py

@@ -0,0 +1,27 @@
+"""Unit tests for remote ollama_pull matching (stdlib helpers)."""
+
+from importlib.util import module_from_spec, spec_from_file_location
+from pathlib import Path
+
+_ROOT = Path(__file__).resolve().parents[1]
+_SPEC = spec_from_file_location(
+    "ollama_pull_remote",
+    _ROOT / "src" / "gpu_rent" / "remote" / "ollama_pull.py",
+)
+assert _SPEC and _SPEC.loader
+_mod = module_from_spec(_SPEC)
+_SPEC.loader.exec_module(_mod)
+already_have = _mod.already_have
+
+
+def test_exact_tag_only():
+    have = {"qwen2.5:3b", "qwen2.5:7b"}
+    assert already_have(have, "qwen2.5:7b")
+    assert not already_have(have, "qwen2.5:14b")
+    assert already_have(have, "qwen2.5:3b")
+
+
+def test_latest_alias():
+    assert already_have({"foo:latest"}, "foo")
+    assert already_have({"foo"}, "foo:latest")
+    assert not already_have({"foo:3b"}, "foo")

tests/test_tunnel_watch.py

@@ -38,12 +38,37 @@ def test_tunnel_forwards_swarm_only(monkeypatch):
     assert tunnel_forwards(Cfg()) == [(17801, 7801)]
 
 
-def test_tunnel_forwards_ollama(monkeypatch):
+def test_tunnel_forwards_prefers_cfg_over_stale_notes(monkeypatch):
     class Cfg:
         swarmui_local_port = 17801
-        llm_runtime = "ollama"
+        llm_runtime = "none"
         ollama_local_port = 17811
         llamacpp_local_port = 17812
 
-    monkeypatch.setattr("gpu_rent.tunnel.load_state", lambda: type("S", (), {"notes": {}})())
-    assert tunnel_forwards(Cfg()) == [(17801, 7801), (17811, 11434)]
+    monkeypatch.setattr(
+        "gpu_rent.tunnel.load_state",
+        lambda: type("S", (), {"notes": {"llm_runtime": "ollama"}})(),
+    )
+    assert tunnel_forwards(Cfg()) == [(17801, 7801)]
+
+
+def test_resolve_llm_notes_only_when_cfg_none(monkeypatch):
+    from gpu_rent.access_card import resolve_llm_runtime
+
+    class Cfg:
+        llm_runtime = "none"
+
+    monkeypatch.setattr(
+        "gpu_rent.access_card.load_state",
+        lambda: type("S", (), {"notes": {"llm_runtime": "ollama"}})(),
+    )
+    assert resolve_llm_runtime(Cfg()) == "ollama"
+
+    class Cfg2:
+        llm_runtime = "llamacpp"
+
+    monkeypatch.setattr(
+        "gpu_rent.access_card.load_state",
+        lambda: type("S", (), {"notes": {"llm_runtime": "ollama"}})(),
+    )
+    assert resolve_llm_runtime(Cfg2()) == "llamacpp"