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/provision.py

@@ -260,13 +260,29 @@ def provision_llm(cfg: Config, host: str, log: Log) -> None:
     from gpu_rent.state import load_state, save_state
 
     runtime = normalize_runtime(cfg.llm_runtime)
+
+    def _stop_units(*names: str) -> None:
+        for name in names:
+            run_ssh(
+                cfg,
+                host,
+                f"sudo -n systemctl stop {name} 2>/dev/null; "
+                f"sudo -n systemctl disable {name} 2>/dev/null || true",
+                check=False,
+            )
+
+    # Always drop the other runtime so VRAM is not held by a leftover unit.
     if runtime == "none":
+        log("LLM: none — останавливаю gpu-rent-ollama / gpu-rent-llamacpp если были")
+        _stop_units("gpu-rent-ollama", "gpu-rent-llamacpp")
         st = load_state()
         st.notes = dict(st.notes or {})
         st.notes["llm_runtime"] = "none"
+        st.notes.pop("llm_error", None)
         save_state(st)
         return
     if runtime == "ollama":
+        _stop_units("gpu-rent-llamacpp")
         log("LLM: ставим/запускаем Ollama")
         run_script_sudo(
             cfg,
@@ -278,6 +294,9 @@ def provision_llm(cfg: Config, host: str, log: Log) -> None:
             log=log,
         )
         entries = parse_ollama_models(cfg.ollama_models_manifest)
+        defaults = [e.name for e in entries if e.default]
+        if defaults:
+            log(f"Ollama preferred: {defaults[0]}")
         names = [e.name for e in entries]
         if not names:
             log("ollama-models.yaml пуст — pull skip")
@@ -293,6 +312,7 @@ def provision_llm(cfg: Config, host: str, log: Log) -> None:
                 log=log,
             )
     elif runtime == "llamacpp":
+        _stop_units("gpu-rent-ollama")
         log("LLM: ставим/запускаем llama.cpp server")
         run_script_sudo(
             cfg,
@@ -306,6 +326,7 @@ def provision_llm(cfg: Config, host: str, log: Log) -> None:
     st = load_state()
     st.notes = dict(st.notes or {})
     st.notes["llm_runtime"] = runtime
+    st.notes.pop("llm_error", None)
     save_state(st)
 
 
@@ -337,15 +358,39 @@ def provision_vm(
     if cfg.pull_output:
         pull_tree(cfg, host, f"{DATA}/Output", cfg.local_output_dir, log)
     ensure_swarmui_running(cfg, host, log, restart=restart)
+
+    from gpu_rent.state import load_state, save_state
+
     try:
         provision_llm(cfg, host, log)
     except Exception as exc:
-        log(f"LLM runtime: {exc}")
+        st = load_state()
+        st.notes = dict(st.notes or {})
+        st.notes["llm_error"] = str(exc)[:500]
+        # Do not claim success — leave previous notes.llm_runtime or clear to none.
+        st.notes["llm_runtime"] = "none"
+        save_state(st)
+        raise CloudError(f"LLM runtime: {exc}") from exc
+
     if conn is not None and server_id:
         try:
             arm_idle_killer(cfg, host, conn, server_id, log)
+            st = load_state()
+            st.notes = dict(st.notes or {})
+            st.notes["idle_killer"] = "armed"
+            st.notes.pop("idle_killer_error", None)
+            save_state(st)
         except GpuRentError as exc:
             log(f"idle-killer: {exc}")
+            st = load_state()
+            st.notes = dict(st.notes or {})
+            st.notes["idle_killer"] = "failed"
+            st.notes["idle_killer_error"] = str(exc)[:500]
+            save_state(st)
+            log(
+                "⚠ idle-killer НЕ вооружён — GPU может тарифицироваться без авто-stop. "
+                "См. status / docs/setup.md"
+            )
     log("SwarmUI слушает 127.0.0.1:7801 — gpu-rent tunnel")
     from gpu_rent.llm_runtime import normalize_runtime