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/cli.py

@@ -33,7 +33,7 @@ if sys.platform == "win32":
             pass
 
 app = typer.Typer(
-    invoke_without_command=True,
+    no_args_is_help=True,
     pretty_exceptions_enable=False,
     add_completion=False,
     help="Прерываемый GPU Selectel + SwarmUI на localhost:17801. Сначала: gpu-rent setup / doctor. Ключи: docs/setup.md",
@@ -43,16 +43,12 @@ console = Console(highlight=False, legacy_windows=False)
 _DEBUG = False
 
 
-@app.callback(invoke_without_command=True)
+@app.callback()
 def _root(
-    ctx: typer.Context,
     debug: bool = typer.Option(False, "--debug", help="Показать traceback"),
 ) -> None:
     global _DEBUG
     _DEBUG = debug
-    if ctx.invoked_subcommand is None:
-        # Без подкоманды → interactive up (как «запуск без параметров»).
-        ctx.invoke(up)
 
 
 def _die(exc: BaseException) -> None:
@@ -62,7 +58,24 @@ def _die(exc: BaseException) -> None:
     raise typer.Exit(1)
 
 
-def _print_checks(checks) -> int:
+def _print_checks(checks, *, quiet: bool = False) -> int:
+    failed = blocking_failed(checks)
+    if quiet:
+        if failed:
+            console.print("[red]doctor: блокирующие проблемы[/red]")
+            for check in failed:
+                console.print(f"  • {check.name}: {check.detail}")
+            _print_next_steps(failed)
+            return 1
+        warns = [c for c in checks if not c.ok and not c.blocking]
+        if warns:
+            console.print(f"[yellow]doctor ok[/yellow] ({len(checks)}), предупреждения:")
+            for check in warns:
+                console.print(f"  • {check.name}: {check.detail}")
+        else:
+            console.print(f"[green]doctor ok[/green] ({len(checks)} проверок)")
+        return 0
+
     table = Table(title="gpu-rent doctor", show_lines=False)
     table.add_column("ok")
     table.add_column("проверка")
@@ -73,7 +86,6 @@ def _print_checks(checks) -> int:
         block = "да" if check.blocking else "нет"
         table.add_row(mark, check.name, block, check.detail)
     console.print(table)
-    failed = blocking_failed(checks)
     if failed:
         console.print("\n[red]Сессию начинать нельзя.[/red] См. docs/setup.md")
         _print_next_steps(failed)
@@ -246,6 +258,12 @@ def status() -> None:
             from gpu_rent.idle_killer import killer_status_lines
 
             table.add_row("idle-killer", "; ".join(killer_status_lines(cfg, state.floating_ip)))
+            note_k = (state.notes or {}).get("idle_killer")
+            if note_k == "failed":
+                err = (state.notes or {}).get("idle_killer_error") or ""
+                table.add_row("idle-killer arm", f"[red]FAILED[/red] {err}"[:120])
+            elif note_k == "armed":
+                table.add_row("idle-killer arm", "ok (в сессии)")
         except GpuRentError as exc:
             table.add_row("диск used/free", f"SSH: {exc}")
             table.add_row("idle-killer", "нет SSH")
@@ -256,16 +274,17 @@ def status() -> None:
     from gpu_rent.local_watchdog import watchdog_status_lines
 
     table.add_row("local-watchdog", "; ".join(watchdog_status_lines()))
-    from gpu_rent.llm_runtime import normalize_runtime
+    from gpu_rent.access_card import resolve_llm_runtime
 
-    rt = normalize_runtime(cfg.llm_runtime)
+    rt = resolve_llm_runtime(cfg)
     noted = (state.notes or {}).get("llm_runtime")
-    if noted:
-        rt = f"{rt} (сессия: {noted})"
-    table.add_row(
-        "LLM",
-        f"{rt}; ollama :{cfg.ollama_local_port} / llamacpp :{cfg.llamacpp_local_port}",
-    )
+    llm_err = (state.notes or {}).get("llm_error")
+    detail = f"{rt}; ollama :{cfg.ollama_local_port} / llamacpp :{cfg.llamacpp_local_port}"
+    if noted and noted != rt:
+        detail += f" (notes: {noted})"
+    if llm_err:
+        detail += f" [red]err: {llm_err[:80]}[/red]"
+    table.add_row("LLM", detail)
 
     if cfg.auth_ok:
         try:
@@ -296,14 +315,9 @@ def open(
     cfg = load_config(require_auth=False)
     if llm:
         from gpu_rent.llm_runtime import normalize_runtime
+        from gpu_rent.access_card import resolve_llm_runtime
 
-        runtime = normalize_runtime(cfg.llm_runtime)
-        state = load_state()
-        if (state.notes or {}).get("llm_runtime"):
-            try:
-                runtime = normalize_runtime(str(state.notes["llm_runtime"]))
-            except ValueError:
-                pass
+        runtime = resolve_llm_runtime(cfg)
         if runtime == "ollama":
             port = cfg.ollama_local_port
         elif runtime == "llamacpp":
@@ -381,6 +395,12 @@ def up(
         "--no-update",
         help="Не делать git pull SwarmUI и установленных extensions",
     ),
+    verbose: bool = typer.Option(
+        False,
+        "--verbose",
+        "-v",
+        help="Полный doctor-таблица на up (по умолчанию кратко)",
+    ),
     llm: Optional[str] = typer.Option(
         None, "--llm", help="none|ollama|llamacpp (override LLM_RUNTIME)"
     ),
@@ -401,7 +421,7 @@ def up(
         from gpu_rent.paths import vars_path
 
         checks = run_doctor()
-        code = _print_checks(checks)
+        code = _print_checks(checks, quiet=not verbose)
         if code != 0:
             raise typer.Exit(1)
         cfg = load_config(require_auth=True)