Update LLM support for llama.cpp and enhance configuration management

- Added support for `llamacpp-models.yaml` in `.gitignore` and implemented logic to copy it in `gpu-rent.ps1` and `gpu-rent.sh`.
- Enhanced CLI to prompt for llama.cpp model presets during setup and execution, improving user experience.
- Updated configuration handling to include `llamacpp_models_manifest` and related functions for managing llama.cpp models.
- Improved documentation in `cli.md` and `llm.md` to reflect changes in llama.cpp integration and model management.
- Refactored provisioning logic to handle llama.cpp model downloads and configurations effectively.

src/gpu_rent/session.py

@@ -33,7 +33,7 @@ from gpu_rent.inventory import (
     pick_volume_type,
     resolve_flavor,
 )
-from gpu_rent.ux import print_up_preview
+from gpu_rent.ux import print_up_preview, prompt_server_plan
 from gpu_rent.pools import best_offer, format_pool_scan, scan_pools
 from gpu_rent.lock import SessionLock
 from gpu_rent.os_client import (
@@ -173,6 +173,7 @@ def cmd_up(
     adopt: bool = False,
     update: bool | None = None,
     confirm: Callable[[str], bool] | None = None,
+    ask: Callable[[str, str], str] | None = None,
     log: Log = _log_default,
 ) -> SessionState:
     do_update = cfg.update_git if update is None else update
@@ -291,6 +292,29 @@ def cmd_up(
 
         print_up_preview(cfg, flavors, picked=picked, spot=spot, log=log)
 
+        if not yes and ask is not None and flavor is None:
+            try:
+                plan = prompt_server_plan(
+                    cfg,
+                    flavors,
+                    picked=picked,
+                    spot=spot,
+                    ask=ask,
+                    confirm=confirm,
+                )
+            except ValueError as exc:
+                raise GpuRentError(str(exc)) from exc
+            picked = plan.flavor
+            spot = plan.spot
+            if plan.data_gb != cfg.data_volume_size_gb:
+                from dataclasses import replace
+
+                cfg = replace(cfg, data_volume_size_gb=plan.data_gb)
+            log(
+                f"выбрано: {'preemptible ' if spot else ''}{picked.name}, "
+                f"data {cfg.data_volume_size_gb} GB"
+            )
+
         prompt = (
             f"Создать {'preemptible ' if spot else ''}GPU {picked.name} "
             f"в {cfg.gpu_rent_az}, образ {getattr(image, 'name', image.id)}, "