Refactor CLI and LLM runtime handling for improved user experience

- Removed deprecated console usage in favor of structured logging functions for error handling and user prompts.
- Enhanced CLI prompts for LLM runtime and preset selection, utilizing menu helpers for better user interaction.
- Updated GPU pool scanning output with improved formatting and error indication for clarity.
- Refactored setup wizard to streamline LLM runtime and preset configuration, ensuring a more intuitive setup process.
- Improved documentation and user feedback in CLI outputs to enhance overall usability.

src/gpu_rent/setup_wizard.py

@@ -7,12 +7,13 @@ from collections.abc import Callable
 from pathlib import Path
 
 from gpu_rent.llm_runtime import (
-    LLAMACPP_PRESET_HELP,
-    PRESET_HELP,
     append_vars_llm_runtime,
     ensure_llamacpp_manifest_from_example,
     ensure_ollama_manifest_from_example,
+    llamacpp_preset_menu,
+    llm_runtime_menu,
     normalize_runtime,
+    ollama_preset_menu,
     write_llamacpp_models_preset,
     write_ollama_models_preset,
 )
@@ -28,6 +29,7 @@ from gpu_rent.paths import (
     vars_example_path,
     vars_path,
 )
+from gpu_rent.prompts import prompt_menu
 
 Log = Callable[[str], None]
 
@@ -74,9 +76,12 @@ def run_setup(
     runtime = llm
     if runtime is None:
         if ask:
-            runtime = ask(
-                "LLM runtime [none/ollama/llamacpp]",
-                "none",
+            runtime = prompt_menu(
+                "LLM runtime",
+                llm_runtime_menu(),
+                default="none",
+                ask=ask,
+                show=log,
             )
         else:
             runtime = "none"
@@ -87,8 +92,13 @@ def run_setup(
     if runtime == "ollama":
         preset = ollama_preset
         if preset is None and ask:
-            log(PRESET_HELP)
-            preset = ask("Ollama preset [recommended/light/stock/alt/empty]", "recommended")
+            preset = prompt_menu(
+                "Ollama preset",
+                ollama_preset_menu(include_keep=False),
+                default="recommended",
+                ask=ask,
+                show=log,
+            )
         if preset is None:
             preset = "recommended"
         if preset.strip().lower() in {"keep", "example", ""}:
@@ -98,12 +108,14 @@ def run_setup(
             write_ollama_models_preset(ollama_models_manifest_path(), preset)
             log(f"ollama-models.yaml пресет={preset}")
     elif runtime == "llamacpp":
-        preset = ollama_preset  # reuse --ollama-preset flag as generic LLM preset in setup
+        preset = ollama_preset
         if preset is None and ask:
-            log(LLAMACPP_PRESET_HELP)
-            preset = ask(
-                "llama.cpp GGUF preset [recommended/light/stock/empty]",
-                "recommended",
+            preset = prompt_menu(
+                "llama.cpp GGUF",
+                llamacpp_preset_menu(include_keep=False),
+                default="recommended",
+                ask=ask,
+                show=log,
             )
         if preset is None:
             preset = "recommended"