feat(us-016): auto-detect shard range from model config

Layer count is now fetched from the curated catalog (zero network calls
for known models) or via AutoConfig.from_pretrained() (~1 KB config.json
only) when model_id is given without --shard-start/--shard-end.

- model_catalog: add detect_num_layers(), two small Qwen models at top
- startup: _detect_num_layers() helper; shard range auto-derived
- wizard: show detected layer count for custom HF repos
- tests: 3 new tests for auto-shard; fix catalog-order assumptions

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

packages/node/meshnet_node/wizard.py

@@ -9,7 +9,7 @@ from pathlib import Path
 from typing import TYPE_CHECKING
 
 from .config import DEFAULTS, _DEFAULT_DOWNLOAD_DIR, _DEFAULT_TRACKER_URL, _DEFAULT_WALLET_PATH
-from .model_catalog import CURATED_MODELS, ModelPreset, browse_hf_hub
+from .model_catalog import CURATED_MODELS, ModelPreset, browse_hf_hub, detect_num_layers
 
 if TYPE_CHECKING:
     pass
@@ -239,6 +239,13 @@ def run_wizard(config_path_override=None) -> dict:
         if choice == len(CURATED_MODELS) + 1:
             repo = _browse_hf_interactive()
             if repo:
+                # Look up layer count for custom repo
+                print(f"  Checking {repo} config...", end=" ", flush=True)
+                layers = detect_num_layers(repo)
+                if layers:
+                    print(f"{layers} layers")
+                else:
+                    print("(layer count unknown — will detect on start)")
                 selected_repo = repo
                 selected_preset = None
         else:
@@ -254,7 +261,10 @@ def run_wizard(config_path_override=None) -> dict:
                     selected_repo = None
                     selected_preset = None
 
-    print(f"\n  ✓ Selected: {selected_repo}")
+    num_layers = (selected_preset.num_layers if selected_preset
+                  else detect_num_layers(selected_repo or ""))
+    layers_str = f"  {num_layers} layers" if num_layers else ""
+    print(f"\n  ✓ Selected: {selected_repo}{layers_str}")
 
     # Step 3b: Quantization
     quant = _ask_quant(gpus, selected_preset)