Fix remaining validate_model_name parameter order inconsistency

Address code review feedback from Gemini Code Assist bot:
- Fix parameter order in validate_model_name method (line 256)
- Ensure consistent use of original model name for restriction validation
- All is_allowed() calls now properly use (provider, original_name, resolved_name)

This completes the fix for GOOGLE_ALLOWED_MODELS shorthand restriction validation.

🤖 Generated with [Claude Code](https://claude.ai/code)

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

providers/gemini.py

@@ -222,7 +222,7 @@ class GeminiModelProvider(ModelProvider):
         from utils.model_restrictions import get_restriction_service
 
         restriction_service = get_restriction_service()
-        if not restriction_service.is_allowed(ProviderType.GOOGLE, resolved_name, model_name):
+        if not restriction_service.is_allowed(ProviderType.GOOGLE, model_name, resolved_name):
             logger.debug(f"Gemini model '{model_name}' -> '{resolved_name}' blocked by restrictions")
             return False