Fix critical model configuration bug

CRITICAL FIX for beginners: User config model changes now work correctly

Issues Fixed:
- rag-mini.py synthesis mode ignored config completely (used hardcoded models)
- LLMSynthesizer fallback ignored config preferences
- Users changing model in config saw no effect in synthesis mode

Changes:
- rag-mini.py now loads config and passes synthesis_model to LLMSynthesizer
- LLMSynthesizer _select_best_model() respects config model_rankings for fallback
- All modes (synthesis and explore) now properly use config settings

Tested: Model config changes now work correctly in both synthesis and explore modes

mini_rag/llm_synthesizer.py

@@ -64,7 +64,10 @@ class LLMSynthesizer:
     def _select_best_model(self) -> str:
         """Select the best available model based on configuration rankings."""
         if not self.available_models:
-            return "qwen2.5:1.5b"  # Fallback preference
+            # Use config fallback if available, otherwise use default
+            if self.config and hasattr(self.config, 'llm') and hasattr(self.config.llm, 'model_rankings') and self.config.llm.model_rankings:
+                return self.config.llm.model_rankings[0]  # First preferred model
+            return "qwen2.5:1.5b"  # System fallback only if no config
         
         # Get model rankings from config or use defaults
         if self.config and hasattr(self.config, 'llm') and hasattr(self.config.llm, 'model_rankings'):

rag-mini.py

@@ -192,7 +192,16 @@ def search_project(project_path: Path, query: str, top_k: int = 10, synthesize:
         # LLM Synthesis if requested
         if synthesize:
             print("🧠 Generating LLM synthesis...")
-            synthesizer = LLMSynthesizer()
+            
+            # Load config to respect user's model preferences
+            from mini_rag.config import ConfigManager
+            config_manager = ConfigManager(project_path)
+            config = config_manager.load_config()
+            
+            synthesizer = LLMSynthesizer(
+                model=config.llm.synthesis_model if config.llm.synthesis_model != "auto" else None,
+                config=config
+            )
             
             if synthesizer.is_available():
                 synthesis = synthesizer.synthesize_search_results(query, results, project_path)