Fix model visibility and config transparency for users

CRITICAL UX FIXES for beginners:

Model Display Issues Fixed:
- TUI now shows ACTUAL configured model, not hardcoded model
- CLI status command shows configured vs actual model with mismatch warnings
- Both TUI and CLI use identical model selection logic (no more inconsistency)

Config File Visibility Improved:
- Config file location prominently displayed in TUI configuration menu
- CLI status shows exact config file path (.mini-rag/config.yaml)
- Added clear documentation in config file header about model settings
- Users can now easily find and edit YAML file for direct configuration

User Trust Restored:
- ✅ Shows 'Using configured: qwen3:1.7b' when config matches reality
- ⚠️ Shows 'Model mismatch!' when config differs from actual
- Config changes now immediately visible in status displays

No more 'I changed the config but nothing happened' confusion!

.mini-rag/config.yaml

@@ -1,5 +1,18 @@
 # FSS-Mini-RAG Configuration
-# Edit this file to customize indexing and search behavior
+# 
+# 🔧 EDIT THIS FILE TO CUSTOMIZE YOUR RAG SYSTEM
+# 
+# This file controls all behavior of your Mini-RAG system.
+# Changes take effect immediately - no restart needed!
+# 
+# 💡 IMPORTANT: To change the AI model, edit the 'synthesis_model' line below
+# 
+# Common model options:
+#   synthesis_model: auto              # Let system choose best available
+#   synthesis_model: qwen3:0.6b        # Ultra-fast (500MB)
+#   synthesis_model: qwen3:1.7b        # Balanced (1.4GB) - recommended
+#   synthesis_model: qwen3:4b          # High quality (2.5GB)
+#
 # See docs/GETTING_STARTED.md for detailed explanations
 
 # Text chunking settings
@@ -46,7 +59,7 @@ search:
 # LLM synthesis and query expansion settings
 llm:
   ollama_host: localhost:11434
-  synthesis_model: auto    # 'auto', 'qwen3:1.7b', etc.
+  synthesis_model: qwen3:1.7b    # 'auto', 'qwen3:1.7b', etc.
   expansion_model: auto     # Usually same as synthesis_model
   max_expansion_terms: 8        # Maximum terms to add to queries
   enable_synthesis: false       # Enable synthesis by default

rag-mini.py

@@ -311,6 +311,43 @@ def status_check(project_path: Path):
         except Exception as e:
             print(f"   ❌ Status check failed: {e}")
         
+        print()
+        
+        # Check LLM status and show actual vs configured model
+        print("🤖 LLM System:")
+        try:
+            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():
+                synthesizer._ensure_initialized()
+                actual_model = synthesizer.model
+                config_model = config.llm.synthesis_model
+                
+                if config_model == "auto":
+                    print(f"   ✅ Auto-selected: {actual_model}")
+                elif config_model == actual_model:
+                    print(f"   ✅ Using configured: {actual_model}")
+                else:
+                    print(f"   ⚠️  Model mismatch!")
+                    print(f"   Configured: {config_model}")
+                    print(f"   Actually using: {actual_model}")
+                    print(f"   (Configured model may not be installed)")
+                    
+                print(f"   Config file: {config_manager.config_path}")
+            else:
+                print("   ❌ Ollama not available")
+                print("   Start with: ollama serve")
+            
+        except Exception as e:
+            print(f"   ❌ LLM status check failed: {e}")
+            
         # Show last search if available
         last_search_file = rag_dir / 'last_search' if rag_dir.exists() else None
         if last_search_file and last_search_file.exists():

rag-tui.py

@@ -79,11 +79,22 @@ class SimpleTUI:
             else:
                 config = RAGConfig()
             
-            synthesizer = LLMSynthesizer(config=config)
+            # Create synthesizer with proper model configuration (same as main CLI)
+            synthesizer = LLMSynthesizer(
+                model=config.llm.synthesis_model if config.llm.synthesis_model != "auto" else None,
+                config=config
+            )
             if synthesizer.is_available():
                 # Get the model that would be selected
                 synthesizer._ensure_initialized()
                 model = synthesizer.model
+                
+                # Show what config says vs what's actually being used
+                config_model = config.llm.synthesis_model
+                if config_model != "auto" and config_model != model:
+                    # Config specified a model but we're using a different one
+                    return "⚠️ Model mismatch", f"{model} (config: {config_model})"
+                else:
                     return "✅ Ready", model
             else:
                 return "❌ Ollama not running", None
@@ -1401,6 +1412,13 @@ Your suggested question (under 10 words):"""
                 print(f"   ⚡ LLM synthesis: {'enabled' if config.llm.enable_synthesis else 'disabled'}")
                 print()
                 
+                # Show config file location prominently
+                config_path = config_manager.config_path
+                print("📁 Configuration File Location:")
+                print(f"   {config_path}")
+                print("   💡 Edit this YAML file directly for advanced settings")
+                print()
+                
                 print("🛠️  Quick Configuration Options:")
                 print("   1. Select AI model (Fast/Recommended/Quality)")
                 print("   2. Configure context window (Development/Production/Advanced)")