Implement comprehensive LLM provider system with global cost protection

- Add multi-provider LLM architecture supporting OpenRouter, OpenAI, Gemini, and custom providers
- Implement global LLM on/off switch with default DISABLED state for cost protection
- Add per-character LLM configuration with provider-specific models and settings
- Create performance-optimized caching system for LLM enabled status checks
- Add API key validation before enabling LLM providers to prevent broken configurations
- Implement audit logging for all LLM enable/disable actions for cost accountability
- Create comprehensive admin UI with prominent cost warnings and confirmation dialogs
- Add visual indicators in character list for custom AI model configurations
- Build character-specific LLM client system with global fallback mechanism
- Add database schema support for per-character LLM settings
- Implement graceful fallback responses when LLM is globally disabled
- Create provider testing and validation system for reliable connections

scripts/update_llm_config.py

@@ -0,0 +1,140 @@
+#!/usr/bin/env python3
+"""
+Script to help migrate from single LLM provider to multi-provider configuration
+"""
+
+import json
+import os
+import sys
+from pathlib import Path
+
+
+def update_fishbowl_config():
+    """Update fishbowl_config.json to include multi-provider LLM configuration"""
+    
+    config_path = Path("config/fishbowl_config.json")
+    
+    if not config_path.exists():
+        print(f"Configuration file not found: {config_path}")
+        return False
+    
+    # Read existing config
+    with open(config_path, 'r') as f:
+        config = json.load(f)
+    
+    # Check if already has providers config
+    if 'providers' in config.get('llm', {}):
+        print("Multi-provider configuration already exists")
+        return True
+    
+    # Get current LLM config
+    current_llm = config.get('llm', {})
+    
+    # Create new multi-provider config
+    providers_config = {
+        "custom": {
+            "type": "custom",
+            "enabled": True,
+            "priority": 70,
+            "config": {
+                "base_url": current_llm.get('base_url', 'http://localhost:11434'),
+                "model": current_llm.get('model', 'llama2'),
+                "api_key": os.getenv('LLM_API_KEY', 'x'),
+                "timeout": current_llm.get('timeout', 300),
+                "max_tokens": current_llm.get('max_tokens', 2000),
+                "temperature": current_llm.get('temperature', 0.8),
+                "api_format": "openai"
+            }
+        }
+    }
+    
+    # Add example provider configurations (disabled by default)
+    providers_config.update({
+        "openrouter": {
+            "type": "openrouter",
+            "enabled": False,
+            "priority": 100,
+            "config": {
+                "api_key": "${OPENROUTER_API_KEY:}",
+                "base_url": "https://openrouter.ai/api/v1",
+                "model": "${OPENROUTER_MODEL:anthropic/claude-3-sonnet}",
+                "timeout": 300,
+                "max_tokens": 2000,
+                "temperature": 0.8,
+                "app_name": "discord-fishbowl"
+            }
+        },
+        "openai": {
+            "type": "openai",
+            "enabled": False,
+            "priority": 90,
+            "config": {
+                "api_key": "${OPENAI_API_KEY:}",
+                "base_url": "https://api.openai.com/v1",
+                "model": "${OPENAI_MODEL:gpt-4o-mini}",
+                "timeout": 300,
+                "max_tokens": 2000,
+                "temperature": 0.8
+            }
+        },
+        "gemini": {
+            "type": "gemini",
+            "enabled": False,
+            "priority": 80,
+            "config": {
+                "api_key": "${GEMINI_API_KEY:}",
+                "base_url": "https://generativelanguage.googleapis.com/v1beta",
+                "model": "${GEMINI_MODEL:gemini-1.5-flash}",
+                "timeout": 300,
+                "max_tokens": 2000,
+                "temperature": 0.8
+            }
+        }
+    })
+    
+    # Update config
+    config['llm']['providers'] = providers_config
+    
+    # Create backup
+    backup_path = config_path.with_suffix('.json.backup')
+    with open(backup_path, 'w') as f:
+        json.dump(config, f, indent=2)
+    print(f"Created backup: {backup_path}")
+    
+    # Write updated config
+    with open(config_path, 'w') as f:
+        json.dump(config, f, indent=2)
+    
+    print(f"Updated {config_path} with multi-provider configuration")
+    print("\nTo enable additional providers:")
+    print("1. Set environment variables for the provider you want to use")
+    print("2. Change 'enabled': false to 'enabled': true in the config")
+    print("3. Restart the application")
+    
+    return True
+
+
+def main():
+    """Main script function"""
+    print("Discord Fishbowl LLM Configuration Updater")
+    print("=" * 50)
+    
+    if update_fishbowl_config():
+        print("\n✅ Configuration updated successfully!")
+        print("\nAvailable providers:")
+        print("- OpenRouter (supports Claude, GPT, Llama, etc.)")
+        print("- OpenAI (GPT models)")
+        print("- Google Gemini")
+        print("- Custom/Local (current setup)")
+        
+        print("\nNext steps:")
+        print("1. Update your .env file with API keys for desired providers")
+        print("2. Enable providers in config/fishbowl_config.json")
+        print("3. Restart the application")
+    else:
+        print("\n❌ Configuration update failed!")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()