feat: add Groq Llama Prompt Guard moderation integration

- Updated .env.example to include Groq API configuration.
- Enhanced config schema in config.ts to support Groq API keys and settings.
- Implemented Groq moderation API call in indonesianTextNormalizer.ts as a fallback for badword detection.
- Removed the Indonesian slang normalization function and related tests to streamline moderation logic.
- Updated tests to reflect changes in moderation strategy, focusing on emoji normalization and badword detection.

.env.example

@@ -52,6 +52,11 @@ AI_LLM_MODEL=free
 # NVIDIA Nemotron Content Safety Configuration
 NVIDIA_NEMOTRON_API_KEY=your_nvidia_api_key_here
 
+# Groq Llama Prompt Guard Fallback Configuration
+GROQ_API_KEY=your_groq_api_key_here
+GROQ_MODERATION_MODEL=meta-llama/llama-prompt-guard-2-86m
+GROQ_MODERATION_BASE_URL=https://api.groq.com/openai/v1/chat/completions
+
 # Database Configuration (PostgreSQL)
 # Option 1: Use DATABASE_URL for connection string
 # DATABASE_URL=postgresql://user:password@localhost:5432/discord_bot