chore(ai-moderation): increase llm client timeout and add test script

- Increase OpenAI client timeout from 15s to 60s to handle high-latency models
- Add `test-llm.js` for manual verification of LLM connectivity and response times

services/discord-gateway/src/modules/ai-moderation/llmClient.ts

@@ -27,7 +27,7 @@ function getClient(): OpenAI | null {
       apiKey: config.AI_LLM_API_KEY,
       baseURL: config.AI_LLM_BASE_URL,
       maxRetries: 0,
-      timeout: 15_000,
+      timeout: 60_000, // Diperbesar dari 15s ke 60s untuk mengakomodasi model delay tinggi
     });
   }
   return openaiClient;