feat(ai-moderation): implement error handling and robust streaming for llmClient

Wrap the LLM completion logic in a try-catch block to provide detailed
error logging, including status codes and raw response data, when
API requests fail.

- Add comprehensive error logging for failed LLM API calls.
- Ensure streaming responses are correctly aggregated and returned
  even when wrapped in error handling logic.

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

@@ -100,6 +100,7 @@ export async function llmChat(
   return retryWithBackoff(
     async () => {
       return withLlmConcurrency(async () => {
+        try {
           const response = await client.chat.completions.create(params);
           if (stream) {
             let content = "";
@@ -140,6 +141,18 @@ export async function llmChat(
             } as OpenAI.Chat.Completions.ChatCompletion;
           }
           return response as OpenAI.Chat.Completions.ChatCompletion;
+        } catch (error: any) {
+          log.error(
+            {
+              error: error.message,
+              status: error.status,
+              rawResponse: error.error || error.body || error.response?.data || "N/A",
+              model
+            },
+            "LLM API request failed"
+          );
+          throw error;
+        }
       });
     },
     {