Refactor: Optimize DB performance, reduce repetitions, and add @-ping protection

- Optimized Markov chain storage: Switched from full rewrites to incremental DB updates.
- Improved AI creativity: Reduced repetitions using presence/frequency penalties and prompt tuning.
- Increased Markov randomness: Lowered order to 1 and enabled learning of special characters/emojis.
- Added @-ping protection: Automatically strips '@' symbols from AI and Markov responses.
- Enhanced robustness: Added startup token checks, directory auto-creation, and admin/bot-info caching.

src/ai.ts

@@ -60,7 +60,9 @@ export async function generateAIResponse(
       model: config.model,
       messages,
       max_tokens: 500,
-      temperature: 0.7,
+      temperature: 0.8,
+      presence_penalty: 0.6,
+      frequency_penalty: 0.6,
     }),
   });