feat(ai-moderation): introduce user reputation and channel culture context

Implements a context-aware moderation system by tracking user behavior
and channel-specific norms to improve AI decision-making accuracy.

- Adds `user_reputations` table to track trust scores, clean streaks,
  and infraction history.
- Adds `channel_cultures` table to store AI-generated summaries of
  channel-specific norms and slang.
- Implements `userReputationStore` to autonomously update user scores
  based on moderation outcomes (clean vs. flagged).
- Implements `cultureLearner` and `channelCultureStore` to manage
  evolving channel contexts.
- Enhances LLM prompts to inject user reputation (trust scores,
  history) and channel culture summaries, enabling "wisdom-based"
  moderation (e.g., giving benefit of the doubt to high-trust users).
- Integrates reputation and culture updates into the existing
  `aiAnalyzer` pipeline.

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

@@ -395,6 +395,10 @@ export interface BuildSystemPromptOptions {
    * examples. Injected between static examples and output instructions.
    */
   correctedExamples?: string;
+  /**
+   * Formatted XML block containing the AI-generated channel culture summary.
+   */
+  channelCulture?: string;
 }
 
 export function buildSystemPrompt(options: BuildSystemPromptOptions): string {
@@ -404,6 +408,7 @@ export function buildSystemPrompt(options: BuildSystemPromptOptions): string {
     includeMediaInstructions,
     correction,
     correctedExamples,
+    channelCulture,
   } = options;
 
   // Backward compatibility: if mode is not set but includeMediaInstructions is,
@@ -433,6 +438,13 @@ export function buildSystemPrompt(options: BuildSystemPromptOptions): string {
     parts.push(correctedExamples);
   }
 
+  // Channel Culture Injection (Learning)
+  if (channelCulture) {
+    parts.push(`## Kultur Channel (Pembelajaran AI)\n${channelCulture}`);
+  }
+
+  parts.push(`## Konteks Pengguna (Ingatan & Kebijaksanaan)\nSetiap pesan mungkin memiliki tag <user_reputation> dan <user_history>. *Gunakan Kebijaksanaan: Jika trust_score tinggi, beri benefit of the doubt pada ambiguitas. Jika trust_score rendah dan memiliki riwayat pelanggaran serupa, jadilah lebih tegas.*`);
+
   parts.push(OUTPUT_INSTRUCTIONS);
 
   // XML-delimited context — prevents prompt injection