feat(ai-moderation): enrich analysis context with recency, repetition, user history and channel topic

- <message> targets now carry time (ISO), repetitions (N identical short texts = spam signal), bot and edited flags; escape id/user XML
- rich <user_reputation>: total_infractions, clean_streak, last_offense_days_ago, repeat_offender (7-day window)
- <user_history> with last flagged messages for repeat offenders (wires dead getUserRecentInfractions)
- <user_profile as_of> staleness signal; <location_context topic> from captured channel topic
- prompt framing + output instructions teach the LLM to use the new signals without treating history as proof
- tests: contextEnrichment.test.ts (13) + topic cases in conversationContext.test.ts

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

@@ -165,6 +165,7 @@ export function buildLocationContext(targets: MessageRecord[]): string {
       channel?: {
         channelName?: string | null;
         threadName?: string | null;
+        topic?: string | null;
         nsfw?: boolean;
         ageRestricted?: boolean;
         nsfwLevel?: string | null;
@@ -181,6 +182,13 @@ export function buildLocationContext(targets: MessageRecord[]): string {
       if (ch.threadName)
         attrs.push(`thread_name="${escapeXml(ch.threadName)}"`);
     }
+    if (typeof ch.topic === "string" && ch.topic.trim().length > 0) {
+      const topic =
+        ch.topic.length > 200
+          ? `${ch.topic.slice(0, 200).trimEnd()}…`
+          : ch.topic;
+      attrs.push(`topic="${escapeXml(topic)}"`);
+    }
     if (typeof ch.nsfw === "boolean") attrs.push(`nsfw="${ch.nsfw}"`);
     if (typeof ch.ageRestricted === "boolean") {
       attrs.push(`age_restricted="${ch.ageRestricted}"`);