refactor(automod): remove regex classifier — LLM is the sole judge

Delete fastClassifier.ts (manual regex patterns for phone/email/IP/crypto/
spam/toxicity) and simpleFallback.ts. These hardcoded patterns were the
source of false positives (Discord emoji snowflakes matched phone_number,
URL digits matched phone, etc.) and produced heuristic verdicts whenever
the LLM failed.

New flow: Message → LLM (with conversation context, media evidence, user
reputation) → verdict. On LLM failure the message is marked 'error' and
retried by the recovery worker — no heuristic verdicts, ever.

Discord markdown tokens (custom emoji/mentions/timestamps) are normalized
to readable placeholders ([emoji:name], @user, @role, #channel, [time])
before reaching the LLM via discordTokens.ts.

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

@@ -7,6 +7,7 @@
 
 import { messageStore } from "../message-capture/messageStore.js";
 import type { MessageRecord } from "../message-capture/types.js";
+import { sanitizeDiscordTokens } from "./discordTokens.js";
 
 /** Simple XML-escaping for content text. */
 export function escapeXml(s: string): string {
@@ -29,7 +30,7 @@ export function getAnalysisContent(message: MessageRecord): string {
     /\[(?:Attachment|Sticker):[^\]]*\]|\[Embed\]/g,
     "",
   );
-  return stripped.trim();
+  return sanitizeDiscordTokens(stripped).trim();
 }
 
 /**