feat(gmw): moderation explainability + semantic message search

- Persist structured verdict (flags/severity/confidence/evidence) on
  moderation_actions so the public web can show WHY a message was moderated.
- Add a persistent Qdrant archive collection (gmw_message_archive); embed
  every captured message at capture time (fire-and-forget, best-effort).
- Public semantic search over the archive (backend oRPC + FE toggle on the
  messages view). Both features are read-only/public and fully automatic.

Migration: 0015_add_moderation_explainability.sql

services/discord-gateway/src/shared/config/index.ts

@@ -178,6 +178,7 @@ export const configSchema = z
     // embedding column remains as a legacy fallback).
     QDRANT_URL: z.string().optional(),
     QDRANT_COLLECTION: z.string().default("gmw_text_moderation"),
+    QDRANT_ARCHIVE_COLLECTION: z.string().default("gmw_message_archive"),
     QDRANT_API_KEY: z.string().optional(),
     AI_LLM_MAX_CONCURRENT: z.coerce.number().int().positive().default(8),
     AI_LLM_IMAGE_MAX_DIMENSION: z.coerce