refactor(ai): remove semantic embedding cache + Qdrant vector store

Hapus seluruh fitur embedding/Qdrant (tidak dipakai lagi):

- gateway: drop embeddingClient.ts, qdrantClient.ts, archiveEmbedder.ts
  dan tes qdrantEnsure.test.ts; moderationOrchestrator kembali ke
  exact-hash cache -> LLM (tanpa phase-2 semantic lookup); textCacheStore
  kehilangan findSimilarTextModeration / parseQdrantVerdict /
  isSemanticBandAccepted / upsertBareKeyToQdrant; cache-prune hanya
  menyapu Postgres.
- backend: drop embed.ts + qdrant.ts, endpoint messages.semanticSearch
  dan schema/type terkait; kolom embedding dilepas dari schema
  text_analysis_cache.
- frontend: hapus toggle EXACT/SEMANTIC, hook useSemanticSearch,
  API client + tipe SemanticSearchResult.
- config: buang AI_LLM_EMBEDDING_* dan QDRANT_* (env + .env.example).
- docs: ARCHITECTURE.md / AGENTS.md / README.md / diagram arsitektur
  disesuaikan (LLM caller - vision, cache = exact-hash saja).

Verifikasi: tsc 0 (backend, gateway, frontend); bun test 135 pass +
37 pass, 0 fail; biome 0 error.

services/frontend/src/lib/api/messages.ts

@@ -6,7 +6,6 @@ import type {
   Guild,
   MessageActivityBucket,
   MessageRecord,
-  SemanticSearchResult,
 } from "@/lib/types";
 
 export const messagesApi = {
@@ -76,17 +75,6 @@ export const messagesApi = {
       results: MessageRecord[];
     }>,
 
-  // Public semantic search over the persistent message archive (Qdrant).
-  semanticSearch: (query: string, limit?: number, guildId?: string) =>
-    orpc.messages.semanticSearch({
-      query,
-      limit,
-      ...(guildId ? { guildId } : {}),
-    }) as unknown as Promise<{
-      results: SemanticSearchResult[];
-      nextCursor: null;
-    }>,
-
   // Public, read-only activity heatmap data (per-hour volume by channel).
   getActivity: (days = 30) =>
     orpc.messages.activity({ days }) as unknown as Promise<