perf(automod): compress prompts ~40% + semantic cache via AI_LLM_EMBEDDING_MODEL

Prompt overhaul (token-frugal, same quality):
- rules.ts 28KB -> 10.3KB: every normative rule kept (safe lists, SARA
  6 kategori, LGBT/Israel zero tolerance, anti-evasion, decision tree,
  evasi hierarchy, image rules) with duplicated phrasing removed
- examples.ts 24.7KB -> 20KB: all 31 teaching examples kept; analysis
  strings shortened, redundant categories/policy_version dropped from
  example outputs (both optional in the response schema)
- output.ts 13.8KB -> 6.8KB: compressed schema + personality + format
  rules; CRITICAL bans on generic analysis and reply-context requirement
  retained
- system.ts: MEDIA_INSTRUCTIONS compressed, key rules kept

Semantic moderation cache (AI_LLM_EMBEDDING_MODEL):
- New embeddingClient.ts: OpenAI-compatible embeddings + cosine
  similarity; degrades gracefully when model/key unset
- textCacheStore: stores embedding JSON per verdict, findSimilarTextModeration
  reuses near-duplicate verdicts (min 0.97 cosine, processing locks skipped)
- moderationOrchestrator: after exact-hash miss, embed text-only targets
  and reuse stored verdict for near-duplicates -> skips expensive chat
  completion for spam variants; fresh verdicts written back with embedding
- Config: AI_LLM_EMBEDDING_MODEL / MIN_SIMILARITY (0.97) / MAX_CANDIDATES (30)
- Migration 0012: ADD COLUMN embedding to text_analysis_cache (idempotent)
- .env.example documents the new vars

services/discord-gateway/src/shared/database/schema.ts

@@ -402,6 +402,9 @@ export const pgTextAnalysisCacheTable = pgTable(
     analyzed_at: pgBigint("analyzed_at", { mode: "number" }).notNull(),
     expires_at: pgBigint("expires_at", { mode: "number" }).notNull(),
     hit_count: pgInteger("hit_count").notNull().default(0),
+    // JSON-encoded embedding vector for semantic moderation cache lookups.
+    // Null for entries stored before embeddings were enabled.
+    embedding: pgText("embedding"),
   },
   (table) => ({
     expiresAtIdx: pgIndex("idx_text_analysis_cache_expires_at").on(