refactor(moderation): improve LLM moderation client - 10 recommendations

- Add XML delimiters to prevent prompt injection (R1)
- Use JSON Schema response format instead of json_object (R2)
- Add concurrency limiter via p-limit (R3)
- Add timeout per media analysis call (R4)
- Resize images with sharp before vision API (R5)
- Split text batches when exceeding batch size limit (R6)
- Add few-shot examples to system prompt (R7)
- Modularize system prompt builder (R8)
- Enhance deferral detection regex with exception patterns (R9)
- Sanitize error messages to avoid leaking internals (R10)

New files: concurrencyLimiter.ts, imageResizer.ts, moderationPrompt.ts
Updated: llmModerationClient.ts, config.ts, package.json, tests

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

package.json

@@ -49,6 +49,7 @@
     "motion": "^12.40.0",
     "openai": "^6.38.0",
     "opusscript": "^0.0.8",
+    "p-limit": "^7.3.0",
     "p-retry": "^8.0.0",
     "pg": "^8.21.0",
     "piscina": "^5.1.4",
@@ -57,6 +58,7 @@
     "prom-client": "^15.1.3",
     "react": "^19.2.6",
     "react-dom": "^19.2.6",
+    "sharp": "^0.34.5",
     "tailwind-merge": "^3.6.0",
     "vite": "^8.0.13",
     "winston": "^3.19.0",