perf: reduce Neon compute usage with cron + caching optimizations

- Reduce cron frequency: changes 2min→4hr, keyword 15min→6hr, metrics hourly→daily
- Add Prisma directUrl for connection pooling support
- Add Vercel KV caching to /api/tools endpoint (graceful degradation if not configured)
- Add X-Cache header to indicate cache hit/miss
- Add NEON_COMPUTE_OPTIMIZATION.md with full strategy guide

These changes should reduce Neon CU usage from 100+ to ~20-30 CU-hrs/month.

apps/web/package.json

@@ -26,6 +26,7 @@
     "@types/react-syntax-highlighter": "^15.5.13",
     "@vercel/analytics": "^1.6.1",
     "@vercel/blob": "^2.0.0",
+    "@vercel/kv": "^3.0.0",
     "ai": "6.0.3",
     "bm25": "^0.1.1",
     "d3": "^7.9.0",