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.

vercel.json

@@ -39,15 +39,15 @@
   "crons": [
     {
       "path": "/api/sync/changes",
-      "schedule": "*/2 * * * *"
+      "schedule": "0 */4 * * *"
     },
     {
       "path": "/api/sync/keyword",
-      "schedule": "*/15 * * * *"
+      "schedule": "0 */6 * * *"
     },
     {
       "path": "/api/sync/metrics",
-      "schedule": "0 * * * *"
+      "schedule": "0 0 * * *"
     },
     {
       "path": "/api/sync/stats-snapshot",