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.

packages/db/prisma/schema.prisma

@@ -6,8 +6,9 @@ generator client {
 }
 
 datasource db {
-  provider = "postgresql"
-  url      = env("DATABASE_URL")
+  provider  = "postgresql"
+  url       = env("DATABASE_URL")
+  directUrl = env("DIRECT_URL") // Direct connection for migrations (bypasses pooler)
 }
 
 /// Package table - stores NPM package metadata (package-level)