perf: Implement Caching Layer for Gemini API Route Handlers (#2)

[adimadhubani]

Summary of Changes

• Added @vercel/kv support with fail-open fallback mechanism.
• Created deterministic SHA-256 cache key utility (lib/cache/hash.ts) that recursively sorts JSON keys.
• Implemented 24-hour TTL caching wrapper (lib/cache/geminiCache.ts) for /api/gemini/chat and /api/gemini/insights.
• Added X-Cache response headers (HIT / MISS) for verification.
• Updated .env.example with KV variables.

Closes #2

[Copilot]

Pull request overview

This PR introduces a shared caching layer for the Gemini API route handlers to reduce redundant Gemini calls, lower latency, and improve scalability by caching successful responses for 24 hours in Vercel KV.

Changes:

• Added @vercel/kv dependency and KV environment variable examples.
• Implemented deterministic SHA-256 cache key generation with stable JSON serialization.
• Wrapped /api/gemini/chat and /api/gemini/insights handlers with a KV-backed cache that sets X-Cache: HIT|MISS.

Reviewed changes

Copilot reviewed 6 out of 7 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
package.json	Adds @vercel/kv dependency for KV-backed caching.
lib/cache/hash.ts	Adds deterministic cache key generation via recursively sorted JSON + SHA-256.
lib/cache/geminiCache.ts	Adds KV read-through cache wrapper with TTL and X-Cache headers.
app/api/gemini/insights/route.ts	Wraps Gemini insights generation in the caching wrapper.
app/api/gemini/chat/route.ts	Wraps chat generation in the caching wrapper.
.env.example	Documents KV env vars needed for caching (with intended fail-open behavior).

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.