feat: semantic (embedding-based) response cache

- cache.rs: cosine-similarity store (threshold, TTL, ring buffer), partitioned by
  routing signature; tracks hit rate and model cost saved
- pipeline: embed routing text, look up before the model call (route_source=cache on
  hit), insert successful responses; stats record cache hits
- config [cache] + admin settings card; dashboard shows hit-rate and savings
- embedding model resolved from the pool (or first kind="embedding")

src/main.rs

@@ -9,6 +9,7 @@
 #![allow(dead_code)]
 
 mod admin;
+mod cache;
 mod config;
 mod error;
 mod model;