feat: update ttft modeling and add cache affinity

src/router/ttl_aware.rs

@@ -1,6 +1,6 @@
 use crate::cluster::meta_store::MetaStore;
 use crate::instance::Instance;
-use crate::router::{local_l0_scores, CandidateInfo, RouteDecision, Router};
+use crate::router::{CandidateInfo, RouteDecision, Router};
 use crate::trace::RequestRecord;
 
 pub struct TtlAwareRouter {
@@ -22,11 +22,11 @@ impl Router for TtlAwareRouter {
         &mut self,
         req: &RequestRecord,
         instances: &[Instance],
-        _meta: &MetaStore,
-        _now: f64,
+        meta: &MetaStore,
+        now: f64,
     ) -> RouteDecision {
         let n = instances.len();
-        let scores = local_l0_scores(req, instances);
+        let scores = meta.score_prefix(&req.hash_ids, now, n);
         let mut best = 0u32;
         let mut best_key = (i64::MIN, f64::INFINITY); // maximize prefix, then minimize load
         let mut candidates = Vec::with_capacity(n);
@@ -52,7 +52,7 @@ impl Router for TtlAwareRouter {
             chosen: best,
             probe_overhead_s: 0.0,
             candidates,
-            reason: "max local L0 prefix, tie -> least loaded",
+            reason: "max meta_store prefix, tie -> least loaded",
         }
     }
 }