fix(cache): honest settings card — clean threshold, live stats, no-embedder warning

Full audit of the semantic cache against a live instance (mock embedder,
identical requests): the mechanism works — miss at 3.1s, then hits at 2ms
with entries/hits/saved-$ counting. Two honest gaps fixed:

- the threshold round-tripped through f32 and rendered as
  0.9200000166893005 in both the TOML and the settings input — the config
  field is f64 now (writes exactly what you typed) and the input rounds
  legacy values to 2 decimals;
- the card now shows proof of life (entries / hits / hit-rate / saved $)
  and, when the cache is enabled with NO embedding model available, a
  warning that it is silently doing nothing and how to fix it — previously
  that state looked identical to a working cache.

Also audited in the same pass, no changes needed: Prometheus /metrics
(toggle on/off applies live, 404 when off), and all 7 protocol switches
(each gates its endpoint instantly both ways). 4 strings ×7 languages.

src/config.rs

@@ -829,9 +829,10 @@ fn default_shadow_soak() -> usize {
 pub struct CacheCfg {
     #[serde(default)]
     pub enabled: bool,
-    /// Cosine-similarity threshold for a hit (0..1).
+    /// Cosine-similarity threshold for a hit (0..1). f64 so the TOML holds
+    /// the number you typed (an f32 round-trips as 0.9200000166893005).
     #[serde(default = "default_semcache_threshold")]
-    pub threshold: f32,
+    pub threshold: f64,
     /// Entry time-to-live, e.g. `1h`.
     #[serde(default = "default_semcache_ttl")]
     pub ttl: String,
@@ -853,7 +854,7 @@ impl Default for CacheCfg {
         }
     }
 }
-fn default_semcache_threshold() -> f32 {
+fn default_semcache_threshold() -> f64 {
     0.92
 }
 fn default_semcache_ttl() -> String {