feat(simulation): voice pipeline integration — Factual bypass, observer wiring, tell iteration (#650 #652 #651)

ContentType::Factual bypasses LLM for fact-bearing lines (numbers,
denials). Observer enrichment systems rewrite dialogue/conversation
text with voiced versions before snapshot assembly. Friendly and
RoutineDeviation tells get concrete surface-pattern examples.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

server/src/voice/cache.rs

@@ -220,6 +220,7 @@ impl Serialize for ContentType {
         match self {
             ContentType::Dialogue => serializer.serialize_u8(0),
             ContentType::Behavior => serializer.serialize_u8(1),
+            ContentType::Factual => serializer.serialize_u8(2),
         }
     }
 }
@@ -230,6 +231,7 @@ impl<'de> Deserialize<'de> for ContentType {
         match v {
             0 => Ok(ContentType::Dialogue),
             1 => Ok(ContentType::Behavior),
+            2 => Ok(ContentType::Factual),
             _ => Err(serde::de::Error::custom("invalid ContentType")),
         }
     }