crates/clawhdf5-agent/src/knowledge.rs

@@ -50,6 +50,9 @@ impl RelationType {
 pub struct Entity {
     pub id: u64,
     pub name: String,
+    /// Lowercased `name`, cached at construction time to avoid re-allocating
+    /// and re-lowercasing on every entity-resolution scan.
+    pub name_lower: String,
     pub entity_type: String,
     /// Index into the memory embeddings array, or -1 if none.
     pub embedding_idx: i64,
@@ -69,6 +72,7 @@ impl Default for Entity {
         Self {
             id: 0,
             name: String::new(),
+            name_lower: String::new(),
             entity_type: String::new(),
             embedding_idx: -1,
             properties: HashMap::new(),
@@ -198,6 +202,7 @@ impl KnowledgeCache {
         self.entities.push(Entity {
             id,
             name: name.to_owned(),
+            name_lower: name.to_lowercase(),
             entity_type: entity_type.to_owned(),
             embedding_idx,
             properties: HashMap::new(),
@@ -310,16 +315,22 @@ impl KnowledgeCache {
     ) -> (u64, bool) {
         let lower_name = name.to_lowercase();
 
-        // Search for the closest existing entity.
-        let best = self
-            .entities
-            .iter()
-            .map(|e| {
-                let dist = levenshtein(&lower_name, &e.name.to_lowercase());
-                (e.id, dist)
-            })
-            .filter(|&(_, dist)| dist <= max_distance)
-            .min_by_key(|&(_, dist)| dist);
+        // Search for the closest existing entity, short-circuiting on an
+        // exact match since no closer candidate can exist.
+        let mut best: Option<(u64, usize)> = None;
+        for e in &self.entities {
+            let dist = levenshtein(&lower_name, &e.name_lower);
+            if dist > max_distance {
+                continue;
+            }
+            if dist == 0 {
+                best = Some((e.id, dist));
+                break;
+            }
+            if best.is_none_or(|(_, best_dist)| dist < best_dist) {
+                best = Some((e.id, dist));
+            }
+        }
 
         if let Some((id, _)) = best {
             return (id, false);
@@ -855,6 +866,19 @@ mod tests {
         assert_eq!(id, orig_id);
     }
 
+    /// An exact match must win even when a near-match with a smaller Levenshtein
+    /// distance-to-zero gap was scanned first — the early exit on dist == 0
+    /// must not skip past a later exact match.
+    #[test]
+    fn test_resolve_or_create_exact_match_beats_earlier_fuzzy_candidate() {
+        let mut cache = KnowledgeCache::new();
+        cache.add_entity("Alyce", "person", -1); // dist 1 from "Alice"
+        let exact_id = cache.add_entity("Alice", "person", -1); // dist 0
+        let (id, created) = cache.resolve_or_create("Alice", "person", -1, 2);
+        assert!(!created);
+        assert_eq!(id, exact_id);
+    }
+
     #[test]
     fn test_resolve_or_create_no_match_beyond_threshold() {
         let mut cache = KnowledgeCache::new();

crates/clawhdf5-agent/src/schema.rs

@@ -480,6 +480,7 @@ fn load_knowledge_group(file: &clawhdf5::File) -> Result<KnowledgeCache, MemoryE
             cache.entities.push(crate::knowledge::Entity {
                 id: entity_ids[i] as u64,
                 name: entity_names[i].clone(),
+                name_lower: entity_names[i].to_lowercase(),
                 entity_type: entity_types[i].clone(),
                 embedding_idx: emb_idxs[i],
                 ..Default::default()