fix(agent): validate per-record dataset lengths when loading a store

The norms guard was the tautology `n.len() == n.len()`, so a norms dataset
of any length was trusted and corrupted every cosine score; other per-record
datasets were not length-checked at all, so a truncated file loaded and then
panicked on the first index. Mismatches are now MemoryError::Schema, stored
norms are used only when they match the record count, and embedding_dim == 0
with records present is rejected instead of panicking in chunks(0).

Co-Authored-By: Claude Fable 5.1 <[email protected]>

crates/clawhdf5-agent/src/schema.rs

@@ -391,20 +391,46 @@ fn load_memory_group(
     let tags = read_string_dataset_from_group(&group, "tags")?;
     let tombstones = read_u8_dataset(&group, "tombstones")?;
 
-    // Read norms if present, otherwise compute from embeddings
-    let norms = match read_f32_dataset(&group, "norms") {
-        Ok(n) if n.len() == n.len() => n,
-        _ => {
-            // Compute norms from flat embeddings
-            flat_embeddings
-                .chunks(embedding_dim)
-                .map(|chunk| {
-                    let sq_sum: f32 = chunk.iter().map(|x| x * x).sum();
-                    sq_sum.sqrt()
-                })
-                .collect()
+    // Every per-record dataset must describe exactly `n` records. Without
+    // this, a truncated or hand-edited file loads "successfully" and then
+    // panics on the first out-of-bounds index during search/delete.
+    if embedding_dim == 0 {
+        return Err(MemoryError::Schema(format!(
+            "/memory has {n} records but embedding_dim is 0"
+        )));
+    }
+    let expected_flat = n.checked_mul(embedding_dim).ok_or_else(|| {
+        MemoryError::Schema(format!("/memory size overflow: {n} x {embedding_dim}"))
+    })?;
+    let check_len = |name: &str, actual: usize, expected: usize| {
+        if actual == expected {
+            Ok(())
+        } else {
+            Err(MemoryError::Schema(format!(
+                "/memory/{name} has {actual} entries, expected {expected} \
+                 ({n} records)"
+            )))
         }
     };
+    check_len("embeddings", flat_embeddings.len(), expected_flat)?;
+    check_len("source_channel", source_channels.len(), n)?;
+    check_len("timestamps", timestamps.len(), n)?;
+    check_len("session_ids", session_ids.len(), n)?;
+    check_len("tags", tags.len(), n)?;
+    check_len("tombstones", tombstones.len(), n)?;
+
+    // Norms are derived data: use the stored ones only if they are present
+    // and the right length, otherwise recompute from the embeddings.
+    let norms = match read_f32_dataset(&group, "norms") {
+        Ok(stored) if stored.len() == n => stored,
+        _ => flat_embeddings
+            .chunks(embedding_dim)
+            .map(|chunk| {
+                let sq_sum: f32 = chunk.iter().map(|x| x * x).sum();
+                sq_sum.sqrt()
+            })
+            .collect(),
+    };
 
     // Unflatten embeddings
     let embeddings: Vec<Vec<f32>> = flat_embeddings
@@ -616,3 +642,78 @@ fn read_u8_dataset(group: &clawhdf5::Group<'_>, name: &str) -> Result<Vec<u8>, M
         .map_err(|e| MemoryError::Hdf5(format!("cannot read u8 from {name}: {e}")))?;
     Ok(data.into_iter().map(|v| v as u8).collect())
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn config() -> MemoryConfig {
+        MemoryConfig::new(std::path::PathBuf::from("unused.h5"), "agent", 4)
+    }
+
+    fn cache_with(n: usize) -> MemoryCache {
+        let mut cache = MemoryCache::new(4);
+        for i in 0..n {
+            cache.push(
+                format!("chunk {i}"),
+                vec![i as f32 + 1.0, 0.0, 0.0, 0.0],
+                "user".into(),
+                i as f64,
+                "s".into(),
+                "t".into(),
+            );
+        }
+        cache
+    }
+
+    fn roundtrip(cache: &MemoryCache) -> Result<MemoryCache, MemoryError> {
+        let bytes = build_hdf5_file(
+            &config(),
+            cache,
+            &SessionCache::new(),
+            &KnowledgeCache::new(),
+        )?;
+        let file =
+            clawhdf5::File::from_bytes(bytes).map_err(|e| MemoryError::Hdf5(e.to_string()))?;
+        validate_and_load(&file).map(|(_, cache, _, _)| cache)
+    }
+
+    #[test]
+    fn consistent_store_loads() {
+        let loaded = roundtrip(&cache_with(3)).unwrap();
+        assert_eq!(loaded.chunks.len(), 3);
+        assert_eq!(loaded.norms, vec![1.0, 2.0, 3.0]);
+    }
+
+    #[test]
+    fn wrong_length_norms_are_recomputed_not_trusted() {
+        // Regression: the guard used to be `n.len() == n.len()`, so a norms
+        // dataset of any length was accepted and corrupted every cosine score.
+        let mut cache = cache_with(3);
+        cache.norms = vec![99.0];
+        let loaded = roundtrip(&cache).unwrap();
+        assert_eq!(loaded.norms, vec![1.0, 2.0, 3.0]);
+    }
+
+    #[test]
+    fn mismatched_per_record_datasets_are_schema_errors() {
+        type Corrupt = fn(&mut MemoryCache);
+        let cases: [(&str, Corrupt); 5] = [
+            ("tombstones", |c| c.tombstones.truncate(1)),
+            ("timestamps", |c| c.timestamps.truncate(1)),
+            ("tags", |c| c.tags.truncate(1)),
+            ("session_ids", |c| c.session_ids.truncate(1)),
+            ("source_channel", |c| c.source_channels.truncate(1)),
+        ];
+        for (name, corrupt) in cases {
+            let mut cache = cache_with(3);
+            corrupt(&mut cache);
+            match roundtrip(&cache) {
+                Err(MemoryError::Schema(msg)) => {
+                    assert!(msg.contains(name), "{name}: unexpected message {msg}")
+                }
+                other => panic!("{name}: expected Schema error, got {:?}", other.map(|_| ())),
+            }
+        }
+    }
+}