Merge remote-tracking branch 'origin/clawmates/mission-01a00c41-421200ee' into verify/v3-plus-v6

# Conflicts:
#	crates/clawhdf5/Cargo.toml

crates/clawhdf5-migrate/src/validate.rs

@@ -1,3 +1,6 @@
+use clawhdf5::reader::File as Hdf5File;
+use clawhdf5_format::provenance::VerifyResult;
+
 use crate::hdf5_reader::read_hdf5;
 use crate::sqlite_reader::SqliteData;
 
@@ -13,6 +16,12 @@ pub struct ValidationSummary {
     pub embedding_dim: u64,
     /// Number of rows whose full content was compared against the source.
     pub rows_checked: u64,
+    /// Whether the `chunks/text` and `chunks/embeddings` SHINES provenance
+    /// hashes (written via [`crate::hdf5_writer`]) were both present and
+    /// matched their recomputed SHA-256 on read-back. `false` when either
+    /// dataset has no provenance metadata (e.g. an older output file) or
+    /// there are zero chunks to check.
+    pub provenance_verified: bool,
 }
 
 /// Validate a migrated HDF5 file against the source data.
@@ -30,6 +39,7 @@ pub fn validate_hdf5(
     float16: bool,
 ) -> Result<ValidationSummary, BoxErr> {
     let got = read_hdf5(path)?;
+    let provenance_verified = verify_chunk_provenance(path)?;
 
     // ---- Counts ----
     check_count("chunk", got.chunks.len(), source.chunks.len())?;
@@ -126,6 +136,7 @@ pub fn validate_hdf5(
         relations: got.relations.len() as u64,
         embedding_dim: got.embedding_dim as u64,
         rows_checked,
+        provenance_verified,
     })
 }
 
@@ -136,6 +147,42 @@ fn check_count(kind: &str, got: usize, expected: usize) -> Result<(), BoxErr> {
     Ok(())
 }
 
+/// Re-verify the SHA-256 provenance hash of `chunks/text` and
+/// `chunks/embeddings` against their actual stored bytes, catching
+/// post-write corruption that a plain content comparison against the
+/// in-memory source wouldn't (the source is compared against what
+/// `read_hdf5` decoded, not against the raw bytes on disk).
+///
+/// Returns `Ok(true)` only if both datasets exist and both hashes match.
+/// Returns `Ok(false)` (not an error) if a dataset has no provenance
+/// attributes at all (e.g. a file written before this check existed) or
+/// there are zero chunks. Returns an error only on an actual hash mismatch —
+/// that indicates real corruption.
+fn verify_chunk_provenance(path: &str) -> Result<bool, BoxErr> {
+    let file = Hdf5File::open(path)?;
+    let Ok(chunks) = file.group("chunks") else {
+        return Ok(false);
+    };
+    let mut all_present = true;
+    for name in ["text", "embeddings"] {
+        let Ok(ds) = chunks.dataset(name) else {
+            all_present = false;
+            continue;
+        };
+        match ds.verify_provenance()? {
+            VerifyResult::Ok => {}
+            VerifyResult::NoHash => all_present = false,
+            VerifyResult::Mismatch { stored, computed } => {
+                return Err(format!(
+                    "provenance hash mismatch on chunks/{name}: stored {stored}, recomputed {computed} — data may be corrupted"
+                )
+                .into());
+            }
+        }
+    }
+    Ok(all_present)
+}
+
 fn field_err<T: std::fmt::Display>(kind: &str, i: usize, field: &str, s: T, g: T) -> BoxErr {
     format!("{kind}[{i}].{field} mismatch: source {s}, HDF5 {g}").into()
 }