quantumclaw/clawhdf5
3
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

fix(agent): fail to open a store whose /meta has an unreadable attribute

Browse Source 
Group::attrs now leaves out an attribute it cannot decode. The agent read
its settings through it, so a store whose float16 (or compression,
quantized_index, WAL mark, signature...) attribute could not be decoded
opened with the default in its place, and no error. /meta is now read
with attrs_with_errors and any unreadable attribute is a Schema error,
as it was before attrs became tolerant. Found by the adversarial review.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
This commit is contained in:
osobh
2026-09-25 22:43:53 -05:00
co-authored by Claude Opus 5.5
parent 256e7b89e4
commit d6e426e6d5
2 changed files with 75 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/clawhdf5-agent/src/schema.rs
+35 -23
View File
@@ -477,10 +477,34 @@ fn write_string_dataset(
}
}
/// `/meta`'s attributes, failing if any of them cannot be read.
///
/// `Group::attrs` leaves out an attribute it cannot decode. For the store's
/// settings that would silently fall back to defaults (e.g. `float16`, the
/// WAL mark), so an unreadable attribute is an error here, as it was before
/// `attrs` became tolerant.
fn meta_attrs(
file: &clawhdf5::File,
) -> Result<std::collections::HashMap<String, AttrValue>, MemoryError> {
let meta = file
.group("meta")
.map_err(|e| MemoryError::Schema(format!("missing /meta group: {e}")))?;
let (attrs, errors) = meta
.attrs_with_errors()
.map_err(|e| MemoryError::Schema(format!("cannot read /meta attrs: {e}")))?;
if let Some(e) = errors.first() {
return Err(MemoryError::Schema(format!(
"cannot read /meta attrs: {} unreadable, first: {e}",
errors.len()
)));
}
Ok(attrs)
}
/// Validate an HDF5 file has the correct schema and load all data.
/// Read the checkpoint's [`WalMark`] from `/meta`, if it has one.
pub fn read_wal_mark(file: &clawhdf5::File) -> Option<WalMark> {
let attrs = file.group("meta").ok()?.attrs().ok()?;
let attrs = meta_attrs(file).ok()?;
let len = match attrs.get(WAL_APPLIED_LEN_ATTR)? {
AttrValue::I64(v) => u64::try_from(*v).ok()?,
_ => return None,
@@ -498,10 +522,7 @@ pub fn read_signature(
file: &clawhdf5::File,
) -> Result<Option<crate::signing::StoredSignature>, MemoryError> {
use crate::signing::{Manifest, StoredSignature, from_hex};
let attrs = file
.group("meta")
.and_then(|g| g.attrs())
.map_err(|e| MemoryError::Schema(format!("cannot read /meta attrs: {e}")))?;
let attrs = meta_attrs(file)?;
let version = match attrs.get(SIG_VERSION_ATTR) {
None => return Ok(None),
Some(AttrValue::I64(v)) => *v,
@@ -552,18 +573,14 @@ pub fn read_signature(
/// Read the checkpoint bookkeeping from `/meta`.
pub fn read_checkpoint_meta(file: &clawhdf5::File) -> CheckpointMeta {
let ann_generation = file
.group("meta")
.ok()
.and_then(|g| g.attrs().ok())
.and_then(|attrs| match attrs.get(ANN_GENERATION_ATTR) {
Some(AttrValue::I64(v)) => Some(*v as u64),
_ => None,
});
let signed = file
.group("meta")
.and_then(|g| g.attrs())
.is_ok_and(|attrs| attrs.contains_key(SIG_VERSION_ATTR));
let ann_generation =
meta_attrs(file)
.ok()
.and_then(|attrs| match attrs.get(ANN_GENERATION_ATTR) {
Some(AttrValue::I64(v)) => Some(*v as u64),
_ => None,
});
let signed = meta_attrs(file).is_ok_and(|attrs| attrs.contains_key(SIG_VERSION_ATTR));
CheckpointMeta {
wal_applied: read_wal_mark(file),
ann_generation,
@@ -575,12 +592,7 @@ pub fn validate_and_load(
file: &clawhdf5::File,
) -> Result<(MemoryConfig, MemoryCache, SessionCache, KnowledgeCache), MemoryError> {
// Read /meta group attributes
let meta = file
.group("meta")
.map_err(|e| MemoryError::Schema(format!("missing /meta group: {e}")))?;
let attrs = meta
.attrs()
.map_err(|e| MemoryError::Schema(format!("cannot read /meta attrs: {e}")))?;
let attrs = meta_attrs(file)?;
let schema_version = match attrs.get("schema_version") {
Some(AttrValue::String(s)) => s.clone(),