fix: metadata explosion bug - 69K files reduced to ~1K

Critical fix for metadata indexing that was creating 60+ chunk files per entity.

Root cause: Vector embeddings (384-dimensional arrays) were being indexed in
metadata, causing each dimension to create a separate chunk file with numeric
field names ("0", "1", "2", etc.).

Changes:
- Modified extractIndexableFields() to exclude vector/embedding fields
- Added NEVER_INDEX set: ['vector', 'embedding', 'embeddings', 'connections']
- Added safety check to skip arrays > 10 elements
- Preserves small array indexing (tags, categories, roles)

Impact:
- Reduces metadata files from 69,429 → ~1,200 (58x reduction)
- Fixes server initialization hangs
- Fixes metadata batch loading stalling at batch 23
- Fixes VFS getDescendants() hanging with large datasets
- Fixes Graph View UI not loading

Test Results:
- 7/7 integration tests passing
- Verified: 6 chunk files for 10 entities (was 7,210 before fix)
- 611/622 unit tests passing

Files Modified:
- src/utils/metadataIndex.ts - Core fix
- src/coreTypes.ts - HNSWVerb type enforcement with VerbType enum
- src/storage/adapters/* - Include core relational fields in HNSWVerb
- src/storage/adapters/baseStorageAdapter.ts - Type enforcement (HNSWNoun, GraphVerb)
- tests/integration/metadata-vector-exclusion.test.ts - Comprehensive test coverage

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
David Snelling 2025-10-16 16:10:31 -07:00
parent 7921a5b744
commit e600865d96
13 changed files with 571 additions and 112 deletions

View file

@ -1515,12 +1515,19 @@ export class S3CompatibleStorage extends BaseStorage {
// Convert connections Map to a serializable format
// CRITICAL: Only save lightweight vector data (no metadata)
// Metadata is saved separately via saveVerbMetadata() (2-file system)
// ARCHITECTURAL FIX (v3.50.1): Include core relational fields in verb vector file
const serializableEdge = {
id: edge.id,
vector: edge.vector,
connections: this.mapToObject(edge.connections, (set) =>
Array.from(set as Set<string>)
)
),
// CORE RELATIONAL DATA (v3.50.1+)
verb: edge.verb,
sourceId: edge.sourceId,
targetId: edge.targetId,
// NO metadata field - saved separately for scalability
}
@ -1640,10 +1647,19 @@ export class S3CompatibleStorage extends BaseStorage {
connections.set(Number(level), new Set(nodeIds as string[]))
}
// ARCHITECTURAL FIX (v3.50.1): Return HNSWVerb with core relational fields
const edge = {
id: parsedEdge.id,
vector: parsedEdge.vector,
connections
connections,
// CORE RELATIONAL DATA (read from vector file)
verb: parsedEdge.verb,
sourceId: parsedEdge.sourceId,
targetId: parsedEdge.targetId,
// User metadata (retrieved separately via getVerbMetadata())
metadata: parsedEdge.metadata
}
this.logger.trace(`Successfully retrieved edge ${id}`)