Added includeVFS parameter to FindParams:
- brain.find() excludes VFS entities by default (clean knowledge graph)
- Opt-in with brain.find({ includeVFS: true })
- Automatically excludes VFS in all query paths (empty, metadata, vector)
- Respects explicit where: { isVFS: ... } queries
Implementation:
- Empty query path: Apply VFS filtering even with no criteria
- Metadata query path: Filter out isVFS: true by default
- Vector search path: Apply VFS filter after search
- Skip auto-exclusion if where clause explicitly queries isVFS
Architecture (Option 3C):
- VFS entities are first-class graph entities
- Marked with isVFS: true flag
- Separated via filtering, not storage
- Enables VFS-knowledge relationships
Moved internal docs to .strategy/:
- README_STORAGE_EXPLORATION.md
- EXPLORATION_SUMMARY.md
- STORAGE_FILES_REFERENCE.md
- STORAGE_ADAPTER_QUICK_REFERENCE.md
- SECURITY.md
|
||
|---|---|---|
| .. | ||
| buildEmbeddedPatterns.ts | ||
| buildKeywordEmbeddings.ts | ||
| buildTypeEmbeddings.ts | ||
| check-keyword-embeddings.cjs | ||
| check-patterns.cjs | ||
| check-type-embeddings.cjs | ||
| create-models-release.sh | ||
| diagnose-workshop-issue.ts | ||
| download-models.cjs | ||
| ensure-models.js | ||
| migrate-to-structured-logger.ts | ||
| prepare-models.js | ||
| release.sh | ||
| setup-github-models.sh | ||
| test-with-memory.sh | ||
| update-augmentations-metadata.sh | ||