LLLin000 0dfbf2a68d feat: PR 8 — Object Vector Retrieval (paperforge_objects collection) ... New paperforge_objects collection in ChromaDB for figure/table caption vector search, completing the memory layer retrieval triad: paperforge_fulltext → legacy_chunk paperforge_body → body_unit paperforge_objects → object_unit (NEW) Changes: - manifest.py: compute_object_units_hash(), manifest records both hashes - _chroma.py: _COLLECTION_NAMES includes paperforge_objects - builder.py: get_object_units_for_embedding() + embed_object_units() - status.py: object_chunk_count, total_chunks - state_snapshot.py: write_vector_runtime() extended with new fields - search.py: 3rd collection, dict-based source mapping, object_kind/label - __init__.py: exports for new functions - commands/embed.py: _has_object_units_in_db, body+object structured path routing with dual-hash resume, extended counters - Test fix: test_build_paper_manifest data complete for hash functions Verification: 20 object vectors embedded, all per-paper counts match, status total consistent (58266 = 57435 + 811 + 20), object caption queries return object_unit results via merge_retrieve. Unit tests: 153 pass, 1 skip.		2026-07-06 19:58:46 +08:00
..
memory-layer-functional-test-plan.md	fix: PR 7 post-test hardening — object units, node_id, expanded tests	2026-07-06 19:34:05 +08:00
memory-layer-implementation-plan.md	feat: PR 1 — nested structure tree + body_units correctness	2026-07-06 16:42:08 +08:00
memory-layer-test-report.md	fix: PR 7 post-test hardening — object units, node_id, expanded tests	2026-07-06 19:34:05 +08:00
pr-2-and-pr-3.md	feat: improve vnext figure matching and split OCR status	2026-07-06 00:55:40 +08:00
pr8-object-vector-retrieval-plan.md	feat: PR 8 — Object Vector Retrieval (paperforge_objects collection)	2026-07-06 19:58:46 +08:00