dan/memory
1
0
Fork 0
mirror of https://github.com/mruwnik/memory.git synced 2026-01-02 17:22:58 +01:00
Code Issues 1 Packages Projects Releases Wiki Activity

Add TODO note for re-indexing existing book chunks

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
mruwnik 2025-12-19 21:05:29 +00:00
parent 9a0f226972
commit d2164a49eb
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
INVESTIGATION.md
View File

@ -48,6 +48,7 @@ This investigation identified **100+ issues** across 7 areas of the memory syste
- **Root Cause:** `extract_text()` defaults to `modality="text"` but BookSection didn't override it - **Root Cause:** `extract_text()` defaults to `modality="text"` but BookSection didn't override it
- **Fix Applied:** Added `modality="book"` to BookSection._chunk_contents() DataChunk creation - **Fix Applied:** Added `modality="book"` to BookSection._chunk_contents() DataChunk creation
- **Note:** Original 1,338 mail items investigation was outdated - current mismatch is 24 mail->text chunks which are actually email attachments (correct behavior) - **Note:** Original 1,338 mail items investigation was outdated - current mismatch is 24 mail->text chunks which are actually email attachments (correct behavior)
- **TODO:** Existing 9,370 book chunks need re-indexing to move from text to book collection
### BUG-003: BM25 Filters Completely Ignored ### BUG-003: BM25 Filters Completely Ignored
- **Severity:** CRITICAL - **Severity:** CRITICAL