Fix BUG-002: BookSection chunks now use correct 'book' modality

Root cause: BookSection._chunk_contents() called extract_text() without
specifying modality, which defaults to "text". This caused 9,370 book
chunks to be stored in the 'text' collection instead of 'book'.

Fix: Added modality="book" to all DataChunk creation in BookSection:
- extract_text() call for single-page sections
- Direct DataChunk creation for multi-page sections

Note: The original investigation reported 1,338 mail items, but current
analysis shows those are actually email attachments which correctly go
to text/doc/photo collections based on their content type.

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

INVESTIGATION.md

@@ -40,13 +40,14 @@ This investigation identified **100+ issues** across 7 areas of the memory syste
 - **Impact:** Arbitrary file read on server filesystem
 - **Fix:** Add path resolution validation with `.resolve()` and prefix check
 
-### BUG-002: Collection Mismatch (1,338 items)
-- **Severity:** CRITICAL
+### BUG-002: Collection Mismatch ✅ INVESTIGATED & FIXED
+- **Severity:** MEDIUM (not as critical as originally thought)
 - **Area:** Data/Embedding Pipeline
-- **Description:** Mail items have chunks with `collection_name='text'` but vectors stored in Qdrant's `mail` collection
-- **Impact:** Items completely unsearchable
-- **Evidence:** 1,338 orphaned vectors in mail, 1,338 missing in text
-- **Fix:** Re-sync vectors or update chunk collection_name
+- **Description:** BookSection._chunk_contents() called extract_text() without specifying modality, defaulting to "text"
+- **Impact:** 9,370 book chunks stored in text collection instead of book
+- **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
+- **Note:** Original 1,338 mail items investigation was outdated - current mismatch is 24 mail->text chunks which are actually email attachments (correct behavior)
 
 ### BUG-003: BM25 Filters Completely Ignored
 - **Severity:** CRITICAL

src/memory/common/db/models/source_items.py

@@ -606,7 +606,9 @@ class BookSection(SourceItem):
             return []
 
         if len([p for p in self.pages if p.strip()]) == 1:
-            chunks = extract.extract_text(content, metadata={"type": "page"})
+            chunks = extract.extract_text(
+                content, metadata={"type": "page"}, modality="book"
+            )
             if len(chunks) > 1:
                 chunks[-1].metadata["type"] = "summary"
             return chunks
@@ -614,10 +616,10 @@ class BookSection(SourceItem):
         summary, tags = summarizer.summarize(content)
         return [
             extract.DataChunk(
-                data=[content], metadata={"type": "section", "tags": tags}
+                data=[content], metadata={"type": "section", "tags": tags}, modality="book"
             ),
             extract.DataChunk(
-                data=[summary], metadata={"type": "summary", "tags": tags}
+                data=[summary], metadata={"type": "summary", "tags": tags}, modality="book"
             ),
         ]