- Changed extract_xlsx_text() to use open_workbook() instead of open_workbook_from_rs()
- Changed extract_xls_text() to use open_workbook() instead of open_workbook_from_rs()
- The calamine 0.26 API uses open_workbook(path) for direct file access
- This matches the pattern used in import_export.rs and vectordb.rs
- Updated AGENTS.md to clarify bots are stored as MinIO buckets
- Added test start.bas with USE KB "sheetlib" for testing KB injection
Root cause: open_workbook_from_rs() is not the correct API for calamine 0.26
Impact: XLSX and XLS files in .gbkb folders were failing to index into vector DB
Fix: Use standard open_workbook() API that accepts file path directly
- Replace docs/sheet/slides with kb-extraction in default features (~4-6min compile time savings, ~300MB less disk)
- Add kb-extraction feature using zip+quick-xml+calamine for lightweight KB extraction
- Split document_processor.rs (829 lines) into mod.rs+types.rs+ooxml_extract.rs+rtf.rs
- Move DOCX/PPTX ZIP-based extraction to document_processor::ooxml_extract (no ooxmlsdk needed)
- Remove dead code: save_docx_preserving(), save_pptx_preserving() (zero callers)
- Fix dep: prefix for optional dependencies in feature definitions
- DriveMonitor: full S3 sync, ETag change detection, KB incremental indexing, config.csv sync
- ConfigManager: real DB reads from bot_configuration table
- 0 warnings, 0 errors on both default and full feature builds
