Ida a7f4055130 fix(rag): preserve per-page granularity + remove on-demand extraction fallbacks ... The default MergeStrategy concatenates every extracted text part into a single ContentPart, collapsing a 500-page PDF into one chunk with a blurred average embedding — RAG retrieval was effectively broken. - ExtractionOptions.mergeStrategy is now Optional[MergeStrategy]; passing None preserves per-part granularity. Default factory kept for backward compatibility. - routeDataFiles._autoIndexFile, _workspaceTools.readFile, and _documentTools.describeImage explicitly pass mergeStrategy=None. - Agent tools no longer carry redundant extraction + requestIngestion fallback paths: the unified ingestion lane owns all corpus writes, and readFile/describeImage are pure consumers of the knowledge store. - Unit test asserts runExtraction(mergeStrategy=None) keeps every part.		2026-04-29 14:39:40 +02:00
..
test_extraction_merge_strategy.py	fix(rag): preserve per-page granularity + remove on-demand extraction fallbacks	2026-04-29 14:39:40 +02:00
test_featureDataAgent_schema.py	trustee agent fix	2026-04-27 08:07:37 +02:00
test_json_extraction_merging.py	fixes	2026-04-23 23:09:38 +02:00
test_renderer_pdf_smoke.py	Graph and data class falignment strict	2026-04-26 22:53:44 +02:00