haiku.rag/haiku_rag_slim/haiku
Chris McDonough 8deac2fee8
Fix constant re-ingestion when server provides no revision header
HTTP, S3, and WebDAV sources all check `revision is not None and
snapshot.get(uri) == revision` to decide UPSERT vs UNCHANGED.  When
a server returns no ETag or Last-Modified, revision is None and the
condition always fails — every sweep emits UPSERT even though the
content hasn't changed.

Now emit UNCHANGED when revision is None and the URI is already
known (has been ingested before).  A first-time discovery with no
revision still correctly emits UPSERT.
2026-06-01 18:14:27 +03:00
..
rag Fix constant re-ingestion when server provides no revision header 2026-06-01 18:14:27 +03:00