Files
DocsGPT/tests/worker
arc53-machine d787f54c2d Keep the chunker's metadata when re-embedding a wiki page
`reembed_wiki_page_worker` built each chunk's metadata from scratch as
`{source, title, filename}`, discarding everything the chunker attached
to the document -- including the per-chunk `token_count` every other
ingest path records. Wiki chunks therefore reached the source viewer
with no count at all.

Carry `extra_info` over and let the page's own path and title win on top,
so a chunk that inherited a stale source from an earlier conversion is
still keyed and filtered correctly.
2026-09-22 13:44:24 +01:00
..
2026-04-18 13:13:57 +01:00