2 Commits

Author SHA1 Message Date
Oleksandr Kozachuk 2caa18a17f igdb search + capped http reads: native fulltext, full-page fetch
search_games used `where name ~ "<q>"*`: prefix-only, diacritic- and
word-order-sensitive -- "MARVEL Tōkon" found nothing though IGDB has
it. Switch to IGDB's native `search` clause (relevance-ranked,
diacritic-insensitive).

fetch_url and image downloads read bodies with content.read(n), which
returns only the first buffered chunk (~7 KB): pages collapsed to
their <title>. httpread.read_capped collects chunks up to the byte
cap; image downloads read limit+1 so over-limit files are still
rejected instead of cached truncated (IMG-10).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-13 19:29:16 +02:00
Oleksandr Kozachuk e21c262299 image input pipeline: content-hash cache, data-url vision, picture_edit real 2026-07-13 16:33:48 +02:00