Commit graph

1 commit

Author SHA1 Message Date
Yun Chan
bcd0cf4f23 fix(meeting): keep learned text from injecting prompt lines
Learned text becomes part of a prompt, so a dictionary word or phrase
containing a newline could add its own instruction line. Every value that
reaches the recognition hint or the polish block is now flattened to one
line and length-capped, and a test proves an injected line stays plain text.

Also cover the invariants that keep the correction safe (random inputs,
Hangul untouched, idempotent, no token growth, large transcript) and the
file-transcription wiring that attaches the learned hint to every chunk and
corrects each chunk and segment before it is stored.
2026-11-06 23:00:29 +09:00