호출 하나에 언어 하나, 빌드가 강제해

HANGUL = re.compile(r"[\uac00-\ud7a3]")
LATIN  = re.compile(r"[A-Za-z]")

def check_segment_language_purity(segments: list[Segment]) -> list[str]:
    """A segment carrying two scripts is a build failure.

    Digits and punctuation are exempt - they are read the same way
    by either voice, so they do not trigger the mispronunciation.
    """
    errors = []
    for seg in segments:
        has_hangul = bool(HANGUL.search(seg.text))
        has_latin = bool(LATIN.search(seg.text))
        if has_hangul and has_latin:
            errors.append(
                f"{seg.key}: mixed script in one synthesis call -"
                f" split at the meaning boundary or transliterate."
                f"  text={seg.text!r}"
            )
    return errors


# Note what this is NOT: a warning, a lint suggestion, a note in
# the style guide. It fails the build, because the defect it
# prevents is intermittent and would otherwise ship.

BAD    one request, both scripts
       "그 사람이 pipeline 이라고 불렀어"
       -> pronunciation is a dice roll on every synthesis

WORSE  splice a one-word foreign call into the line
       [ko run] + [1-word en call] + [ko run]
       -> the gap reads as a hiccup, not a quotation

GOOD   transliterate into the run's own script
       "그 사람이 파이프라인이라고 불렀어"
       -> one script, one call, no gamble

ALSO GOOD   if the term must stay in its original form,
            the whole line is in that language, and the
            switch happens at a meaning boundary.