More bugfixes in the glossary protection guard module

This commit is contained in:
2026-04-22 12:17:52 -05:00
parent 15cdf01f58
commit 87c47517a0
9 changed files with 269 additions and 28 deletions

View File

@@ -2,7 +2,8 @@ import pytest
from audita.corrections import apply_corrections
from audita.errors import AuditaValidationError
from audita.schemas import CorrectionCandidate, parse_transcript_json
from audita.protection import ProtectedVocabulary
from audita.schemas import CorrectionCandidate, parse_glossary_yaml, parse_transcript_json
def _transcript():
@@ -200,6 +201,44 @@ def test_apply_corrections_skips_when_guard_rejects_replacement():
assert result.skipped[0].actual_text == "Hrank moves."
def test_apply_corrections_guards_only_replacement_span():
transcript = parse_transcript_json(
"""
[
{"id": 1, "speaker": "Eric", "start": 0.0, "end": 1.0, "text": "You have to keep it bind. Svend sees the jesters."}
]
"""
)
glossary = parse_glossary_yaml(
"""
glossary:
- name: "Svend"
category: pc
summary: "Svend is a player character."
- name: "Jesters"
category: faction
summary: "The Jesters are a faction."
"""
)
correction = CorrectionCandidate(
id=1,
original_text="keep it bind",
corrected_text="keep in mind",
confidence=0.8,
)
result = apply_corrections(
transcript,
[correction],
confidence_threshold=0.8,
replacement_mode="require_unique",
correction_guard=ProtectedVocabulary.from_glossary(glossary).violation_reason,
)
assert result.transcript[0].text == "You have to keep in mind. Svend sees the jesters."
assert result.skipped == []
def test_apply_corrections_without_guard_remains_permissive():
transcript = parse_transcript_json(
"""