eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Implemented the grammar LLM review module

Browse Source
This commit is contained in:
Eric Rakestraw
2026-04-25 09:06:06 -05:00
parent 52d29f7228
commit 4724cd16c8
12 changed files with 471 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
tests/test_new_pipeline.py
View File

@@ -61,6 +61,7 @@ def test_process_transcript_runs_noop_framework(tmp_path):
{"corrections": []},
{"corrections": []},
{"corrections": []},
{"corrections": []},
]
)
revised = process_transcript(
@@ -78,6 +79,7 @@ def test_process_transcript_runs_noop_framework(tmp_path):
"homophones:proposal",
"glossary_2:proposal",
"spoken_word:proposal",
"grammar:proposal",
]
@@ -93,7 +95,9 @@ def test_process_transcript_result_writes_report_and_preserves_skips_per_policy(
max_retries=config.max_retries,
max_section_tokens=config.max_section_tokens,
glossary_confidence_threshold=config.glossary_confidence_threshold,
grammar_confidence_threshold=config.grammar_confidence_threshold,
homophones_confidence_threshold=config.homophones_confidence_threshold,
spoken_word_confidence_threshold=config.spoken_word_confidence_threshold,
normalize_max_segment_gap=config.normalize_max_segment_gap,
normalize_ellipsis_gap=config.normalize_ellipsis_gap,
normalize_max_segment_duration=config.normalize_max_segment_duration,
@@ -108,6 +112,7 @@ def test_process_transcript_result_writes_report_and_preserves_skips_per_policy(
{"corrections": []},
{"corrections": []},
{"corrections": []},
{"corrections": []},
]
)
result = process_transcript_result(_transcript(), _glossary(), config, llm_client=llm_client)
@@ -135,6 +140,12 @@ def test_process_transcript_result_writes_report_and_preserves_skips_per_policy(
"spoken_word_review",
"meaning_reversal_review",
]
assert [validator["name"] for validator in result.report.modules[4].to_dict()["validators"]] == [
"proposal_confidence_guard",
"protected_glossary_guard",
"grammar_only_guard",
"meaning_reversal_review",
]
def test_external_report_can_be_written(tmp_path):
@@ -145,6 +156,7 @@ def test_external_report_can_be_written(tmp_path):
{"corrections": []},
{"corrections": []},
{"corrections": []},
{"corrections": []},
]
)
result = process_transcript_result(_transcript(), _glossary(), config, llm_client=llm_client)
@@ -191,7 +203,12 @@ def test_default_module_specs_expose_final_validator_order():
"spoken_word_review",
"meaning_reversal_review",
]
assert [validator.name for validator in specs[4].module.validators()] == ["protected_glossary_guard"]
assert [validator.name for validator in specs[4].module.validators()] == [
"proposal_confidence_guard",
"protected_glossary_guard",
"grammar_only_guard",
"meaning_reversal_review",
]
def test_process_transcript_result_missing_api_key_writes_failed_report(tmp_path):
@@ -206,7 +223,9 @@ def test_process_transcript_result_missing_api_key_writes_failed_report(tmp_path
max_retries=config.max_retries,
max_section_tokens=config.max_section_tokens,
glossary_confidence_threshold=config.glossary_confidence_threshold,
grammar_confidence_threshold=config.grammar_confidence_threshold,
homophones_confidence_threshold=config.homophones_confidence_threshold,
spoken_word_confidence_threshold=config.spoken_word_confidence_threshold,
normalize_max_segment_gap=config.normalize_max_segment_gap,
normalize_ellipsis_gap=config.normalize_ellipsis_gap,
normalize_max_segment_duration=config.normalize_max_segment_duration,
@@ -257,7 +276,9 @@ def test_process_transcript_result_preserves_partial_progress_when_later_module_
max_retries=config.max_retries,
max_section_tokens=config.max_section_tokens,
glossary_confidence_threshold=config.glossary_confidence_threshold,
grammar_confidence_threshold=config.grammar_confidence_threshold,
homophones_confidence_threshold=config.homophones_confidence_threshold,
spoken_word_confidence_threshold=config.spoken_word_confidence_threshold,
normalize_max_segment_gap=config.normalize_max_segment_gap,
normalize_ellipsis_gap=config.normalize_ellipsis_gap,
normalize_max_segment_duration=config.normalize_max_segment_duration,
@@ -330,7 +351,9 @@ def test_process_transcript_result_preserves_partial_skips_and_validator_diagnos
max_retries=config.max_retries,
max_section_tokens=config.max_section_tokens,
glossary_confidence_threshold=0.8,
grammar_confidence_threshold=config.grammar_confidence_threshold,
homophones_confidence_threshold=config.homophones_confidence_threshold,
spoken_word_confidence_threshold=config.spoken_word_confidence_threshold,
normalize_max_segment_gap=config.normalize_max_segment_gap,
normalize_ellipsis_gap=config.normalize_ellipsis_gap,
normalize_max_segment_duration=config.normalize_max_segment_duration,
@@ -404,7 +427,7 @@ def test_process_transcript_result_supports_grammar_only_module_override(tmp_pat
_glossary(),
config,
module_keys=["grammar"],
llm_client=FakeStructuredLLMClient([]),
llm_client=FakeStructuredLLMClient([{"corrections": []}]),
)
assert [segment.id for segment in result.transcript] == [1, 2]