Stabilize Meeting Lab pipeline for RC1 evaluation
This commit significantly improves the robustness and determinism of the Meeting Lab processing pipeline and establishes the first Release Candidate baseline for end-to-end evaluation. Highlights - BUG-009 - Implement deterministic responsible-party validation - Normalize participant aliases using Meeting Context - Reject invalid responsible values (dates, locations, technical terms, projects, products, unknown entities) - Record structured responsibility validation metadata - Add focused regression tests - BUG-010 - Implement adaptive num_predict estimation for Semantic Consolidator - Eliminate JSON truncation caused by fixed output limits - Add deterministic source coverage repair - Preserve strict post-repair validation - Add regression tests - BUG-011 - Implement Working Protocol V2 renderer contract enforcement - Preserve raw renderer responses - Reject invalid protocol output instead of accepting malformed documents - Add deterministic cleanup for harmless formatting deviations - Add focused renderer regression tests - Meeting Context - Validate Meeting Context V1 - Integrate authoritative participant alias normalization - Documentation - Update architecture documentation - Update output documentation - Update regression bug tracker The pipeline now fails safely instead of silently accepting invalid intermediate or final artifacts. Remaining work focuses primarily on extraction quality and semantic classification (decisions, action items, protocol faithfulness), rather than pipeline robustness.
This commit is contained in:
@@ -19,6 +19,8 @@ EMPTY_EXTRACTION = {
|
||||
"technical": [],
|
||||
}
|
||||
|
||||
PROGEO_CONTEXT = Path("samples/real_live/progeo_meeting/meeting_context.yaml")
|
||||
|
||||
|
||||
def write_extraction(directory: Path, name: str, data: dict) -> Path:
|
||||
path = directory / name
|
||||
@@ -163,6 +165,102 @@ class CanonicalizeTests(unittest.TestCase):
|
||||
self.assertEqual(output["stats"]["input_item_count"], 0)
|
||||
self.assertEqual(output["stats"]["output_item_count"], 0)
|
||||
|
||||
def test_responsible_aliases_normalize_with_meeting_context(self) -> None:
|
||||
with tempfile.TemporaryDirectory() as directory:
|
||||
root = Path(directory)
|
||||
data = dict(EMPTY_EXTRACTION)
|
||||
data["todos"] = [
|
||||
{"task": "A", "responsible": "Martin", "deadline": None, "evidence": "e"},
|
||||
{"task": "B", "responsible": "Herr Tazl", "deadline": None, "evidence": "e"},
|
||||
{"task": "C", "responsible": "Marlene", "deadline": None, "evidence": "e"},
|
||||
{"task": "D", "responsible": "Gothard", "deadline": None, "evidence": "e"},
|
||||
{"task": "E", "responsible": "Henning", "deadline": None, "evidence": "e"},
|
||||
]
|
||||
write_extraction(root, "chunk_01_extraction.json", data)
|
||||
|
||||
output = canonicalize_extractions(root, meeting_context_path=PROGEO_CONTEXT)
|
||||
responsibles = [item["responsible"] for item in output["items"]]
|
||||
|
||||
self.assertEqual(
|
||||
responsibles,
|
||||
["Martin", "Martin", "Marleen", "Gotthard", "Henning"],
|
||||
)
|
||||
self.assertEqual(output["stats"]["responsibility_rejection_count"], 0)
|
||||
self.assertEqual(output["stats"]["responsibility_normalization_count"], 3)
|
||||
|
||||
def test_invalid_responsible_values_are_cleared_with_validation_report(self) -> None:
|
||||
invalid_values = [
|
||||
"31. August",
|
||||
"15. oder 16. September",
|
||||
"27.8.",
|
||||
"am 31.",
|
||||
"morgen",
|
||||
"nächste Woche",
|
||||
"Frankfurt",
|
||||
"Progeo",
|
||||
"Secugrid",
|
||||
"8:30 Uhr",
|
||||
"Unbekannte Person",
|
||||
]
|
||||
with tempfile.TemporaryDirectory() as directory:
|
||||
root = Path(directory)
|
||||
data = dict(EMPTY_EXTRACTION)
|
||||
data["todos"] = [
|
||||
{
|
||||
"task": f"Task {index}",
|
||||
"responsible": value,
|
||||
"deadline": None,
|
||||
"evidence": "e",
|
||||
}
|
||||
for index, value in enumerate(invalid_values, start=1)
|
||||
]
|
||||
data["todos"].append(
|
||||
{
|
||||
"task": "Null task",
|
||||
"responsible": None,
|
||||
"deadline": None,
|
||||
"evidence": "e",
|
||||
}
|
||||
)
|
||||
write_extraction(root, "chunk_01_extraction.json", data)
|
||||
|
||||
output = canonicalize_extractions(root, meeting_context_path=PROGEO_CONTEXT)
|
||||
|
||||
self.assertTrue(all(item["responsible"] is None for item in output["items"]))
|
||||
self.assertEqual(
|
||||
output["stats"]["responsibility_rejection_count"],
|
||||
len(invalid_values),
|
||||
)
|
||||
rejected = output["responsibility_validations"]
|
||||
self.assertEqual([item["original_value"] for item in rejected], invalid_values)
|
||||
self.assertTrue(all(item["cleared_to_null"] for item in rejected))
|
||||
|
||||
def test_null_responsible_remains_valid_without_warning(self) -> None:
|
||||
with tempfile.TemporaryDirectory() as directory:
|
||||
root = Path(directory)
|
||||
data = dict(EMPTY_EXTRACTION)
|
||||
data["todos"] = [
|
||||
{"task": "Task", "responsible": None, "deadline": None, "evidence": "e"}
|
||||
]
|
||||
write_extraction(root, "chunk_01_extraction.json", data)
|
||||
|
||||
output = canonicalize_extractions(root, meeting_context_path=PROGEO_CONTEXT)
|
||||
|
||||
self.assertIsNone(output["items"][0]["responsible"])
|
||||
self.assertEqual(output["responsibility_validations"], [])
|
||||
|
||||
def test_responsible_validation_does_not_run_without_meeting_context(self) -> None:
|
||||
with tempfile.TemporaryDirectory() as directory:
|
||||
root = Path(directory)
|
||||
data = dict(EMPTY_EXTRACTION)
|
||||
data["todos"] = ["Update docs | Mira | Friday | I will update docs"]
|
||||
write_extraction(root, "chunk_01_extraction.json", data)
|
||||
|
||||
output = canonicalize_extractions(root)
|
||||
|
||||
self.assertEqual(output["items"][0]["responsible"], "Mira")
|
||||
self.assertEqual(output["responsibility_validations"], [])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
Reference in New Issue
Block a user