Add diarization and reusable MVP meeting pipeline

This commit is contained in:
2026-08-23 19:29:47 +02:00
parent f2d21c1faf
commit 8dab928763
18 changed files with 1697 additions and 180 deletions
+47
View File
@@ -11,8 +11,10 @@ from src.meeting_lab.extraction.extract_chunks import (
)
from src.meeting_lab.models.meeting_context import (
MeetingContextValidationError,
create_meeting_context,
load_meeting_context,
render_meeting_context_for_prompt,
serialize_meeting_context_yaml,
validate_meeting_context,
)
@@ -192,6 +194,51 @@ class MeetingContextTests(unittest.TestCase):
self.assertNotIn("responsible: Björn", prompt_context)
self.assertNotIn("responsible: Jovana", prompt_context)
def test_existing_context_without_speaker_mappings_remains_valid(self) -> None:
self.assertEqual(self.context.speaker_mappings, {})
self.assertIsNone(self.context.participant_for_speaker("SPEAKER_00"))
def test_explicit_speaker_mapping_is_authoritative(self) -> None:
data = copy.deepcopy(self.context.data)
participant = data["participants"][0]
data["speaker_mappings"] = {"SPEAKER_03": participant["participant_id"]}
context = create_meeting_context(data)
rendered = render_meeting_context_for_prompt(context)
self.assertEqual(
context.participant_for_speaker("SPEAKER_03")["participant_id"],
participant["participant_id"],
)
self.assertIsNone(context.participant_for_speaker("SPEAKER_04"))
self.assertIn("Confirmed diarization speaker mappings (authoritative)", rendered)
self.assertIn("Unmapped SPEAKER_XX labels must remain anonymous", rendered)
def test_speaker_mapping_must_reference_existing_participant(self) -> None:
data = copy.deepcopy(self.context.data)
data["speaker_mappings"] = {"SPEAKER_00": "unknown-person"}
with self.assertRaisesRegex(MeetingContextValidationError, "unknown participant"):
validate_meeting_context(data)
def test_speaker_mapping_label_must_use_pyannote_shape(self) -> None:
data = copy.deepcopy(self.context.data)
data["speaker_mappings"] = {
"Martin": data["participants"][0]["participant_id"]
}
with self.assertRaisesRegex(MeetingContextValidationError, "speaker label"):
validate_meeting_context(data)
def test_generated_context_yaml_is_deterministic_and_round_trips(self) -> None:
first = serialize_meeting_context_yaml(self.context)
second = serialize_meeting_context_yaml(self.context)
self.assertEqual(first, second)
SCRATCH_DIR.mkdir(exist_ok=True)
path = SCRATCH_DIR / "generated_context.yaml"
path.write_text(first, encoding="utf-8")
loaded = load_meeting_context(path)
self.assertEqual(loaded.data, self.context.data)
if __name__ == "__main__":
unittest.main()