feat: add post-diarization speaker mapping workflow

This commit is contained in:
2026-08-25 15:30:16 +02:00
parent df89a38829
commit 8a0f38fce4
6 changed files with 233 additions and 2 deletions
+59
View File
@@ -142,6 +142,65 @@ class MvpApiTests(unittest.TestCase):
],
)
self.assertTrue(all(event.progress is None for event in events))
self.assertEqual(protocol_generator.call_args.kwargs["num_ctx"], 32_768)
self.assertEqual(
protocol_generator.call_args.kwargs["safe_input_token_budget"],
29_000,
)
def test_protocol_only_regeneration_reuses_diarized_artifacts(self):
with tempfile.TemporaryDirectory() as directory:
root = Path(directory)
run_dir = root / "existing-run"
diarization_dir = run_dir / "diarization"
diarization_dir.mkdir(parents=True)
source = diarization_dir / "transcript_diarized.json"
source.write_text(
json.dumps(
{
"text": "SPEAKER_00: Existing statement.\n",
"segments": [
{
"start": 0.0,
"end": 1.0,
"speaker_id": "SPEAKER_00",
"text": "Existing statement.",
}
],
"speaker_labels_anonymous": True,
}
),
encoding="utf-8",
)
source_before = source.read_bytes()
mapped_context = context_data()
mapped_context["speaker_mappings"] = {"SPEAKER_00": "person-1"}
with (
patch.object(mvp_api, "prepare_audio") as preparation,
patch.object(mvp_api, "transcribe_audio") as transcription,
patch.object(mvp_api, "diarize_audio") as diarization,
patch.object(
mvp_api, "generate_direct_protocol", side_effect=fake_protocol
) as protocol,
):
result = mvp_api.regenerate_mvp_protocol(
run_dir,
meeting_context=mapped_context,
model="qwen3.8:27b",
protocol_num_ctx=32_768,
protocol_safe_input_token_budget=29_000,
)
self.assertEqual(result.exit_code, 0)
self.assertEqual(result.protocol_path, run_dir / "protocol.md")
preparation.assert_not_called()
transcription.assert_not_called()
diarization.assert_not_called()
self.assertEqual(protocol.call_args.args[0], source)
self.assertEqual(protocol.call_args.kwargs["num_ctx"], 32_768)
self.assertEqual(source.read_bytes(), source_before)
persisted = load_meeting_context(run_dir / "context/meeting_context.yaml")
self.assertEqual(persisted.speaker_mappings, {"SPEAKER_00": "person-1"})
def test_failure_emits_terminal_failure_event(self):
with tempfile.TemporaryDirectory() as directory: