Add diarization and reusable MVP meeting pipeline

tests/test_mvp_api.py

@@ -0,0 +1,175 @@
+import json
+import subprocess
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch
+
+from scripts import run_mvp_meeting as cli
+from src.meeting_lab.models.meeting_context import load_meeting_context
+from src.meeting_lab.orchestration import mvp as mvp_api
+from src.meeting_lab.orchestration.mvp import MvpMeetingConfig, MvpRunResult
+from src.meeting_lab.protocol.generate_direct_protocol import DirectProtocolResult
+from src.meeting_lab.transcription.whisper import TranscriptionError, TranscriptionResult
+
+
+def context_data():
+    return {
+        "schema_version": "1",
+        "meeting": {
+            "meeting_id": "programmatic-test",
+            "title": "Programmatic Test",
+            "language": "de",
+            "date": None,
+            "objective": "API prüfen",
+            "notes": "",
+        },
+        "participants": [
+            {
+                "participant_id": "person-1",
+                "display_name": "Test Person",
+                "aliases": [],
+                "role": "Projektleitung",
+                "department": None,
+                "attendance_status": "present",
+                "notes": None,
+            }
+        ],
+        "speaker_mappings": {"SPEAKER_00": "person-1"},
+        "mentioned_people": [],
+        "organization": {"name": "Example", "departments": []},
+        "known_entities": {},
+        "context_rules": {"do_not_infer_responsibilities": True},
+    }
+
+
+def fake_transcribe(audio, model, output, language, **kwargs):
+    output.mkdir(parents=True, exist_ok=True)
+    raw = output / "whisper_raw.json"
+    transcript = output / "transcript.json"
+    text = output / "transcript.txt"
+    metadata = output / "runtime_metadata.json"
+    raw.write_text('{"transcription": []}\n', encoding="utf-8")
+    transcript.write_text(
+        json.dumps(
+            {
+                "text": "Ein kurzer Besprechungstext.",
+                "segments": [
+                    {
+                        "id": 0,
+                        "start": 0.0,
+                        "end": 1.0,
+                        "text": "Ein kurzer Besprechungstext.",
+                    }
+                ],
+            }
+        ),
+        encoding="utf-8",
+    )
+    text.write_text("Ein kurzer Besprechungstext.\n", encoding="utf-8")
+    metadata.write_text('{"runtime_seconds": 0.1}\n', encoding="utf-8")
+    return TranscriptionResult(output, raw, transcript, text, metadata, 0.1)
+
+
+def fake_protocol(transcript, context, **kwargs):
+    rendered_context = load_meeting_context(context)
+    assert rendered_context.meeting_id == "programmatic-test"
+    return DirectProtocolResult(
+        protocol_text="# Meeting Protocol\n",
+        exact_prompt="prompt",
+        model_metadata={"model": kwargs["model"]},
+        runtime_metadata={"request_count": 1},
+        raw_response={"response": "# Meeting Protocol\n"},
+    )
+
+
+class MvpApiTests(unittest.TestCase):
+    def config(self, root: Path):
+        audio = root / "meeting.wav"
+        model = root / "model.bin"
+        audio.write_bytes(b"audio")
+        model.write_bytes(b"model")
+        return MvpMeetingConfig(
+            audio_file=audio,
+            whisper_model=model,
+            output_root=root / "runs",
+            model="test:model",
+        )
+
+    def test_programmatic_context_is_persisted_without_source_yaml(self):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            config = self.config(root)
+            events = []
+            with (
+                patch.object(mvp_api, "transcribe_audio", side_effect=fake_transcribe),
+                patch.object(
+                    mvp_api, "generate_direct_protocol", side_effect=fake_protocol
+                ),
+                patch.object(subprocess, "run") as subprocess_run,
+            ):
+                result = mvp_api.run_mvp_meeting(
+                    config, meeting_context=context_data(), progress_sink=events.append
+                )
+
+            self.assertEqual(result.exit_code, 0)
+            context_path = result.run_dir / "context/meeting_context.yaml"
+            self.assertTrue(context_path.is_file())
+            persisted = load_meeting_context(context_path)
+            self.assertEqual(persisted.meeting_id, "programmatic-test")
+            self.assertEqual(persisted.speaker_mappings, {"SPEAKER_00": "person-1"})
+            subprocess_run.assert_not_called()
+            self.assertEqual(
+                [(event.stage, event.status) for event in events],
+                [
+                    ("preparing", "started"),
+                    ("preparing", "completed"),
+                    ("transcription", "started"),
+                    ("transcription", "completed"),
+                    ("protocol_generation", "started"),
+                    ("protocol_generation", "completed"),
+                    ("completed", "completed"),
+                ],
+            )
+            self.assertTrue(all(event.progress is None for event in events))
+
+    def test_failure_emits_terminal_failure_event(self):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            config = self.config(root)
+            events = []
+            with patch.object(
+                mvp_api,
+                "transcribe_audio",
+                side_effect=TranscriptionError("stopped"),
+            ):
+                result = mvp_api.run_mvp_meeting(config, progress_sink=events.append)
+
+            self.assertEqual(result.exit_code, 2)
+            self.assertEqual(events[-1].stage, "failed")
+            self.assertEqual(events[-1].status, "failed")
+            self.assertIn("transcription", events[-1].message)
+            metadata = json.loads((result.run_dir / "run_metadata.json").read_text())
+            self.assertEqual(metadata["status"], "failed")
+
+    def test_cli_defaults_and_wrapper_delegate_without_subprocess(self):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            config = self.config(root)
+            args = cli.parse_args(
+                [str(config.audio_file), "--whisper-model", str(config.whisper_model)]
+            )
+            expected = MvpRunResult(0, root / "run", root / "run/protocol.md")
+            with patch.object(cli, "run_mvp_meeting", return_value=expected) as api:
+                actual = cli.run(args, context_override=context_data())
+
+            self.assertEqual(actual, (0, expected.run_dir, expected.protocol_path))
+            delegated = api.call_args.args[0]
+            self.assertEqual(delegated.diarization, "off")
+            self.assertEqual(delegated.language, "de")
+            self.assertEqual(delegated.whisper_executable, "whisper-cli")
+            self.assertEqual(api.call_args.kwargs["meeting_context"], context_data())
+
+
+if __name__ == "__main__":
+    unittest.main()