Add canonical audio preparation and meeting context support

tests/test_mvp_api.py

@@ -1,11 +1,14 @@
 import json
+import shutil
 import subprocess
 import tempfile
 import unittest
+from dataclasses import replace
 from pathlib import Path
 from unittest.mock import patch
 
 from scripts import run_mvp_meeting as cli
+from src.meeting_lab.audio import PreparedAudio
 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
@@ -71,6 +74,12 @@ def fake_transcribe(audio, model, output, language, **kwargs):
     return TranscriptionResult(output, raw, transcript, text, metadata, 0.1)
 
 
+def fake_prepare(source, destination, **kwargs):
+    destination.parent.mkdir(parents=True, exist_ok=True)
+    shutil.copyfile(source, destination)
+    return PreparedAudio(source, source.suffix.removeprefix("."), destination, "ffmpeg", "ffmpeg")
+
+
 def fake_protocol(transcript, context, **kwargs):
     rendered_context = load_meeting_context(context)
     assert rendered_context.meeting_id == "programmatic-test"
@@ -103,6 +112,7 @@ class MvpApiTests(unittest.TestCase):
             events = []
             with (
                 patch.object(mvp_api, "transcribe_audio", side_effect=fake_transcribe),
+                patch.object(mvp_api, "prepare_audio", side_effect=fake_prepare),
                 patch.object(
                     mvp_api, "generate_direct_protocol", side_effect=fake_protocol
                 ),
@@ -142,7 +152,7 @@ class MvpApiTests(unittest.TestCase):
                 mvp_api,
                 "transcribe_audio",
                 side_effect=TranscriptionError("stopped"),
-            ):
+            ), patch.object(mvp_api, "prepare_audio", side_effect=fake_prepare):
                 result = mvp_api.run_mvp_meeting(config, progress_sink=events.append)
 
             self.assertEqual(result.exit_code, 2)
@@ -168,8 +178,72 @@ class MvpApiTests(unittest.TestCase):
             self.assertEqual(delegated.diarization, "off")
             self.assertEqual(delegated.language, "de")
             self.assertEqual(delegated.whisper_executable, "whisper-cli")
+            self.assertEqual(delegated.ffmpeg_executable, "ffmpeg")
+            self.assertTrue(delegated.audio_normalization)
             self.assertEqual(api.call_args.kwargs["meeting_context"], context_data())
 
+    def test_cli_explicit_audio_normalization_values_are_propagated(self):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            config = self.config(root)
+            enabled = cli.config_from_args(
+                cli.parse_args(
+                    [
+                        str(config.audio_file),
+                        "--whisper-model",
+                        str(config.whisper_model),
+                        "--audio-normalization",
+                    ]
+                )
+            )
+            disabled = cli.config_from_args(
+                cli.parse_args(
+                    [
+                        str(config.audio_file),
+                        "--whisper-model",
+                        str(config.whisper_model),
+                        "--no-audio-normalization",
+                    ]
+                )
+            )
+
+            self.assertTrue(enabled.audio_normalization)
+            self.assertFalse(disabled.audio_normalization)
+
+    def test_transcription_receives_prepared_wav_for_encoded_inputs(self):
+        for suffix in (".flac", ".m4a"):
+            with self.subTest(suffix=suffix), tempfile.TemporaryDirectory() as directory:
+                root = Path(directory)
+                config = self.config(root)
+                encoded = config.audio_file.with_suffix(suffix)
+                config.audio_file.rename(encoded)
+                config = replace(config, audio_file=encoded)
+                received = []
+
+                def capture_transcribe(audio, *args, received_paths=received, **kwargs):
+                    received_paths.append(audio)
+                    return fake_transcribe(audio, *args, **kwargs)
+
+                with (
+                    patch.object(mvp_api, "prepare_audio", side_effect=fake_prepare),
+                    patch.object(mvp_api, "transcribe_audio", side_effect=capture_transcribe),
+                    patch.object(mvp_api, "generate_direct_protocol", side_effect=fake_protocol),
+                ):
+                    result = mvp_api.run_mvp_meeting(
+                        config, meeting_context=context_data()
+                    )
+
+                self.assertEqual(result.exit_code, 0)
+                self.assertEqual(received, [result.run_dir / "audio" / "prepared.wav"])
+                manifest = json.loads(
+                    (result.run_dir / "audio" / "input_manifest.json").read_text()
+                )
+                self.assertEqual(manifest["format"], suffix.removeprefix("."))
+                self.assertEqual(
+                    manifest["prepared_audio"]["prepared_audio_path"],
+                    str((result.run_dir / "audio" / "prepared.wav").resolve()),
+                )
+
 
 if __name__ == "__main__":
     unittest.main()