Add canonical audio preparation and meeting context support

src/meeting_lab/orchestration/mvp.py

@@ -7,11 +7,13 @@ import re
 import shutil
 import sys
 import time
+from collections.abc import Callable, Mapping, Sequence
 from dataclasses import dataclass
 from datetime import datetime
 from pathlib import Path
-from typing import Any, Callable, Mapping, Sequence
+from typing import Any
 
+from src.meeting_lab.audio import prepare_audio
 from src.meeting_lab.diarization import (
     DEFAULT_MODEL as DEFAULT_DIARIZATION_MODEL,
     diarize_audio,
@@ -44,6 +46,8 @@ class MvpMeetingConfig:
     audio_file: Path
     whisper_model: Path
     whisper_executable: str = "whisper-cli"
+    ffmpeg_executable: str = "ffmpeg"
+    audio_normalization: bool = True
     context_file: Path | None = None
     output_root: Path = DEFAULT_OUTPUT_ROOT
     language: str = "de"
@@ -187,6 +191,7 @@ def run_mvp_meeting(
     stage_runtimes: dict[str, float | None] = {
         "validation": round(validation_runtime, 3),
         "setup": None,
+        "audio_preparation": None,
         "whisper": None,
         "transcript_validation": None,
         "protocol": None,
@@ -198,6 +203,7 @@ def run_mvp_meeting(
         "run_id": run_dir.name,
         "timestamp": timestamp,
         "input_audio": str(config.audio_file.resolve()),
+        "audio_preparation": None,
         "transcript_output": str(transcript_path.resolve()),
         "protocol_output": str(protocol_path.resolve()),
         "whisper_model": str(config.whisper_model.resolve()),
@@ -238,6 +244,33 @@ def run_mvp_meeting(
             },
         )
 
+        preparation_started = time.perf_counter()
+        current_stage = "audio_preparation"
+        stage_started = preparation_started
+        prepared_audio = prepare_audio(
+            config.audio_file,
+            audio_dir / "prepared.wav",
+            ffmpeg_executable=config.ffmpeg_executable,
+            normalization_enabled=config.audio_normalization,
+        )
+        stage_runtimes["audio_preparation"] = round(
+            time.perf_counter() - preparation_started, 3
+        )
+        current_stage = "preparing"
+        preparation_metadata = prepared_audio.metadata()
+        metadata["audio_preparation"] = preparation_metadata
+        _write_json(audio_dir / "preparation_metadata.json", preparation_metadata)
+        _write_json(
+            audio_dir / "input_manifest.json",
+            {
+                "source_file": str(config.audio_file.resolve()),
+                "filename": config.audio_file.name,
+                "size_bytes": config.audio_file.stat().st_size,
+                "format": config.audio_file.suffix.lower().removeprefix("."),
+                "prepared_audio": preparation_metadata,
+            },
+        )
+
         preserved_context: Path | None = None
         if effective_context is not None:
             preserved_context = context_dir / "meeting_context.yaml"
@@ -252,7 +285,7 @@ def run_mvp_meeting(
         stage_started = time.perf_counter()
         _emit(progress_sink, "transcription", "started", overall_started)
         transcription = transcribe_audio(
-            config.audio_file,
+            prepared_audio.prepared_path,
             config.whisper_model,
             transcript_dir,
             config.language,
@@ -275,7 +308,7 @@ def run_mvp_meeting(
             _emit(progress_sink, "diarization", "started", overall_started)
             diarization_dir = run_dir / "diarization"
             diarization = diarize_audio(
-                config.audio_file,
+                prepared_audio.prepared_path,
                 diarization_dir,
                 config.diarization,
                 runtime=config.diarization_runtime,
@@ -330,6 +363,7 @@ def run_mvp_meeting(
     except Exception as exc:
         metadata_stage = {
             "preparing": "setup",
+            "audio_preparation": "audio_preparation",
             "transcription": "whisper",
             "diarization": "diarization",
             "protocol_generation": "protocol",