Add Streamlit meeting assistant MVP

2026-08-24 10:28:44 +02:00
parent 443a85528b
commit 13d06b8a60
19 changed files with 1188 additions and 20 deletions
@@ -0,0 +1,299 @@
+import json
+from dataclasses import dataclass
+from datetime import date
+from pathlib import Path
+from types import SimpleNamespace
+from typing import Any
+
+from mka.application.config import AppSettings
+from mka.application.meeting_service import (
+    MeetingDetails,
+    MeetingProcessingService,
+    ParticipantInput,
+    ProcessingOptions,
+)
+
+
+@dataclass
+class FakeContext:
+    data: dict[str, Any]
+
+    @property
+    def meeting_id(self) -> str:
+        return self.data["meeting"]["meeting_id"]
+
+
+class FakeMeetingLab:
+    def __init__(self, run_dir: Path) -> None:
+        self.run_dir = run_dir
+        self.context_data: dict[str, Any] | None = None
+        self.config_values: dict[str, Any] | None = None
+        self.fail = False
+
+    def create_context(self, data: dict[str, Any]) -> FakeContext:
+        self.context_data = data
+        if not data["meeting"]["title"]:
+            raise ValueError("meeting.title must be present and non-empty")
+        participant_ids = [item["participant_id"] for item in data["participants"]]
+        if len(participant_ids) != len(set(participant_ids)):
+            raise ValueError("Duplicate participant_id")
+        return FakeContext(data)
+
+    def create_config(self, values: dict[str, Any]) -> dict[str, Any]:
+        self.config_values = values
+        return values
+
+    def run(self, config: Any, meeting_context: Any, progress_sink: Any) -> Any:
+        self.run_dir.mkdir(parents=True, exist_ok=True)
+        progress_sink(
+            SimpleNamespace(
+                stage="preparing",
+                status="started",
+                elapsed_seconds=0.1,
+                progress=None,
+                message=None,
+            )
+        )
+        progress_sink(
+            SimpleNamespace(
+                stage="preparing",
+                status="completed",
+                elapsed_seconds=0.2,
+                progress=None,
+                message=None,
+            )
+        )
+        progress_sink(
+            SimpleNamespace(
+                stage="transcription",
+                status="started",
+                elapsed_seconds=0.2,
+                progress=0.25,
+                message="transcribing",
+            )
+        )
+        if self.fail:
+            (self.run_dir / "run_metadata.json").write_text(
+                json.dumps({"failure": {"stage": "whisper", "message": "model failed"}}),
+                encoding="utf-8",
+            )
+            progress_sink(
+                SimpleNamespace(
+                    stage="failed",
+                    status="failed",
+                    elapsed_seconds=0.3,
+                    progress=None,
+                    message="transcription: model failed",
+                )
+            )
+            return SimpleNamespace(exit_code=2, run_dir=self.run_dir, protocol_path=None)
+        protocol = self.run_dir / "protocol.md"
+        protocol.write_text("# Generated protocol\n", encoding="utf-8")
+        return SimpleNamespace(exit_code=0, run_dir=self.run_dir, protocol_path=protocol)
+
+
+def make_service(tmp_path: Path) -> tuple[MeetingProcessingService, FakeMeetingLab]:
+    model = tmp_path / "model.bin"
+    model.write_bytes(b"model")
+    gateway = FakeMeetingLab(tmp_path / "backend-run")
+    settings = AppSettings(
+        data_root=tmp_path / "meetings",
+        whisper_model=model,
+        whisper_executable="/opt/whisper-cli",
+        protocol_model="test:model",
+        diarization_mode="gpu",
+    )
+    return MeetingProcessingService(settings, gateway), gateway
+
+
+def meeting() -> MeetingDetails:
+    return MeetingDetails(
+        title="Architecture Review",
+        language="de",
+        meeting_date=date(2026, 8, 23),
+        description="Review the MVP.",
+    )
+
+
+def participants() -> list[ParticipantInput]:
+    return [
+        ParticipantInput(
+            participant_id="martin",
+            display_name="Martin",
+            role="Project lead",
+            organization="Engineering",
+        ),
+        ParticipantInput(
+            participant_id="alex",
+            display_name="Alex",
+            organization="Engineering",
+        ),
+    ]
+
+
+def test_build_context_uses_actual_v1_shape(tmp_path: Path) -> None:
+    service, gateway = make_service(tmp_path)
+
+    context = service.build_context(meeting(), participants())
+
+    assert context.meeting_id == "architecture-review"
+    assert gateway.context_data is not None
+    assert gateway.context_data["meeting"]["date"] == "2026-08-23"
+    assert gateway.context_data["meeting"]["notes"] == "Review the MVP."
+    assert gateway.context_data["participants"][0] == {
+        "participant_id": "martin",
+        "display_name": "Martin",
+        "aliases": [],
+        "role": "Project lead",
+        "department": "engineering",
+        "attendance_status": "present",
+        "notes": None,
+    }
+    assert gateway.context_data["organization"]["departments"] == [
+        {"id": "engineering", "name": "Engineering", "aliases": []}
+    ]
+
+
+def test_build_context_preserves_explicit_speaker_mapping(tmp_path: Path) -> None:
+    service, gateway = make_service(tmp_path)
+
+    service.build_context(meeting(), participants(), {"SPEAKER_00": "martin"})
+
+    assert gateway.context_data is not None
+    assert gateway.context_data["speaker_mappings"] == {"SPEAKER_00": "martin"}
+
+
+def test_build_context_translates_mentioned_only_person(tmp_path: Path) -> None:
+    service, gateway = make_service(tmp_path)
+    people = participants() + [
+        ParticipantInput(
+            participant_id="sam",
+            display_name="Sam",
+            attendance_status="mentioned_only",
+        )
+    ]
+
+    service.build_context(meeting(), people)
+
+    assert gateway.context_data is not None
+    assert [item["participant_id"] for item in gateway.context_data["participants"]] == [
+        "martin",
+        "alex",
+    ]
+    assert gateway.context_data["mentioned_people"] == [
+        {
+            "person_id": "sam",
+            "display_name": "Sam",
+            "aliases": [],
+            "role": None,
+            "department": None,
+            "attendance_status": "mentioned_only",
+            "notes": None,
+        }
+    ]
+
+
+def test_process_translates_configuration_and_disables_diarization(
+    tmp_path: Path,
+) -> None:
+    service, gateway = make_service(tmp_path)
+    audio = tmp_path / "meeting.wav"
+    audio.write_bytes(b"audio")
+
+    outcome = service.process(
+        audio, meeting(), participants(), ProcessingOptions(diarization_enabled=False)
+    )
+
+    assert outcome.succeeded
+    assert gateway.config_values is not None
+    assert gateway.config_values["diarization"] == "off"
+    assert gateway.config_values["model"] == "test:model"
+    assert gateway.config_values["whisper_executable"] == "/opt/whisper-cli"
+    assert gateway.config_values["ffmpeg_executable"] == "ffmpeg"
+    assert gateway.config_values["audio_normalization"] is True
+    assert gateway.config_values["output_root"] == (
+        tmp_path / "meetings" / "architecture-review" / "runs"
+    )
+
+
+def test_process_propagates_disabled_audio_normalization(tmp_path: Path) -> None:
+    service, gateway = make_service(tmp_path)
+    audio = tmp_path / "meeting.m4a"
+    audio.write_bytes(b"audio")
+
+    outcome = service.process(
+        audio,
+        meeting(),
+        participants(),
+        ProcessingOptions(audio_normalization=False),
+    )
+
+    assert outcome.succeeded
+    assert gateway.config_values is not None
+    assert gateway.config_values["audio_normalization"] is False
+
+
+def test_processing_options_default_to_audio_normalization_on() -> None:
+    assert ProcessingOptions().audio_normalization is True
+
+
+def test_process_propagates_enabled_diarization_and_progress(tmp_path: Path) -> None:
+    service, gateway = make_service(tmp_path)
+    audio = tmp_path / "meeting.flac"
+    audio.write_bytes(b"audio")
+    events = []
+
+    service.process(
+        audio,
+        meeting(),
+        participants(),
+        ProcessingOptions(diarization_enabled=True),
+        progress_sink=events.append,
+    )
+
+    assert gateway.config_values is not None
+    assert gateway.config_values["diarization"] == "gpu"
+    assert [(event.stage, event.status) for event in events[:2]] == [
+        ("preparing", "started"),
+        ("preparing", "completed"),
+    ]
+    assert events[2].progress == 0.25
+
+
+def test_result_and_user_edit_are_preserved_separately(tmp_path: Path) -> None:
+    service, _ = make_service(tmp_path)
+    audio = tmp_path / "meeting.wav"
+    audio.write_bytes(b"audio")
+
+    outcome = service.process(audio, meeting(), participants(), ProcessingOptions())
+    edited_path = service.save_edited_protocol(outcome.run_dir, "# Reviewed\n")
+
+    assert outcome.original_protocol == "# Generated protocol\n"
+    assert outcome.protocol_path.read_text(encoding="utf-8") == "# Generated protocol\n"
+    assert edited_path.read_text(encoding="utf-8") == "# Reviewed\n"
+
+
+def test_failure_reports_stage_and_preserves_run_dir(tmp_path: Path) -> None:
+    service, gateway = make_service(tmp_path)
+    gateway.fail = True
+    audio = tmp_path / "meeting.wav"
+    audio.write_bytes(b"audio")
+
+    outcome = service.process(audio, meeting(), participants(), ProcessingOptions())
+
+    assert not outcome.succeeded
+    assert outcome.failed_stage == "transcription"
+    assert outcome.error_message == "model failed"
+    assert outcome.run_dir == gateway.run_dir
+    assert (gateway.run_dir / "run_metadata.json").is_file()
+
+
+def test_uploaded_source_is_preserved_in_meeting_directory(tmp_path: Path) -> None:
+    service, _ = make_service(tmp_path)
+    source = SimpleNamespace(getbuffer=lambda: b"source audio")
+
+    destination = service.preserve_upload("meeting-1", "../unsafe.wav", source)
+
+    assert destination.parent == tmp_path / "meetings" / "meeting-1" / "uploads"
+    assert destination.name.endswith("_unsafe.wav")
+    assert destination.read_bytes() == b"source audio"