feat(voice-client): PySide6 desktop client and Windows build scripts

Add voice_confirmation_client (poll, TTS MP3 playback, mic WAV resolve), PyInstaller spec, start/build helpers, and API unit tests. Pending manual testing: end-to-end on OR workstations and packaged exe. Made-with: Cursor
2026-04-27 09:52:10 +08:00
parent e4c6127619
commit 4c3f9a367b
19 changed files with 1324 additions and 0 deletions
--- a/voice_confirmation_client/gui/init.py
+++ b/voice_confirmation_client/gui/init.py
@@ -0,0 +1 @@
+"""PySide6 desktop GUI."""
--- a/voice_confirmation_client/gui/main_window.py
+++ b/voice_confirmation_client/gui/main_window.py
@@ -0,0 +1,198 @@
+"""Main PySide6 window for the voice confirmation client."""
+
+from __future__ import annotations
+
+import json
+from datetime import datetime
+from typing import Any
+
+from PySide6.QtCore import Qt, Signal, QObject
+from PySide6.QtGui import QCloseEvent
+from PySide6.QtWidgets import (
+    QCheckBox,
+    QComboBox,
+    QDoubleSpinBox,
+    QFormLayout,
+    QGroupBox,
+    QHBoxLayout,
+    QLabel,
+    QLineEdit,
+    QMainWindow,
+    QMessageBox,
+    QPushButton,
+    QPlainTextEdit,
+    QSplitter,
+    QVBoxLayout,
+    QWidget,
+)
+
+from voice_confirmation_client.core.monitor_worker import MonitorWorker
+
+
+class _Bridge(QObject):
+    log_line = Signal(str)
+    state_text = Signal(str)
+    pending_payload = Signal(object)
+
+
+class MainWindow(QMainWindow):
+    def __init__(self) -> None:
+        super().__init__()
+        self.setWindowTitle("手术室耗材语音确认客户端")
+        self.resize(920, 640)
+
+        self._bridge = _Bridge()
+        self._bridge.log_line.connect(self._append_log)
+        self._bridge.pending_payload.connect(self._show_pending)
+
+        self._worker = MonitorWorker(
+            on_log=lambda m: self._bridge.log_line.emit(m),
+            on_state=lambda s: self._bridge.state_text.emit(s),
+            on_pending=lambda p: self._bridge.pending_payload.emit(p),
+        )
+        self._worker.start_thread()
+
+        central = QWidget()
+        self.setCentralWidget(central)
+        root = QVBoxLayout(central)
+
+        form_box = QGroupBox("连接与手术")
+        form = QFormLayout(form_box)
+        self._base_url = QLineEdit("http://127.0.0.1:38080")
+        self._surgery_id = QLineEdit("")
+        self._surgery_id.setPlaceholderText("6 位数字，如 123456")
+        self._interval = QDoubleSpinBox()
+        self._interval.setRange(1.0, 120.0)
+        self._interval.setValue(5.0)
+        self._interval.setSuffix(" s")
+        self._record_sec = QDoubleSpinBox()
+        self._record_sec.setRange(2.0, 60.0)
+        self._record_sec.setValue(8.0)
+        self._record_sec.setSuffix(" s")
+        form.addRow("服务端 Base URL", self._base_url)
+        form.addRow("手术号 surgery_id", self._surgery_id)
+        form.addRow("轮询间隔", self._interval)
+        form.addRow("录音时长", self._record_sec)
+        root.addWidget(form_box)
+
+        adv = QGroupBox("音频 / 调试")
+        adv_l = QFormLayout(adv)
+        self._device_combo = QComboBox()
+        self._device_combo.addItem("系统默认麦克风", None)
+        self._populate_input_devices()
+        self._prefer_ffmpeg = QCheckBox("优先使用 ffmpeg 录音（需本机 ffmpeg 且设备参数可用）")
+        self._hide_404 = QCheckBox("隐藏 404 轮询日志（推荐）")
+        self._hide_404.setChecked(True)
+        self._dry_run = QCheckBox("Dry-run：录音后不上传")
+        adv_l.addRow("输入设备", self._device_combo)
+        adv_l.addRow(self._prefer_ffmpeg)
+        adv_l.addRow(self._hide_404)
+        adv_l.addRow(self._dry_run)
+        root.addWidget(adv)
+
+        btn_row = QHBoxLayout()
+        self._btn_start = QPushButton("开始监控")
+        self._btn_stop = QPushButton("停止监控")
+        self._btn_stop.setEnabled(False)
+        self._btn_retry = QPushButton("重试本轮（播放+录音+上传）")
+        self._btn_replay = QPushButton("仅重播话术")
+        btn_row.addWidget(self._btn_start)
+        btn_row.addWidget(self._btn_stop)
+        btn_row.addWidget(self._btn_retry)
+        btn_row.addWidget(self._btn_replay)
+        btn_row.addStretch()
+        root.addLayout(btn_row)
+
+        self._status_label = QLabel("待机")
+        root.addWidget(self._status_label)
+        self._bridge.state_text.connect(self._status_label.setText)
+
+        split = QSplitter(Qt.Orientation.Horizontal)
+        self._pending_view = QPlainTextEdit()
+        self._pending_view.setReadOnly(True)
+        self._pending_view.setPlaceholderText("待确认内容将显示在这里…")
+        self._log = QPlainTextEdit()
+        self._log.setReadOnly(True)
+        self._log.setPlaceholderText("日志…")
+        split.addWidget(self._pending_view)
+        split.addWidget(self._log)
+        split.setSizes([360, 520])
+        root.addWidget(split, stretch=1)
+
+        self._btn_start.clicked.connect(self._start_monitoring)
+        self._btn_stop.clicked.connect(self._stop_monitoring)
+        self._btn_retry.clicked.connect(self._worker.retry_failed)
+        self._btn_replay.clicked.connect(self._worker.replay_prompt_only)
+
+        self._apply_settings_silent()
+
+    def _show_pending(self, payload: object) -> None:
+        if payload is None:
+            self._pending_view.clear()
+            return
+        if not isinstance(payload, dict):
+            self._pending_view.setPlainText(str(payload))
+            return
+        try:
+            text = json.dumps(payload, ensure_ascii=False, indent=2)
+        except (TypeError, ValueError):
+            text = str(payload)
+        self._pending_view.setPlainText(text)
+
+    def _populate_input_devices(self) -> None:
+        try:
+            import sounddevice as sd
+        except ImportError:
+            return
+        try:
+            devices = sd.query_devices()
+            hostapis = sd.query_hostapis()
+        except Exception:
+            return
+        for i, d in enumerate(devices):
+            if d.get("max_input_channels", 0) <= 0:
+                continue
+            ha = hostapis[d["hostapi"]]["name"] if d.get("hostapi") is not None else ""
+            label = f"{i}: {d.get('name', '')} ({ha})"
+            self._device_combo.addItem(label, i)
+
+    def _apply_settings_silent(self) -> None:
+        dev_data = self._device_combo.currentData()
+        self._worker.set_settings(
+            base_url=self._base_url.text().strip(),
+            surgery_id=self._surgery_id.text().strip(),
+            interval_sec=float(self._interval.value()),
+            record_seconds=float(self._record_sec.value()),
+            dry_run=self._dry_run.isChecked(),
+            hide_404_logs=self._hide_404.isChecked(),
+            prefer_ffmpeg_record=self._prefer_ffmpeg.isChecked(),
+            sounddevice_device=dev_data,
+        )
+
+    def _start_monitoring(self) -> None:
+        sid = self._surgery_id.text().strip()
+        if len(sid) != 6 or not sid.isdigit():
+            QMessageBox.warning(self, "校验失败", "手术号必须为 6 位数字。")
+            return
+        self._apply_settings_silent()
+        self._worker.set_monitoring(True)
+        self._btn_start.setEnabled(False)
+        self._btn_stop.setEnabled(True)
+        self._append_log("—— 开始监控 ——")
+
+    def _stop_monitoring(self) -> None:
+        self._worker.set_monitoring(False)
+        self._btn_start.setEnabled(True)
+        self._btn_stop.setEnabled(False)
+        self._append_log("—— 已停止监控 ——")
+        self._status_label.setText("已停止")
+
+    def _append_log(self, line: str) -> None:
+        ts = datetime.now().strftime("%H:%M:%S")
+        self._log.appendPlainText(f"[{ts}] {line}")
+        sb = self._log.verticalScrollBar()
+        sb.setValue(sb.maximum())
+
+    def closeEvent(self, event: QCloseEvent) -> None:
+        self._worker.stop_thread()
+        event.accept()