Fix keep-server-running on macOS: ignore SIGHUP, watchdog grace period, build script fixes

backend/server.py

@@ -58,6 +58,12 @@ def disable_watchdog():
     """Disable the parent watchdog so the server keeps running after parent exits."""
     global _watchdog_disabled
     _watchdog_disabled = True
+    # Ignore SIGHUP so the server survives when the parent Tauri process exits.
+    # On Unix, child processes receive SIGHUP when the parent's session leader
+    # exits, which would kill the server even though we want it to persist.
+    if sys.platform != "win32":
+        import signal
+        signal.signal(signal.SIGHUP, signal.SIG_IGN)
 
 
 def _start_parent_watchdog(parent_pid, data_dir=None):
@@ -130,7 +136,16 @@ def _start_parent_watchdog(parent_pid, data_dir=None):
                 watchdog_logger.info("Watchdog disabled (keep server running), stopping monitor")
                 return
             if not _is_pid_alive(parent_pid):
-                watchdog_logger.info(f"Parent process {parent_pid} gone, shutting down server...")
+                # Parent is gone. Before shutting down, give the app a moment
+                # to send /watchdog/disable — there is a race where the Tauri
+                # RunEvent::Exit handler sends the disable request while we are
+                # mid-iteration (already past the _watchdog_disabled check above).
+                watchdog_logger.info(f"Parent process {parent_pid} gone, waiting for possible disable request...")
+                time.sleep(1)
+                if _watchdog_disabled:
+                    watchdog_logger.info("Watchdog was disabled during grace period, keeping server alive")
+                    return
+                watchdog_logger.info("Watchdog still enabled after grace period, shutting down server...")
                 if sys.platform == "win32":
                     # sys.exit triggers SystemExit, allowing uvicorn to run
                     # shutdown handlers. os.kill(SIGTERM) on Windows calls

backend/voicebox-server.spec

@@ -1,35 +1,34 @@
 # -*- mode: python ; coding: utf-8 -*-
 from PyInstaller.utils.hooks import collect_data_files
 from PyInstaller.utils.hooks import collect_submodules
+from PyInstaller.utils.hooks import collect_all
 from PyInstaller.utils.hooks import copy_metadata
 
 datas = []
-hiddenimports = ['backend', 'backend.main', 'backend.config', 'backend.database', 'backend.models', 'backend.profiles', 'backend.history', 'backend.tts', 'backend.transcribe', 'backend.platform_detect', 'backend.backends', 'backend.backends.pytorch_backend', 'backend.utils.audio', 'backend.utils.cache', 'backend.utils.progress', 'backend.utils.hf_progress', 'backend.utils.validation', 'torch', 'transformers', 'fastapi', 'uvicorn', 'sqlalchemy', 'librosa', 'soundfile', 'qwen_tts', 'qwen_tts.inference', 'qwen_tts.inference.qwen3_tts_model', 'qwen_tts.inference.qwen3_tts_tokenizer', 'qwen_tts.core', 'qwen_tts.cli', 'pkg_resources.extern', 'backend.backends.mlx_backend', 'mlx', 'mlx.core', 'mlx.nn', 'mlx_audio', 'mlx_audio.tts', 'mlx_audio.stt']
+binaries = []
+hiddenimports = ['backend', 'backend.main', 'backend.config', 'backend.database', 'backend.models', 'backend.profiles', 'backend.history', 'backend.tts', 'backend.transcribe', 'backend.platform_detect', 'backend.backends', 'backend.backends.pytorch_backend', 'backend.utils.audio', 'backend.utils.cache', 'backend.utils.progress', 'backend.utils.hf_progress', 'backend.utils.validation', 'backend.cuda_download', 'backend.effects', 'backend.utils.effects', 'backend.versions', 'pedalboard', 'torch', 'transformers', 'fastapi', 'uvicorn', 'sqlalchemy', 'librosa', 'soundfile', 'qwen_tts', 'qwen_tts.inference', 'qwen_tts.inference.qwen3_tts_model', 'qwen_tts.inference.qwen3_tts_tokenizer', 'qwen_tts.core', 'qwen_tts.cli', 'pkg_resources.extern', 'backend.backends.mlx_backend', 'mlx', 'mlx.core', 'mlx.nn', 'mlx_audio', 'mlx_audio.tts', 'mlx_audio.stt']
 datas += collect_data_files('qwen_tts')
-# Use collect_all (not collect_data_files) so native .dylib and .metallib
-# files are bundled as binaries, not data. Without this, MLX raises OSError
-# when loading Metal shaders inside the PyInstaller bundle.
-from PyInstaller.utils.hooks import collect_all as _collect_all
-_mlx_datas, _mlx_bins, _mlx_hidden = _collect_all('mlx')
-_mlxa_datas, _mlxa_bins, _mlxa_hidden = _collect_all('mlx_audio')
-datas += _mlx_datas + _mlxa_datas
 datas += copy_metadata('qwen-tts')
 hiddenimports += collect_submodules('qwen_tts')
 hiddenimports += collect_submodules('jaraco')
 hiddenimports += collect_submodules('mlx')
 hiddenimports += collect_submodules('mlx_audio')
+tmp_ret = collect_all('mlx')
+datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
+tmp_ret = collect_all('mlx_audio')
+datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
 
 
 a = Analysis(
     ['server.py'],
     pathex=[],
-    binaries=_mlx_bins + _mlxa_bins,
+    binaries=binaries,
     datas=datas,
     hiddenimports=hiddenimports,
     hookspath=[],
     hooksconfig={},
     runtime_hooks=[],
-    excludes=[],
+    excludes=['nvidia', 'nvidia.cublas', 'nvidia.cuda_cupti', 'nvidia.cuda_nvrtc', 'nvidia.cuda_runtime', 'nvidia.cudnn', 'nvidia.cufft', 'nvidia.curand', 'nvidia.cusolver', 'nvidia.cusparse', 'nvidia.nccl', 'nvidia.nvjitlink', 'nvidia.nvtx'],
     noarchive=False,
     optimize=0,
 )