@vortex-os/computer-use 0.7.0 → 0.7.1

package/scripts/audio-duck.ps1

@@ -1,180 +1,180 @@
-# computer-use — audio ducking helper (pwsh; WASAPI Core Audio via inline C#, NO install).
-#
-# When the companion speaks, briefly lower OTHER apps' audio sessions (game / video / music) so the voice
-# stands out, then restore EXACTLY on completion. Per-app, not master volume — our own voice is excluded.
-#
-# SAFETY: restore is the whole point. Volumes are snapshotted and always restored in a finally block, even if
-# playback throws or the process is asked to stop — a failed restore would leave the user's other apps quiet.
-#
-# Two uses:
-#   1. Dot-source and call [CU.AudioDuck]::Duck(factor, excludePids) -> handle ; [CU.AudioDuck]::Restore(handle).
-#      (speak.ps1 / Heami wraps System.Speech this way, excluding its own $PID.)
-#   2. -WavPath <wav>: duck (excluding THIS process), play the WAV via SoundPlayer, restore in finally.
-#      (speak-supertonic.mjs spawns this to play its synthesized WAV.)
-#
-# factor is the multiplier applied to other sessions (0.45 = reduce to 45%). 1.0 disables ducking.
-param(
-  [string]$WavPath = '',
-  [double]$Factor = 0.45,
-  [int[]]$ExcludePid = @()
-)
-$ErrorActionPreference = 'Stop'
-try { [Console]::OutputEncoding = [System.Text.UTF8Encoding]::new($false) } catch {}
-
-if (-not ('CU.AudioDuck' -as [type])) {
-Add-Type -TypeDefinition @'
-using System;
-using System.Collections.Generic;
-using System.Runtime.InteropServices;
-
-namespace CU {
-  [ComImport, Guid("BCDE0395-E52F-467C-8E3D-C4579291692E")] class MMDeviceEnumeratorComObject { }
-
-  enum EDataFlow { eRender = 0, eCapture = 1, eAll = 2 }
-  enum ERole { eConsole = 0, eMultimedia = 1, eCommunications = 2 }
-
-  [ComImport, Guid("A95664D2-9614-4F35-A746-DE8DB63617E6"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
-  interface IMMDeviceEnumerator {
-    [PreserveSig] int EnumAudioEndpoints(EDataFlow dataFlow, int dwStateMask, out IMMDeviceCollection ppDevices);
-    [PreserveSig] int GetDefaultAudioEndpoint(EDataFlow dataFlow, ERole role, out IMMDevice ppEndpoint);
-  }
-
-  [ComImport, Guid("0BD7A1BE-7A1A-44DB-8397-CC5392387B5E"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
-  interface IMMDeviceCollection {
-    [PreserveSig] int GetCount(out uint pcDevices);
-    [PreserveSig] int Item(uint nDevice, out IMMDevice ppDevice);
-  }
-
-  [ComImport, Guid("D666063F-1587-4E43-81F1-B948E807363F"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
-  interface IMMDevice {
-    [PreserveSig] int Activate(ref Guid iid, int dwClsCtx, IntPtr pActivationParams,
-      [MarshalAs(UnmanagedType.IUnknown)] out object ppInterface);
-  }
-
-  [ComImport, Guid("77AA99A0-1BD6-484F-8BC7-2C654C9A9B6F"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
-  interface IAudioSessionManager2 {
-    [PreserveSig] int NotImpl1();
-    [PreserveSig] int NotImpl2();
-    [PreserveSig] int GetSessionEnumerator(out IAudioSessionEnumerator SessionEnum);
-  }
-
-  [ComImport, Guid("E2F5BB11-0570-40CA-ACDD-3AA01277DEE8"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
-  interface IAudioSessionEnumerator {
-    [PreserveSig] int GetCount(out int SessionCount);
-    [PreserveSig] int GetSession(int SessionCount, out IAudioSessionControl Session);
-  }
-
-  [ComImport, Guid("F4B1A599-7266-4319-A8CA-E70ACB11E8CD"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
-  interface IAudioSessionControl { }
-
-  [ComImport, Guid("bfb7ff88-7239-4fc9-8fa2-07c950be9c6d"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
-  interface IAudioSessionControl2 {
-    // 9 inherited IAudioSessionControl slots (unused) ...
-    [PreserveSig] int N1();  [PreserveSig] int N2();  [PreserveSig] int N3();
-    [PreserveSig] int N4();  [PreserveSig] int N5();  [PreserveSig] int N6();
-    [PreserveSig] int N7();  [PreserveSig] int N8();  [PreserveSig] int N9();
-    // IAudioSessionControl2 own slots:
-    [PreserveSig] int GetSessionIdentifier([MarshalAs(UnmanagedType.LPWStr)] out string s);
-    [PreserveSig] int GetSessionInstanceIdentifier([MarshalAs(UnmanagedType.LPWStr)] out string s);
-    [PreserveSig] int GetProcessId(out uint pid);
-    [PreserveSig] int IsSystemSoundsSession();
-  }
-
-  [ComImport, Guid("87CE5498-68D6-44E5-9215-6DA47EF883D8"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
-  interface ISimpleAudioVolume {
-    [PreserveSig] int SetMasterVolume(float level, ref Guid ctx);
-    [PreserveSig] int GetMasterVolume(out float level);
-    [PreserveSig] int SetMute(bool mute, ref Guid ctx);
-    [PreserveSig] int GetMute(out bool mute);
-  }
-
-  public class Handle { internal ISimpleAudioVolume Vol; public float Original; public uint Pid; }
-
-  public static class AudioDuck {
-    static Guid IID_IAudioSessionManager2 = new Guid("77AA99A0-1BD6-484F-8BC7-2C654C9A9B6F");
-    static Guid CTX = Guid.Empty;
-
-    static IAudioSessionEnumerator SessionsForDevice(IMMDevice dev) {
-      object o; if (dev.Activate(ref IID_IAudioSessionManager2, 23 /*CLSCTX_ALL*/, IntPtr.Zero, out o) != 0) return null;
-      var mgr = (IAudioSessionManager2)o;
-      IAudioSessionEnumerator en; if (mgr.GetSessionEnumerator(out en) != 0) return null;
-      return en;
-    }
-
-    // Lower every session (except excludePids and system-sounds) to original*factor, across ALL active render
-    // devices (not just the default endpoint) so virtual-audio routing (e.g. VoiceMeeter) is still caught.
-    // Returns restore handles. DEVICE_STATE_ACTIVE = 0x1.
-    public static List<Handle> Duck(double factor, int[] excludePids) {
-      var handles = new List<Handle>();
-      var deo = (IMMDeviceEnumerator)(new MMDeviceEnumeratorComObject());
-      IMMDeviceCollection coll;
-      if (deo.EnumAudioEndpoints(EDataFlow.eRender, 0x1, out coll) != 0 || coll == null) return handles;
-      uint dcount; if (coll.GetCount(out dcount) != 0) return handles;
-      var excl = new HashSet<uint>(); foreach (var p in excludePids) excl.Add((uint)p);
-      for (uint di = 0; di < dcount; di++) {
-        IMMDevice dev; if (coll.Item(di, out dev) != 0 || dev == null) continue;
-        var en = SessionsForDevice(dev); if (en == null) continue;
-        int count; if (en.GetCount(out count) != 0) continue;
-        for (int i = 0; i < count; i++) {
-          IAudioSessionControl ctl; if (en.GetSession(i, out ctl) != 0 || ctl == null) continue;
-          try {
-            var c2 = (IAudioSessionControl2)ctl;
-            if (c2.IsSystemSoundsSession() == 0) continue; // S_OK(0) means IS system sounds -> skip it
-            uint pid; if (c2.GetProcessId(out pid) != 0) continue;
-            if (excl.Contains(pid)) continue;
-            var vol = (ISimpleAudioVolume)ctl;
-            float cur; if (vol.GetMasterVolume(out cur) != 0) continue;
-            var h = new Handle { Vol = vol, Original = cur, Pid = pid };
-            vol.SetMasterVolume((float)(cur * factor), ref CTX);
-            handles.Add(h);
-          } catch { }
-        }
-      }
-      return handles;
-    }
-
-    public static void Restore(List<Handle> handles) {
-      if (handles == null) return;
-      foreach (var h in handles) { try { h.Vol.SetMasterVolume(h.Original, ref CTX); } catch { } }
-    }
-
-    // Inspection helpers (for the isolation test): current live level / snapshotted original per handle.
-    public static float[] Levels(List<Handle> handles) {
-      var a = new float[handles.Count];
-      for (int i = 0; i < handles.Count; i++) { float c = 0; try { handles[i].Vol.GetMasterVolume(out c); } catch { } a[i] = c; }
-      return a;
-    }
-    public static float[] Originals(List<Handle> handles) {
-      var a = new float[handles.Count];
-      for (int i = 0; i < handles.Count; i++) a[i] = handles[i].Original;
-      return a;
-    }
-    public static uint[] Pids(List<Handle> handles) {
-      var a = new uint[handles.Count];
-      for (int i = 0; i < handles.Count; i++) a[i] = handles[i].Pid;
-      return a;
-    }
-  }
-}
-'@
-}
-
-function Invoke-Duck([double]$factor, [int[]]$exclude) {
-  if ($factor -ge 1.0 -or $factor -lt 0) { return $null }
-  try { return [CU.AudioDuck]::Duck($factor, $exclude) } catch { return $null }
-}
-function Restore-Duck($handles) {
-  if ($null -eq $handles) { return }
-  try { [CU.AudioDuck]::Restore($handles) } catch { }
-}
-
-# -WavPath mode: duck others (excluding THIS process, which owns the playback), play, restore in finally.
-if ($WavPath) {
-  $h = Invoke-Duck $Factor @($PID)
-  try {
-    $p = New-Object System.Media.SoundPlayer $WavPath
-    $p.PlaySync()
-  } finally {
-    Restore-Duck $h
-  }
-}
+# computer-use — audio ducking helper (pwsh; WASAPI Core Audio via inline C#, NO install).
+#
+# When the companion speaks, briefly lower OTHER apps' audio sessions (game / video / music) so the voice
+# stands out, then restore EXACTLY on completion. Per-app, not master volume — our own voice is excluded.
+#
+# SAFETY: restore is the whole point. Volumes are snapshotted and always restored in a finally block, even if
+# playback throws or the process is asked to stop — a failed restore would leave the user's other apps quiet.
+#
+# Two uses:
+#   1. Dot-source and call [CU.AudioDuck]::Duck(factor, excludePids) -> handle ; [CU.AudioDuck]::Restore(handle).
+#      (speak.ps1 / Heami wraps System.Speech this way, excluding its own $PID.)
+#   2. -WavPath <wav>: duck (excluding THIS process), play the WAV via SoundPlayer, restore in finally.
+#      (speak-supertonic.mjs spawns this to play its synthesized WAV.)
+#
+# factor is the multiplier applied to other sessions (0.45 = reduce to 45%). 1.0 disables ducking.
+param(
+  [string]$WavPath = '',
+  [double]$Factor = 0.45,
+  [int[]]$ExcludePid = @()
+)
+$ErrorActionPreference = 'Stop'
+try { [Console]::OutputEncoding = [System.Text.UTF8Encoding]::new($false) } catch {}
+
+if (-not ('CU.AudioDuck' -as [type])) {
+Add-Type -TypeDefinition @'
+using System;
+using System.Collections.Generic;
+using System.Runtime.InteropServices;
+
+namespace CU {
+  [ComImport, Guid("BCDE0395-E52F-467C-8E3D-C4579291692E")] class MMDeviceEnumeratorComObject { }
+
+  enum EDataFlow { eRender = 0, eCapture = 1, eAll = 2 }
+  enum ERole { eConsole = 0, eMultimedia = 1, eCommunications = 2 }
+
+  [ComImport, Guid("A95664D2-9614-4F35-A746-DE8DB63617E6"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
+  interface IMMDeviceEnumerator {
+    [PreserveSig] int EnumAudioEndpoints(EDataFlow dataFlow, int dwStateMask, out IMMDeviceCollection ppDevices);
+    [PreserveSig] int GetDefaultAudioEndpoint(EDataFlow dataFlow, ERole role, out IMMDevice ppEndpoint);
+  }
+
+  [ComImport, Guid("0BD7A1BE-7A1A-44DB-8397-CC5392387B5E"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
+  interface IMMDeviceCollection {
+    [PreserveSig] int GetCount(out uint pcDevices);
+    [PreserveSig] int Item(uint nDevice, out IMMDevice ppDevice);
+  }
+
+  [ComImport, Guid("D666063F-1587-4E43-81F1-B948E807363F"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
+  interface IMMDevice {
+    [PreserveSig] int Activate(ref Guid iid, int dwClsCtx, IntPtr pActivationParams,
+      [MarshalAs(UnmanagedType.IUnknown)] out object ppInterface);
+  }
+
+  [ComImport, Guid("77AA99A0-1BD6-484F-8BC7-2C654C9A9B6F"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
+  interface IAudioSessionManager2 {
+    [PreserveSig] int NotImpl1();
+    [PreserveSig] int NotImpl2();
+    [PreserveSig] int GetSessionEnumerator(out IAudioSessionEnumerator SessionEnum);
+  }
+
+  [ComImport, Guid("E2F5BB11-0570-40CA-ACDD-3AA01277DEE8"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
+  interface IAudioSessionEnumerator {
+    [PreserveSig] int GetCount(out int SessionCount);
+    [PreserveSig] int GetSession(int SessionCount, out IAudioSessionControl Session);
+  }
+
+  [ComImport, Guid("F4B1A599-7266-4319-A8CA-E70ACB11E8CD"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
+  interface IAudioSessionControl { }
+
+  [ComImport, Guid("bfb7ff88-7239-4fc9-8fa2-07c950be9c6d"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
+  interface IAudioSessionControl2 {
+    // 9 inherited IAudioSessionControl slots (unused) ...
+    [PreserveSig] int N1();  [PreserveSig] int N2();  [PreserveSig] int N3();
+    [PreserveSig] int N4();  [PreserveSig] int N5();  [PreserveSig] int N6();
+    [PreserveSig] int N7();  [PreserveSig] int N8();  [PreserveSig] int N9();
+    // IAudioSessionControl2 own slots:
+    [PreserveSig] int GetSessionIdentifier([MarshalAs(UnmanagedType.LPWStr)] out string s);
+    [PreserveSig] int GetSessionInstanceIdentifier([MarshalAs(UnmanagedType.LPWStr)] out string s);
+    [PreserveSig] int GetProcessId(out uint pid);
+    [PreserveSig] int IsSystemSoundsSession();
+  }
+
+  [ComImport, Guid("87CE5498-68D6-44E5-9215-6DA47EF883D8"), InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
+  interface ISimpleAudioVolume {
+    [PreserveSig] int SetMasterVolume(float level, ref Guid ctx);
+    [PreserveSig] int GetMasterVolume(out float level);
+    [PreserveSig] int SetMute(bool mute, ref Guid ctx);
+    [PreserveSig] int GetMute(out bool mute);
+  }
+
+  public class Handle { internal ISimpleAudioVolume Vol; public float Original; public uint Pid; }
+
+  public static class AudioDuck {
+    static Guid IID_IAudioSessionManager2 = new Guid("77AA99A0-1BD6-484F-8BC7-2C654C9A9B6F");
+    static Guid CTX = Guid.Empty;
+
+    static IAudioSessionEnumerator SessionsForDevice(IMMDevice dev) {
+      object o; if (dev.Activate(ref IID_IAudioSessionManager2, 23 /*CLSCTX_ALL*/, IntPtr.Zero, out o) != 0) return null;
+      var mgr = (IAudioSessionManager2)o;
+      IAudioSessionEnumerator en; if (mgr.GetSessionEnumerator(out en) != 0) return null;
+      return en;
+    }
+
+    // Lower every session (except excludePids and system-sounds) to original*factor, across ALL active render
+    // devices (not just the default endpoint) so virtual-audio routing (e.g. VoiceMeeter) is still caught.
+    // Returns restore handles. DEVICE_STATE_ACTIVE = 0x1.
+    public static List<Handle> Duck(double factor, int[] excludePids) {
+      var handles = new List<Handle>();
+      var deo = (IMMDeviceEnumerator)(new MMDeviceEnumeratorComObject());
+      IMMDeviceCollection coll;
+      if (deo.EnumAudioEndpoints(EDataFlow.eRender, 0x1, out coll) != 0 || coll == null) return handles;
+      uint dcount; if (coll.GetCount(out dcount) != 0) return handles;
+      var excl = new HashSet<uint>(); foreach (var p in excludePids) excl.Add((uint)p);
+      for (uint di = 0; di < dcount; di++) {
+        IMMDevice dev; if (coll.Item(di, out dev) != 0 || dev == null) continue;
+        var en = SessionsForDevice(dev); if (en == null) continue;
+        int count; if (en.GetCount(out count) != 0) continue;
+        for (int i = 0; i < count; i++) {
+          IAudioSessionControl ctl; if (en.GetSession(i, out ctl) != 0 || ctl == null) continue;
+          try {
+            var c2 = (IAudioSessionControl2)ctl;
+            if (c2.IsSystemSoundsSession() == 0) continue; // S_OK(0) means IS system sounds -> skip it
+            uint pid; if (c2.GetProcessId(out pid) != 0) continue;
+            if (excl.Contains(pid)) continue;
+            var vol = (ISimpleAudioVolume)ctl;
+            float cur; if (vol.GetMasterVolume(out cur) != 0) continue;
+            var h = new Handle { Vol = vol, Original = cur, Pid = pid };
+            vol.SetMasterVolume((float)(cur * factor), ref CTX);
+            handles.Add(h);
+          } catch { }
+        }
+      }
+      return handles;
+    }
+
+    public static void Restore(List<Handle> handles) {
+      if (handles == null) return;
+      foreach (var h in handles) { try { h.Vol.SetMasterVolume(h.Original, ref CTX); } catch { } }
+    }
+
+    // Inspection helpers (for the isolation test): current live level / snapshotted original per handle.
+    public static float[] Levels(List<Handle> handles) {
+      var a = new float[handles.Count];
+      for (int i = 0; i < handles.Count; i++) { float c = 0; try { handles[i].Vol.GetMasterVolume(out c); } catch { } a[i] = c; }
+      return a;
+    }
+    public static float[] Originals(List<Handle> handles) {
+      var a = new float[handles.Count];
+      for (int i = 0; i < handles.Count; i++) a[i] = handles[i].Original;
+      return a;
+    }
+    public static uint[] Pids(List<Handle> handles) {
+      var a = new uint[handles.Count];
+      for (int i = 0; i < handles.Count; i++) a[i] = handles[i].Pid;
+      return a;
+    }
+  }
+}
+'@
+}
+
+function Invoke-Duck([double]$factor, [int[]]$exclude) {
+  if ($factor -ge 1.0 -or $factor -lt 0) { return $null }
+  try { return [CU.AudioDuck]::Duck($factor, $exclude) } catch { return $null }
+}
+function Restore-Duck($handles) {
+  if ($null -eq $handles) { return }
+  try { [CU.AudioDuck]::Restore($handles) } catch { }
+}
+
+# -WavPath mode: duck others (excluding THIS process, which owns the playback), play, restore in finally.
+if ($WavPath) {
+  $h = Invoke-Duck $Factor @($PID)
+  try {
+    $p = New-Object System.Media.SoundPlayer $WavPath
+    $p.PlaySync()
+  } finally {
+    Restore-Duck $h
+  }
+}

package/scripts/classify.ps1

@@ -1,8 +1,8 @@
-# computer-use — classify_activity raw-signal adapter over lib.ps1::Get-AxClassifyActivity.
-# Output = a single JSON blob of raw signals (foreground process/title, notification state, UIA count, fullscreen).
-# The JS side (activity.mjs) derives the activity class from these. Read-only, no images.
-param([int]$UiaCap = 60)
-$ErrorActionPreference = 'Stop'
-. (Join-Path $PSScriptRoot 'lib.ps1')
-Initialize-AxEnv
-Get-AxClassifyActivity -UiaCap $UiaCap | ConvertTo-Json -Depth 4
+# computer-use — classify_activity raw-signal adapter over lib.ps1::Get-AxClassifyActivity.
+# Output = a single JSON blob of raw signals (foreground process/title, notification state, UIA count, fullscreen).
+# The JS side (activity.mjs) derives the activity class from these. Read-only, no images.
+param([int]$UiaCap = 60)
+$ErrorActionPreference = 'Stop'
+. (Join-Path $PSScriptRoot 'lib.ps1')
+Initialize-AxEnv
+Get-AxClassifyActivity -UiaCap $UiaCap | ConvertTo-Json -Depth 4

package/scripts/fetch-supertonic.mjs

@@ -1,65 +1,82 @@
-#!/usr/bin/env node
-// computer-use — Supertonic 3 model downloader (one-time, ~380 MB) for the optional neural TTS engine.
-//
-// Downloads Supertone/supertonic-3 (OpenRAIL-M weights — commercial use permitted) into the model cache the
-// speak path expects. Idempotent: existing non-empty files are skipped, so re-running resumes a partial fetch.
-// Usage: node fetch-supertonic.mjs [targetDir]   (default: VORTEX_CU_TTS_MODEL_DIR or ~/.vortex/computer-use/supertonic-3)
-//
-// The engine code (speak-supertonic.mjs) is adapted from Supertone's MIT Node example; only the weights are
-// downloaded here, never bundled, keeping the npm package small and the license boundary clean.
-
-import { createWriteStream, existsSync, statSync, mkdirSync, renameSync, unlinkSync } from 'node:fs';
-import { Readable } from 'node:stream';
-import { pipeline } from 'node:stream/promises';
-import { join, dirname } from 'node:path';
-import { homedir } from 'node:os';
-
-const HF = 'https://huggingface.co/Supertone/supertonic-3/resolve/main';
-const FILES = [
-  'onnx/duration_predictor.onnx',
-  'onnx/text_encoder.onnx',
-  'onnx/vector_estimator.onnx',
-  'onnx/vocoder.onnx',
-  'onnx/tts.json',
-  'onnx/unicode_indexer.json',
-  'config.json',
-  ...['F1', 'F2', 'F3', 'F4', 'F5', 'M1', 'M2', 'M3', 'M4', 'M5'].map((v) => `voice_styles/${v}.json`),
-];
-
-const targetDir = process.argv[2] || process.env.VORTEX_CU_TTS_MODEL_DIR || join(homedir(), '.vortex', 'computer-use', 'supertonic-3');
-
-async function fetchToFile(url, dest) {
-  const res = await fetch(url, { redirect: 'follow' });
-  if (!res.ok || !res.body) throw new Error(`HTTP ${res.status}`);
-  const tmp = dest + '.part';
-  mkdirSync(dirname(dest), { recursive: true });
-  await pipeline(Readable.fromWeb(res.body), createWriteStream(tmp));
-  renameSync(tmp, dest);
-  return statSync(dest).size;
-}
-
-async function main() {
-  console.log(`Supertonic 3 model cache: ${targetDir}`);
-  let downloaded = 0, skipped = 0, bytes = 0;
-  for (const rel of FILES) {
-    const dest = join(targetDir, rel);
-    if (existsSync(dest) && statSync(dest).size > 0) { skipped++; continue; }
-    process.stdout.write(`  ↓ ${rel} ... `);
-    try {
-      const t = Date.now();
-      const sz = await fetchToFile(`${HF}/${rel}`, dest);
-      bytes += sz;
-      downloaded++;
-      console.log(`${(sz / 1048576).toFixed(1)} MB (${((Date.now() - t) / 1000).toFixed(1)}s)`);
-    } catch (e) {
-      console.log(`FAILED: ${e.message}`);
-      try { unlinkSync(dest + '.part'); } catch {}
-      console.error(`\nDownload failed for ${rel}. Re-run to resume.`);
-      process.exit(1);
-    }
-  }
-  console.log(`\nDone — ${downloaded} downloaded (${(bytes / 1048576).toFixed(0)} MB), ${skipped} already present.`);
-  console.log('Neural TTS is ready. Set VORTEX_CU_TTS_ENGINE=auto (default) to use it.');
-}
-
-main().catch((e) => { console.error(e); process.exit(1); });
+#!/usr/bin/env node
+// computer-use — Supertonic 3 model downloader (one-time, ~380 MB) for the optional neural TTS engine.
+//
+// Downloads Supertone/supertonic-3 (OpenRAIL-M weights — commercial use permitted) into the model cache the
+// speak path expects. Idempotent: existing non-empty files are skipped, so re-running resumes a partial fetch.
+// Usage: node fetch-supertonic.mjs [targetDir]   (default: VORTEX_CU_TTS_MODEL_DIR or ~/.vortex/computer-use/supertonic-3)
+//
+// The engine code (speak-supertonic.mjs) is adapted from Supertone's MIT Node example; only the weights are
+// downloaded here, never bundled, keeping the npm package small and the license boundary clean.
+
+import { createWriteStream, existsSync, statSync, mkdirSync, renameSync, unlinkSync, writeFileSync } from 'node:fs';
+import { Readable } from 'node:stream';
+import { pipeline } from 'node:stream/promises';
+import { join, dirname } from 'node:path';
+import { homedir } from 'node:os';
+
+const HF = 'https://huggingface.co/Supertone/supertonic-3/resolve/main';
+const FILES = [
+  'onnx/duration_predictor.onnx',
+  'onnx/text_encoder.onnx',
+  'onnx/vector_estimator.onnx',
+  'onnx/vocoder.onnx',
+  'onnx/tts.json',
+  'onnx/unicode_indexer.json',
+  'config.json',
+  ...['F1', 'F2', 'F3', 'F4', 'F5', 'M1', 'M2', 'M3', 'M4', 'M5'].map((v) => `voice_styles/${v}.json`),
+];
+
+const targetDir = process.argv[2] || process.env.VORTEX_CU_TTS_MODEL_DIR || join(homedir(), '.vortex', 'computer-use', 'supertonic-3');
+// Per-process temp suffix so two concurrent fetchers (e.g. two instances on one
+// machine racing the same file) never write the SAME `.part` stream — each
+// renames its own complete download into place, so a present `dest` is always a
+// whole file, never a half-written one.
+const PART_SUFFIX = `.${process.pid}.part`;
+// Clear the session-start auto-download lock (base writes it before spawning us)
+// on exit — success OR failure — so a fast/transient failure never wedges the
+// retry window for hours. Harmless when run manually (no such lock, or already
+// gone). `exit` fires on normal completion and on process.exit(); the unlink is
+// synchronous as required there.
+const DOWNLOAD_LOCK = join(homedir(), '.vortex', 'computer-use', '.supertonic-download.lock');
+process.on('exit', () => { try { unlinkSync(DOWNLOAD_LOCK); } catch {} });
+
+async function fetchToFile(url, dest) {
+  const res = await fetch(url, { redirect: 'follow' });
+  if (!res.ok || !res.body) throw new Error(`HTTP ${res.status}`);
+  const tmp = dest + PART_SUFFIX;
+  mkdirSync(dirname(dest), { recursive: true });
+  await pipeline(Readable.fromWeb(res.body), createWriteStream(tmp));
+  renameSync(tmp, dest);
+  return statSync(dest).size;
+}
+
+async function main() {
+  console.log(`Supertonic 3 model cache: ${targetDir}`);
+  let downloaded = 0, skipped = 0, bytes = 0;
+  for (const rel of FILES) {
+    const dest = join(targetDir, rel);
+    if (existsSync(dest) && statSync(dest).size > 0) { skipped++; continue; }
+    process.stdout.write(`  ↓ ${rel} ... `);
+    try {
+      const t = Date.now();
+      const sz = await fetchToFile(`${HF}/${rel}`, dest);
+      bytes += sz;
+      downloaded++;
+      console.log(`${(sz / 1048576).toFixed(1)} MB (${((Date.now() - t) / 1000).toFixed(1)}s)`);
+    } catch (e) {
+      console.log(`FAILED: ${e.message}`);
+      try { unlinkSync(dest + PART_SUFFIX); } catch {}
+      console.error(`\nDownload failed for ${rel}. Re-run to resume.`);
+      process.exit(1);
+    }
+  }
+  // Completion marker — written only after every file has landed, so a consumer
+  // (e.g. base session-start's auto-download gate) can check ONE path to know the
+  // model is fully present instead of stat'ing the whole file list. A partial or
+  // interrupted run exits before this, leaving no marker, so the next run resumes.
+  try { writeFileSync(join(targetDir, '.ready'), new Date().toISOString() + '\n'); } catch {}
+  console.log(`\nDone — ${downloaded} downloaded (${(bytes / 1048576).toFixed(0)} MB), ${skipped} already present.`);
+  console.log('Neural TTS is ready. Set VORTEX_CU_TTS_ENGINE=auto (default) to use it.');
+}
+
+main().catch((e) => { console.error(e); process.exit(1); });