Merge remote-tracking branch 'origin/feat/moss-tts-nano-isolated' into feat/cosyvoice3-isolated

backend/engines/voxcpm2_subprocess/main.py

@@ -142,6 +142,20 @@ def _sample_rate(model) -> int:
     return VOXCPM2_SAMPLE_RATE
 
 
+def _at_engine_rate(wav, sample_rate: int):
+    """The waveform at VOXCPM2_SAMPLE_RATE. The parent reads the PCM at that
+    fixed rate (it trims the tail and labels the audio with it), so a model
+    reporting another rate is resampled here rather than mislabelled."""
+    if sample_rate == VOXCPM2_SAMPLE_RATE:
+        return wav
+    import torch  # noqa: PLC0415
+    import torchaudio  # noqa: PLC0415
+
+    tensor = torch.as_tensor(wav.detach().cpu() if hasattr(wav, "detach") else wav,
+                             dtype=torch.float32).reshape(-1)
+    return torchaudio.functional.resample(tensor, sample_rate, VOXCPM2_SAMPLE_RATE)
+
+
 def _to_pcm_b64(wav) -> tuple[str, int]:
     """A float waveform in [-1, 1] (numpy or torch) as base64 int16 PCM."""
     import numpy as np  # noqa: PLC0415
@@ -189,11 +203,11 @@ def _handle_synthesize(msg: dict, stdout) -> None:
             prompt_wav_path=ref_audio if ref_text else None,
             prompt_text=ref_text,
         )
-    pcm_b64, n_samples = _to_pcm_b64(wav)
+    pcm_b64, n_samples = _to_pcm_b64(_at_engine_rate(wav, _sample_rate(model)))
     _send(stdout, {
         "op": "audio",
         "audio_pcm_b64": pcm_b64,
-        "sample_rate": _sample_rate(model),
+        "sample_rate": VOXCPM2_SAMPLE_RATE,
         "n_samples": n_samples,
     })
 

backend/services/sidecar_install.py

@@ -648,7 +648,14 @@ def engine_venv_python(env_var: str) -> Optional[Path]:
     if not env_dir:
         return None
     py = _venv_python(Path(env_dir) / ".venv")
-    return py if py.is_file() else None
+    # The interpreter alone proves nothing: a reinstall that failed partway
+    # leaves it behind. The completion marker is written only after the
+    # engine's import probe passed in this venv, and removed when a new
+    # dependency step starts, so it is the probe's verdict without running a
+    # multi-second import on every engine-list refresh.
+    if not py.is_file() or not (Path(env_dir) / _INSTALL_COMPLETE_MARKER).is_file():
+        return None
+    return py
 
 
 def _legacy_managed_checkouts(spec: SidecarSpec) -> tuple[Path, ...]:

tests/test_moss_tts_nano_subprocess.py

@@ -120,7 +120,7 @@ def test_the_sidecar_imports_nothing_from_the_app():
 def test_the_class_switches_to_the_sidecar_once_its_venv_exists(monkeypatch, tmp_path):
     from engines.moss_tts_nano_subprocess import MossTTSNanoSubprocessBackend
     from services import tts_backend
-    from services.sidecar_install import _venv_python
+    from services.sidecar_install import _INSTALL_COMPLETE_MARKER, _venv_python
 
     monkeypatch.setenv("OMNIVOICE_MOSS_TTS_NANO_DIR", "")
     monkeypatch.delenv("OMNIVOICE_MOSS_TTS_NANO_DIR")
@@ -129,6 +129,7 @@ def test_the_class_switches_to_the_sidecar_once_its_venv_exists(monkeypatch, tmp
     py = _venv_python(tmp_path / ".venv")
     py.parent.mkdir(parents=True)
     py.write_text("#!fake\n")
+    (tmp_path / _INSTALL_COMPLETE_MARKER).write_text("x\n", encoding="utf-8")
     monkeypatch.setenv("OMNIVOICE_MOSS_TTS_NANO_DIR", str(tmp_path))
 
     cls = tts_backend.get_backend_class("moss-tts-nano")

tests/test_pockettts_deferred.py

@@ -289,7 +289,7 @@ def test_prefers_the_venv_its_one_click_install_made(monkeypatch, tmp_path, mock
     interpreter, where `uv sync --extra pockettts` installs it."""
     from pathlib import Path
 
-    from services.sidecar_install import _venv_python
+    from services.sidecar_install import _INSTALL_COMPLETE_MARKER, _venv_python
 
     mock_settings_store["pockettts"] = True
     monkeypatch.delenv("OMNIVOICE_POCKETTTS_DIR", raising=False)
@@ -298,6 +298,7 @@ def test_prefers_the_venv_its_one_click_install_made(monkeypatch, tmp_path, mock
     py = _venv_python(tmp_path / ".venv")
     py.parent.mkdir(parents=True)
     py.write_text("#!fake\n")
+    (tmp_path / _INSTALL_COMPLETE_MARKER).write_text("x\n", encoding="utf-8")
     monkeypatch.setenv("OMNIVOICE_POCKETTTS_DIR", str(tmp_path))
     assert _backend_cls().venv_python() == py
     # Available without pocket_tts importable in the app's own environment.

tests/test_sidecar_install.py

@@ -1221,6 +1221,9 @@ def test_engine_venv_python_needs_a_real_interpreter(monkeypatch, tmp_path):
     py = si._venv_python(tmp_path / ".venv")
     py.parent.mkdir(parents=True)
     py.write_text("#!fake\n")
+    # An interpreter without the marker is a failed or unfinished install.
+    assert si.engine_venv_python("OMNIVOICE_FAKE_SIDE_DIR") is None
+    (tmp_path / si._INSTALL_COMPLETE_MARKER).write_text("x\n", encoding="utf-8")
     assert si.engine_venv_python("OMNIVOICE_FAKE_SIDE_DIR") == py
 
 

tests/test_supertonic3.py

@@ -389,7 +389,7 @@ def test_prefers_the_venv_its_one_click_install_made(monkeypatch, tmp_path, mock
     from pathlib import Path
 
     from engines.supertonic3.backend import Supertonic3Backend
-    from services.sidecar_install import _venv_python
+    from services.sidecar_install import _INSTALL_COMPLETE_MARKER, _venv_python
 
     mock_settings_store["supertonic3"] = True
     monkeypatch.delenv("OMNIVOICE_SUPERTONIC3_DIR", raising=False)
@@ -398,6 +398,7 @@ def test_prefers_the_venv_its_one_click_install_made(monkeypatch, tmp_path, mock
     py = _venv_python(tmp_path / ".venv")
     py.parent.mkdir(parents=True)
     py.write_text("#!fake\n")
+    (tmp_path / _INSTALL_COMPLETE_MARKER).write_text("x\n", encoding="utf-8")
     monkeypatch.setenv("OMNIVOICE_SUPERTONIC3_DIR", str(tmp_path))
     assert Supertonic3Backend.venv_python() == py
     # Available without supertonic importable in the app's own environment.

tests/test_voxcpm2_subprocess.py

@@ -129,11 +129,15 @@ def test_retries_a_transient_download_failure_only(monkeypatch):
     assert sidecar._with_retries(flaky) == "model"
     assert len(attempts) == 3
 
+    broken_calls = []
+
     def broken():
+        broken_calls.append(1)
         raise ValueError("bad config")
 
     with pytest.raises(ValueError):
         sidecar._with_retries(broken)
+    assert len(broken_calls) == 1  # a permanent error is not retried
 
 
 def test_the_sidecar_imports_nothing_from_the_app():
@@ -145,7 +149,7 @@ def test_the_sidecar_imports_nothing_from_the_app():
 def test_the_class_switches_to_the_sidecar_once_its_venv_exists(monkeypatch, tmp_path):
     from engines.voxcpm2_subprocess import VoxCPM2SubprocessBackend
     from services import tts_backend
-    from services.sidecar_install import _venv_python
+    from services.sidecar_install import _INSTALL_COMPLETE_MARKER, _venv_python
 
     monkeypatch.setenv("OMNIVOICE_VOXCPM2_DIR", "")
     monkeypatch.delenv("OMNIVOICE_VOXCPM2_DIR")
@@ -154,6 +158,7 @@ def test_the_class_switches_to_the_sidecar_once_its_venv_exists(monkeypatch, tmp
     py = _venv_python(tmp_path / ".venv")
     py.parent.mkdir(parents=True)
     py.write_text("#!fake\n")
+    (tmp_path / _INSTALL_COMPLETE_MARKER).write_text("x\n", encoding="utf-8")
     monkeypatch.setenv("OMNIVOICE_VOXCPM2_DIR", str(tmp_path))
 
     cls = tts_backend.get_backend_class("voxcpm2")
@@ -197,3 +202,29 @@ def test_the_sidecar_class_prepares_the_reference_and_trims_the_tail(monkeypatch
     assert sent["ref_audio"] == "/clip.wav.prepared.wav"
     assert trimmed["sr"] == 48000
     assert tuple(out.shape) == (1, 10)
+
+
+def test_output_is_resampled_to_the_48_khz_the_parent_assumes(monkeypatch):
+    """The parent trims and labels the PCM at a fixed 48 kHz, so a model that
+    reports another rate must be resampled, not passed through."""
+    sidecar = _load_sidecar(monkeypatch, [])
+    sidecar._handle_synthesize({"text": "warm up"}, io.BytesIO())
+    type(sidecar._MODEL).sample_rate = 24000
+    out = io.BytesIO()
+    sidecar._handle_synthesize({"text": "hi"}, out)
+    audio = _frames(out)[-1]
+    assert audio["sample_rate"] == 48000
+    assert audio["n_samples"] == 960  # 480 samples at 24 kHz
+
+
+def test_a_failed_install_leaves_voxcpm2_in_process(monkeypatch, tmp_path):
+    """A venv interpreter without the completion marker (a reinstall that
+    failed partway) must not hide the working in-process engine."""
+    from services import tts_backend
+    from services.sidecar_install import _venv_python
+
+    py = _venv_python(tmp_path / ".venv")
+    py.parent.mkdir(parents=True)
+    py.write_text("#!fake\n")
+    monkeypatch.setenv("OMNIVOICE_VOXCPM2_DIR", str(tmp_path))
+    assert tts_backend.get_backend_class("voxcpm2") is tts_backend.VoxCPM2Backend