mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
33313e88f8
Salvaged from PR #68063 (@malaiwah). MatrixAdapter.send_voice now transcodes any non-Ogg audio to Ogg/Opus at the adapter boundary (best-effort — the original file is sent unchanged when ffmpeg is unavailable), so MSC3245 voice bubbles render even when a caller hands the adapter MP3/WAV audio. _matrix_voice_metadata_for_file probing now runs via asyncio.to_thread so ffprobe/ffmpeg subprocess timeouts can't stall the adapter event loop. The PR's tools/tts_tool.py want_opus hunk was dropped: main's OPUS_VOICE_PLATFORMS set (PR #73072) already includes matrix; the Matrix opus-routing test is kept. Refs #14841
97 lines
3.3 KiB
Python
97 lines
3.3 KiB
Python
import json
|
|
from pathlib import Path
|
|
from unittest.mock import Mock
|
|
|
|
import pytest
|
|
|
|
from gateway.session_context import _UNSET, _VAR_MAP
|
|
from tools import tts_tool
|
|
|
|
|
|
def _reset_session_context() -> None:
|
|
for var in _VAR_MAP.values():
|
|
var.set(_UNSET)
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _clean_session_platform(monkeypatch):
|
|
_reset_session_context()
|
|
monkeypatch.delenv("HERMES_SESSION_PLATFORM", raising=False)
|
|
yield
|
|
_reset_session_context()
|
|
|
|
|
|
async def _write_edge_output(_text: str, output_path: str, _tts_config: dict) -> str:
|
|
Path(output_path).write_bytes(b"mp3")
|
|
return output_path
|
|
|
|
|
|
def test_edge_cli_preserves_native_mp3(tmp_path, monkeypatch):
|
|
out = tmp_path / "speech.mp3"
|
|
convert = Mock()
|
|
|
|
monkeypatch.setattr(tts_tool, "_load_tts_config", lambda: {"provider": "edge"})
|
|
monkeypatch.setattr(tts_tool, "_import_edge_tts", lambda: object())
|
|
monkeypatch.setattr(tts_tool, "_generate_edge_tts", _write_edge_output)
|
|
monkeypatch.setattr(tts_tool, "_convert_to_opus", convert)
|
|
|
|
result = json.loads(tts_tool.text_to_speech_tool("hello", output_path=str(out)))
|
|
|
|
assert result["success"] is True
|
|
assert result["file_path"] == str(out)
|
|
assert result["voice_compatible"] is False
|
|
assert result["media_tag"] == f"MEDIA:{out}"
|
|
convert.assert_not_called()
|
|
|
|
|
|
def test_edge_telegram_converts_to_opus_voice(tmp_path, monkeypatch):
|
|
out = tmp_path / "speech.mp3"
|
|
opus = tmp_path / "speech.ogg"
|
|
|
|
def fake_convert(path: str) -> str:
|
|
assert path == str(out)
|
|
opus.write_bytes(b"ogg")
|
|
return str(opus)
|
|
|
|
convert = Mock(side_effect=fake_convert)
|
|
|
|
monkeypatch.setenv("HERMES_SESSION_PLATFORM", "telegram")
|
|
monkeypatch.setattr(tts_tool, "_load_tts_config", lambda: {"provider": "edge"})
|
|
monkeypatch.setattr(tts_tool, "_import_edge_tts", lambda: object())
|
|
monkeypatch.setattr(tts_tool, "_generate_edge_tts", _write_edge_output)
|
|
monkeypatch.setattr(tts_tool, "_convert_to_opus", convert)
|
|
|
|
result = json.loads(tts_tool.text_to_speech_tool("hello", output_path=str(out)))
|
|
|
|
assert result["success"] is True
|
|
assert result["file_path"] == str(opus)
|
|
assert result["voice_compatible"] is True
|
|
assert result["media_tag"] == f"[[audio_as_voice]]\nMEDIA:{opus}"
|
|
convert.assert_called_once_with(str(out))
|
|
|
|
|
|
def test_edge_matrix_converts_to_opus_voice(tmp_path, monkeypatch):
|
|
"""Matrix voice bubbles need Ogg/Opus too (MSC3245, issue #14841)."""
|
|
out = tmp_path / "speech.mp3"
|
|
opus = tmp_path / "speech.ogg"
|
|
|
|
def fake_convert(path: str) -> str:
|
|
assert path == str(out)
|
|
opus.write_bytes(b"ogg")
|
|
return str(opus)
|
|
|
|
convert = Mock(side_effect=fake_convert)
|
|
|
|
monkeypatch.setenv("HERMES_SESSION_PLATFORM", "matrix")
|
|
monkeypatch.setattr(tts_tool, "_load_tts_config", lambda: {"provider": "edge"})
|
|
monkeypatch.setattr(tts_tool, "_import_edge_tts", lambda: object())
|
|
monkeypatch.setattr(tts_tool, "_generate_edge_tts", _write_edge_output)
|
|
monkeypatch.setattr(tts_tool, "_convert_to_opus", convert)
|
|
|
|
result = json.loads(tts_tool.text_to_speech_tool("hello", output_path=str(out)))
|
|
|
|
assert result["success"] is True
|
|
assert result["file_path"] == str(opus)
|
|
assert result["voice_compatible"] is True
|
|
assert result["media_tag"] == f"[[audio_as_voice]]\nMEDIA:{opus}"
|
|
convert.assert_called_once_with(str(out))
|