Files
hermes-agent/tests/gateway/test_stt_config.py
teknium1 1f72ce71b7 fix: restore local STT fallback for gateway voice notes
Restore local STT command fallback for voice transcription, detect whisper and ffmpeg in common local install paths, and avoid bogus no-provider messaging when only a backend-specific key is missing.
2026-03-15 21:51:40 -07:00

78 lines
2.4 KiB
Python

"""Gateway STT config tests — honor stt.enabled: false from config.yaml."""
from pathlib import Path
from unittest.mock import AsyncMock, patch
import pytest
import yaml
from gateway.config import GatewayConfig, load_gateway_config
def test_gateway_config_stt_disabled_from_dict_nested():
config = GatewayConfig.from_dict({"stt": {"enabled": False}})
assert config.stt_enabled is False
def test_load_gateway_config_bridges_stt_enabled_from_config_yaml(tmp_path, monkeypatch):
hermes_home = tmp_path / ".hermes"
hermes_home.mkdir()
(hermes_home / "config.yaml").write_text(
yaml.dump({"stt": {"enabled": False}}),
encoding="utf-8",
)
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
monkeypatch.setattr(Path, "home", lambda: tmp_path)
config = load_gateway_config()
assert config.stt_enabled is False
@pytest.mark.asyncio
async def test_enrich_message_with_transcription_skips_when_stt_disabled():
from gateway.run import GatewayRunner
runner = GatewayRunner.__new__(GatewayRunner)
runner.config = GatewayConfig(stt_enabled=False)
with patch(
"tools.transcription_tools.transcribe_audio",
side_effect=AssertionError("transcribe_audio should not be called when STT is disabled"),
), patch(
"tools.transcription_tools.get_stt_model_from_config",
return_value=None,
):
result = await runner._enrich_message_with_transcription(
"caption",
["/tmp/voice.ogg"],
)
assert "transcription is disabled" in result.lower()
assert "caption" in result
@pytest.mark.asyncio
async def test_enrich_message_with_transcription_avoids_bogus_no_provider_message_for_backend_key_errors():
from gateway.run import GatewayRunner
runner = GatewayRunner.__new__(GatewayRunner)
runner.config = GatewayConfig(stt_enabled=True)
with patch(
"tools.transcription_tools.transcribe_audio",
return_value={"success": False, "error": "VOICE_TOOLS_OPENAI_KEY not set"},
), patch(
"tools.transcription_tools.get_stt_model_from_config",
return_value=None,
):
result = await runner._enrich_message_with_transcription(
"caption",
["/tmp/voice.ogg"],
)
assert "No STT provider is configured" not in result
assert "trouble transcribing" in result
assert "caption" in result