mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
0f597dd127
Legacy flat stt.model config key (from cli-config.yaml.example and older versions) was passed as a model override to transcribe_audio() by the gateway, bypassing provider-specific model resolution. When the provider was 'local' (faster-whisper), this caused: ValueError: Invalid model size 'whisper-1' Changes: - gateway/run.py, discord.py: stop passing model override — let transcribe_audio() handle provider-specific model resolution internally - get_stt_model_from_config(): now provider-aware, reads from the correct nested section (stt.local.model, stt.openai.model, etc.); ignores legacy flat key for local provider to prevent model name mismatch - cli-config.yaml.example: updated STT section to show nested provider config structure instead of legacy flat key - config migration v13→v14: moves legacy stt.model to the correct provider section and removes the flat key Reported by community user on Discord.
71 lines
2.2 KiB
Python
71 lines
2.2 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"),
|
|
):
|
|
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"},
|
|
):
|
|
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
|