mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-13 09:01:54 +00:00
d55304c39f
Salvaged from #6600 (@kristianvast) — re-scoped to the voice half only and
rebased onto current main. The cascading-interrupt hang half of the original
PR landed independently in dd0d1222a, so this carries ONLY Problem 1.
When a voice/audio message arrives while the agent is busy on the same
session, it hit the interrupt path with empty text because STT only ran after
the running-agent guard — the voice was effectively lost. Now we transcribe
audio BEFORE signaling the agent (and on the fresh-message path), echo the raw
transcript back to the user (🎙️), and _enrich_message_with_transcription
returns (text, transcripts) so callers can echo. A new
_dequeue_pending_with_transcription drives the post-agent drain the same way.
Reapplied onto _prepare_inbound_message_text (inbound enrichment was extracted
from the inline dispatch block since the original PR).
Co-authored-by: Kristian Vastveit <kristian@agrointel.no>
145 lines
4.4 KiB
Python
145 lines
4.4 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, Platform, load_gateway_config
|
|
from gateway.platforms.base import MessageEvent, MessageType
|
|
from gateway.session import SessionSource
|
|
|
|
|
|
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_surfaces_path_when_stt_disabled():
|
|
from gateway.run import GatewayRunner
|
|
|
|
runner = GatewayRunner.__new__(GatewayRunner)
|
|
runner.config = GatewayConfig(stt_enabled=False)
|
|
runner._has_setup_skill = lambda: True # Should NOT be consulted in disabled branch.
|
|
|
|
with patch(
|
|
"tools.transcription_tools.transcribe_audio",
|
|
side_effect=AssertionError("transcribe_audio should not be called when STT is disabled"),
|
|
), patch(
|
|
"gateway.run._probe_audio_duration",
|
|
new=AsyncMock(return_value="0:12"),
|
|
):
|
|
result, transcripts = await runner._enrich_message_with_transcription(
|
|
"caption",
|
|
["/tmp/voice.ogg"],
|
|
)
|
|
|
|
assert "/tmp/voice.ogg" in result
|
|
assert "voice message" in result.lower()
|
|
assert "(duration: 0:12)" in result
|
|
assert "caption" in result
|
|
assert transcripts == []
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_enrich_message_with_transcription_omits_duration_on_probe_failure():
|
|
from gateway.run import GatewayRunner
|
|
|
|
runner = GatewayRunner.__new__(GatewayRunner)
|
|
runner.config = GatewayConfig(stt_enabled=False)
|
|
|
|
with patch(
|
|
"gateway.run._probe_audio_duration",
|
|
new=AsyncMock(return_value=None),
|
|
):
|
|
result, transcripts = await runner._enrich_message_with_transcription(
|
|
"",
|
|
["/tmp/voice.ogg"],
|
|
)
|
|
|
|
assert "/tmp/voice.ogg" in result
|
|
assert "duration" not in result.lower()
|
|
assert transcripts == []
|
|
|
|
|
|
@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, transcripts = 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
|
|
assert transcripts == []
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_prepare_inbound_message_text_transcribes_queued_voice_event():
|
|
from gateway.run import GatewayRunner
|
|
|
|
runner = GatewayRunner.__new__(GatewayRunner)
|
|
runner.config = GatewayConfig(stt_enabled=True)
|
|
runner.adapters = {}
|
|
runner._model = "test-model"
|
|
runner._base_url = ""
|
|
runner._has_setup_skill = lambda: False
|
|
|
|
source = SessionSource(
|
|
platform=Platform.TELEGRAM,
|
|
chat_id="123",
|
|
chat_type="dm",
|
|
)
|
|
event = MessageEvent(
|
|
text="",
|
|
message_type=MessageType.VOICE,
|
|
source=source,
|
|
media_urls=["/tmp/queued-voice.ogg"],
|
|
media_types=["audio/ogg"],
|
|
)
|
|
|
|
with patch(
|
|
"tools.transcription_tools.transcribe_audio",
|
|
return_value={
|
|
"success": True,
|
|
"transcript": "queued voice transcript",
|
|
"provider": "local_command",
|
|
},
|
|
):
|
|
result = await runner._prepare_inbound_message_text(
|
|
event=event,
|
|
source=source,
|
|
history=[],
|
|
)
|
|
|
|
assert result is not None
|
|
assert "queued voice transcript" in result
|
|
assert "voice message" in result.lower()
|