mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
ba13132298
Saying OR typing a configured stop phrase (voice.stop_phrases, default
"stop") now ends the voice chat everywhere, not just classic CLI PTT:
- hermes_cli/voice.py: new explicit on_stop_phrase callback through
start_continuous/stop_continuous. The force-transcribe path previously
DISCARDED the stop phrase silently — with auto_restart=False the client
re-arms the next capture, so the conversation never ended. Both halt
paths now fire on_stop_phrase (fallback: on_silent_limit for legacy
callers) as user intent, distinct from the no-speech timeout.
- tui_gateway/server.py: voice.record wires on_stop_phrase and emits
voice.transcript {stop_phrase: true} after flipping HERMES_VOICE(_TTS)
off and stopping streaming TTS — same teardown as /voice off. The TTS
barge-in monitor stop-checks its transcript too. prompt.submit consumes
a TYPED bare stop phrase at the server-side choke point when voice mode
is on (returns {voice_stopped: true}, no turn starts).
- ui-tui: voice.transcript {stop_phrase} ends voice mode with a clear
'voice chat ended' notice (distinct from the no-speech-limit message);
submitPrompt releases the busy latch on a consumed voice_stopped reply.
- cli.py: _typed_voice_stop in process_loop — typing a bare stop phrase
while voice mode/continuous is active ends voice mode instead of
sending 'stop' to the agent; typed 'stop' outside voice mode is
unchanged. Voice transcripts skip the check (already stop-checked).
- desktop: interceptsTypedVoiceStop — the composer's onSubmit ends the
live voice conversation (same path as clicking end on the pill) when a
bare stop command is typed with no attachments; renderer-owned loop, so
handled client-side like the existing spoken isVoiceStopCommand.
- tools/voice_mode.py: transcribe_recording never lets the Whisper
hallucination filter swallow a configured stop phrase (e.g. 'bye'
configured as a stop phrase is both a hallucination-blocklist entry and
a stop phrase — stop-phrase check now wins).
Tests: continuous-loop signal (sabotage-verified), force-transcribe stop
signal + legacy fallback, hallucination-filter ordering, typed-stop CLI
unit tests (voice on/off/longer text), prompt.submit typed-stop gateway
tests, TUI vitest for stop_phrase event handling, desktop vitest for the
typed-stop interceptor.
305 lines
12 KiB
Python
305 lines
12 KiB
Python
"""Tests for the voice-chat stop phrase (say "stop" and nothing else to end).
|
|
|
|
Contract:
|
|
- `is_voice_stop_phrase` matches ONLY when the whole utterance equals a
|
|
configured phrase (case-insensitive, surrounding punctuation stripped).
|
|
- Default phrase list is ("stop",); `voice.stop_phrases` in config.yaml
|
|
customizes it; `[]` disables the feature.
|
|
- In the shared continuous loop, a stop phrase halts the loop (like the
|
|
silent-cycle limit) and is NEVER delivered to the agent.
|
|
"""
|
|
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
from tools.voice_mode import (
|
|
DEFAULT_VOICE_STOP_PHRASES,
|
|
_load_voice_stop_phrases,
|
|
is_voice_stop_phrase,
|
|
)
|
|
|
|
|
|
class TestIsVoiceStopPhrase:
|
|
@pytest.mark.parametrize("utterance", [
|
|
"stop", "Stop", "STOP", "stop.", "Stop!", " stop ", '"Stop."', "stop?",
|
|
])
|
|
def test_bare_stop_matches(self, utterance):
|
|
assert is_voice_stop_phrase(utterance, ("stop",)) is True
|
|
|
|
@pytest.mark.parametrize("utterance", [
|
|
"stop doing that",
|
|
"please stop",
|
|
"stop the build and rerun tests",
|
|
"don't stop",
|
|
"stopwatch",
|
|
"",
|
|
" ",
|
|
"ok",
|
|
])
|
|
def test_longer_utterances_pass_through(self, utterance):
|
|
assert is_voice_stop_phrase(utterance, ("stop",)) is False
|
|
|
|
def test_custom_phrases(self):
|
|
phrases = ("stop", "goodbye hermes")
|
|
assert is_voice_stop_phrase("Goodbye Hermes!", phrases) is True
|
|
assert is_voice_stop_phrase("goodbye hermes, one more thing", phrases) is False
|
|
|
|
def test_empty_phrase_list_disables(self):
|
|
assert is_voice_stop_phrase("stop", ()) is False
|
|
|
|
def test_uses_config_when_phrases_omitted(self):
|
|
with patch("tools.voice_mode._load_voice_stop_phrases", return_value=("halt",)):
|
|
assert is_voice_stop_phrase("halt") is True
|
|
assert is_voice_stop_phrase("stop") is False
|
|
|
|
|
|
class TestLoadVoiceStopPhrases:
|
|
def _with_cfg(self, voice_cfg):
|
|
return patch(
|
|
"hermes_cli.config.load_config",
|
|
return_value={"voice": voice_cfg},
|
|
)
|
|
|
|
def test_default(self):
|
|
with self._with_cfg({}):
|
|
assert _load_voice_stop_phrases() == DEFAULT_VOICE_STOP_PHRASES
|
|
|
|
def test_custom_list(self):
|
|
with self._with_cfg({"stop_phrases": ["Stop", " Goodbye Hermes "]}):
|
|
assert _load_voice_stop_phrases() == ("stop", "goodbye hermes")
|
|
|
|
def test_empty_list_disables(self):
|
|
with self._with_cfg({"stop_phrases": []}):
|
|
assert _load_voice_stop_phrases() == ()
|
|
|
|
def test_bare_string_coerced(self):
|
|
with self._with_cfg({"stop_phrases": "halt"}):
|
|
assert _load_voice_stop_phrases() == ("halt",)
|
|
|
|
def test_malformed_falls_back(self):
|
|
with self._with_cfg({"stop_phrases": {"bad": "shape"}}):
|
|
assert _load_voice_stop_phrases() == DEFAULT_VOICE_STOP_PHRASES
|
|
|
|
def test_config_error_falls_back(self):
|
|
with patch("hermes_cli.config.load_config", side_effect=RuntimeError):
|
|
assert _load_voice_stop_phrases() == DEFAULT_VOICE_STOP_PHRASES
|
|
|
|
|
|
class TestContinuousLoopStopPhrase:
|
|
"""The shared continuous-loop silence callback ends the loop on a stop
|
|
phrase and never forwards it to on_transcript."""
|
|
|
|
def _run_silence_cycle(self, transcript_text):
|
|
import hermes_cli.voice as v
|
|
|
|
delivered = []
|
|
silent_limit_fired = []
|
|
|
|
class _FakeRecorder:
|
|
_peak_rms = 500
|
|
|
|
def stop(self):
|
|
return "/tmp/fake.wav"
|
|
|
|
def cancel(self):
|
|
pass
|
|
|
|
def start(self, on_silence_stop=None):
|
|
pass
|
|
|
|
fake_result = {"success": True, "transcript": transcript_text}
|
|
with patch.object(v, "_continuous_active", True), \
|
|
patch.object(v, "_continuous_recorder", _FakeRecorder()), \
|
|
patch.object(v, "_continuous_on_transcript", delivered.append), \
|
|
patch.object(v, "_continuous_on_status", None), \
|
|
patch.object(v, "_continuous_on_silent_limit",
|
|
lambda: silent_limit_fired.append(True)), \
|
|
patch.object(v, "_continuous_no_speech_count", 0), \
|
|
patch.object(v, "transcribe_recording", return_value=fake_result), \
|
|
patch.object(v, "_play_beep", lambda **kw: None), \
|
|
patch.object(v.os.path, "isfile", return_value=False):
|
|
v._continuous_on_silence()
|
|
still_active = v._continuous_active
|
|
return delivered, silent_limit_fired, still_active
|
|
|
|
def test_stop_phrase_halts_loop_and_is_not_delivered(self):
|
|
delivered, silent_limit, still_active = self._run_silence_cycle("Stop.")
|
|
assert delivered == []
|
|
assert silent_limit == [True]
|
|
assert still_active is False
|
|
|
|
def test_normal_transcript_is_delivered(self):
|
|
delivered, silent_limit, _ = self._run_silence_cycle("stop the build and rerun")
|
|
assert delivered == ["stop the build and rerun"]
|
|
assert silent_limit == []
|
|
|
|
|
|
class TestContinuousLoopStopPhraseSignal:
|
|
"""The explicit on_stop_phrase signal: fired on a spoken stop phrase so
|
|
consumers (TUI, desktop) end the conversation as user intent, with
|
|
on_silent_limit as the legacy fallback when it isn't wired."""
|
|
|
|
class _FakeRecorder:
|
|
_peak_rms = 500
|
|
|
|
def stop(self):
|
|
return "/tmp/fake.wav"
|
|
|
|
def cancel(self):
|
|
pass
|
|
|
|
def start(self, on_silence_stop=None):
|
|
pass
|
|
|
|
def _run_silence_cycle(self, transcript_text, on_stop_phrase):
|
|
import hermes_cli.voice as v
|
|
|
|
delivered = []
|
|
silent_limit_fired = []
|
|
|
|
fake_result = {"success": True, "transcript": transcript_text}
|
|
with patch.object(v, "_continuous_active", True), \
|
|
patch.object(v, "_continuous_recorder", self._FakeRecorder()), \
|
|
patch.object(v, "_continuous_on_transcript", delivered.append), \
|
|
patch.object(v, "_continuous_on_status", None), \
|
|
patch.object(v, "_continuous_on_silent_limit",
|
|
lambda: silent_limit_fired.append(True)), \
|
|
patch.object(v, "_continuous_on_stop_phrase", on_stop_phrase), \
|
|
patch.object(v, "_continuous_no_speech_count", 0), \
|
|
patch.object(v, "transcribe_recording", return_value=fake_result), \
|
|
patch.object(v, "_play_beep", lambda **kw: None), \
|
|
patch.object(v.os.path, "isfile", return_value=False):
|
|
v._continuous_on_silence()
|
|
still_active = v._continuous_active
|
|
return delivered, silent_limit_fired, still_active
|
|
|
|
def test_stop_phrase_fires_dedicated_signal_not_silent_limit(self):
|
|
stop_fired = []
|
|
delivered, silent_limit, still_active = self._run_silence_cycle(
|
|
"Stop.", stop_fired.append
|
|
)
|
|
assert stop_fired == ["Stop."]
|
|
assert silent_limit == []
|
|
assert delivered == []
|
|
assert still_active is False
|
|
|
|
def test_normal_transcript_never_fires_stop_signal(self):
|
|
stop_fired = []
|
|
delivered, silent_limit, _ = self._run_silence_cycle(
|
|
"stop the build and rerun", stop_fired.append
|
|
)
|
|
assert stop_fired == []
|
|
assert delivered == ["stop the build and rerun"]
|
|
assert silent_limit == []
|
|
|
|
def test_force_transcribe_stop_phrase_fires_signal(self):
|
|
"""stop_continuous(force_transcribe=True) — the auto_restart=False
|
|
client-driven path (TUI/desktop voice.record stop) — must fire the
|
|
stop signal instead of silently discarding the transcript, or the
|
|
client re-arms the next capture and the conversation never ends."""
|
|
import hermes_cli.voice as v
|
|
|
|
delivered = []
|
|
stop_fired = []
|
|
threads = []
|
|
|
|
fake_result = {"success": True, "transcript": "stop"}
|
|
with patch.object(v, "_continuous_active", True), \
|
|
patch.object(v, "_continuous_auto_restart", False), \
|
|
patch.object(v, "_continuous_recorder", self._FakeRecorder()), \
|
|
patch.object(v, "_continuous_on_transcript", delivered.append), \
|
|
patch.object(v, "_continuous_on_status", None), \
|
|
patch.object(v, "_continuous_on_silent_limit", None), \
|
|
patch.object(v, "_continuous_on_stop_phrase", stop_fired.append), \
|
|
patch.object(v, "_continuous_no_speech_count", 0), \
|
|
patch.object(v, "transcribe_recording", return_value=fake_result), \
|
|
patch.object(v, "_play_beep", lambda **kw: None), \
|
|
patch.object(v.threading, "Thread",
|
|
side_effect=lambda target, daemon=None: threads.append(target)
|
|
or _ImmediateThread(target)), \
|
|
patch.object(v.os.path, "isfile", return_value=False):
|
|
v.stop_continuous(force_transcribe=True)
|
|
|
|
assert stop_fired == ["stop"]
|
|
assert delivered == []
|
|
|
|
def test_force_transcribe_stop_phrase_falls_back_to_silent_limit(self):
|
|
"""Legacy consumers that never wired on_stop_phrase still get the
|
|
voice-off signal via on_silent_limit."""
|
|
import hermes_cli.voice as v
|
|
|
|
silent_limit_fired = []
|
|
|
|
fake_result = {"success": True, "transcript": "stop"}
|
|
with patch.object(v, "_continuous_active", True), \
|
|
patch.object(v, "_continuous_auto_restart", False), \
|
|
patch.object(v, "_continuous_recorder", self._FakeRecorder()), \
|
|
patch.object(v, "_continuous_on_transcript", lambda t: None), \
|
|
patch.object(v, "_continuous_on_status", None), \
|
|
patch.object(v, "_continuous_on_silent_limit",
|
|
lambda: silent_limit_fired.append(True)), \
|
|
patch.object(v, "_continuous_on_stop_phrase", None), \
|
|
patch.object(v, "_continuous_no_speech_count", 0), \
|
|
patch.object(v, "transcribe_recording", return_value=fake_result), \
|
|
patch.object(v, "_play_beep", lambda **kw: None), \
|
|
patch.object(v.threading, "Thread",
|
|
side_effect=lambda target, daemon=None: _ImmediateThread(target)), \
|
|
patch.object(v.os.path, "isfile", return_value=False):
|
|
v.stop_continuous(force_transcribe=True)
|
|
|
|
assert silent_limit_fired == [True]
|
|
|
|
def test_start_continuous_accepts_on_stop_phrase_kwarg(self):
|
|
import inspect
|
|
|
|
import hermes_cli.voice as v
|
|
|
|
assert "on_stop_phrase" in inspect.signature(v.start_continuous).parameters
|
|
|
|
|
|
class _ImmediateThread:
|
|
"""Thread stand-in that runs the target synchronously on start()."""
|
|
|
|
def __init__(self, target):
|
|
self._target = target
|
|
|
|
def start(self):
|
|
self._target()
|
|
|
|
|
|
class TestStopPhraseSurvivesHallucinationFilter:
|
|
"""Ordering contract: a configured stop phrase must never be eaten by the
|
|
Whisper hallucination filter inside transcribe_recording. "bye" is BOTH a
|
|
known hallucination and a plausible stop phrase — when configured as a
|
|
stop phrase it must come through so the stop check can end the chat."""
|
|
|
|
def _transcribe(self, text, phrases):
|
|
import tools.voice_mode as vm
|
|
|
|
with patch.object(
|
|
vm, "_load_voice_stop_phrases", return_value=tuple(phrases)
|
|
), patch(
|
|
"tools.transcription_tools.transcribe_audio",
|
|
return_value={"success": True, "transcript": text},
|
|
):
|
|
return vm.transcribe_recording("/tmp/fake.wav")
|
|
|
|
def test_configured_stop_phrase_survives_blocklist(self):
|
|
result = self._transcribe("Bye.", ["stop", "bye"])
|
|
assert result["success"] is True
|
|
assert result["transcript"] == "Bye."
|
|
assert not result.get("filtered")
|
|
|
|
def test_unconfigured_hallucination_still_filtered(self):
|
|
result = self._transcribe("Bye.", ["stop"])
|
|
assert result["success"] is True
|
|
assert result["transcript"] == ""
|
|
assert result.get("filtered") is True
|
|
|
|
def test_default_stop_survives_repeat_regex_adjacent_phrases(self):
|
|
# "stop." is not in the blocklist/repeat regex today; this pins the
|
|
# contract so a future blocklist addition can't swallow it.
|
|
result = self._transcribe("Stop.", ["stop"])
|
|
assert result["transcript"] == "Stop."
|
|
assert not result.get("filtered")
|