mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
39975613b1
Second, deeper pass over tools/gateway/hermes_cli plus first pass over the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker, dashboard, conformance, monitoring, secret_sources, hermes_state, providers). Same rubric as wave 1 (AGENTS.md test policy); security, alternation/caching invariants, issue-number regressions, and E2E kept. Real test-quality fixes found and rooted out along the way: - tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls (DEFAULT_CONFIG smart-approval leaked in) — pinned approval mode=manual via autouse fixture: 17.4s → 0.4s. - test_model_switch_custom_providers.py / test_user_providers_model_switch.py silently probed live provider catalogs (~2s/test) — stubbed cached_provider_model_ids/provider_model_ids/fetch_api_models. - test_telegram_noise_filter.py: 15-platform copy-paste matrix over shared gateway.run logic → 3 representative platforms (55s → 3.9s). - test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on MagicMock agents — interrupt.side_effect now clears _running_agents (22s → 1.0s). - test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait 5s → 0.5s. - test_telegram_init_deadline.py: loop-block margin restored to 1.0s with rationale comment — the watchdog-dump assertion needs the loop blocked well past deadline+grace under parallel load (flaked once in the 40-worker verification run at a 0.2s margin). Verification: full hermetic suite via scripts/run_tests.sh — 2,438 files, 21,718 tests passed, 0 failed, 293.9s wall. Suite totals vs original baseline: 46,820 → 19,757 test functions (−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
127 lines
4.7 KiB
Python
127 lines
4.7 KiB
Python
"""
|
|
Tests for #24870 — Telegram: audio file attachments must NOT be routed to STT.
|
|
|
|
Telegram distinguishes three kinds of audio payloads:
|
|
- message.voice → Opus/OGG voice message → STT pipeline
|
|
- message.audio → audio file attachment → file path note, NOT STT
|
|
- message.document (audio mime) → generic file route
|
|
|
|
These tests confirm that:
|
|
1. MessageType.VOICE events still flow through the STT pipeline.
|
|
2. MessageType.AUDIO events bypass STT and get a file-path context note instead.
|
|
3. Mixed media lists (voice + audio) split correctly.
|
|
"""
|
|
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
from gateway.config import GatewayConfig, Platform
|
|
from gateway.platforms.base import MessageEvent, MessageType
|
|
from gateway.session import SessionSource
|
|
|
|
|
|
def _make_runner(stt_enabled: bool = True) -> "GatewayRunner": # type: ignore[name-defined]
|
|
from gateway.run import GatewayRunner
|
|
|
|
runner = GatewayRunner.__new__(GatewayRunner)
|
|
runner.config = GatewayConfig(stt_enabled=stt_enabled)
|
|
runner.adapters = {}
|
|
runner._model = "test-model"
|
|
runner._base_url = ""
|
|
runner._has_setup_skill = lambda: False
|
|
return runner
|
|
|
|
|
|
def _voice_event(path: str = "/tmp/voice.ogg") -> MessageEvent:
|
|
return MessageEvent(
|
|
text="",
|
|
message_type=MessageType.VOICE,
|
|
source=SessionSource(platform=Platform.TELEGRAM, chat_id="1", chat_type="dm"),
|
|
media_urls=[path],
|
|
media_types=["audio/ogg"],
|
|
)
|
|
|
|
|
|
def _audio_event(path: str = "/tmp/song.mp3") -> MessageEvent:
|
|
return MessageEvent(
|
|
text="",
|
|
message_type=MessageType.AUDIO,
|
|
source=SessionSource(platform=Platform.TELEGRAM, chat_id="1", chat_type="dm"),
|
|
media_urls=[path],
|
|
media_types=["audio/mpeg"],
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 1. VOICE still goes through STT
|
|
# ---------------------------------------------------------------------------
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_voice_message_still_transcribed():
|
|
"""MessageType.VOICE must still be sent through _enrich_message_with_transcription."""
|
|
runner = _make_runner(stt_enabled=True)
|
|
source = SessionSource(platform=Platform.TELEGRAM, chat_id="1", chat_type="dm")
|
|
event = _voice_event("/tmp/voice.ogg")
|
|
|
|
with patch(
|
|
"tools.transcription_tools.transcribe_audio",
|
|
return_value={"success": True, "transcript": "hello world", "provider": "whisper"},
|
|
) as mock_transcribe:
|
|
result = await runner._prepare_inbound_message_text(
|
|
event=event,
|
|
source=source,
|
|
history=[],
|
|
)
|
|
|
|
mock_transcribe.assert_called_once_with("/tmp/voice.ogg")
|
|
# The transcript passes through as a plain quoted line — no "voice message"
|
|
# meta-commentary in the LLM-visible prompt.
|
|
assert "hello world" in result
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 2. AUDIO file attachment bypasses STT
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_audio_attachment_context_note_format():
|
|
"""Context note for audio file attachments should include the file path and guidance."""
|
|
runner = _make_runner(stt_enabled=True)
|
|
source = SessionSource(platform=Platform.TELEGRAM, chat_id="1", chat_type="dm")
|
|
event = _audio_event("/tmp/cache_12345_my_song.mp3")
|
|
|
|
with patch(
|
|
"tools.transcription_tools.transcribe_audio",
|
|
side_effect=AssertionError("must not be called"),
|
|
):
|
|
with patch(
|
|
"tools.credential_files.to_agent_visible_cache_path",
|
|
side_effect=lambda p: p,
|
|
):
|
|
result = await runner._prepare_inbound_message_text(
|
|
event=event,
|
|
source=source,
|
|
history=[],
|
|
)
|
|
|
|
assert "my_song.mp3" in result
|
|
assert "audio file attachment" in result.lower()
|
|
# Should NOT contain the voice-message transcription wrapper text
|
|
assert "voice message" not in result.lower()
|
|
# Guides the agent to transcribe/process the file itself rather than
|
|
# punting back to the user (same bug class as the PDF/DOCX note).
|
|
assert "transcri" in result.lower()
|
|
assert "ask the user what they'd like" not in result.lower()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 3. STT disabled still results in no transcription for audio file attachments
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 4. Telegram gateway: msg.audio → MessageType.AUDIO (not VOICE)
|
|
# ---------------------------------------------------------------------------
|
|
|