2f1609a86c
Self-review follow-ups on the F821 sweep: - plugins/platforms/sms/adapter.py: the optional-import block now sets AIOHTTP_AVAILABLE like the homeassistant / webhook / whatsapp_cloud adapters, and both call sites test the flag. Removes the `if not aiohttp is not None:` double negation left by inlining `_aiohttp_available()`. - tools/mcp_tool_sampling.py: `call_context` defaults to `lambda: None` so the use site is a single call instead of an Optional guard; the only None caller was a test. The `from __future__ import annotations` was noise (`Context` is a runtime import). Comment names the actual cycle (mcp_tool_server_run imports this module). - gateway/platforms/helpers.py: drop the `from __future__ import annotations` — the only MessageEvent annotations are attribute-target locals, which are never evaluated. - tests/gateway/test_telegram_audio_vs_voice.py, test_video_context_note.py: module-level `from gateway.run import GatewayRunner` like the ~100 sibling files; the TYPE_CHECKING block + `# type: ignore[name-defined]` were contradicting each other. (tests/e2e/conftest.py and test_feishu.py keep TYPE_CHECKING deliberately: they stub telegram/discord before importing, and FeishuAdapter is gated on optional lark_oapi.) Mutation check: neutralising the thunk read (`captured = None`) fails test_captured_context_is_replayed_in_consent_call; restored → 14/14 green. ty on the three touched production files vs origin/main: 0 new, 6 resolved.
127 lines
4.6 KiB
Python
127 lines
4.6 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.event import MessageEvent, MessageType
|
|
from gateway.run import GatewayRunner
|
|
from gateway.session import SessionSource
|
|
|
|
|
|
def _make_runner(stt_enabled: bool = True) -> 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", None, "gateway")
|
|
# 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)
|
|
# ---------------------------------------------------------------------------
|
|
|