hermes-agent/tests/gateway/test_tts_media_routing.py
teknium1 43b8ba4181 fix(telegram): preserve Bot API update queue on watcher reconnect
After a prolonged outage the in-process network-error ladder escalates to
fatal and GatewayRunner._platform_reconnect_watcher rebuilds a fresh adapter
that reconnects through the bootstrap path. That path called
start_polling(drop_pending_updates=True), discarding every update Telegram
queued during the outage — all messages sent while the bot was down were
silently lost. The in-process ladder and 409-conflict handler already passed
drop_pending_updates=False; only bootstrap did not distinguish a cold first
boot from a reconnect.

Thread an is_reconnect signal from the watcher through
_connect_adapter_with_timeout into adapter.connect(). The base
BasePlatformAdapter.connect() gains a keyword-only is_reconnect=False so every
adapter inherits a tolerant signature (no per-platform breakage when the
runner forwards the kwarg). Telegram translates is_reconnect into
drop_pending_updates=not is_reconnect on both the polling and webhook bootstrap
calls. Cold boot still drops the stale queue; a watcher reconnect preserves it.

Fixes #46621.

Co-authored-by: annguyenNous <annguyen@nousresearch.com>
Co-authored-by: kyssta-exe <kyssta-exe@users.noreply.github.com>
Co-authored-by: Kewe63 <Kewe63@users.noreply.github.com>
2026-06-25 21:29:57 -07:00

263 lines
10 KiB
Python

"""
Tests for cross-platform audio/voice media routing.
These tests pin the expected delivery path for audio media files across
Telegram (where Bot-API sendAudio only accepts MP3/M4A and .ogg/.opus
only renders as a voice bubble when explicitly flagged) and via
``GatewayRunner._deliver_media_from_response``.
"""
from types import SimpleNamespace
from unittest.mock import AsyncMock
import pytest
from gateway.config import Platform, PlatformConfig
from gateway.platforms.base import BasePlatformAdapter, MessageEvent, MessageType, SendResult
from gateway.run import GatewayRunner
from gateway.session import SessionSource, build_session_key
class _MediaRoutingAdapter(BasePlatformAdapter):
def __init__(self):
super().__init__(PlatformConfig(enabled=True, token="test"), Platform.TELEGRAM)
async def connect(self, *, is_reconnect: bool = False):
return True
async def disconnect(self):
pass
async def send(self, chat_id, content=None, **kwargs):
return SendResult(success=True, message_id="text")
async def get_chat_info(self, chat_id):
return {"id": chat_id, "type": "dm"}
def _event(thread_id=None):
source = SessionSource(
platform=Platform.TELEGRAM,
chat_id="chat-1",
chat_type="dm",
thread_id=thread_id,
)
return MessageEvent(
text="make speech",
message_type=MessageType.TEXT,
source=source,
message_id="msg-1",
)
def _allowed_media_path(tmp_path, monkeypatch, name):
root = tmp_path / "media-cache"
media_file = root / name
media_file.parent.mkdir(parents=True, exist_ok=True)
media_file.write_bytes(b"media")
monkeypatch.setattr(
"gateway.platforms.base.MEDIA_DELIVERY_SAFE_ROOTS",
(root,),
)
return media_file.resolve()
@pytest.mark.asyncio
async def test_base_adapter_routes_telegram_flac_media_tag_to_document_sender(tmp_path, monkeypatch):
adapter = _MediaRoutingAdapter()
event = _event()
media_file = _allowed_media_path(tmp_path, monkeypatch, "speech.flac")
adapter._message_handler = AsyncMock(return_value=f"MEDIA:{media_file}")
adapter.send_voice = AsyncMock(return_value=SendResult(success=True, message_id="voice"))
adapter.send_document = AsyncMock(return_value=SendResult(success=True, message_id="doc"))
await adapter._process_message_background(event, build_session_key(event.source))
adapter.send_document.assert_awaited_once_with(
chat_id="chat-1",
file_path=str(media_file),
metadata={"notify": True},
)
adapter.send_voice.assert_not_awaited()
@pytest.mark.asyncio
async def test_base_adapter_routes_non_voice_telegram_ogg_media_tag_to_document_sender(tmp_path, monkeypatch):
adapter = _MediaRoutingAdapter()
event = _event()
media_file = _allowed_media_path(tmp_path, monkeypatch, "speech.ogg")
adapter._message_handler = AsyncMock(return_value=f"MEDIA:{media_file}")
adapter.send_voice = AsyncMock(return_value=SendResult(success=True, message_id="voice"))
adapter.send_document = AsyncMock(return_value=SendResult(success=True, message_id="doc"))
await adapter._process_message_background(event, build_session_key(event.source))
adapter.send_document.assert_awaited_once_with(
chat_id="chat-1",
file_path=str(media_file),
metadata={"notify": True},
)
adapter.send_voice.assert_not_awaited()
@pytest.mark.asyncio
async def test_base_adapter_routes_voice_tagged_telegram_ogg_media_tag_to_voice_sender(tmp_path, monkeypatch):
adapter = _MediaRoutingAdapter()
event = _event()
media_file = _allowed_media_path(tmp_path, monkeypatch, "speech.ogg")
adapter._message_handler = AsyncMock(
return_value=f"[[audio_as_voice]]\nMEDIA:{media_file}"
)
adapter.send_voice = AsyncMock(return_value=SendResult(success=True, message_id="voice"))
adapter.send_document = AsyncMock(return_value=SendResult(success=True, message_id="doc"))
await adapter._process_message_background(event, build_session_key(event.source))
adapter.send_voice.assert_awaited_once_with(
chat_id="chat-1",
audio_path=str(media_file),
metadata={"notify": True},
)
adapter.send_document.assert_not_awaited()
def _fake_runner(thread_meta):
"""Build a fake GatewayRunner-like object with the helper methods needed by
_deliver_media_from_response."""
runner = SimpleNamespace(
_thread_metadata_for_source=lambda source, anchor=None: thread_meta,
_reply_anchor_for_event=lambda event: None,
)
return runner
@pytest.mark.asyncio
async def test_streaming_delivery_routes_telegram_flac_media_tag_to_document_sender(tmp_path, monkeypatch):
event = _event(thread_id="topic-1")
media_file = _allowed_media_path(tmp_path, monkeypatch, "speech.flac")
adapter = SimpleNamespace(
name="test",
extract_media=BasePlatformAdapter.extract_media,
extract_images=BasePlatformAdapter.extract_images,
extract_local_files=BasePlatformAdapter.extract_local_files,
send_voice=AsyncMock(return_value=SendResult(success=True, message_id="voice")),
send_document=AsyncMock(return_value=SendResult(success=True, message_id="doc")),
send_image_file=AsyncMock(return_value=SendResult(success=True, message_id="image")),
send_video=AsyncMock(return_value=SendResult(success=True, message_id="video")),
)
await GatewayRunner._deliver_media_from_response(
_fake_runner({"thread_id": "topic-1"}),
f"MEDIA:{media_file}",
event,
adapter,
)
adapter.send_document.assert_awaited_once_with(
chat_id="chat-1",
file_path=str(media_file),
metadata={"thread_id": "topic-1"},
)
adapter.send_voice.assert_not_awaited()
@pytest.mark.asyncio
async def test_streaming_delivery_routes_non_voice_telegram_ogg_media_tag_to_document_sender(tmp_path, monkeypatch):
event = _event(thread_id="topic-1")
media_file = _allowed_media_path(tmp_path, monkeypatch, "speech.ogg")
adapter = SimpleNamespace(
name="test",
extract_media=BasePlatformAdapter.extract_media,
extract_images=BasePlatformAdapter.extract_images,
extract_local_files=BasePlatformAdapter.extract_local_files,
send_voice=AsyncMock(return_value=SendResult(success=True, message_id="voice")),
send_document=AsyncMock(return_value=SendResult(success=True, message_id="doc")),
send_image_file=AsyncMock(return_value=SendResult(success=True, message_id="image")),
send_video=AsyncMock(return_value=SendResult(success=True, message_id="video")),
)
await GatewayRunner._deliver_media_from_response(
_fake_runner({"thread_id": "topic-1"}),
f"MEDIA:{media_file}",
event,
adapter,
)
adapter.send_document.assert_awaited_once_with(
chat_id="chat-1",
file_path=str(media_file),
metadata={"thread_id": "topic-1"},
)
adapter.send_voice.assert_not_awaited()
@pytest.mark.asyncio
async def test_streaming_delivery_routes_telegram_mp3_media_tag_to_voice_sender(tmp_path, monkeypatch):
"""MP3 audio on Telegram must go through send_voice (which routes to
sendAudio internally); Telegram accepts MP3 for the audio player."""
event = _event(thread_id="topic-1")
media_file = _allowed_media_path(tmp_path, monkeypatch, "speech.mp3")
adapter = SimpleNamespace(
name="test",
extract_media=BasePlatformAdapter.extract_media,
extract_images=BasePlatformAdapter.extract_images,
extract_local_files=BasePlatformAdapter.extract_local_files,
send_voice=AsyncMock(return_value=SendResult(success=True, message_id="voice")),
send_document=AsyncMock(return_value=SendResult(success=True, message_id="doc")),
send_image_file=AsyncMock(return_value=SendResult(success=True, message_id="image")),
send_video=AsyncMock(return_value=SendResult(success=True, message_id="video")),
)
await GatewayRunner._deliver_media_from_response(
_fake_runner({"thread_id": "topic-1"}),
f"MEDIA:{media_file}",
event,
adapter,
)
adapter.send_voice.assert_awaited_once_with(
chat_id="chat-1",
audio_path=str(media_file),
metadata={"thread_id": "topic-1"},
)
adapter.send_document.assert_not_awaited()
@pytest.mark.asyncio
async def test_streaming_delivery_blocks_media_path_outside_allowed_roots(tmp_path, monkeypatch):
event = _event(thread_id="topic-1")
allowed_root = tmp_path / "media-cache"
allowed_root.mkdir()
secret = tmp_path / "outside.pdf"
secret.write_bytes(b"%PDF secret")
monkeypatch.setattr(
"gateway.platforms.base.MEDIA_DELIVERY_SAFE_ROOTS",
(allowed_root,),
)
# This test exercises the strict-allowlist path; force strict mode on
# and disable recency trust so the freshly-written tmp_path file is not
# auto-accepted by the trust window. (Recency trust is covered separately
# in test_platform_base.py. The public default flipped to non-strict in
# 2026-05; this test pins strict on explicitly.)
monkeypatch.setenv("HERMES_MEDIA_DELIVERY_STRICT", "1")
monkeypatch.setenv("HERMES_MEDIA_TRUST_RECENT_FILES", "0")
adapter = SimpleNamespace(
name="test",
extract_media=BasePlatformAdapter.extract_media,
extract_images=BasePlatformAdapter.extract_images,
extract_local_files=BasePlatformAdapter.extract_local_files,
send_voice=AsyncMock(return_value=SendResult(success=True, message_id="voice")),
send_document=AsyncMock(return_value=SendResult(success=True, message_id="doc")),
send_image_file=AsyncMock(return_value=SendResult(success=True, message_id="image")),
send_video=AsyncMock(return_value=SendResult(success=True, message_id="video")),
)
await GatewayRunner._deliver_media_from_response(
_fake_runner({"thread_id": "topic-1"}),
f"MEDIA:{secret}",
event,
adapter,
)
adapter.send_document.assert_not_awaited()
adapter.send_voice.assert_not_awaited()