mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
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.
98 lines
3.3 KiB
Python
98 lines
3.3 KiB
Python
"""Regression test for issue #27970 Bug 2.
|
|
|
|
The auto Telegram voice reply (``GatewayRunner._send_voice_reply``) is the
|
|
final response of a turn. It must mark its metadata as ``notify=True`` so
|
|
adapters that gate push notifications (Telegram's "important" mode) deliver
|
|
it as a normal push instead of a silent message — mirroring the existing
|
|
final-text path in ``gateway/platforms/base.py``.
|
|
"""
|
|
|
|
import json
|
|
import os
|
|
import tempfile
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock
|
|
|
|
import pytest
|
|
|
|
from gateway.config import Platform
|
|
from gateway.platforms.base import MessageEvent, MessageType
|
|
from gateway.run import GatewayRunner
|
|
from gateway.session import SessionSource
|
|
|
|
|
|
def _make_event(thread_id=None):
|
|
source = SessionSource(
|
|
platform=Platform.TELEGRAM,
|
|
chat_id="208214988",
|
|
user_id="208214988",
|
|
chat_type="dm",
|
|
thread_id=thread_id,
|
|
)
|
|
return MessageEvent(
|
|
text="hi",
|
|
message_type=MessageType.TEXT,
|
|
source=source,
|
|
message_id="m1",
|
|
)
|
|
|
|
|
|
def _runner_with_adapter(send_voice_mock):
|
|
runner = object.__new__(GatewayRunner)
|
|
adapter = SimpleNamespace(
|
|
send_voice=send_voice_mock,
|
|
is_in_voice_channel=lambda *_a, **_k: False,
|
|
)
|
|
runner.adapters = {Platform.TELEGRAM: adapter}
|
|
return runner
|
|
|
|
|
|
def _fake_tts_call(monkeypatch, audio_bytes=b"\x00" * 32):
|
|
"""Patch the TTS tool so it writes a real file at the requested path."""
|
|
|
|
def _fake_text_to_speech_tool(*, text, output_path, **_kwargs):
|
|
os.makedirs(os.path.dirname(output_path), exist_ok=True)
|
|
with open(output_path, "wb") as fh:
|
|
fh.write(audio_bytes)
|
|
return json.dumps({"success": True, "file_path": output_path})
|
|
|
|
monkeypatch.setattr(
|
|
"tools.tts_tool.text_to_speech_tool",
|
|
_fake_text_to_speech_tool,
|
|
)
|
|
monkeypatch.setattr(
|
|
"tools.tts_tool._strip_markdown_for_tts",
|
|
lambda text: text,
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_voice_reply_marks_existing_thread_metadata_without_mutation(monkeypatch, tmp_path):
|
|
"""When thread metadata exists (Telegram DM-topic), notify=True is added without mutating the source dict."""
|
|
monkeypatch.setattr(tempfile, "gettempdir", lambda: str(tmp_path))
|
|
_fake_tts_call(monkeypatch)
|
|
|
|
send_voice = AsyncMock()
|
|
runner = _runner_with_adapter(send_voice)
|
|
# Use a DM topic source so _thread_metadata_for_source returns a non-None dict.
|
|
event = _make_event(thread_id="17585")
|
|
source_meta_snapshot = runner._thread_metadata_for_source(
|
|
event.source, runner._reply_anchor_for_event(event)
|
|
)
|
|
assert source_meta_snapshot is not None
|
|
snapshot_copy = dict(source_meta_snapshot)
|
|
|
|
await runner._send_voice_reply(event, "Hello there.")
|
|
|
|
send_voice.assert_awaited_once()
|
|
kwargs = send_voice.await_args.kwargs
|
|
assert kwargs["metadata"].get("notify") is True
|
|
# All pre-existing thread keys are preserved.
|
|
for k, v in snapshot_copy.items():
|
|
assert kwargs["metadata"].get(k) == v
|
|
# The freshly-computed source-side metadata must NOT have been mutated
|
|
# (would otherwise leak notify=True into the typing-indicator state).
|
|
fresh = runner._thread_metadata_for_source(
|
|
event.source, runner._reply_anchor_for_event(event)
|
|
)
|
|
assert "notify" not in fresh
|