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.
89 lines
2.7 KiB
Python
89 lines
2.7 KiB
Python
"""Regression tests for clarify replies while a gateway session is busy."""
|
|
|
|
import asyncio
|
|
from unittest.mock import AsyncMock, patch
|
|
|
|
import pytest
|
|
|
|
from gateway.config import Platform, PlatformConfig
|
|
from gateway.platforms.base import (
|
|
BasePlatformAdapter,
|
|
MessageEvent,
|
|
MessageType,
|
|
SendResult,
|
|
)
|
|
from gateway.session import SessionSource, build_session_key
|
|
|
|
|
|
class _ClarifyBypassAdapter(BasePlatformAdapter):
|
|
def __init__(self):
|
|
super().__init__(PlatformConfig(enabled=True, token="test"), Platform.TELEGRAM)
|
|
|
|
async def connect(self):
|
|
return True
|
|
|
|
async def disconnect(self):
|
|
pass
|
|
|
|
async def send(self, chat_id, content, reply_to=None, metadata=None):
|
|
return SendResult(success=True, message_id="text")
|
|
|
|
async def get_chat_info(self, chat_id):
|
|
return {"id": chat_id, "type": "private"}
|
|
|
|
|
|
def _event(text="custom answer"):
|
|
return MessageEvent(
|
|
text=text,
|
|
message_type=MessageType.TEXT,
|
|
source=SessionSource(
|
|
platform=Platform.TELEGRAM,
|
|
chat_id="12345",
|
|
chat_type="private",
|
|
user_id="user1",
|
|
),
|
|
message_id="msg1",
|
|
)
|
|
|
|
|
|
def _clear_clarify_state():
|
|
from tools import clarify_gateway as cm
|
|
|
|
with cm._lock:
|
|
cm._entries.clear()
|
|
cm._session_index.clear()
|
|
cm._notify_cbs.clear()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_active_session_routes_typed_choice_clarify_reply_to_runner_not_busy_queue():
|
|
"""Typed text must resolve a pending choice clarify even while the agent is busy.
|
|
|
|
Telegram button clarifies keep the adapter session active while the agent
|
|
thread blocks on ``wait_for_response``. If the adapter only bypasses for
|
|
entries already marked ``awaiting_text``, typed replies to the visible
|
|
multi-choice prompt are handled as busy follow-ups and the clarify wait is
|
|
never resolved.
|
|
"""
|
|
_clear_clarify_state()
|
|
from tools import clarify_gateway as cm
|
|
|
|
adapter = _ClarifyBypassAdapter()
|
|
adapter._message_handler = AsyncMock(return_value="")
|
|
adapter._busy_session_handler = AsyncMock(return_value=True)
|
|
event = _event("None of those are valid options")
|
|
session_key = build_session_key(
|
|
event.source,
|
|
group_sessions_per_user=adapter.config.extra.get("group_sessions_per_user", True),
|
|
thread_sessions_per_user=adapter.config.extra.get("thread_sessions_per_user", False),
|
|
)
|
|
adapter._active_sessions[session_key] = asyncio.Event()
|
|
cm.register("clarify-1", session_key, "Pick one", ["A", "B"])
|
|
|
|
await adapter.handle_message(event)
|
|
|
|
adapter._message_handler.assert_awaited_once_with(event)
|
|
adapter._busy_session_handler.assert_not_awaited()
|
|
assert adapter._pending_messages == {}
|
|
|
|
|