mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +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.
79 lines
2.6 KiB
Python
79 lines
2.6 KiB
Python
"""Tests verifying interrupt key consistency between adapter and gateway.
|
|
|
|
Regression test for a bug where monitor_for_interrupt() in _run_agent used
|
|
source.chat_id to query the adapter, but the adapter stores interrupts under
|
|
the full session key (build_session_key output). This mismatch meant
|
|
interrupts were never detected, causing subagents to ignore new messages.
|
|
"""
|
|
|
|
import asyncio
|
|
|
|
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 StubAdapter(BasePlatformAdapter):
|
|
"""Minimal adapter for interrupt tests."""
|
|
|
|
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, reply_to=None, metadata=None):
|
|
return SendResult(success=True, message_id="1")
|
|
|
|
async def send_typing(self, chat_id, metadata=None):
|
|
pass
|
|
|
|
async def get_chat_info(self, chat_id):
|
|
return {"id": chat_id}
|
|
|
|
|
|
def _source(chat_id="123456", chat_type="dm", thread_id=None):
|
|
return SessionSource(
|
|
platform=Platform.TELEGRAM,
|
|
chat_id=chat_id,
|
|
chat_type=chat_type,
|
|
thread_id=thread_id,
|
|
)
|
|
|
|
|
|
class TestInterruptKeyConsistency:
|
|
"""Ensure adapter interrupt methods are queried with session_key, not chat_id."""
|
|
|
|
|
|
def test_session_key_differs_from_chat_id_for_group(self):
|
|
"""Session key for a group chat includes prefix, unlike raw chat_id."""
|
|
source = _source("-1001234", "group")
|
|
session_key = build_session_key(source)
|
|
assert session_key != source.chat_id
|
|
assert "agent:main:" in session_key
|
|
assert source.chat_id in session_key
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_has_pending_interrupt_requires_session_key(self):
|
|
"""has_pending_interrupt returns True only when queried with session_key."""
|
|
adapter = StubAdapter()
|
|
source = _source("123456", "dm")
|
|
session_key = build_session_key(source)
|
|
|
|
# Simulate adapter storing interrupt under session_key
|
|
interrupt_event = asyncio.Event()
|
|
adapter._active_sessions[session_key] = interrupt_event
|
|
interrupt_event.set()
|
|
|
|
# Using session_key → found
|
|
assert adapter.has_pending_interrupt(session_key) is True
|
|
|
|
# Using chat_id → NOT found (this was the bug)
|
|
assert adapter.has_pending_interrupt(source.chat_id) is False
|
|
|
|
|