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.
104 lines
3.6 KiB
Python
104 lines
3.6 KiB
Python
"""Tests for ``BasePlatformAdapter.register_post_delivery_callback`` chaining.
|
|
|
|
When two features want to run after the final response lands on the same
|
|
session (e.g. background-review release + temporary-progress cleanup), the
|
|
registration API chains them rather than clobbering. Per-callback
|
|
exceptions are swallowed so one bad callback can't sabotage the others.
|
|
Stale-generation registrations are rejected.
|
|
|
|
The chained wrapper is ``async`` so it transparently supports sync or async
|
|
callbacks — the outer invoker in ``_handle_message`` awaits awaitable
|
|
callbacks, and a sync wrapper would silently drop coroutine results from
|
|
async callbacks chained behind it.
|
|
"""
|
|
import asyncio
|
|
import inspect
|
|
|
|
import pytest
|
|
|
|
from gateway.config import Platform, PlatformConfig
|
|
from gateway.platforms.base import BasePlatformAdapter, SendResult
|
|
|
|
|
|
class _MinAdapter(BasePlatformAdapter):
|
|
async def connect(self, *, is_reconnect: bool = False) -> bool:
|
|
return True
|
|
|
|
async def disconnect(self) -> None:
|
|
return None
|
|
|
|
async def send(self, chat_id, content, reply_to=None, metadata=None) -> SendResult:
|
|
return SendResult(success=True, message_id="1")
|
|
|
|
async def get_chat_info(self, chat_id):
|
|
return {"id": chat_id}
|
|
|
|
|
|
@pytest.fixture
|
|
def adapter():
|
|
return _MinAdapter(PlatformConfig(enabled=True), Platform.TELEGRAM)
|
|
|
|
|
|
def _invoke(cb):
|
|
"""Invoke a popped callback, awaiting if it returns a coroutine.
|
|
|
|
Single-registration callbacks are returned as the raw user callable
|
|
(sync). Chained callbacks (two or more registrations on the same
|
|
session) are wrapped in an async helper. Tests use this helper so
|
|
they don't have to care which case they're exercising.
|
|
"""
|
|
result = cb()
|
|
if inspect.isawaitable(result):
|
|
asyncio.run(result)
|
|
|
|
|
|
class TestPostDeliveryCallbackChaining:
|
|
def test_single_callback_fires(self, adapter):
|
|
fired = []
|
|
adapter.register_post_delivery_callback("s", lambda: fired.append("A"))
|
|
cb = adapter.pop_post_delivery_callback("s")
|
|
_invoke(cb)
|
|
assert fired == ["A"]
|
|
|
|
def test_two_callbacks_chain_in_order(self, adapter):
|
|
fired = []
|
|
adapter.register_post_delivery_callback("s", lambda: fired.append("A"))
|
|
adapter.register_post_delivery_callback("s", lambda: fired.append("B"))
|
|
cb = adapter.pop_post_delivery_callback("s")
|
|
_invoke(cb)
|
|
assert fired == ["A", "B"]
|
|
|
|
def test_three_callbacks_chain_in_order(self, adapter):
|
|
"""Chain composes over an already-chained callback."""
|
|
fired = []
|
|
for label in ("A", "B", "C"):
|
|
adapter.register_post_delivery_callback(
|
|
"s", lambda x=label: fired.append(x)
|
|
)
|
|
cb = adapter.pop_post_delivery_callback("s")
|
|
_invoke(cb)
|
|
assert fired == ["A", "B", "C"]
|
|
|
|
|
|
class TestPostDeliveryCallbackAsyncChaining:
|
|
"""When an async callback is chained, the wrapper must await it.
|
|
|
|
Regression test for a bug where the sync ``_chained`` wrapper called
|
|
async callbacks without awaiting, silently dropping the returned
|
|
coroutine. This broke ``/goal`` continuations (Discord etc.) where
|
|
the continuation injection is an async ``_deliver()`` coroutine.
|
|
"""
|
|
|
|
def test_async_callback_in_chain_is_awaited(self, adapter):
|
|
fired = []
|
|
|
|
async def async_cb():
|
|
await asyncio.sleep(0)
|
|
fired.append("async")
|
|
|
|
adapter.register_post_delivery_callback("s", lambda: fired.append("sync"))
|
|
adapter.register_post_delivery_callback("s", async_cb)
|
|
cb = adapter.pop_post_delivery_callback("s")
|
|
_invoke(cb)
|
|
assert fired == ["sync", "async"]
|
|
|