Teknium
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.
83 lines
2.4 KiB
Python
83 lines
2.4 KiB
Python
from __future__ import annotations
|
|
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
|
|
from gateway.config import Platform
|
|
from gateway.platforms.base import MessageEvent, MessageType
|
|
from gateway.run import GatewayRunner
|
|
from gateway.session import SessionSource
|
|
from hermes_cli.goals import CONTINUATION_PROMPT_TEMPLATE
|
|
|
|
|
|
class FakeAdapter:
|
|
def __init__(self):
|
|
self.calls = []
|
|
self.callbacks = {}
|
|
self._active_sessions = {}
|
|
|
|
async def send(self, chat_id, content, reply_to=None, metadata=None):
|
|
self.calls.append(
|
|
{
|
|
"chat_id": chat_id,
|
|
"content": content,
|
|
"reply_to": reply_to,
|
|
"metadata": metadata,
|
|
}
|
|
)
|
|
return SimpleNamespace(success=True)
|
|
|
|
def register_post_delivery_callback(self, session_key, callback, *, generation=None):
|
|
self.callbacks[session_key] = (generation, callback)
|
|
|
|
|
|
def _goal_continuation_event(source, goal="finish the task"):
|
|
return MessageEvent(
|
|
text=CONTINUATION_PROMPT_TEMPLATE.format(goal=goal),
|
|
message_type=MessageType.TEXT,
|
|
source=source,
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_goal_status_notice_defers_until_post_delivery_callback():
|
|
"""Regression: goal status must appear after the agent's visible reply.
|
|
|
|
_post_turn_goal_continuation runs before BasePlatformAdapter sends the
|
|
returned final response. It should therefore register a post-delivery
|
|
callback, not send the judge status immediately.
|
|
"""
|
|
runner = GatewayRunner.__new__(GatewayRunner)
|
|
adapter = FakeAdapter()
|
|
runner.adapters = {Platform.DISCORD: adapter}
|
|
runner.config = SimpleNamespace(group_sessions_per_user=True, thread_sessions_per_user=False)
|
|
|
|
source = SessionSource(
|
|
platform=Platform.DISCORD,
|
|
chat_id="parent-channel",
|
|
thread_id="thread-123",
|
|
user_id="user-1",
|
|
)
|
|
|
|
await runner._defer_goal_status_notice_after_delivery(source, "✓ Goal achieved: done")
|
|
|
|
assert adapter.calls == []
|
|
assert len(adapter.callbacks) == 1
|
|
|
|
_, callback = next(iter(adapter.callbacks.values()))
|
|
result = callback()
|
|
if hasattr(result, "__await__"):
|
|
await result
|
|
|
|
assert adapter.calls == [
|
|
{
|
|
"chat_id": "parent-channel",
|
|
"content": "✓ Goal achieved: done",
|
|
"reply_to": None,
|
|
"metadata": {"thread_id": "thread-123"},
|
|
}
|
|
]
|
|
|
|
|