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.
86 lines
2.6 KiB
Python
86 lines
2.6 KiB
Python
"""Regression tests for the Discord /model picker.
|
|
|
|
Uses the shared discord mock from tests/gateway/conftest.py (installed
|
|
at collection time via _ensure_discord_mock()). Previously this file
|
|
installed its own mock at module-import time and clobbered sys.modules,
|
|
breaking other gateway tests under pytest-xdist.
|
|
"""
|
|
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock
|
|
|
|
import pytest
|
|
|
|
from gateway.platforms.base import utf16_len
|
|
from plugins.platforms.discord.adapter import ModelPickerView
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_model_picker_clears_controls_before_running_switch_callback():
|
|
events: list[object] = []
|
|
|
|
async def on_model_selected(chat_id: str, model_id: str, provider_slug: str) -> str:
|
|
events.append(("switch", chat_id, model_id, provider_slug))
|
|
return "Model switched"
|
|
|
|
async def edit_message(**kwargs):
|
|
events.append(
|
|
(
|
|
"initial-edit",
|
|
kwargs["embed"].title,
|
|
kwargs["embed"].description,
|
|
kwargs["view"],
|
|
)
|
|
)
|
|
|
|
async def edit_original_response(**kwargs):
|
|
events.append((
|
|
"final-edit",
|
|
kwargs["embed"].title,
|
|
kwargs["embed"].description,
|
|
kwargs["view"],
|
|
))
|
|
|
|
view = ModelPickerView(
|
|
providers=[
|
|
{
|
|
"slug": "copilot",
|
|
"name": "GitHub Copilot",
|
|
"models": ["gpt-5.4"],
|
|
"total_models": 1,
|
|
"is_current": True,
|
|
}
|
|
],
|
|
current_model="gpt-5-mini",
|
|
current_provider="copilot",
|
|
session_key="session-1",
|
|
on_model_selected=on_model_selected,
|
|
allowed_user_ids={"123"}, # matches the interaction user; empty = fail-closed
|
|
)
|
|
view._selected_provider = "copilot"
|
|
|
|
interaction = SimpleNamespace(
|
|
user=SimpleNamespace(id=123),
|
|
channel_id=456,
|
|
data={"values": ["gpt-5.4"]},
|
|
response=SimpleNamespace(
|
|
defer=AsyncMock(),
|
|
send_message=AsyncMock(),
|
|
edit_message=AsyncMock(side_effect=edit_message),
|
|
),
|
|
edit_original_response=AsyncMock(side_effect=edit_original_response),
|
|
)
|
|
|
|
await view._on_model_selected(interaction)
|
|
|
|
assert events == [
|
|
("initial-edit", "⚙ Switching Model", "Switching to `gpt-5.4`...", None),
|
|
("switch", "456", "gpt-5.4", "copilot"),
|
|
("final-edit", "⚙ Model Switched", "Model switched", None),
|
|
]
|
|
interaction.response.edit_message.assert_awaited_once()
|
|
interaction.response.defer.assert_not_called()
|
|
interaction.edit_original_response.assert_awaited_once()
|
|
|
|
|