Files
hermes-agent/tests/gateway/test_destructive_slash_confirm.py
T
Teknium 39975613b1 test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
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.
2026-07-29 13:39:40 -07:00

148 lines
4.9 KiB
Python

"""Tests for the gateway's destructive-slash-confirm wrapper.
When ``approvals.destructive_slash_confirm`` is True (default), /new,
/reset, and /undo route through the slash-confirm primitive — native
yes/no buttons on Telegram/Discord/Slack, text fallback elsewhere.
When False (after "Always Approve"), the destructive action runs
immediately.
"""
from __future__ import annotations
from datetime import datetime
from types import SimpleNamespace
from unittest.mock import AsyncMock, MagicMock
import pytest
from gateway.config import GatewayConfig, Platform, PlatformConfig
from gateway.platforms.base import MessageEvent
from gateway.session import SessionEntry, SessionSource, build_session_key
def _make_source() -> SessionSource:
return SessionSource(
platform=Platform.TELEGRAM,
user_id="u1",
chat_id="c1",
user_name="tester",
chat_type="dm",
)
def _make_event(text: str) -> MessageEvent:
return MessageEvent(text=text, source=_make_source(), message_id="m1")
def _make_runner():
"""Mirror tests/gateway/test_unknown_command.py::_make_runner."""
from gateway.run import GatewayRunner
runner = object.__new__(GatewayRunner)
runner.config = GatewayConfig(
platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")}
)
adapter = MagicMock()
adapter.send = AsyncMock()
# No send_slash_confirm override -> button render returns None,
# _request_slash_confirm falls back to text path.
adapter.send_slash_confirm = AsyncMock(return_value=None)
runner.adapters = {Platform.TELEGRAM: adapter}
session_entry = SessionEntry(
session_key=build_session_key(_make_source()),
session_id="sess-1",
created_at=datetime.now(),
updated_at=datetime.now(),
platform=Platform.TELEGRAM,
chat_type="dm",
)
runner.session_store = MagicMock()
runner.session_store.get_or_create_session.return_value = session_entry
runner.session_store.load_transcript.return_value = []
runner.session_store.append_to_transcript = MagicMock()
runner.session_store.rewrite_transcript = MagicMock()
runner._running_agents = {}
runner._pending_messages = {}
import itertools as _it
runner._slash_confirm_counter = _it.count(1)
runner.hooks = SimpleNamespace(
emit=AsyncMock(),
emit_collect=AsyncMock(return_value=[]),
loaded_hooks=False,
)
runner._thread_metadata_for_source = lambda *a, **kw: None
runner._reply_anchor_for_event = lambda _e: None
return runner
@pytest.mark.asyncio
async def test_gate_on_pending_confirm_registered(monkeypatch):
"""When the gate is on, a pending slash-confirm entry is registered for
the session — the user's /approve reply will resolve it."""
from tools import slash_confirm as _slash_confirm_mod
runner = _make_runner()
runner._read_user_config = lambda: {"approvals": {"destructive_slash_confirm": True}}
session_key = build_session_key(_make_source())
runner._session_key_for_source = lambda src: session_key
_slash_confirm_mod.clear(session_key)
execute = AsyncMock(return_value="reset done")
await runner._maybe_confirm_destructive_slash(
event=_make_event("/new"),
command="new",
title="/new",
detail="Discards history.",
execute=execute,
)
pending = _slash_confirm_mod.get_pending(session_key)
assert pending is not None
assert pending["command"] == "new"
_slash_confirm_mod.clear(session_key)
@pytest.mark.asyncio
async def test_resolve_always_persists_opt_out_and_runs_execute(monkeypatch):
"""Resolving with 'always' must (a) flip the config gate to False,
(b) run execute, and (c) include a one-time opt-out note in the reply."""
from tools import slash_confirm as _slash_confirm_mod
runner = _make_runner()
runner._read_user_config = lambda: {"approvals": {"destructive_slash_confirm": True}}
session_key = build_session_key(_make_source())
runner._session_key_for_source = lambda src: session_key
_slash_confirm_mod.clear(session_key)
saved: dict = {}
def _fake_save(path, value):
saved[path] = value
return True
import cli as cli_mod
monkeypatch.setattr(cli_mod, "save_config_value", _fake_save)
execute = AsyncMock(return_value="✨ fresh")
await runner._maybe_confirm_destructive_slash(
event=_make_event("/new"),
command="new",
title="/new",
detail="Discards history.",
execute=execute,
)
pending = _slash_confirm_mod.get_pending(session_key)
assert pending is not None
resolved = await _slash_confirm_mod.resolve(
session_key, pending["confirm_id"], "always",
)
execute.assert_awaited_once()
assert saved.get("approvals.destructive_slash_confirm") is False
assert resolved is not None
assert "✨ fresh" in resolved
assert "config.yaml" in resolved