hermes-agent/tests/gateway/test_external_drain_control.py
Teknium 6b81590c55
test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions
Systematic prune per AGENTS.md test policy, one pass over every major
test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli,
cron, tui_gateway, honcho/openviking, root-level):

- DELETE: source-reading tests (read_text/getsource on prod files),
  change-detector tests (exact catalog counts, model-name snapshots,
  config version literals), mock-echo tests (assert a mock returns what
  it was told), assertion-free/trivial tests, near-duplicate
  parametrizations (boundaries + one representative kept), async/sync
  twin duplicates, cosmetic within-file variations.
- KEEP (mandatory): security/redaction/approval guards, message-role
  alternation invariants, prompt-caching/deterministic-call-id
  invariants, issue-number regression tests (deduped), E2E tests.
- 6 test files deleted outright (script-style/no-assert or fully
  redundant); conftest.py, fakes/, fixtures/ untouched.
- tests/acp/conftest.py added: autouse fixture stubs the live
  models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server
  tests performed on every session create — test_server.py 147s → 3.4s,
  and the tests are now genuinely hermetic.
- Sleep-based slowness shrunk where safe (codex_ttfb_watchdog,
  compression_concurrent_fork, etc.); no wall-clock assertion tightened.

Verification: full hermetic suite via scripts/run_tests.sh —
2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall
(baseline: 583s wall, 13,564s subprocess CPU).
2026-07-29 13:10:23 -07:00

213 lines
7.9 KiB
Python

"""Tests for the external drain-control marker contract + gateway state machine.
Task 2.2/2.3. Two layers:
* drain_control.py — the presence-based marker contract (write/clear/read,
HERMES_HOME-scoped, never-raises).
* GatewayRunner enter/exit/watcher + the new-turn accept gate — the
reversible state machine driven by the marker.
Mocked tests are necessary-not-sufficient here (the HARD live-validation gate,
Q-B, exercises a real `hermes gateway run`); these lock the unit contract.
"""
from __future__ import annotations
import asyncio
from pathlib import Path
from unittest.mock import MagicMock
import pytest
import gateway.drain_control as dc
from gateway.run import GatewayRunner
from gateway.config import Platform
from gateway.platforms.base import MessageEvent, MessageType
from tests.gateway.restart_test_helpers import make_restart_runner, make_restart_source
# ---------------------------------------------------------------------------
# Marker contract (drain_control.py)
# ---------------------------------------------------------------------------
@pytest.fixture
def home(tmp_path, monkeypatch):
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
return tmp_path
class TestMarkerContract:
def test_absent_by_default(self, home):
assert dc.drain_requested() is False
assert dc.read_drain_request() is None
def test_write_then_present(self, home):
payload = dc.write_drain_request(principal="nas")
assert dc.drain_requested() is True
assert payload["action"] == "drain"
assert payload["principal"] == "nas"
body = dc.read_drain_request()
assert body is not None and body["principal"] == "nas"
class TestSuppressNotification:
"""The generic suppress_notification flag on the drain marker.
Gates ONLY the gateway's home-channel shutdown broadcast (NAS auto-update
sets it true). Default-false so legacy/operator drains behave as before.
The reader reuses the NS-570 epoch-staleness check so an orphaned marker
can never silence a fresh gateway.
"""
def test_default_false(self, home):
payload = dc.write_drain_request(principal="nas")
assert payload["suppress_notification"] is False
assert dc.drain_notification_suppressed() is False
def test_flag_round_trips_true(self, home):
payload = dc.write_drain_request(principal="nas", suppress_notification=True)
assert payload["suppress_notification"] is True
body = dc.read_drain_request()
assert body is not None and body["suppress_notification"] is True
assert dc.drain_notification_suppressed() is True
# ---------------------------------------------------------------------------
# Instantiation-epoch staleness (NS-570: orphaned marker on durable volume)
# ---------------------------------------------------------------------------
class TestInstantiationEpoch:
def test_write_stamps_current_epoch(self, home):
payload = dc.write_drain_request(principal="nas")
assert payload["epoch"] == dc.current_instantiation_epoch()
body = dc.read_drain_request()
assert body is not None and body["epoch"] == dc.current_instantiation_epoch()
def test_marker_from_prior_instantiation_reads_as_absent(self, home, monkeypatch):
# THE NS-570 REGRESSION. A begin-drain marker written by a PREVIOUS
# container/VM instantiation survives on the durable HERMES_HOME volume
# across a machine restart. The freshly-restarted gateway (new epoch)
# must treat it as absent, NOT re-engage drain.
monkeypatch.setattr(dc, "current_instantiation_epoch", lambda: "epoch-OLD")
dc.write_drain_request(principal="nas") # stamps "epoch-OLD"
assert dc.drain_requested() is True # same epoch → active
# Simulate the restart: a brand-new instantiation epoch.
monkeypatch.setattr(dc, "current_instantiation_epoch", lambda: "epoch-NEW")
# The marker file is still physically present on the volume…
assert dc.drain_request_path().exists() is True
# …but it is ignored because its epoch belongs to a prior instantiation.
assert dc.drain_requested() is False
def test_current_epoch_empty_when_proc_unreadable(self, monkeypatch):
# When neither /proc identity source is readable, the epoch is "" so
# the staleness check is disabled rather than crashing.
from pathlib import Path as _P
orig_read_text = _P.read_text
def _boom(self, *a, **k):
if str(self).startswith("/proc/"):
raise OSError("no /proc")
return orig_read_text(self, *a, **k)
dc.current_instantiation_epoch.cache_clear()
monkeypatch.setattr(_P, "read_text", _boom)
try:
assert dc.current_instantiation_epoch() == ""
finally:
dc.current_instantiation_epoch.cache_clear()
# ---------------------------------------------------------------------------
# Gateway state machine (enter / exit / idempotency)
# ---------------------------------------------------------------------------
def _drain_runner():
runner, adapter = make_restart_runner()
runner._external_drain_active = False
# Bind the real methods under test.
runner._enter_external_drain = GatewayRunner._enter_external_drain.__get__(
runner, GatewayRunner
)
runner._exit_external_drain = GatewayRunner._exit_external_drain.__get__(
runner, GatewayRunner
)
return runner, adapter
class TestDrainStateMachine:
def test_enter_idempotent(self):
runner, _ = _drain_runner()
runner._enter_external_drain()
runner._update_runtime_status.reset_mock()
runner._enter_external_drain() # second call — no-op
runner._update_runtime_status.assert_not_called()
def test_exit_during_shutdown_does_not_revert_to_running(self):
runner, _ = _drain_runner()
runner._enter_external_drain()
runner._update_runtime_status.reset_mock()
# A shutdown drain is now in progress — exit must NOT resurrect running.
runner._draining = True
runner._exit_external_drain()
assert runner._external_drain_active is False
runner._update_runtime_status.assert_not_called()
# ---------------------------------------------------------------------------
# Watcher reconciliation
# ---------------------------------------------------------------------------
class TestDrainWatcher:
@pytest.mark.asyncio
async def test_watcher_enters_then_exits_with_marker(self, home):
runner, _ = _drain_runner()
runner._drain_control_watcher = GatewayRunner._drain_control_watcher.__get__(
runner, GatewayRunner
)
# Drive a few ticks manually rather than spinning the loop.
dc.write_drain_request()
task = asyncio.create_task(runner._drain_control_watcher(interval=0.02))
await asyncio.sleep(0.06)
assert runner._external_drain_active is True
dc.clear_drain_request()
await asyncio.sleep(0.06)
assert runner._external_drain_active is False
runner._running = False
await asyncio.sleep(0.04)
task.cancel()
try:
await task
except asyncio.CancelledError:
pass
# ---------------------------------------------------------------------------
# New-turn accept gate
# ---------------------------------------------------------------------------
class TestNewTurnGate:
@pytest.mark.asyncio
async def test_new_turn_refused_during_external_drain(self):
runner, _ = _drain_runner()
runner._external_drain_active = True
event = MessageEvent(
text="hello",
message_type=MessageType.TEXT,
source=make_restart_source(),
message_id="m1",
)
result = await runner._handle_message(event)
assert result is not None
assert "draining" in result.lower()