hermes-agent/tests/gateway/test_lifecycle_ledger.py
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

170 lines
5.7 KiB
Python

"""Tests for gateway.lifecycle_ledger — unclean-shutdown detection (NS-608).
The ledger is a tiny sentinel state machine:
``record_startup`` claims ``state/gateway.lifecycle.json`` as
``phase=running``; every exit path calls ``mark_exited``; the next boot's
``record_startup``/``detect_unclean_exit`` reports a still-``running``
sentinel from a dead process as an unclean death (SIGKILL / OOM / VM loss)
and enriches the report with the last heartbeat's memory sample.
"""
from __future__ import annotations
import json
import os
import sys
from pathlib import Path
import pytest
from gateway.lifecycle_ledger import (
detect_unclean_exit,
get_lifecycle_sentinel_path,
mark_exited,
read_prior_exit_label,
record_startup,
sample_memory,
)
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
_DEAD_PID = 2 ** 22 + 12345 # beyond default pid_max on Linux; never alive
def _write_sentinel(home: Path, payload: dict) -> Path:
path = get_lifecycle_sentinel_path(home)
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(json.dumps(payload), encoding="utf-8")
return path
def _read_sentinel(home: Path) -> dict:
return json.loads(get_lifecycle_sentinel_path(home).read_text(encoding="utf-8"))
def _write_heartbeat(home: Path, payload: dict) -> Path:
path = home / "state" / "gateway.heartbeat"
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(json.dumps(payload), encoding="utf-8")
return path
def _exit_diag_records(home: Path) -> list[dict]:
path = home / "logs" / "gateway-exit-diag.log"
if not path.exists():
return []
return [
json.loads(line)
for line in path.read_text(encoding="utf-8").splitlines()
if line.strip()
]
# ---------------------------------------------------------------------------
# sample_memory
# ---------------------------------------------------------------------------
@pytest.mark.skipif(sys.platform != "linux", reason="/proc is Linux-only")
def test_sample_memory_has_expected_keys_on_linux() -> None:
sample = sample_memory()
assert sample.get("rss_kib", 0) > 0
assert sample.get("mem_total_kib", 0) > 0
assert "mem_available_kib" in sample
# ---------------------------------------------------------------------------
# First boot / clean lifecycle
# ---------------------------------------------------------------------------
def test_first_boot_reports_nothing_and_claims_sentinel(tmp_path: Path) -> None:
assert record_startup(home=tmp_path) is None
sentinel = _read_sentinel(tmp_path)
assert sentinel["phase"] == "running"
assert sentinel["pid"] == os.getpid()
assert "start_time" in sentinel
def test_clean_exit_then_boot_reports_nothing(tmp_path: Path) -> None:
record_startup(home=tmp_path)
mark_exited(0, reason="graceful_shutdown", home=tmp_path)
sentinel = _read_sentinel(tmp_path)
assert sentinel["phase"] == "exited"
assert sentinel["exit_code"] == 0
assert sentinel["exit_reason"] == "graceful_shutdown"
assert record_startup(home=tmp_path) is None
assert _exit_diag_records(tmp_path) == []
# ---------------------------------------------------------------------------
# Unclean-death detection
# ---------------------------------------------------------------------------
def test_running_sentinel_from_dead_pid_is_unclean(tmp_path: Path) -> None:
_write_sentinel(tmp_path, {
"phase": "running",
"pid": _DEAD_PID,
"start_time": 1000.0,
"started_at": "2026-07-11T04:30:00+00:00",
})
evidence = detect_unclean_exit(home=tmp_path)
assert evidence is not None
assert evidence["prior_pid"] == _DEAD_PID
assert evidence["prior_started_at"] == "2026-07-11T04:30:00+00:00"
def test_record_startup_persists_unclean_report_and_reclaims(tmp_path: Path) -> None:
_write_sentinel(tmp_path, {
"phase": "running",
"pid": _DEAD_PID,
"start_time": 1000.0,
"started_at": "2026-07-11T04:30:00+00:00",
})
evidence = record_startup(home=tmp_path)
assert evidence is not None
records = _exit_diag_records(tmp_path)
assert len(records) == 1
assert records[0]["tag"] == "gateway.previous_unclean_exit"
assert records[0]["prior_pid"] == _DEAD_PID
assert records[0]["pid"] == os.getpid()
# Sentinel reclaimed for the new life.
sentinel = _read_sentinel(tmp_path)
assert sentinel["phase"] == "running"
assert sentinel["pid"] == os.getpid()
# ---------------------------------------------------------------------------
# Takeover ownership guard on mark_exited
# ---------------------------------------------------------------------------
def test_mark_exited_leaves_pid_none_sentinel_alone(tmp_path: Path) -> None:
"""A sentinel with pid=None has unknown ownership — mark_exited must not
clobber it with a clean-exit claim it cannot prove is its own."""
_write_sentinel(tmp_path, {"phase": "running", "pid": None, "start_time": 2000.0})
mark_exited(0, reason="graceful_shutdown", home=tmp_path)
sentinel = _read_sentinel(tmp_path)
assert sentinel["phase"] == "running"
assert sentinel["pid"] is None
# ---------------------------------------------------------------------------
# read_prior_exit_label (container-boot annotation)
# ---------------------------------------------------------------------------
def test_prior_exit_label_survives_corrupt_sentinel(tmp_path: Path) -> None:
path = get_lifecycle_sentinel_path(tmp_path)
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text("garbage", encoding="utf-8")
assert read_prior_exit_label(tmp_path) == "unknown"