bvandeusenandClaude Opus 5.5
c7ff5bc556
#5756 "The agent says when its host rebooted and when it lost contact, so downtime is recorded as what it was". Agent 1.14.0 posts events with the next post that gets through: started (with the host's boot time), stopping (on SIGTERM, with whether systemd says the host is going down) and lost_contact (from its first unanswered post to the one carrying it). Steward keeps them as the host's downtime (host_downtime): reboot, agent_stop, unclean (a boot after the agent was last heard that nobody announced) or lost_contact. Retried posts apply once. An announced stop explains the silence for reboot_grace_seconds (Settings -> Plugins -> host_agent, 10 minutes): seconds_since_seen reads 0 until then, and the host's other rules go quiet with it (agents_away beside #5721's registry). Past the grace, agent offline fires. The host's Agent card lists the last 7 days of downtime. Rows are pruned at data.retention_days. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
58 lines
2.4 KiB
Python
58 lines
2.4 KiB
Python
"""The agent says what happened to its host (#5756): when it started and the
|
|
host booted, when it stops and whether the host is going down with it, and how
|
|
long it couldn't reach Steward."""
|
|
import subprocess
|
|
from datetime import datetime
|
|
from types import SimpleNamespace
|
|
from unittest.mock import patch
|
|
|
|
from plugins.host_agent import agent as a
|
|
|
|
|
|
def test_events_ride_the_payload_only_when_there_are_some():
|
|
assert "events" not in a.build_payload([], "h", {})
|
|
assert a.build_payload([], "h", {}, events=[{"kind": "started"}])["events"] == [{"kind": "started"}]
|
|
|
|
|
|
def test_started_says_when_the_host_booted():
|
|
with patch.object(a, "_read_file", return_value="3600.5 100.0\n"), \
|
|
patch.object(a.time, "time", return_value=1_800_000_000.0):
|
|
event = a.started_event()
|
|
assert event["kind"] == "started"
|
|
assert datetime.fromisoformat(event["boot_at"]).timestamp() == 1_800_000_000.0 - 3600.5
|
|
|
|
|
|
def test_started_without_uptime_still_says_it_started():
|
|
with patch.object(a, "_read_file", side_effect=OSError):
|
|
event = a.started_event()
|
|
assert event["kind"] == "started" and "boot_at" not in event
|
|
|
|
|
|
def test_the_host_is_going_down_when_systemd_says_stopping():
|
|
def run(out):
|
|
return patch.object(a.subprocess, "run", return_value=SimpleNamespace(stdout=out))
|
|
with run("stopping\n"):
|
|
assert a.host_shutting_down() is True
|
|
with run("running\n"):
|
|
assert a.host_shutting_down() is False
|
|
with run("degraded\n"):
|
|
assert a.host_shutting_down() is False
|
|
with patch.object(a.subprocess, "run", side_effect=FileNotFoundError):
|
|
assert a.host_shutting_down() is None
|
|
with patch.object(a.subprocess, "run", side_effect=subprocess.TimeoutExpired("systemctl", 3)):
|
|
assert a.host_shutting_down() is None
|
|
|
|
|
|
def test_stopping_says_whether_the_host_goes_with_it():
|
|
with patch.object(a, "host_shutting_down", return_value=True):
|
|
event = a.stopping_event()
|
|
assert event["kind"] == "stopping" and event["host_shutdown"] is True and event["at"]
|
|
|
|
|
|
def test_lost_contact_is_no_answer_or_a_proxy_s_5xx_not_steward_refusing():
|
|
assert a.lost_contact(None) and a.lost_contact(502) and a.lost_contact(503)
|
|
assert not a.lost_contact(400) and not a.lost_contact(401)
|
|
event = a.lost_contact_event("2026-10-14T10:00:00+00:00")
|
|
assert event["kind"] == "lost_contact" and event["from"] == "2026-10-14T10:00:00+00:00"
|
|
assert event["to"] > event["from"]
|