feat(host_agent): Steward hands a host a maintenance job and follows it through the reboot (#5767)

#5767 "Steward hands a host a maintenance job and follows it to the end,
through its own restarts", milestone 514.

A host_maintenance_jobs row per job: queued → updating → [draining →]
rebooting → [undraining →] done, or failed / timed_out. Steward's answer to
an ingest post carries the step that host's agent should carry out now; the
agent (1.18.0) leaves each step id for the root helper once, and the helper
refuses an id it already ran, so repeats are harmless. Results come back as
the #5766 maintenance events, matched by step id; the reboot completes when
the host's `started` event has a boot_at after the reboot was handed out.

The job reboots only when the update says one is needed (or never, if asked).
A swarm node is drained first by itself if it's a manager or by a manager
with the helper, and made active after; with no manager to drain it the job
is refused. A minute tick times out a job past its state's deadline. A
maintenance window over host_agent/<host> lasts the rest of the job.

Everything is on the row, so a Steward restart, or the reboot of the host
Steward runs on, resumes from the next post. Ingest runs it in its own
savepoint so a job going wrong never costs the samples.

The Agent panel leads with a running job and says what a finished one did;
Manage agent has Update now (with "never reboot"), or says why a job can't
start. Integration test: hand off, Steward restarts, the post-boot events
close the job.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/plugins/host_agent/test_maintenance.py

@@ -0,0 +1,154 @@
+# tests/plugins/host_agent/test_maintenance.py
+"""#5767: a host's maintenance job, step by step, from the agent's reports.
+
+The transitions are model-free, so a job here is a SimpleNamespace with the
+row's attributes; the database side is tests/integration/test_host_maintenance_job.py.
+"""
+import json
+from datetime import datetime, timedelta, timezone
+from types import SimpleNamespace
+
+import pytest
+
+from plugins.host_agent import agent as a
+from plugins.host_agent import maintenance as m
+
+T0 = datetime(2026, 10, 14, 23, 0, tzinfo=timezone.utc)
+
+
+def _job(**kw):
+    base = dict(id="job-1", host_id="h1", state="queued", state_at=T0, created_at=T0,
+                reboot_policy="if_required", step_id=None, step_seen=False, node_id=None,
+                drain_host_id=None, packages=None, reboot_needed=None, back_at=None,
+                detail=None, finished_at=None)
+    base.update(kw)
+    return SimpleNamespace(**base)
+
+
+def _result(job, state, **kw):
+    return {"kind": "maintenance", "id": job.step_id, "state": state, **kw}
+
+
+def test_an_update_with_no_reboot_needed_is_done_after_the_update():
+    job = _job()
+    m.start(job, T0)
+    assert m.handoff(job) == {"id": "job-1-update", "action": "update"}
+    assert m.apply_result(job, _result(job, "running"), T0)
+    assert m.handoff(job) is None                       # taken: not handed again
+    m.apply_result(job, _result(job, "done", ok=True, packages=3, reboot_required=False), T0)
+    assert (job.state, job.packages, job.finished_at) == ("done", 3, T0)
+    assert m.summary(job) == "Done: 3 packages updated, no reboot needed"
+
+
+def test_a_swarm_node_is_drained_rebooted_and_made_active_again():
+    job = _job(node_id="n" * 25, drain_host_id="mgr")
+    m.start(job, T0)
+    m.apply_result(job, _result(job, "done", ok=True, packages=12, reboot_required=True), T0)
+    assert job.state == "draining" and m.executor(job) == "mgr"
+    assert m.handoff(job) == {"id": "job-1-drain", "action": "drain", "node": "n" * 25}
+    m.apply_result(job, _result(job, "done", ok=True), T0)
+    assert job.state == "rebooting" and m.executor(job) == "h1"
+    assert m.handoff(job) == {"id": "job-1-reboot", "action": "reboot"}
+    t1 = T0 + timedelta(minutes=4)
+    assert m.apply_boot(job, T0 + timedelta(minutes=2), t1)
+    assert job.state == "undraining" and job.back_at == t1 and m.executor(job) == "mgr"
+    m.apply_result(job, _result(job, "done", ok=True), t1)
+    assert job.state == "done"
+    assert m.summary(job) == "Done: 12 packages updated, rebooted"
+
+
+def test_a_job_that_may_never_reboot_stops_after_the_update():
+    job = _job(reboot_policy="never")
+    m.start(job, T0)
+    m.apply_result(job, _result(job, "done", ok=True, packages=1, reboot_required=True), T0)
+    assert job.state == "done"
+    assert "reboot needed, not allowed" in m.summary(job)
+
+
+def test_only_a_boot_after_the_reboot_was_handed_out_completes_it():
+    job = _job(state="rebooting", step_id="job-1-reboot", state_at=T0)
+    assert not m.apply_boot(job, T0 - timedelta(days=3), T0)    # the agent restarted, not the host
+    assert not m.apply_boot(job, None, T0)
+    assert job.state == "rebooting"
+    assert m.apply_boot(job, T0 - timedelta(seconds=30), T0)     # within the clock slack
+    assert job.state == "done"
+
+
+def test_a_failed_step_fails_the_job_and_says_which():
+    job = _job(state="undraining", step_id="job-1-undrain", node_id="n" * 25, drain_host_id="mgr")
+    m.apply_result(job, _result(job, "failed", ok=False, detail="This node is not a swarm manager."), T0)
+    assert job.state == "failed"
+    assert job.detail.startswith("undrain failed: This node is not a swarm manager.")
+    assert "still drained" in job.detail
+
+
+def test_a_late_or_repeated_result_does_nothing():
+    job = _job()
+    m.start(job, T0)
+    stale = {"kind": "maintenance", "id": "job-1-drain", "state": "done", "ok": True}
+    assert not m.apply_result(job, stale, T0)
+    assert m.apply_result(job, _result(job, "running"), T0)
+    assert not m.apply_result(job, _result(job, "running"), T0)
+    m.apply_result(job, _result(job, "done", ok=True, reboot_required=False), T0)
+    assert not m.apply_result(job, {"kind": "maintenance", "id": "job-1-update", "state": "done"}, T0)
+
+
+@pytest.mark.parametrize("state,minutes,expected", [
+    ("queued", 59, False), ("queued", 61, True),
+    ("updating", 91, True), ("rebooting", 29, False), ("rebooting", 31, True),
+])
+def test_a_job_is_given_up_past_its_state_deadline(state, minutes, expected):
+    job = _job(state=state, step_id=f"job-1-{m.STEP_ACTION.get(state, 'x')}")
+    assert m.check_deadline(job, T0 + timedelta(minutes=minutes)) is expected
+    if expected:
+        assert job.state == "timed_out" and "within" in job.detail
+
+
+def test_the_window_lasts_the_rest_of_the_job_and_ends_with_it():
+    job = _job(state="rebooting", step_id="job-1-reboot")
+    assert m.window_end(job, T0) == T0 + timedelta(minutes=30 + 10)
+    job.state = "done"
+    assert m.window_end(job, T0) == T0
+
+
+def test_a_manager_drains_itself_and_a_worker_is_drained_by_a_manager():
+    nodes = {"docker02": "a" * 25, "docker03": "b" * 25}
+    managers = {"h2": "a" * 25}
+    assert m.pick_drainer(nodes, managers, "Docker02", "h2", {"h2", "h3"}) == ("a" * 25, "h2")
+    assert m.pick_drainer(nodes, managers, "Docker03", "h3", {"h2", "h3"}) == ("b" * 25, "h2")
+    assert m.pick_drainer(nodes, managers, "Util01", "h4", {"h2"}) == (None, None)
+    with pytest.raises(m.CannotStart, match="no swarm manager"):
+        m.pick_drainer(nodes, managers, "Docker03", "h3", {"h3"})
+
+
+# ── the agent's side ─────────────────────────────────────────────────────────
+
+def test_the_agent_leaves_each_handed_step_once(tmp_path):
+    requested: set = set()
+    steps = [{"id": "job-1-update", "action": "update"}, {"id": "job-1-x", "action": "shell"}, "junk"]
+    assert a.take_maintenance(steps, requested, requests_dir=str(tmp_path)) == ["job-1-update"]
+    assert json.loads((tmp_path / "job-1-update.json").read_text()) == {
+        "id": "job-1-update", "action": "update"}
+    (tmp_path / "job-1-update.json").unlink()          # the helper took it
+    assert a.take_maintenance(steps, requested, requests_dir=str(tmp_path)) == []
+    assert not (tmp_path / "job-1-update.json").exists()
+    assert a.take_maintenance(None, requested, requests_dir=str(tmp_path)) == []
+
+
+def test_the_agent_reads_stewards_answer_when_asked(monkeypatch):
+    class Resp:
+        status = 200
+
+        def read(self, n):
+            return b'{"ok": true, "maintenance": [{"id": "job-1-reboot", "action": "reboot"}]}'
+
+        def __enter__(self):
+            return self
+
+        def __exit__(self, *exc):
+            return False
+
+    monkeypatch.setattr(a.urllib.request, "urlopen", lambda req, timeout: Resp())
+    answer: dict = {}
+    assert a.post_payload("https://x", "tok", {}, answer) == (True, 200)
+    assert answer["maintenance"] == [{"id": "job-1-reboot", "action": "reboot"}]