homelab-codex-ws/services/control-plane/tests/test_dormant_nodes.py

198 lines
6.6 KiB
Python
Raw Normal View History

"""Dormant-node handling (topology `status: dormant`, etap 0 truth cleanup).
Contract (kb/decisions/architektura-2026-07-28.md): a dormant node keeps its
last-known world state, the observer emits NO liveness events for it, and the
supervisor generates NO actions of any kind for it.
"""
from __future__ import annotations
import json
import sys
import time
from pathlib import Path
import pytest
sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
sys.path.insert(0, str(Path(__file__).parent.parent.parent.parent / "scripts"))
import observer.observer as obs_mod
from observer.observer import Observer
import supervisor as supervisor_module
from supervisor import Supervisor
TOPOLOGY_YAML = (
"nodes:\n"
" piha:\n"
" status: active\n"
" roles: [infra]\n"
" oldnode:\n"
" status: dormant\n"
" dormant_reason: \"hardware down\"\n"
" roles: [remote]\n"
)
# ---------------------------------------------------------------------------
# Observer
# ---------------------------------------------------------------------------
@pytest.fixture
def obs_paths(tmp_path, monkeypatch):
world = tmp_path / "world"
state = tmp_path / "state"
events = tmp_path / "events"
logs = tmp_path / "logs"
repo = tmp_path / "repo"
for d in (world, state, events, logs, repo / "inventory", repo / "hosts"):
d.mkdir(parents=True, exist_ok=True)
(repo / "inventory" / "topology.yaml").write_text(TOPOLOGY_YAML)
monkeypatch.setattr(obs_mod, "WORLD_DIR", world)
monkeypatch.setattr(obs_mod, "STATE_DIR", state)
monkeypatch.setattr(obs_mod, "EVENTS_DIR", events)
monkeypatch.setattr(obs_mod, "LOGS_DIR", logs)
monkeypatch.setattr(obs_mod, "INVENTORY_TOPOLOGY", repo / "inventory" / "topology.yaml")
monkeypatch.setattr(obs_mod, "REPO_ROOT", repo)
monkeypatch.setattr(obs_mod, "FAILED_EVENTS_DIR", state / "observer_failed_events")
monkeypatch.setattr(obs_mod, "OBSERVER_STATE_FILE", state / "observer_checkpoint.json")
monkeypatch.setattr(obs_mod, "PROM_SHADOW_URL", "")
monkeypatch.setattr(obs_mod, "SHADOW_LOG_DIR", logs / "observer")
return tmp_path
def test_observer_loads_dormant_set_from_topology(obs_paths):
obs = Observer()
assert obs.dormant_nodes == {"oldnode"}
def test_observer_freezes_dormant_node_and_emits_nothing(obs_paths):
"""A dormant node whose heartbeats stopped long ago must NOT be
reclassified (staledead would normally fire node_offline)."""
obs = Observer()
stale_age = int(time.time()) - 999999
obs.world_state["nodes"] = {
"oldnode": {"status": "stale", "liveness": "stale", "last_seen": stale_age},
"piha": {"status": "unknown", "last_seen": int(time.time())},
}
obs._prune_stale_world()
frozen = obs.world_state["nodes"]["oldnode"]
assert frozen["liveness"] == "stale" # unchanged, despite dead-level age
assert frozen["status"] == "stale" # unchanged
# No liveness event file was written for the dormant node.
assert not list((obs_paths / "events").glob("**/evt-oldnode-*"))
# The active node is still processed normally.
assert obs.world_state["nodes"]["piha"]["liveness"] == "fresh"
def test_observer_keeps_dormant_node_in_world_state(obs_paths):
"""Dormant nodes are in the inventory, so pruning must not remove them."""
obs = Observer()
obs.world_state["nodes"] = {"oldnode": {"status": "offline", "last_seen": 1}}
obs._prune_stale_world()
assert "oldnode" in obs.world_state["nodes"]
# ---------------------------------------------------------------------------
# Supervisor
# ---------------------------------------------------------------------------
@pytest.fixture
def sup(tmp_path, monkeypatch):
actions = tmp_path / "actions"
events = tmp_path / "events"
world = tmp_path / "world"
state = tmp_path / "state"
repo = tmp_path / "repo"
for d in (actions, events, world, state, repo / "inventory", repo / "hosts" / "oldnode"):
d.mkdir(parents=True, exist_ok=True)
(repo / "inventory" / "topology.yaml").write_text(TOPOLOGY_YAML)
(repo / "hosts" / "oldnode" / "services.yaml").write_text(
"host: oldnode\nservices:\n some-svc:\n role: x\n"
)
monkeypatch.setattr(supervisor_module, "ACTIONS_DIR", actions)
monkeypatch.setattr(supervisor_module, "EVENTS_DIR", events)
monkeypatch.setattr(supervisor_module, "WORLD_DIR", world)
monkeypatch.setattr(supervisor_module, "REPO_ROOT", repo)
s = Supervisor()
return s
def _pending(tmp_path):
return list((tmp_path / "actions" / "pending").glob("*.json"))
def test_supervisor_loads_dormant_set(sup):
feat(supervisor): duty-cycle nodes — liveness transitions logged, not actioned solaria (powered off ~16 h/day by design) and lustro (nightly display power-off) generated node_offline/node_stale/node_online alerts on every daily cycle. Six of them have sat in actions/pending/ since 2026-06-17/18, unapproved. Because an unapproved pending action suppresses its own dedup ID indefinitely (recon D14, supervisor.py pending/approved/running check), those stale alerts also meant a *real* future outage on either node would generate nothing at all. Suppression is data-driven from inventory/topology.yaml, not a hardcoded node-name check: - topology.yaml: new `duty_cycle` (+ `duty_cycle_reason`) on solaria and lustro, mirroring the existing dormant/dormant_reason shape. vps and piha deliberately do not carry it — an offline 24/7 node is a real incident. - supervisor: _load_dormant_nodes() -> _load_node_policy(), loading both dormant_nodes and duty_cycle_nodes from one topology read. dormant behavior is byte-for-byte unchanged. - supervisor: one guard in _route_node_event. Duty-cycle liveness events are logged at INFO and return; no action is written. duty_cycle is deliberately NOT dormant. A duty-cycle node stays fully active: its services are still reconciled (missing_service -> redeploy), its disk pressure still generates disk_cleanup, and its ha_* events still route. Only the liveness alert is suppressed. Regression tests pin all three. Fail-loud: an unreadable topology leaves both sets empty, which disables suppression and lets alerts through. A broken topology must never silently mute the fleet. Accepted trade-off: a genuine permanent outage of solaria or lustro no longer alerts. It stays visible in the operator UI (which computes liveness independently at read time) and in the event feed. An "offline longer than the expected window" escalation is the natural follow-up and needs a schedule in the topology field rather than a bare marker. Tests: 169 passed in services/control-plane/tests (was 157; +12). Runtime deployment is deliberately NOT part of this commit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-05 13:48:29 +02:00
sup._load_node_policy()
assert sup.dormant_nodes == {"oldnode"}
def test_dormant_services_excluded_from_desired_state(sup):
feat(supervisor): duty-cycle nodes — liveness transitions logged, not actioned solaria (powered off ~16 h/day by design) and lustro (nightly display power-off) generated node_offline/node_stale/node_online alerts on every daily cycle. Six of them have sat in actions/pending/ since 2026-06-17/18, unapproved. Because an unapproved pending action suppresses its own dedup ID indefinitely (recon D14, supervisor.py pending/approved/running check), those stale alerts also meant a *real* future outage on either node would generate nothing at all. Suppression is data-driven from inventory/topology.yaml, not a hardcoded node-name check: - topology.yaml: new `duty_cycle` (+ `duty_cycle_reason`) on solaria and lustro, mirroring the existing dormant/dormant_reason shape. vps and piha deliberately do not carry it — an offline 24/7 node is a real incident. - supervisor: _load_dormant_nodes() -> _load_node_policy(), loading both dormant_nodes and duty_cycle_nodes from one topology read. dormant behavior is byte-for-byte unchanged. - supervisor: one guard in _route_node_event. Duty-cycle liveness events are logged at INFO and return; no action is written. duty_cycle is deliberately NOT dormant. A duty-cycle node stays fully active: its services are still reconciled (missing_service -> redeploy), its disk pressure still generates disk_cleanup, and its ha_* events still route. Only the liveness alert is suppressed. Regression tests pin all three. Fail-loud: an unreadable topology leaves both sets empty, which disables suppression and lets alerts through. A broken topology must never silently mute the fleet. Accepted trade-off: a genuine permanent outage of solaria or lustro no longer alerts. It stays visible in the operator UI (which computes liveness independently at read time) and in the event feed. An "offline longer than the expected window" escalation is the natural follow-up and needs a schedule in the topology field rather than a bare marker. Tests: 169 passed in services/control-plane/tests (was 157; +12). Runtime deployment is deliberately NOT part of this commit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-05 13:48:29 +02:00
sup._load_node_policy()
sup._load_desired_state()
assert "oldnode/some-svc" not in sup.desired_state["services"]
def test_reconcile_generates_no_actions_for_dormant_node(sup, tmp_path):
"""Full reconcile: missing service + high disk pressure on a dormant node
must produce zero pending actions."""
world = tmp_path / "world"
(world / "nodes.json").write_text(json.dumps(
{"oldnode": {"status": "offline", "disk_pressure": "high"}}
))
(world / "services.json").write_text("{}")
(world / "incidents.json").write_text("{}")
sup.reconcile()
assert _pending(tmp_path) == []
def test_node_event_from_dormant_node_not_routed(sup, tmp_path):
feat(supervisor): duty-cycle nodes — liveness transitions logged, not actioned solaria (powered off ~16 h/day by design) and lustro (nightly display power-off) generated node_offline/node_stale/node_online alerts on every daily cycle. Six of them have sat in actions/pending/ since 2026-06-17/18, unapproved. Because an unapproved pending action suppresses its own dedup ID indefinitely (recon D14, supervisor.py pending/approved/running check), those stale alerts also meant a *real* future outage on either node would generate nothing at all. Suppression is data-driven from inventory/topology.yaml, not a hardcoded node-name check: - topology.yaml: new `duty_cycle` (+ `duty_cycle_reason`) on solaria and lustro, mirroring the existing dormant/dormant_reason shape. vps and piha deliberately do not carry it — an offline 24/7 node is a real incident. - supervisor: _load_dormant_nodes() -> _load_node_policy(), loading both dormant_nodes and duty_cycle_nodes from one topology read. dormant behavior is byte-for-byte unchanged. - supervisor: one guard in _route_node_event. Duty-cycle liveness events are logged at INFO and return; no action is written. duty_cycle is deliberately NOT dormant. A duty-cycle node stays fully active: its services are still reconciled (missing_service -> redeploy), its disk pressure still generates disk_cleanup, and its ha_* events still route. Only the liveness alert is suppressed. Regression tests pin all three. Fail-loud: an unreadable topology leaves both sets empty, which disables suppression and lets alerts through. A broken topology must never silently mute the fleet. Accepted trade-off: a genuine permanent outage of solaria or lustro no longer alerts. It stays visible in the operator UI (which computes liveness independently at read time) and in the event feed. An "offline longer than the expected window" escalation is the natural follow-up and needs a schedule in the topology field rather than a bare marker. Tests: 169 passed in services/control-plane/tests (was 157; +12). Runtime deployment is deliberately NOT part of this commit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-05 13:48:29 +02:00
sup._load_node_policy()
event = {
"id": "evt-oldnode-1-node_offline-node",
"type": "node_offline",
"node": "oldnode",
"payload": {"affected_node": "oldnode"},
}
(tmp_path / "events" / f"{event['id']}.json").write_text(json.dumps(event))
sup._process_ha_events()
assert _pending(tmp_path) == []
def test_ha_event_from_dormant_node_not_routed(sup, tmp_path):
feat(supervisor): duty-cycle nodes — liveness transitions logged, not actioned solaria (powered off ~16 h/day by design) and lustro (nightly display power-off) generated node_offline/node_stale/node_online alerts on every daily cycle. Six of them have sat in actions/pending/ since 2026-06-17/18, unapproved. Because an unapproved pending action suppresses its own dedup ID indefinitely (recon D14, supervisor.py pending/approved/running check), those stale alerts also meant a *real* future outage on either node would generate nothing at all. Suppression is data-driven from inventory/topology.yaml, not a hardcoded node-name check: - topology.yaml: new `duty_cycle` (+ `duty_cycle_reason`) on solaria and lustro, mirroring the existing dormant/dormant_reason shape. vps and piha deliberately do not carry it — an offline 24/7 node is a real incident. - supervisor: _load_dormant_nodes() -> _load_node_policy(), loading both dormant_nodes and duty_cycle_nodes from one topology read. dormant behavior is byte-for-byte unchanged. - supervisor: one guard in _route_node_event. Duty-cycle liveness events are logged at INFO and return; no action is written. duty_cycle is deliberately NOT dormant. A duty-cycle node stays fully active: its services are still reconciled (missing_service -> redeploy), its disk pressure still generates disk_cleanup, and its ha_* events still route. Only the liveness alert is suppressed. Regression tests pin all three. Fail-loud: an unreadable topology leaves both sets empty, which disables suppression and lets alerts through. A broken topology must never silently mute the fleet. Accepted trade-off: a genuine permanent outage of solaria or lustro no longer alerts. It stays visible in the operator UI (which computes liveness independently at read time) and in the event feed. An "offline longer than the expected window" escalation is the natural follow-up and needs a schedule in the topology field rather than a bare marker. Tests: 169 passed in services/control-plane/tests (was 157; +12). Runtime deployment is deliberately NOT part of this commit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-05 13:48:29 +02:00
sup._load_node_policy()
event = {
"id": "evt-oldnode-2-ha_entity_unavailable_long-homeassistant",
"type": "ha_entity_unavailable_long",
"node": "oldnode",
"payload": {},
}
(tmp_path / "events" / f"{event['id']}.json").write_text(json.dumps(event))
sup._process_ha_events()
assert _pending(tmp_path) == []
def test_active_node_events_still_routed(sup, tmp_path):
"""Sanity: the dormant guard must not swallow active-node events."""
feat(supervisor): duty-cycle nodes — liveness transitions logged, not actioned solaria (powered off ~16 h/day by design) and lustro (nightly display power-off) generated node_offline/node_stale/node_online alerts on every daily cycle. Six of them have sat in actions/pending/ since 2026-06-17/18, unapproved. Because an unapproved pending action suppresses its own dedup ID indefinitely (recon D14, supervisor.py pending/approved/running check), those stale alerts also meant a *real* future outage on either node would generate nothing at all. Suppression is data-driven from inventory/topology.yaml, not a hardcoded node-name check: - topology.yaml: new `duty_cycle` (+ `duty_cycle_reason`) on solaria and lustro, mirroring the existing dormant/dormant_reason shape. vps and piha deliberately do not carry it — an offline 24/7 node is a real incident. - supervisor: _load_dormant_nodes() -> _load_node_policy(), loading both dormant_nodes and duty_cycle_nodes from one topology read. dormant behavior is byte-for-byte unchanged. - supervisor: one guard in _route_node_event. Duty-cycle liveness events are logged at INFO and return; no action is written. duty_cycle is deliberately NOT dormant. A duty-cycle node stays fully active: its services are still reconciled (missing_service -> redeploy), its disk pressure still generates disk_cleanup, and its ha_* events still route. Only the liveness alert is suppressed. Regression tests pin all three. Fail-loud: an unreadable topology leaves both sets empty, which disables suppression and lets alerts through. A broken topology must never silently mute the fleet. Accepted trade-off: a genuine permanent outage of solaria or lustro no longer alerts. It stays visible in the operator UI (which computes liveness independently at read time) and in the event feed. An "offline longer than the expected window" escalation is the natural follow-up and needs a schedule in the topology field rather than a bare marker. Tests: 169 passed in services/control-plane/tests (was 157; +12). Runtime deployment is deliberately NOT part of this commit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-05 13:48:29 +02:00
sup._load_node_policy()
event = {
"id": "evt-piha-3-node_stale-node",
"type": "node_stale",
"node": "piha",
"payload": {"affected_node": "piha"},
}
(tmp_path / "events" / f"{event['id']}.json").write_text(json.dumps(event))
sup._process_ha_events()
assert len(_pending(tmp_path)) == 1