feat(docker): Docker's own status reaches Steward — an empty answer clears a host, a lost one greys it, a demoted manager's swarm rows go (#5152)
The agent (1.9.0) said nothing when Docker could not be asked and nothing when Docker had no containers, so Steward could tell neither apart from the other, and kept a host's last containers on screen as running either way. - Agent: collect_docker returns (status, detail, containers). "ok" sends docker: [] when there are none; "unavailable" (no socket, nothing listening) and "error" (permission, timeout, bad answer) say why. collect_swarm says whether /info answered, and a node that is not a manager sends swarm_manager: false. A failed /info says nothing. - Ingest: an empty docker list is a snapshot; the newest sample's status goes to the Docker plugin with the rest. - docker_host_status (docker_011): per host, status, detail, since and last report. A host that never had Docker gets no row. - An "ok" empty snapshot reaps the host's containers; an error keeps them. swarm_manager: false drops the host's swarm services and nodes. - Docker page: a "Docker not answering" card names each such host, why, and since when; its containers read as stale. Duplicate header comment in rows.html removed. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,79 @@
|
||||
"""Integration: an agent's Docker status reaches Steward through ingest (#5152).
|
||||
|
||||
The newest sample's status wins over a backlog's older ones; "error" keeps
|
||||
the containers Docker last listed; an "ok" with an empty list clears them.
|
||||
|
||||
Rows are read with plain SQL: importing the plugin's models again after the
|
||||
app loaded the plugin raises "Table already defined" (see test_mcp_plugin_tools)."""
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import hashlib
|
||||
import os
|
||||
import uuid
|
||||
from datetime import datetime, timedelta, timezone
|
||||
|
||||
import pytest
|
||||
|
||||
pytestmark = pytest.mark.integration
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def app():
|
||||
if not os.environ.get("STEWARD_DATABASE_URL"):
|
||||
pytest.skip("needs Postgres")
|
||||
from steward.app import create_app
|
||||
return create_app(testing=False)
|
||||
|
||||
|
||||
def test_ingest_records_docker_status_and_clears_on_an_empty_answer(app):
|
||||
from sqlalchemy import text
|
||||
from steward.models.hosts import Host
|
||||
|
||||
web = {"name": "web", "status": "running", "cpu_pct": 1.0, "mem_pct": 1.0,
|
||||
"restart_count": 0, "exit_code": None, "oom_killed": False, "health": None}
|
||||
|
||||
async def _go():
|
||||
tag = uuid.uuid4().hex[:8]
|
||||
token = f"tok-{tag}-{uuid.uuid4().hex}"
|
||||
async with app.db_sessionmaker() as s:
|
||||
async with s.begin():
|
||||
host = Host(name=f"dock-{tag}", address="10.9.9.3")
|
||||
s.add(host)
|
||||
await s.flush()
|
||||
await s.execute(text(
|
||||
"INSERT INTO host_agent_registrations "
|
||||
"(id, host_id, token_hash, token_created_at, created_at, updated_at) "
|
||||
"VALUES (:id, :host, :hash, now(), now(), now())"),
|
||||
{"id": str(uuid.uuid4()), "host": host.id,
|
||||
"hash": hashlib.sha256(token.encode()).hexdigest()})
|
||||
host_id = host.id
|
||||
|
||||
client = app.test_client()
|
||||
now = datetime.now(timezone.utc)
|
||||
|
||||
async def post(*samples):
|
||||
resp = await client.post("/plugins/host_agent/ingest", json={"samples": list(samples)},
|
||||
headers={"Authorization": f"Bearer {token}"})
|
||||
assert resp.status_code == 200, await resp.get_data(as_text=True)
|
||||
async with app.db_sessionmaker() as s:
|
||||
status = (await s.execute(text(
|
||||
"SELECT status, detail FROM docker_host_status WHERE host_id = :h"),
|
||||
{"h": host_id})).first()
|
||||
names = [r[0] for r in (await s.execute(text(
|
||||
"SELECT name FROM docker_containers WHERE host_id = :h"), {"h": host_id})).all()]
|
||||
return (tuple(status) if status else None), names
|
||||
|
||||
def at(seconds_ago):
|
||||
return (now - timedelta(seconds=seconds_ago)).isoformat()
|
||||
|
||||
# A backlog, newest first: Docker listed web, then stopped answering.
|
||||
backlog = await post(
|
||||
{"ts": at(60), "docker_status": "error", "docker_detail": "permission denied on /s"},
|
||||
{"ts": at(90), "docker_status": "ok", "docker": [web]})
|
||||
emptied = await post({"ts": at(30), "docker_status": "ok", "docker": []})
|
||||
return backlog, emptied
|
||||
|
||||
backlog, emptied = asyncio.run(_go())
|
||||
assert backlog == (("error", "permission denied on /s"), ["web"])
|
||||
assert emptied == (("ok", None), [])
|
||||
Reference in New Issue
Block a user