bvandeusenandClaude Opus 5.5
6cf04f57e1
The Docker page opens with a "Needs attention" card: every container
with something wrong, worst problem first — restarting, crash-looping,
unhealthy, OOM-killed, exited non-zero — each with what it does ("is
restarting and keeps dying · exit 1 · since 8m ago"), linked to its page.
It is ranked by the same code as the MCP tools: container_problems,
problem_since and the per-container ranking move from mcp_tools into
service.py (ranked_containers, needs_attention), and mcp_tools' _rows and
findings now read them from there.
Counts follow as stat tiles: needs attention, unhealthy, restarting (or
crash-looping), running, stopped, stale, services, hosts.
A container whose last report is older than the host agent's staleness
window (stale_after_seconds, 180 s by default) carries a Stale badge with
when it last reported, instead of a live-looking green dot.
The per-container CPU and memory history columns are gone from the
overview, and with them one history query per container per refresh; the
container's own page keeps its charts. With nothing left to range over,
the time-range control goes too, and the page now refreshes on the poll
interval. CPU and memory are graded by Settings → Thresholds rather than
50/80 and 70/90 written into the template.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
77 lines
4.3 KiB
Python
77 lines
4.3 KiB
Python
"""The Docker page leads with what needs attention, ranked the way the MCP
|
|
tools rank it, and marks a container whose report is old as stale (#5123)."""
|
|
import re
|
|
from datetime import datetime, timedelta, timezone
|
|
from types import SimpleNamespace as NS
|
|
|
|
|
|
from plugins.docker import service as svc
|
|
from plugins.docker.routes import _is_stale
|
|
from tests._templates import render_plugin_template
|
|
from tests.test_style_tokens import hex_colours
|
|
|
|
NOW = datetime.now(timezone.utc)
|
|
|
|
|
|
def _c(name, **kw):
|
|
base = dict(name=name, host_id="h1", image="nginx:1", status="running", health=None, exit_code=None,
|
|
oom_killed=False, restart_count=0, cpu_pct=5.0, mem_pct=10.0, compose_project=None,
|
|
service_name=None, ports_json=None, started_at=NOW - timedelta(hours=2),
|
|
scraped_at=NOW - timedelta(seconds=20))
|
|
base.update(kw)
|
|
return NS(**base)
|
|
|
|
|
|
def test_needs_attention_ranks_the_worst_problem_first():
|
|
ranked = [{"container": _c(n), "problems": p, "since": None, "replaced": False} for n, p in [
|
|
("fine", []), ("oom", ["oom_killed"]), ("sick", ["unhealthy"]),
|
|
("loop", ["crash_looping"]), ("exit", ["exited_nonzero"]), ("bounce", ["restarting", "crash_looping"])]]
|
|
assert [r["container"].name for r in svc.needs_attention(ranked)] == ["bounce", "loop", "sick", "oom", "exit"]
|
|
|
|
|
|
def test_stale_is_older_than_the_agents_window():
|
|
assert not _is_stale(_c("a"), NOW, 180)
|
|
assert _is_stale(_c("a", scraped_at=NOW - timedelta(minutes=10)), NOW, 180)
|
|
assert _is_stale(_c("a", scraped_at=None), NOW, 180)
|
|
assert svc.stale_after_seconds({"PLUGINS": {"host_agent": {"stale_after_seconds": 60}}}) == 60
|
|
assert svc.stale_after_seconds({}) == 180
|
|
|
|
|
|
async def test_a_crash_loop_comes_first_and_a_stale_row_says_so(app):
|
|
loop = _c("api", status="restarting", exit_code=1, restart_count=7)
|
|
old = _c("cache", scraped_at=NOW - timedelta(minutes=30), cpu_pct=95.0)
|
|
attention = [{"container": loop, "problems": ["restarting", "crash_looping"], "replaced": False,
|
|
"since": datetime.now(timezone.utc) - timedelta(minutes=8), "stale": False}]
|
|
groups = [{"host": None, "host_id": "h1", "host_name": "nas", "running": 1, "stopped": 1, "grouped": False,
|
|
"subgroups": [{"label": None, "containers": [
|
|
{"container": loop, "ports": [], "uptime": None, "stale": False},
|
|
{"container": old, "ports": [], "uptime": "2h", "stale": True}]}]}]
|
|
async with app.test_request_context("/plugins/docker/rows"):
|
|
page = await render_plugin_template(
|
|
app, "docker", "docker/rows.html", attention=attention, says=svc.PROBLEM_SAYS, severity=svc.PROBLEM_SEVERITY,
|
|
unhealthy=0, restarting=1, stale=1, host_groups=groups, swarm_services=[],
|
|
running=1, stopped=1, total=2)
|
|
page = re.sub(r">\s+<", "><", " ".join(page.split()))
|
|
|
|
card = page[page.index("Needs attention"):page.index("</section>")]
|
|
assert '<span class="badge badge-crit">Restarting</span>' in card
|
|
assert 'href="/plugins/docker/container/h1/api">api</a>' in card
|
|
assert "is restarting and keeps dying · exit 1 · since <time" in card and ">8m ago</time>" in card
|
|
assert "cache" not in card
|
|
assert page.index("Needs attention") < page.index("<table")
|
|
|
|
assert '<span class="stat-tile-label">Restarting</span><span class="stat-tile-value">1</span>' in page
|
|
assert '<span class="stat-tile-label">Stale</span><span class="stat-tile-value">1</span>' in page
|
|
assert 'class="badge badge-warn" title="Last report' in page # the stale row
|
|
assert '<span class="tone-crit">95.0%</span>' in page # CPU through Settings → Thresholds
|
|
assert "history" not in page.lower() and "<svg" not in page # no sparklines on the overview
|
|
assert not hex_colours(page), hex_colours(page)
|
|
|
|
|
|
async def test_a_healthy_board_has_no_attention_card(app):
|
|
async with app.test_request_context("/plugins/docker/rows"):
|
|
page = await render_plugin_template(
|
|
app, "docker", "docker/rows.html", attention=[], says=svc.PROBLEM_SAYS, severity=svc.PROBLEM_SEVERITY,
|
|
unhealthy=0, restarting=0, stale=0, host_groups=[], swarm_services=[], running=0, stopped=0, total=0)
|
|
assert "Needs attention</h2>" not in page and "No containers reported yet" in page
|