bvandeusenandClaude Opus 5.5
414c942cbf
Traefik: routers are graded from their latest scrape (router_state: crit on any real 5xx share, warn on p95 past the latency critical cutoff or a high 4xx share). Failing and slow routers lead as cards that say why; healthy ones fold into one table that stays open or shut across polls. Proxy counts are stat tiles; certificates are graded by Settings -> Thresholds (tls_days). UniFi: WAN health is a stat strip (latency graded by the thresholds), devices carry status dots, event categories and firewall actions are badges, the alarm count reuses .count-badge (renamed from .nav-count). SNMP: each device wears a status badge and its readings are stat tiles. Agent fleet: the table comes first, with a Status column (Reporting / Silent / Never reported, by the host page's stale_after_seconds), silent agents first, hosts linked, last seen as |ago. Audit: entries name their entity (one query per type, steward/audit/ service.py) and link it; something deleted since keeps the name its entry recorded and says "(deleted)". Tokens: charts read colours through chart-colors.js (stewardColor resolves a token to the rgb the browser computed; Chart.js defaults take the page's text and border colours), so host, history, Traefik and SNMP charts drop their hex. Template hex colours reach 0 (HEX_CEILING = 0), the last rgba pills go, and heavy weights (600/700/bold, 60 of them) become 500, the house pair being 400/500; a guard keeps templates there. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
66 lines
3.0 KiB
Python
66 lines
3.0 KiB
Python
"""The Traefik page puts failing and slow routers first and folds the healthy
|
|
ones into one table; certificates are graded by Settings → Thresholds (#5126)."""
|
|
from datetime import datetime, timedelta, timezone
|
|
from types import SimpleNamespace as NS
|
|
|
|
import pytest
|
|
|
|
from plugins.traefik.routes import router_state, split_routers
|
|
from steward.core.settings import to_thresholds_cfg
|
|
from tests._templates import render_plugin_template
|
|
from tests.test_style_tokens import hex_colours
|
|
|
|
TH = to_thresholds_cfg({}) # latency crit 200 ms
|
|
|
|
|
|
def _latest(req=1.0, p95=20.0, e4=0.0, e5=0.0):
|
|
return NS(request_rate=req, response_bytes_rate=1000.0, latency_p95_ms=p95, latency_p99_ms=p95 * 1.5,
|
|
error_rate_4xx_pct=e4, error_rate_5xx_pct=e5,
|
|
scraped_at=datetime.now(timezone.utc) - timedelta(seconds=30))
|
|
|
|
|
|
@pytest.mark.parametrize("latest, grade", [
|
|
(_latest(), "ok"),
|
|
(_latest(e5=2.5), "crit"),
|
|
(_latest(p95=450.0), "warn"),
|
|
(_latest(e4=5.0), "warn"),
|
|
(_latest(p95=120.0, e4=0.5), "ok"), # slow-ish but under the critical cutoff
|
|
])
|
|
def test_router_state(latest, grade):
|
|
assert router_state(latest, TH)[0] == grade
|
|
|
|
|
|
def _router(name, latest):
|
|
state, why = router_state(latest, TH)
|
|
return {"name": name, "latest": latest, "state": state, "why": why,
|
|
"sparkline_req": "", "sparkline_p95": "", "sparkline_5xx": ""}
|
|
|
|
|
|
def test_failing_routers_come_before_slow_ones_and_healthy_ones_split_off():
|
|
problems, healthy = split_routers([
|
|
_router("b-ok", _latest()), _router("slow", _latest(p95=450.0)),
|
|
_router("broken", _latest(e5=3.0)), _router("a-ok", _latest())])
|
|
assert [r["name"] for r in problems] == ["broken", "slow"]
|
|
assert [r["name"] for r in healthy] == ["a-ok", "b-ok"]
|
|
|
|
|
|
async def test_the_page_leads_with_problems_and_folds_the_healthy(app):
|
|
problems, healthy = split_routers([
|
|
_router("api", _latest(e5=3.0)), _router("web", _latest()), _router("docs", _latest())])
|
|
now = datetime.now(timezone.utc)
|
|
certs = [{"serial": "1", "cn": "soon.example", "sans": [], "not_after": now + timedelta(days=2),
|
|
"days_remaining": 2.0},
|
|
{"serial": "2", "cn": "fine.example", "sans": [], "not_after": now + timedelta(days=60),
|
|
"days_remaining": 60.0}]
|
|
async with app.test_request_context("/plugins/traefik/rows"):
|
|
page = await render_plugin_template(app, "traefik", "traefik/rows.html", problems=problems,
|
|
healthy=healthy, global_stat=None, certs=certs, range_key="24h",
|
|
error_4xx=1.0, error_5xx=0.1)
|
|
|
|
assert page.index(">api</h3>") < page.index('id="traefik-healthy"')
|
|
assert "3.0% of responses are 5xx" in page
|
|
assert ">2 healthy routers</summary>" in page
|
|
assert page.index(">docs</td>") < page.index(">web</td>")
|
|
assert 'class="tone-crit">2 days</td>' in page and 'class="tone-ok">60 days</td>' in page
|
|
assert "font-weight:600" not in page and not hex_colours(page), hex_colours(page)
|