bvandeusen/FabledSteward
1
0
Fork 0
Code Issues 1 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

feat(dashboard): a curated default layout, merged duplicate widgets, a labelled Overview (#5213)
CI / lint (push) Successful in 2s
Details
CI / integration (push) Successful in 50s
Details
CI / unit (push) Failing after 1m16s
Details
CI / publish (push) Skipped
Details

Browse Source 
- New installs start from widgets.RECOMMENDED, packed row by row for the
  enabled plugins; the edit drawer can reset a dashboard to it.
- Host Agent — Resources folds into Hosts — Overview (which gains load 1m),
  UniFi — Devices into UniFi — Overview; migration 0032 moves existing
  dashboards onto the survivors.
- The Overview labels what it counts (hosts, monitors up/down/pending,
  alerts firing) and lists firing alerts and down monitors with since-times.
- Uptime polls every 5 minutes (poll_seconds) instead of every cycle.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
bvandeusen
2026-10-07 00:42:04 -04:00
co-authored by Claude Opus 5.5
parent 5ec930bf76
commit 5492336f1e
18 changed files with 381 additions and 309 deletions
Download Patch File Download Diff File Expand all files Collapse all files
plugins/host_agent/routes.py
+1 -103
View File
@@ -17,7 +17,7 @@ from sqlalchemy import select, or_, and_
from datetime import timedelta
from steward.core.formatting import worst_reading
from steward.core.metric_series import latest_by_resource, points as metric_points
from steward.core.metric_series import points as metric_points
from steward.core.settings import get_setting, public_base_url
from steward.core.time_range import parse_range, RANGE_OPTIONS
from steward.models.hosts import Host
@@ -477,108 +477,6 @@ def _stale_after_seconds() -> int:
)
async def _fleet_rows(session) -> list[dict]:
"""One row per registered host with its latest host-level metrics + stale flag.
Only bare host-level resources are used here (sub-resources carry a ':' and
are skipped) so the fleet glance stays one line per host.
"""
regs = (await session.execute(select(HostAgentRegistration))).scalars().all()
host_ids = [r.host_id for r in regs]
hosts = {
h.id: h for h in (await session.execute(
select(Host).where(Host.id.in_(host_ids))
)).scalars().all()
} if host_ids else {}
host_names = [h.name for h in hosts.values()]
latest_by = await latest_by_resource(
session, SOURCE_MODULE, host_names + [n + ":/" for n in host_names])
latest: dict[str, dict[str, float]] = {}
root_disk: dict[str, float] = {} # host_name → root (/) disk %
for resource, metrics in latest_by.items():
if resource.endswith(":/"):
if "disk_used_pct" in metrics:
root_disk[resource[:-2]] = metrics["disk_used_pct"].value
continue
latest[resource] = {m: r.value for m, r in metrics.items()}
# Per-host recent series for the inline sparklines (cpu/mem/load host-level,
# disk from the root mount), so each metric shows its trend beside the value —
# the host-panel at-a-glance, on the fleet widget. 1h window keeps it cheap.
spark_series: dict[str, dict[str, list]] = {
n: {"cpu": [], "mem": [], "disk": [], "load": []} for n in host_names
}
if host_names:
since = datetime.now(timezone.utc) - timedelta(hours=1)
sp_rows = (await session.execute(
select(PluginMetric).where(
PluginMetric.source_module == SOURCE_MODULE,
PluginMetric.recorded_at >= since,
or_(
and_(PluginMetric.resource_name.in_(host_names),
PluginMetric.metric_name.in_(("cpu_pct", "mem_used_pct", "load_1m"))),
and_(PluginMetric.resource_name.in_([n + ":/" for n in host_names]),
PluginMetric.metric_name == "disk_used_pct"),
),
).order_by(PluginMetric.recorded_at)
)).scalars().all()
for r in sp_rows:
if r.resource_name.endswith(":/"):
name = r.resource_name[:-2]
if name in spark_series:
spark_series[name]["disk"].append(r.value)
else:
key = {"cpu_pct": "cpu", "mem_used_pct": "mem", "load_1m": "load"}.get(r.metric_name)
if key and r.resource_name in spark_series:
spark_series[r.resource_name][key].append(r.value)
from steward.core.status import sparkline_svg
stale_after = _stale_after_seconds()
now = datetime.now(timezone.utc)
rows = []
for reg in regs:
host = hosts.get(reg.host_id)
if host is None:
continue
m = latest.get(host.name, {})
ls = reg.last_seen_at
stale = ls is None or (now - ls).total_seconds() > stale_after
ser = spark_series.get(host.name, {})
sparks = {
k: (sparkline_svg(v[-60:], width=72, height=16) if len(v) >= 2 else "")
for k, v in ser.items()
}
rows.append({
"host": host,
"reg": reg,
"stale": stale,
"cpu_pct": m.get("cpu_pct"),
"mem_used_pct": m.get("mem_used_pct"),
"disk_worst": m.get("disk_used_pct_worst"), # health dot only
"disk_root": root_disk.get(host.name), # displayed at-a-glance
"load_1m": m.get("load_1m"),
"temp_max": m.get("temp_c_max"),
"net_rx_bps": m.get("net_rx_bps"),
"net_tx_bps": m.get("net_tx_bps"),
"disk_read_bps": m.get("disk_read_bps"),
"disk_write_bps": m.get("disk_write_bps"),
"sparks": sparks,
})
rows.sort(key=lambda r: r["host"].name.lower())
return rows
@host_agent_bp.get("/widget")
@require_role(UserRole.viewer)
async def widget_table():
"""Fleet-glance dashboard widget: one row per monitored host, latest metrics."""
async with current_app.db_sessionmaker() as session:
rows = await _fleet_rows(session)
return await render_template("widget_table.html", rows=rows)
@host_agent_bp.get("/widget/history")
@require_role(UserRole.viewer)
async def widget_history():
plugins/host_agent/templates/widget_table.html
-69
View File
@@ -1,69 +0,0 @@
{# host_agent widget — fleet glance. One horizontal row per host, zebra-striped
so adjacent hosts read as distinct groupings: health dot + host name on the
left, metric cells (cpu/mem/disk/load) each with a trend sparkline laid out
horizontally on the right. The name wraps (never hard-truncated) but the row
stays horizontal. #}
{% if rows %}
{% macro metric_cell(label, value, fmt, svg, style="", title="") %}
<div style="min-width:62px;flex:0 0 auto;" title="{{ title }}">
<div style="font-size:0.62rem;color:var(--text-dim);text-transform:uppercase;letter-spacing:0.03em;">{{ label }}</div>
<div style="font-weight:500;font-size:0.8rem;font-variant-numeric:tabular-nums;{{ style }}">
{% if value is not none %}{{ fmt|format(value) }}{% else %}—{% endif %}
</div>
<div style="line-height:0;height:16px;">{{ svg | safe }}</div>
</div>
{% endmacro %}
{# Two-line down/up (or read/write) throughput cell. #}
{% macro io_cell(label, down_sym, down_val, up_sym, up_val, title="") %}
<div style="min-width:80px;flex:0 0 auto;" title="{{ title }}">
<div style="font-size:0.62rem;color:var(--text-dim);text-transform:uppercase;letter-spacing:0.03em;">{{ label }}</div>
<div style="font-size:0.72rem;font-variant-numeric:tabular-nums;line-height:1.3;">
<div>{{ down_sym }} {{ down_val|rate }}</div>
<div>{{ up_sym }} {{ up_val|rate }}</div>
</div>
</div>
{% endmacro %}
<div class="host-fleet">
{% for r in rows %}
{% set stale = r.stale %}
<div style="display:flex;align-items:center;gap:0.6rem 1rem;flex-wrap:wrap;padding:0.5rem 0.6rem;border-radius:4px;{% if loop.index0 % 2 %}background:var(--bg-elevated);{% endif %}">
{# Left — health dot + full host name (wraps, never truncated) + last seen #}
<div style="display:flex;align-items:center;gap:0.5rem;flex:1 1 150px;min-width:120px;">
<span class="dot {% if stale %}dot-dim{% elif (r.cpu_pct or 0) >= 90 or (r.mem_used_pct or 0) >= 90 or (r.disk_worst or 0) >= 90 %}dot-warn{% else %}dot-up{% endif %}"
style="flex-shrink:0;"
title="{% if stale %}stale / no recent data{% else %}warns at CPU/memory ≥90% or any disk mount ≥90% (the 'disk /' figure shows root only){% endif %}"></span>
<span style="min-width:0;">
{% if session.user_id %}
<a href="/hosts/{{ r.host.id }}" style="font-weight:500;font-size:0.85rem;overflow-wrap:anywhere;">{{ r.host.name }}</a>
{% else %}
<span style="font-weight:500;font-size:0.85rem;overflow-wrap:anywhere;">{{ r.host.name }}</span>
{% endif %}
<span style="display:block;font-size:0.7rem;color:var(--text-dim);">
{% if r.reg.last_seen_at %}seen {{ r.reg.last_seen_at|ago }}{% else %}never seen{% endif %}
</span>
</span>
</div>
{# Right — metric cells with value + trend, laid out horizontally #}
<div style="display:flex;flex-wrap:wrap;gap:0.4rem 1rem;justify-content:flex-end;">
{{ metric_cell("cpu", r.cpu_pct, "%.0f%%", r.sparks.cpu, threshold_style(r.cpu_pct, 'cpu'), "Average CPU utilization") }}
{{ metric_cell("mem", r.mem_used_pct, "%.0f%%", r.sparks.mem, threshold_style(r.mem_used_pct, 'mem'), "Memory in use") }}
{{ metric_cell("disk /", r.disk_root, "%.0f%%", r.sparks.disk, threshold_style(r.disk_root, 'disk'), "Root filesystem (/) usage") }}
{{ metric_cell("load", r.load_1m, "%.2f", r.sparks.load, "", "Load average (1m)") }}
{# Extra agent metrics — shown only when the host reports them (VMs/containers
often have no temp sensor, etc.) so absent data doesn't clutter the row. #}
{% if r.net_rx_bps is not none or r.net_tx_bps is not none %}
{{ io_cell("net", "↓", r.net_rx_bps, "↑", r.net_tx_bps, "Network throughput (down / up)") }}
{% endif %}
{% if r.disk_read_bps is not none or r.disk_write_bps is not none %}
{{ io_cell("disk i/o", "rd", r.disk_read_bps, "wr", r.disk_write_bps, "Disk I/O (read / write)") }}
{% endif %}
{% if r.temp_max is not none %}
{{ metric_cell("temp", r.temp_max, "%.0f°C", "", threshold_style(r.temp_max, 'temp'), "Hottest sensor") }}
{% endif %}
</div>
</div>
{% endfor %}
</div>
{% else %}
<p class="empty" style="padding:0.5rem 0;font-size:0.85rem;">No hosts with agent data yet.</p>
{% endif %}