dashboard: fix what a real fleet showed, which tests could not
Some checks failed
CI / backend (push) Failing after 8s
CI / naming (push) Successful in 2s
CI / frontend (push) Successful in 10s
CI / migrations-mysql (push) Failing after 7s

Three faults, visible only once the board ran against production data.

BACKUPS SAID THE WHOLE FLEET HAD STOPPED. The lastseenat backfill was wrong. It
seeded from collectedat, reasoning that the last change was the last provable
moment - but an unchanged config writes no revision, so a machine whose settings
last changed nine months ago got a nine-month-old lastseenat and was instantly
reported as a dead backup. Every chain lit up at once, which is worse than no
card: it says the site is broken when it is fine.

The honest value is NULL. Before the column existed nothing recorded when a
config was last confirmed, and inventing a date does not change that. Migration
0003 clears the backfill, and staleness now IGNORES a NULL chain rather than
substituting timestamps that mean something else. A chain becomes measurable the
first time its PC posts, which for NTLARS is within a day.

TONER READ "None%". The supply dict has no 'percent' key - it is 'remaining'.
Supply names are also shortened, because "Black Toner Level 4%" spends three
words saying what the card already says.

THE CARDS READ AS WALLS OF TEXT. Rows wrapped into paragraphs and a card with
forty PCs pushed everything below it off the screen. Now: at most five rows with
"and N more", one line per row that truncates rather than wraps, meta pushed
right and dropped first since it matters least, and severity reduced to a small
dot beside an uppercase label instead of a coloured card - six severity-painted
cards read as a crisis, which is how a board stops being read.

Worth recording that none of this could fail in a test. Every one needed real
data on a real fleet.
This commit is contained in:
cproudlock
2026-08-11 14:45:28 -04:00
parent 5eb84873e8
commit e0e4cce8bd
7 changed files with 188 additions and 37 deletions

View File

@@ -7,6 +7,7 @@
:class="'dc-' + (card.severity || 'info')"
>
<header class="dc-head">
<span class="dc-dot" aria-hidden="true"></span>
<h3 class="dc-title">{{ card.title }}</h3>
<span v-if="card.render !== 'metric'" class="dc-count">{{ countOf(card) }}</span>
</header>
@@ -14,20 +15,23 @@
<!-- metric: the count IS the story -->
<p v-if="card.render === 'metric'" class="dc-metric">{{ metricValue(card) }}</p>
<!-- exceptions / list: things that need a person, each linking to itself -->
<!-- exceptions / list: one line per thing, each linking to itself -->
<ul v-else class="dc-rows">
<li v-for="(row, index) in cardRows(card)" :key="index" class="dc-row">
<li v-for="(row, index) in visibleRows(card)" :key="index" class="dc-row">
<router-link v-if="row.link" :to="row.link" class="dc-row-title">
{{ row.title }}
</router-link>
<span v-else class="dc-row-title dc-row-nolink">{{ row.title }}</span>
<span v-if="row.detail" class="dc-row-detail">{{ row.detail }}</span>
<span v-for="(meta, m) in row.meta" :key="m" class="dc-row-meta"
:class="{ mono: meta.mono }">{{ meta.text }}</span>
<span v-if="row.meta.length" class="dc-row-meta">
{{ row.meta.map((m) => m.text).join(' / ') }}
</span>
</li>
</ul>
<p v-if="!hasRows(card)" class="dc-clear">Nothing to action.</p>
<p v-if="overflowCount(card)" class="dc-more">
and {{ overflowCount(card) }} more
</p>
</section>
</div>
</template>
@@ -45,7 +49,7 @@ import { ref, computed, onMounted } from 'vue'
import api from '../api'
import { useAuthStore } from '@/stores/auth'
import {
toApiPath, cardRows, metricValue, cardVisible, sortCards,
toApiPath, visibleRows, overflowCount, metricValue, cardVisible, sortCards,
permittedCards, renderableCards, rows as cardData,
} from './dashboardCards'
@@ -54,10 +58,6 @@ const cards = ref([])
const visibleCards = computed(() => sortCards(cards.value.filter(cardVisible)))
function hasRows(card) {
return card.render === 'metric' ? metricValue(card) > 0 : cardData(card).length > 0
}
function countOf(card) {
return cardData(card).length
}
@@ -93,35 +93,97 @@ defineExpose({ load })
<style scoped>
.dc-grid {
display: grid;
grid-template-columns: repeat(auto-fill, minmax(20rem, 1fr));
grid-template-columns: repeat(auto-fill, minmax(22rem, 1fr));
gap: 1rem;
margin-bottom: 1.5rem;
margin-bottom: 1.75rem;
align-items: start;
}
.dc-card {
background: var(--bg-card);
border: 1px solid var(--border);
border-left-width: 4px;
border-radius: 8px;
padding: 0.9rem 1rem;
padding: 0.85rem 1rem 0.9rem;
}
/* Severity is carried by the left edge only. A fully coloured card reads as an
alert even when it holds one minor row, and six of them read as a crisis. */
.dc-critical { border-left-color: var(--danger); }
.dc-warning { border-left-color: var(--warning); }
.dc-info { border-left-color: var(--primary); }
.dc-head { display: flex; align-items: baseline; justify-content: space-between; gap: 0.5rem; }
.dc-title { margin: 0; font-size: 0.95rem; font-weight: 600; color: var(--text); }
.dc-count { font-size: 0.8rem; color: var(--text-light); }
.dc-metric { margin: 0.4rem 0 0; font-size: 2rem; font-weight: 600; color: var(--text); }
/* Severity is a small dot beside the title, not a coloured card or a thick
bar. A card painted by severity reads as an alert even when it holds one
minor row, and six of them read as a crisis - which is how a board stops
being read at all. */
.dc-dot { width: 0.5rem; height: 0.5rem; border-radius: 50%; flex: none; }
.dc-critical .dc-dot { background: var(--danger); }
.dc-warning .dc-dot { background: var(--warning); }
.dc-info .dc-dot { background: var(--primary); }
.dc-rows { list-style: none; margin: 0.6rem 0 0; padding: 0; display: flex; flex-direction: column; gap: 0.5rem; }
.dc-row { display: flex; flex-wrap: wrap; align-items: baseline; gap: 0.5rem; font-size: 0.85rem; }
.dc-row-title { font-weight: 600; color: var(--link); text-decoration: none; }
.dc-head {
display: flex;
align-items: center;
gap: 0.5rem;
padding-bottom: 0.55rem;
border-bottom: 1px solid var(--border);
}
.dc-title {
margin: 0;
font-size: 0.8rem;
font-weight: 600;
letter-spacing: 0.02em;
text-transform: uppercase;
color: var(--text-light);
flex: 1;
}
.dc-count {
font-size: 0.8rem;
font-weight: 600;
color: var(--text);
font-variant-numeric: tabular-nums;
}
.dc-metric { margin: 0.5rem 0 0; font-size: 2rem; font-weight: 600; color: var(--text); }
/* One row per line, not a wrapped paragraph. Each row is title / detail /
meta on a single line that truncates, so ten rows are ten scannable lines
rather than a block of text that has to be read. */
.dc-rows { list-style: none; margin: 0; padding: 0; }
.dc-row {
display: flex;
align-items: baseline;
gap: 0.5rem;
padding: 0.4rem 0;
border-bottom: 1px solid var(--border);
font-size: 0.85rem;
min-width: 0;
}
.dc-row:last-child { border-bottom: none; }
.dc-row-title {
font-weight: 600;
color: var(--link);
text-decoration: none;
flex: none;
max-width: 45%;
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
}
.dc-row-title:hover { text-decoration: underline; }
.dc-row-nolink { color: var(--text); }
.dc-row-detail { color: var(--text); }
.dc-row-meta { color: var(--text-light); }
.dc-row-meta.mono { font-family: ui-monospace, Menlo, Consolas, monospace; }
.dc-clear { margin: 0.5rem 0 0; font-size: 0.85rem; color: var(--text-light); }
.dc-row-detail {
color: var(--text);
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
}
/* Meta is pushed right and allowed to disappear first: it is the least
important part of the line, and letting it wrap is what made rows look
like paragraphs. */
.dc-row-meta {
margin-left: auto;
padding-left: 0.5rem;
color: var(--text-light);
font-size: 0.8rem;
white-space: nowrap;
flex: none;
}
.dc-more {
margin: 0.5rem 0 0;
font-size: 0.8rem;
color: var(--text-light);
}
</style>

View File

@@ -75,6 +75,20 @@ export function mapLink(card, item) {
return missing ? null : href
}
// How many rows a card shows before collapsing the rest behind a count. A card
// listing forty PCs is a report someone has to read, not a board someone can
// scan - and it pushes every card below it off the screen. Five is enough to
// see the shape of the problem; the link goes to the full list.
export const MAXROWS = 5
export function visibleRows(card) {
return cardRows(card).slice(0, MAXROWS)
}
export function overflowCount(card) {
return Math.max(0, rows(card).length - MAXROWS)
}
export function cardRows(card) {
return rows(card).map((item) => ({
title: mapTitle(card, item),

View File

@@ -2,6 +2,7 @@ import { describe, it, expect } from 'vitest'
import {
toApiPath, rows, mapMeta, mapLink, cardRows, metricValue,
cardVisible, sortCards, permittedCards, renderableCards,
visibleRows, overflowCount,
} from './dashboardCards'
const failuresCard = {
@@ -77,6 +78,24 @@ describe('mapping a row', () => {
})
})
describe('long lists', () => {
const many = (n) => ({
render: 'exceptions',
map: { title: 'hostname' },
_data: Array.from({ length: n }, (_v, i) => ({ hostname: `PC${i}` })),
})
it('shows at most five rows so one card cannot bury the rest', () => {
expect(visibleRows(many(40))).toHaveLength(5)
expect(overflowCount(many(40))).toBe(35)
})
it('does not claim an overflow when everything fits', () => {
expect(visibleRows(many(3))).toHaveLength(3)
expect(overflowCount(many(3))).toBe(0)
})
})
describe('empty handling', () => {
it('hides a card with nothing to report by default', () => {
// The whole point: a card saying "nothing wrong" daily trains people to

View File

@@ -0,0 +1,38 @@
"""backups: clear the backfilled lastseenat - it was a guess, and it showed.
0002 added lastseenat and backfilled it from collectedat, reasoning that the
last change was the last moment the config could be PROVEN current. On a fleet
that was wrong in practice: an unchanged config writes no revision, so a machine
whose settings last changed nine months ago got a nine-month-old lastseenat and
was immediately reported as a stopped backup. Every chain lit up at once, which
is worse than no card - it says the fleet is broken when it is fine.
The honest value is NULL: before this column existed, nothing recorded when a
config was last confirmed, and inventing a date does not change that. A chain
becomes measurable the first time its PC posts after the upgrade, which for
NTLARS is within a day.
So staleness now IGNORES a chain whose lastseenat is NULL, rather than falling
back to timestamps that mean something else.
"""
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision = 'backups0003clearlastseen'
down_revision = 'backups0002lastseenat'
branch_labels = None
depends_on = None
def upgrade():
columns = {c['name'] for c in
sa.inspect(op.get_bind()).get_columns('backuprevisions')}
if 'lastseenat' in columns:
op.execute('UPDATE backuprevisions SET lastseenat = NULL')
def downgrade():
# Nothing to restore: the backfilled values were derived, not recorded.
pass

View File

@@ -65,10 +65,14 @@ def stalechains(days=None, limit=50):
rows = []
for revision in latestperchain().values():
# Rows written before lastseenat existed fall back to the timestamps
# that do exist, so an old install reports something sane on day one
# rather than every chain at once.
seen = revision.lastseenat or revision.collectedat or revision.createdat
# NULL means never confirmed since the column existed, and it is NOT
# substituted with collectedat. That substitution is what the first
# version did, and on a real fleet it reported every machine whose
# config had simply been stable for months as a stopped backup - the
# whole board lit up and said the site was broken when it was fine.
# A chain becomes measurable the first time its PC posts; until then
# this card says nothing about it, which is the truth.
seen = revision.lastseenat
if seen is None or seen >= cutoff:
continue
asset = db.session.get(Asset, revision.assetid)

View File

@@ -1395,6 +1395,18 @@ def delete_model_supply(modelsupplyid: int):
return success_response(message='Supply deleted')
def _shortsupplyname(name):
"""'Black Toner Level' -> 'Black'. The card has one line per printer, and
the words Toner and Level carry no information when every row is a toner
level."""
text = (name or 'supply').strip()
for noise in (' Cartridge Level', ' Toner Level', ' Level', ' Cartridge'):
if text.endswith(noise):
text = text[:-len(noise)]
break
return text or 'supply'
@printers_asset_bp.route('/dashboard/supplies', methods=['GET'])
@jwt_required()
@require_permission('printers.view')
@@ -1426,9 +1438,11 @@ def dashboard_supplies():
'printername': printer['printername'] or printer['assetnumber'],
'location': printer['location'],
'status': 'critical' if criticals else 'low',
# 'remaining' is the percent left. There is no 'percent' key -
# reading one rendered every cartridge as "None%" on the board.
'supplies': ', '.join(
'{} {}%'.format(s.get('name') or s.get('type') or 'supply',
s.get('percent'))
'{} {}%'.format(_shortsupplyname(s.get('name')),
s.get('remaining'))
for s in worst),
'iscritical': bool(criticals),
})

View File

@@ -49,7 +49,7 @@ EXPECTED_HEAD_REVISION['measuringtools'] = 'measuringtools0001baseline'
# backups is also post-cutover: its 0001 really creates backuprevisions, and
# 0002 adds lastseenat - when a config was last CONFIRMED unchanged, which dedup
# otherwise throws away.
EXPECTED_HEAD_REVISION['backups'] = 'backups0002lastseenat'
EXPECTED_HEAD_REVISION['backups'] = 'backups0003clearlastseen'
# geenforce adds the content-addressed blob store (manifestblobs) on top of its
# baseline.
EXPECTED_HEAD_REVISION['geenforce'] = 'geenforce0002blobs'