Give each team its own dead man's switches, and the UI a team to show
CI / chart (pull_request) Successful in 1s
CI / security (pull_request) Successful in 14s
CI / test (pull_request) Successful in 1m57s

The rest of #4. Two halves that belong together because they are the
same sentence from opposite ends: a team decides which of its alerts are
heartbeats, and the UI has to be able to say which team it is talking
about.

Switches were three environment variables, which made them one setting
for the whole install. That was the last piece of the alerting path a
team could not control: it could take its own alerts on its own key and
still not say which of them were heartbeats, or how long a silence had
to last. They are a row per team now, edited by an owner through
PUT /api/teams/{teamID}/deadman, and the sweeper runs each team against
its own matchers, timeout and severity.

The environment variables become the starting point rather than the
setting. Every team without a configuration is seeded from them at
startup, so an upgrade keeps watching exactly what it was watching, and
SeedDeadmanConfigs never overwrites -- a redeploy must not put the
environment's value back over an owner's edit. A team created later
watches nothing until somebody says otherwise: inheriting an
install-wide heartbeat would page a new team about a source it has never
heard of, and a switch nobody chose is the kind that gets muted rather
than fixed.

A matcher string with no alertname in it is refused at the door instead
of stored. Storing it would produce a switch that watches nothing
silently, which is the exact failure the feature exists to prevent.

NewRouter and Sweep lose their DeadmanConfig parameter -- there is no
longer one answer to hand them. The type stays, because parsing a
matcher string is still parsing a matcher string.

The UI side: rows in the queue carry a team badge, the filter row gains
a team chip per team, and "on call now" shows one card per team. All
three appear only when the viewer is in more than one team -- otherwise
they are the same word repeated down a list, which is noise rather than
information, and the single-team install reads exactly as it did before
teams existed.

Verified against a live two-team server as well as in tests: the
combined queue labelled by team, the team_id filter, a heartbeat that is
a heartbeat in one team and an ordinary alert in another, and a new
team's switches starting empty while the upgraded team keeps the
environment's.

Claude-Session: https://claude.ai/code/session_01RHPj4ggeFdEjKKfm4SHbD7
This commit is contained in:
Niklas Ye
2026-09-20 15:18:22 +02:00
parent a4fbd60441
commit 74359c72ab
15 changed files with 579 additions and 58 deletions
+62 -3
View File
@@ -26,12 +26,32 @@ const EMPTY = {
};
let filter = loadFilter();
let teamFilter = loadTeamFilter(); // '' for every team the viewer is in
let items = null; // null while loading
let error = null;
let selected = null;
let cursor = -1; // keyboard position in the list
let built = false;
function loadTeamFilter() {
try {
return sessionStorage.getItem('terdut.queue.team') || '';
} catch {
return '';
}
}
function setTeamFilter(id) {
teamFilter = id;
try {
sessionStorage.setItem('terdut.queue.team', id);
} catch {
/* storage unavailable */
}
renderChips();
refresh({ fresh: true });
}
function loadFilter() {
try {
const f = sessionStorage.getItem('terdut.queue.filter');
@@ -64,7 +84,11 @@ export async function refresh({ fresh = false } = {}) {
const requested = filter;
try {
// The open list is already fetched for the badges; no need to ask twice.
const result = filter === 'open' && !fresh ? state.open : await api.incidents(f.query);
// The cached open queue covers every team, so it can only be reused when
// no team filter is applied.
const query = teamFilter ? { ...f.query, team_id: teamFilter } : f.query;
const cached = filter === 'open' && !fresh && !teamFilter;
const result = cached ? state.open : await api.incidents(query);
if (requested !== filter) return;
items = result;
error = null;
@@ -88,7 +112,7 @@ function setFilter(id) {
function renderChips() {
const el = document.getElementById('queue-filters');
clear(el, FILTERS.map((f) =>
const chips = FILTERS.map((f) =>
h('button', {
class: 'chip',
type: 'button',
@@ -97,7 +121,34 @@ function renderChips() {
onclick: () => setFilter(f.id),
text: f.label,
}),
));
);
// Somebody in one team has nothing to choose between, so the row of team
// chips appears only when there is more than one. The default is all of
// them: the combined queue is the point.
if (state.teams.length > 1) {
chips.push(h('span', { class: 'chip-sep' }));
chips.push(h('button', {
class: 'chip',
type: 'button',
role: 'tab',
'aria-selected': String(teamFilter === ''),
onclick: () => setTeamFilter(''),
text: 'All teams',
}));
for (const team of state.teams) {
chips.push(h('button', {
class: 'chip',
type: 'button',
role: 'tab',
'aria-selected': String(teamFilter === String(team.id)),
onclick: () => setTeamFilter(String(team.id)),
text: team.name,
}));
}
}
clear(el, chips);
}
function renderList() {
@@ -142,6 +193,13 @@ function row(inc, index) {
// The server already puts the group labels in the title; show only the rest.
const labels = labelSummary(Object.fromEntries(
Object.entries(inc.group_labels || {}).filter(([k, v]) => !inc.title.includes(`${k}=${v}`))));
// The team is shown only to somebody who is in more than one. For everybody
// else it is the same word on every row, which is noise rather than
// information.
const team = state.teams.length > 1 && inc.team_name
? h('span', { class: 'row-team', text: inc.team_name })
: null;
return h('a', {
class: `row ${severityClass(inc.severity)} ${resolved ? 'resolved' : ''} ${index === cursor ? 'kbd-focus' : ''}`,
href: `/incidents/${inc.id}`,
@@ -153,6 +211,7 @@ function row(inc, index) {
h('div', { class: 'row-meta' },
status,
assignee,
team,
labels && h('span', { class: 'labels', text: labels }),
),
);