3183e7e5c5
Closes #6, and closes the thing this whole line of work was opened for. Until now an unacknowledged incident re-paged the same topic every notify_repeat forever, which is a louder version of the same silence: if the person on call is asleep, out of signal or has left the company, nothing else happened. A team can now configure an ordered ladder. Each level has a timeout and a set of targets; a target is a named person or whoever the team's rota says is on call today. That second kind is the one that keeps working when the rota changes and nobody remembers to edit the policy. When a level's timeout passes with the incident still triggered, the next level is paged; off the end the chain repeats repeat_count times and then the team's fallback topic is paged once. The incident stays open throughout, because running out of people to wake is not somebody answering. Escalation rides the notifier's existing 30-second tick and its outbox rather than adding a second scheduler, and runs before delivery so a level that comes due on a tick is paged on that tick. Each target gets its own outbox row and therefore its own Acknowledge token: the button in a notification must acknowledge as the person holding the phone, not as whoever was paged first. Acknowledging or resolving takes the incident off the ladder. Snoozing pauses it -- a deliberate "not now" holds the ladder where it is and it resumes when the snooze runs out, rather than carrying on without the person who asked for quiet. Reminders and escalation never both run. A team with a ladder gets escalation; a team without keeps today's behaviour exactly. Both would mean two pages for one silence, which is how a tool gets muted. A level whose targets cannot be reached -- no topic, a disabled account, an empty rota -- is entered anyway, recorded as "nobody reachable", and the ladder moves on. Stalling on a rung that cannot ring would be the failure this feature exists to prevent, wearing the feature's clothes. A policy with such a level cannot be created, but an older row could hold one. The API replaces the ladder wholesale rather than patching a rung, because the levels are an order: editing one has to answer what happens to the numbering of the others, and a whole-ladder PUT makes that the client's decision and the edit atomic. Verified against a live server as well as in tests: alice paged, nobody answers, bob paged, nobody answers, the fallback topic paged once and the timeline reading "level 2: bob" then "escalation exhausted: paged terdut-oncall-all" -- and a second incident acknowledged before its timeout, which woke nobody else. No UI yet. The team-settings screens for escalation, integrations and dead man's switches are all still missing, and they are one piece of work rather than three. Claude-Session: https://claude.ai/code/session_01RHPj4ggeFdEjKKfm4SHbD7
314 lines
10 KiB
Go
314 lines
10 KiB
Go
package api
|
|
|
|
import (
|
|
"context"
|
|
"database/sql"
|
|
"encoding/json"
|
|
"sort"
|
|
"strings"
|
|
"time"
|
|
|
|
"git.ryuvia.com/niklas/terdut-server/internal/models"
|
|
)
|
|
|
|
// Values for incidents.resolution_source, recording who closed the incident:
|
|
// every member alert stopped firing, or a person decided it was done.
|
|
const (
|
|
incidentResolutionAlerts = "alerts"
|
|
incidentResolutionManual = "manual"
|
|
|
|
// incidentResolutionRecovered closes a dead man's switch incident whose
|
|
// heartbeat started arriving again. It cannot be "alerts": these incidents
|
|
// have no member alerts for the cascade to work from.
|
|
incidentResolutionRecovered = "recovered"
|
|
)
|
|
|
|
// Incident timeline event types. Stored as free text so adding one later is not
|
|
// a migration, but these are the ones the server writes.
|
|
const (
|
|
evTriggered = "triggered"
|
|
evAlertAdded = "alert_added"
|
|
evAlertResolved = "alert_resolved"
|
|
evAcknowledged = "acknowledged"
|
|
evUnacknowledged = "unacknowledged"
|
|
evAssigned = "assigned"
|
|
evSnoozed = "snoozed"
|
|
evUnsnoozed = "unsnoozed"
|
|
evResolved = "resolved"
|
|
evNote = "note"
|
|
evDeadmanSilent = "deadman_silent"
|
|
)
|
|
|
|
// severityLabel is the Alertmanager label an incident's severity is derived from.
|
|
const severityLabel = "severity"
|
|
|
|
// querier is satisfied by both *sql.DB and *sql.Tx, so the helpers below work
|
|
// inside the webhook's transaction and standalone from handlers and the sweeper.
|
|
type querier interface {
|
|
ExecContext(ctx context.Context, query string, args ...any) (sql.Result, error)
|
|
QueryContext(ctx context.Context, query string, args ...any) (*sql.Rows, error)
|
|
QueryRowContext(ctx context.Context, query string, args ...any) *sql.Row
|
|
}
|
|
|
|
const incidentSelectFrom = `
|
|
SELECT i.id, i.team_id, t.name, i.group_key, i.title, i.group_labels, i.status, i.severity,
|
|
i.triggered_at,
|
|
i.acknowledged_by, i.acknowledged_at, ack.username,
|
|
i.assigned_to, asg.username, i.snoozed_until,
|
|
i.resolved_at, i.resolution_source, i.archived_at
|
|
FROM incidents i
|
|
JOIN teams t ON t.id = i.team_id
|
|
LEFT JOIN users ack ON ack.id = i.acknowledged_by
|
|
LEFT JOIN users asg ON asg.id = i.assigned_to`
|
|
|
|
func scanIncident(s scanner) (models.Incident, error) {
|
|
var i models.Incident
|
|
var groupLabelsJSON string
|
|
var triggeredAt int64
|
|
var ackAt, snoozedUntil, resolvedAt, archivedAt *int64
|
|
|
|
if err := s.Scan(
|
|
&i.ID, &i.TeamID, &i.TeamName, &i.GroupKey, &i.Title, &groupLabelsJSON, &i.Status, &i.Severity,
|
|
&triggeredAt,
|
|
&i.AcknowledgedByID, &ackAt, &i.AcknowledgedByUser,
|
|
&i.AssignedToID, &i.AssignedToUser, &snoozedUntil,
|
|
&resolvedAt, &i.ResolutionSource, &archivedAt,
|
|
); err != nil {
|
|
return i, err
|
|
}
|
|
|
|
json.Unmarshal([]byte(groupLabelsJSON), &i.GroupLabels) //nolint:errcheck
|
|
i.TriggeredAt = time.Unix(triggeredAt, 0).UTC()
|
|
i.AcknowledgedAt = unixPtr(ackAt)
|
|
i.SnoozedUntil = unixPtr(snoozedUntil)
|
|
i.ResolvedAt = unixPtr(resolvedAt)
|
|
i.ArchivedAt = unixPtr(archivedAt)
|
|
return i, nil
|
|
}
|
|
|
|
// unixPtr converts a nullable Unix-second column to a nullable UTC time.
|
|
func unixPtr(sec *int64) *time.Time {
|
|
if sec == nil {
|
|
return nil
|
|
}
|
|
t := time.Unix(*sec, 0).UTC()
|
|
return &t
|
|
}
|
|
|
|
func fetchIncident(ctx context.Context, q querier, id int64) (models.Incident, error) {
|
|
return scanIncident(q.QueryRowContext(ctx, incidentSelectFrom+" WHERE i.id = $1", id))
|
|
}
|
|
|
|
// logEvent appends one entry to an incident's timeline. A nil userID means the
|
|
// server acted rather than a person.
|
|
func logEvent(ctx context.Context, q querier, incidentID int64, evType string, userID, alertID *int64, detail *string) error {
|
|
_, err := q.ExecContext(ctx, `
|
|
INSERT INTO incident_events (incident_id, type, user_id, alert_id, detail, created_at)
|
|
VALUES ($1, $2, $3, $4, $5, $6)`,
|
|
incidentID, evType, userID, alertID, detail, time.Now().Unix())
|
|
return err
|
|
}
|
|
|
|
// todayUTC is the schedule's day key. The schedule's smallest unit is one UTC day.
|
|
func todayUTC() string {
|
|
return time.Now().UTC().Format("2006-01-02")
|
|
}
|
|
|
|
// currentOnCall returns a team's on-call user for today, or nil when nobody is
|
|
// scheduled. A missing schedule entry is not an error — incidents just open
|
|
// unassigned.
|
|
//
|
|
// Per team: each team keeps its own rota, so two teams can have two different
|
|
// people on call on the same day, which was the point of scoping the schedule.
|
|
func currentOnCall(ctx context.Context, q querier, teamID int64) (*int64, error) {
|
|
var userID int64
|
|
err := q.QueryRowContext(ctx,
|
|
"SELECT user_id FROM schedule_entries WHERE team_id = $1 AND date = $2",
|
|
teamID, todayUTC()).Scan(&userID)
|
|
if err == sql.ErrNoRows {
|
|
return nil, nil
|
|
}
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
return &userID, nil
|
|
}
|
|
|
|
// severityRank orders the conventional Alertmanager severity label values.
|
|
// Anything unrecognised sorts below all of them rather than being dropped.
|
|
func severityRank(s string) int {
|
|
switch strings.ToLower(s) {
|
|
case "critical":
|
|
return 4
|
|
case "error":
|
|
return 3
|
|
case "warning":
|
|
return 2
|
|
case "info":
|
|
return 1
|
|
default:
|
|
return 0
|
|
}
|
|
}
|
|
|
|
// refreshSeverity raises an incident's severity to the highest `severity` label
|
|
// seen across its alerts.
|
|
//
|
|
// It is a high-water mark, never lowered: an incident that hit critical was a
|
|
// critical incident, even after the critical alert clears and a warning is all
|
|
// that is left firing. Downgrading a live incident would also quietly demote it
|
|
// in the queue while the work is still open.
|
|
func refreshSeverity(ctx context.Context, q querier, incidentID int64) error {
|
|
rows, err := q.QueryContext(ctx, `
|
|
SELECT a.labels ->> $1
|
|
FROM incident_alerts ia
|
|
JOIN alerts a ON a.id = ia.alert_id
|
|
WHERE ia.incident_id = $2`, severityLabel, incidentID)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
best := ""
|
|
for rows.Next() {
|
|
var sev *string
|
|
if err := rows.Scan(&sev); err != nil {
|
|
rows.Close()
|
|
return err
|
|
}
|
|
if sev != nil && severityRank(*sev) > severityRank(best) {
|
|
best = *sev
|
|
}
|
|
}
|
|
if err := rows.Err(); err != nil {
|
|
rows.Close()
|
|
return err
|
|
}
|
|
rows.Close()
|
|
|
|
if best == "" {
|
|
return nil
|
|
}
|
|
// The comparison lives in SQL so an unrelated concurrent update cannot be
|
|
// clobbered by a stale read.
|
|
_, err = q.ExecContext(ctx, `
|
|
UPDATE incidents SET severity = $1
|
|
WHERE id = $2
|
|
AND (severity IS NULL OR `+severityRankSQL("severity")+` < $3)`,
|
|
best, incidentID, severityRank(best))
|
|
return err
|
|
}
|
|
|
|
// severityRankSQL mirrors severityRank for use inside a statement. SQL cannot
|
|
// order these strings meaningfully on its own.
|
|
func severityRankSQL(col string) string {
|
|
return `CASE lower(COALESCE(` + col + `, ''))
|
|
WHEN 'critical' THEN 4
|
|
WHEN 'error' THEN 3
|
|
WHEN 'warning' THEN 2
|
|
WHEN 'info' THEN 1
|
|
ELSE 0 END`
|
|
}
|
|
|
|
// resolveIfSettled closes an incident once every alert under it has stopped
|
|
// firing — PagerDuty's cascade, and the only automatic route out of the open
|
|
// state. Reports whether it actually resolved anything.
|
|
func resolveIfSettled(ctx context.Context, q querier, incidentID int64) (bool, error) {
|
|
res, err := q.ExecContext(ctx, `
|
|
UPDATE incidents
|
|
SET status = 'resolved',
|
|
resolved_at = $1,
|
|
resolution_source = $2
|
|
WHERE id = $3
|
|
AND resolved_at IS NULL
|
|
-- An incident with no members yet is mid-creation, not settled.
|
|
AND EXISTS (SELECT 1 FROM incident_alerts ia WHERE ia.incident_id = incidents.id)
|
|
AND NOT EXISTS (SELECT 1
|
|
FROM incident_alerts ia
|
|
JOIN alerts a ON a.id = ia.alert_id
|
|
WHERE ia.incident_id = incidents.id
|
|
AND a.status = 'firing')`,
|
|
time.Now().Unix(), incidentResolutionAlerts, incidentID)
|
|
if err != nil {
|
|
return false, err
|
|
}
|
|
n, _ := res.RowsAffected()
|
|
if n == 0 {
|
|
return false, nil
|
|
}
|
|
if err := stopEscalation(ctx, q, incidentID); err != nil {
|
|
return false, err
|
|
}
|
|
if err := logEvent(ctx, q, incidentID, evResolved, nil, nil, nil); err != nil {
|
|
return false, err
|
|
}
|
|
// The all-clear goes only to whoever was paged in the first place, which
|
|
// enqueueResolved works out from the incident's own notification history.
|
|
// Manual resolution sends nothing: the person who closed it already knows.
|
|
return true, enqueueResolved(ctx, q, incidentID)
|
|
}
|
|
|
|
// acknowledgeIncident records that userID has picked an incident up, and reports
|
|
// whether it changed anything — an already-resolved incident is left alone.
|
|
// Shared by the authenticated handler and the Acknowledge button in a push
|
|
// notification, so both write the same state and the same timeline entry.
|
|
func acknowledgeIncident(ctx context.Context, q querier, incidentID, userID int64) (bool, error) {
|
|
res, err := q.ExecContext(ctx, `
|
|
UPDATE incidents
|
|
SET status = 'acknowledged', acknowledged_by = $1, acknowledged_at = $2
|
|
WHERE id = $3 AND resolved_at IS NULL`,
|
|
userID, time.Now().Unix(), incidentID)
|
|
if err != nil {
|
|
return false, err
|
|
}
|
|
if n, _ := res.RowsAffected(); n == 0 {
|
|
return false, nil
|
|
}
|
|
// Somebody has it: stop waking anybody else.
|
|
if err := stopEscalation(ctx, q, incidentID); err != nil {
|
|
return false, err
|
|
}
|
|
return true, logEvent(ctx, q, incidentID, evAcknowledged, &userID, nil, nil)
|
|
}
|
|
|
|
// openIncidentForAlert returns the open incident an alert currently belongs to,
|
|
// or 0 when it has none. Used when an alert resolves or expires so the event
|
|
// lands on the right timeline.
|
|
func openIncidentForAlert(ctx context.Context, q querier, alertID int64) (int64, error) {
|
|
var id int64
|
|
err := q.QueryRowContext(ctx, `
|
|
SELECT i.id
|
|
FROM incident_alerts ia
|
|
JOIN incidents i ON i.id = ia.incident_id
|
|
WHERE ia.alert_id = $1 AND i.resolved_at IS NULL`, alertID).Scan(&id)
|
|
if err == sql.ErrNoRows {
|
|
return 0, nil
|
|
}
|
|
return id, err
|
|
}
|
|
|
|
// incidentTitle renders a human-readable title from Alertmanager's groupLabels,
|
|
// leading with the alert name and appending whatever else the operator grouped
|
|
// by. Falls back to the alert's own name when the payload carried no groupLabels.
|
|
func incidentTitle(groupLabels map[string]string, fallback string) string {
|
|
name := groupLabels["alertname"]
|
|
if name == "" {
|
|
name = fallback
|
|
}
|
|
if name == "" {
|
|
name = "Incident"
|
|
}
|
|
|
|
rest := make([]string, 0, len(groupLabels))
|
|
for k, v := range groupLabels {
|
|
if k == "alertname" {
|
|
continue
|
|
}
|
|
rest = append(rest, k+"="+v)
|
|
}
|
|
if len(rest) == 0 {
|
|
return name
|
|
}
|
|
sort.Strings(rest)
|
|
return name + " (" + strings.Join(rest, ", ") + ")"
|
|
}
|