Show notes from similar earlier incidents

Each incident gets a signature: the alert name plus the group labels that
say what is broken, minus the ones that only say where it ran (instance,
pod, container, ...). GET /api/incidents/{id}/similar returns resolved
incidents in the same team with the same signature that have notes.

Notes can be marked as the resolution note, "what fixed it", either with a
resolution field on resolve or pinned on a note. Those lead the similar
list, show on the incident page as "Seen before", and the triggered
notification carries the latest one.

Claude-Session: https://claude.ai/code/session_01MMados3BD1oSjevHxbmVqU
This commit is contained in:
Niklas Ye
2026-09-25 15:42:25 +02:00
parent 734cd9c5fd
commit 60ebb75cd2
12 changed files with 400 additions and 23 deletions
+113
View File
@@ -0,0 +1,113 @@
package api
import (
"context"
"database/sql"
"net/http"
"strconv"
"time"
"git.ryuvia.com/niklas/terdut-server/internal/models"
)
const (
similarDefaultLimit = 5
similarMaxLimit = 20
)
// handleIncidentSimilar lists earlier, resolved incidents in the same team with
// the same signature that someone left notes on, incidents with a resolution
// note first. This is the "have we seen this before" answer for a responder
// looking at a fresh incident; the plain notes are one timeline fetch away.
func handleIncidentSimilar(db *sql.DB) http.HandlerFunc {
return func(w http.ResponseWriter, r *http.Request) {
id, ok := incidentIDParam(w, r, db)
if !ok {
return
}
limit := similarDefaultLimit
if v := r.URL.Query().Get("limit"); v != "" {
n, err := strconv.Atoi(v)
if err != nil || n < 1 {
respond(w, http.StatusBadRequest, errResp("invalid limit"))
return
}
limit = min(n, similarMaxLimit)
}
out, err := similarIncidents(r.Context(), db, id, limit)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
return
}
respond(w, http.StatusOK, out)
}
}
func similarIncidents(ctx context.Context, q querier, id int64, limit int) ([]models.SimilarIncident, error) {
rows, err := q.QueryContext(ctx, `
SELECT o.id, o.title, o.triggered_at, o.resolved_at,
(SELECT COUNT(*) FROM incident_events e
WHERE e.incident_id = o.id AND e.type = $3)
FROM incidents i
JOIN incidents o ON o.team_id = i.team_id AND o.signature = i.signature
WHERE i.id = $1 AND o.id <> i.id AND o.resolved_at IS NOT NULL
AND EXISTS (SELECT 1 FROM incident_events e
WHERE e.incident_id = o.id AND e.type IN ($3, $4))
ORDER BY EXISTS (SELECT 1 FROM incident_events e
WHERE e.incident_id = o.id AND e.type = $4) DESC,
o.triggered_at DESC
LIMIT $2`, id, limit, evNote, evResolutionNote)
if err != nil {
return nil, err
}
defer rows.Close()
out := []models.SimilarIncident{}
ids := []int64{}
for rows.Next() {
var s models.SimilarIncident
var triggered, resolved int64
if err := rows.Scan(&s.ID, &s.Title, &triggered, &resolved, &s.NoteCount); err != nil {
return nil, err
}
s.TriggeredAt = time.Unix(triggered, 0).UTC()
s.ResolvedAt = time.Unix(resolved, 0).UTC()
s.ResolutionNotes = []models.IncidentEvent{}
out = append(out, s)
ids = append(ids, s.ID)
}
if err := rows.Err(); err != nil {
return nil, err
}
if len(out) == 0 {
return out, nil
}
nrows, err := q.QueryContext(ctx, `
SELECT e.id, e.incident_id, e.type, e.user_id, u.username, e.detail, e.created_at
FROM incident_events e
LEFT JOIN users u ON u.id = e.user_id
WHERE e.incident_id = ANY($1) AND e.type = $2
ORDER BY e.created_at, e.id`, ids, evResolutionNote)
if err != nil {
return nil, err
}
defer nrows.Close()
byID := make(map[int64]*models.SimilarIncident, len(out))
for i := range out {
byID[out[i].ID] = &out[i]
}
for nrows.Next() {
var e models.IncidentEvent
var ts int64
if err := nrows.Scan(&e.ID, &e.IncidentID, &e.Type, &e.UserID, &e.Username, &e.Detail, &ts); err != nil {
return nil, err
}
e.CreatedAt = time.Unix(ts, 0).UTC()
s := byID[e.IncidentID]
s.ResolutionNotes = append(s.ResolutionNotes, e)
}
return out, nrows.Err()
}