jcoffey-dev
9435115ab7
Saved, shareable multi-panel dashboards (table/line/bar/single-stat panels via gridstack + uPlot, global + per-panel time range, JSON export/import) and threshold/absence alert rules with an ok/pending/firing evaluator and webhook/Slack/PagerDuty delivery. - New /metadata component: Postgres control-plane store for dashboards, panels, notification targets, alert rules/state, and delivery log -- see docs/phase-3-dashboard-design.md for why ClickHouse's MergeTree family isn't a fit for this access pattern (needs real row-level locking and read-your-writes consistency). - api/internal/dashboards: dashboard/panel CRUD, pure -- panel query execution stays client-side, reusing the existing /query endpoint. - New /alerting service: rule/target CRUD, a ticker-driven evaluator (claim-then-evaluate concurrency control, transactional-outbox delivery, query errors and threshold zero-rows never coerced into a false transition) and webhook/Slack/PagerDuty delivery with retry/backoff. See docs/phase-3-alerting-design.md for the full state-machine design and the four correctness properties it implements. - web: /dashboards and /alerts UIs; cli: sentryctl dashboards/alerts list/get/apply, seeding a future Terraform provider's JSON contract. - hack/alert-load-test: 500 rules against real ClickHouse data, real measured results in docs/phase-3-runbook.md. Five real bugs found by actually running this against a live stack (documented in the runbook, not just fixed silently): a latent Phase 2 bug where ClickHouse rejected the timestamp format used for earliest=/latest= queries; a "now" literal token injected into query text; a GridStack/uPlot layout-timing race; JS's Date.parse being too lenient to use as a timestamp-detection heuristic; a rule's "enabled" field silently defaulting to false when omitted; and the evaluator's claim-batch-size and worker-pool-concurrency defaulting to the same value, causing 500 concurrently-due rules to take 125s to cycle through instead of the configured 60s.
89 lines
2.8 KiB
Go
89 lines
2.8 KiB
Go
package delivery
|
|
|
|
import (
|
|
"encoding/json"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/sentry/sentry/alerting/internal/notifystore"
|
|
)
|
|
|
|
func TestBuildPayloadGenericDefaultShape(t *testing.T) {
|
|
target := notifystore.Target{Kind: notifystore.KindWebhook}
|
|
value := 142.0
|
|
payload, err := BuildPayload(target, Event{
|
|
RuleID: "r1", RuleName: "High error rate", EventType: "firing",
|
|
Value: &value, Timestamp: time.Date(2026, 8, 14, 0, 0, 0, 0, time.UTC),
|
|
})
|
|
if err != nil {
|
|
t.Fatalf("BuildPayload: %v", err)
|
|
}
|
|
var got defaultGenericPayload
|
|
if err := json.Unmarshal(payload, &got); err != nil {
|
|
t.Fatalf("unmarshaling payload: %v", err)
|
|
}
|
|
if got.RuleName != "High error rate" || got.EventType != "firing" || got.Value == nil || *got.Value != 142.0 {
|
|
t.Fatalf("unexpected payload: %+v", got)
|
|
}
|
|
}
|
|
|
|
func TestBuildPayloadGenericUsesTemplate(t *testing.T) {
|
|
tmpl := `{"custom": "{{.RuleName}} is {{.EventType}}"}`
|
|
target := notifystore.Target{Kind: notifystore.KindWebhook, PayloadTemplate: &tmpl}
|
|
payload, err := BuildPayload(target, Event{RuleName: "disk full", EventType: "firing"})
|
|
if err != nil {
|
|
t.Fatalf("BuildPayload: %v", err)
|
|
}
|
|
var got map[string]string
|
|
if err := json.Unmarshal(payload, &got); err != nil {
|
|
t.Fatalf("unmarshaling templated payload: %v", err)
|
|
}
|
|
if got["custom"] != "disk full is firing" {
|
|
t.Fatalf("got %q", got["custom"])
|
|
}
|
|
}
|
|
|
|
func TestBuildPayloadSlackShape(t *testing.T) {
|
|
target := notifystore.Target{Kind: notifystore.KindSlack}
|
|
payload, err := BuildPayload(target, Event{RuleName: "High error rate", EventType: "resolved"})
|
|
if err != nil {
|
|
t.Fatalf("BuildPayload: %v", err)
|
|
}
|
|
var got slackPayload
|
|
if err := json.Unmarshal(payload, &got); err != nil {
|
|
t.Fatalf("unmarshaling slack payload: %v", err)
|
|
}
|
|
if got.Text == "" {
|
|
t.Fatalf("expected non-empty Slack text")
|
|
}
|
|
}
|
|
|
|
func TestBuildPayloadPagerDutyMapsEventActionAndRoutingKey(t *testing.T) {
|
|
secret := "R0UT1NGKEY"
|
|
target := notifystore.Target{Kind: notifystore.KindPagerDuty, Secret: &secret}
|
|
|
|
firing, err := BuildPayload(target, Event{RuleID: "r1", RuleName: "disk full", EventType: "firing"})
|
|
if err != nil {
|
|
t.Fatalf("BuildPayload firing: %v", err)
|
|
}
|
|
var gotFiring pagerDutyPayload
|
|
if err := json.Unmarshal(firing, &gotFiring); err != nil {
|
|
t.Fatalf("unmarshaling: %v", err)
|
|
}
|
|
if gotFiring.EventAction != "trigger" || gotFiring.RoutingKey != secret || gotFiring.DedupKey != "r1" {
|
|
t.Fatalf("unexpected firing payload: %+v", gotFiring)
|
|
}
|
|
|
|
resolved, err := BuildPayload(target, Event{RuleID: "r1", RuleName: "disk full", EventType: "resolved"})
|
|
if err != nil {
|
|
t.Fatalf("BuildPayload resolved: %v", err)
|
|
}
|
|
var gotResolved pagerDutyPayload
|
|
if err := json.Unmarshal(resolved, &gotResolved); err != nil {
|
|
t.Fatalf("unmarshaling: %v", err)
|
|
}
|
|
if gotResolved.EventAction != "resolve" {
|
|
t.Fatalf("expected event_action=resolve, got %q", gotResolved.EventAction)
|
|
}
|
|
}
|