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.
115 lines
3.0 KiB
Go
115 lines
3.0 KiB
Go
// Package notifystore is pgx-backed CRUD for notification_targets.
|
|
package notifystore
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"errors"
|
|
|
|
"github.com/google/uuid"
|
|
"github.com/jackc/pgx/v5"
|
|
"github.com/jackc/pgx/v5/pgxpool"
|
|
)
|
|
|
|
var ErrNotFound = errors.New("not found")
|
|
|
|
type Kind string
|
|
|
|
const (
|
|
KindWebhook Kind = "webhook"
|
|
KindSlack Kind = "slack"
|
|
KindPagerDuty Kind = "pagerduty"
|
|
)
|
|
|
|
func ValidKind(k Kind) bool {
|
|
switch k {
|
|
case KindWebhook, KindSlack, KindPagerDuty:
|
|
return true
|
|
default:
|
|
return false
|
|
}
|
|
}
|
|
|
|
type Target struct {
|
|
ID string `json:"id"`
|
|
TenantID string `json:"tenant_id"`
|
|
Name string `json:"name"`
|
|
Kind Kind `json:"kind"`
|
|
WebhookURL string `json:"webhook_url"`
|
|
PayloadTemplate *string `json:"payload_template,omitempty"`
|
|
Headers json.RawMessage `json:"headers,omitempty"`
|
|
Secret *string `json:"secret,omitempty"`
|
|
CreatedBy string `json:"created_by"`
|
|
}
|
|
|
|
type Store struct {
|
|
pool *pgxpool.Pool
|
|
}
|
|
|
|
func NewStore(pool *pgxpool.Pool) *Store {
|
|
return &Store{pool: pool}
|
|
}
|
|
|
|
func (s *Store) Create(ctx context.Context, t *Target) error {
|
|
t.ID = uuid.NewString()
|
|
if t.TenantID == "" {
|
|
t.TenantID = "default"
|
|
}
|
|
if t.CreatedBy == "" {
|
|
t.CreatedBy = "anonymous"
|
|
}
|
|
if len(t.Headers) == 0 {
|
|
t.Headers = json.RawMessage(`{}`)
|
|
}
|
|
_, err := s.pool.Exec(ctx, `
|
|
INSERT INTO notification_targets (id, tenant_id, name, kind, webhook_url, payload_template, headers, secret, created_by)
|
|
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9)`,
|
|
t.ID, t.TenantID, t.Name, t.Kind, t.WebhookURL, t.PayloadTemplate, t.Headers, t.Secret, t.CreatedBy)
|
|
return err
|
|
}
|
|
|
|
func (s *Store) List(ctx context.Context) ([]Target, error) {
|
|
rows, err := s.pool.Query(ctx, `
|
|
SELECT id, tenant_id, name, kind, webhook_url, payload_template, headers, secret, created_by
|
|
FROM notification_targets ORDER BY created_at DESC`)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer rows.Close()
|
|
|
|
var out []Target
|
|
for rows.Next() {
|
|
var t Target
|
|
if err := rows.Scan(&t.ID, &t.TenantID, &t.Name, &t.Kind, &t.WebhookURL, &t.PayloadTemplate, &t.Headers, &t.Secret, &t.CreatedBy); err != nil {
|
|
return nil, err
|
|
}
|
|
out = append(out, t)
|
|
}
|
|
return out, rows.Err()
|
|
}
|
|
|
|
func (s *Store) Get(ctx context.Context, id string) (*Target, error) {
|
|
var t Target
|
|
row := s.pool.QueryRow(ctx, `
|
|
SELECT id, tenant_id, name, kind, webhook_url, payload_template, headers, secret, created_by
|
|
FROM notification_targets WHERE id = $1`, id)
|
|
if err := row.Scan(&t.ID, &t.TenantID, &t.Name, &t.Kind, &t.WebhookURL, &t.PayloadTemplate, &t.Headers, &t.Secret, &t.CreatedBy); err != nil {
|
|
if errors.Is(err, pgx.ErrNoRows) {
|
|
return nil, ErrNotFound
|
|
}
|
|
return nil, err
|
|
}
|
|
return &t, nil
|
|
}
|
|
|
|
func (s *Store) Delete(ctx context.Context, id string) error {
|
|
tag, err := s.pool.Exec(ctx, `DELETE FROM notification_targets WHERE id = $1`, id)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if tag.RowsAffected() == 0 {
|
|
return ErrNotFound
|
|
}
|
|
return nil
|
|
}
|