feat: telemetry alert rules with webhook delivery

core.alert_rules (migration 00012) — heartbeat_silence and error_spike rules evaluated by a 60s backend ticker. Transition-based firing: alert.fired on breach, alert.resolved on recovery, both first-class webhook event types riding the signed dispatcher + realtime stream. Dashboard manages rules on the Integrations page. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-28 15:51:23 +00:00 · 2026-09-24 19:09:19 +02:00
1 parent 345cf7918b
commit 2f4de543a9
@@ -0,0 +1,290 @@
+// Code generated by sqlc. DO NOT EDIT.
+// versions:
+//   sqlc v1.29.0
+// source: alert_rules.sql
+
+package db
+
+import (
+	"context"
+
+	"github.com/google/uuid"
+	"github.com/jackc/pgx/v5/pgtype"
+)
+
+const createAlertRule = `-- name: CreateAlertRule :one
+INSERT INTO core.alert_rules (project_id, name, kind, config)
+VALUES ($1, $2, $3, $4)
+RETURNING id, project_id, name, kind, config, enabled, state, created_at, updated_at
+`
+
+type CreateAlertRuleParams struct {
+	ProjectID uuid.UUID `json:"project_id"`
+	Name      string    `json:"name"`
+	Kind      string    `json:"kind"`
+	Config    []byte    `json:"config"`
+}
+
+func (q *Queries) CreateAlertRule(ctx context.Context, arg CreateAlertRuleParams) (CoreAlertRule, error) {
+	row := q.db.QueryRow(ctx, createAlertRule,
+		arg.ProjectID,
+		arg.Name,
+		arg.Kind,
+		arg.Config,
+	)
+	var i CoreAlertRule
+	err := row.Scan(
+		&i.ID,
+		&i.ProjectID,
+		&i.Name,
+		&i.Kind,
+		&i.Config,
+		&i.Enabled,
+		&i.State,
+		&i.CreatedAt,
+		&i.UpdatedAt,
+	)
+	return i, err
+}
+
+const deleteAlertRule = `-- name: DeleteAlertRule :exec
+DELETE FROM core.alert_rules
+WHERE id = $1 AND project_id = $2
+`
+
+type DeleteAlertRuleParams struct {
+	ID        uuid.UUID `json:"id"`
+	ProjectID uuid.UUID `json:"project_id"`
+}
+
+func (q *Queries) DeleteAlertRule(ctx context.Context, arg DeleteAlertRuleParams) error {
+	_, err := q.db.Exec(ctx, deleteAlertRule, arg.ID, arg.ProjectID)
+	return err
+}
+
+const getAlertRule = `-- name: GetAlertRule :one
+SELECT id, project_id, name, kind, config, enabled, state, created_at, updated_at FROM core.alert_rules
+WHERE id = $1 AND project_id = $2
+`
+
+type GetAlertRuleParams struct {
+	ID        uuid.UUID `json:"id"`
+	ProjectID uuid.UUID `json:"project_id"`
+}
+
+func (q *Queries) GetAlertRule(ctx context.Context, arg GetAlertRuleParams) (CoreAlertRule, error) {
+	row := q.db.QueryRow(ctx, getAlertRule, arg.ID, arg.ProjectID)
+	var i CoreAlertRule
+	err := row.Scan(
+		&i.ID,
+		&i.ProjectID,
+		&i.Name,
+		&i.Kind,
+		&i.Config,
+		&i.Enabled,
+		&i.State,
+		&i.CreatedAt,
+		&i.UpdatedAt,
+	)
+	return i, err
+}
+
+const lastHeartbeats = `-- name: LastHeartbeats :many
+SELECT co.name AS component_name, max(e.ts)::timestamptz AS last_beat
+FROM core.components co
+JOIN core.events e ON e.component_id = co.id AND e.type = 'heartbeat'
+WHERE co.project_id = $1
+GROUP BY co.name
+`
+
+type LastHeartbeatsRow struct {
+	ComponentName string             `json:"component_name"`
+	LastBeat      pgtype.Timestamptz `json:"last_beat"`
+}
+
+// Per-component most recent heartbeat — heartbeat_silence detection.
+func (q *Queries) LastHeartbeats(ctx context.Context, projectID uuid.UUID) ([]LastHeartbeatsRow, error) {
+	rows, err := q.db.Query(ctx, lastHeartbeats, projectID)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var items []LastHeartbeatsRow
+	for rows.Next() {
+		var i LastHeartbeatsRow
+		if err := rows.Scan(&i.ComponentName, &i.LastBeat); err != nil {
+			return nil, err
+		}
+		items = append(items, i)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return items, nil
+}
+
+const listAlertRules = `-- name: ListAlertRules :many
+SELECT id, project_id, name, kind, config, enabled, state, created_at, updated_at FROM core.alert_rules
+WHERE project_id = $1
+ORDER BY name
+`
+
+func (q *Queries) ListAlertRules(ctx context.Context, projectID uuid.UUID) ([]CoreAlertRule, error) {
+	rows, err := q.db.Query(ctx, listAlertRules, projectID)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var items []CoreAlertRule
+	for rows.Next() {
+		var i CoreAlertRule
+		if err := rows.Scan(
+			&i.ID,
+			&i.ProjectID,
+			&i.Name,
+			&i.Kind,
+			&i.Config,
+			&i.Enabled,
+			&i.State,
+			&i.CreatedAt,
+			&i.UpdatedAt,
+		); err != nil {
+			return nil, err
+		}
+		items = append(items, i)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return items, nil
+}
+
+const listEnabledAlertRules = `-- name: ListEnabledAlertRules :many
+SELECT id, project_id, name, kind, config, enabled, state, created_at, updated_at FROM core.alert_rules
+WHERE enabled
+`
+
+func (q *Queries) ListEnabledAlertRules(ctx context.Context) ([]CoreAlertRule, error) {
+	rows, err := q.db.Query(ctx, listEnabledAlertRules)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var items []CoreAlertRule
+	for rows.Next() {
+		var i CoreAlertRule
+		if err := rows.Scan(
+			&i.ID,
+			&i.ProjectID,
+			&i.Name,
+			&i.Kind,
+			&i.Config,
+			&i.Enabled,
+			&i.State,
+			&i.CreatedAt,
+			&i.UpdatedAt,
+		); err != nil {
+			return nil, err
+		}
+		items = append(items, i)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return items, nil
+}
+
+const recentErrorCounts = `-- name: RecentErrorCounts :many
+SELECT co.name AS component_name, count(*) AS errors
+FROM core.events e
+JOIN core.components co ON co.id = e.component_id
+WHERE e.project_id = $1 AND e.type = 'error'
+  AND e.ts > now() - make_interval(secs => $2::bigint)
+GROUP BY co.name
+`
+
+type RecentErrorCountsParams struct {
+	ProjectID uuid.UUID `json:"project_id"`
+	Column2   int64     `json:"column_2"`
+}
+
+type RecentErrorCountsRow struct {
+	ComponentName string `json:"component_name"`
+	Errors        int64  `json:"errors"`
+}
+
+// Per-component error count inside a sliding window — error_spike detection.
+func (q *Queries) RecentErrorCounts(ctx context.Context, arg RecentErrorCountsParams) ([]RecentErrorCountsRow, error) {
+	rows, err := q.db.Query(ctx, recentErrorCounts, arg.ProjectID, arg.Column2)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var items []RecentErrorCountsRow
+	for rows.Next() {
+		var i RecentErrorCountsRow
+		if err := rows.Scan(&i.ComponentName, &i.Errors); err != nil {
+			return nil, err
+		}
+		items = append(items, i)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return items, nil
+}
+
+const setAlertRuleState = `-- name: SetAlertRuleState :exec
+UPDATE core.alert_rules
+SET state = $3, updated_at = NOW()
+WHERE id = $1 AND project_id = $2
+`
+
+type SetAlertRuleStateParams struct {
+	ID        uuid.UUID `json:"id"`
+	ProjectID uuid.UUID `json:"project_id"`
+	State     []byte    `json:"state"`
+}
+
+func (q *Queries) SetAlertRuleState(ctx context.Context, arg SetAlertRuleStateParams) error {
+	_, err := q.db.Exec(ctx, setAlertRuleState, arg.ID, arg.ProjectID, arg.State)
+	return err
+}
+
+const updateAlertRule = `-- name: UpdateAlertRule :one
+UPDATE core.alert_rules
+SET name = $3, config = $4, enabled = $5, updated_at = NOW()
+WHERE id = $1 AND project_id = $2
+RETURNING id, project_id, name, kind, config, enabled, state, created_at, updated_at
+`
+
+type UpdateAlertRuleParams struct {
+	ID        uuid.UUID `json:"id"`
+	ProjectID uuid.UUID `json:"project_id"`
+	Name      string    `json:"name"`
+	Config    []byte    `json:"config"`
+	Enabled   bool      `json:"enabled"`
+}
+
+func (q *Queries) UpdateAlertRule(ctx context.Context, arg UpdateAlertRuleParams) (CoreAlertRule, error) {
+	row := q.db.QueryRow(ctx, updateAlertRule,
+		arg.ID,
+		arg.ProjectID,
+		arg.Name,
+		arg.Config,
+		arg.Enabled,
+	)
+	var i CoreAlertRule
+	err := row.Scan(
+		&i.ID,
+		&i.ProjectID,
+		&i.Name,
+		&i.Kind,
+		&i.Config,
+		&i.Enabled,
+		&i.State,
+		&i.CreatedAt,
+		&i.UpdatedAt,
+	)
+	return i, err
+}
@@ -140,6 +140,18 @@ func (ns NullCoreProjectRole) Value() (driver.Value, error) {
 	return string(ns.CoreProjectRole), nil
 }

+type CoreAlertRule struct {
+	ID        uuid.UUID          `json:"id"`
+	ProjectID uuid.UUID          `json:"project_id"`
+	Name      string             `json:"name"`
+	Kind      string             `json:"kind"`
+	Config    []byte             `json:"config"`
+	Enabled   bool               `json:"enabled"`
+	State     []byte             `json:"state"`
+	CreatedAt pgtype.Timestamptz `json:"created_at"`
+	UpdatedAt pgtype.Timestamptz `json:"updated_at"`
+}
+
 type CoreApiKey struct {
 	ID              uuid.UUID          `json:"id"`
 	ProjectID       uuid.UUID          `json:"project_id"`
@@ -23,6 +23,7 @@ type Querier interface {
 	CountOrganizations(ctx context.Context) (int64, error)
 	CountProjectAdmins(ctx context.Context, projectID uuid.UUID) (int64, error)
 	CreateAPIKey(ctx context.Context, arg CreateAPIKeyParams) (CoreApiKey, error)
+	CreateAlertRule(ctx context.Context, arg CreateAlertRuleParams) (CoreAlertRule, error)
 	CreateAuditLog(ctx context.Context, arg CreateAuditLogParams) (CoreAuditLog, error)
 	CreateBucket(ctx context.Context, arg CreateBucketParams) (CoreBucket, error)
 	CreateBucketObject(ctx context.Context, arg CreateBucketObjectParams) (CoreBucketObject, error)
@@ -35,6 +36,7 @@ type Querier interface {
 	CreateProject(ctx context.Context, arg CreateProjectParams) (CoreProject, error)
 	CreateScheduledJob(ctx context.Context, arg CreateScheduledJobParams) (CoreScheduledJob, error)
 	CreateWebhook(ctx context.Context, arg CreateWebhookParams) (CoreWebhook, error)
+	DeleteAlertRule(ctx context.Context, arg DeleteAlertRuleParams) error
 	DeleteBucketByID(ctx context.Context, id uuid.UUID) (CoreBucket, error)
 	DeleteBucketObjectByKey(ctx context.Context, arg DeleteBucketObjectByKeyParams) (CoreBucketObject, error)
 	DeleteCollection(ctx context.Context, arg DeleteCollectionParams) error
@@ -54,6 +56,7 @@ type Querier interface {
 	FinishScheduledJobRun(ctx context.Context, arg FinishScheduledJobRunParams) (CoreScheduledJobRun, error)
 	GetAPIKeyByIDForProject(ctx context.Context, arg GetAPIKeyByIDForProjectParams) (CoreApiKey, error)
 	GetAPIKeyByPrefix(ctx context.Context, prefix string) (GetAPIKeyByPrefixRow, error)
+	GetAlertRule(ctx context.Context, arg GetAlertRuleParams) (CoreAlertRule, error)
 	GetBucketByID(ctx context.Context, id uuid.UUID) (GetBucketByIDRow, error)
 	GetBucketObjectByKey(ctx context.Context, arg GetBucketObjectByKeyParams) (CoreBucketObject, error)
 	GetCollectionByID(ctx context.Context, id uuid.UUID) (CoreCollection, error)
@@ -80,7 +83,10 @@ type Querier interface {
 	InsertEvent(ctx context.Context, arg InsertEventParams) (CoreEvent, error)
 	InsertScheduledJobRun(ctx context.Context, arg InsertScheduledJobRunParams) (CoreScheduledJobRun, error)
 	InsertWebhookDelivery(ctx context.Context, arg InsertWebhookDeliveryParams) (CoreWebhookDelivery, error)
+	// Per-component most recent heartbeat — heartbeat_silence detection.
+	LastHeartbeats(ctx context.Context, projectID uuid.UUID) ([]LastHeartbeatsRow, error)
 	ListAPIKeysForProject(ctx context.Context, projectID uuid.UUID) ([]CoreApiKey, error)
+	ListAlertRules(ctx context.Context, projectID uuid.UUID) ([]CoreAlertRule, error)
 	ListAuditLogsForProject(ctx context.Context, arg ListAuditLogsForProjectParams) ([]CoreAuditLog, error)
 	ListBucketObjects(ctx context.Context, arg ListBucketObjectsParams) ([]CoreBucketObject, error)
 	ListBucketsForOrganization(ctx context.Context, organizationID uuid.UUID) ([]uuid.UUID, error)
@@ -90,6 +96,7 @@ type Querier interface {
 	ListDBConnections(ctx context.Context, projectID uuid.UUID) ([]CoreDbConnection, error)
 	ListDocuments(ctx context.Context, arg ListDocumentsParams) ([]CoreDocument, error)
 	ListDueScheduledJobs(ctx context.Context, nextRunAt pgtype.Timestamptz) ([]CoreScheduledJob, error)
+	ListEnabledAlertRules(ctx context.Context) ([]CoreAlertRule, error)
 	ListErrorGroups(ctx context.Context, arg ListErrorGroupsParams) ([]ListErrorGroupsRow, error)
 	ListEvents(ctx context.Context, arg ListEventsParams) ([]ListEventsRow, error)
 	ListIntegrations(ctx context.Context, projectID uuid.UUID) ([]CoreIntegration, error)
@@ -114,10 +121,13 @@ type Querier interface {
 	MetricSeries(ctx context.Context, arg MetricSeriesParams) ([]MetricSeriesRow, error)
 	MoveBucketObject(ctx context.Context, arg MoveBucketObjectParams) (CoreBucketObject, error)
 	PruneScheduledJobRuns(ctx context.Context, arg PruneScheduledJobRunsParams) error
+	// Per-component error count inside a sliding window — error_spike detection.
+	RecentErrorCounts(ctx context.Context, arg RecentErrorCountsParams) ([]RecentErrorCountsRow, error)
 	RemoveOrganizationMember(ctx context.Context, arg RemoveOrganizationMemberParams) (CoreOrganizationMember, error)
 	RemoveProjectMember(ctx context.Context, arg RemoveProjectMemberParams) (CoreProjectMember, error)
 	RemoveProjectMembershipsForOrganizationUser(ctx context.Context, arg RemoveProjectMembershipsForOrganizationUserParams) error
 	RevokeAPIKey(ctx context.Context, arg RevokeAPIKeyParams) (CoreApiKey, error)
+	SetAlertRuleState(ctx context.Context, arg SetAlertRuleStateParams) error
 	SweepExpiredAuditLogs(ctx context.Context) (int64, error)
 	// Per-project retention sweeps. A retention of 0 days disables the sweep for
 	// that stream. Pending webhook deliveries are never swept — they may still be
@@ -128,6 +138,7 @@ type Querier interface {
 	SweepExpiredOrgAuditLogs(ctx context.Context) (int64, error)
 	SweepExpiredWebhookDeliveries(ctx context.Context) (int64, error)
 	TouchAPIKey(ctx context.Context, id uuid.UUID) error
+	UpdateAlertRule(ctx context.Context, arg UpdateAlertRuleParams) (CoreAlertRule, error)
 	UpdateBucketByID(ctx context.Context, arg UpdateBucketByIDParams) (CoreBucket, error)
 	UpdateCollection(ctx context.Context, arg UpdateCollectionParams) (CoreCollection, error)
 	UpdateDocument(ctx context.Context, arg UpdateDocumentParams) (CoreDocument, error)