feat(server/diagnostics): device debug-reporting ingest + admin timeline + retention (M9)

New diagnostic_events table + per-account users.debug_mode_enabled flag. When an account's flag is on, its client(s) POST a batch timeseries of connectivity / UPnP-sync / power / lifecycle events to /api/diagnostics (no-op 204 when off, kind whitelist mirrors the CHECK constraint). Admin surface: GET /api/admin/diagnostics (optional account/device/kind/ time-window filters, RFC3339-or-epoch-ms, export-sized paging) + a /diagnostics/devices overview + PUT /api/admin/users/{id}/debug-mode to flip an account remotely while a bug is live. debug_mode_enabled is now exposed on /api/me (client gate) and the admin user views. Retention: a 30-day gc-worker sweep (GcPruneDiagnostics), keyed on the server clock so a skewed device clock can't keep rows alive. Refs Scribe M9 (#119), tasks #1172 #1173. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01K55iTxn95BtshocgdE1shW
2026-06-29 18:38:56 -04:00
parent f4f4df7708
commit 4ed831d9c3
12 changed files with 804 additions and 18 deletions
@@ -0,0 +1,221 @@
+// Code generated by sqlc. DO NOT EDIT.
+// versions:
+//   sqlc v1.31.1
+// source: diagnostics.sql
+
+package dbq
+
+import (
+	"context"
+
+	"github.com/jackc/pgx/v5/pgtype"
+)
+
+const gcPruneDiagnostics = `-- name: GcPruneDiagnostics :execrows
+DELETE FROM diagnostic_events WHERE received_at < now() - INTERVAL '30 days'
+`
+
+// Retention sweep for the gc worker. Deletes diagnostic_events older
+// than 30 days by server clock (received_at) so a skewed client clock
+// can't keep rows alive. Matches the other gc lifecycle sweeps'
+// hardcoded-threshold style; diagnostics are debug telemetry, not user
+// data, and 30 days is ample to investigate a live incident after the
+// fact. Returns the affected row count for the sweep log line.
+func (q *Queries) GcPruneDiagnostics(ctx context.Context) (int64, error) {
+	result, err := q.db.Exec(ctx, gcPruneDiagnostics)
+	if err != nil {
+		return 0, err
+	}
+	return result.RowsAffected(), nil
+}
+
+const insertDiagnosticEvent = `-- name: InsertDiagnosticEvent :one
+INSERT INTO diagnostic_events (
+    user_id, client_id, app_version, os_version, kind, payload, occurred_at
+)
+VALUES ($1, $2, $3, $4, $5, $6, $7)
+RETURNING id, received_at
+`
+
+type InsertDiagnosticEventParams struct {
+	UserID     pgtype.UUID
+	ClientID   string
+	AppVersion *string
+	OsVersion  *string
+	Kind       string
+	Payload    []byte
+	OccurredAt pgtype.Timestamptz
+}
+
+type InsertDiagnosticEventRow struct {
+	ID         pgtype.UUID
+	ReceivedAt pgtype.Timestamptz
+}
+
+// Records one client-reported diagnostic event. The writer validates the
+// `kind` category against its whitelist before this runs; the CHECK
+// constraint is the belt-and-braces guard. payload carries the finer
+// event discriminator + all event-specific fields. Returns received_at
+// so the caller can confirm ingest.
+func (q *Queries) InsertDiagnosticEvent(ctx context.Context, arg InsertDiagnosticEventParams) (InsertDiagnosticEventRow, error) {
+	row := q.db.QueryRow(ctx, insertDiagnosticEvent,
+		arg.UserID,
+		arg.ClientID,
+		arg.AppVersion,
+		arg.OsVersion,
+		arg.Kind,
+		arg.Payload,
+		arg.OccurredAt,
+	)
+	var i InsertDiagnosticEventRow
+	err := row.Scan(&i.ID, &i.ReceivedAt)
+	return i, err
+}
+
+const listAdminDiagnostics = `-- name: ListAdminDiagnostics :many
+SELECT
+    de.id          AS id,
+    de.user_id     AS user_id,
+    u.username     AS username,
+    de.client_id   AS client_id,
+    de.app_version AS app_version,
+    de.os_version  AS os_version,
+    de.kind        AS kind,
+    de.payload     AS payload,
+    de.occurred_at AS occurred_at,
+    de.received_at AS received_at
+FROM diagnostic_events de
+JOIN users u ON u.id = de.user_id
+WHERE ($1::uuid   IS NULL OR de.user_id   = $1::uuid)
+  AND ($2::text IS NULL OR de.client_id = $2::text)
+  AND ($3::text      IS NULL OR de.kind      = $3::text)
+  AND ($4::timestamptz IS NULL
+       OR de.occurred_at >= $4::timestamptz)
+  AND ($5::timestamptz IS NULL
+       OR de.occurred_at <= $5::timestamptz)
+ORDER BY de.occurred_at DESC
+LIMIT $7::int OFFSET $6::int
+`
+
+type ListAdminDiagnosticsParams struct {
+	UserID   pgtype.UUID
+	ClientID *string
+	Kind     *string
+	FromTs   pgtype.Timestamptz
+	ToTs     pgtype.Timestamptz
+	Off      int32
+	Lim      int32
+}
+
+type ListAdminDiagnosticsRow struct {
+	ID         pgtype.UUID
+	UserID     pgtype.UUID
+	Username   string
+	ClientID   string
+	AppVersion *string
+	OsVersion  *string
+	Kind       string
+	Payload    []byte
+	OccurredAt pgtype.Timestamptz
+	ReceivedAt pgtype.Timestamptz
+}
+
+// Admin timeline query. All filters are optional (NULL = no filter):
+// account (user_id), device (client_id), category (kind), and the
+// occurred_at window (from_ts/to_ts). Newest-first; the SPA reverses for
+// a chronological timeline / export. Joined with users for the username
+// so the view renders without a second round-trip.
+func (q *Queries) ListAdminDiagnostics(ctx context.Context, arg ListAdminDiagnosticsParams) ([]ListAdminDiagnosticsRow, error) {
+	rows, err := q.db.Query(ctx, listAdminDiagnostics,
+		arg.UserID,
+		arg.ClientID,
+		arg.Kind,
+		arg.FromTs,
+		arg.ToTs,
+		arg.Off,
+		arg.Lim,
+	)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var items []ListAdminDiagnosticsRow
+	for rows.Next() {
+		var i ListAdminDiagnosticsRow
+		if err := rows.Scan(
+			&i.ID,
+			&i.UserID,
+			&i.Username,
+			&i.ClientID,
+			&i.AppVersion,
+			&i.OsVersion,
+			&i.Kind,
+			&i.Payload,
+			&i.OccurredAt,
+			&i.ReceivedAt,
+		); err != nil {
+			return nil, err
+		}
+		items = append(items, i)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return items, nil
+}
+
+const listDiagnosticDevices = `-- name: ListDiagnosticDevices :many
+SELECT
+    de.client_id            AS client_id,
+    de.user_id              AS user_id,
+    u.username              AS username,
+    max(de.app_version)::text        AS app_version,
+    max(de.os_version)::text         AS os_version,
+    max(de.occurred_at)::timestamptz AS last_seen,
+    count(*)                         AS event_count
+FROM diagnostic_events de
+JOIN users u ON u.id = de.user_id
+WHERE ($1::uuid IS NULL OR de.user_id = $1::uuid)
+GROUP BY de.client_id, de.user_id, u.username
+ORDER BY last_seen DESC
+`
+
+type ListDiagnosticDevicesRow struct {
+	ClientID   string
+	UserID     pgtype.UUID
+	Username   string
+	AppVersion string
+	OsVersion  string
+	LastSeen   pgtype.Timestamptz
+	EventCount int64
+}
+
+// Distinct devices that have reported, for the admin device filter +
+// "who is currently reporting" overview. Optionally scoped to one account.
+func (q *Queries) ListDiagnosticDevices(ctx context.Context, userID pgtype.UUID) ([]ListDiagnosticDevicesRow, error) {
+	rows, err := q.db.Query(ctx, listDiagnosticDevices, userID)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var items []ListDiagnosticDevicesRow
+	for rows.Next() {
+		var i ListDiagnosticDevicesRow
+		if err := rows.Scan(
+			&i.ClientID,
+			&i.UserID,
+			&i.Username,
+			&i.AppVersion,
+			&i.OsVersion,
+			&i.LastSeen,
+			&i.EventCount,
+		); err != nil {
+			return nil, err
+		}
+		items = append(items, i)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return items, nil
+}