feat(gateway): temporary IP ban (fail2ban) fed by rejections + honeypot/honeytoken
CI / changes (pull_request) Successful in 3s
CI / unit (pull_request) Successful in 11s
CI / integration (pull_request) Successful in 17s
CI / ui (pull_request) Successful in 53s
CI / gate (pull_request) Successful in 0s
CI / deploy (pull_request) Successful in 1m11s
CI / changes (pull_request) Successful in 3s
CI / unit (pull_request) Successful in 11s
CI / integration (pull_request) Successful in 17s
CI / ui (pull_request) Successful in 53s
CI / gate (pull_request) Successful in 0s
CI / deploy (pull_request) Successful in 1m11s
Add a prod-only, in-memory IP ban enforced at the edge, fed by three signals:
sustained rate-limiter rejections (the IP-keyed public/email/admin classes — the
user class stays the backend soft-flag's concern), a honeypot decoy-path hit (the
contour caddy tags decoys with X-Scrabble-Honeypot and routes them to the gateway),
and a honeytoken (a planted bearer, GATEWAY_HONEYTOKEN). A banned IP is refused with
429 by the abuseGuard middleware before any work — covering the Connect edge, the
live stream and the static SPA/landing the per-op limiter never gated.
The ban is off by default: it keys by the real client IP the shared-NAT test contour
does not expose, so a ban there would be self-inflicted; detection still logs in the
contour, only the ban action is gated (GATEWAY_ABUSE_BAN_ENABLED). Rejection bans last
GATEWAY_ABUSE_BAN_DURATION; tripwire/honeytoken hits are near-zero-false-positive and
earn longer fixed bans. Each ban increments gateway_abuse_banned_total{reason}.
Operators see and lift active bans on the admin console's Throttled page; the gateway
syncs its active set to the backend every 30s (POST /api/v1/internal/bans/sync,
backend/internal/banview) and applies the operator unbans the response returns.
PRERELEASE phase AG. Docs baked into ARCHITECTURE / FUNCTIONAL (+ru) / both READMEs.
This commit is contained in:
@@ -26,6 +26,7 @@ var activeUserWindows = []struct {
|
||||
type serverMetrics struct {
|
||||
edge metric.Float64Histogram
|
||||
rateLimited metric.Int64Counter
|
||||
banned metric.Int64Counter
|
||||
active *activeUsers
|
||||
}
|
||||
|
||||
@@ -48,7 +49,12 @@ func newServerMetrics(meter metric.Meter) *serverMetrics {
|
||||
if err != nil {
|
||||
c, _ = noop.NewMeterProvider().Meter(meterName).Int64Counter("gateway_rate_limited_total")
|
||||
}
|
||||
m := &serverMetrics{edge: h, rateLimited: c, active: newActiveUsers()}
|
||||
b, err := meter.Int64Counter("gateway_abuse_banned_total",
|
||||
metric.WithDescription("Temporary IP bans applied at the edge, by reason (rejections, tripwire or honeytoken)."))
|
||||
if err != nil {
|
||||
b, _ = noop.NewMeterProvider().Meter(meterName).Int64Counter("gateway_abuse_banned_total")
|
||||
}
|
||||
m := &serverMetrics{edge: h, rateLimited: c, banned: b, active: newActiveUsers()}
|
||||
|
||||
gauge, err := meter.Int64ObservableGauge("active_users",
|
||||
metric.WithDescription("Distinct accounts that performed an authenticated action within the window (in-memory, single gateway instance)."))
|
||||
@@ -86,3 +92,9 @@ func (m *serverMetrics) recordActive(uid string) {
|
||||
func (m *serverMetrics) recordRateLimited(ctx context.Context, class string) {
|
||||
m.rateLimited.Add(ctx, 1, metric.WithAttributes(attribute.String("class", class)))
|
||||
}
|
||||
|
||||
// recordBan counts one temporary IP ban under reason (rejections, tripwire or
|
||||
// honeytoken).
|
||||
func (m *serverMetrics) recordBan(ctx context.Context, reason string) {
|
||||
m.banned.Add(ctx, 1, metric.WithAttributes(attribute.String("reason", reason)))
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user