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

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:
Ilia Denisov
2026-06-21 08:54:20 +02:00
parent 3fffee7817
commit 041106d623
28 changed files with 1295 additions and 19 deletions
+41
View File
@@ -68,6 +68,9 @@ const (
// throttleReportInterval is the cadence of the rate-limiter rejection
// summary: the Warn log per throttled key and the report to the backend.
throttleReportInterval = 30 * time.Second
// banSyncInterval is the cadence of the active-ban sync to the backend (which
// feeds the admin-console view) and the operator-unban pull.
banSyncInterval = 30 * time.Second
)
func main() {
@@ -119,6 +122,12 @@ func run(ctx context.Context, cfg config.Config, logger *zap.Logger) error {
sessions := session.NewCache(backend, cfg.SessionTTL, cfg.SessionCacheMax)
limiter := ratelimit.New()
tracker := ratelimit.NewTracker()
banlist := ratelimit.NewBanlist(ratelimit.BanConfig{
Enabled: cfg.Abuse.BanEnabled,
Threshold: cfg.Abuse.BanThreshold,
Window: cfg.Abuse.BanWindow,
Duration: cfg.Abuse.BanDuration,
})
hub := push.NewHub(0)
var validator transcode.TelegramValidator
@@ -183,6 +192,8 @@ func run(ctx context.Context, cfg config.Config, logger *zap.Logger) error {
Sessions: sessions,
Limiter: limiter,
Tracker: tracker,
Banlist: banlist,
Honeytoken: cfg.Abuse.Honeytoken,
Hub: hub,
RateLimit: cfg.RateLimit,
Heartbeat: cfg.PushHeartbeatInterval,
@@ -197,6 +208,11 @@ func run(ctx context.Context, cfg config.Config, logger *zap.Logger) error {
go runPushPump(ctx, backend, hub, botHub, logger)
// Periodically summarise rate-limiter rejections (Warn log + backend report).
go runThrottleReporter(ctx, tracker, backend, logger)
// When the IP ban is enabled (prod), sync the active set to the backend (the
// admin-console view) and apply the operator unbans it returns.
if cfg.Abuse.BanEnabled {
go runBanSync(ctx, banlist, backend, logger)
}
public := &http.Server{Addr: cfg.HTTPAddr, Handler: edge.HTTPHandler(), ReadHeaderTimeout: readHeaderTimeout}
servers := []*namedServer{{name: "public", srv: public}}
@@ -298,6 +314,31 @@ func runThrottleReporter(ctx context.Context, tracker *ratelimit.Tracker, backen
}
}
// runBanSync periodically reports the gateway's active IP bans to the backend (the
// admin-console view) and applies the operator unbans it returns, until the
// context is done. A failed sync is logged and dropped — the next tick reports
// fresh state, and a missed unban is retried on it.
func runBanSync(ctx context.Context, banlist *ratelimit.Banlist, backend *backendclient.Client, logger *zap.Logger) {
ticker := time.NewTicker(banSyncInterval)
defer ticker.Stop()
for {
select {
case <-ctx.Done():
return
case <-ticker.C:
}
unban, err := backend.SyncBans(ctx, banlist.Active())
if err != nil {
logger.Warn("ban sync failed", zap.Error(err))
continue
}
for _, ip := range unban {
banlist.Unban(ip)
logger.Info("ban cleared by operator", zap.String("client_ip", ip))
}
}
}
// runPushPump keeps a backend push subscription open, forwarding every event to
// the hub and re-subscribing after the stream ends, until the context is done. For
// the out-of-app push kinds it also routes events whose recipient has no live