feat(gateway): unsupported-engine telemetry beacon + Grafana counter #177

Merged
developer merged 1 commits from feature/unsupported-engine-telemetry into development 2026-07-04 21:16:23 +00:00
8 changed files with 298 additions and 4 deletions
Showing only changes of commit 2feb638329 - Show all commits
+1 -1
View File
@@ -86,7 +86,7 @@
# The game SPA and the Connect edge are served by the gateway. Strip any
# client-supplied X-Scrabble-Honeypot here so the gateway only ever honours the
# tag the honeypot block sets below (a client cannot self-tag a real request).
@gateway path /app /app/* /telegram /telegram/* /vk /vk/* /dict/* /dl/* /metrics/* /scrabble.edge.v1.Gateway/*
@gateway path /app /app/* /telegram /telegram/* /vk /vk/* /dict/* /dl/* /metrics/* /telemetry/* /scrabble.edge.v1.Gateway/*
handle @gateway {
reverse_proxy gateway:8081 {
header_up -X-Scrabble-Honeypot
+16
View File
@@ -56,6 +56,22 @@
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 24 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "refId": "A", "expr": "sum(rate(local_eval_preview_total[1h])) by (path)", "legendFormat": "{{path}}" }]
},
{
"type": "timeseries",
"title": "Unsupported-engine screens (cumulative by reason)",
"description": "Clients turned away by the index.html boot guard because the engine cannot run the app (an old Android System WebView), by reason: no_bigint / no_proxy (a missing unpolyfillable primitive) or boot_error (an uncaught startup failure). Deduped per device/version, so this counts distinct blocked installs, not launches. The effective floor is Chrome 67 (BigInt).",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 32 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "refId": "A", "expr": "sum(unsupported_engine_total) by (reason)", "legendFormat": "{{reason}}" }]
},
{
"type": "timeseries",
"title": "Unsupported engines by Chromium (rate)",
"description": "The same blocked clients by reported Chromium major version — which old in-app WebViews are still in the wild. \"other\" is an unparseable or out-of-range version.",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 32 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "refId": "A", "expr": "sum(rate(unsupported_engine_total[1h])) by (chromium)", "legendFormat": "Chromium {{chromium}}" }]
}
]
}
+11
View File
@@ -1070,6 +1070,17 @@ browser), so an open in-app session reflects it at once.
it fills IndexedDB — and is surfaced on the **Scrabble — Users** dashboard. Lossy by
design (a dropped beacon just retries its batch on the next flush); it is telemetry, never
a game input.
- **Unsupported-engine screens (client-reported):** the ES5 boot guard in `index.html` (§13)
shows a full-screen "your device's OS or browser can't run the app" screen — instead of a white
screen — when the engine lacks an unpolyfillable essential (`BigInt`, the 64-bit FlatBuffers
decode; or `Proxy`, Svelte 5 runes) or an uncaught error aborts boot; the effective floor is
Chrome 67. It then fires one fire-and-forget beacon (`POST /telemetry/unsupported`
unauthenticated, since the client never booted, but per-IP public-limited and body-capped),
deduped in `localStorage` by app version + reason + Chromium so a user reopening the app is one
report. The gateway folds it into `unsupported_engine_total` (`reason` =
no_bigint/no_proxy/boot_error/other; `chromium` = the major version reduced to a bounded range so
a spoofed beacon cannot inflate cardinality) and logs the full user agent (not a label). Surfaced
on the **Scrabble — Users** dashboard beside app opens.
- **Rate-limit observability:** every limiter rejection increments the gateway
counter `gateway_rate_limited_total` (`class` = user/public/email/admin — aggregate
only, honouring the no-per-user-label discipline above) and logs one **Debug** line;
+14
View File
@@ -32,6 +32,8 @@ type serverMetrics struct {
localColdStart metric.Int64Counter
localDictLoad metric.Int64Counter
localPreview metric.Int64Counter
// Clients turned away by the unsupported-engine boot screen (see unsupportedEngineHandler).
unsupportedEngine metric.Int64Counter
}
// newServerMetrics builds the instruments on meter (nil selects a no-op meter),
@@ -63,6 +65,8 @@ func newServerMetrics(meter metric.Meter) *serverMetrics {
localColdStart: counterOf(meter, "local_eval_cold_start_total", "App cold starts reported by clients — the denominator for local-move-preview adoption."),
localDictLoad: counterOf(meter, "local_eval_dict_load_total", "Client dictionary loads for the local move preview, by result (fetched, cache_hit or miss)."),
localPreview: counterOf(meter, "local_eval_preview_total", "Client move previews, by path (local on-device, or network fallback)."),
unsupportedEngine: counterOf(meter, "unsupported_engine_total",
"Clients that hit the unsupported-engine boot screen (the app cannot run), by reason (no_bigint, no_proxy, boot_error, other) and Chromium major — a deduped beacon from the index.html boot guard; the full user agent is logged, not labelled."),
}
gauge, err := meter.Int64ObservableGauge("active_users",
@@ -108,6 +112,16 @@ func (m *serverMetrics) recordBan(ctx context.Context, reason string) {
m.banned.Add(ctx, 1, metric.WithAttributes(attribute.String("reason", reason)))
}
// recordUnsupportedEngine counts one client turned away by the unsupported-engine boot screen,
// labelled by reason and Chromium major. The caller passes both already reduced to bounded label
// sets (see normalizeUnsupported) so a spoofed beacon cannot explode the metric cardinality.
func (m *serverMetrics) recordUnsupportedEngine(ctx context.Context, reason, chromium string) {
m.unsupportedEngine.Add(ctx, 1, metric.WithAttributes(
attribute.String("reason", reason),
attribute.String("chromium", chromium),
))
}
// localEvalReport is the client-reported local move-preview telemetry batch — deltas since
// the client's previous report. It backs the adoption dashboard: app cold starts vs cached
// dictionaries vs on-device previews.
@@ -128,3 +128,70 @@ func TestBannedMetric(t *testing.T) {
t.Errorf("banned counts = %v, want tripwire=2 honeytoken=1", counts)
}
}
// TestUnsupportedEngineMetric records unsupported-engine beacons through a manual reader and asserts
// unsupported_engine_total splits by reason and Chromium major.
func TestUnsupportedEngineMetric(t *testing.T) {
ctx := context.Background()
reader := sdkmetric.NewManualReader()
meter := sdkmetric.NewMeterProvider(sdkmetric.WithReader(reader)).Meter("test")
m := newServerMetrics(meter)
m.recordUnsupportedEngine(ctx, "no_bigint", "66")
m.recordUnsupportedEngine(ctx, "no_bigint", "66")
m.recordUnsupportedEngine(ctx, "boot_error", "74")
var rm metricdata.ResourceMetrics
if err := reader.Collect(ctx, &rm); err != nil {
t.Fatalf("collect: %v", err)
}
type key struct{ reason, chromium string }
counts := map[key]int64{}
for _, sm := range rm.ScopeMetrics {
for _, md := range sm.Metrics {
if md.Name != "unsupported_engine_total" {
continue
}
sum, ok := md.Data.(metricdata.Sum[int64])
if !ok {
t.Fatalf("unsupported_engine_total is not an int64 sum")
}
for _, dp := range sum.DataPoints {
reason, _ := dp.Attributes.Value(attribute.Key("reason"))
chromium, _ := dp.Attributes.Value(attribute.Key("chromium"))
counts[key{reason.AsString(), chromium.AsString()}] += dp.Value
}
}
}
if got := counts[key{"no_bigint", "66"}]; got != 2 {
t.Errorf("unsupported no_bigint/66 = %d, want 2", got)
}
if got := counts[key{"boot_error", "74"}]; got != 1 {
t.Errorf("unsupported boot_error/74 = %d, want 1", got)
}
}
// TestNormalizeUnsupported checks that a beacon's reason and Chromium are reduced to bounded label
// values, so a spoofed beacon cannot explode the metric cardinality.
func TestNormalizeUnsupported(t *testing.T) {
cases := []struct {
reason, chromium string
wantReason, wantChromium string
}{
{"no_bigint", "66", "no_bigint", "66"},
{"no_proxy", " 74 ", "no_proxy", "74"},
{"boot_error", "105", "boot_error", "105"},
{"garbage", "66", "other", "66"},
{"", "", "other", "other"},
{"no_bigint", "not-a-number", "no_bigint", "other"},
{"no_bigint", "9999", "no_bigint", "other"},
{"no_bigint", "0", "no_bigint", "other"},
{"no_bigint", "-5", "no_bigint", "other"},
}
for _, c := range cases {
gotR, gotC := normalizeUnsupported(c.reason, c.chromium)
if gotR != c.wantReason || gotC != c.wantChromium {
t.Errorf("normalizeUnsupported(%q,%q) = %q,%q; want %q,%q", c.reason, c.chromium, gotR, gotC, c.wantReason, c.wantChromium)
}
}
}
+74
View File
@@ -15,6 +15,7 @@ import (
"io"
"net"
"net/http"
"strconv"
"strings"
"time"
@@ -197,6 +198,9 @@ func (s *Server) HTTPHandler() http.Handler {
mux.Handle("/dl/", s.exportDownloadHandler())
// The client posts its local-move-preview adoption telemetry here (session-gated).
mux.Handle("/metrics/local-eval", s.localEvalMetricsHandler())
// The index.html boot guard beacons here when it turns a client away on the unsupported-engine
// screen (the app cannot run). Unauthenticated — the client never booted — but rate-limited.
mux.Handle("/telemetry/unsupported", s.unsupportedEngineHandler())
// The embedded UI: the game SPA under /app/ (web), /telegram/ (the Telegram Mini
// App) and /vk/ (the VK Mini App) — the single-origin model (docs/ARCHITECTURE.md
// §13). All sit below the h2c wrap so the Connect edge (a more specific prefix) keeps
@@ -582,6 +586,76 @@ func clampReport(r *localEvalReport) {
clamp(&r.PreviewNetwork)
}
// unsupportedEngineBeacon is the small fire-and-forget report the index.html boot guard sends when
// it turns a client away on the unsupported-engine screen (no BigInt/Proxy, or an uncaught boot
// error). It is deduped client-side (one per device / app version / reason).
type unsupportedEngineBeacon struct {
Reason string `json:"reason"`
Chromium string `json:"chromium"`
Version string `json:"version"`
UA string `json:"ua"`
}
// unsupportedEngineHandler folds one unsupported-engine beacon into the edge counter. It is
// unauthenticated (the client never booted, so it carries no session) but per-IP rate-limited with
// the public limiter and body-capped. reason and the Chromium major are reduced to bounded label
// sets (normalizeUnsupported) so a spoofed beacon cannot inflate the metric cardinality; the full
// user agent is logged, not labelled. Only POST; the reply is always 204.
func (s *Server) unsupportedEngineHandler() http.Handler {
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodPost {
http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
return
}
ip := peerIP(r.RemoteAddr, r.Header)
if !s.limiter.Allow("public:"+ip, s.publicPolicy) {
s.noteRateLimited(r.Context(), classPublic, ip, "unsupported")
http.Error(w, "rate limited", http.StatusTooManyRequests)
return
}
var b unsupportedEngineBeacon
if err := json.NewDecoder(io.LimitReader(r.Body, 2048)).Decode(&b); err != nil {
http.Error(w, "bad request", http.StatusBadRequest)
return
}
reason, chromium := normalizeUnsupported(b.Reason, b.Chromium)
s.metrics.recordUnsupportedEngine(r.Context(), reason, chromium)
s.log.Info("unsupported engine",
zap.String("reason", reason),
zap.String("chromium", chromium),
zap.String("app_version", truncate(b.Version, 40)),
zap.String("user_agent", truncate(b.UA, 400)),
)
w.WriteHeader(http.StatusNoContent)
})
}
// normalizeUnsupported reduces a beacon's reason and Chromium fields to bounded label values, so a
// spoofed beacon cannot explode the metric cardinality: reason is allow-listed, and Chromium is
// parsed as a major version kept only within a plausible range, otherwise "other".
func normalizeUnsupported(reason, chromium string) (string, string) {
switch reason {
case "no_bigint", "no_proxy", "boot_error":
// a recognised reason — keep as-is
default:
reason = "other"
}
major := "other"
if n, err := strconv.Atoi(strings.TrimSpace(chromium)); err == nil && n >= 1 && n <= 199 {
major = strconv.Itoa(n)
}
return reason, major
}
// truncate bounds a logged, client-supplied string to n bytes (a spoofed beacon field is not
// trusted to be small).
func truncate(s string, n int) string {
if len(s) > n {
return s[:n]
}
return s
}
// resolve extracts and resolves the Authorization bearer token to an account id
// and its guest flag, returning a Connect Unauthenticated error when it is missing
// or unknown.
@@ -0,0 +1,81 @@
package connectsrv_test
import (
"bytes"
"context"
"net/http"
"net/http/httptest"
"testing"
"go.opentelemetry.io/otel/attribute"
sdkmetric "go.opentelemetry.io/otel/sdk/metric"
"go.opentelemetry.io/otel/sdk/metric/metricdata"
"scrabble/gateway/internal/config"
"scrabble/gateway/internal/connectsrv"
"scrabble/gateway/internal/ratelimit"
)
// TestUnsupportedEngineHandler drives the /telemetry/unsupported beacon route end to end: a POST
// increments unsupported_engine_total with the normalised labels and replies 204; a GET is 405.
func TestUnsupportedEngineHandler(t *testing.T) {
reader := sdkmetric.NewManualReader()
meter := sdkmetric.NewMeterProvider(sdkmetric.WithReader(reader)).Meter("test")
edge := connectsrv.NewServer(connectsrv.Deps{
Limiter: ratelimit.New(),
RateLimit: config.DefaultRateLimit(),
Meter: meter,
})
srv := httptest.NewServer(edge.HTTPHandler())
defer srv.Close()
url := srv.URL + "/telemetry/unsupported"
// A GET is rejected.
getResp, err := http.Get(url)
if err != nil {
t.Fatalf("get: %v", err)
}
getResp.Body.Close()
if getResp.StatusCode != http.StatusMethodNotAllowed {
t.Errorf("GET status = %d, want 405", getResp.StatusCode)
}
// A POST is accepted (204) and folded into the counter with normalised labels.
body := `{"reason":"no_bigint","chromium":"66","version":"v1.2.3","ua":"Mozilla/5.0 ... Chrome/66"}`
resp, err := http.Post(url, "application/json", bytes.NewBufferString(body))
if err != nil {
t.Fatalf("post: %v", err)
}
resp.Body.Close()
if resp.StatusCode != http.StatusNoContent {
t.Errorf("POST status = %d, want 204", resp.StatusCode)
}
var rm metricdata.ResourceMetrics
if err := reader.Collect(context.Background(), &rm); err != nil {
t.Fatalf("collect: %v", err)
}
var total int64
for _, sm := range rm.ScopeMetrics {
for _, md := range sm.Metrics {
if md.Name != "unsupported_engine_total" {
continue
}
sum, ok := md.Data.(metricdata.Sum[int64])
if !ok {
t.Fatalf("unsupported_engine_total is not an int64 sum")
}
for _, dp := range sum.DataPoints {
reason, _ := dp.Attributes.Value(attribute.Key("reason"))
chromium, _ := dp.Attributes.Value(attribute.Key("chromium"))
if reason.AsString() != "no_bigint" || chromium.AsString() != "66" {
t.Errorf("labels = %s/%s, want no_bigint/66", reason.AsString(), chromium.AsString())
}
total += dp.Value
}
}
}
if total != 1 {
t.Errorf("unsupported_engine_total = %d, want 1", total)
}
}
+34 -3
View File
@@ -97,9 +97,40 @@
}
var shown = false;
function show(reason) {
// Fire-and-forget beacon so the gateway can count who hits this screen (Grafana). Deduped
// in localStorage by app version + reason + Chromium, so a user reopening the app ten times
// is one report. sendBeacon (Chrome 39+, present on the engines that reach here) with a
// fetch fallback; both are best-effort and never block or throw.
function beacon(code) {
try {
var cm = /Chrom(?:e|ium)\/(\d+)/.exec(ua);
var chromium = cm ? cm[1] : '';
var sig = VERSION + '|' + code + '|' + chromium;
try {
if (localStorage.getItem('scrabble_unsupp') === sig) return;
} catch (e) {}
var payload = JSON.stringify({ reason: code, chromium: chromium, version: VERSION, ua: ua });
var sent = false;
try {
if (nav.sendBeacon) sent = nav.sendBeacon('/telemetry/unsupported', new Blob([payload], { type: 'application/json' }));
} catch (e) {}
if (!sent && typeof fetch === 'function') {
try {
fetch('/telemetry/unsupported', { method: 'POST', body: payload, headers: { 'Content-Type': 'application/json' }, keepalive: true }).catch(function () {});
sent = true;
} catch (e) {}
}
if (sent) {
try {
localStorage.setItem('scrabble_unsupp', sig);
} catch (e) {}
}
} catch (e) {}
}
function show(reason, code) {
if (shown) return;
shown = true;
beacon(code);
var root = el('div', 'position:fixed;left:0;top:0;right:0;bottom:0;z-index:2147483647;overflow:auto;' +
'-webkit-overflow-scrolling:touch;background:#0f1115;color:#e8eaed;box-sizing:border-box;padding:24px;' +
'font:16px/1.5 -apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,Arial,sans-serif;');
@@ -179,7 +210,7 @@
// 1 + 2: the gate.
if (hardMissing.length) {
show((RU ? 'нет: ' : 'missing: ') + hardMissing.join(', '));
show((RU ? 'нет: ' : 'missing: ') + hardMissing.join(', '), hardMissing.indexOf('BigInt') >= 0 ? 'no_bigint' : 'no_proxy');
} else if (softMissing) {
document.write('<script src="polyfills.js"><\/script>');
}
@@ -201,7 +232,7 @@
note(r && (r.stack || r.message) ? r.stack || r.message : String(r));
});
setTimeout(function () {
if (!window.__booted && bootErr && !shown) show((RU ? 'ошибка запуска: ' : 'boot error: ') + bootErr);
if (!window.__booted && bootErr && !shown) show((RU ? 'ошибка запуска: ' : 'boot error: ') + bootErr, 'boot_error');
}, 8000);
})();
</script>