Merge pull request 'fix(gateway): forward the real client IP to the backend on every call (last-login IP was the docker addr)' (#264) from feature/forward-client-ip into development

The tg (bot) VPS came up on Europe/Moscow while the main host is UTC, so host-level
timestamps (journald, file mtimes, cron) sat 3h apart across the fleet. Add a
community.general.timezone task to the common role so every provisioned host is UTC
(idempotent — a no-op on the already-UTC main host). Applied live to the tg host in
the same change; the containerised services run in UTC regardless, so no restart.

backend/internal/telemetry/middleware.go

@@ -56,6 +56,9 @@ func Middleware(logger *zap.Logger) gin.HandlerFunc {
 			zap.String("path", route),
 			zap.Int("status", status),
 			zap.Duration("latency", elapsed),
+			// The gateway forwards the real caller as X-Forwarded-For (and Caddy does for /_gm), which
+			// gin resolves here — so the access log carries the client IP, not the gateway's connection.
+			zap.String("client_ip", c.ClientIP()),
 		}
 		fields = append(fields, TraceFieldsFromContext(ctx)...)
 

deploy/ansible/roles/common/tasks/main.yml

@@ -150,6 +150,13 @@
     enabled: true
     state: started
 
+# Pin every host to UTC so host-level timestamps (journald, file mtimes, cron) line up
+# across the fleet — some VPS images ship a local zone (the tg host came up on MSK). The
+# services themselves run in UTC regardless; this is about host-side log correlation.
+- name: Set the system timezone to UTC
+  community.general.timezone:
+    name: Etc/UTC
+
 # --- Swap file (OOM cushion) ---------------------------------------------------
 # The prod main host is tight (1.9 GiB) and the per-container memory caps
 # (docker-compose.prod.yml) sum to more than RAM, so a simultaneous spike could hit

docs/ARCHITECTURE.md

@@ -151,7 +151,10 @@ dropped). Horizontal scaling is explicit future work.
   and GCG are unaffected** (they stay decoded concrete characters, §9.1).
 - **gateway ↔ backend (sync)**: plain HTTP REST/JSON. The gateway injects
   `X-User-ID` (and the session's trusted `X-Platform`, §3) for authenticated
-  requests; `backend` never re-derives identity or platform from the body. Because every sync call targets the one backend host, the
+  requests, plus the caller's real IP as **`X-Forwarded-For`** on **every** call
+  (carried on the request context), so the backend records the real caller — the
+  account's last-login IP, chat/feedback moderation, the access log — rather than
+  the gateway's own connection address; `backend` never re-derives identity or platform from the body. Because every sync call targets the one backend host, the
   gateway's REST client widens its keep-alive pool well past the stdlib default
   of 2 idle connections per host; otherwise the per-request connection churn
   exhausts ephemeral ports and burns gateway CPU under load (see
@@ -1496,7 +1499,8 @@ Two contours, two secret/variable prefixes (`TEST_` / `PROD_`):
   forwards the domain to `scrabble:80`, so the in-compose caddy serves plain HTTP
   (`CADDY_SITE_ADDRESS=:80`). The in-compose caddy **trusts X-Forwarded-For from
   private-range upstreams** (`trusted_proxies private_ranges`), so the real client IP —
-  used for chat-moderation logging and the gateway's per-IP rate limiting — survives the
+  used for the gateway's per-IP rate limiting and, forwarded on to the backend, the account's
+  last-login IP, chat/feedback moderation and the access log — survives the
   host-caddy hop; in prod (no host caddy) public clients are untrusted and Caddy uses the
   real peer, so the single config is correct and spoof-safe in both contours. The
   **bot-link mTLS material** (a private CA + gateway/bot leaves, CN=`gateway`) is

gateway/internal/backendclient/client.go

@@ -139,6 +139,26 @@ func platformFromContext(ctx context.Context) string {
 	return p
 }
 
+// clientIPCtxKey types the request-context slot the originating client IP rides in.
+type clientIPCtxKey struct{}
+
+// WithClientIP returns a copy of ctx carrying the originating client IP that do injects as
+// X-Forwarded-For on every downstream backend request — so the backend records the real caller
+// (the account's last-login IP, chat/feedback moderation, the access log) rather than the gateway's
+// own connection. An empty IP leaves ctx unchanged, so no header is sent.
+func WithClientIP(ctx context.Context, ip string) context.Context {
+	if ip == "" {
+		return ctx
+	}
+	return context.WithValue(ctx, clientIPCtxKey{}, ip)
+}
+
+// clientIPFromContext returns the client IP stored by WithClientIP, or an empty string when none.
+func clientIPFromContext(ctx context.Context) string {
+	ip, _ := ctx.Value(clientIPCtxKey{}).(string)
+	return ip
+}
+
 // do performs one REST call. userID, when non-empty, is forwarded as X-User-ID;
 // clientIP, when non-empty, as X-Forwarded-For (for chat moderation); the trusted
 // platform carried on ctx (see WithPlatform), when present, as X-Platform. A non-2xx
@@ -160,6 +180,13 @@ func (c *Client) do(ctx context.Context, method, path, userID, clientIP string,
 	if userID != "" {
 		req.Header.Set("X-User-ID", userID)
 	}
+	// The client IP rides X-Forwarded-For so the backend records the real caller. It comes from the
+	// explicit param (chat/feedback) or, for every other call, the request context (WithClientIP, set
+	// once per request in the Connect edge) — so the backend never falls back to the gateway's own
+	// connection address.
+	if clientIP == "" {
+		clientIP = clientIPFromContext(ctx)
+	}
 	if clientIP != "" {
 		req.Header.Set("X-Forwarded-For", clientIP)
 	}

gateway/internal/backendclient/client_test.go

@@ -122,3 +122,44 @@ func TestXPlatformInjection(t *testing.T) {
 		}
 	})
 }
+
+// TestXForwardedForInjection verifies the client IP carried on the context (WithClientIP) rides every
+// backend call as X-Forwarded-For — not just chat/feedback, which pass it explicitly — so the backend
+// records the real caller (e.g. the account's last-login IP on the profile fetch) rather than the
+// gateway's own connection. Absent when no client IP is set.
+func TestXForwardedForInjection(t *testing.T) {
+	var gotXFF string
+	var hadHeader bool
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		gotXFF = r.Header.Get("X-Forwarded-For")
+		_, hadHeader = r.Header["X-Forwarded-For"]
+		_, _ = w.Write([]byte(`{}`))
+	}))
+	defer srv.Close()
+
+	c, err := backendclient.New(srv.URL, "localhost:9090", 2*time.Second)
+	if err != nil {
+		t.Fatalf("backendclient: %v", err)
+	}
+	defer func() { _ = c.Close() }()
+
+	t.Run("client IP on ctx rides a non-chat call", func(t *testing.T) {
+		ctx := backendclient.WithClientIP(context.Background(), "203.0.113.7")
+		if _, err := c.Profile(ctx, "user-1"); err != nil {
+			t.Fatalf("Profile: %v", err)
+		}
+		if gotXFF != "203.0.113.7" {
+			t.Fatalf("X-Forwarded-For = %q, want 203.0.113.7", gotXFF)
+		}
+	})
+
+	t.Run("no client IP omits the header", func(t *testing.T) {
+		hadHeader = true
+		if _, err := c.Profile(context.Background(), "user-1"); err != nil {
+			t.Fatalf("Profile: %v", err)
+		}
+		if hadHeader {
+			t.Fatal("X-Forwarded-For must be absent when no client IP is set")
+		}
+	})
+}

gateway/internal/connectsrv/server.go

@@ -418,6 +418,10 @@ func (s *Server) Execute(ctx context.Context, req *connect.Request[edgev1.Execut
 		return nil, connect.NewError(connect.CodeNotFound, errUnknownMessageType(msgType))
 	}
 	clientIP := peerIP(req.Peer().Addr, req.Header())
+	// Carry the client IP on the context so the backend client injects it as X-Forwarded-For on every
+	// downstream REST call for this request — the account's last-login IP, chat/feedback moderation and
+	// the backend access log, not only the chat/feedback calls that pass it explicitly.
+	ctx = backendclient.WithClientIP(ctx, clientIP)
 
 	tr := transcode.Request{Payload: req.Msg.GetPayload(), ClientIP: clientIP}
 	if op.Auth {