fix(ws): raise bounded agent message limit

internal/agent/wsclient/client.go

@@ -108,6 +108,7 @@ func connectOnce(ctx context.Context, cfg Config, handle Handler) error {
 	if err != nil {
 		return fmt.Errorf("dial: %w", err)
 	}
+	conn.SetReadLimit(api.MaxWebSocketMessageBytes)
 	// On a successful upgrade coder/websocket transfers ownership of the
 	// response stream to conn and deliberately sets res.Body to nil. Closing
 	// the connection below releases that stream.

internal/agent/wsclient/client_test.go

@@ -2,12 +2,16 @@ package wsclient
 
 import (
 	"context"
+	"encoding/json"
 	"net/http"
 	"net/http/httptest"
+	"strings"
 	"testing"
 	"time"
 
 	"github.com/coder/websocket"
+
+	"gitea.dcglab.co.uk/steve/restic-manager/internal/api"
 )
 
 func TestConnectOnceCleanDisconnectDoesNotPanic(t *testing.T) {
@@ -44,3 +48,56 @@ func TestConnectOnceCleanDisconnectDoesNotPanic(t *testing.T) {
 		t.Fatalf("server websocket: %v", err)
 	}
 }
+
+func TestConnectOnceAcceptsMessageLargerThanDefaultReadLimit(t *testing.T) {
+	received := make(chan struct{}, 1)
+	serverErr := make(chan error, 1)
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		conn, err := websocket.Accept(w, r, nil)
+		if err != nil {
+			serverErr <- err
+			return
+		}
+		defer conn.CloseNow() //nolint:errcheck
+		if _, _, err := conn.Read(r.Context()); err != nil {
+			serverErr <- err
+			return
+		}
+		env := api.Envelope{
+			Type:    api.MsgConfigUpdate,
+			Payload: json.RawMessage(`{"padding":"` + strings.Repeat("x", 40*1024) + `"}`),
+		}
+		raw, _ := json.Marshal(env)
+		serverErr <- conn.Write(r.Context(), websocket.MessageText, raw)
+		<-r.Context().Done()
+	}))
+	defer srv.Close()
+
+	ctx, cancel := context.WithCancel(context.Background())
+	done := make(chan error, 1)
+	go func() {
+		done <- connectOnce(ctx, Config{
+			ServerURL:       srv.URL,
+			AgentToken:      "test-token",
+			HeartbeatPeriod: time.Hour,
+		}, func(_ context.Context, env api.Envelope, _ Sender) error {
+			if env.Type == api.MsgConfigUpdate {
+				received <- struct{}{}
+				cancel()
+			}
+			return nil
+		})
+	}()
+
+	select {
+	case <-received:
+	case <-time.After(5 * time.Second):
+		t.Fatal("agent did not receive oversized server message")
+	}
+	if err := <-serverErr; err != nil {
+		t.Fatalf("server websocket: %v", err)
+	}
+	if err := <-done; err == nil {
+		t.Fatal("connectOnce returned nil")
+	}
+}

internal/api/wire.go

@@ -10,6 +10,13 @@ import (
 // (not iota ints) makes traffic readable in logs and packet captures.
 type MessageType string
 
+// MaxWebSocketMessageBytes is the protocol-wide upper bound for one agent ↔
+// server envelope. Snapshot projections and restic JSON log events can exceed
+// coder/websocket's 32 KiB default on ordinary repositories, so both peers set
+// this limit explicitly. It remains bounded to protect either process from an
+// untrusted or malfunctioning peer allocating without limit.
+const MaxWebSocketMessageBytes int64 = 8 << 20
+
 // Agent → server message types.
 const (
 	MsgHello          MessageType = "hello"

internal/server/ws/handler.go

@@ -77,6 +77,7 @@ func AgentHandler(deps HandlerDeps) stdhttp.Handler {
 			slog.Warn("ws accept failed", "err", err, "host_id", host.ID)
 			return
 		}
+		conn.SetReadLimit(api.MaxWebSocketMessageBytes)
 
 		c := NewConn(host.ID, conn)
 		// Keep agents alive across NAT boxes; coder/websocket

internal/server/ws/hub_test.go

@@ -123,6 +123,68 @@ func TestWSHelloAndHeartbeat(t *testing.T) {
 	t.Error("heartbeat did not update last_seen_at")
 }
 
+func TestWSAcceptsSnapshotReportLargerThanDefaultReadLimit(t *testing.T) {
+	t.Parallel()
+	url, token, hostID, st, hub := setupTestHub(t)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+	c, _, err := websocket.Dial(ctx, url, &websocket.DialOptions{
+		HTTPHeader: stdhttp.Header{"Authorization": []string{"Bearer " + token}},
+	})
+	if err != nil {
+		t.Fatalf("dial: %v", err)
+	}
+	defer c.CloseNow() //nolint:errcheck
+
+	hello, _ := api.Marshal(api.MsgHello, "", api.HelloPayload{
+		ProtocolVersion: api.CurrentProtocolVersion,
+		AgentVersion:    "0.1.0",
+		ResticVersion:   "0.17.1",
+		Hostname:        "h1",
+		OS:              api.OSLinux,
+		Arch:            api.ArchAmd64,
+	})
+	helloRaw, _ := json.Marshal(hello)
+	if err := c.Write(ctx, websocket.MessageText, helloRaw); err != nil {
+		t.Fatalf("write hello: %v", err)
+	}
+	deadline := time.Now().Add(time.Second)
+	for !hub.Connected(hostID) && time.Now().Before(deadline) {
+		time.Sleep(10 * time.Millisecond)
+	}
+
+	report, _ := api.Marshal(api.MsgSnapshotsRpt, "", api.SnapshotsReportPayload{
+		Snapshots: []api.Snapshot{{
+			ID:       strings.Repeat("a", 64),
+			ShortID:  "aaaaaaaa",
+			Time:     time.Now().UTC(),
+			Hostname: "h1",
+			Paths:    []string{"/" + strings.Repeat("long-path/", 5000)},
+		}},
+	})
+	reportRaw, _ := json.Marshal(report)
+	if len(reportRaw) <= 32*1024 {
+		t.Fatalf("test payload is only %d bytes; must exceed old limit", len(reportRaw))
+	}
+	if int64(len(reportRaw)) >= api.MaxWebSocketMessageBytes {
+		t.Fatalf("test payload %d exceeds protocol limit", len(reportRaw))
+	}
+	if err := c.Write(ctx, websocket.MessageText, reportRaw); err != nil {
+		t.Fatalf("write snapshots.report: %v", err)
+	}
+
+	deadline = time.Now().Add(2 * time.Second)
+	for time.Now().Before(deadline) {
+		host, err := st.GetHost(context.Background(), hostID)
+		if err == nil && host.SnapshotCount == 1 {
+			return
+		}
+		time.Sleep(10 * time.Millisecond)
+	}
+	t.Fatal("oversized snapshots.report was not projected")
+}
+
 func TestWSRejectsOldProtocol(t *testing.T) {
 	t.Parallel()
 	url, token, _, _, _ := setupTestHub(t)