fix(realtime): raise WebRTC data-channel max-message-size + keep sendLoop alive (#10407)

* fix(realtime): raise WebRTC data-channel max-message-size for large events

Browsers advertise a conservative SCTP max-message-size in their SDP offer
(Chrome uses 256 KiB). pion enforces the remote's advertised value on send, so
a single realtime event larger than it cannot be sent over the "oai-events"
data channel: SendText fails, the event is dropped, and the turn silently
yields no response. Some turns legitimately produce a >256 KiB JSON event —
notably tool calls with sizeable schemas or results.

Browsers advertise the value conservatively but their SCTP stacks reassemble
much larger messages, so raise the max-message-size honored for our own
server-generated events by rewriting the attribute in the offer before
SetRemoteDescription.

Assisted-by: Claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(realtime): keep the WebRTC sendLoop alive when one event send fails

A failed SendText on the oai-events data channel exited the sender goroutine,
so a single dropped event (e.g. one over the negotiated SCTP max-message-size)
tore down the session and silently dropped every subsequent event. Log and skip
the offending event instead and keep draining; a genuinely dead transport is
still handled by the closed / connection-state path.

Assisted-by: Claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>

Author: localai-bot

core/http/endpoints/openai/realtime_transport_webrtc.go

@@ -113,16 +113,22 @@ func (t *WebRTCTransport) sendLoop() {
 				return
 			}
 			if err := t.dc.SendText(string(data)); err != nil {
-				xlog.Error("data channel send failed", "error", err)
-				return
+				// Drop just this event and keep the loop alive: a single
+				// failed send (e.g. an event over the negotiated SCTP
+				// max-message-size) must not tear down the session and
+				// silently drop every subsequent event. A genuinely dead
+				// transport is handled by the <-t.closed case.
+				xlog.Error("data channel send failed, dropping event", "error", err)
+				continue
 			}
 		case <-t.closed:
 			// Drain any remaining queued events before exiting
 			for {
 				select {
 				case data := <-t.outEvents:
 					if err := t.dc.SendText(string(data)); err != nil {
-						return
+						xlog.Error("data channel send failed while draining, dropping event", "error", err)
+						continue
 					}
 				default:
 					return

core/http/endpoints/openai/realtime_webrtc.go

@@ -128,10 +128,13 @@ func RealtimeCalls(application *application.Application) echo.HandlerFunc {
 			handleIncomingAudioTrack(track, transport)
 		})
 
-		// Set the remote SDP (client's offer)
+		// Set the remote SDP (client's offer). Raise the data-channel
+		// max-message-size the browser advertised so pion permits the larger
+		// realtime events some turns produce (e.g. tool calls), which would
+		// otherwise be dropped on send. See realtime_webrtc_sctp.go.
 		if err := pc.SetRemoteDescription(webrtc.SessionDescription{
 			Type: webrtc.SDPTypeOffer,
-			SDP:  req.SDP,
+			SDP:  raiseDataChannelMaxMessageSize(req.SDP),
 		}); err != nil {
 			transport.Close()
 			xlog.Error("failed to set remote description", "error", err)

core/http/endpoints/openai/realtime_webrtc_sctp.go

@@ -0,0 +1,29 @@
+package openai
+
+import (
+	"fmt"
+	"regexp"
+)
+
+// realtimeDataChannelMaxMessageSize is the SCTP max-message-size LocalAI honors
+// for the "oai-events" data channel, in bytes.
+//
+// Browsers advertise a conservative max-message-size in their SDP offer (Chrome
+// uses 262144 = 256 KiB). pion enforces the remote's advertised value on send,
+// so a single realtime event larger than it cannot be sent: the SendText fails,
+// the event is dropped, and the turn silently yields no response. Some turns
+// legitimately produce a single JSON event above 256 KiB (notably tool calls
+// with sizeable schemas or results). Browsers advertise this value
+// conservatively but their SCTP stacks reassemble much larger messages, so we
+// raise the value honored for our own server-generated events.
+const realtimeDataChannelMaxMessageSize = 16 * 1024 * 1024 // 16 MiB
+
+var maxMessageSizeAttrRe = regexp.MustCompile(`a=max-message-size:\d+`)
+
+// raiseDataChannelMaxMessageSize rewrites the SCTP max-message-size attribute in
+// an SDP offer to realtimeDataChannelMaxMessageSize so pion permits larger
+// outbound realtime events. Offers that don't carry the attribute are returned
+// unchanged.
+func raiseDataChannelMaxMessageSize(sdp string) string {
+	return maxMessageSizeAttrRe.ReplaceAllString(sdp, fmt.Sprintf("a=max-message-size:%d", realtimeDataChannelMaxMessageSize))
+}

core/http/endpoints/openai/realtime_webrtc_sctp_test.go

@@ -0,0 +1,33 @@
+package openai
+
+import (
+	"fmt"
+	"strings"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+var _ = Describe("raiseDataChannelMaxMessageSize", func() {
+	It("raises a max-message-size the browser advertised", func() {
+		offer := "v=0\r\nm=application 9 UDP/DTLS/SCTP webrtc-datachannel\r\na=max-message-size:262144\r\n"
+		out := raiseDataChannelMaxMessageSize(offer)
+		Expect(out).To(ContainSubstring(fmt.Sprintf("a=max-message-size:%d", realtimeDataChannelMaxMessageSize)))
+		Expect(out).NotTo(ContainSubstring("a=max-message-size:262144"))
+	})
+
+	It("leaves an offer without the attribute unchanged", func() {
+		offer := "v=0\r\nm=application 9 UDP/DTLS/SCTP webrtc-datachannel\r\n"
+		Expect(raiseDataChannelMaxMessageSize(offer)).To(Equal(offer))
+	})
+
+	It("rewrites every occurrence", func() {
+		offer := "a=max-message-size:1024\r\na=max-message-size:262144\r\n"
+		out := raiseDataChannelMaxMessageSize(offer)
+		Expect(strings.Count(out, fmt.Sprintf("a=max-message-size:%d", realtimeDataChannelMaxMessageSize))).To(Equal(2))
+	})
+
+	It("raises above the 256 KiB browsers advertise", func() {
+		Expect(realtimeDataChannelMaxMessageSize).To(BeNumerically(">", 262144))
+	})
+})