From f7caf83da49c4214980faca0fe00527646c7395b Mon Sep 17 00:00:00 2001
From: Peter Steinberger <steipete@gmail.com>
Date: Sat, 25 Apr 2026 03:27:03 +0100
Subject: [PATCH] fix(voice-call): coalesce webhook server starts

---
 CHANGELOG.md                              |  1 +
 extensions/voice-call/src/webhook.test.ts | 15 +++++++++++++++
 extensions/voice-call/src/webhook.ts      | 18 ++++++++++++++++--
 3 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 87eadff6c0e..e18ecae0199 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -75,6 +75,7 @@ Docs: https://docs.openclaw.ai
 - Browser/sandbox: clean up idle tracked tabs opened by primary-agent browser sessions, while preserving active tab reuse and lifecycle cleanup for subagents, cron, and ACP sessions. Fixes #71165. Thanks @dwbutler.
 - Plugins/Voice Call: reuse the webhook runtime across in-process plugin contexts, avoiding `EADDRINUSE` when agent tools or CLI commands run while the Gateway already owns the voice webhook port. Fixes #58115. Thanks @sfbrian.
 - Plugins/Voice Call: answer accepted Telnyx inbound Call Control legs on `call.initiated`, so webhooks that reach OpenClaw no longer leave the caller ringing until hangup. Fixes #58231 and #40131. Thanks @KonsultDigital.
+- Plugins/Voice Call: coalesce concurrent webhook server starts on the same runtime instance, avoiding a second `listen()` bind when overlapping startup paths race. Thanks @education-01.
 - Plugins/Voice Call: pin voice response sessions to `responseModel` before embedded agent runs, avoiding live-session model switch failures when the global default model differs. Fixes #60118. Thanks @xinbenlv.
 - Media tools: honor the configured web-fetch SSRF policy for media understanding, image/music/video generation references, and PDF inputs, so explicit RFC2544 opt-ins cover WebChat OSS uploads without weakening defaults. Fixes #71300. (#71321) Thanks @neeravmakwana.
 - Agents/TTS: suppress successful spoken transcripts from verbose chat tool output when structured voice media is already queued, while preserving text output for non-builtin tool-name collisions. Fixes #71282. Thanks @neeravmakwana.
diff --git a/extensions/voice-call/src/webhook.test.ts b/extensions/voice-call/src/webhook.test.ts
index 1c3ee15df7f..f0a13b802b3 100644
--- a/extensions/voice-call/src/webhook.test.ts
+++ b/extensions/voice-call/src/webhook.test.ts
@@ -1002,6 +1002,21 @@ describe("VoiceCallWebhookServer start idempotency", () => {
     }
   });
 
+  it("supports concurrent start() calls without double-binding the port", async () => {
+    const { manager } = createManager([]);
+    const config = createConfig({ serve: { port: 0, bind: "127.0.0.1", path: "/voice/webhook" } });
+    const server = new VoiceCallWebhookServer(config, manager, provider);
+
+    try {
+      const [firstUrl, secondUrl] = await Promise.all([server.start(), server.start()]);
+
+      expectWebhookUrl(firstUrl, "/voice/webhook");
+      expect(secondUrl).toBe(firstUrl);
+    } finally {
+      await server.stop();
+    }
+  });
+
   it("can start again after stop()", async () => {
     const { manager } = createManager([]);
     const config = createConfig({ serve: { port: 0, bind: "127.0.0.1", path: "/voice/webhook" } });
diff --git a/extensions/voice-call/src/webhook.ts b/extensions/voice-call/src/webhook.ts
index 8b35dc93589..24b3a908878 100644
--- a/extensions/voice-call/src/webhook.ts
+++ b/extensions/voice-call/src/webhook.ts
@@ -150,6 +150,7 @@ function buildRealtimeRejectedTwiML(): WebhookResponsePayload {
 export class VoiceCallWebhookServer {
   private server: http.Server | null = null;
   private listeningUrl: string | null = null;
+  private startPromise: Promise<string> | null = null;
   private config: VoiceCallConfig;
   private manager: CallManager;
   private provider: VoiceCallProvider;
@@ -443,7 +444,11 @@ export class VoiceCallWebhookServer {
       await this.initializeMediaStreaming();
     }
 
-    return new Promise((resolve, reject) => {
+    if (this.startPromise) {
+      return this.startPromise;
+    }
+
+    this.startPromise = new Promise((resolve, reject) => {
       this.server = http.createServer((req, res) => {
         this.handleRequest(req, res, webhookPath).catch((err) => {
           console.error("[voice-call] Webhook error:", err);
@@ -468,11 +473,17 @@ export class VoiceCallWebhookServer {
         });
       }
 
-      this.server.on("error", reject);
+      this.server.on("error", (err) => {
+        this.server = null;
+        this.listeningUrl = null;
+        this.startPromise = null;
+        reject(err);
+      });
 
       this.server.listen(port, bind, () => {
         const url = this.resolveListeningUrl(bind, webhookPath);
         this.listeningUrl = url;
+        this.startPromise = null;
         console.log(`[voice-call] Webhook server listening on ${url}`);
         if (this.mediaStreamHandler) {
           const address = this.server?.address();
@@ -491,6 +502,8 @@ export class VoiceCallWebhookServer {
         });
       });
     });
+
+    return this.startPromise;
   }
 
   /**
@@ -502,6 +515,7 @@ export class VoiceCallWebhookServer {
     }
     this.pendingDisconnectHangups.clear();
     this.webhookInFlightLimiter.clear();
+    this.startPromise = null;
 
     if (this.stopStaleCallReaper) {
       this.stopStaleCallReaper();