diff --git a/CHANGELOG.md b/CHANGELOG.md
index 2c4a35e51b9..30155fbb47d 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -22,6 +22,7 @@ Docs: https://docs.openclaw.ai
 - Gateway/restart: preserve group and channel chat context when resuming an agent turn after a Gateway restart, so continuation replies keep the same prompt, routing, and tool-status behavior as the original conversation.
 - Gateway/pairing: shared-secret loopback CLI clients now silently auto-approve `metadata-upgrade` pairing (platform / device family refresh) instead of being disconnected with `1008 pairing required`. This matches the scope-upgrade and role-upgrade behavior added in #69431 and unblocks non-interactive CLI automation when a paired-device record has a stale platform string (e.g. device key replicated across hosts, install migrated between OSes, or platform-string format changed between OpenClaw versions). Browser / Control-UI clients keep the existing approval-required flow for metadata changes.
 - Gateway/pairing: treat any forwarded-header evidence (`Forwarded`, `X-Forwarded-*`, or `X-Real-IP`) as proxied WebSocket traffic before pairing locality checks, so reverse-proxy topologies cannot use the loopback shared-secret helper auto-pairing path.
+- Agents/OpenAI: treat exact `NO_REPLY` assistant output as a deliberate silent reply in embedded runs, so GPT-5.4 turns with signed reasoning plus a silent final no longer surface a false incomplete-turn error.
 - Gateway/pairing webchat: render `/pair qr` replies as structured media instead of raw markdown text, preserve inline reply threading and silent-control handling on media replies, avoid persisting sensitive QR images into transcript history, and keep local webchat media embedding behind internal-only trust markers. (#70047) Thanks @BunsDev.
 - Codex harness: default app-server runs to unchained local execution, so OpenAI heartbeats can use network and shell tools without stalling behind native Codex approvals or the workspace-write sandbox.
 - Codex harness: apply the GPT-5 behavior and heartbeat prompt overlay to native Codex app-server runs, so `codex/gpt-5.x` sessions get the same follow-through, tool-use, and proactive heartbeat guidance as OpenAI GPT-5 runs.
diff --git a/src/agents/pi-embedded-runner/run.incomplete-turn.test.ts b/src/agents/pi-embedded-runner/run.incomplete-turn.test.ts
index c45376b065e..550ff995505 100644
--- a/src/agents/pi-embedded-runner/run.incomplete-turn.test.ts
+++ b/src/agents/pi-embedded-runner/run.incomplete-turn.test.ts
@@ -23,6 +23,7 @@ import {
   resolveEmptyResponseRetryInstruction,
   resolvePlanningOnlyRetryLimit,
   resolvePlanningOnlyRetryInstruction,
+  resolveIncompleteTurnPayloadText,
   resolveReasoningOnlyRetryInstruction,
   STRICT_AGENTIC_BLOCKED_TEXT,
   resolveReplayInvalidFlag,
@@ -732,6 +733,34 @@ describe("runEmbeddedPiAgent incomplete-turn safety", () => {
     expect(retryInstruction).toBe(REASONING_ONLY_RETRY_INSTRUCTION);
   });
 
+  it("treats exact NO_REPLY as a deliberate silent assistant reply", () => {
+    const incompleteTurnText = resolveIncompleteTurnPayloadText({
+      payloadCount: 0,
+      aborted: false,
+      timedOut: false,
+      attempt: makeAttemptResult({
+        assistantTexts: ["NO_REPLY"],
+        lastAssistant: {
+          role: "assistant",
+          stopReason: "stop",
+          provider: "openai",
+          model: "gpt-5.4",
+          content: [
+            {
+              type: "thinking",
+              thinking: "internal reasoning",
+              thinkingSignature: JSON.stringify({ id: "rs_no_reply", type: "reasoning" }),
+            },
+            { type: "text", text: "" },
+            { type: "text", text: "NO_REPLY" },
+          ],
+        } as unknown as EmbeddedRunAttemptResult["lastAssistant"],
+      }),
+    });
+
+    expect(incompleteTurnText).toBeNull();
+  });
+
   it("does not retry reasoning-only GPT turns after side effects", () => {
     const retryInstruction = resolveReasoningOnlyRetryInstruction({
       provider: "openai",
diff --git a/src/agents/pi-embedded-runner/run/incomplete-turn.ts b/src/agents/pi-embedded-runner/run/incomplete-turn.ts
index 7da969a6398..da543c92f2b 100644
--- a/src/agents/pi-embedded-runner/run/incomplete-turn.ts
+++ b/src/agents/pi-embedded-runner/run/incomplete-turn.ts
@@ -1,4 +1,5 @@
 import type { AgentMessage } from "@mariozechner/pi-agent-core";
+import { isSilentReplyPayloadText, SILENT_REPLY_TOKEN } from "../../../auto-reply/tokens.js";
 import type { EmbeddedPiExecutionContract } from "../../../config/types.agent-defaults.js";
 import { normalizeLowercaseStringOrEmpty } from "../../../shared/string-coerce.js";
 import { isStrictAgenticSupportedProviderModel } from "../../execution-contract.js";
@@ -173,6 +174,10 @@ export function resolveIncompleteTurnPayloadText(params: {
     return null;
   }
 
+  if (hasOnlySilentAssistantReply(params.attempt.assistantTexts)) {
+    return null;
+  }
+
   const stopReason = params.attempt.lastAssistant?.stopReason;
   const incompleteTerminalAssistant = isIncompleteTerminalAssistantTurn({
     hasAssistantVisibleText: params.payloadCount > 0,
@@ -199,6 +204,14 @@ export function resolveIncompleteTurnPayloadText(params: {
     : "⚠️ Agent couldn't generate a response. Please try again.";
 }
 
+function hasOnlySilentAssistantReply(assistantTexts: readonly string[]): boolean {
+  const nonEmptyTexts = assistantTexts.filter((text) => text.trim().length > 0);
+  return (
+    nonEmptyTexts.length > 0 &&
+    nonEmptyTexts.every((text) => isSilentReplyPayloadText(text, SILENT_REPLY_TOKEN))
+  );
+}
+
 export function resolveReplayInvalidFlag(params: {
   attempt: RunLivenessAttempt;
   incompleteTurnText?: string | null;