diff --git a/CHANGELOG.md b/CHANGELOG.md
index 2fd8c3968a2..676d1078972 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -16,6 +16,7 @@ Docs: https://docs.openclaw.ai
 - CLI/help: treat positional `help` invocations like `openclaw channels help` as help paths for startup gating, avoiding model/auth warmup while preserving positional arguments such as `openclaw docs help`. Thanks @gumadeiras.
 - Matrix/E2EE: stabilize recovery and broken-device QA flows while avoiding Matrix device-cleanup sync races that could leave shutdown-time crypto work running. Thanks @gumadeiras.
 - Cron: treat isolated run-level agent failures as job errors even when no reply payload is produced, synthesizing a safe error payload so model/provider failures increment error counters and trigger failure notifications instead of clearing as successful. Fixes #43604; carries forward #43631. Thanks @SPFAdvisors.
+- Cron: preserve exact `NO_REPLY` tool results from isolated jobs with empty final assistant turns as quiet successes instead of surfacing incomplete-turn errors. Fixes #68452; carries forward #68453. Thanks @anyech.
 - Cron: classify isolated runs as errors from structured embedded-run execution-denial metadata, with final-output marker fallback for `SYSTEM_RUN_DENIED`, `INVALID_REQUEST`, and approval-binding refusals, so blocked commands no longer appear green in cron history. Fixes #67172; carries forward #67186. Thanks @oc-gh-dr, @hclsys, and @1yihui.
 - Onboarding/GitHub Copilot: add manifest-owned `--github-copilot-token` support for non-interactive setup, including env fallback, tokenRef storage in ref mode, saved-profile reuse, and current Copilot default-model wiring. Refs #50002 and supersedes #50003. Thanks @scottgl9.
 - Gateway/install: add a validated `--wrapper`/`OPENCLAW_WRAPPER` service install path that persists executable LaunchAgent/systemd wrappers across forced reinstalls, updates, and doctor repairs instead of falling back to raw node/bun `ProgramArguments`. Fixes #69400. (#72445) Thanks @willtmc.
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 b5637314703..bd0b27ab1fe 100644
--- a/src/agents/pi-embedded-runner/run.incomplete-turn.test.ts
+++ b/src/agents/pi-embedded-runner/run.incomplete-turn.test.ts
@@ -30,6 +30,7 @@ import {
   STRICT_AGENTIC_BLOCKED_TEXT,
   resolveReplayInvalidFlag,
   resolveRunLivenessState,
+  resolveSilentToolResultReplyPayload,
   shouldTreatEmptyAssistantReplyAsSilent,
 } from "./run/incomplete-turn.js";
 import type { EmbeddedRunAttemptResult } from "./run/types.js";
@@ -76,6 +77,113 @@ describe("runEmbeddedPiAgent incomplete-turn safety", () => {
     expect(result.payloads?.[0]?.text).toContain("verify before retrying");
   });
 
+  it("synthesizes a silent cron payload from a trailing current-attempt NO_REPLY tool result", () => {
+    const payload = resolveSilentToolResultReplyPayload({
+      isCronTrigger: true,
+      payloadCount: 0,
+      aborted: false,
+      timedOut: false,
+      attempt: makeAttemptResult({
+        assistantTexts: [],
+        toolMetas: [{ toolName: "exec" }],
+        messagesSnapshot: [
+          {
+            role: "toolResult",
+            content: [{ type: "text", text: "NO_REPLY" }],
+            details: { aggregated: "NO_REPLY" },
+          } as unknown as EmbeddedRunAttemptResult["messagesSnapshot"][number],
+          {
+            role: "assistant",
+            stopReason: "stop",
+            provider: "openai",
+            model: "gpt-5.4",
+            content: [],
+          } as unknown as EmbeddedRunAttemptResult["messagesSnapshot"][number],
+        ],
+      }),
+    });
+
+    expect(payload).toEqual({ text: "NO_REPLY" });
+  });
+
+  it("does not reuse an older NO_REPLY tool result without current-attempt tool activity", () => {
+    const payload = resolveSilentToolResultReplyPayload({
+      isCronTrigger: true,
+      payloadCount: 0,
+      aborted: false,
+      timedOut: false,
+      attempt: makeAttemptResult({
+        assistantTexts: [],
+        toolMetas: [],
+        messagesSnapshot: [
+          {
+            role: "toolResult",
+            content: [{ type: "text", text: "NO_REPLY" }],
+          } as unknown as EmbeddedRunAttemptResult["messagesSnapshot"][number],
+          {
+            role: "user",
+            content: [{ type: "text", text: "Current cron prompt" }],
+          } as unknown as EmbeddedRunAttemptResult["messagesSnapshot"][number],
+          {
+            role: "assistant",
+            stopReason: "stop",
+            provider: "openai",
+            model: "gpt-5.4",
+            content: [],
+          } as unknown as EmbeddedRunAttemptResult["messagesSnapshot"][number],
+        ],
+      }),
+    });
+
+    expect(payload).toBeNull();
+  });
+
+  it("treats exact NO_REPLY tool output as a quiet cron success when the final assistant is empty", async () => {
+    mockedClassifyFailoverReason.mockReturnValue(null);
+    mockedRunEmbeddedAttempt.mockResolvedValueOnce(
+      makeAttemptResult({
+        assistantTexts: [],
+        toolMetas: [{ toolName: "exec" }],
+        messagesSnapshot: [
+          {
+            role: "toolResult",
+            content: [{ type: "text", text: "NO_REPLY" }],
+            details: { aggregated: "NO_REPLY" },
+          } as unknown as EmbeddedRunAttemptResult["messagesSnapshot"][number],
+          {
+            role: "assistant",
+            stopReason: "stop",
+            provider: "openai",
+            model: "gpt-5.4",
+            content: [],
+          } as unknown as EmbeddedRunAttemptResult["messagesSnapshot"][number],
+        ],
+        lastAssistant: {
+          role: "assistant",
+          stopReason: "stop",
+          provider: "openai",
+          model: "gpt-5.4",
+          content: [],
+        } as unknown as EmbeddedRunAttemptResult["lastAssistant"],
+      }),
+    );
+
+    const result = await runEmbeddedPiAgent({
+      ...overflowBaseRunParams,
+      trigger: "cron",
+      provider: "openai",
+      model: "gpt-5.4",
+      runId: "run-cron-no-reply-empty-final",
+    });
+
+    expect(mockedRunEmbeddedAttempt).toHaveBeenCalledTimes(1);
+    expect(result.payloads).toEqual([{ text: "NO_REPLY" }]);
+    expect(result.meta.livenessState).toBe("working");
+    expect(mockedLog.warn).not.toHaveBeenCalledWith(
+      expect.stringContaining("incomplete turn detected"),
+    );
+  });
+
   it("uses explicit agentId without a session key before surfacing the strict-agentic blocked state", async () => {
     mockedClassifyFailoverReason.mockReturnValue(null);
     mockedRunEmbeddedAttempt.mockResolvedValue(
diff --git a/src/agents/pi-embedded-runner/run.ts b/src/agents/pi-embedded-runner/run.ts
index 3adbcc24131..43070b8ab14 100644
--- a/src/agents/pi-embedded-runner/run.ts
+++ b/src/agents/pi-embedded-runner/run.ts
@@ -119,6 +119,7 @@ import {
   resolvePlanningOnlyRetryLimit,
   resolvePlanningOnlyRetryInstruction,
   resolveReasoningOnlyRetryInstruction,
+  resolveSilentToolResultReplyPayload,
   STRICT_AGENTIC_BLOCKED_TEXT,
   resolveReplayInvalidFlag,
   resolveRunLivenessState,
@@ -1910,7 +1911,19 @@ export async function runEmbeddedPiAgent(
             };
           }
 
-          const payloadCount = payloadsWithToolMedia?.length ?? 0;
+          const silentToolResultReplyPayload = resolveSilentToolResultReplyPayload({
+            isCronTrigger: params.trigger === "cron",
+            payloadCount: payloadsWithToolMedia?.length ?? 0,
+            aborted,
+            timedOut,
+            attempt,
+          });
+          const payloadsForTerminalPath = payloadsWithToolMedia?.length
+            ? payloadsWithToolMedia
+            : silentToolResultReplyPayload
+              ? [silentToolResultReplyPayload]
+              : payloadsWithToolMedia;
+          const payloadCount = payloadsForTerminalPath?.length ?? 0;
           const emptyAssistantReplyIsSilent = shouldTreatEmptyAssistantReplyAsSilent({
             allowEmptyAssistantReplyAsSilent: params.allowEmptyAssistantReplyAsSilent,
             payloadCount,
@@ -2192,7 +2205,7 @@ export async function runEmbeddedPiAgent(
           if (incompleteTurnText) {
             const replayInvalid = resolveReplayInvalidForAttempt(incompleteTurnText);
             const livenessState = resolveRunLivenessState({
-              payloadCount: payloads.length,
+              payloadCount,
               aborted,
               timedOut,
               attempt,
@@ -2205,7 +2218,7 @@ export async function runEmbeddedPiAgent(
             const incompleteStopReason = attempt.lastAssistant?.stopReason;
             log.warn(
               `incomplete turn detected: runId=${params.runId} sessionId=${params.sessionId} ` +
-                `stopReason=${incompleteStopReason} payloads=0 — surfacing error to user`,
+                `stopReason=${incompleteStopReason} payloads=${payloadCount} — surfacing error to user`,
             );
 
             // Mark the failing profile for cooldown so multi-profile setups
@@ -2265,7 +2278,7 @@ export async function runEmbeddedPiAgent(
           }
           const replayInvalid = resolveReplayInvalidForAttempt(null);
           const livenessState = resolveRunLivenessState({
-            payloadCount: payloads.length,
+            payloadCount,
             aborted,
             timedOut,
             attempt,
@@ -2278,7 +2291,7 @@ export async function runEmbeddedPiAgent(
               : (sessionLastAssistant?.stopReason as string | undefined);
           const terminalPayloads = emptyAssistantReplyIsSilent
             ? [{ text: SILENT_REPLY_TOKEN }]
-            : payloadsWithToolMedia;
+            : payloadsForTerminalPath;
           attempt.setTerminalLifecycleMeta?.({
             replayInvalid,
             livenessState,
diff --git a/src/agents/pi-embedded-runner/run/incomplete-turn.ts b/src/agents/pi-embedded-runner/run/incomplete-turn.ts
index e8837d5c3d8..332a25dd7ee 100644
--- a/src/agents/pi-embedded-runner/run/incomplete-turn.ts
+++ b/src/agents/pi-embedded-runner/run/incomplete-turn.ts
@@ -1,7 +1,12 @@
 import type { AgentMessage } from "@mariozechner/pi-agent-core";
-import { isSilentReplyPayloadText, SILENT_REPLY_TOKEN } from "../../../auto-reply/tokens.js";
+import {
+  isSilentReplyPayloadText,
+  isSilentReplyText,
+  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 { collectTextContentBlocks } from "../../content-blocks.js";
 import {
   isStrictAgenticSupportedProviderModel,
   stripProviderPrefix,
@@ -52,6 +57,16 @@ type PlanningOnlyAttempt = Pick<
   | "toolMetas"
 >;
 
+type SilentToolResultAttempt = Pick<
+  EmbeddedRunAttemptResult,
+  | "clientToolCall"
+  | "yieldDetected"
+  | "didSendDeterministicApprovalPrompt"
+  | "lastToolError"
+  | "messagesSnapshot"
+  | "toolMetas"
+>;
+
 type RunLivenessAttempt = Pick<
   EmbeddedRunAttemptResult,
   "lastAssistant" | "promptErrorSource" | "replayMetadata" | "timedOutDuringCompaction"
@@ -253,6 +268,81 @@ function hasOnlySilentAssistantReply(assistantTexts: readonly string[]): boolean
   );
 }
 
+function isToolResultRole(role: string): boolean {
+  return role === "toolresult" || role === "tool_result" || role === "tool";
+}
+
+function readMessageTextContent(message: AgentMessage): string | undefined {
+  const content = (message as { content?: unknown }).content;
+  if (typeof content === "string") {
+    const trimmed = content.trim();
+    return trimmed || undefined;
+  }
+  const text = collectTextContentBlocks(content)
+    .map((item) => item.trim())
+    .filter((item) => item.length > 0)
+    .join("\n");
+  return text || undefined;
+}
+
+function readToolResultAggregatedText(message: AgentMessage): string | undefined {
+  const aggregated = (message as { details?: { aggregated?: unknown } }).details?.aggregated;
+  if (typeof aggregated !== "string") {
+    return undefined;
+  }
+  const trimmed = aggregated.trim();
+  return trimmed || undefined;
+}
+
+function hasTrailingSilentToolResult(messages: readonly AgentMessage[]): boolean {
+  for (let i = messages.length - 1; i >= 0; i -= 1) {
+    const message = messages[i];
+    if (!message) {
+      continue;
+    }
+    const role = normalizeLowercaseStringOrEmpty(message?.role);
+    if (isToolResultRole(role)) {
+      if ((message as { isError?: boolean }).isError === true) {
+        return false;
+      }
+      const text = readMessageTextContent(message) ?? readToolResultAggregatedText(message);
+      return isSilentReplyText(text, SILENT_REPLY_TOKEN);
+    }
+    if (role === "assistant" && !readMessageTextContent(message)) {
+      continue;
+    }
+    return false;
+  }
+  return false;
+}
+
+export function resolveSilentToolResultReplyPayload(params: {
+  isCronTrigger: boolean;
+  payloadCount: number;
+  aborted: boolean;
+  timedOut: boolean;
+  attempt: SilentToolResultAttempt;
+}): { text: typeof SILENT_REPLY_TOKEN } | null {
+  if (
+    !params.isCronTrigger ||
+    params.payloadCount !== 0 ||
+    params.aborted ||
+    params.timedOut ||
+    params.attempt.toolMetas.length === 0 ||
+    params.attempt.clientToolCall ||
+    params.attempt.yieldDetected ||
+    params.attempt.didSendDeterministicApprovalPrompt ||
+    params.attempt.lastToolError ||
+    params.attempt.messagesSnapshot.length === 0
+  ) {
+    return null;
+  }
+
+  return hasTrailingSilentToolResult(params.attempt.messagesSnapshot)
+    ? { text: SILENT_REPLY_TOKEN }
+    : null;
+}
+
 export function resolveReplayInvalidFlag(params: {
   attempt: RunLivenessAttempt;
   incompleteTurnText?: string | null;