refactor(agents): use silent token constant in prompts

src/agents/subagent-announce.format.e2e.test.ts

@@ -1,4 +1,5 @@
 import { beforeEach, describe, expect, it, vi } from "vitest";
+import { SILENT_REPLY_TOKEN } from "../auto-reply/tokens.js";
 
 const agentSpy = vi.fn(async () => ({ runId: "run-main", status: "ok" }));
 const sessionsDeleteSpy = vi.fn();
@@ -222,7 +223,7 @@ describe("subagent announce formatting", () => {
     expect(msg).toContain("[sessionId: child-session-usage]");
     expect(msg).toContain("A completed subagent task is ready for user delivery.");
     expect(msg).toContain(
-      "Reply ONLY: NO_REPLY if this exact result was already delivered to the user in this same turn.",
+      `Reply ONLY: ${SILENT_REPLY_TOKEN} if this exact result was already delivered to the user in this same turn.`,
     );
     expect(msg).toContain("step-0");
     expect(msg).toContain("step-139");

src/agents/subagent-announce.ts

@@ -1,4 +1,5 @@
 import { resolveQueueSettings } from "../auto-reply/reply/queue.js";
+import { SILENT_REPLY_TOKEN } from "../auto-reply/tokens.js";
 import { loadConfig } from "../config/config.js";
 import {
   loadSessionStore,
@@ -364,9 +365,9 @@ function buildAnnounceReplyInstruction(params: {
     return `There are still ${params.remainingActiveSubagentRuns} active subagent ${activeRunsLabel} for this session. If they are part of the same workflow, wait for the remaining results before sending a user update. If they are unrelated, respond normally using only the result above.`;
   }
   if (params.requesterIsSubagent) {
-    return "Convert this completion into a concise internal orchestration update for your parent agent in your own words. Keep this internal context private (don't mention system/log/stats/session details or announce type). If this result is duplicate or no update is needed, reply ONLY: NO_REPLY.";
+    return `Convert this completion into a concise internal orchestration update for your parent agent in your own words. Keep this internal context private (don't mention system/log/stats/session details or announce type). If this result is duplicate or no update is needed, reply ONLY: ${SILENT_REPLY_TOKEN}.`;
   }
-  return `A completed ${params.announceType} is ready for user delivery. Convert the result above into your normal assistant voice and send that user-facing update now. Keep this internal context private (don't mention system/log/stats/session details or announce type), and do not copy the system message verbatim. Reply ONLY: NO_REPLY if this exact result was already delivered to the user in this same turn.`;
+  return `A completed ${params.announceType} is ready for user delivery. Convert the result above into your normal assistant voice and send that user-facing update now. Keep this internal context private (don't mention system/log/stats/session details or announce type), and do not copy the system message verbatim. Reply ONLY: ${SILENT_REPLY_TOKEN} if this exact result was already delivered to the user in this same turn.`;
 }
 
 export async function runSubagentAnnounceFlow(params: {

src/agents/system-prompt.e2e.test.ts

@@ -1,4 +1,5 @@
 import { describe, expect, it } from "vitest";
+import { SILENT_REPLY_TOKEN } from "../auto-reply/tokens.js";
 import { buildSubagentSystemPrompt } from "./subagent-announce.js";
 import { buildAgentSystemPrompt, buildRuntimeLine } from "./system-prompt.js";
 
@@ -367,7 +368,7 @@ describe("buildAgentSystemPrompt", () => {
 
     expect(prompt).toContain("message: Send messages and channel actions");
     expect(prompt).toContain("### message tool");
-    expect(prompt).toContain("respond with ONLY: NO_REPLY");
+    expect(prompt).toContain(`respond with ONLY: ${SILENT_REPLY_TOKEN}`);
   });
 
   it("includes runtime provider capabilities when present", () => {

src/agents/system-prompt.ts

@@ -112,7 +112,7 @@ function buildMessagingSection(params: {
     "- Cross-session messaging → use sessions_send(sessionKey, message)",
     "- Sub-agent orchestration → use subagents(action=list|steer|kill)",
     "- `[System Message] ...` blocks are internal context and are not user-visible by default.",
-    "- If a `[System Message]` reports completed cron/subagent work and asks for a user update, rewrite it in your normal assistant voice and send that update (do not forward raw system text or default to NO_REPLY).",
+    `- If a \`[System Message]\` reports completed cron/subagent work and asks for a user update, rewrite it in your normal assistant voice and send that update (do not forward raw system text or default to ${SILENT_REPLY_TOKEN}).`,
     "- Never use exec/curl for provider messaging; OpenClaw handles all routing internally.",
     params.availableTools.has("message")
       ? [

src/agents/tools/tts-tool.test.ts

@@ -0,0 +1,16 @@
+import { describe, expect, it, vi } from "vitest";
+
+vi.mock("../../auto-reply/tokens.js", () => ({
+  SILENT_REPLY_TOKEN: "QUIET_TOKEN",
+}));
+
+const { createTtsTool } = await import("./tts-tool.js");
+
+describe("createTtsTool", () => {
+  it("uses SILENT_REPLY_TOKEN in guidance text", () => {
+    const tool = createTtsTool();
+
+    expect(tool.description).toContain("QUIET_TOKEN");
+    expect(tool.description).not.toContain("NO_REPLY");
+  });
+});

src/agents/tools/tts-tool.ts

@@ -2,6 +2,7 @@ import { Type } from "@sinclair/typebox";
 import type { OpenClawConfig } from "../../config/config.js";
 import type { GatewayMessageChannel } from "../../utils/message-channel.js";
 import type { AnyAgentTool } from "./common.js";
+import { SILENT_REPLY_TOKEN } from "../../auto-reply/tokens.js";
 import { loadConfig } from "../../config/config.js";
 import { textToSpeech } from "../../tts/tts.js";
 import { readStringParam } from "./common.js";
@@ -20,8 +21,7 @@ export function createTtsTool(opts?: {
   return {
     label: "TTS",
     name: "tts",
-    description:
-      "Convert text to speech. Audio is delivered automatically from the tool result — reply with NO_REPLY after a successful call to avoid duplicate messages.",
+    description: `Convert text to speech. Audio is delivered automatically from the tool result — reply with ${SILENT_REPLY_TOKEN} after a successful call to avoid duplicate messages.`,
     parameters: TtsToolSchema,
     execute: async (_toolCallId, args) => {
       const params = args as Record<string, unknown>;

src/auto-reply/reply/dispatch-from-config.test.ts

@@ -138,6 +138,45 @@ describe("dispatchReplyFromConfig", () => {
     );
   });
 
+  it("routes media-only tool results when summaries are suppressed", async () => {
+    mocks.tryFastAbortFromMessage.mockResolvedValue({
+      handled: false,
+      aborted: false,
+    });
+    mocks.routeReply.mockClear();
+    const cfg = {} as OpenClawConfig;
+    const dispatcher = createDispatcher();
+    const ctx = buildTestCtx({
+      Provider: "slack",
+      ChatType: "group",
+      AccountId: "acc-1",
+      OriginatingChannel: "telegram",
+      OriginatingTo: "telegram:999",
+    });
+
+    const replyResolver = async (
+      _ctx: MsgContext,
+      opts: GetReplyOptions | undefined,
+      _cfg: OpenClawConfig,
+    ) => {
+      expect(opts?.onToolResult).toBeDefined();
+      await opts?.onToolResult?.({
+        text: "NO_REPLY",
+        mediaUrls: ["https://example.com/tts-routed.opus"],
+      });
+      return undefined;
+    };
+
+    await dispatchReplyFromConfig({ ctx, cfg, dispatcher, replyResolver });
+
+    expect(dispatcher.sendToolResult).not.toHaveBeenCalled();
+    expect(dispatcher.sendFinalReply).not.toHaveBeenCalled();
+    expect(mocks.routeReply).toHaveBeenCalledTimes(1);
+    const routed = mocks.routeReply.mock.calls[0]?.[0] as { payload?: ReplyPayload } | undefined;
+    expect(routed?.payload?.mediaUrls).toEqual(["https://example.com/tts-routed.opus"]);
+    expect(routed?.payload?.text).toBeUndefined();
+  });
+
   it("provides onToolResult in DM sessions", async () => {
     mocks.tryFastAbortFromMessage.mockResolvedValue({
       handled: false,