fix: disable tts tool for voice provider

CHANGELOG.md

@@ -65,6 +65,7 @@ Docs: https://docs.openclaw.ai
 - Followups/Typing indicator: ensure followup turns mark dispatch idle on every exit path (including `NO_REPLY`, empty payloads, and agent errors) so typing keepalive cleanup always runs and channel typing indicators do not get stuck after queued/silent followups. (#26881) Thanks @codexGW.
 - Telegram/Preview cleanup: keep finalized text previews when a later assistant message is media-only (for example mixed text plus voice turns) by skipping finalized preview archival at assistant-message boundaries, preventing cleanup from deleting already-visible final text messages. (#27042)
 - Slack/Allowlist channels: match channel IDs case-insensitively during channel allowlist resolution so lowercase config keys (for example `c0abc12345`) correctly match Slack runtime IDs (`C0ABC12345`) under `groupPolicy: "allowlist"`, preventing silent channel-event drops. (#26878) Thanks @lbo728.
+- Voice-call/TTS tools: hide the `tts` tool when the message provider is `voice`, preventing voice-call runs from selecting self-playback TTS and falling into silent no-output loops. (#27025)
 - Tests/Low-memory stability: disable Vitest `vmForks` by default on low-memory local hosts (`<64 GiB`), keep low-profile extension lane parallelism at 4 workers, and align cron isolated-agent tests with `setSessionRuntimeModel` usage to avoid deterministic suite failures. (#26324) Thanks @ngutman.
 - Slack/Inbound media fallback: deliver file-only messages even when Slack media downloads fail by adding a filename placeholder fallback, capping fallback names to the shared media-file limit, and normalizing empty filenames to `file` so attachment-only messages are not silently dropped. (#25181) Thanks @justinhuangcode.
 

src/agents/pi-tools.create-openclaw-coding-tools.adds-claude-style-aliases-schemas-without-dropping.test.ts

@@ -319,6 +319,11 @@ describe("createOpenClawCodingTools", () => {
     expect(names.has("telegram")).toBe(false);
     expect(names.has("whatsapp")).toBe(false);
   });
+  it("does not expose tts tool for voice message provider", () => {
+    const tools = createOpenClawCodingTools({ messageProvider: "voice" });
+    const names = new Set(tools.map((tool) => tool.name));
+    expect(names.has("tts")).toBe(false);
+  });
   it("filters session tools for sub-agent sessions by default", () => {
     const tools = createOpenClawCodingTools({
       sessionKey: "agent:main:subagent:test",

src/agents/pi-tools.ts

@@ -217,6 +217,8 @@ export function createOpenClawCodingTools(options?: {
   /** Whether the sender is an owner (required for owner-only tools). */
   senderIsOwner?: boolean;
 }): AnyAgentTool[] {
+  const rawMessageProvider = options?.messageProvider?.trim().toLowerCase();
+  const isVoiceMessageProvider = rawMessageProvider === "voice";
   const execToolName = "exec";
   const sandbox = options?.sandbox?.enabled ? options.sandbox : undefined;
   const {
@@ -480,9 +482,12 @@ export function createOpenClawCodingTools(options?: {
       senderIsOwner: options?.senderIsOwner,
     }),
   ];
+  const toolsForMessageProvider = isVoiceMessageProvider
+    ? tools.filter((tool) => tool.name !== "tts")
+    : tools;
   // Security: treat unknown/undefined as unauthorized (opt-in, not opt-out)
   const senderIsOwner = options?.senderIsOwner === true;
-  const toolsByAuthorization = applyOwnerOnlyToolPolicy(tools, senderIsOwner);
+  const toolsByAuthorization = applyOwnerOnlyToolPolicy(toolsForMessageProvider, senderIsOwner);
   const subagentFiltered = applyToolPolicyPipeline({
     tools: toolsByAuthorization,
     toolMeta: (tool) => getPluginToolMeta(tool),