### Fixes

- TTS: honor explicit short `[[tts:text]]...[[/tts:text]]` blocks while keeping untagged short auto-TTS suppressed, so tagged voice replies are synthesized instead of being dropped as empty voice-only payloads. Fixes #73758. Thanks @yfge.

- Proxy/audio: convert standard `FormData` bodies before proxy-backed undici fetches, so audio transcription and multipart uploads no longer send `[object FormData]` when `HTTP_PROXY` or `HTTPS_PROXY` is configured. Fixes #48554. Thanks @dco5.

- Gateway/diagnostics: include a bounded redacted startup error message in stability bundles, so crash-loop reports identify the failing plugin or contract without exposing secrets. Refs #75797. Thanks @ymebosma.

- Gateway/pricing: abort in-flight model pricing catalog fetches when Gateway shutdown stops the refresh loop, and avoid post-stop cache writes or refresh timers. Fixes #72208. Thanks @rzcq.

});

});

it("synthesizes explicitly tagged short hidden TTS text", async () => {

const cfg = createTtsConfig("openclaw-speech-core-short-hidden-tts-test");

let mediaDir: string | undefined;

try {

const result = await maybeApplyTtsToPayload({

payload: {

text: "[[tts:text]]hello[[/tts:text]]",

audioAsVoice: true,

},

cfg,

channel: "telegram",

kind: "final",

});

expect(synthesizeMock).toHaveBeenCalledWith(expect.objectContaining({ text: "hello" }));

expect(result.mediaUrl).toMatch(/voice-\d+\.ogg$/);

expect(result.audioAsVoice).toBe(true);

expect(result.text).toBeUndefined();

mediaDir = result.mediaUrl ? path.dirname(result.mediaUrl) : undefined;

} finally {

if (mediaDir) {

rmSync(mediaDir, { recursive: true, force: true });

}

}

});

it("keeps skipping untagged short TTS text", async () => {

const cfg = createTtsConfig("openclaw-speech-core-short-plain-tts-test");

const result = await maybeApplyTtsToPayload({

payload: {

text: "hello",

audioAsVoice: true,

},

cfg,

channel: "telegram",

kind: "final",

});

expect(synthesizeMock).not.toHaveBeenCalled();

expect(result).toEqual({

text: "hello",

audioAsVoice: true,

});

});

it("keeps skipping explicit tagged TTS text that strips to empty markdown", async () => {

const cfg = createTtsConfig("openclaw-speech-core-empty-hidden-tts-test");

const result = await maybeApplyTtsToPayload({

payload: {

text: "[[tts:text]]***[[/tts:text]]",

audioAsVoice: true,

},

cfg,

channel: "telegram",

kind: "final",

});

expect(synthesizeMock).not.toHaveBeenCalled();

expect(result).toEqual({

audioAsVoice: true,

});

});

it("selects persona preferred provider before config fallback", () => {

const cfg: OpenClawConfig = {

messages: {

const cleanedText = directives.cleanedText;

const trimmedCleaned = cleanedText.trim();

const visibleText = trimmedCleaned.length > 0 ? trimmedCleaned : "";

const ttsText = directives.ttsText?.trim() || visibleText;

const explicitTtsText = directives.ttsText?.trim() || "";

const ttsText = explicitTtsText || visibleText;

const nextPayload =

visibleText === text.trim()

if (text.includes("MEDIA:")) {

return nextPayload;

}

if (ttsText.trim().length < 10) {

if (!explicitTtsText && ttsText.trim().length < 10) {

return nextPayload;

}

}

textForAudio = stripMarkdown(textForAudio).trim();

if (textForAudio.length < 10) {

if (!textForAudio) {

return nextPayload;

}

if (!explicitTtsText && textForAudio.length < 10) {

return nextPayload;

}