AI-Profile-Router/integrations/openclaw-athena-talk/test-transcription.mjs

import assert from "node:assert/strict";
import { createServer } from "node:http";
import { test } from "node:test";
import plugin from "./dist/index.js";

async function waitFor(predicate, timeoutMs = 2000) {
  const deadline = Date.now() + timeoutMs;
  while (!predicate()) {
    if (Date.now() >= deadline) throw new Error("timed out waiting for condition");
    await new Promise((resolve) => setTimeout(resolve, 10));
  }
}

test("dictation registers separately and sends G.711 audio to Athena Qwen3-ASR", async () => {
  let transcription;
  plugin.register({
    registerRealtimeTranscriptionProvider: (value) => { transcription = value; },
    registerRealtimeVoiceProvider: () => {},
    registerHttpRoute: () => {},
  });
  assert.equal(transcription.id, "athena-talk");

  let uploads = 0;
  const server = createServer(async (req, res) => {
    uploads += 1;
    assert.equal(req.url, "/v1/audio/transcriptions");
    assert.equal(req.headers.authorization, "Bearer test-key");
    const form = await new Request("http://localhost", {
      method: "POST",
      headers: { "Content-Type": req.headers["content-type"] },
      body: req,
      duplex: "half",
    }).formData();
    const wav = Buffer.from(await form.get("file").arrayBuffer());
    assert.equal(wav.toString("ascii", 0, 4), "RIFF");
    assert.equal(wav.readUInt32LE(24), 8000);
    assert.equal(wav.readUInt16LE(34), 16);
    assert.equal(wav.length, 48);
    assert.equal(form.get("language"), "de");
    assert.equal(form.get("model"), "qwen3-asr");
    res.writeHead(200, { "Content-Type": "application/json" }).end(JSON.stringify({ text: "Hallo Athena" }));
  });
  await new Promise((resolve) => server.listen(0, "127.0.0.1", resolve));
  const cfg = { talk: { realtime: { providers: { "athena-talk": {
    baseUrl: `http://127.0.0.1:${server.address().port}/v1`, apiKey: "test-key", language: "de",
  } } } } };
  const providerConfig = transcription.resolveConfig({ cfg, rawConfig: {} });
  assert.equal(transcription.isConfigured({ cfg, providerConfig }), true);
  try {
    const result = new Promise((resolve, reject) => {
      const session = transcription.createSession({
        cfg, providerConfig,
        onTranscript: resolve,
        onError: reject,
      });
      session.connect().then(() => {
        session.sendAudio(Buffer.from([0xff, 0xff]));
        session.close();
      }, reject);
    });
    assert.equal(await result, "Hallo Athena");
    assert.equal(uploads, 1);
  } finally {
    server.closeAllConnections();
    await new Promise((resolve) => server.close(resolve));
  }
});

test("dictation reuses only a TTS key for the same Athena origin", () => {
  let transcription;
  plugin.register({
    registerRealtimeTranscriptionProvider: (value) => { transcription = value; },
    registerRealtimeVoiceProvider: () => {},
    registerHttpRoute: () => {},
  });
  const base = {
    talk: { realtime: { providers: { "athena-talk": { modelProvider: "llama-cpp" } } } },
    models: { providers: { "llama-cpp": { baseUrl: "http://athena:8081/v1" } } },
  };
  const withTts = (baseUrl) => ({ ...base, tts: { providers: { openai: {
    baseUrl, apiKey: "shared-key",
  } } } });
  assert.equal(transcription.resolveConfig({
    cfg: withTts("http://athena:8081/v1"), rawConfig: {},
  }).apiKey, "shared-key");
  assert.equal(transcription.resolveConfig({
    cfg: withTts("http://other:8081/v1"), rawConfig: {},
  }).apiKey, "");
});

test("long dictation is transcribed incrementally before the recording closes", async () => {
  let transcription;
  plugin.register({
    registerRealtimeTranscriptionProvider: (value) => { transcription = value; },
    registerRealtimeVoiceProvider: () => {},
    registerHttpRoute: () => {},
  });

  const answers = [
    "Dies ist ein langer Abschnitt",
    "langer Abschnitt mit einer Fortsetzung",
    "einer Fortsetzung und einem Ende.",
  ];
  let uploads = 0;
  const server = createServer(async (req, res) => {
    const index = uploads++;
    const form = await new Request("http://localhost", {
      method: "POST",
      headers: { "Content-Type": req.headers["content-type"] },
      body: req,
      duplex: "half",
    }).formData();
    const wav = Buffer.from(await form.get("file").arrayBuffer());
    assert.equal(wav.readUInt32LE(24), 8000);
    if (index > 0) assert.ok(String(form.get("prompt") || "").length > 0);
    res.writeHead(200, { "Content-Type": "application/json" })
      .end(JSON.stringify({ text: answers[index] }));
  });
  await new Promise((resolve) => server.listen(0, "127.0.0.1", resolve));
  const cfg = { talk: { realtime: { providers: { "athena-talk": {
    baseUrl: `http://127.0.0.1:${server.address().port}/v1`, language: "de",
  } } } } };
  const providerConfig = transcription.resolveConfig({ cfg, rawConfig: {} });
  const transcripts = [];
  const errors = [];
  try {
    const session = transcription.createSession({
      cfg,
      providerConfig,
      onTranscript: (text) => transcripts.push(text),
      onError: (error) => errors.push(error),
    });
    await session.connect();

    // Six seconds start the first request while dictation is still active.
    session.sendAudio(Buffer.alloc(48_000, 0xff));
    await waitFor(() => uploads === 1);
    assert.deepEqual(transcripts, []);

    // Another 5.5 seconds form the next overlapping segment. The remaining
    // 2 seconds are finalized only when the user stops dictation.
    session.sendAudio(Buffer.alloc(44_000, 0xff));
    await waitFor(() => uploads === 2);
    session.sendAudio(Buffer.alloc(16_000, 0xff));
    session.close();

    await waitFor(() => transcripts.length === 3);
    assert.deepEqual(transcripts, [
      "Dies ist ein langer Abschnitt",
      "mit einer Fortsetzung",
      "und einem Ende.",
    ]);
    assert.equal(uploads, 3);
    assert.deepEqual(errors, []);
  } finally {
    server.closeAllConnections();
    await new Promise((resolve) => server.close(resolve));
  }
});