mirror of
https://github.com/QwenLM/qwen-code.git
synced 2026-07-09 17:19:02 +00:00
b9c5e3566b
* feat(voice): voice dictation with native capture, streaming, and biasing
Add voice dictation for the prompt input:
- /voice [hold|tap|off|status] command + general.voice.{enabled,mode,language,protocol} settings; push-to-talk via Space, /model --voice to pick the model
- Native microphone capture (@qwen-code/audio-capture, miniaudio N-API) with arecord/SoX fallback, silence auto-stop, cold-start warm-up, and macOS permission query
- Batch transcription via DashScope Qwen-ASR (OpenAI-compatible chat/completions + input_audio) with language + keyterm biasing and an echo guard
- Live streaming over the DashScope realtime WebSocket (fun-asr-realtime / paraformer-realtime-v2) with interim text and an input-level waveform, behind voice.protocol=dashscope-realtime
- Rich VoiceIndicator UI (state, level meter, live partial transcript)
- Cross-platform prebuilds via prebuildify + node-gyp-build and a CI matrix
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
* feat(cli): route voice ASR by model
* feat(cli): polish voice realtime parity
* ci: fix voice workflow checks
* fix(cli): address voice review blockers
* fix(cli): harden voice transcription failures
* fix(cli): address voice PR review blockers
* fix(cli): harden voice review follow-ups
* fix(voice): handle realtime review blockers
* fix(cli): add voice command i18n keys
* fix(cli): address voice review blockers
* fix(cli): address voice review follow-ups
* fix(voice): harden review edge cases
* fix(voice): address release and realtime review blockers
* fix(voice): address realtime suggestion followups
* fix(voice): handle realtime review followups
* fix(voice): address realtime review blockers
* fix(voice): address review feedback
* fix(voice): address recorder review feedback
* docs(voice): document ssrf guard boundary
* fix(voice): address review feedback
* fix(voice): preserve warm recorder session safety
* fix(voice): address stream review suggestions
* fix(voice): address multi-round review findings
Realtime/streaming:
- Salvage an already-committed transcript when the WebSocket closes right
after finish() instead of rejecting the whole dictation
(qwenAsrRealtimeSession, voiceStreamSession) + regression tests.
useVoiceInput state machine:
- Single-shot finalize guard so a tap-stop racing the silence auto-stop can't
double-stop the recorder and surface a spurious failure.
- Reset mountedRef on (re)mount so StrictMode (DEBUG) can't freeze the voice UI.
- Widen the hold-mode first-press release window above common key-repeat delays.
Model selection:
- Reject ids with no ASR transport at /model --voice and in the model dialog via
a new isSelectableVoiceModel; move resolveVoiceTransport into voiceModel so the
record-time config resolver stays transport-agnostic (+ tests).
macOS mic permission:
- Surface the not-determined state in voice warmup so the first dictation isn't
silently lost behind the TCC dialog.
Native packaging:
- Make the audio-capture native install non-fatal (falls back to SoX/arecord) so
a voice-only build failure can't break npm ci.
- Download audio-capture prebuilds before building standalone release archives.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
* fix(voice): address review blockers
* fix(voice): update batch recording audio level
* fix(voice): tap-mode transcript loss, stream leaks, and dead keyterm cleanup
- Tap-mode dictation submitted a stale empty buffer.text, wiping the just-
inserted transcript and sending nothing: thread the resulting prompt text
through onSubmit(text) instead of reading buffer.text back synchronously
after the async insert (useVoiceInput, InputPrompt).
- Streaming finalize leaked the WebSocket session when recorder.drain() threw:
abort the session before propagating the error.
- voiceStreamSession: reject the connect promise when 'task-finished' arrives
before 'task-started' instead of hanging forever in 'transcribing'.
- Remove dead keyterm enrichment (project/branch/recent-file paths were
unreachable after the privacy fix) and the now-inert CJK echo guard, plus the
tests that asserted that removed behavior; fix the misleading "OpenAI prompt
field" comment.
- Add the missing 'Voice Model' and macOS mic-permission i18n keys to
en/zh/zh-TW (they were falling back to English; check-i18n doesn't flag keys
absent from en).
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
* fix(voice): reject partial stream transcripts
* fix(cli): let dialogs consume voice keys first
* fix(voice): reject incomplete qwen realtime transcripts
* fix(voice): handle stream review blockers
* fix(voice): salvage qwen realtime transcript on close
* fix(voice): sanitize streamed transcript text
* test(audio): run audio capture tests in CI
* fix(voice): address review blockers
* fix(voice): report stream close while recording
* fix(voice): reduce keyterm echo false positives
* fix(voice): handle realtime close diagnostics
* fix(voice): address realtime review blockers
* fix(lint): allow legacy voice filenames
* chore(cli): rename voice files to kebab-case
---------
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
152 lines
3.9 KiB
JavaScript
152 lines
3.9 KiB
JavaScript
/**
|
|
* @license
|
|
* Copyright 2026 Qwen Team
|
|
* SPDX-License-Identifier: Apache-2.0
|
|
*/
|
|
|
|
import {
|
|
existsSync,
|
|
mkdirSync,
|
|
mkdtempSync,
|
|
readFileSync,
|
|
readdirSync,
|
|
rmSync,
|
|
writeFileSync,
|
|
} from 'node:fs';
|
|
import { tmpdir } from 'node:os';
|
|
import path from 'node:path';
|
|
import { afterEach, describe, expect, it, vi } from 'vitest';
|
|
import { copyBundleAssets } from '../copy_bundle_assets.js';
|
|
import { preparePackage } from '../prepare-package.js';
|
|
|
|
describe('package asset scripts', () => {
|
|
const tempDirs = [];
|
|
|
|
afterEach(() => {
|
|
vi.restoreAllMocks();
|
|
for (const tempDir of tempDirs.splice(0)) {
|
|
rmSync(tempDir, { force: true, recursive: true });
|
|
}
|
|
});
|
|
|
|
it('copies extension examples into the bundled runtime dist', () => {
|
|
const rootDir = createFixtureRoot();
|
|
stubConsole();
|
|
|
|
copyBundleAssets({ root: rootDir });
|
|
|
|
expect(readdirSync(path.join(rootDir, 'dist', 'examples')).sort()).toEqual([
|
|
'agent',
|
|
'commands',
|
|
'context',
|
|
'mcp-server',
|
|
'skills',
|
|
]);
|
|
expect(
|
|
existsSync(
|
|
path.join(rootDir, 'dist', 'examples', 'mcp-server', 'package.json'),
|
|
),
|
|
).toBe(true);
|
|
});
|
|
|
|
it('includes extension examples in the prepared dist package', () => {
|
|
const rootDir = createFixtureRoot();
|
|
createBundleArtifacts(rootDir);
|
|
stubConsole();
|
|
|
|
preparePackage({ rootDir });
|
|
|
|
const distPackageJson = JSON.parse(
|
|
readFileSync(path.join(rootDir, 'dist', 'package.json'), 'utf8'),
|
|
);
|
|
const rootPackageJson = JSON.parse(
|
|
readFileSync(path.join(rootDir, 'package.json'), 'utf8'),
|
|
);
|
|
|
|
expect(distPackageJson.files).toContain('examples');
|
|
expect(distPackageJson.optionalDependencies).toMatchObject({
|
|
'@qwen-code/audio-capture': rootPackageJson.version,
|
|
});
|
|
expect(
|
|
existsSync(
|
|
path.join(rootDir, 'dist', 'examples', 'mcp-server', 'package.json'),
|
|
),
|
|
).toBe(true);
|
|
});
|
|
|
|
function createFixtureRoot() {
|
|
const rootDir = mkdtempSync(path.join(tmpdir(), 'qwen-package-assets-'));
|
|
tempDirs.push(rootDir);
|
|
|
|
writeFile(rootDir, 'README.md', '# Qwen Code\n');
|
|
writeFile(rootDir, 'LICENSE', 'Apache-2.0\n');
|
|
writeFile(
|
|
rootDir,
|
|
'package.json',
|
|
JSON.stringify(
|
|
{
|
|
name: '@qwen-code/qwen-code',
|
|
version: '0.17.0',
|
|
description: 'Qwen Code',
|
|
repository: {
|
|
type: 'git',
|
|
url: 'https://github.com/QwenLM/qwen-code.git',
|
|
},
|
|
config: {},
|
|
engines: {
|
|
node: '>=22.0.0',
|
|
},
|
|
},
|
|
null,
|
|
2,
|
|
),
|
|
);
|
|
|
|
writeFile(
|
|
rootDir,
|
|
'packages/cli/src/i18n/locales/en.json',
|
|
'{"hello":"world"}\n',
|
|
);
|
|
|
|
for (const template of [
|
|
'agent',
|
|
'commands',
|
|
'context',
|
|
'mcp-server',
|
|
'skills',
|
|
]) {
|
|
writeFile(
|
|
rootDir,
|
|
`packages/cli/src/commands/extensions/examples/${template}/package.json`,
|
|
'{}\n',
|
|
);
|
|
}
|
|
|
|
return rootDir;
|
|
}
|
|
|
|
function createBundleArtifacts(rootDir) {
|
|
writeFile(rootDir, 'dist/cli.js', '');
|
|
mkdirSync(path.join(rootDir, 'dist', 'vendor'), { recursive: true });
|
|
mkdirSync(path.join(rootDir, 'dist', 'bundled', 'qc-helper', 'docs'), {
|
|
recursive: true,
|
|
});
|
|
// Web Shell release gate (prepare-package.js verifyBundleArtifacts): the
|
|
// published package must ship the UI, so the fixture provides it too.
|
|
writeFile(rootDir, 'dist/web-shell/index.html', '<!doctype html>');
|
|
mkdirSync(path.join(rootDir, 'dist', 'web-shell', 'assets'), {
|
|
recursive: true,
|
|
});
|
|
}
|
|
|
|
function writeFile(rootDir, relativePath, content) {
|
|
const filePath = path.join(rootDir, relativePath);
|
|
mkdirSync(path.dirname(filePath), { recursive: true });
|
|
writeFileSync(filePath, content);
|
|
}
|
|
|
|
function stubConsole() {
|
|
vi.spyOn(console, 'log').mockImplementation(() => {});
|
|
vi.spyOn(console, 'warn').mockImplementation(() => {});
|
|
}
|
|
});
|