qwen-code/scripts/prepare-package.js
qqqys b9c5e3566b
feat(voice): voice dictation with native capture, streaming, and biasing (#5502)
* 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>
2026-06-22 14:33:36 +08:00

254 lines
7.6 KiB
JavaScript

/**
* @license
* Copyright 2025 Qwen
* SPDX-License-Identifier: Apache-2.0
*/
/**
* Prepares the bundled CLI package for npm publishing
* This script adds publishing metadata (package.json, README, LICENSE) to dist/
* All runtime assets (cli.js, vendor/, *.sb) are already in dist/ from the bundle step
*/
import fs from 'node:fs';
import path from 'node:path';
import { fileURLToPath } from 'node:url';
const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);
const defaultRootDir = path.resolve(__dirname, '..');
export function preparePackage({ rootDir = defaultRootDir } = {}) {
const distDir = path.join(rootDir, 'dist');
verifyBundleArtifacts(rootDir, distDir);
copyDocumentationFiles(rootDir, distDir);
copyLocales(rootDir, distDir);
copyExtensionExamples(rootDir, distDir);
writeDistPackageJson(rootDir, distDir);
printPackageStructure(distDir);
}
if (isDirectRun()) {
preparePackage();
}
function isDirectRun() {
return process.argv[1]
? fileURLToPath(import.meta.url) === path.resolve(process.argv[1])
: false;
}
function verifyBundleArtifacts(rootDir, distDir) {
const requiredPaths = [
path.join(distDir, 'cli.js'),
path.join(distDir, 'vendor'),
path.join(distDir, 'bundled', 'qc-helper', 'docs'),
// The Web Shell ships with the published package ("Web Shell out of the
// box"). Gate on it here so a build that skipped the web-shell workspace
// (e.g. `npm ci --ignore-scripts` bypassing the root `prepare`) fails
// loudly during packaging instead of silently publishing an API-only CLI
// whose `GET /` 404s. copy_bundle_assets.js stays warn-and-skip for
// --cli-only dev bundles; this is the release gate.
path.join(distDir, 'web-shell', 'index.html'),
path.join(distDir, 'web-shell', 'assets'),
];
if (!fs.existsSync(distDir)) {
console.error('Error: dist/ directory not found');
console.error('Please run "npm run bundle" first');
process.exit(1);
}
for (const requiredPath of requiredPaths) {
if (!fs.existsSync(requiredPath)) {
console.error(
`Error: Required package artifact not found: ${requiredPath}`,
);
console.error('Please run "npm run bundle" first');
process.exit(1);
}
}
}
function copyDocumentationFiles(rootDir, distDir) {
console.log('Copying documentation files...');
const filesToCopy = ['README.md', 'LICENSE'];
for (const file of filesToCopy) {
const sourcePath = path.join(rootDir, file);
const destPath = path.join(distDir, file);
if (fs.existsSync(sourcePath)) {
fs.copyFileSync(sourcePath, destPath);
console.log(`Copied ${file}`);
} else {
console.warn(`Warning: ${file} not found at ${sourcePath}`);
}
}
}
function copyLocales(rootDir, distDir) {
console.log('Copying locales folder...');
const localesSourceDir = path.join(
rootDir,
'packages',
'cli',
'src',
'i18n',
'locales',
);
const localesDestDir = path.join(distDir, 'locales');
if (fs.existsSync(localesSourceDir)) {
copyRecursiveSync(localesSourceDir, localesDestDir);
console.log('Copied locales folder');
} else {
console.warn(`Warning: locales folder not found at ${localesSourceDir}`);
}
}
function copyExtensionExamples(rootDir, distDir) {
console.log('Copying extension examples folder...');
const extensionExamplesDir = path.join(
rootDir,
'packages',
'cli',
'src',
'commands',
'extensions',
'examples',
);
const extensionExamplesDestDir = path.join(distDir, 'examples');
if (fs.existsSync(extensionExamplesDir)) {
copyRecursiveSync(extensionExamplesDir, extensionExamplesDestDir);
console.log('Copied extension examples folder');
} else {
console.warn(
`Warning: extension examples folder not found at ${extensionExamplesDir}`,
);
}
}
function writeDistPackageJson(rootDir, distDir) {
console.log('Creating package.json for distribution...');
const cliEntryContent = `#!/usr/bin/env node
import { spawnSync } from 'node:child_process';
import { fileURLToPath } from 'node:url';
import { dirname, join } from 'node:path';
const __dirname = dirname(fileURLToPath(import.meta.url));
const cliPath = join(__dirname, 'cli.js');
const result = spawnSync(
process.execPath,
['--expose-gc', cliPath, ...process.argv.slice(2)],
{ stdio: 'inherit' },
);
if (result.signal) {
process.kill(process.pid, result.signal);
} else {
process.exit(result.status ?? 1);
}
`;
const cliEntryPath = path.join(distDir, 'cli-entry.js');
fs.writeFileSync(cliEntryPath, cliEntryContent, { mode: 0o755 });
console.log('Created dist cli-entry.js wrapper');
const rootPackageJson = JSON.parse(
fs.readFileSync(path.join(rootDir, 'package.json'), 'utf-8'),
);
const distPackageJson = {
name: rootPackageJson.name,
version: rootPackageJson.version,
description:
rootPackageJson.description || 'Qwen Code - AI-powered coding assistant',
repository: rootPackageJson.repository,
type: 'module',
main: 'cli.js',
bin: {
qwen: 'cli-entry.js',
},
files: [
'cli-entry.js',
'cli.js',
// Worker thread entry loaded by FzfWorkerHandle at runtime via
// `resolveBundleDir(import.meta.url)` + `path.join(dir, 'fzfWorker.js')`.
// Must ship in the tarball or the @-picker silently falls back to the
// in-thread AsyncFzf path on big workspaces in npm-installed CLIs.
'fzfWorker.js',
'chunks',
'vendor',
'*.sb',
'README.md',
'LICENSE',
'locales',
'examples',
'bundled',
'web-shell',
],
config: rootPackageJson.config,
dependencies: {},
optionalDependencies: {
'@qwen-code/audio-capture': rootPackageJson.version,
'@lydell/node-pty': '1.2.0-beta.10',
'@lydell/node-pty-darwin-arm64': '1.2.0-beta.10',
'@lydell/node-pty-darwin-x64': '1.2.0-beta.10',
'@lydell/node-pty-linux-x64': '1.2.0-beta.10',
'@lydell/node-pty-win32-arm64': '1.2.0-beta.10',
'@lydell/node-pty-win32-x64': '1.2.0-beta.10',
'@teddyzhu/clipboard': '0.0.5',
'@teddyzhu/clipboard-darwin-arm64': '0.0.5',
'@teddyzhu/clipboard-darwin-x64': '0.0.5',
'@teddyzhu/clipboard-linux-x64-gnu': '0.0.5',
'@teddyzhu/clipboard-linux-arm64-gnu': '0.0.5',
'@teddyzhu/clipboard-win32-x64-msvc': '0.0.5',
'@teddyzhu/clipboard-win32-arm64-msvc': '0.0.5',
},
engines: rootPackageJson.engines,
};
fs.writeFileSync(
path.join(distDir, 'package.json'),
JSON.stringify(distPackageJson, null, 2) + '\n',
);
}
function printPackageStructure(distDir) {
console.log('\n✅ Package prepared for publishing at dist/');
console.log('\nPackage structure:');
// Use Node.js to list directory contents (cross-platform)
const distFiles = fs.readdirSync(distDir);
for (const file of distFiles) {
const filePath = path.join(distDir, file);
const stats = fs.statSync(filePath);
const size = stats.isDirectory() ? '<DIR>' : formatBytes(stats.size);
console.log(` ${size.padEnd(12)} ${file}`);
}
}
function copyRecursiveSync(src, dest) {
const stats = fs.statSync(src);
if (stats.isDirectory()) {
if (!fs.existsSync(dest)) {
fs.mkdirSync(dest, { recursive: true });
}
const entries = fs.readdirSync(src);
for (const entry of entries) {
const srcPath = path.join(src, entry);
const destPath = path.join(dest, entry);
copyRecursiveSync(srcPath, destPath);
}
} else {
fs.copyFileSync(src, dest);
}
}
function formatBytes(bytes) {
if (bytes < 1024) return `${bytes}B`;
if (bytes < 1024 * 1024) return `${(bytes / 1024).toFixed(1)}KB`;
return `${(bytes / (1024 * 1024)).toFixed(1)}MB`;
}