@deepseek-ai/dsh-experimental-client-ui-voice-input 0.1.7-alpha.1

package/lib/index.js

@@ -0,0 +1,6 @@
+//#region lib/types/index.js
+/** Host marker for the optional browser voice input contribution. */
+/** Browser behavior is provided by the client export. */
+function apply() {}
+//#endregion
+export { apply };

package/lib/types/client/PreparationCard.d.ts

@@ -0,0 +1,14 @@
+import type { InjectFace, PropsLocale } from '@deepseek-ai/dsh-client-ui-slots';
+import type { SpeechProviderView } from '@deepseek-ai/dsh-experimental-speech-to-text/types';
+import type { VoiceInputInjected } from './VoiceInput.tsx';
+import { NS } from './locales.ts';
+/** One recognizer's resource readiness and explicit preparation controls. */
+export type PreparationCardProps = Pick<InjectFace<VoiceInputInjected>, 'prepare' | 'cancelPreparation'> & PropsLocale<typeof NS> & {
+    readonly provider: SpeechProviderView;
+    readonly connected: boolean;
+};
+/** Render a collapsed current-step summary or all Host-owned preparation steps. */
+export declare function PreparationCard({ provider, connected, prepare, cancelPreparation, t }: PreparationCardProps): import("react").JSX.Element;
+/** Recognition preferences and preparation cards shared by plugin details and Settings. */
+export declare function VoicePreparation({ useSpeechReadiness, ...props }: InjectFace<VoiceInputInjected> & PropsLocale<typeof NS>): import("react").JSX.Element;
+//# sourceMappingURL=PreparationCard.d.ts.map

package/lib/types/client/VoiceInput.d.ts

@@ -0,0 +1,27 @@
+import type { HostObservable, InjectFace, PropsLocale, PropsRuntime } from '@deepseek-ai/dsh-client-ui-slots';
+import type { TranscriptionRequest } from '@deepseek-ai/dsh-experimental-api-speech-to-text/types';
+import type { SpeechProviderId, SpeechSelectionPatch, Transcript } from '@deepseek-ai/dsh-experimental-speech-to-text/types';
+import type { RemoteResult } from '@deepseek-ai/dsh-typert-protocol';
+import { type Recording } from './audio.ts';
+import type { SpeechReadiness } from './readiness.ts';
+import { NS } from './locales.ts';
+/** Host calls injected without exposing a Cordis Context to React. */
+export interface VoiceInputActions {
+    /** @returns one microphone operation owned by the plugin lifecycle. */
+    createRecording: () => Recording;
+    transcribe: (request: TranscriptionRequest, signal: AbortSignal) => Promise<RemoteResult<Transcript>>;
+    prepare: (providerId: SpeechProviderId) => Promise<void>;
+    cancelPreparation: (providerId: SpeechProviderId) => Promise<void>;
+    configure: (patch: SpeechSelectionPatch) => Promise<void>;
+}
+/** Entry-injected Host readiness and microphone operations. */
+export interface VoiceInputInjected extends VoiceInputActions {
+    hooks: {
+        speechReadiness: HostObservable<SpeechReadiness>;
+    };
+}
+/** Composer-owned expansion and draft actions; preferences stay in plugin settings. */
+export type VoiceInputProps = Pick<PropsRuntime<'conversation.input.activity'>, 'sessionId' | 'inputActions' | 'locked' | 'onActiveChange'> & PropsLocale<typeof NS> & InjectFace<VoiceInputInjected>;
+/** Render a compact microphone or an expanded capture, transcription, or retry row. */
+export declare function VoiceInput({ sessionId, inputActions, locked, onActiveChange, createRecording, transcribe, useSpeechReadiness, t }: VoiceInputProps): import("react").JSX.Element;
+//# sourceMappingURL=VoiceInput.d.ts.map

package/lib/types/client/VoiceSetupPrompt.d.ts

@@ -0,0 +1,12 @@
+import type { InjectFace, PropsLocale, PropsRuntime } from '@deepseek-ai/dsh-client-ui-slots';
+import type { VoiceInputInjected } from './VoiceInput.tsx';
+import type { NS } from './locales.ts';
+/** Registration shares for the bundle's activation guidance. */
+export type VoiceSetupPromptProps = PropsRuntime<'plugins.bundle.activation'> & PropsLocale<typeof NS> & Pick<InjectFace<VoiceInputInjected>, 'useSpeechReadiness'>;
+/**
+ * Offer navigation to installation without starting a download.
+ * @param props - activation navigation and the shared Host readiness observer.
+ * @returns the shared modal only when the selected local provider needs preparation.
+ */
+export declare function VoiceSetupPrompt({ useSpeechReadiness, onDismiss, onOpenDetails, t }: VoiceSetupPromptProps): import("react").JSX.Element;
+//# sourceMappingURL=VoiceSetupPrompt.d.ts.map

package/lib/types/client/Waveform.d.ts

@@ -0,0 +1,7 @@
+import type { Recording } from './audio.ts';
+/** Render recent measured microphone levels; silent audio remains a dotted baseline. */
+export declare function Waveform({ recording, label }: {
+    readonly recording: Recording | undefined;
+    readonly label: string;
+}): import("react").JSX.Element;
+//# sourceMappingURL=Waveform.d.ts.map

package/lib/types/client/audio.d.ts

@@ -0,0 +1,55 @@
+/** Browser-owned microphone capture and native Web Audio resampling. */
+/** Capture failure whose message is localized by the caller. */
+export declare class RecordingError extends Error {
+    readonly kind: 'unavailable' | 'permission' | 'empty' | 'cancelled' | 'interrupted';
+    constructor(kind: 'unavailable' | 'permission' | 'empty' | 'cancelled' | 'interrupted');
+}
+/**
+ * Encode mono floating-point samples as the canonical PCM16 WAV accepted by the Host.
+ * @param samples - native-resampled 16 kHz mono samples.
+ * @returns complete little-endian WAV bytes.
+ */
+export declare function encodeWave(samples: Float32Array): Uint8Array<ArrayBuffer>;
+/**
+ * Encode the binary recording for the existing JSON Remote carrier.
+ * @param bytes - complete recording.
+ * @returns base64 with no data URL prefix.
+ */
+export declare function audioBase64(bytes: Uint8Array): string;
+/** One microphone acquisition, including a permission prompt that may settle after cancellation. */
+export declare class Recording {
+    private readonly onDispose;
+    private stream;
+    private recorder;
+    private context;
+    private analyser;
+    private samples;
+    private chunks;
+    private readonly lifetime;
+    private disposal;
+    constructor(onDispose: () => void);
+    /**
+     * Acquire the microphone for this recording.
+     * @param onError - receives failures during capture, before asynchronous resource release finishes.
+     * @returns after capture starts; a cancelled permission grant immediately releases its tracks.
+     */
+    start(onError?: (error: RecordingError) => void): Promise<void>;
+    /**
+     * Read the live microphone signal.
+     * @returns the measured RMS level, or zero outside capture.
+     */
+    amplitude(): number;
+    /**
+     * Finish capture and resample the recording.
+     * @param maxDurationSeconds - truncate timer overshoot to the Host limit.
+     * @returns one recording after the final MediaRecorder chunk arrives.
+     */
+    stop(maxDurationSeconds: number): Promise<Uint8Array<ArrayBuffer>>;
+    /**
+     * Release this recording and invalidate pending permission grants.
+     * @returns the shared release promise, including any AudioContext close failure.
+     */
+    dispose(): Promise<void>;
+    private release;
+}
+//# sourceMappingURL=audio.d.ts.map

package/lib/types/client/index.d.ts

@@ -0,0 +1,10 @@
+/** Browser entry for the optional speech Remote contribution and composer control. */
+import type { Context } from '@deepseek-ai/cordis';
+export { inject } from './mount.ts';
+/**
+ * Activate the experimental microphone contribution.
+ * @param ctx - Client runtime.
+ * @returns complete UI and Remote disposer.
+ */
+export declare function apply(ctx: Context): Promise<() => Promise<void>>;
+//# sourceMappingURL=index.d.ts.map

package/lib/types/client/locales.d.ts

@@ -0,0 +1,108 @@
+/** Dictionary namespace for every voice control. */
+export declare const NS = "voice-input";
+/** Chinese dictionary and key source. */
+export declare const zh: {
+    readonly dictate: "听写";
+    readonly 'setupPrompt.title': "使用语音输入前需要安装";
+    readonly 'setupPrompt.body': "语音输入插件已开启。首次使用需要在本机下载并准备识别模型，请前往插件详情页查看空间、内存和时间说明，再开始安装。";
+    readonly 'setupPrompt.later': "稍后";
+    readonly 'setupPrompt.open': "前往安装";
+    readonly 'setup.local': "将在运行 DSH 的机器上下载本地模型，无需安装 Python 或编译工具。";
+    readonly 'setup.disk': "硬盘空间";
+    readonly 'setup.diskValue': "建议预留约 {gb} GB，包含模型、运行时和下载缓存";
+    readonly 'setup.memory': "运行内存";
+    readonly 'setup.memoryValue': "模型加载后约 {gb} GB，识别时可能更高";
+    readonly 'setup.time': "首次准备";
+    readonly 'setup.timeValue': "参考 {min}–{max} 分钟，取决于网络和机器性能";
+    readonly 'setup.estimateNote': "以上为估算；网络较慢时可能更久。已下载的资源会复用，默认在闲置后释放模型内存。";
+    readonly 'step.check': "检查本地资源";
+    readonly 'step.model': "准备语音识别模型";
+    readonly 'step.vad': "准备语音检测模型";
+    readonly 'step.verify': "校验模型文件";
+    readonly 'step.load': "加载 {name}";
+    readonly 'stepStatus.pending': "未开始";
+    readonly 'stepStatus.running': "进行中";
+    readonly 'stepStatus.complete': "已完成";
+    readonly 'stepStatus.failed': "失败";
+    readonly 'stepStatus.cancelled': "已取消";
+    readonly 'short.downloading': "下载中";
+    readonly 'short.failed': "准备失败";
+    readonly retryRecording: "重新录音";
+    readonly preparationSteps: "准备步骤";
+    readonly prepare: "下载并准备";
+    readonly retryPrepare: "重试准备";
+    readonly cancelPrepare: "取消准备";
+    readonly downloadProgress: "下载进度";
+    readonly downloadBytes: "下载：{completed} / {total} MB，{percent}%";
+    readonly downloadUnknown: "已下载 {completed} MB";
+    readonly elapsed: "已等待 {seconds} 秒";
+    readonly preparationFailed: "准备失败：{message}";
+    readonly 'download.network': "无法下载 {resource}：连接下载服务失败。";
+    readonly 'download.dns': "无法下载 {resource}：无法解析下载地址。";
+    readonly 'download.timeout': "下载 {resource} 超时。";
+    readonly 'download.certificate': "无法下载 {resource}：安全连接的证书校验失败。";
+    readonly 'download.http': "无法下载 {resource}：下载服务返回 HTTP {status}。";
+    readonly 'download.integrity': "{resource} 下载不完整或文件校验失败。";
+    readonly 'download.storage': "无法保存 {resource}：磁盘空间不足或没有写入权限。";
+    readonly 'download.unknown': "准备 {resource} 失败。";
+    readonly 'downloadAdvice.network': "请检查运行 DSH 的机器能否访问下载来源及其模型下载服务；如需代理，请在该机器上配置后重试。";
+    readonly 'downloadAdvice.dns': "请检查运行 DSH 的机器的 DNS 和代理设置，确认可以解析下载来源的域名后重试。";
+    readonly 'downloadAdvice.timeout': "请检查运行 DSH 的机器的网络或代理连接，稍后重试。已下载并通过校验的文件会保留。";
+    readonly 'downloadAdvice.certificate': "请检查运行 DSH 的机器的系统时间、受信任证书和代理设置后重试。";
+    readonly 'downloadAdvice.http': "请确认下载地址可用、代理可正常连接下载服务，或稍后重试。";
+    readonly 'downloadAdvice.integrity': "请重试下载。已完成并通过校验的其他文件会保留。";
+    readonly 'downloadAdvice.storage': "请检查运行 DSH 的机器的剩余磁盘空间，以及模型目录的写入权限后重试。";
+    readonly 'downloadAdvice.unknown': "请检查运行 DSH 的机器的网络、磁盘空间和模型目录权限后重试。";
+    readonly downloadSource: "下载来源：{source}";
+    readonly downloadCode: "错误码：{code}";
+    readonly reconnecting: "正在连接语音服务…";
+    readonly 'preparation.unprepared': "首次使用需要下载本地识别模型。";
+    readonly 'preparation.checking': "正在检查本地资源…";
+    readonly 'preparation.loading': "正在加载 {name}…";
+    readonly 'preparation.waking': "正在唤醒本地语音…";
+    readonly 'preparation.ready': "本地语音已就绪。";
+    readonly 'preparation.standby': "本地资源已准备，录音时自动唤醒。";
+    readonly 'preparation.cancelled': "准备已取消，已完成的下载会保留。";
+    readonly 'preparation.cancelling': "正在取消准备…";
+    readonly cloudReady: "云端语音识别已就绪。";
+    readonly prepareRequired: "请先在语音插件设置中准备识别服务";
+    readonly discard: "丢弃识别文字";
+    readonly transcribingShort: "识别中…";
+    readonly wakingShort: "唤醒中…";
+    readonly provider: "识别服务";
+    readonly language: "识别语言";
+    readonly auto: "自动识别";
+    readonly zh: "中文";
+    readonly en: "英语";
+    readonly yue: "粤语";
+    readonly ja: "日语";
+    readonly ko: "韩语";
+    readonly start: "开始录音";
+    readonly stop: "停止并识别";
+    readonly cancel: "取消";
+    readonly insert: "插入文字";
+    readonly loading: "正在读取识别服务…";
+    readonly requesting: "请允许使用麦克风…";
+    readonly recording: "正在录音…";
+    readonly interrupted: "录音中断，请重试。";
+    readonly local: "音频在运行 DSH 的机器上识别。首次准备默认从 Hugging Face 下载模型，该机器需要能访问 Hugging Face 及其模型下载服务。如需代理，请在该机器上配置。";
+    readonly cloud: "音频将发送至所选云端服务。";
+    readonly empty: "未识别到语音";
+    readonly cancelled: "已取消语音输入。";
+    readonly conflict: "草稿已被修改。识别文字已保留，可在当前光标位置插入。";
+    readonly failed: "语音识别失败：{message}";
+    readonly unavailable: "当前浏览器不支持录音，请使用支持麦克风的浏览器。";
+    readonly permission: "麦克风权限未开启，请在浏览器和系统设置中允许访问。";
+    readonly tooLarge: "录音超过服务限制，请缩短录音后重试。";
+};
+/** Keys accepted by the voice input translator. */
+export type VoiceKey = keyof typeof zh;
+/** English dictionary with the same complete key set. */
+export declare const en: Record<VoiceKey, string>;
+declare module '@deepseek-ai/dsh-client-ui-slots' {
+    interface LocaleNamespaceMap {
+        /** Experimental microphone and transcription controls. */
+        'voice-input': VoiceKey;
+    }
+}
+//# sourceMappingURL=locales.d.ts.map

package/lib/types/client/mount.d.ts

@@ -0,0 +1,12 @@
+/** Source-safe lifecycle for the optional speech Remote and browser UI. */
+import type { Context } from '@deepseek-ai/cordis';
+import type { TypertRemoteContribution } from '@deepseek-ai/dsh-typert-protocol';
+export declare const inject: string[];
+/**
+ * Mount this experimental namespace without adding it to stable API Remotes.
+ * @param ctx - Client runtime owning the Remote, dictionaries and slots.
+ * @param contribution - generated speech Remote definitions.
+ * @returns disposer joining UI and Remote withdrawal.
+ */
+export declare function mountVoiceInput(ctx: Context, contribution: TypertRemoteContribution): Promise<() => Promise<void>>;
+//# sourceMappingURL=mount.d.ts.map

package/lib/types/client/readiness.d.ts

@@ -0,0 +1,20 @@
+/** One reconnecting Host readiness mirror shared by every voice UI occurrence. */
+import type { Context } from '@deepseek-ai/cordis';
+import { type SnapshotStore } from '@deepseek-ai/dsh-client-store';
+import type { SpeechCatalog } from '@deepseek-ai/dsh-experimental-api-speech-to-text/types';
+/** Complete provider state, with a separate transport failure that never rewrites Host readiness. */
+export interface SpeechReadiness {
+    readonly catalog: SpeechCatalog | null;
+    readonly connected: boolean;
+    readonly error: string | null;
+}
+/**
+ * Subscribe once per Client plugin, independent of rendered pages and Sessions.
+ * @param ctx - mounted speech Remote owner.
+ * @returns shared readiness snapshot and joined observation cleanup.
+ */
+export declare function observeReadiness(ctx: Context): {
+    state: SnapshotStore<SpeechReadiness>;
+    dispose: () => Promise<void>;
+};
+//# sourceMappingURL=readiness.d.ts.map

package/lib/types/index.d.ts

@@ -0,0 +1,4 @@
+/** Host marker for the optional browser voice input contribution. */
+/** Browser behavior is provided by the client export. */
+export declare function apply(): void;
+//# sourceMappingURL=index.d.ts.map

package/package.json

@@ -0,0 +1,97 @@
+{
+  "name": "@deepseek-ai/dsh-experimental-client-ui-voice-input",
+  "description": "Record speech and insert editable text into the conversation draft",
+  "version": "0.1.7-alpha.1",
+  "publishConfig": {
+    "access": "public"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/deepseek-ai/deepseek-harness.git",
+    "directory": "packages/experimental/client-ui-voice-input"
+  },
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json",
+    "./client": {
+      "types": "./lib/types/client/index.d.ts",
+      "default": "./lib/client.js"
+    }
+  },
+  "files": [
+    "lib/index.js",
+    "lib/client.js",
+    "lib/types/**/*.d.ts"
+  ],
+  "license": "MIT",
+  "dependencies": {},
+  "peerDependencies": {
+    "@deepseek-ai/cordis": "^4.0.3",
+    "@deepseek-ai/dsh-api-remotes": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-api-session-controller": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-locale": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-conversation": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-primitives": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-session": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-renderer": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-slots": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-session": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-experimental-speech-to-text": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-api-gateway": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-store": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-typert-protocol": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-plugin-manager": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-experimental-api-speech-to-text": "^0.1.7-alpha.1"
+  },
+  "devDependencies": {
+    "@types/react": "~18.3.1",
+    "react": "^18.2.0",
+    "react-dom": "^18.2.0",
+    "@testing-library/react": "^16.1.0",
+    "@deepseek-ai/dsh-api-remotes": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-api-session-controller": "^0.1.7-alpha.1",
+    "@deepseek-ai/cordis": "^4.0.3",
+    "@deepseek-ai/dsh-client-locale": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-primitives": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-conversation": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-renderer": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-session": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-slots": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-session": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-typert-protocol": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-experimental-api-speech-to-text": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-experimental-speech-to-text": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-test-runtime": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-api-gateway": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-store": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-client-ui-plugin-manager": "^0.1.7-alpha.1"
+  },
+  "dsh": {
+    "client": {
+      "inject": [
+        "@deepseek-ai/dsh-api-remotes",
+        "@deepseek-ai/dsh-api-session-controller",
+        "@deepseek-ai/dsh-client-locale",
+        "@deepseek-ai/dsh-client-ui-conversation",
+        "@deepseek-ai/dsh-client-ui-primitives",
+        "@deepseek-ai/dsh-api-gateway",
+        "@deepseek-ai/dsh-client-ui-plugin-manager"
+      ],
+      "platform": "web",
+      "external": [
+        "@deepseek-ai/dsh-api-gateway/client"
+      ]
+    }
+  },
+  "scripts": {
+    "bundle": "tsdown",
+    "watch": "tsdown --watch"
+  }
+}