feat(34-02): voice onboarding step + PersonalAssistant voice wiring

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Nexus Dev 2026-04-03 22:42:45 +00:00
parent 982d75d0b3
commit c7974fa67c
3 changed files with 135 additions and 12 deletions

View file

@ -22,6 +22,7 @@ import { ModeSelector } from "./onboarding/ModeSelector";
import { HardwareSummaryStep } from "./onboarding/HardwareSummaryStep";
import { ProviderSelectionStep } from "./onboarding/ProviderSelectionStep";
import { OnboardingSummaryStep } from "./onboarding/OnboardingSummaryStep";
import { VoiceStep } from "./onboarding/VoiceStep";
import { useHardwareInfo } from "../hooks/useHardwareInfo";
import { updateNexusSettings, type NexusMode } from "../api/hardware";
import { useChatPanel } from "../context/ChatPanelContext";
@ -37,7 +38,7 @@ function deriveProviderLabel(
return "None selected";
}
// [nexus] 5-step onboarding wizard: hardware detection → mode selection → provider selection → root directory → summary
// [nexus] 6-step onboarding wizard: hardware detection → mode selection → provider selection → voice → root directory → summary
export function OnboardingWizard() {
const { onboardingOpen, onboardingOptions, closeOnboarding } = useDialog();
const { companies, setSelectedCompanyId, loading: companiesLoading } = useCompany();
@ -65,12 +66,15 @@ export function OnboardingWizard() {
setRouteDismissed(false);
}, [location.pathname]);
// Step state: 1 = hardware detection, 2 = mode selection, 3 = provider selection, 4 = root directory, 5 = summary
// Step state: 1 = hardware detection, 2 = mode selection, 3 = provider selection, 4 = voice, 5 = root directory, 6 = summary
const [step, setStep] = useState(1);
// Mode state: "both" pre-selected per UI-SPEC
const [selectedMode, setSelectedMode] = useState<NexusMode>("both");
// Voice preference — captured in step 4
const [voiceEnabled, setVoiceEnabled] = useState(false);
// [nexus] Provider credentials — captured in React state for post-company-creation submission
const [puterToken, setPuterToken] = useState<string | null>(null);
const [googleOAuthStateId, setGoogleOAuthStateId] = useState<string | null>(null);
@ -97,6 +101,7 @@ export function OnboardingWizard() {
setLoading(false);
setStep(1);
setSelectedMode("both");
setVoiceEnabled(false);
setPuterToken(null);
setGoogleOAuthStateId(null);
setApiKeyData(null);
@ -210,6 +215,15 @@ export function OnboardingWizard() {
// Non-blocking — mode defaults to "both" if save fails
}
// Persist voice preference — non-blocking
if (voiceEnabled) {
try {
await updateNexusSettings({ voiceEnabled: true });
} catch {
// Non-blocking
}
}
// [nexus] Store collected provider credentials after company creation — all non-blocking
if (puterToken) {
await puterProxyApi.storeToken(company.id, puterToken).catch(() => {});
@ -248,7 +262,7 @@ export function OnboardingWizard() {
async function handleStartChat() {
// Guard: claude_local requires rootDir
if (defaultAdapter === "claude_local" && !rootDir.trim()) {
setError("Root directory is required for Claude Code. Go back to step 4 to set it.");
setError("Root directory is required for Claude Code. Go back to step 5 to set it.");
return;
}
@ -288,7 +302,7 @@ export function OnboardingWizard() {
>
{/* Step indicator */}
<p className="text-xs text-muted-foreground text-center">
{step === 5 ? "Summary" : `Step ${step} of 4`}
{step === 6 ? "Summary" : `Step ${step} of 5`}
</p>
{/* Step 1 — Hardware Detection */}
@ -397,8 +411,39 @@ export function OnboardingWizard() {
</>
)}
{/* Step 4 — Root Directory (was step 3) */}
{/* Step 4 — Voice */}
{step === 4 && (
<>
<div className="flex flex-col gap-2 text-center">
<h1 className="text-2xl font-semibold tracking-tight">
Voice features
</h1>
<p className="text-sm text-muted-foreground">
Speak to your assistant and hear responses read aloud. Runs entirely on your device.
</p>
</div>
<VoiceStep
onEnable={() => {
setVoiceEnabled(true);
setStep(5);
}}
onSkip={() => setStep(5)}
/>
<Button
type="button"
variant="ghost"
onClick={() => setStep(3)}
className="w-full"
>
Back
</Button>
</>
)}
{/* Step 5 — Root Directory (was step 4) */}
{step === 5 && (
<>
{/* Header */}
<div className="flex flex-col gap-2 text-center">
@ -442,7 +487,7 @@ export function OnboardingWizard() {
<Button
type="button"
onClick={() => setStep(5)}
onClick={() => setStep(6)}
disabled={loading || probing}
className="w-full"
>
@ -452,7 +497,7 @@ export function OnboardingWizard() {
<Button
type="button"
variant="ghost"
onClick={() => setStep(3)}
onClick={() => setStep(4)}
className="w-full"
disabled={loading}
>
@ -462,7 +507,7 @@ export function OnboardingWizard() {
<Button
type="button"
variant="ghost"
onClick={() => setStep(5)}
onClick={() => setStep(6)}
className="w-full"
disabled={loading}
>
@ -472,8 +517,8 @@ export function OnboardingWizard() {
</>
)}
{/* Step 5 — Summary */}
{step === 5 && (
{/* Step 6 — Summary (was step 5) */}
{step === 6 && (
<OnboardingSummaryStep
hardwareInfo={hardwareInfo}
selectedMode={selectedMode}
@ -482,7 +527,7 @@ export function OnboardingWizard() {
loading={loading}
error={error}
onStartChat={handleStartChat}
onBack={() => setStep(4)}
onBack={() => setStep(5)}
/>
)}
</div>

View file

@ -0,0 +1,57 @@
import { useEffect, useState } from "react";
import { Mic, Volume2 } from "lucide-react";
import { Button } from "@/components/ui/button";
interface VoiceStepProps {
onEnable: () => void;
onSkip: () => void;
}
export function VoiceStep({ onEnable, onSkip }: VoiceStepProps) {
const [micAvailable, setMicAvailable] = useState<boolean | null>(null);
useEffect(() => {
navigator.mediaDevices?.enumerateDevices()
.then(devices => setMicAvailable(devices.some(d => d.kind === "audioinput")))
.catch(() => setMicAvailable(false));
}, []);
return (
<div className="flex flex-col gap-4">
<div className="flex flex-col gap-3">
<div className="flex items-center gap-3 rounded-lg border p-3">
<Mic className="h-5 w-5 text-primary shrink-0" />
<div>
<p className="text-sm font-medium">Speech-to-Text (Whisper)</p>
<p className="text-xs text-muted-foreground">
{micAvailable === false
? "No microphone detected — unavailable"
: micAvailable === true
? "Microphone detected — speak to your assistant"
: "Checking microphone..."}
</p>
</div>
</div>
<div className="flex items-center gap-3 rounded-lg border p-3">
<Volume2 className="h-5 w-5 text-primary shrink-0" />
<div>
<p className="text-sm font-medium">Text-to-Speech (Piper)</p>
<p className="text-xs text-muted-foreground">
Hear responses read aloud. Runs entirely on your device no server needed.
</p>
</div>
</div>
</div>
<div className="flex flex-col gap-2">
<Button onClick={onEnable} className="w-full">
Enable voice
</Button>
<Button variant="ghost" onClick={onSkip} className="w-full">
Skip
</Button>
</div>
</div>
);
}

View file

@ -8,6 +8,9 @@ import { useCompany } from "../context/CompanyContext";
import { useToast } from "../context/ToastContext";
import { chatApi } from "../api/chat";
import { Button } from "@/components/ui/button";
import { VoiceRecordButton } from "@/components/VoiceRecordButton";
import { TtsButton } from "@/components/TtsButton";
import { usePiperTts } from "../hooks/usePiperTts";
import type { ChatConversationListItem, ChatMessage } from "@paperclipai/shared";
@ -100,6 +103,7 @@ export function PersonalAssistant() {
const queryClient = useQueryClient();
const navigate = useNavigate();
const { pushToast } = useToast();
const { status: ttsStatus, progress: ttsProgress, prewarm, speak, stop } = usePiperTts();
const [selectedConvId, setSelectedConvId] = useState<string | null>(routeConvId ?? null);
const [isCreating, setIsCreating] = useState(false);
@ -320,7 +324,20 @@ export function PersonalAssistant() {
)}
{messages.map((msg) => (
<MessageBubble key={msg.id} message={msg} />
<div key={msg.id}>
<MessageBubble message={msg} />
{msg.role === "assistant" && msg.content && (
<div className="flex justify-start pl-10 -mt-1 mb-1">
<TtsButton
status={ttsStatus}
progress={ttsProgress}
onSpeak={() => speak(msg.content)}
onStop={stop}
onPrewarm={prewarm}
/>
</div>
)}
</div>
))}
{streamingContent !== null && (
@ -349,6 +366,10 @@ export function PersonalAssistant() {
el.style.height = `${Math.min(el.scrollHeight, 160)}px`;
}}
/>
<VoiceRecordButton
onTranscription={(text) => setInputValue((prev) => prev ? prev + " " + text : text)}
disabled={isSending}
/>
<Button
onClick={handleSend}
disabled={!inputValue.trim() || isSending}