Files
FabledScribe/frontend/src/components/ChatInputBar.vue
T
bvandeusen 6cf880506d fix(voice): allow WASM compilation in CSP for Silero VAD
Add 'wasm-unsafe-eval' to script-src and blob: to worker-src in
Content-Security-Policy header. Required by onnxruntime-web to compile
the Silero VAD ONNX model. Also surface VAD init errors as a toast
instead of silent console log.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-16 20:10:29 -04:00

668 lines
21 KiB
Vue

<script setup lang="ts">
import { ref, computed, nextTick, onMounted, onUnmounted, watch } from 'vue'
import { apiGet, transcribeAudio } from '@/api/client'
import { useVoiceRecorder } from '@/composables/useVoiceRecorder'
import { useVad } from '@/composables/useVad'
import { useStreamingTts } from '@/composables/useStreamingTts'
import { useVoiceAudio, setVoiceVolume } from '@/composables/useVoiceAudio'
import { useListenMode } from '@/composables/useListenMode'
import { useChatStore } from '@/stores/chat'
import { useSettingsStore } from '@/stores/settings'
import { useToastStore } from '@/stores/toast'
import type { Note } from '@/types/note'
const props = withDefaults(defineProps<{
/** Textarea placeholder */
placeholder?: string
/** When true, hides the note picker (briefing mode) */
briefingMode?: boolean
/** Pill shape — compact rounded style for widget */
pill?: boolean
}>(), {
placeholder: 'Type a message… (Enter to send, Shift+Enter for new line)',
briefingMode: false,
pill: false,
})
const emit = defineEmits<{
submit: [payload: { content: string; contextNoteId?: number }]
abort: []
}>()
const store = useChatStore()
const settingsStore = useSettingsStore()
const voiceEnabled = computed(() => settingsStore.voiceSttReady)
const voiceTtsEnabled = computed(() => settingsStore.voiceTtsReady)
// ── Streaming TTS (listen mode) ───────────────────────────────────────────────
const listenMode = useListenMode()
const audio = useVoiceAudio()
const speakerPopoverOpen = ref(false)
const tts = useStreamingTts({
streamingContent: computed(() => store.streamingContent),
streaming: computed(() => store.streaming),
enabled: computed(() => listenMode.value && voiceTtsEnabled.value),
})
function lastAssistantContent(): string {
const msgs = store.currentConversation?.messages ?? []
return [...msgs].reverse().find((m) => m.role === 'assistant')?.content ?? ''
}
function toggleListen() {
listenMode.value = !listenMode.value
if (listenMode.value) {
tts.speak(lastAssistantContent())
} else {
tts.stop()
}
}
// ── Core input ────────────────────────────────────────────────────────────────
const messageInput = ref('')
const inputEl = ref<HTMLTextAreaElement | null>(null)
const wrapperEl = ref<HTMLElement | null>(null)
function autoResize() {
const el = inputEl.value
if (!el) return
el.style.height = 'auto'
el.style.height = Math.min(el.scrollHeight, 150) + 'px'
}
function resetTextareaHeight() {
const el = inputEl.value
if (!el) return
el.style.height = 'auto'
}
function onInputKeydown(e: KeyboardEvent) {
if (e.key === 'Enter' && !e.shiftKey) {
e.preventDefault()
onSubmit()
}
}
function onSubmit() {
const content = messageInput.value.trim()
if (!content) return
emit('submit', { content, contextNoteId: attachedNote.value?.id })
messageInput.value = ''
attachedNote.value = null
resetTextareaHeight()
}
// ── Note picker ───────────────────────────────────────────────────────────────
const attachedNote = ref<{ id: number; title: string } | null>(null)
const showNotePicker = ref(false)
const noteSearchQuery = ref('')
const noteSearchResults = ref<{ id: number; title: string }[]>([])
const noteSearchLoading = ref(false)
let noteSearchTimer: ReturnType<typeof setTimeout> | null = null
function toggleNotePicker() {
showNotePicker.value = !showNotePicker.value
if (showNotePicker.value) {
noteSearchQuery.value = ''
noteSearchResults.value = []
nextTick(() => {
(wrapperEl.value?.querySelector('.note-picker-search') as HTMLInputElement)?.focus()
})
}
}
function onNoteSearchInput() {
if (noteSearchTimer) clearTimeout(noteSearchTimer)
noteSearchTimer = setTimeout(async () => {
const q = noteSearchQuery.value.trim()
if (!q) { noteSearchResults.value = []; return }
noteSearchLoading.value = true
try {
const data = await apiGet<{ notes: Note[] }>(`/api/notes?q=${encodeURIComponent(q)}&all=true&limit=5`)
noteSearchResults.value = data.notes.map((n) => ({ id: n.id, title: n.title }))
} catch {
noteSearchResults.value = []
} finally {
noteSearchLoading.value = false
}
}, 250)
}
function selectNote(note: { id: number; title: string }) {
attachedNote.value = note
showNotePicker.value = false
}
function removeAttachedNote() {
attachedNote.value = null
}
// ── Voice (click-to-toggle + VAD speech detection) ─────────────────────────
const transcribingVoice = ref(false)
const recorder = useVoiceRecorder()
// Tracks whether VAD detected speech during the current recording session.
// Used to skip the Whisper round-trip when the user manually stops without
// ever speaking — the recording is ambient noise and will transcribe to "".
const vadSawSpeech = ref(false)
const vad = useVad({
onSpeechEnd: () => {
// VAD auto-stop: speech was detected and the user has paused. Proceed
// to transcribe the MediaRecorder output.
void stopRecording(false)
},
onNoSpeech: () => {
useToastStore().show('No speech detected', 'warning')
},
onVadError: (msg) => {
useToastStore().show(`VAD failed: ${msg}`, 'error')
},
})
// Live mic halo. A solid red disc sits behind the mic button and scales
// with `vad.amplitude` (0..1 RMS, already amplified for visibility).
const micGlowStyle = computed(() => {
if (!recorder.recording.value) return { display: 'none' }
const pulse = 0.2 + Math.min(vad.amplitude.value, 1) * 0.8
return {
transform: `translate(-50%, -50%) scale(${1 + pulse * 1.6})`,
opacity: String(0.45 + pulse * 0.4),
}
})
// vad.speaking flips true on speech-start. Watch it once per session to
// capture that speech was detected at some point, without clearing when
// speech ends. This drives the no-speech guard in stopRecording.
watch(() => vad.speaking.value, (on) => {
if (on) vadSawSpeech.value = true
})
async function toggleVoice() {
if (transcribingVoice.value) return
if (recorder.recording.value) {
await stopRecording(true)
} else {
await startRecording()
}
}
async function startRecording() {
if (!voiceEnabled.value || recorder.recording.value) return
if (!recorder.isSupported) {
useToastStore().show('Microphone requires HTTPS or localhost', 'error')
return
}
vadSawSpeech.value = false
await recorder.startRecording()
if (recorder.error.value) {
useToastStore().show(recorder.error.value, 'error')
return
}
if (recorder.stream.value) {
await vad.start(recorder.stream.value)
}
}
async function stopRecording(manual: boolean) {
if (manual) {
await vad.stopAndCheck()
} else {
await vad.stop()
}
if (!recorder.recording.value) return
transcribingVoice.value = true
try {
const blob = await recorder.stopRecording()
// No-speech guard: user manually stopped without VAD seeing speech.
// Skip Whisper — the toast was already shown by onNoSpeech.
if (manual && !vadSawSpeech.value) {
return
}
// Pass last assistant message as context to reduce STT mishearings
const msgs = store.currentConversation?.messages ?? []
const lastAssistant = [...msgs].reverse().find(m => m.role === 'assistant')?.content
const { transcript } = await transcribeAudio(blob, lastAssistant)
if (transcript.trim()) {
messageInput.value = transcript.trim()
await nextTick()
autoResize()
onSubmit()
}
} catch { /* transcription failed silently */ }
finally { transcribingVoice.value = false }
}
// ── Click-outside to dismiss speaker popover ──────────────────────────────────
function onDocumentMousedown(e: MouseEvent) {
if (!speakerPopoverOpen.value) return
const target = e.target as HTMLElement | null
if (!target?.closest('.speaker-wrapper')) speakerPopoverOpen.value = false
}
onMounted(() => document.addEventListener('mousedown', onDocumentMousedown))
onUnmounted(() => document.removeEventListener('mousedown', onDocumentMousedown))
// ── Exposed interface ─────────────────────────────────────────────────────────
function focus() {
inputEl.value?.focus()
}
function prefill(text: string) {
messageInput.value = text
nextTick(() => {
autoResize()
inputEl.value?.focus()
})
}
defineExpose({ focus, prefill })
</script>
<template>
<div ref="wrapperEl" class="chat-input-bar" :class="{ 'chat-input-bar--pill': pill }">
<!-- Attached note pill -->
<div v-if="attachedNote" class="attached-note">
<span class="attached-note-pill">
{{ attachedNote.title }}
<button class="attached-note-remove" aria-label="Remove" @click="removeAttachedNote">&times;</button>
</span>
</div>
<div class="input-row">
<!-- Note picker -->
<div class="note-picker-wrapper">
<button
class="btn-icon"
@click="toggleNotePicker"
:disabled="!store.chatReady"
title="Attach a note"
>
<svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M21.44 11.05l-9.19 9.19a6 6 0 01-8.49-8.49l9.19-9.19a4 4 0 015.66 5.66l-9.2 9.19a2 2 0 01-2.83-2.83l8.49-8.48"/>
</svg>
</button>
<div v-if="showNotePicker" class="note-picker-dropdown">
<input
class="note-picker-search"
v-model="noteSearchQuery"
@input="onNoteSearchInput"
placeholder="Search notes..."
/>
<div class="note-picker-results">
<div
v-for="note in noteSearchResults"
:key="note.id"
class="note-picker-item"
@click="selectNote(note)"
>{{ note.title || 'Untitled' }}</div>
<div v-if="noteSearchLoading" class="note-picker-empty">Searching...</div>
<div v-else-if="noteSearchQuery && !noteSearchResults.length" class="note-picker-empty">No notes found</div>
</div>
</div>
</div>
<!-- Textarea -->
<textarea
ref="inputEl"
v-model="messageInput"
@keydown="onInputKeydown"
@input="autoResize"
:placeholder="!store.chatReady ? 'Chat unavailable' : store.streaming ? 'Type to queue… (Enter to queue)' : placeholder"
:disabled="!store.chatReady"
rows="1"
class="input-textarea"
></textarea>
<!-- Speaker / listen-mode popover -->
<div v-if="voiceTtsEnabled" class="speaker-wrapper">
<button
class="btn-icon btn-speaker"
:class="{ 'speaker-active': listenMode, 'speaker-busy': tts.speaking.value }"
@click="speakerPopoverOpen = !speakerPopoverOpen"
:title="listenMode ? 'Listen mode on' : 'Listen / volume'"
aria-label="Listen and volume settings"
>
<svg v-if="!tts.speaking.value" width="17" height="17" viewBox="0 0 24 24" fill="currentColor">
<path d="M3 9v6h4l5 5V4L7 9H3zm13.5 3c0-1.77-1.02-3.29-2.5-4.03v8.05c1.48-.73 2.5-2.25 2.5-4.02zM14 3.23v2.06c2.89.86 5 3.54 5 6.71s-2.11 5.85-5 6.71v2.06c4.01-.91 7-4.49 7-8.77s-2.99-7.86-7-8.77z"/>
</svg>
<svg v-else width="17" height="17" viewBox="0 0 24 24" fill="currentColor">
<path d="M18 12c0-1.77-1.02-3.29-2.5-4.03v2.21l2.45 2.45c.03-.2.05-.41.05-.63zm2.5 0c0 .94-.2 1.82-.54 2.64l1.51 1.51C21.8 14.82 22 13.43 22 12c0-4.28-2.99-7.86-7-8.77v2.06c2.89.86 5 3.54 5 6.71zM4.27 3L3 4.27 7.73 9H3v6h4l5 5v-6.73l4.25 4.25c-.67.52-1.42.93-2.25 1.18v2.06c1.38-.31 2.63-.95 3.69-1.81L19.73 21 21 19.73l-9-9L4.27 3zM12 4L9.91 6.09 12 8.18V4z"/>
</svg>
</button>
<div v-if="speakerPopoverOpen" class="speaker-popover">
<button
class="speaker-row speaker-row--toggle"
:class="{ 'speaker-row--active': listenMode }"
@click="toggleListen"
>
<span class="speaker-row-label">{{ listenMode ? 'Listening' : 'Read aloud' }}</span>
<span class="speaker-switch" :class="{ on: listenMode }"></span>
</button>
<div class="speaker-row">
<span class="speaker-row-label">Volume</span>
<input
type="range" min="0" max="1" step="0.05"
:value="audio.volume.value"
@input="setVoiceVolume(+($event.target as HTMLInputElement).value)"
class="speaker-volume-range"
aria-label="Volume"
/>
<span class="speaker-volume-pct">{{ Math.round(audio.volume.value * 100) }}%</span>
</div>
<button
v-if="tts.speaking.value"
class="speaker-row speaker-row--stop"
@click="tts.stop()"
>
<svg width="12" height="12" viewBox="0 0 14 14" fill="currentColor"><rect width="14" height="14" rx="2"/></svg>
<span>Stop playback</span>
</button>
</div>
</div>
<!-- PTT mic (with live amplitude halo behind) -->
<div v-if="voiceEnabled" class="mic-wrapper">
<div class="mic-glow" :style="micGlowStyle" aria-hidden="true"></div>
<button
class="btn-icon btn-mic"
:class="{ 'mic-recording': recorder.recording.value, 'mic-transcribing': transcribingVoice }"
@click.prevent="toggleVoice"
:disabled="transcribingVoice || !store.chatReady"
:title="recorder.recording.value ? 'Click to stop (or wait for silence)' : 'Click to speak'"
:aria-label="recorder.recording.value ? 'Stop recording' : 'Start recording'"
>
<svg v-if="!transcribingVoice" width="17" height="17" viewBox="0 0 24 24" fill="currentColor">
<path d="M12 14c1.66 0 3-1.34 3-3V5c0-1.66-1.34-3-3-3S9 3.34 9 5v6c0 1.66 1.34 3 3 3zm-1-9c0-.55.45-1 1-1s1 .45 1 1v6c0 .55-.45 1-1 1s-1-.45-1-1V5zm6 6c0 2.76-2.24 5-5 5s-5-2.24-5-5H5c0 3.53 2.61 6.43 6 6.92V21h2v-3.08c3.39-.49 6-3.39 6-6.92h-2z"/>
</svg>
<svg v-else width="17" height="17" viewBox="0 0 24 24" fill="currentColor">
<circle cx="12" cy="12" r="8" opacity="0.35"/><circle cx="12" cy="12" r="4"/>
</svg>
</button>
</div>
<!-- Abort (streaming) or Send -->
<button
v-if="store.streaming"
class="btn-abort-inline"
@click="emit('abort')"
title="Stop generation"
>
<svg width="14" height="14" viewBox="0 0 14 14" fill="currentColor"><rect width="14" height="14" rx="2"/></svg>
</button>
<button
v-else
class="btn-send"
@click="onSubmit"
:disabled="!messageInput.trim() || !store.chatReady"
>&uarr;</button>
</div>
</div>
</template>
<style scoped>
.chat-input-bar {
width: 100%;
}
.attached-note {
padding: 0.25rem 0.5rem;
}
.attached-note-pill {
display: inline-flex;
align-items: center;
gap: 0.2rem;
background: var(--color-primary);
color: #fff;
border-radius: 10px;
padding: 0.15rem 0.4rem;
font-size: 0.75rem;
}
.attached-note-remove {
background: none;
border: none;
color: rgba(255, 255, 255, 0.7);
cursor: pointer;
font-size: 0.9rem;
line-height: 1;
padding: 0 0.1rem;
}
.attached-note-remove:hover { color: #fff; }
.input-row {
display: flex;
align-items: center;
gap: 0.4rem;
padding: 0.5rem 0.5rem 0.5rem 0.75rem;
background: var(--color-input-bar-bg);
border-radius: 12px;
box-shadow: 0 2px 8px var(--color-shadow);
}
.chat-input-bar--pill .input-row {
border-radius: 24px;
padding: 0.6rem 0.6rem 0.6rem 1rem;
}
.input-textarea {
flex: 1;
resize: none;
padding: 0.35rem 0.5rem;
border: none;
background: transparent;
color: var(--color-input-bar-text);
outline: none;
font-family: inherit;
font-size: 0.9rem;
max-height: 150px;
overflow-y: auto;
}
.input-textarea::placeholder { color: var(--color-input-bar-placeholder); }
.input-textarea:disabled { opacity: 0.5; }
.btn-icon {
background: none;
border: none;
cursor: pointer;
color: var(--color-input-bar-text);
opacity: 0.6;
padding: 0.2rem;
display: flex;
align-items: center;
justify-content: center;
border-radius: var(--radius-sm);
flex-shrink: 0;
}
.btn-icon:hover { opacity: 1; }
.btn-icon:disabled { opacity: 0.3; cursor: default; }
.btn-mic.mic-recording {
opacity: 1;
/* White icon sits on top of the red halo so it stays legible at any
pulse size. */
color: #fff;
position: relative;
z-index: 1;
}
.btn-mic.mic-transcribing { opacity: 0.5; }
/* Mic wrapper + live amplitude halo. The glow is a filled red disc
absolutely positioned behind the button, scaled/faded by the
computed `micGlowStyle` so the user gets unmistakable feedback
that their voice is being picked up while the mic icon itself
stays put and readable on top. */
.mic-wrapper {
position: relative;
display: inline-flex;
align-items: center;
justify-content: center;
flex-shrink: 0;
}
.mic-glow {
position: absolute;
top: 50%;
left: 50%;
width: 28px;
height: 28px;
border-radius: 50%;
background: radial-gradient(
circle,
rgba(239, 68, 68, 0.9) 0%,
rgba(239, 68, 68, 0.6) 55%,
rgba(239, 68, 68, 0) 100%
);
transform: translate(-50%, -50%) scale(1);
transform-origin: center;
pointer-events: none;
/* Smooth between amplitude samples (~100ms) so the pulse feels continuous
rather than stepping. */
transition: transform 0.12s ease-out, opacity 0.12s ease-out;
z-index: 0;
}
.note-picker-wrapper { position: relative; }
.note-picker-dropdown {
position: absolute;
bottom: calc(100% + 8px);
left: 0;
width: 260px;
background: var(--color-bg-card);
border: 1px solid var(--color-border);
border-radius: var(--radius-md);
box-shadow: 0 4px 16px var(--color-shadow);
z-index: 20;
overflow: hidden;
}
.note-picker-search {
width: 100%;
padding: 0.45rem 0.65rem;
border: none;
border-bottom: 1px solid var(--color-border);
background: transparent;
color: var(--color-text);
font-size: 0.85rem;
outline: none;
font-family: inherit;
box-sizing: border-box;
}
.note-picker-results { max-height: 180px; overflow-y: auto; }
.note-picker-item {
padding: 0.4rem 0.65rem;
cursor: pointer;
font-size: 0.85rem;
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
}
.note-picker-item:hover { background: var(--color-bg-secondary); }
.note-picker-empty { padding: 0.4rem 0.65rem; color: var(--color-text-muted); font-size: 0.8rem; }
.btn-send {
width: 30px;
min-width: 30px;
height: 30px;
padding: 0;
display: flex;
align-items: center;
justify-content: center;
background: var(--gradient-cta);
color: #fff;
border: none;
border-radius: 50%;
cursor: pointer;
font-size: 1rem;
flex-shrink: 0;
transition: box-shadow 0.15s;
}
.btn-send:hover { box-shadow: 0 0 16px rgba(124, 58, 237, 0.35); }
.btn-send:disabled { opacity: 0.35; cursor: default; box-shadow: none; }
.btn-abort-inline {
width: 28px;
min-width: 28px;
height: 28px;
padding: 0;
display: flex;
align-items: center;
justify-content: center;
background: var(--color-bg-secondary);
border: 1px solid var(--color-border);
border-radius: 50%;
cursor: pointer;
flex-shrink: 0;
}
.btn-abort-inline:hover { border-color: #ef4444; color: #ef4444; }
/* Speaker / listen-mode popover */
.speaker-wrapper { position: relative; display: inline-flex; flex-shrink: 0; }
.btn-speaker.speaker-active { opacity: 1; color: var(--color-primary); }
.btn-speaker.speaker-busy { opacity: 1; color: #f59e0b; }
.speaker-popover {
position: absolute;
bottom: calc(100% + 8px);
right: 0;
min-width: 220px;
background: var(--color-bg-card);
border: 1px solid var(--color-border);
border-radius: var(--radius-md);
box-shadow: 0 4px 16px var(--color-shadow);
padding: 0.35rem;
z-index: 30;
display: flex;
flex-direction: column;
gap: 0.2rem;
}
.speaker-row {
display: flex;
align-items: center;
gap: 0.6rem;
padding: 0.45rem 0.6rem;
background: none;
border: none;
border-radius: var(--radius-sm);
color: var(--color-text);
font-size: 0.85rem;
cursor: default;
text-align: left;
width: 100%;
}
.speaker-row--toggle { cursor: pointer; }
.speaker-row--toggle:hover { background: var(--color-bg-secondary); }
.speaker-row--active { color: var(--color-primary); }
.speaker-row--stop {
cursor: pointer;
color: var(--color-text-muted);
justify-content: flex-start;
}
.speaker-row--stop:hover { color: #ef4444; background: var(--color-bg-secondary); }
.speaker-row-label { flex: 1; }
.speaker-volume-range { flex: 1; min-width: 0; }
.speaker-volume-pct {
font-size: 0.75rem;
color: var(--color-text-muted);
min-width: 2.5rem;
text-align: right;
}
.speaker-switch {
position: relative;
width: 28px;
height: 16px;
border-radius: 9999px;
background: var(--color-border);
transition: background 0.15s;
flex-shrink: 0;
}
.speaker-switch::after {
content: '';
position: absolute;
top: 2px;
left: 2px;
width: 12px;
height: 12px;
border-radius: 50%;
background: var(--color-bg-card);
transition: transform 0.15s;
}
.speaker-switch.on { background: var(--color-primary); }
.speaker-switch.on::after { transform: translateX(12px); }
</style>