Merge pull request 'Release v26.04.07.3' (#23) from dev into main

frontend/src/App.vue

@@ -3,7 +3,6 @@ import { onMounted, onUnmounted, ref, watch } from "vue";
 import { useRouter } from "vue-router";
 import AppHeader from "@/components/AppHeader.vue";
 import ToastNotification from "@/components/ToastNotification.vue";
-import VoiceOverlay from "@/components/VoiceOverlay.vue";
 import { useTheme } from "@/composables/useTheme";
 import { useShortcuts } from "@/composables/useShortcuts";
 import { useAuthStore } from "@/stores/auth";
@@ -26,6 +25,15 @@ function startAppServices() {
   settingsStore.checkVoiceStatus();
   // Sync browser timezone to the server on every login/page load.
   apiPut("/api/settings", { user_timezone: Intl.DateTimeFormat().resolvedOptions().timeZone }).catch(() => {});
+  // Re-check voice status when the tab becomes visible again (model may
+  // have finished loading while the user was away).
+  document.addEventListener("visibilitychange", onVisibilityChange);
+}
+
+function onVisibilityChange() {
+  if (document.visibilityState === "visible" && authStore.isAuthenticated) {
+    settingsStore.checkVoiceStatus();
+  }
 }
 
 function stopAppServices() {
@@ -121,10 +129,6 @@ function onGlobalKeydown(e: KeyboardEvent) {
         router.push("/chat");
       }
       break;
-    case " ":
-      e.preventDefault();
-      document.dispatchEvent(new CustomEvent("voice:ptt-toggle"));
-      break;
   }
 }
 
@@ -155,6 +159,7 @@ watch(
 
 onUnmounted(() => {
   document.removeEventListener("keydown", onGlobalKeydown);
+  document.removeEventListener("visibilitychange", onVisibilityChange);
   stopAppServices();
 });
 </script>
@@ -274,10 +279,6 @@ onUnmounted(() => {
                 <kbd class="shortcut-key">Enter</kbd>
                 <span class="shortcut-desc">New line</span>
               </div>
-              <div class="shortcut-row">
-                <kbd class="shortcut-key">Space</kbd>
-                <span class="shortcut-desc">Tap to speak (voice, when enabled)</span>
-              </div>
             </div>
           </div>
         </div>
@@ -287,7 +288,6 @@ onUnmounted(() => {
   <template v-else>
     <router-view />
   </template>
-  <VoiceOverlay />
   <ToastNotification />
 </template>
 

frontend/src/api/client.ts

@@ -649,9 +649,10 @@ export const getVoiceStatus = () => apiGet<VoiceStatusResult>('/api/voice/status
 export const getVoiceList = () =>
   apiGet<{ voices: VoiceEntry[] }>('/api/voice/voices').then(r => r.voices)
 
-export async function transcribeAudio(blob: Blob): Promise<{ transcript: string; duration_ms: number }> {
+export async function transcribeAudio(blob: Blob, context?: string): Promise<{ transcript: string; duration_ms: number }> {
   const form = new FormData()
   form.append('audio', blob, 'audio.webm')
+  if (context) form.append('context', context)
   const res = await fetch('/api/voice/transcribe', { method: 'POST', body: form })
   if (!res.ok) {
     const err = await res.json().catch(() => ({ error: `HTTP ${res.status}` }))

frontend/src/components/ChatInputBar.vue

@@ -2,8 +2,10 @@
 import { ref, computed, nextTick } from 'vue'
 import { apiGet, transcribeAudio } from '@/api/client'
 import { useVoiceRecorder } from '@/composables/useVoiceRecorder'
+import { useSilenceDetector } from '@/composables/useSilenceDetector'
 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<{
@@ -107,21 +109,46 @@ function removeAttachedNote() {
   attachedNote.value = null
 }
 
-// ── PTT ───────────────────────────────────────────────────────────────────────
+// ── Voice (click-to-toggle + silence detection) ─────────────────────────────
 const transcribingVoice = ref(false)
 const recorder = useVoiceRecorder()
+const silenceDetector = useSilenceDetector()
 
-async function startPtt() {
-  if (!voiceEnabled.value || recorder.recording.value) return
-  await recorder.startRecording()
+async function toggleVoice() {
+  if (transcribingVoice.value) return
+  if (recorder.recording.value) {
+    await stopRecording()
+  } else {
+    await startRecording()
+  }
 }
 
-async function stopPtt() {
+async function startRecording() {
+  if (!voiceEnabled.value || recorder.recording.value) return
+  if (!recorder.isSupported) {
+    useToastStore().show('Microphone requires HTTPS or localhost', 'error')
+    return
+  }
+  await recorder.startRecording()
+  if (recorder.error.value) {
+    useToastStore().show(recorder.error.value, 'error')
+    return
+  }
+  if (recorder.stream.value) {
+    silenceDetector.start(recorder.stream.value, () => stopRecording())
+  }
+}
+
+async function stopRecording() {
+  silenceDetector.stop()
   if (!recorder.recording.value) return
   transcribingVoice.value = true
   try {
     const blob = await recorder.stopRecording()
-    const { transcript } = await transcribeAudio(blob)
+    // 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()
@@ -205,16 +232,13 @@ defineExpose({ focus, prefill })
 
       <!-- PTT mic -->
       <button
-        v-if="voiceEnabled && recorder.isSupported"
+        v-if="voiceEnabled"
         class="btn-icon btn-mic"
         :class="{ 'mic-recording': recorder.recording.value, 'mic-transcribing': transcribingVoice }"
-        @mousedown.prevent="startPtt"
-        @mouseup.prevent="stopPtt"
-        @touchstart.prevent="startPtt"
-        @touchend.prevent="stopPtt"
+        @click.prevent="toggleVoice"
         :disabled="transcribingVoice || !store.chatReady"
-        :title="recorder.recording.value ? 'Release to send' : 'Hold to speak'"
-        aria-label="Push to talk"
+        :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"/>

frontend/src/components/VoiceOverlay.vue

@@ -1,568 +0,0 @@
-<script setup lang="ts">
-/**
- * VoiceOverlay — global floating push-to-talk button.
- *
- * Full flow: record → transcribe → send to voice conv → stream → TTS → play.
- * Manages its own "voice" conversation; does NOT touch the chat store so it
- * never disrupts an open chat session.
- *
- * Space bar toggles PTT when no input field is focused (wired from App.vue via
- * the "voice:ptt-toggle" custom event).
- */
-import { ref, onMounted, onUnmounted, computed } from 'vue'
-import { useVoiceRecorder } from '@/composables/useVoiceRecorder'
-import { useVoiceAudio } from '@/composables/useVoiceAudio'
-import { useSilenceDetector } from '@/composables/useSilenceDetector'
-import { apiPost, apiSSEStream, getVoiceStatus, transcribeAudio, synthesiseSpeech } from '@/api/client'
-
-// ─── Voice service availability ──────────────────────────────────────────────
-const voiceEnabled = ref(false)
-
-async function checkVoice() {
-  try {
-    const s = await getVoiceStatus()
-    voiceEnabled.value = s.enabled && s.stt && s.tts
-  } catch { /* feature absent */ }
-}
-
-// ─── Conversation management ─────────────────────────────────────────────────
-const STORAGE_KEY = 'voice_overlay_conv_id'
-const convId = ref<number | null>(Number(localStorage.getItem(STORAGE_KEY)) || null)
-
-interface VoiceMessage { role: 'user' | 'assistant'; content: string }
-const messages = ref<VoiceMessage[]>([])
-
-async function ensureConversation(): Promise<number> {
-  if (convId.value) {
-    // Verify it still exists
-    try {
-      await fetch(`/api/chat/conversations/${convId.value}`)
-        .then((r) => { if (!r.ok) throw new Error('gone') })
-      return convId.value
-    } catch {
-      convId.value = null
-      localStorage.removeItem(STORAGE_KEY)
-    }
-  }
-  const conv = await apiPost<{ id: number }>('/api/chat/conversations', {
-    title: 'Voice',
-    conversation_type: 'voice',
-  })
-  convId.value = conv.id
-  localStorage.setItem(STORAGE_KEY, String(conv.id))
-  return conv.id
-}
-
-// ─── State machine ────────────────────────────────────────────────────────────
-type Phase = 'idle' | 'recording' | 'transcribing' | 'generating' | 'speaking' | 'error'
-const phase = ref<Phase>('idle')
-const errorMsg = ref('')
-const streamContent = ref('')
-const open = ref(false)
-
-const isBusy = computed(() => phase.value !== 'idle' && phase.value !== 'error')
-
-// ─── Composables ─────────────────────────────────────────────────────────────
-const recorder = useVoiceRecorder()
-const audio = useVoiceAudio()
-const silenceDetector = useSilenceDetector()
-
-// ─── Core PTT flow ────────────────────────────────────────────────────────────
-async function startPtt() {
-  if (!voiceEnabled.value || isBusy.value) return
-  // Stop any in-progress TTS playback before opening the mic
-  audio.stop()
-  errorMsg.value = ''
-  open.value = true
-  await recorder.startRecording()
-  if (recorder.error.value) {
-    phase.value = 'error'
-    errorMsg.value = recorder.error.value
-    return
-  }
-  phase.value = 'recording'
-  if (recorder.stream.value) {
-    silenceDetector.start(recorder.stream.value, stopPtt)
-  }
-}
-
-async function stopPtt() {
-  silenceDetector.stop()
-  if (phase.value !== 'recording') return
-
-  phase.value = 'transcribing'
-  let blob: Blob
-  try {
-    blob = await recorder.stopRecording()
-  } catch {
-    phase.value = 'error'
-    errorMsg.value = 'Recording failed'
-    return
-  }
-
-  let transcript: string
-  try {
-    const result = await transcribeAudio(blob)
-    transcript = result.transcript.trim()
-  } catch {
-    phase.value = 'error'
-    errorMsg.value = 'Transcription failed'
-    return
-  }
-
-  if (!transcript) {
-    phase.value = 'idle'
-    return
-  }
-
-  messages.value.push({ role: 'user', content: transcript })
-  scrollToBottom()
-
-  // Send to voice conversation
-  phase.value = 'generating'
-  streamContent.value = ''
-
-  let cid: number
-  try {
-    cid = await ensureConversation()
-  } catch {
-    phase.value = 'error'
-    errorMsg.value = 'Could not create voice conversation'
-    return
-  }
-
-  let assistantMessageId: number
-  try {
-    const resp = await apiPost<{ assistant_message_id: number }>(
-      `/api/chat/conversations/${cid}/messages`,
-      {
-        content: transcript,
-        user_timezone: Intl.DateTimeFormat().resolvedOptions().timeZone,
-      }
-    )
-    assistantMessageId = resp.assistant_message_id
-  } catch {
-    phase.value = 'error'
-    errorMsg.value = 'Failed to send message'
-    return
-  }
-
-  // Stream the response
-  await new Promise<void>((resolve) => {
-    const handle = apiSSEStream(
-      `/api/chat/conversations/${cid}/generation/stream`,
-      (event) => {
-        switch (event.event) {
-          case 'chunk':
-            streamContent.value += event.data.chunk as string
-            break
-          case 'done':
-            handle.close()
-            resolve()
-            break
-          case 'error':
-            handle.close()
-            resolve()
-            break
-        }
-      }
-    )
-    // Safety timeout: 3 minutes
-    setTimeout(() => { handle.close(); resolve() }, 180_000)
-  })
-
-  const responseText = streamContent.value.trim()
-  if (responseText) {
-    messages.value.push({ role: 'assistant', content: responseText })
-    streamContent.value = ''
-    scrollToBottom()
-  }
-
-  // Synthesise and play
-  if (responseText) {
-    phase.value = 'speaking'
-    try {
-      const wavBlob = await synthesiseSpeech(responseText)
-      await audio.play(wavBlob)
-    } catch {
-      // TTS failure is non-critical; show response text
-    }
-  }
-
-  phase.value = 'idle'
-  assistantMessageId // consumed; suppress lint
-}
-
-function onBtnClick() {
-  if (phase.value === 'error') { phase.value = 'idle'; return }
-  if (phase.value === 'recording') { stopPtt(); return }
-  if (phase.value === 'idle') { startPtt() }
-}
-
-function cancelAll() {
-  silenceDetector.stop()
-  recorder.stopRecording().catch(() => {})
-  audio.stop()
-  phase.value = 'idle'
-  streamContent.value = ''
-  errorMsg.value = ''
-}
-
-// ─── Space bar PTT (event from App.vue) ──────────────────────────────────────
-function onPttToggle() {
-  if (!voiceEnabled.value) return
-  if (phase.value === 'recording') {
-    stopPtt()
-  } else if (phase.value === 'idle' || phase.value === 'error') {
-    startPtt()
-  }
-}
-
-// ─── Scroll ───────────────────────────────────────────────────────────────────
-const transcriptEl = ref<HTMLElement | null>(null)
-function scrollToBottom() {
-  setTimeout(() => {
-    if (transcriptEl.value) {
-      transcriptEl.value.scrollTop = transcriptEl.value.scrollHeight
-    }
-  }, 50)
-}
-
-// ─── Lifecycle ────────────────────────────────────────────────────────────────
-onMounted(() => {
-  checkVoice()
-  document.addEventListener('voice:ptt-toggle', onPttToggle)
-})
-
-onUnmounted(() => {
-  document.removeEventListener('voice:ptt-toggle', onPttToggle)
-  cancelAll()
-})
-</script>
-
-<template>
-  <Teleport to="body">
-    <div v-if="voiceEnabled" class="voice-overlay">
-
-      <!-- Expanded transcript panel -->
-      <Transition name="panel-slide">
-        <div v-if="open && messages.length > 0" class="voice-panel">
-          <div class="voice-panel-header">
-            <span class="voice-panel-title">Voice</span>
-            <button class="voice-panel-close" @click="open = false" aria-label="Close">×</button>
-          </div>
-          <div class="voice-transcript" ref="transcriptEl">
-            <div
-              v-for="(msg, i) in messages.slice(-10)"
-              :key="i"
-              :class="['voice-msg', `voice-msg--${msg.role}`]"
-            >{{ msg.content }}</div>
-            <!-- Live streaming text -->
-            <div v-if="phase === 'generating' && streamContent" class="voice-msg voice-msg--assistant voice-msg--streaming">
-              {{ streamContent }}<span class="voice-cursor">▌</span>
-            </div>
-          </div>
-        </div>
-      </Transition>
-
-      <!-- PTT button -->
-      <div class="voice-btn-wrap">
-        <!-- Status label -->
-        <div v-if="phase !== 'idle'" class="voice-status-label">
-          <span v-if="phase === 'recording'">Recording…</span>
-          <span v-else-if="phase === 'transcribing'">Transcribing…</span>
-          <span v-else-if="phase === 'generating'">Thinking…</span>
-          <span v-else-if="phase === 'speaking'">Speaking…</span>
-          <span v-else-if="phase === 'error'" class="voice-error-label">{{ errorMsg || 'Error' }}</span>
-        </div>
-        <div v-else-if="!open || !messages.length" class="voice-status-label voice-hint">
-          Tap or press <kbd>Space</kbd>
-        </div>
-
-        <!-- Cancel button (shown while busy or speaking) -->
-        <button
-          v-if="isBusy || audio.playing.value"
-          class="voice-cancel"
-          @click="cancelAll"
-          aria-label="Cancel"
-          title="Cancel"
-        >
-          <svg width="13" height="13" viewBox="0 0 24 24" fill="currentColor">
-            <path d="M19 6.41L17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/>
-          </svg>
-        </button>
-
-        <!-- Main PTT button -->
-        <button
-          class="voice-ptt-btn"
-          :class="{
-            'voice-ptt--recording': phase === 'recording',
-            'voice-ptt--busy': phase === 'generating' || phase === 'transcribing',
-            'voice-ptt--speaking': phase === 'speaking' || audio.playing.value,
-            'voice-ptt--error': phase === 'error',
-          }"
-          @click.prevent="onBtnClick"
-          :disabled="phase === 'transcribing' || phase === 'generating'"
-          :aria-label="phase === 'recording' ? 'Click to stop' : 'Click to speak'"
-          :title="phase === 'recording' ? 'Click to stop or wait for silence' : 'Click or press Space to speak'"
-        >
-          <!-- Idle: mic icon -->
-          <svg v-if="phase === 'idle' || phase === 'error'" width="22" height="22" 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>
-          <!-- Recording: amplitude bars -->
-          <span v-else-if="phase === 'recording'" class="voice-amp-bars">
-            <span
-              v-for="n in 3"
-              :key="n"
-              class="voice-amp-bar"
-              :style="{ transform: `scaleY(${0.3 + silenceDetector.amplitude.value * (0.4 + n * 0.15)})` }"
-            ></span>
-          </span>
-          <!-- Busy: spinner dots -->
-          <span v-else-if="phase === 'transcribing' || phase === 'generating'" class="voice-spinner">
-            <span></span><span></span><span></span>
-          </span>
-          <!-- Speaking: sound waves -->
-          <svg v-else-if="phase === 'speaking'" width="22" height="22" 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>
-        </button>
-      </div>
-
-    </div>
-  </Teleport>
-</template>
-
-<style scoped>
-.voice-overlay {
-  position: fixed;
-  bottom: 2rem;
-  right: 1.5rem;
-  z-index: 8000;
-  display: flex;
-  flex-direction: column;
-  align-items: flex-end;
-  gap: 0.5rem;
-  pointer-events: none;
-}
-
-/* ─── Panel ──────────────────────────────────────────────────────────────── */
-.voice-panel {
-  pointer-events: all;
-  width: min(320px, 90vw);
-  background: var(--color-bg-card);
-  border: 1px solid var(--color-border);
-  border-radius: 14px;
-  box-shadow: 0 8px 32px var(--color-shadow, rgba(0,0,0,0.22));
-  overflow: hidden;
-  display: flex;
-  flex-direction: column;
-  max-height: 340px;
-}
-
-.voice-panel-header {
-  display: flex;
-  align-items: center;
-  justify-content: space-between;
-  padding: 0.6rem 0.85rem 0.5rem;
-  border-bottom: 1px solid var(--color-border);
-  flex-shrink: 0;
-}
-.voice-panel-title {
-  font-size: 0.75rem;
-  font-weight: 700;
-  text-transform: uppercase;
-  letter-spacing: 0.07em;
-  color: var(--color-primary);
-}
-.voice-panel-close {
-  background: none;
-  border: none;
-  font-size: 1.3rem;
-  line-height: 1;
-  color: var(--color-text-muted);
-  cursor: pointer;
-  padding: 0 0.1rem;
-}
-.voice-panel-close:hover { color: var(--color-text); }
-
-.voice-transcript {
-  flex: 1;
-  overflow-y: auto;
-  padding: 0.65rem 0.85rem;
-  display: flex;
-  flex-direction: column;
-  gap: 0.45rem;
-}
-
-.voice-msg {
-  font-size: 0.875rem;
-  line-height: 1.45;
-  padding: 0.4rem 0.65rem;
-  border-radius: 10px;
-  max-width: 88%;
-  white-space: pre-wrap;
-  word-break: break-word;
-}
-.voice-msg--user {
-  align-self: flex-end;
-  background: color-mix(in srgb, var(--color-primary) 12%, transparent);
-  border: 1px solid color-mix(in srgb, var(--color-primary) 25%, transparent);
-  color: var(--color-text);
-}
-.voice-msg--assistant {
-  align-self: flex-start;
-  background: var(--color-bg-secondary);
-  border: 1px solid var(--color-border);
-  color: var(--color-text);
-}
-.voice-msg--streaming { opacity: 0.85; }
-.voice-cursor {
-  display: inline-block;
-  animation: blink 0.9s step-end infinite;
-  margin-left: 1px;
-  color: var(--color-primary);
-}
-@keyframes blink { 0%, 100% { opacity: 1; } 50% { opacity: 0; } }
-
-/* ─── Button cluster ─────────────────────────────────────────────────────── */
-.voice-btn-wrap {
-  pointer-events: all;
-  display: flex;
-  flex-direction: column;
-  align-items: flex-end;
-  gap: 0.35rem;
-}
-
-.voice-status-label {
-  font-size: 0.72rem;
-  color: var(--color-text-muted);
-  background: var(--color-bg-card);
-  border: 1px solid var(--color-border);
-  border-radius: 6px;
-  padding: 0.18rem 0.5rem;
-  white-space: nowrap;
-  box-shadow: 0 2px 6px var(--color-shadow, rgba(0,0,0,0.12));
-}
-.voice-hint { opacity: 0.7; }
-.voice-hint kbd {
-  font-family: ui-monospace, monospace;
-  font-size: 0.68rem;
-  padding: 0.05rem 0.25rem;
-  border: 1px solid var(--color-border);
-  border-radius: 3px;
-  background: var(--color-bg-secondary);
-}
-.voice-error-label { color: #ef4444; }
-
-.voice-cancel {
-  background: var(--color-bg-card);
-  border: 1px solid var(--color-border);
-  border-radius: 50%;
-  width: 28px;
-  height: 28px;
-  display: flex;
-  align-items: center;
-  justify-content: center;
-  cursor: pointer;
-  color: var(--color-text-muted);
-  box-shadow: 0 2px 6px var(--color-shadow, rgba(0,0,0,0.12));
-  transition: all 0.15s;
-}
-.voice-cancel:hover { color: #ef4444; border-color: #ef4444; }
-
-.voice-ptt-btn {
-  width: 58px;
-  height: 58px;
-  border-radius: 50%;
-  border: none;
-  background: linear-gradient(135deg, #6366f1, #4f46e5);
-  color: #fff;
-  display: flex;
-  align-items: center;
-  justify-content: center;
-  cursor: pointer;
-  box-shadow: 0 4px 16px rgba(99, 102, 241, 0.45);
-  transition: transform 0.12s, box-shadow 0.12s, background 0.2s;
-  touch-action: none;
-  user-select: none;
-  flex-shrink: 0;
-}
-.voice-ptt-btn:hover:not(:disabled) {
-  transform: scale(1.06);
-  box-shadow: 0 6px 20px rgba(99, 102, 241, 0.55);
-}
-.voice-ptt-btn:disabled { opacity: 0.6; cursor: not-allowed; }
-
-.voice-ptt--recording {
-  background: linear-gradient(135deg, #ef4444, #dc2626) !important;
-  box-shadow: 0 4px 16px rgba(239, 68, 68, 0.5) !important;
-  animation: ptt-pulse 0.9s ease-in-out infinite;
-}
-.voice-ptt--busy {
-  background: linear-gradient(135deg, #8b5cf6, #7c3aed) !important;
-  box-shadow: 0 4px 16px rgba(139, 92, 246, 0.45) !important;
-}
-.voice-ptt--speaking {
-  background: linear-gradient(135deg, #10b981, #059669) !important;
-  box-shadow: 0 4px 16px rgba(16, 185, 129, 0.45) !important;
-  animation: ptt-pulse 1.4s ease-in-out infinite;
-}
-.voice-ptt--error {
-  background: linear-gradient(135deg, #6b7280, #4b5563) !important;
-  box-shadow: none !important;
-}
-
-@keyframes ptt-pulse {
-  0%, 100% { transform: scale(1); }
-  50% { transform: scale(1.08); }
-}
-
-/* ─── Spinner dots ───────────────────────────────────────────────────────── */
-.voice-spinner {
-  display: flex;
-  gap: 4px;
-  align-items: center;
-}
-.voice-spinner span {
-  width: 5px;
-  height: 5px;
-  border-radius: 50%;
-  background: #fff;
-  animation: dot-bounce 1.2s ease-in-out infinite;
-}
-.voice-spinner span:nth-child(2) { animation-delay: 0.2s; }
-.voice-spinner span:nth-child(3) { animation-delay: 0.4s; }
-@keyframes dot-bounce {
-  0%, 80%, 100% { transform: scale(0.7); opacity: 0.5; }
-  40% { transform: scale(1); opacity: 1; }
-}
-
-/* ─── Amplitude bars (recording state) ──────────────────────────���───────── */
-.voice-amp-bars {
-  display: flex;
-  gap: 3px;
-  align-items: center;
-  height: 22px;
-}
-.voice-amp-bar {
-  width: 4px;
-  height: 18px;
-  background: #fff;
-  border-radius: 2px;
-  transform-origin: center;
-  transition: transform 0.08s ease;
-}
-
-/* ─── Transition ───────────────────────���──────────────────────���──────────── */
-.panel-slide-enter-active,
-.panel-slide-leave-active {
-  transition: opacity 0.2s ease, transform 0.2s ease;
-}
-.panel-slide-enter-from,
-.panel-slide-leave-to {
-  opacity: 0;
-  transform: translateY(8px);
-}
-</style>

frontend/src/views/SettingsView.vue

@@ -500,6 +500,8 @@ async function saveAdminVoice() {
     adminVoiceSaved.value = true;
     setTimeout(() => { adminVoiceSaved.value = false; }, 2000);
     voiceTabLoaded.value = false;
+    // Always update global voice state so mic buttons appear/disappear immediately
+    await store.checkVoiceStatus();
     if (adminVoiceEnabled.value) {
       await reloadVoiceModels();
     }

src/fabledassistant/config.py

@@ -27,7 +27,7 @@ class Config:
     # Lightweight model for background tasks (title generation, tag suggestions,
     # project summaries, RSS classification). Using a separate model keeps the
     # main model's KV cache intact between user messages, enabling prefix cache hits.
-    OLLAMA_BACKGROUND_MODEL: str = os.environ.get("OLLAMA_BACKGROUND_MODEL", "qwen2.5:0.5b")
+    OLLAMA_BACKGROUND_MODEL: str = os.environ.get("OLLAMA_BACKGROUND_MODEL", "qwen2.5:3b")
     # KV cache context window for generation. Keep this as small as practical —
     # a larger context forces more KV cache into CPU RAM, drastically slowing prefill.
     # 16384 covers ~30+ message conversations with our system prompt comfortably.

src/fabledassistant/routes/voice.py

@@ -80,10 +80,12 @@ async def transcribe_audio():
         return jsonify({"error": "Audio file too large (max 25 MB)"}), 413
 
     mime_type = audio_file.content_type or "audio/webm"
+    form = await request.form
+    context = (form.get("context") or "").strip() or None
 
     t0 = time.monotonic()
     try:
-        transcript = await transcribe(audio_bytes, mime_type)
+        transcript = await transcribe(audio_bytes, mime_type, initial_prompt=context)
     except Exception:
         logger.exception("STT transcription failed")
         return jsonify({"error": "Transcription failed"}), 500

src/fabledassistant/services/generation_task.py

@@ -118,31 +118,45 @@ _TOOL_LABELS: dict[str, str] = {
 
 
 async def _generate_title(messages: list[dict], user_id: int) -> str:
-    """Ask the LLM for a concise conversation title."""
-    # Build conversation text like summarize_conversation_as_note
-    conv_lines = []
+    """Ask the LLM for a concise conversation title.
+
+    Only uses user messages to avoid feeding tool-call JSON, system prompt
+    fragments, or other noise into the title generator. Caps input length
+    to keep the task fast and focused.
+    """
+    user_texts = []
     for m in messages:
-        if m["role"] == "system":
-            continue
-        label = "User" if m["role"] == "user" else "Assistant"
-        conv_lines.append(f"{label}: {m['content']}")
-    # Keep only last 6 pairs worth of text
-    conv_lines = conv_lines[-12:]
+        if m["role"] == "user":
+            content = (m.get("content") or "").strip()
+            if content:
+                user_texts.append(content[:300])
+    if not user_texts:
+        return ""
+    # First + last user messages capture intent best
+    if len(user_texts) > 2:
+        user_texts = [user_texts[0], user_texts[-1]]
 
     prompt_messages = [
         {
-            "role": "system",
+            "role": "user",
             "content": (
-                "Generate a concise 3-8 word title for this conversation. "
-                "Reply with ONLY the title, no quotes or punctuation."
+                "Generate a concise 3-8 word title for a conversation that started with:\n\n"
+                + "\n\n".join(user_texts)
+                + "\n\nReply with ONLY the title. No quotes, no punctuation, no explanation."
             ),
         },
-        {"role": "user", "content": "\n\n".join(conv_lines)},
     ]
     bg_model = await get_setting(user_id, "background_model", Config.OLLAMA_BACKGROUND_MODEL)
-    title = await generate_completion(prompt_messages, bg_model, max_tokens=30)
+    title = await generate_completion(prompt_messages, bg_model, max_tokens=30, num_ctx=1024)
+    # Strip common LLM noise: quotes, thinking tags, role labels
     title = title.strip().strip('"\'').strip()
-    return title[:100] if title else ""
+    for prefix in ("Title:", "title:", "Assistant:", "User:"):
+        if title.startswith(prefix):
+            title = title[len(prefix):].strip()
+    # Drop anything after a newline (model sometimes adds explanation)
+    if "\n" in title:
+        title = title.split("\n")[0].strip()
+    return title[:80] if title else ""
 
 
 async def _update_message(

src/fabledassistant/services/llm.py

@@ -538,6 +538,11 @@ async def build_context(
         "Delete tools require an explicit user request. "
         "Never proactively search notes or comment on absent context."
     )
+    tool_lines.append(
+        "IMPORTANT: When creating tasks or notes, NEVER infer or guess a project name. "
+        "Only set the project parameter if the user explicitly names a project. "
+        "If the user says 'create a task to buy milk', do NOT assign it to a project."
+    )
     tool_guidance = "\n".join(tool_lines)
 
     static_block = (

src/fabledassistant/services/projects.py

@@ -124,7 +124,7 @@ async def generate_project_summary(user_id: int, project_id: int) -> None:
         from fabledassistant.services.settings import get_setting
         messages = [{"role": "user", "content": prompt}]
         bg_model = await get_setting(user_id, "background_model", Config.OLLAMA_BACKGROUND_MODEL)
-        summary = await generate_completion(messages, model=bg_model, max_tokens=400)
+        summary = await generate_completion(messages, model=bg_model, max_tokens=400, num_ctx=2048)
         if not summary:
             return
 

src/fabledassistant/services/stt.py

@@ -55,8 +55,12 @@ def stt_available() -> bool:
     return _model is not None
 
 
-async def transcribe(audio_bytes: bytes, mime_type: str = "audio/webm") -> str:
-    """Transcribe audio bytes to text. Runs the model in a thread executor."""
+async def transcribe(audio_bytes: bytes, mime_type: str = "audio/webm", initial_prompt: str | None = None) -> str:
+    """Transcribe audio bytes to text. Runs the model in a thread executor.
+
+    initial_prompt: optional text to bias the model toward domain-specific vocabulary
+    (e.g. recent conversation context). Reduces mishearings like "gold" for "cold".
+    """
     if _model is None:
         raise RuntimeError("STT model not loaded")
 
@@ -73,7 +77,11 @@ async def transcribe(audio_bytes: bytes, mime_type: str = "audio/webm") -> str:
             f.write(audio_bytes)
             f.flush()
             t0 = time.monotonic()
-            segments, _ = _model.transcribe(f.name, beam_size=5)  # type: ignore[union-attr]
+            segments, _ = _model.transcribe(  # type: ignore[union-attr]
+                f.name,
+                beam_size=5,
+                initial_prompt=initial_prompt or None,
+            )
             text = " ".join(seg.text.strip() for seg in segments).strip()
             logger.debug("STT transcription took %.2fs", time.monotonic() - t0)
             return text