mission-control-v2/frontend/src/lib/voice/audio.ts

// Sequentielle Audio-Wiedergabe für die TTS-Antworten + Pegel-Messung fürs Lippensync.
//
// Die einzelnen Satz-WAVs kommen nacheinander rein (satzweise Synthese → niedrige Latenz).
// Wir spielen sie über EINEN AudioContext geordnet ab und hängen einen AnalyserNode dazwischen,
// dessen Energie pro Frame in `level.current` (0..1) landet — der 3D-Avatar liest das im
// useFrame und öffnet den Mund entsprechend. Kein Re-Render pro Frame (Mutable-Ref-Muster).

export class AudioQueue {
  private ctx: AudioContext
  private analyser: AnalyserNode
  private queue: ArrayBuffer[] = []
  private playing = false
  private raf = 0
  private freq: Uint8Array<ArrayBuffer>
  /** Mutable, vom Avatar pro Frame gelesen. 0 = Mund zu, 1 = weit offen. */
  readonly level = { current: 0 }
  onSpeaking?: (speaking: boolean) => void

  constructor() {
    const Ctor = window.AudioContext || (window as any).webkitAudioContext
    this.ctx = new Ctor()
    this.analyser = this.ctx.createAnalyser()
    this.analyser.fftSize = 256
    this.analyser.smoothingTimeConstant = 0.6
    this.analyser.connect(this.ctx.destination)
    this.freq = new Uint8Array(new ArrayBuffer(this.analyser.frequencyBinCount))
  }

  async enqueue(buf: ArrayBuffer) {
    this.queue.push(buf)
    if (!this.playing) await this.playNext()
  }

  /** Laufende + wartende Wiedergabe verwerfen (z.B. wenn der Nutzer dazwischenredet). */
  clear() {
    this.queue = []
  }

  private async playNext(): Promise<void> {
    const buf = this.queue.shift()
    if (!buf) {
      this.playing = false
      this.stopMeter()
      this.onSpeaking?.(false)
      return
    }
    this.playing = true
    this.onSpeaking?.(true)
    if (this.ctx.state === "suspended") {
      try { await this.ctx.resume() } catch { /* vom User-Gesture freigeschaltet */ }
    }
    let audioBuf: AudioBuffer
    try {
      audioBuf = await this.ctx.decodeAudioData(buf.slice(0))
    } catch {
      return this.playNext()   // kaputtes Segment überspringen
    }
    const src = this.ctx.createBufferSource()
    src.buffer = audioBuf
    src.connect(this.analyser)
    src.onended = () => { void this.playNext() }
    src.start()
    this.startMeter()
  }

  private startMeter() {
    cancelAnimationFrame(this.raf)
    const tick = () => {
      this.analyser.getByteFrequencyData(this.freq)
      // Sprachenergie liegt v.a. in den unteren/mittleren Bändern.
      const n = Math.min(this.freq.length, 48)
      let sum = 0
      for (let i = 2; i < n; i++) sum += this.freq[i]
      const avg = sum / (n - 2) / 255
      this.level.current = Math.min(1, avg * 1.9)
      this.raf = requestAnimationFrame(tick)
    }
    tick()
  }

  private stopMeter() {
    cancelAnimationFrame(this.raf)
    this.level.current = 0
  }
}