Maven/cmd/mavwaked/main.go

// Package main — mavwaked: always-on voice listening client.
//
// Spawns arecord(1) as a subprocess, reads 16kHz mono PCM from its stdout,
// runs an energy-based VAD over 30ms windows, and when a complete utterance
// is detected sends it as a PushToTalk frame to the voice server. The reply
// audio is played back through aplay(1).
//
// No wake-word model yet (MVP uses voice-activity-only trigger). The
// SurfaceVoice auth layer caps all commands at L0 (no destructive acts),
// making accidental triggers safe by design. A proper wake-word engine
// (openWakeWord / Silero VAD ONNX) is the planned upgrade — the VAD shape
// (30ms frames, 16kHz PCM) matches silero-vad's input interface exactly, so
// swapping energy-threshold for ONNX-inference is a local change in vad.go.
//
// While a reply is playing the capture side is muted (half-duplex): without
// it, Maven's own voice comes back in through the mic and she answers
// herself. -barge-in punches one hole in that gate — sustained energy above
// -barge-in-rms cuts playback so he can talk over her. It is off by default
// because the threshold is room-specific; see playback.go. The threshold is a
// raw frame RMS and has no reference to what the speaker actually leaks, so
// the daemon logs the mean energy of the frames it suppressed while speaking.
// Set -barge-in-rms from those numbers rather than by guessing.
//
//	usage:
//	  mavwaked                          # default ALSA device, 127.0.0.1:9100
//	  mavwaked -barge-in                # let him interrupt her mid-reply
//	  mavwaked -device hw:1,0 -addr 10.42.0.1:9100
//	  mavwaked -test file.wav           # read from file, no arecord
package main

import (
	"bufio"
	"context"
	"errors"
	"flag"
	"fmt"
	"io"
	"log"
	"os"
	"os/exec"
	"os/signal"
	"syscall"
	"time"

	"github.com/kami/maven/internal/audio"
	"github.com/kami/maven/internal/voice"
)

// Defaults.
const (
	defaultDevice   = "default"
	defaultAddr     = "127.0.0.1:9100"
	defaultLang     = "ru"
	defaultReadSize = 4096 // max PCM bytes per read from arecord (fits multiple frames)
)

func main() {
	if err := run(os.Args[1:]); err != nil && !errors.Is(err, context.Canceled) {
		fmt.Fprintln(os.Stderr, "mavwaked:", err)
		os.Exit(1)
	}
}

func run(args []string) error {
	device := flag.String("device", defaultDevice, "ALSA capture device")
	addr := flag.String("addr", defaultAddr, "voice server TCP address")
	lang := flag.String("lang", defaultLang, "STT language hint (ru/en/mixed)")
	minRMS := flag.Int("min-rms", 100, "RMS floor ×10000 (e.g. 100 = 0.01)")
	speechMs := flag.Int("speech-ms", defaultSpeechMs, "min speech ms before trigger")
	silenceMs := flag.Int("silence-ms", defaultSilenceMs, "silence ms to end utterance")
	maxMs := flag.Int("max-ms", defaultMaxMs, "max utterance ms")
	testFile := flag.String("test", "", "read PCM from file instead of arecord (testing only)")
	bargeIn := flag.Bool("barge-in", false, "cut Maven off when he talks over her (needs a room-tuned -barge-in-rms)")
	bargeRMS := flag.Int("barge-in-rms", defaultBargeRMS, "RMS x10000 a frame must clear to count as barge-in")
	bargeFrames := flag.Int("barge-in-frames", defaultBargeFrames, "consecutive frames over -barge-in-rms before playback is cut")
	flag.CommandLine.Parse(args)

	ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM, syscall.SIGHUP)
	defer stop()

	// Voice client — reused across utterances; SendRequest reconnects on error.
	vc := voice.Dial(*addr)
	defer vc.Close()

	// VAD engine.
	vad := NewVAD(*minRMS, *speechMs, *silenceMs, *maxMs)

	// Audio source.
	var src io.ReadCloser
	if *testFile != "" {
		f, err := os.Open(*testFile)
		if err != nil {
			return fmt.Errorf("open test file: %w", err)
		}
		defer f.Close()
		src = f
		log.Printf("mavwaked: reading from test file %s", *testFile)
	} else {
		arec := exec.CommandContext(ctx, "arecord",
			"-D", *device,
			"-f", "S16_LE",
			"-r", "16000",
			"-c", "1",
			"-t", "raw",
		)
		arec.Stderr = os.Stderr
		pipe, err := arec.StdoutPipe()
		if err != nil {
			return fmt.Errorf("arecord stdout pipe: %w", err)
		}
		if err := arec.Start(); err != nil {
			return fmt.Errorf("start arecord: %w", err)
		}
		src = pipe
		log.Printf("mavwaked: listening on device %s → %s", *device, *addr)

		// Ensure arecord is killed when we exit.
		go func() {
			<-ctx.Done()
			if p := arec.Process; p != nil {
				_ = p.Signal(syscall.SIGTERM)
				// Give it a moment, then force-kill.
				go func() {
					time.Sleep(2 * time.Second)
					_ = p.Kill()
				}()
			}
		}()
	}

	defer src.Close()

	var barge bargeInConfig
	if *bargeIn {
		barge = bargeInConfig{RMS: float64(*bargeRMS) / 10000.0, Frames: *bargeFrames}
		if barge.Enabled() {
			log.Printf("mavwaked: barge-in on (rms %.4f x %d frames)", barge.RMS, barge.Frames)
		} else {
			// The log used to say "barge-in on (rms 0.0000 x 5)" here and then
			// nothing happened, because Enabled needs a positive threshold.
			log.Printf("mavwaked: -barge-in was passed but rms %.4f x %d frames disables it; "+
				"both must be above zero, so barge-in is OFF",
				barge.RMS, barge.Frames)
		}
	}
	sess := newSession(vad, newAplayPlayer(), &voiceSender{vc: vc}, *lang, barge)

	return captureLoop(ctx, src, sess)
}

// captureLoop reads PCM from src and hands whole frames to the session.
// Returns when ctx is done or src is exhausted.
func captureLoop(ctx context.Context, src io.Reader, sess *session) error {
	br := bufio.NewReaderSize(src, defaultReadSize)
	frameBytes := sess.vad.FrameSamples() * 2 // 480 samples × 2 bytes = 960 bytes per 30ms

	log.Printf("mavwaked: capture loop starting (frame=%d bytes, %dms)",
		frameBytes, defaultFrameMs)

	var partial []byte
	for {
		select {
		case <-ctx.Done():
			log.Printf("mavwaked: context done, stopping capture")
			return ctx.Err()
		default:
		}

		// Read exactly one frame (or wait for more data).
		buf := make([]byte, frameBytes)
		n, err := io.ReadFull(br, buf)
		if err != nil {
			if errors.Is(err, io.EOF) || errors.Is(err, io.ErrUnexpectedEOF) {
				if n > 0 {
					// Flush partial frame.
					partial = append(partial, buf[:n]...)
					if len(partial) >= frameBytes {
						if err := sess.feed(ctx, partial[:frameBytes]); err != nil {
							log.Printf("mavwaked: process frame: %v", err)
						}
						partial = partial[frameBytes:]
					}
				}
				return nil
			}
			return fmt.Errorf("read audio: %w", err)
		}

		// Include any leftover from previous partial read.
		full := buf
		if len(partial) > 0 {
			full = append(partial, buf...)
			partial = nil
		}

		if err := sess.feed(ctx, full); err != nil {
			log.Printf("mavwaked: process frame: %v", err)
		}
	}
}

// voiceSender is the production utteranceSender: one PushToTalk round-trip
// over the voice wire. SurfaceVoice (not the default SurfacePCClient that
// c.PushToTalk uses) caps everything at L0, which is what makes an accidental
// VAD trigger safe.
type voiceSender struct{ vc *voice.Client }

func (s *voiceSender) Send(ctx context.Context, utt audio.Audio, lang string) (audio.Audio, error) {
	var resp voice.PushToTalkResp
	err := s.vc.SendRequest(ctx, voice.MethodPushToTalk, voice.PushToTalkReq{
		Audio:   utt,
		Lang:    lang,
		Surface: voice.SurfaceVoice,
	}, &resp)
	if err != nil {
		return audio.Audio{}, fmt.Errorf("push-to-talk: %w", err)
	}
	log.Printf("mavwaked: reply: %q (%.2fs audio)", resp.ReplyText, resp.ReplyAudio.Duration())
	if len(resp.RoutedChannels) > 0 {
		log.Printf("mavwaked: also routed to: %v", resp.RoutedChannels)
	}
	return resp.ReplyAudio, nil
}