Sanad/voice/audio_manager.py

"""Audio I/O manager — recording and playback via PyAudio.

Handles microphone capture, speaker playback, and speaker-monitor recording.
Thread-safe; one playback at a time via play_lock.

Device selection is dynamic — read from voice.audio_devices on each refresh.
"""

from __future__ import annotations

import subprocess
import threading
import time
import wave
from pathlib import Path
from typing import Any

try:
    import pyaudio
except ImportError:
    pyaudio = None  # optional — only needed for local PCM playback

from Project.Sanad.config import (
    CHANNELS,
    CHUNK_SIZE,
    RECEIVE_SAMPLE_RATE,
    SINK as DEFAULT_SINK,
    SOURCE as DEFAULT_SOURCE,
    MONITOR_SOURCE,
)
from Project.Sanad.core.logger import get_logger
from Project.Sanad.voice import audio_devices as ad

log = get_logger("audio_manager")

FORMAT = pyaudio.paInt16 if pyaudio else 8

# Cached current selection — updated by refresh_devices()
_DEVICE_LOCK = threading.Lock()
_current_sink = DEFAULT_SINK
_current_source = DEFAULT_SOURCE


def _run_pactl(args: list[str]) -> subprocess.CompletedProcess[str]:
    return subprocess.run(["pactl", *args], check=True, text=True, capture_output=True)


def _resolve_devices() -> tuple[str, str]:
    """Return current (sink, source) — falls back to config defaults."""
    try:
        cur = ad.current_selection()
        sink = cur.get("sink") or DEFAULT_SINK
        source = cur.get("source") or DEFAULT_SOURCE
        return sink, source
    except Exception as exc:
        log.warning("Could not resolve audio devices: %s", exc)
        return DEFAULT_SINK, DEFAULT_SOURCE


def ensure_audio_defaults():
    """Re-scan all USB ports, resolve the active profile, set pactl defaults.

    This is called at startup AND before every playback/recording so that
    even if the user unplugs/re-plugs a device into a different port, the
    correct sink/source is always used.
    """
    try:
        result = ad.apply_current_selection()
        cur = result.get("selection", {})
        sink = cur.get("sink", "")
        source = cur.get("source", "")
        with _DEVICE_LOCK:
            global _current_sink, _current_source
            _current_sink = sink or DEFAULT_SINK
            _current_source = source or DEFAULT_SOURCE
    except Exception as exc:
        log.warning("Audio defaults not applied: %s", exc)


class AudioManager:
    def __init__(self):
        if pyaudio is None:
            raise RuntimeError(
                "pyaudio not installed — AudioManager cannot play local PCM. "
                "Install with `pip install pyaudio` (needs portaudio headers), "
                "or rely on the G1 speaker via AudioClient.PlayStream."
            )
        self.pya = pyaudio.PyAudio()
        self.play_lock = threading.Lock()
        # Resolve devices and set PulseAudio defaults at startup
        self.refresh_devices()
        ensure_audio_defaults()

    def refresh_devices(self) -> dict[str, str]:
        """Re-read selected sink/source from audio_devices module."""
        sink, source = _resolve_devices()
        with _DEVICE_LOCK:
            global _current_sink, _current_source
            _current_sink, _current_source = sink, source
        log.info("AudioManager devices refreshed: sink=%s source=%s", sink, source)
        return {"sink": sink, "source": source}

    @property
    def current_sink(self) -> str:
        with _DEVICE_LOCK:
            return _current_sink

    @property
    def current_source(self) -> str:
        with _DEVICE_LOCK:
            return _current_source

    def close(self):
        self.pya.terminate()

    def sample_width(self) -> int:
        return self.pya.get_sample_size(FORMAT)

    # -- playback --

    def play_pcm(self, pcm_bytes: bytes, channels: int, sample_rate: int, sample_width: int):
        with self.play_lock:
            ensure_audio_defaults()
            stream = self.pya.open(
                format=self.pya.get_format_from_width(sample_width),
                channels=channels,
                rate=sample_rate,
                output=True,
                frames_per_buffer=CHUNK_SIZE,
            )
            try:
                frame_bytes = CHUNK_SIZE * channels * sample_width
                for offset in range(0, len(pcm_bytes), frame_bytes):
                    stream.write(pcm_bytes[offset : offset + frame_bytes])
            finally:
                stream.stop_stream()
                stream.close()

    def play_wav(self, path: Path) -> dict[str, Any]:
        with wave.open(str(path), "rb") as wf:
            channels = wf.getnchannels()
            sw = wf.getsampwidth()
            rate = wf.getframerate()
            data = wf.readframes(wf.getnframes())
        self.play_pcm(data, channels, rate, sw)
        duration = len(data) / (rate * channels * sw) if rate else 0
        return {"path": str(path), "duration_seconds": round(duration, 3)}

    # -- recording --

    def record_mic(self, duration_sec: float) -> bytes:
        """Record from default mic for *duration_sec* seconds, return raw PCM."""
        ensure_audio_defaults()
        stream = self.pya.open(
            format=FORMAT,
            channels=CHANNELS,
            rate=RECEIVE_SAMPLE_RATE,
            input=True,
            frames_per_buffer=CHUNK_SIZE,
        )
        frames: list[bytes] = []
        total_chunks = int(RECEIVE_SAMPLE_RATE / CHUNK_SIZE * duration_sec)
        try:
            for _ in range(total_chunks):
                frames.append(stream.read(CHUNK_SIZE, exception_on_overflow=False))
        finally:
            stream.stop_stream()
            stream.close()
        return b"".join(frames)

    def save_wav(self, pcm_bytes: bytes, path: Path, channels: int, sample_rate: int):
        path.parent.mkdir(parents=True, exist_ok=True)
        with wave.open(str(path), "wb") as wf:
            wf.setnchannels(channels)
            wf.setsampwidth(self.sample_width())
            wf.setframerate(sample_rate)
            wf.writeframes(pcm_bytes)