"""Barge-in: notice that the user started talking *while the pet is talking*
so playback can be cut short mid-sentence.

Deliberately dumber than the utterance VAD in mic.py. The mic hears the pet's
own voice coming back out of the speakers, so a single loud frame proves
nothing — this requires several consecutive frames well above the normal
speech threshold (BARGE_IN_RMS_THRESHOLD defaults to 4x VAD_RMS_THRESHOLD).
Takes the same injectable stream shape as mic.record_utterance, so tests feed
it fake frames instead of real audio hardware.
"""

from __future__ import annotations

import numpy as np

from .. import config
from .mic import AudioStream, rms


class BargeInDetector:
    """Poll-driven: call check() repeatedly while audio plays. Each call
    consumes exactly one mic frame (80ms at the default frame length), which
    is also what paces the playback loop's polling."""

    def __init__(
        self,
        stream: AudioStream,
        threshold: int = None,
        required_frames: int = None,
        frame_len: int = config.FRAME_LEN,
    ):
        self._stream = stream
        self._threshold = config.BARGE_IN_RMS_THRESHOLD if threshold is None else threshold
        self._required = max(1, config.BARGE_IN_FRAMES if required_frames is None else required_frames)
        self._frame_len = frame_len
        self._loud_frames = 0

    @property
    def loud_frames(self) -> int:
        return self._loud_frames

    def reset(self) -> None:
        self._loud_frames = 0

    def check(self) -> bool:
        """True once the user has been loud for long enough to count as an
        interruption. Never raises: a mic hiccup mid-playback should not kill
        the reply, it should just mean "no barge-in this frame"."""
        try:
            chunk, _ = self._stream.read(self._frame_len)
        except Exception:
            return False
        frame = np.asarray(chunk)
        if frame.ndim > 1:
            frame = frame[:, 0]
        if frame.size == 0:
            return False
        if rms(frame) >= self._threshold:
            self._loud_frames += 1
        else:
            self._loud_frames = 0  # a single thump/cough shouldn't count
        return self._loud_frames >= self._required