"""Export real Smart Turn scores across complete recordings for EOT Studio."""
import csv
import hashlib
import json

import numpy as np
import soundfile as sf
from loguru import logger
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
from evaluate_can_reply import HERE, ROOT, block_origin


def read(p):
    with p.open(encoding='utf-8-sig') as f:
        return list(csv.DictReader(f))


def main():
    logger.remove()
    checkpoints = read(HERE/'results/work-data-can-reply/predictions.csv')
    history = read(ROOT/'labels/EOT标注/工作数据/asr_history.csv')
    events = read(HERE/'results/work-data-pipecat/events.csv')
    weight = HERE/'smart-turn-v3.2-cpu.onnx'
    analyzer = LocalSmartTurnAnalyzerV3(smart_turn_model_path=str(weight),cpu_count=4)
    calls=[]
    for call in sorted({r['call_id'] for r in checkpoints}):
        path=ROOT/'data/韩泰机器人抢话/音频'/f'{call}.mp3'
        pcm,sr=sf.read(path,dtype='int16',always_2d=True)
        duration=round(len(pcm)*1000/sr,3)
        call_labels=[r for r in checkpoints if r['call_id']==call]
        exact={int(r['decision_ms']):float(r['probability']) for r in call_labels}
        times=sorted(set(range(200,int(duration)+1,200))|set(exact)|{int(duration)})
        call_history=[r for r in history if r['call_id']==call]
        starts=sorted(float(e['event_ms']) for e in events if e['call_id']==call and e['event']=='vad_start')
        analyzer.set_sample_rate(sr)
        points=[]
        for decision in times:
            origin=block_origin(call_history,decision)
            if origin is None:
                past=[t for t in starts if t<=decision]
                origin=max(0,past[-1]+32-200-500) if past else 0
            end=decision*sr//1000
            start=max(round(origin*sr/1000),end-sr*8)
            assert 0<=start<end<=len(pcm)
            # Endpoint resampling can only read the already cropped prefix.
            samples=np.ascontiguousarray(pcm[start:end,0].astype(np.float32)/32768.)
            score=float(analyzer._predict_endpoint(samples)['probability'])
            assert np.isfinite(score) and 0<=score<=1
            if decision in exact:
                assert abs(score-exact[decision])<1e-4,(call,decision,score,exact[decision])
            points.append([decision,round(score,7)])
        calls.append(dict(call_id=call,audio_path=f'韩泰机器人抢话/音频/{call}.mp3',
            audio_sha256=hashlib.sha256(path.read_bytes()).hexdigest(),duration_ms=duration,
            points=points,checkpoints=[[t,round(p,7)] for t,p in sorted(exact.items())]))
        print(f'{call[:8]}: {len(points)} timeline scores; checkpoints verified',flush=True)
    output=dict(schema_version=1,model='smart_turn',name='Smart Turn',sample_interval_ms=200,
        score='completion probability',
        method='Direct endpoint call every 200ms and at every original annotation. Same past-ASR block origin, 500ms pre-speech, <=3s continuation and last 8s user-channel audio as the point baseline; past VAD fallback when ASR missing. No EOT/timeout gates. Crop before resampling.',
        model_sha256=hashlib.sha256(weight.read_bytes()).hexdigest(),
        script_sha256=hashlib.sha256((HERE/'export_timeline.py').read_bytes()).hexdigest(),calls=calls)
    (HERE/'results/score-timeline.json').write_text(json.dumps(output,ensure_ascii=False,separators=(',',':'))+'\n')


if __name__=='__main__':
    main()