use std::sync::Arc;

use kon_core::error::{KonError, Result};
use kon_core::types::{AudioSamples, TranscriptionOptions};

use crate::local_engine::{LocalEngine, TimedTranscript};

/// Runs inference on a blocking thread. Encapsulates all threading concerns.
/// Callers never see spawn_blocking — they call this async function.
pub async fn run_inference(
    engine: Arc<LocalEngine>,
    audio: AudioSamples,
    options: TranscriptionOptions,
) -> Result<TimedTranscript> {
    tokio::task::spawn_blocking(move || {
        engine.transcribe_sync(&audio, &options)
    })
    .await
    .map_err(|e| {
        KonError::TranscriptionFailed(format!("Task join error: {e}"))
    })?
}