/// Audio pipeline constants.
pub const WHISPER_SAMPLE_RATE: u32 = 16_000;
pub const WHISPER_CHANNELS: u16 = 1;

/// Parakeet mel spectrogram constants.
pub const PARAKEET_N_FFT: usize = 512;
pub const PARAKEET_HOP_LENGTH: usize = 160;
pub const PARAKEET_WIN_LENGTH: usize = 400;
pub const PARAKEET_N_MELS: usize = 80;
pub const PARAKEET_PRE_EMPHASIS: f32 = 0.97;
pub const PARAKEET_BLANK_TOKEN: usize = 1024;
pub const PARAKEET_LOG_GUARD: f32 = 5.960_464_5e-8; // 2^-24

/// Chunk timing for live transcription.
pub const CHUNK_INTERVAL_MS: u64 = 3000;
pub const MIN_CHUNK_SAMPLES: usize = 8000;

/// Post-processing thresholds.
pub const SMART_PARAGRAPH_GAP_SECS: f64 = 2.0;

/// Lower bound for inference threads. Single-threaded inference is
/// measurably worse than two on every multi-core part; we never go below
/// 2. (Whisper Tiny is the exception where the work is so small that
/// thread count barely matters — but the floor still costs nothing.)
pub const MIN_INFERENCE_THREADS: usize = 2;

/// Upper bound for inference threads. Both whisper.cpp and llama.cpp
/// scaling flattens around physical core count; SMT siblings contend
/// for shared FPU resources during heavy F16/F32 matmul, which means
/// going past physical cores often anti-scales. Empirical evidence:
/// whisper.cpp issue #200 (sweet spot at 7t on 8c/16t Ryzen 3700X),
/// llama.cpp #3167 ("SMT hurts inference"). 8 is a conservative
/// ceiling that leaves <5% on the table for big-iron desktops while
/// keeping consumer 6c/12t laptops out of contention territory.
pub const MAX_INFERENCE_THREADS: usize = 8;

/// History limits.
pub const HISTORY_MAX_ENTRIES: usize = 100;

/// RAM thresholds for model recommendations (in GB).
pub const RAM_MINIMUM_FOR_LOCAL_STT: f64 = 2.0;
pub const RAM_THRESHOLD_LIGHTWEIGHT: f64 = 4.0;
pub const RAM_THRESHOLD_STANDARD: f64 = 8.0;
pub const RAM_THRESHOLD_COMFORTABLE: f64 = 16.0;

/// VAD configuration defaults.
pub const VAD_SPEECH_THRESHOLD: f64 = 0.5;
pub const VAD_MIN_SPEECH_DURATION_MS: u32 = 250;
pub const VAD_MAX_SPEECH_DURATION_S: u32 = 30;
pub const VAD_MIN_SILENCE_DURATION_MS: u32 = 300;
pub const VAD_SPEECH_PAD_MS: u32 = 100;

/// Model download chunk size for progress reporting.
pub const DOWNLOAD_CHUNK_BYTES: usize = 65_536;

/// Inference thread count, clamped to physical-core budget.
///
/// Returns the system's physical-core count, clamped to
/// `[MIN_INFERENCE_THREADS, MAX_INFERENCE_THREADS]`. Uses physical
/// rather than logical cores because SMT/hyperthreaded siblings
/// contend for shared FPU resources during heavy matmul; counting
/// them as additional workers is well-documented to anti-scale on
/// both whisper.cpp and llama.cpp.
///
/// Falls back to `available_parallelism` only if the physical-core
/// probe is unavailable (some non-Linux/non-Windows platforms or
/// containerised environments).
///
/// Users can override at runtime by setting
/// `MAGNOTIA_INFERENCE_THREADS=N` — useful for benchmarking and for
/// users on big-iron desktops who want to push past the cap.
pub fn inference_thread_count() -> usize {
    if let Ok(s) = std::env::var("MAGNOTIA_INFERENCE_THREADS") {
        if let Ok(n) = s.parse::<usize>() {
            if n > 0 {
                return n;
            }
        }
    }
    let physical = num_cpus::get_physical();
    let chosen = if physical > 0 {
        physical
    } else {
        std::thread::available_parallelism()
            .map(|p| p.get())
            .unwrap_or(MIN_INFERENCE_THREADS)
    };
    chosen.clamp(MIN_INFERENCE_THREADS, MAX_INFERENCE_THREADS)
}