//! End-to-end LFM2-MoE (`lfm2moe` arch) GGUF decode oracle. Ignored by default —
//! needs the real ~5 GB Q4_K_M checkpoint on disk.
//!
//! Reference is `llama.cpp` on the same file. NOTE: LFM2 prepends a BOS
//! (`<|startoftext|>` = 124894). We validate on a *sharp* idiom prompt where the
//! next token is unambiguous, so the argmax cannot be flipped by the small
//! numerical difference between this f32 forward and llama.cpp's Q4_K matmul
//! (a flat prompt like "The capital of France is" is a poor oracle for that
//! reason — LFM2 there is genuinely torn between " city"/" Paris"/" the").
//!
//! Run: `cargo test -p jouleclaw-loader-gguf --release --features rayon \
//!   --test real_lfm2_oracle -- --ignored --nocapture`

use jouleclaw_loader_gguf::bpe_tokenizer::BpeTokenizer;
use jouleclaw_loader_gguf::lfm2moe::Lfm2Moe;
use jouleclaw_loader_gguf::read_gguf_file;

const GG: &str =
    "/Volumes/macos_4TB_external_1/neuronexus_ai/model_library/lfm2.5-8b-a1b-gguf/LFM2.5-8B-A1B-Q4_K_M.gguf";

const BOS: u32 = 124894;
/// "The quick brown fox jumps over the lazy" (+BOS) per `llama-tokenize`.
const FOX: [u32; 9] = [BOS, 597, 4104, 10299, 35886, 56085, 890, 278, 45698];
/// " dog" — llama.cpp's confident greedy next token.
const DOG: u32 = 4448;

fn argmax(v: &[f32]) -> usize {
    v.iter()
        .enumerate()
        .fold((0usize, f32::NEG_INFINITY), |(bi, bv), (i, &x)| if x > bv { (i, x) } else { (bi, bv) })
        .0
}

#[test]
#[ignore]
fn real_lfm2_predicts_dog() {
    if !std::path::Path::new(GG).exists() {
        eprintln!("skip: lfm2 GGUF not present");
        return;
    }
    let m = Lfm2Moe::load(GG).expect("load lfm2 gguf");
    eprintln!(
        "lfm2moe: {} layers, d={}, heads={}/{}, experts={}/{}, dense_lead={}, L={}, vocab={}",
        m.cfg.n_layers, m.cfg.d_model, m.cfg.n_heads, m.cfg.n_kv, m.cfg.n_used, m.cfg.n_experts,
        m.cfg.leading_dense, m.cfg.l_cache, m.cfg.vocab
    );
    let got = argmax(&m.forward(&FOX));
    eprintln!("argmax = {got} (expected {DOG} = ' dog')");
    assert_eq!(got, DOG as usize, "greedy next token diverges from llama.cpp");
}

/// Full text-in / text-out through the GGUF-embedded tokenizer (+BOS): the prompt
/// tokenizes to the llama.cpp ids and greedy decode reads "... dog".
#[test]
#[ignore]
fn real_lfm2_text_roundtrip() {
    if !std::path::Path::new(GG).exists() {
        eprintln!("skip: lfm2 GGUF not present");
        return;
    }
    let tok = BpeTokenizer::from_gguf(&read_gguf_file(GG).expect("gguf")).expect("tokenizer");
    let body = tok.encode("The quick brown fox jumps over the lazy");
    assert_eq!(body, FOX[1..].to_vec(), "tokenization diverges from llama.cpp");
    let mut ids = vec![BOS];
    ids.extend_from_slice(&body);

    let m = Lfm2Moe::load(GG).expect("load");
    let text = tok.decode(&m.generate(&ids, 3));
    eprintln!("generated = {text:?}");
    assert!(text.starts_with(" dog"), "greedy decode should start ' dog', got {text:?}");
}