//! Cross-encoder reranking via `score_binary_tokens`: a Qwen3-Reranker (or any
//! instruct model) scores a (query, document) pair by the yes-vs-no logit after a
//! single forward pass. Ranks relevant documents above irrelevant ones.
//!
//! Ignored by default (needs a real GGUF). Run with:
//!   JOULE_RERANK=/path/qwen3-reranker-0.6b-q8_0.gguf \
//!   cargo test -p jouleclaw-runtime --test real_reranker -- --ignored --nocapture
use jouleclaw_loader_gguf::read_gguf_file;
use jouleclaw_loader_gguf::tokenizer::Vocab;
use jouleclaw_runtime::chat::encode_with_specials;
use jouleclaw_runtime::generate::score_binary_tokens;

fn rerank_prompt(instruct: &str, query: &str, doc: &str) -> String {
    // Qwen3-Reranker format WITHOUT the reasoning `<think>` block — the 0.6B GGUF
    // predicts yes/no directly; the think block derails it.
    format!("<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be \"yes\" or \"no\".<|im_end|>\n<|im_start|>user\n<Instruct>: {instruct}\n<Query>: {query}\n<Document>: {doc}<|im_end|>\n<|im_start|>assistant\n")
}

#[test]
#[ignore]
fn reranker_ranks_relevant_above_irrelevant() {
    let path = std::env::var("JOULE_RERANK").expect("set JOULE_RERANK to a reranker gguf");
    let model = read_gguf_file(&path).expect("read");
    let vocab = Vocab::from_gguf(&model).expect("vocab");
    let yes = *vocab.token_to_id.get("yes").expect("yes token");
    let no = *vocab.token_to_id.get("no").expect("no token");

    let instruct = "Given a code search query, find the relevant source file";
    let query = "how to invalidate the cache";
    let score = |doc: &str| {
        let toks = encode_with_specials(&vocab, &rerank_prompt(instruct, query, doc), &["<|im_start|>", "<|im_end|>"], false);
        score_binary_tokens(&model, &vocab, &toks, yes, no).expect("score")
    };

    let relevant = score("fn cache_invalidate() { self.entries.clear(); }");
    let irrelevant = score("struct Color { r: u8, g: u8, b: u8 }");
    eprintln!("relevant={relevant:.3} irrelevant={irrelevant:.3}");
    assert!(relevant > irrelevant, "reranker must rank the cache fn above the color struct");
}