//! Per-model token accounting. Entry point for the ModelMatrix work
//! the aibridge `context::estimate_tokens` deprecation has been pointing
//! at. Starts minimal — just `estimate_tokens` — so call sites can
//! migrate off the deprecated helper. Extend with per-model context
//! windows, max_tokens defaults, provider hints, etc. as we move the
//! rest of `aibridge::context::known_windows` over.

/// Namespace for per-model token + context accounting. Methods are
/// associated functions — no instance required — because the underlying
/// estimates are deterministic and stateless.
pub struct ModelMatrix;

impl ModelMatrix {
    /// Rough token count — char count divided by 4, rounded up. This
    /// is the same heuristic OpenAI's cookbook uses for English text;
    /// it's within ±15% of BPE tokenizers for code + prose and doesn't
    /// require a tokenizer lookup. Good enough for budget math where
    /// the goal is "don't blow the context window" rather than exact
    /// billing.
    ///
    /// Moved from `aibridge::context::estimate_tokens` (still there with
    /// a `#[deprecated]` pointer — callers should migrate here). Empty
    /// string → 0; one char → 1 (ceiling of 1/4 = 1).
    pub fn estimate_tokens(text: &str) -> usize {
        (text.chars().count() + 3) / 4
    }
}

#[cfg(test)]
mod tests {
    use super::ModelMatrix;

    #[test]
    fn empty_string_is_zero_tokens() {
        assert_eq!(ModelMatrix::estimate_tokens(""), 0);
    }

    #[test]
    fn three_chars_is_one_token() {
        // 3 → ceil(3/4) = 1. Matches the deprecated helper's behavior
        // so the migration is a drop-in replacement.
        assert_eq!(ModelMatrix::estimate_tokens("abc"), 1);
    }

    #[test]
    fn four_chars_is_one_token() {
        assert_eq!(ModelMatrix::estimate_tokens("abcd"), 1);
    }

    #[test]
    fn five_chars_is_two_tokens() {
        assert_eq!(ModelMatrix::estimate_tokens("abcde"), 2);
    }

    #[test]
    fn counts_chars_not_bytes() {
        // Multi-byte UTF-8 chars count as 1 char each — important for
        // prompts with emoji or non-ASCII text. "héllo" is 5 chars
        // (5 unicode scalars) → ceil(5/4) = 2 tokens, same as "hello".
        assert_eq!(ModelMatrix::estimate_tokens("héllo"), 2);
        assert_eq!(ModelMatrix::estimate_tokens("📚📚📚📚"), 1);  // 4 chars
    }

    #[test]
    fn large_text_scales_linearly() {
        assert_eq!(ModelMatrix::estimate_tokens(&"x".repeat(400)), 100);
        assert_eq!(ModelMatrix::estimate_tokens(&"x".repeat(401)), 101);
    }
}