#!/usr/bin/env python3
"""The Phase A prototype net: a small, known HalfKAv2_hm architecture
per NNUE.md's architecture decisions -- 256x2-32-32-1-ish, a single
shared feature-transformer weight matrix applied independently to
each perspective's active-feature set (that sharing, not two
separate tables, is what makes the two 256-wide "accumulator" halves
comparable before concatenation), own-perspective-half-first
concatenation keyed by side-to-move so the net's single scalar
output is side-to-move-relative by construction (per the "Output
convention" architecture decision), and a sigmoid-WDL loss against
the already-fitted K=1.3123 (per "WDL-sigmoid target conversion
built and run", fit_k_and_label.py) rather than raw centipawn MSE.

Deliberately NOT doing yet (explicitly deferred, see NNUE.md): clipped
activations / quantization-aware scaling (this is a float32-only
Phase A prototype, no export-for-C-inference step exists yet), the
lazy-eval PSQT-term fast path, and the super-lazy material-only
prefilter. All irrelevant to proving the training pipeline works.
"""
import torch
import torch.nn as nn

from nnue_feature_spec import DIMENSIONS

L1 = 256   # feature-transformer output width (per perspective)
L2 = 32
L3 = 32

DEFAULT_K = 1.3123   # pawns; fit_k_and_label.py's Phase-A train-split fit


class NnueNet(nn.Module):
    def __init__(self, dimensions=DIMENSIONS, l1=L1, l2=L2, l3=L3):
        super().__init__()
        # Single shared feature transformer: one [dimensions, l1]
        # weight matrix, applied once per perspective to that
        # perspective's own active-feature set. mode="sum" matches
        # Stockfish's own feature-transformer semantics (accumulate
        # one weight row per active feature).
        self.ft = nn.EmbeddingBag(dimensions, l1, mode="sum")
        self.ft_bias = nn.Parameter(torch.zeros(l1))

        self.fc1 = nn.Linear(2 * l1, l2)
        self.fc2 = nn.Linear(l2, l3)
        self.fc3 = nn.Linear(l3, 1)

    def forward(self, white_idx, white_off, black_idx, black_off, stm):
        """stm: float/long tensor of shape [B], 1.0 if white to move
        else 0.0. Returns raw score in pawn-ish units, shape [B]."""
        white_acc = self.ft(white_idx, white_off) + self.ft_bias
        black_acc = self.ft(black_idx, black_off) + self.ft_bias

        white_acc = torch.relu(white_acc)
        black_acc = torch.relu(black_acc)

        stm = stm.view(-1, 1).float()
        # own-perspective-first concatenation, per side to move.
        own = stm * white_acc + (1.0 - stm) * black_acc
        enemy = stm * black_acc + (1.0 - stm) * white_acc
        x = torch.cat([own, enemy], dim=1)

        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x.view(-1)

    def win_probability(self, white_idx, white_off, black_idx, black_off, stm, k=DEFAULT_K):
        raw = self.forward(white_idx, white_off, black_idx, black_off, stm)
        return torch.sigmoid(raw / k)