Betafish.js

Parses Forsyth-Edwards Notation (FEN) strings to reconstruct complete chess board states including piece placement, active player, castling rights, en passant targets, and move counters. Enables bidirectional conversion between FEN format and internal board representation, allowing users to load specific positions from games or export analyzed positions for external use. Implements standard FEN parsing with validation of piece placement, turn indicators, and special move flags.

Executes minimax-based chess position evaluation with adjustable search depth (thinking time) to balance analysis quality against computation latency. Implements alpha-beta pruning to reduce the game tree search space, allowing users to control the trade-off between deeper analysis and faster results. The thinking time parameter directly maps to search depth, enabling users to analyze positions in seconds (shallow) or minutes (deep) depending on device capability and analysis requirements.

Computes numeric evaluation scores (in centipawns) for chess positions using a heuristic evaluation function that assesses material balance, piece positioning, pawn structure, and king safety. Returns evaluation from the perspective of the side to move, with positive scores indicating advantage for the moving player and negative scores indicating disadvantage. Updates evaluation dynamically as the engine searches deeper, allowing users to observe how the assessment changes with additional computation.

Identifies the strongest move in a position by selecting the move with the highest evaluation score from the minimax search tree, and returns the principal variation (PV) — the sequence of best moves both sides would play in response. Implements move ordering heuristics (killer moves, history heuristics) to prioritize promising moves early in the search, improving alpha-beta pruning efficiency. Returns both the recommended move in algebraic notation and the full line of play that justifies the recommendation.

Provides a graphical chess board interface that allows users to place pieces, set up custom positions, and visualize the current board state with piece symbols and square highlighting. Implements click-based piece movement with validation to ensure moves are legal (no moving opponent pieces, respecting piece movement rules). Updates the visual board representation in real-time as positions change, and maintains internal board state synchronized with the displayed board.

Executes all chess engine analysis entirely within the browser using JavaScript, eliminating the need for external API calls or cloud servers. The engine runs as client-side code, processing positions and computing evaluations on the user's device without transmitting position data to remote servers. This architecture ensures privacy (positions never leave the device), offline functionality (analysis works without internet), and zero latency for engine communication (no network round-trips).

Validates that moves conform to chess rules by checking piece movement patterns (pawns move forward one square or two from starting position, knights move in L-shape, bishops move diagonally, rooks move horizontally/vertically, queens move any direction, kings move one square). Prevents illegal moves such as moving into check, capturing your own pieces, or moving opponent pieces. Implements special move handling for castling (king and rook movement with position requirements), en passant (pawn capture of enemy pawn that just moved two squares), and pawn promotion (automatic or user-selected piece).

Maintains a complete record of moves played during a game session, allowing users to navigate backward and forward through the move history to review the game progression. Stores each position state and the move that led to it, enabling undo/redo functionality and position replay. Implements move history as a linear sequence (no branching variations), allowing users to step through the game move-by-move or jump to specific positions.