Args:
    username: Lichess nebo Chess.com username
    max_games: Maximalni pocet her (1-50)
    source: Platforma - 'lichess' nebo 'chesscom'

Args:
    game_id: Lichess game ID (8 chars), or empty if using PGN directly
    pgn: PGN string of the game, or empty if using game_id
    username: Your username (to determine your color), or specify color
    color: Your color if username not provided ('white' or 'black')
    depth: Stockfish analysis depth (8-24, default 14)

Args:
    fen: FEN string of the position
    depth: Stockfish analysis depth (8-24, default 18)
    use_cloud: Try Lichess cloud eval first (faster if cached)

Args:
    fen: FEN string of the position
    source: Database - 'lichess' (public games) or 'masters' (OTB master games)

Args:
    username: Lichess username

Analyzes recent games and identifies recurring tactical blind spots,
phase weaknesses (opening/middlegame/endgame), leaky openings,
and pattern frequencies. Structured logging per P19.

Args:
    username: Lichess username
    max_games: Number of recent games to analyze (5-50)
    depth: Stockfish depth for analysis (8-18, lower = faster)

Analyzes recent games and matches them against the pattern library
imported from chess_pattern_v5.json. Returns detected patterns with
confidence scores, evidence, mitigation advice, and compression validation.

Args:
    username: Lichess username
    max_games: Number of games to analyze (5-50)
    depth: Stockfish depth (8-18)

Parses any PGN (lichess, chess.com, GM games, custom PGN) through the same
Stockfish pipeline used for online games. Returns per-move evaluation,
classification (blunder/mistake/inaccuracy/good/best), and phase detection.
Results are stored in L2 Resources for later retrieval.

Use this to:
- Analyze your own games from any platform
- Import GM games and compare against your patterns (via lichess_match_patterns)
- Analyze opponent games you have PGN for
- Build a custom game library from PGN files

Args:
    pgn: Full PGN string of the game (including headers)
    color: Your color ('white' or 'black', default 'white')
    depth: Stockfish analysis depth (8-24, default 14)
    game_id: Optional game identifier (auto-detected from PGN Site header if empty)