//! F17's reproduction: what is ATTACK worth? (CB-WP-0029 follow-up.)
//!
//! The maintainer reported *"there is no incentive to play attacks as long
//! as I have positive cards"*. F17 sat as a note because nothing
//! demonstrated it. This is the artifact.
//!
//! GreedyPolicy ranks Attack at 10, below everything (bot.rs). So its zero
//! attacks measure OUR HEURISTIC, not the game. The test is a policy
//! identical in every other respect with Attack promoted: if it wins as
//! often, attacking is neutral; much less, avoiding it is correct play;
//! more, and greedy is simply wrong.
use cb_game_runtime::{ScenarioGame, Setup};
use cb_kernel::PlayerId;
use games_ground::bot::{play, Choice, GreedyPolicy, Policy};
use games_ground::{Action, GroundCommand, GroundState};

/// Greedy's ordering with ATTACK promoted to the top of the action list.
/// A copy of the ranking, not a call into it: `GreedyPolicy::rank` is
/// private, and the point is to vary exactly one number.
struct Attacker(i32);
impl Policy for Attacker {
    fn name(&self) -> &'static str {
        "attacker"
    }
    fn choose(
        &mut self,
        state: &GroundState,
        seat: PlayerId,
        legal: &[GroundCommand],
        _p: bool,
    ) -> Choice {
        let gated = state
            .players
            .get(&seat)
            .is_some_and(|p| p.stress >= 4 && !p.freedom_gate_lifted);
        let rank = |c: &GroundCommand| -> i32 {
            match c {
                GroundCommand::SelectAction {
                    action, problem, ..
                } => match action {
                    Action::Ground if gated => 100,
                    Action::Attack => self.0, // <-- the ONE varying number (greedy: 10)
                    Action::Solve
                        if problem
                            .and_then(|p| state.problems.get(&p))
                            .is_some_and(|p| p.claimed_by.is_some()) =>
                    {
                        5
                    }
                    Action::Solve => 90,
                    Action::Investigate => 80,
                    Action::Support => 70,
                    Action::Ground => 60,
                },
                GroundCommand::SpendFreedom => {
                    if gated {
                        96
                    } else {
                        0
                    }
                }
                GroundCommand::Reveal | GroundCommand::Resolve | GroundCommand::EndRound => -1,
                _ => 50,
            }
        };
        let mut best = 0usize;
        for (i, c) in legal.iter().enumerate() {
            if rank(c) > rank(&legal[best]) {
                best = i;
            }
        }
        Choice::Command(best)
    }
}

fn sweep(
    name: &str,
    players: u8,
    mk: &dyn Fn(u64, u8) -> Vec<Box<dyn Policy>>,
) -> (u32, u32, u32, u32) {
    let (mut games, mut won, mut atk, mut darvo) = (0, 0, 0, 0);
    for seed in 0..200u64 {
        let Ok(st) = GroundState::setup(
            &Setup {
                players,
                preset: format!("standard-{players}p"),
                patch: Default::default(),
            },
            seed,
        ) else {
            continue;
        };
        let mut ps = mk(seed, players);
        let Ok(g) = play(st, &mut ps) else { continue };
        games += 1;
        if g.state.outcome.as_ref().is_some_and(|o| o.group_success) {
            won += 1;
        }
        for (_, c) in &g.steps {
            if let GroundCommand::SelectAction {
                action: Action::Attack,
                ..
            } = c
            {
                atk += 1;
            }
        }
        for e in &g.events {
            if matches!(e, games_ground::GroundEvent::DarvoTriggered { .. }) {
                darvo += 1;
            }
        }
    }
    let _ = name;
    (games, won, atk, darvo)
}

fn main() {
    println!("F17: does ATTACK cost you the game, or does our bot just avoid it?\n");
    // The gradient, not just the extremes: greedy ranks Attack at 10,
    // below everything. 75 puts it above SUPPORT and below INVESTIGATE --
    // "attack when convenient". 95 is "attack whenever legal".
    println!("       rank=10 (greedy)   rank=75 (sometimes)  rank=95 (always)");
    println!("seats   won  atk darvo     won  atk darvo      won  atk darvo");
    for players in [2u8, 3, 4, 5, 6] {
        let cell = |r: i32, p: u8| {
            sweep("x", p, &move |_s, n| {
                (0..n)
                    .map(|_| Box::new(Attacker(r)) as Box<dyn Policy>)
                    .collect()
            })
        };
        let (_, gw, ga, gd) = sweep("greedy", players, &|_s, p| {
            (0..p)
                .map(|_| Box::new(GreedyPolicy) as Box<dyn Policy>)
                .collect()
        });
        let (_, mw, ma, md) = cell(75, players);
        let (_, aw, aa, ad) = cell(95, players);
        println!("  {players}p   {gw:>4} {ga:>4} {gd:>5}    {mw:>4} {ma:>4} {md:>5}     {aw:>4} {aa:>4} {ad:>5}");
    }
    println!("\n(200 games per cell; greedy shown as the rank=10 column)");
}