//! Does H1 do nothing, or does it do nothing **to a seat that already
//! manages its Stress**? (CB-WP-0039)
//!
//! [`CB-EV-0030`] measured ground-game's H1 with a panel that was
//! greedy-family throughout, and found DARVO never arms. But
//! `GreedyPolicy` ranks `Action::Ground if gated => 100`: the moment the
//! stress gate bites it grounds, Stress plateaus at 3, and the arm at 5
//! is unreachable **by construction**.
//!
//! H1 was written for the seat that does *not* do that. So this varies
//! **exactly one preference** — GROUND demoted below ATTACK — and holds
//! every other ranking identical to greedy's.
//!
//! [`CB-EV-0030`]: ../../../evidence/CB-EV-0030-h1-measured.md

use cb_game_runtime::{ScenarioGame, Setup};
use cb_kernel::PlayerId;
use games_ground::bot::{play, Choice, GreedyPolicy, Policy};
use games_ground::{Action, GroundCommand, GroundState, ScoringMode, Variant};

/// Greedy, with GROUND demoted below ATTACK. Nothing else differs.
///
/// **It delegates.** An earlier version re-typed an abridged copy of
/// greedy's ranking and called changing one line of the copy "one
/// preference"; it differed in five, and the seat burned its Freedom
/// token in round one of every game. This comment used to argue for the
/// copy, which gave a future maintainer written cover to restore it
/// (CB-REV-0002 #11).
struct Reactive;

impl Policy for Reactive {
    fn name(&self) -> &'static str {
        "reactive"
    }
    fn choose(
        &mut self,
        state: &GroundState,
        seat: PlayerId,
        legal: &[GroundCommand],
        _may_pass: bool,
    ) -> Choice {
        let gated = state
            .players
            .get(&seat)
            .is_some_and(|p| p.stress >= 4 && !p.freedom_gate_lifted);
        // ONE ARM OVERRIDDEN, THE REST DELEGATED.
        //
        // The first version re-typed greedy's ranking and changed one
        // line of the copy. It differed in five places, and the review
        // found it: `SpendFreedom` ranked 95 unconditionally instead of
        // greedy's `95 if gated else 0`, so this seat spent its Freedom
        // token in round one of every game — a second change to the very
        // mechanism under study. Delegating makes "exactly one preference
        // differs" structurally true instead of a claim in a comment.
        let rank = |c: &GroundCommand| -> i32 {
            match c {
                GroundCommand::SelectAction {
                    action: Action::Ground,
                    ..
                } if gated => 5,
                other => GreedyPolicy::rank(state, seat, other),
            }
        };
        let mut best = 0;
        for (i, c) in legal.iter().enumerate() {
            if rank(c) > rank(&legal[best]) {
                best = i;
            }
        }
        Choice::Command(best)
    }
}

/// The starting Stress, **read off the dealt state** rather than declared.
///
/// It was a `const 2` "named so the peak metric cannot silently disagree
/// with setup" — and nothing compared it to setup, so raising it to 7
/// printed `peak 7` in every cell with no warning (CB-REV-0003 #6).
/// Naming a constant is not checking it.
fn start_stress(state: &GroundState) -> u8 {
    state.players.values().map(|p| p.stress).max().unwrap_or(0)
}

/// Games per cell. Named once so the assertion and the banner cannot
/// disagree — the banner said "200 games per cell" over 196-game columns.
const GAMES: u32 = 200;

struct Cell {
    games: u32,
    won: u32,
    atk: u32,
    darvo: u32,
    peak_stress: u8,
    /// Setups the engine refused. **Counted, not skipped** (CB-REV-0001
    /// #11): CB-EV-0030 §3 credited this pass with fixing silent skips
    /// and only the `play` path was instrumented.
    setup_fails: u32,
    /// DARVO arms at the End of Round 5. `GameEnded` is pushed
    /// immediately after, so the sequence never advances a stage — the
    /// arm is real and can do nothing. Reported separately, because
    /// ground-game's criterion 1 is asking about DARVO *mattering*.
    inert_arms: u32,
    /// Games that reached an outcome over the full five rounds.
    ///
    /// **`games` counts `play` returning `Ok`, which is not the claim.**
    /// Stopping the engine after one round produced 200 games, all-zero
    /// columns and exit 0 — the exact signature CB-EV-0030 §3 says the
    /// instrumentation distinguishes from a real result.
    played: u32,
}

fn sweep(mode: ScoringMode, variant: Variant, players: u8, reactive: bool) -> Cell {
    let mut c = Cell {
        games: 0,
        won: 0,
        atk: 0,
        darvo: 0,
        peak_stress: 0,
        setup_fails: 0,
        inert_arms: 0,
        played: 0,
    };
    for seed in 0..GAMES as u64 {
        let Ok(mut st) = GroundState::setup(
            &Setup {
                players,
                preset: format!("standard-{players}p"),
                patch: Default::default(),
            },
            seed,
        ) else {
            c.setup_fails += 1;
            continue;
        };
        st.mode = mode;
        st.variant = variant;
        // The dealt state, kept so the peak metric can read the real
        // starting Stress rather than trust a constant.
        let started = st.clone();
        let mut ps: Vec<Box<dyn Policy>> = (0..players)
            .map(|_| {
                if reactive {
                    Box::new(Reactive) as Box<dyn Policy>
                } else {
                    Box::new(GreedyPolicy) as Box<dyn Policy>
                }
            })
            .collect();
        // A refused game is not a lost game (CB-EV-0030 §3).
        let g = match play(st, &mut ps) {
            Ok(g) => g,
            Err(e) => {
                eprintln!("  !! {players}p seed {seed}: {e:?}");
                continue;
            }
        };
        c.games += 1;
        // A game that RAN is not a game that was PLAYED (CB-REV-0003 #2).
        if g.state.outcome.is_some() && g.rounds == 5 {
            c.played += 1;
        }
        if g.state.outcome.as_ref().is_some_and(|o| o.group_success) {
            c.won += 1;
        }
        for (_, cmd) in &g.steps {
            if let GroundCommand::SelectAction {
                action: Action::Attack,
                ..
            } = cmd
            {
                c.atk += 1;
            }
        }
        // Peak Stress **held**.
        //
        // The original took a maximum over `StressSet` PAYLOADS, and the
        // starting value is written by `setup` and never by an event — so
        // a table that sat at 2 all game reported 1.
        //
        // **The first correction did not change the number it computes**
        // (CB-REV-0003 #5): `held`'s values are exactly
        // `{start} ∪ {payloads}`, so with the floor applied
        // `peak_held ≡ max(start, peak_payload)` for every possible input,
        // and the comment claiming a change of subject was false of the
        // new code too. The real fix is that `start` is now read off the
        // dealt state instead of asserted by a constant.
        // An arm is inert when NO `RoundEnded` follows it: the game
        // ended in the same End step, so the sequence never advances a
        // stage. `g.rounds >= 5` is a property of the GAME, not of the
        // event, and using it marked every arm in every completed game
        // as inert — which is how a metric ends up equal to the thing it
        // was supposed to be a subset of.
        let last_round_ended = g
            .events
            .iter()
            .rposition(|e| matches!(e, games_ground::GroundEvent::RoundEnded { .. }));
        let start = start_stress(&started);
        let mut held: std::collections::BTreeMap<PlayerId, u8> =
            g.state.players.keys().map(|s| (*s, start)).collect();
        c.peak_stress = c.peak_stress.max(start);
        for (i, e) in g.events.iter().enumerate() {
            if matches!(e, games_ground::GroundEvent::DarvoTriggered { .. }) {
                c.darvo += 1;
                if last_round_ended.is_none_or(|last| i > last) {
                    c.inert_arms += 1;
                }
            }
            if let games_ground::GroundEvent::StressSet { player, stress } = e {
                held.insert(*player, *stress);
            }
            // Read from `held`, which is the point. The first correction
            // BUILT `held`, then took the max over event payloads anyway
            // and silenced the unused binding with `let _ = held;` — so
            // the comment described code that did not exist (CB-REV-0002
            // #10). The published figures were right only because the
            // START_STRESS floor made the two agree.
            c.peak_stress = c
                .peak_stress
                .max(held.values().copied().max().unwrap_or(start));
        }
    }
    // **`games`, not `games + setup_fails`** (CB-REV-0002 #1).
    //
    // The first version asserted the SUM — and a refused setup increments
    // `setup_fails` while skipping `games`, so the sum is invariant under
    // exactly the failure it claimed to catch. It could only ever fire on
    // a `play` error, the path that was already instrumented. Verified by
    // injecting setup failures: green, exit 0, and a full table printed
    // over 196-game columns under a banner reading "200 games per cell".
    assert_eq!(
        c.games, GAMES,
        "{players}p {variant:?}: only {} of {GAMES} games ran ({} setups refused) — \
         the cell is short, so every number in it is over a sample nobody chose",
        c.games, c.setup_fails
    );
    assert_eq!(
        c.played, GAMES,
        "{players}p {variant:?}: {} of {} games reached an outcome over five rounds",
        c.played, c.games
    );
    if c.setup_fails > 0 {
        eprintln!(
            "  !! {players}p {variant:?}: {} setups refused",
            c.setup_fails
        );
    }
    c
}

fn main() {
    println!("CB-WP-0039 — does H1 reach a seat that does not regulate?\n");
    println!("`reactive` is greedy with ONE preference changed: GROUND is");
    println!("demoted below ATTACK, so the seat never grounds to shed Stress.");
    println!("SHARED GROUND; `won` is group success; {GAMES} games per cell.\n");

    for (vlabel, variant) in [
        ("BASELINE ground-darvo-r0", Variant::Baseline),
        ("H1 h1-problem-stress", Variant::H1ProblemStress),
    ] {
        println!("{vlabel}");
        println!("            greedy (regulates)          reactive (does not)");
        println!("seats   games won  atk darvo peak    games won  atk darvo peak   inert");
        for players in [2u8, 3, 4, 6] {
            let g = sweep(ScoringMode::SharedGround, variant, players, false);
            let r = sweep(ScoringMode::SharedGround, variant, players, true);
            println!(
                "  {players}p    {:>4} {:>4} {:>4} {:>5} {:>4}    {:>4} {:>4} {:>4} {:>5} {:>4}  {:>6}",
                g.games,
                g.won,
                g.atk,
                g.darvo,
                g.peak_stress,
                r.games,
                r.won,
                r.atk,
                r.darvo,
                r.peak_stress,
                r.inert_arms
            );
        }
        println!();
    }
}