station-master/test/harness.test.ts

/**
 * The measurement machinery itself.
 *
 * These tests exist because a measurement tool that is quietly wrong is worse than no tool: it does
 * not fail, it just produces numbers that decide what the bot becomes. Each one guards a property
 * the paired method depends on.
 */

import { describe, it } from 'node:test';
import assert from 'node:assert/strict';
import { existsSync, readFileSync, readdirSync } from 'node:fs';
import { dirname, join } from 'node:path';
import { fileURLToPath } from 'node:url';

import { pump } from '../src/engine/advance.ts';
import { createGame } from '../src/engine/setup.ts';
import { adTrackCount } from '../src/engine/state.ts';
import type { GameConfig, GameState } from '../src/engine/state.ts';
import type { BotPolicy } from '../src/sim/bot.ts';
import { developerBot, makeDeveloperBot, playGame } from '../src/sim/bot.ts';
import { compare, parseTweaks } from '../src/sim/compare.ts';
import { applyIntent } from '../src/engine/apply.ts';
import { legalActions } from '../src/engine/legal.ts';
import { ROLLING_STOCK_SUPPLY } from '../src/engine/content.ts';
import { fromSave } from '../src/web/game.ts';
import { makeFunnelProbe, summarize } from '../src/sim/stats.ts';

const root = join(dirname(fileURLToPath(import.meta.url)), '..');

const config: GameConfig = {
  mode: 'solitaire',
  days: 5,
  minCombinedRevenue: 0,
  maxCollisionsPerDay: 0,
  maxCollisionsTotal: 0,
  pvpCardsAllowed: false,
  // These fixtures were written against a Whistle Post opening — one A/D track and no
  // Control Point — and several of them test exactly that. Named explicitly since the
  // default became a Depot.
  houseRules: { startingOffice: 'whistlePost' },
  optionalRules: {
    reducedVisibility: false,
    employeeRotation: false,
    emergencyToolbox: false,
  },
};

const game = (seed: number): GameState =>
  createGame({ id: `h${seed}`, seed, config, playerNames: ['bot'] });

/** One game, reduced to a string: every event type in order, plus the final revenue. */
function fingerprint(policy: BotPolicy, seed: number): string {
  const s = game(seed);
  const r = playGame(s, policy, pump);
  return `${r.revenue[0]}|${r.events.map((e) => e.type).join(',')}`;
}

describe('the paired method rests on determinism', () => {
  it('plays the identical game twice from one seed', () => {
    /**
     * THE PROPERTY EVERYTHING ELSE DEPENDS ON. A paired comparison subtracts two games that share a
     * deal; if the same policy on the same seed can diverge, the difference is measuring the engine's
     * own noise and every heuristic verdict is worthless.
     *
     * It is also the engine's central claim — pure, seeded, no ambient randomness — and the failure
     * mode is silent: one `Math.random`, one Map iterated in a different order, and this is the only
     * thing that would notice.
     */
    for (const seed of [1000, 8919, 775569289]) {
      assert.equal(fingerprint(developerBot, seed), fingerprint(developerBot, seed), `seed ${seed} diverged`);
    }
  });

  it('gives the untweaked variant the identical game too', () => {
    // `developerBot` IS `makeDeveloperBot({})`, and the refactor that introduced tweaks must not
    // have changed a single decision. If this fails, every number measured before it is unusable.
    for (const seed of [1000, 8919, 775569289]) {
      assert.equal(
        fingerprint(developerBot, seed),
        fingerprint(makeDeveloperBot({}), seed),
        `seed ${seed}: the untweaked variant plays a different game`,
      );
    }
  });
});

describe('a tweak has to actually do something', () => {
  it('actually holds the trains the Office cannot hold', () => {
    /**
     * REGRESSION, and the reason this file exists. The first `trainCapSlack` gated the two branches
     * whose comments say they exist to play a train card — and measured **exactly zero difference
     * over 400 paired seeds**, because `followThrough` ends with a generic "play what is in hand"
     * fallback that played the card anyway.
     *
     * ASSERT THE CONTRACT, NOT MERELY A DIFFERENCE. A first version of this test only checked that
     * some decision changed somewhere, and it passed against the broken bot: with a tight cap the
     * gated branches do change which Local Operations option is chosen, they just fail to stop the
     * card being played two steps later. "Something moved" is not the promise. The promise is that
     * committed trains never exceed what the Office can hold.
     *
     * Office tiers only ever go up, so the final A/D count is the most generous the cap ever was.
     */
    const committed = (s: GameState): number =>
      s.timetable.filter((t) => t !== null).length + s.pendingExtras.length;

    const uncapped = makeDeveloperBot({ noTrainCap: true });
    let cappedWorst = 0;
    let ablatedWorst = 0;
    for (const seed of [1000, 8919, 16838, 24757, 32676, 40595, 48514]) {
      const a = game(seed);
      playGame(a, developerBot, pump);
      cappedWorst = Math.max(cappedWorst, committed(a) - adTrackCount(a, 0));

      const b = game(seed);
      playGame(b, uncapped, pump);
      ablatedWorst = Math.max(ablatedWorst, committed(b) - adTrackCount(b, 0));
    }
    assert.ok(
      cappedWorst <= 0,
      `the bot committed ${cappedWorst} train(s) more than the Office can hold`,
    );
    // And the cap is not vacuous: with it ablated, the bot really does overshoot on these seeds.
    assert.ok(ablatedWorst > 0, 'the ablated bot never overshoots either, so this test proves nothing');
  });

  it('names itself so a report cannot confuse two runs', () => {
    assert.equal(developerBot.name, 'developer');
    assert.equal(makeDeveloperBot({}).name, 'developer');
    assert.equal(makeDeveloperBot({ noTrainCap: true }).name, 'developer+noTrainCap=true');
  });

  it('refuses a tweak name it does not know', () => {
    // A typo silently parsed as "no tweaks" would compare the bot against itself and report a
    // confident zero — the most expensive possible failure of this tool.
    assert.deepEqual(parseTweaks(['400', 'noTrainCap=1']), { noTrainCap: true });
    assert.throws(() => parseTweaks(['noTrainCapp=1']), /unknown tweak/);
  });
});

describe('the funnel counts what it claims to count', () => {
  it('keeps every gate inside the total it is a fraction of', () => {
    const s = game(430);
    const probe = makeFunnelProbe(0);
    const r = playGame(s, developerBot, pump, 50_000, probe.onEvent, probe.onTurn);
    const f = probe.funnel;

    assert.ok(f.arrivals > 0, 'no train reached an Office in a whole game');
    for (const [name, n] of [
      ['at a passenger office', f.arrivalsAtPassengerOffice],
      ['with an empty coach', f.arrivalsWithEmptyCoach],
      ['with a loaded coach', f.arrivalsWithLoadedCoach],
      ['with a wanted car', f.arrivalsWithWantedCar],
    ] as const) {
      assert.ok(n <= f.arrivals, `${name} (${n}) exceeds arrivals (${f.arrivals})`);
    }

    assert.ok(f.cargoPhases > 0, 'no Cargo phase was sampled');
    for (const [name, n] of [
      ['with a facility', f.cargoWithFacility],
      ['green stocked', f.cargoGreenStocked],
      ['car spotted', f.cargoCarSpotted],
      ['laborer free', f.cargoLaborerFree],
      ['ready', f.cargoReady],
    ] as const) {
      assert.ok(n <= f.cargoPhases, `${name} (${n}) exceeds Cargo phases (${f.cargoPhases})`);
    }
    // "All three at one industry" cannot exceed any of the three it is made of.
    assert.ok(f.cargoReady <= Math.min(f.cargoGreenStocked, f.cargoCarSpotted, f.cargoLaborerFree));
    assert.ok(f.buriedWithDigAvailable <= f.buriedTurns);

    // Sampled once per Cargo phase, never once per decision: 5 Days x 12 Stages is the ceiling.
    assert.ok(f.cargoPhases <= 60, `${f.cargoPhases} Cargo phases in a 5-Day game`);

    // And the arrivals it counted are the arrivals that happened.
    const arrived = r.events.filter((e) => e.type === 'trainArrived').length;
    assert.equal(f.arrivals, arrived, 'the probe and the event log disagree about arrivals');
  });

  it('rides along on the harness summary', () => {
    const s = game(202);
    const probe = makeFunnelProbe(0);
    const r = playGame(s, developerBot, pump, 50_000, probe.onEvent, probe.onTurn);
    const stats = summarize(202, r.events, r.intents, s, probe.funnel);
    assert.ok(stats.funnel, 'summarize dropped the funnel');
    assert.equal(stats.funnel!.arrivals, probe.funnel.arrivals);
    // Optional, so a caller with no probe still gets a summary.
    assert.equal(summarize(202, r.events, r.intents, s).funnel, undefined);
  });
});

describe('the game conserves Rolling Stock', () => {
  it('creates no car that was not dealt, and destroys none but in a collision', () => {
    /**
     * REGRESSION, found by audit rather than by a failing test — which is why this one exists.
     *
     * `TODO.md` had it as an open question: a census of every holder came to 92 against the 80 cars
     * dealt, "not necessarily duplication, because some of those objects are cargo in transit". It
     * was duplication, and it came from two rules the engine had not implemented:
     *
     *   §9.3 unload   — "a load on the industry's track AND AN EMPTY CAR OF THAT TYPE IN THE
     *                    DIVISION YARD ... replaces the load with an empty car of that type"
     *   §9.2 de-train — "a white empty coach IN THE DIVISION YARD ... replace the blue coach on the
     *                    train with the white one"
     *
     * Both requirements were unchecked and both replacement cars were conjured rather than taken, so
     * every unload and every de-training minted a car — 1.29 a game against a supply of 80, which is
     * the number `ROLLING_STOCK_SUPPLY` exists to control.
     *
     * Censused after every batch, because that is the only way this class of bug shows up at all.
     */
    const supply = ROLLING_STOCK_SUPPLY.reduce((n, r) => n + r.loaded + r.empty, 0);
    const census = (st: GameState): number => {
      let n = st.yards.divisionYard.length + st.yards.classificationYard.length;
      for (const t of st.trays.values()) n += t.consist.length;
      for (const [, area] of st.officeAreas) {
        for (const card of area.grid.values()) {
          n += card.standing.length;
          const f = card.facility;
          if (!f) continue;
          n += f.industryTrack.cars.length + f.outboundBox.length + f.inboundBox.length;
          n += (f.menAtWork ?? []).filter((m) => m !== null).length;
        }
      }
      return n;
    };

    for (const seed of [1000, 8919, 16838, 24757, 32676, 40595]) {
      const s = game(seed);
      assert.equal(census(s), supply, `seed ${seed}: the deal itself is short`);
      let expected = supply;

      for (let t = 0; t < 50_000; t++) {
        const before = census(s);
        const pumped = pump(s);
        /**
         * A COLLISION DESTROYS NO CAR, and this used to assume it destroyed all of them.
         *
         * The subtraction that stood here — `expected -= tr.consist.length` for every train in a
         * `trainsDestroyed` event — describes a rule the engine does not have. Gap 2c (`advance.ts`,
         * "TAKE THE WRECK OFF THE CARD") sends the wreck's cabooses back to the Division Yard and
         * everything else to Classification, so the stock is conserved through a collision like any
         * other move. The train is destroyed; its cars are not.
         *
         * It passed for as long as it did because none of the six seeds below ever collided, so the
         * branch never ran. Changing the deck to the sheet's counts (Gitea#14) moved the deals, seed
         * 24757 collided, and the test failed claiming the engine had CONJURED three cars — the
         * exact opposite of what had happened.
         *
         * So the census is now held flat, unconditionally, which is both the real invariant and a
         * stronger test than the one it replaces: there is no longer any event that excuses a
         * change, and `expected` cannot drift away from the supply it was dealt.
         */
        assert.equal(
          census(s),
          before,
          `seed ${seed}: the engine changed the census by ${census(s) - before} while pumping`,
        );
        if (s.status === 'finished') break;
        const actor = s.clock.pendingDecision !== null ? s.clock.superintendent : s.clock.currentActor;
        if (actor === null) break;
        const options = legalActions(s, actor);
        if (options.length === 0) break;
        const was = census(s);
        const r = applyIntent(s, actor, developerBot.choose(s, actor, options));
        if (!r.ok) break;
        assert.equal(
          census(s),
          was,
          `seed ${seed}: a player action changed the Rolling Stock census by ${census(s) - was}`,
        );
      }
      assert.equal(census(s), expected, `seed ${seed}: ended holding ${census(s)} of an expected ${expected}`);
    }
  });
});

describe('every published replay actually replays', () => {
  it('reaches the end of its own history', () => {
    /**
     * REGRESSION, and it had already bitten. `TODO.md` records both published replays going dead
     * without anyone noticing: `fromSave` stops at the first intent the rules no longer accept and
     * returns a SHORTER game, which on screen looks exactly like a game that ended early. Measured
     * when this test was written, all three published replays managed **2 intents of roughly 400**
     * — the site was serving three recordings of nothing.
     *
     * A replay is a save from a particular ruleset, so this is really a test that the rules have not
     * moved under the files in `public/replays`. When it fails, re-record rather than edit:
     * `node src/sim/save-replay.ts 400 --top 3`.
     */
    const dir = join(root, 'public/replays');
    const files = existsSync(dir) ? readdirSync(dir).filter((f) => f.endsWith('.json') && f !== 'manifest.json') : [];
    assert.ok(files.length > 0, 'no replays are published at all');

    for (const f of files) {
      const save = JSON.parse(readFileSync(join(dir, f), 'utf8')) as {
        seed: number;
        history: unknown[];
        rules?: unknown;
      };
      // The WHOLE save, `rules` included. Rebuilding it from seed and history alone threw away the
      // one field that says which ruleset the file was recorded under, so this replayed every
      // published file under the pre-dialog defaults no matter what it said — a test that would
      // pass a genuinely dead replay the moment the defaults and the file disagreed.
      const back = fromSave(save as never);
      assert.equal(
        back.history.length,
        save.history.length,
        `${f} is dead — it replays ${back.history.length} of ${save.history.length} intents. ` +
          'Re-record it with save-replay.ts rather than editing the file.',
      );
      /**
       * `awaitingExtension` counts as the end since Gitea#11 — and for a published file it is the
       * EXPECTED end. These saves were recorded before extended play existed, so their histories
       * carry no `game.extend` vote: replaying one runs the timetable out and stops on the question
       * nobody was there to answer. That is a game that reached the end of its own history, which is
       * what this test is about. `active` would still be a dead replay.
       */
      assert.ok(
        back.state.status === 'finished' || back.state.status === 'awaitingExtension',
        `${f} does not reach the end of its game — status ${back.state.status}`,
      );
      assert.ok(back.state.official !== null, `${f} ends without recording a result`);
    }
  });
});

describe('the comparison arithmetic', () => {
  it('reports a dead heat as a dead heat', () => {
    // Comparing the bot with itself must produce exactly zero, no games differing, and a t of 0 —
    // if the machinery has any asymmetry in it, this is where it shows.
    const r = compare({}, 12);
    assert.equal(r.mean, 0);
    assert.equal(r.identical, 12);
    assert.equal(r.better, 0);
    assert.equal(r.worse, 0);
    assert.equal(r.t, 0);
  });

  it('pairs by seed, and deals the same seeds the harness does', () => {
    const r = compare({ noTrainCap: true }, 5);
    assert.deepEqual(
      r.deltas.map((d) => d.seed),
      [0, 1, 2, 3, 4].map((i) => 1000 + i * 7919),
      'compare and the harness must talk about the same games',
    );
    for (let i = 0; i < r.deltas.length; i++) {
      assert.equal(r.baseStats[i]!.seed, r.deltas[i]!.seed);
      assert.equal(r.variantStats[i]!.seed, r.deltas[i]!.seed);
      assert.equal(r.deltas[i]!.delta, r.variantStats[i]!.revenue.net - r.baseStats[i]!.revenue.net);
    }
  });

  it('computes the standard error from the PAIRED difference', () => {
    // The whole gain of pairing is that σ of the difference is smaller than σ of either side. Using
    // the level's σ by mistake would quietly restore the ±1.0 noise floor this exists to escape.
    const r = compare({ noTrainCap: true }, 40);
    const d = r.deltas.map((x) => x.delta);
    const m = d.reduce((p, c) => p + c, 0) / d.length;
    const sd = Math.sqrt(d.reduce((p, c) => p + (c - m) ** 2, 0) / (d.length - 1));
    assert.ok(Math.abs(r.mean - m) < 1e-9);
    assert.ok(Math.abs(r.sd - sd) < 1e-9);
    assert.ok(Math.abs(r.stderr - sd / Math.sqrt(d.length)) < 1e-9);
  });
});