History/server/regions.ts

// Region-key data access (server). Loads the deterministic region-key manifest
// (region-keys.json: stable feature id -> region key), the sub-national geo
// (regions.geo.json: feature id -> { name, parent }), and — optionally — the
// precomputed region-adjacency manifest (region-adjacency.json: region key ->
// bordering region keys, built by scripts/build-region-adjacency.mjs) and the
// precomputed region-centroid manifest (region-centroids.json: region key ->
// { lat, lon, spread }, built by scripts/build-region-centroids.mjs) — all
// from public/ in dev (Vite serves it) or dist/ in prod (Vite copies
// public/* -> dist/ at build, and the Docker image keeps only dist/) — and
// joins them into the lookups the region-level ownership model needs:
//
//   - expand a nation's ISO_A3 country list -> the region keys of all its sub-regions (v0.19, #16 P1)
//   - build the LLM "regions" reference table (key -> "name (parent ISO_A3)")
//   - the set of all valid region keys (to ignore hallucinated keys in applyTurnResult)
//   - neighboursOf(): the union of the bordering keys for a set of keys — the
//     data behind the LLM's getNeighbours tool and the player-frontier prompt
//     field (v0.21, #16 P2)
//   - centroidOf(): a region key's precomputed anchor point ({ lat, lon, spread })
//     — the data behind LLM-placed map markers (v0.27, #44)
//   - geoOf(): a region key's area (km²) + population (from region-geo.json)
//     — the weighting source for the per-region stats model (v0.28, #46)
//   - resourceOf(): a region key's synthesized resource profile (from
//     region-resources.json) — the data behind the LLM's industry lever
//     (v0.36, #59)
//
// Deliberately turf-free: it reads the JSON files with plain JSON.parse and
// never imports @turf/@types/geojson (importing one pulls @types/geojson into
// the tsc program and breaks WorldMap.tsx; see the v0.17 changelog note).
// Loaded once at boot; the accessors below are pure data reads thereafter.
import { existsSync, readFileSync } from 'node:fs';
import path from 'node:path';
import type { GameState, RegionResources } from '../shared/types';

/** { name, parent } for one sub-region, where parent is the ISO_A3 country. */
interface RegionInfo {
  name: string;
  parent: string;
}

interface RegionData {
  /** stable feature id -> region key (from public/region-keys.json). */
  idToKey: Record<string, string>;
  /** region key -> { name, parent }. */
  keyToInfo: Record<string, RegionInfo>;
  /** ISO_A3 parent -> region keys of its sub-regions (file order, stable). */
  keysByCountry: Record<string, string[]>;
  /** the set of all region keys. */
  validKeys: Set<string>;
  /** region key -> bordering region keys (from public/region-adjacency.json). */
  adjacency: Record<string, string[]>;
  /** region key -> anchor point (from public/region-centroids.json). */
  centroids: Record<string, { lat: number; lon: number; spread: number }>;
  /** region key -> { area (km²), population } (from public/region-geo.json, v0.28 #46). */
  geo: Record<string, { area: number; population: number }>;
  /** region key -> resource profile (from public/region-resources.json, v0.36 #59). */
  resources: Record<string, RegionResources>;
}

let data: RegionData | null = null;

/**
 * Load (or reload) the region-key manifest, geo, adjacency, and centroids.
 * Idempotent.
 * The files are served to the client from `public/` in dev (Vite serves it
 * directly) and from `dist/` in prod (Vite copies `public/*` → `dist/` at build
 * and the Docker image keeps only `dist/`), so probe `public/` then `dist/`
 * (plus the root as a last resort) and use the first directory that holds the
 * key manifest + geo. The adjacency manifest is OPTIONAL: when it is missing
 * or broken, `adjacency` stays empty and `neighboursOf`/`hasAdjacency` simply
 * report "no adjacency" (the LLM tool and the frontier prompt field switch
 * off; everything else keeps working). The centroid manifest is likewise
 * OPTIONAL (v0.27, #44): when missing or broken, `centroids` stays empty and
 * `centroidOf`/`hasCentroids` report "no centroids" (new map markers can't be
 * placed, but everything else keeps working). Returns true when the core pair loaded
 * cleanly; a missing/broken pair clears the data and returns false so the
 * server still boots and degrades gracefully (expansion becomes a no-op,
 * ownership falls back to the raw input keys).
 */
export function loadRegions(root: string): boolean {
  const keyFile = 'region-keys.json';
  const geoFile = 'regions.geo.json';
  const adjacencyFile = 'region-adjacency.json';
  const centroidsFile = 'region-centroids.json';
  const regionGeoFile = 'region-geo.json';
  const regionResourcesFile = 'region-resources.json';
  const base = [
    path.join(root, 'public'), // dev: Vite serves public/ at /
    path.join(root, 'dist'), // prod: Vite copies public/* -> dist/ (== clientDir)
    root, // last resort
  ].find((d) => existsSync(path.join(d, keyFile)) && existsSync(path.join(d, geoFile)));
  if (!base) {
    data = null;
    return false;
  }
  const keyPath = path.join(base, keyFile);
  const geoPath = path.join(base, geoFile);
  try {
    const idToKey = JSON.parse(readFileSync(keyPath, 'utf8')) as Record<string, string>;
    const geoJson = JSON.parse(readFileSync(geoPath, 'utf8')) as {
      features?: Array<{ id?: string | number; properties?: { name?: string; parent?: string } }>;
    };
    const keyToInfo: Record<string, RegionInfo> = {};
    const keysByCountry: Record<string, string[]> = {};
    const validKeys = new Set<string>();
    for (const f of geoJson.features ?? []) {
      const id = f.id == null ? '' : String(f.id);
      const key = idToKey[id];
      if (!key) continue; // a geo feature with no manifest entry is skipped
      const name = typeof f.properties?.name === 'string' ? f.properties.name : '';
      const parent = typeof f.properties?.parent === 'string' ? f.properties.parent : '';
      keyToInfo[key] = { name, parent };
      validKeys.add(key);
      if (parent) (keysByCountry[parent] ??= []).push(key);
    }

    // Adjacency is optional: a missing file means "no adjacency data".
    let adjacency: Record<string, string[]> = {};
    const adjacencyPath = path.join(base, adjacencyFile);
    if (existsSync(adjacencyPath)) {
      try {
        adjacency = JSON.parse(readFileSync(adjacencyPath, 'utf8')) as Record<string, string[]>;
      } catch (err) {
        // A corrupt manifest must not kill the core region data: degrade to
        // "no adjacency" (the LLM tool / frontier guidance simply switch off).
        console.error('[regions] failed to load region-adjacency.json, continuing without it', err);
        adjacency = {};
      }
    }

    // Centroids are optional too (v0.27, #44): a missing/broken file means
    // "no centroid data" — new markers can't be placed (their adds are
    // dropped), but everything else keeps working.
    let centroids: Record<string, { lat: number; lon: number; spread: number }> = {};
    const centroidsPath = path.join(base, centroidsFile);
    if (existsSync(centroidsPath)) {
      try {
        const raw = JSON.parse(readFileSync(centroidsPath, 'utf8')) as Record<
          string,
          { lat?: unknown; lon?: unknown; spread?: unknown }
        >;
        // Keep only well-formed entries; a corrupt file degrades to "none".
        for (const [k, v] of Object.entries(raw)) {
          if (
            v &&
            typeof v.lat === 'number' &&
            typeof v.lon === 'number' &&
            typeof v.spread === 'number' &&
            Number.isFinite(v.lat) &&
            Number.isFinite(v.lon) &&
            Number.isFinite(v.spread)
          ) {
            centroids[k] = { lat: v.lat, lon: v.lon, spread: v.spread };
          }
        }
      } catch (err) {
        console.error('[regions] failed to load region-centroids.json, continuing without it', err);
        centroids = {};
      }
    }

    // The region-geo manifest (v0.28, #46): area (km²) + population per region
    // key — the weighting source for the per-region stats model. OPTIONAL like
    // the others: a missing/broken file means "no geo data", and weighting
    // degrades to uniform (every region weight 1) while everything else keeps
    // working.
    let geo: Record<string, { area: number; population: number }> = {};
    const geoDataPath = path.join(base, regionGeoFile);
    if (existsSync(geoDataPath)) {
      try {
        const raw = JSON.parse(readFileSync(geoDataPath, 'utf8')) as Record<
          string,
          { area?: unknown; population?: unknown }
        >;
        // Keep only well-formed entries; a corrupt file degrades to "none".
        for (const [k, v] of Object.entries(raw)) {
          if (
            v &&
            typeof v.area === 'number' &&
            Number.isFinite(v.area) &&
            v.area >= 0 &&
            typeof v.population === 'number' &&
            Number.isFinite(v.population) &&
            v.population >= 0
          ) {
            geo[k] = { area: v.area, population: v.population };
          }
        }
      } catch (err) {
        console.error('[regions] failed to load region-geo.json, continuing without it', err);
        geo = {};
      }
    }

    // The region-resources manifest (v0.36, #59): a synthesized four-value
    // resource profile per region key — the data behind the LLM's industry
    // lever. OPTIONAL like the others: a missing/broken file means "no
    // resource data" — industry boosts degrade to the unscaled base value and
    // the prompt omits the aggregate profile — while everything else keeps
    // working.
    let resources: Record<string, RegionResources> = {};
    const resourcesPath = path.join(base, regionResourcesFile);
    if (existsSync(resourcesPath)) {
      try {
        const raw = JSON.parse(readFileSync(resourcesPath, 'utf8')) as Record<
          string,
          { oil?: unknown; iron?: unknown; food?: unknown; industry?: unknown }
        >;
        // Keep only well-formed entries (all four values finite numbers in
        // [0, 1]); a corrupt file degrades to "none".
        for (const [k, v] of Object.entries(raw)) {
          if (
            v &&
            typeof v.oil === 'number' && Number.isFinite(v.oil) && v.oil >= 0 && v.oil <= 1 &&
            typeof v.iron === 'number' && Number.isFinite(v.iron) && v.iron >= 0 && v.iron <= 1 &&
            typeof v.food === 'number' && Number.isFinite(v.food) && v.food >= 0 && v.food <= 1 &&
            typeof v.industry === 'number' && Number.isFinite(v.industry) && v.industry >= 0 && v.industry <= 1
          ) {
            resources[k] = { oil: v.oil, iron: v.iron, food: v.food, industry: v.industry };
          }
        }
      } catch (err) {
        console.error('[regions] failed to load region-resources.json, continuing without it', err);
        resources = {};
      }
    }

    data = { idToKey, keyToInfo, keysByCountry, validKeys, adjacency, centroids, geo, resources };
    return validKeys.size > 0;
  } catch (err) {
    console.error('[regions] failed to load region data', err);
    data = null;
    return false;
  }
}

/** Test/dev seam: drop the loaded data (the next accessors behave as "no data"). */
export function resetRegions(): void {
  data = null;
}

/** True when the manifest + geo loaded cleanly. */
export function hasRegionData(): boolean {
  return data !== null;
}

/**
 * Expand a nation's ISO_A3 country list to the region keys of all its sub-regions
 * (file order, deduped). This is what turns a preset's country-level territory
 * into region-level ownership at game creation. Returns the input unchanged when
 * no region data is loaded (graceful degradation — behaves like the old model).
 */
export function expandCountriesToKeys(countries: string[]): string[] {
  if (!data) return countries;
  const out: string[] = [];
  const seen = new Set<string>();
  for (const c of countries) {
    for (const key of data.keysByCountry[c] ?? []) {
      if (!seen.has(key)) {
        seen.add(key);
        out.push(key);
      }
    }
  }
  return out;
}

/**
 * Build the LLM reference table: region key -> "<name> (<parent ISO_A3>)", e.g.
 * `moselle-rygy -> "Moselle (FRA)"`. Only the given keys are included (the caller
 * passes the game's owned-region universe) so the prompt stays bounded.
 */
export function referenceForKeys(keys: Iterable<string>): Record<string, string> {
  const out: Record<string, string> = {};
  if (!data) return out;
  for (const key of keys) {
    const info = data.keyToInfo[key];
    if (info) out[key] = info.parent ? `${info.name} (${info.parent})` : info.name;
  }
  return out;
}

/** The region key's human name (for the dossier), or undefined if unknown. */
export function regionName(key: string): string | undefined {
  return data?.keyToInfo[key]?.name;
}

/** The union of every nation's territory region keys (the game's region universe). */
export function allTerritoryKeys(state: GameState): Set<string> {
  const out = new Set<string>();
  for (const n of Object.values(state.nations)) {
    for (const key of n.territory) out.add(key);
  }
  return out;
}

/** The set of all valid region keys (to ignore hallucinated keys in applyTurnResult). */
export function validKeys(): ReadonlySet<string> {
  return data ? data.validKeys : new Set<string>();
}

/**
 * The set of ISO_A3 country codes that own at least one sub-region in the
 * manifest (the valid `territory` codes for a world draft, v0.31 #52). These
 * are the keys of `keysByCountry` — i.e. the distinct `properties.parent`
 * values in regions.geo.json. Empty when no region data is loaded; callers
 * pass it (or `undefined` to skip filtering) to `validateWorldDraft` so a
 * draft's territory is checked against real countries.
 */
export function validCountryCodes(): ReadonlySet<string> {
  return data ? new Set(Object.keys(data.keysByCountry)) : new Set<string>();
}

/**
 * True when the region-adjacency manifest loaded with at least one entry.
 * Callers (the server's jump route) use this to decide whether to hand the
 * engine an adjacency resolver (which turns on the LLM's getNeighbours tool
 * and the frontier prompt field) or fall back to the plain chat() path.
 */
export function hasAdjacency(): boolean {
  return data !== null && Object.keys(data.adjacency).length > 0;
}

/**
 * True when the region-centroid manifest loaded with at least one entry
 * (v0.27, #44). The server's jump route uses this to decide whether to hand
 * the engine a centroid resolver (which lets a turn place new map markers)
 * or skip marker placement (existing markers are still maintained).
 */
export function hasCentroids(): boolean {
  return data !== null && Object.keys(data.centroids).length > 0;
}

/**
 * True when the region-geo manifest loaded with at least one entry (v0.28,
 * #46). The server's jump route uses this to decide whether to hand the
 * engine a geo resolver (which weights the per-region stats derivation by
 * area×population) or fall back to a uniform (unweighted) median.
 */
export function hasGeo(): boolean {
  return data !== null && Object.keys(data.geo).length > 0;
}

/**
 * The precomputed anchor point for a region key: the centroid of its
 * largest-area part, plus a `spread` (≈ 0.1 × that part's smallest bbox
 * dimension, in degrees) the engine scatters markers within
 * ±(spread/2) of the centroid. `undefined` for an unknown key or when no
 * centroid data is loaded (v0.27, #44).
 */
export function centroidOf(key: string): { lat: number; lon: number; spread: number } | undefined {
  return data?.centroids[key];
}

/**
 * The precomputed area (km²) + population for a region key (v0.28, #46) — the
 * weighting source for the per-region stats model. `undefined` for an unknown
 * key or when no geo data is loaded (the derivation then falls back to a
 * uniform weight of 1 for that region).
 */
export function geoOf(key: string): { area: number; population: number } | undefined {
  return data?.geo[key];
}

/**
 * True when the region-resources manifest loaded with at least one entry
 * (v0.36, #59). The server's jump route uses this to decide whether to hand
 * the engine a resource resolver (which lets a turn scale industry boosts by a
 * region's `industry` value and carry each nation's aggregate resource profile
 * in the LLM prompt) or skip both (industry boosts fall back to the unscaled
 * base value).
 */
export function hasResources(): boolean {
  return data !== null && Object.keys(data.resources).length > 0;
}

/**
 * The synthesized resource profile for a region key (v0.36, #59): the
 * four-value `{ oil, iron, food, industry }` from the committed
 * `public/region-resources.json`. `undefined` for an unknown key or when no
 * resource data is loaded (industry boosts then use the unscaled base value,
 * and the aggregate profile is simply omitted from the prompt).
 */
export function resourceOf(key: string): RegionResources | undefined {
  return data?.resources[key];
}

/**
 * The union of the region keys that share a land border with any of the given
 * keys — deduplicated, the queried keys themselves excluded, and sorted for
 * determinism. This is the data behind the LLM's getNeighbours tool and the
 * player-frontier computation in the turn prompt (v0.21, #16 P2). Returns
 * `[]` when no region data (or no adjacency manifest) is loaded.
 */
export function neighboursOf(keys: Iterable<string>): string[] {
  if (!data) return [];
  const out = new Set<string>();
  for (const key of keys) {
    for (const n of data.adjacency[key] ?? []) out.add(n);
  }
  for (const key of keys) out.delete(key); // never report a key as its own neighbour
  return [...out].sort();
}