Solver: best decisions per dragon colour, and the bot advisor

- packages/core/src/solver.js: decision tree with perfect recall over the
  community form's choices; chance events (first dragon, deaths, shadow,
  meadow dragon, encounter outcome) depend on earlier choices through
  hierarchical Dirichlet back-off with empirical-Bayes concentration per
  event; backward induction for P(colour this attempt) and Dinkelbach for
  P(colour) / (P(colour) + P(other colour)); 200 posterior draws for
  credible intervals and "still best" rates; cross-fitted held-out check.
- Only genuine attempts inform encounter outcomes (goal / Malek intent).
- data/public/policy.json (all runs and a low-bias sample) and the readable
  docs/POLICY.md; published on Pages with solver.js for the bot.
- Bot advisor: re-solves from any history, maps advice onto screen text,
  reports margins so ties can be randomised. docs/BOT_INTEGRATION.md.
- Tests on a synthetic world with known answers; daily source update now
  rebuilds the policy.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UCzTd31GphpMXDhQqWrCMQ
This commit is contained in:
ekcSchiano
2026-11-01 22:34:38 +00:00
co-authored by Claude Opus 5.5
parent 46ee08a56b
commit d2ffb84b5e
12 changed files with 1842 additions and 5 deletions
+39
View File
@@ -0,0 +1,39 @@
// Build data/public/policy.json: the best decisions for each dragon colour, under both objectives.
// node scripts/build-policy.js [--draws 200]
const fs = require("fs");
const path = require("path");
const E = require("../packages/core/src/engine.js");
const S = require("../packages/core/src/solver.js");
const root = path.resolve(__dirname, "..");
const arg = (k, d) => { const i = process.argv.indexOf("--" + k); return i > 0 ? process.argv[i + 1] : d; };
const draws = +arg("draws", 200);
const raw = JSON.parse(fs.readFileSync(path.join(root, "data/public/form_responses.json"), "utf8"));
const { runs } = E.codeRows(raw.rows, raw.headers);
const isRare = (g) => ["Blue", "Black", "Blue or Black"].includes(g);
const samples = {
// every run
all: runs,
// runs least affected by selective reporting: bulk logs, plus form runs from riders not chasing a rare dragon
lowBias: runs.filter((r) => r.source !== "Form" || !isRare(r.goal)),
};
const t0 = Date.now();
const out = { schema: 1, source: { form_rows: raw.rows.length }, samples: {} };
for (const [name, rs] of Object.entries(samples)) {
out.samples[name] = S.buildPolicy(rs, { draws });
console.log(`${name}: ${rs.length} runs, ${((Date.now() - t0) / 1000).toFixed(1)} s`);
}
// a content id, so the bot can record which policy produced each run (no timestamps: the build is reproducible)
out.id = require("crypto").createHash("sha1").update(JSON.stringify(out.samples)).digest("hex").slice(0, 12);
fs.writeFileSync(path.join(root, "data/public/policy.json"), JSON.stringify(out));
console.log("policy id", out.id);
const pct = (p) => (100 * p).toFixed(p < 0.01 ? 2 : 1) + "%";
for (const [name, s] of Object.entries(out.samples)) {
console.log(`\n${name} alphas ${JSON.stringify(s.model.alphas)}`);
for (const [X, t] of Object.entries(s.targets)) {
const a = t.thisAttempt, b = t.eventually;
console.log(` ${X.padEnd(6)} this attempt ${pct(a.pX.mean)} [${pct(a.pX.lo)}, ${pct(a.pX.hi)}] other bond ${pct(a.pOther.mean)}` +
` | eventually: ratio ${pct(b.ratio.mean)}, P(X) ${pct(b.pX.mean)}, ~${b.expectedAttempts.mean.toFixed(0)} attempts` +
` | cross-fit ${pct(t.crossFit.inSample)} -> held-out ${pct(t.crossFit.heldOut)}`);
}
}