- the importer reads data/accounts/*/runs.jsonl and logs/accounts/*/encounters.jsonl; with account folders, the top-level files (a mirror of the first account) are skipped - run records that carry their steps (schema 2) become trajectories directly, keeping what the bot saw (shadow, meadow dragons), propensities, decision mode and policy id; older runs are still rebuilt from the decision log; bonded runs without steps are kept - account names become salted hashes (DK_ACCOUNT_SALT, or a private salt in data/raw) - runs_clean.csv: new bot_mode column; saw_shadow and saw_blue_meadow from what the bot saw; deliberate burns say why - crosswalk: the valley Red, leaving squadmates, squad direction, hold your ground, hide/approach reactions, the wounded cadet's other two choices Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01UCzTd31GphpMXDhQqWrCMQ
9.5 KiB
Connecting the DragonKind bot to the atlas
Data flows both ways:
community sources, reports ─────┐
├─► threshing-atlas ──► policy.json + solver.js ──► bot (advice per screen)
bot runs (anonymised) ──────────┘ ▲ │
└──────────── collection --source bot + PR ◄┘
Without GitHub: swapping zips
When GitHub Pages is not available, the same files travel as zips:
- Atlas → bot:
python -m collection export-bot-kitwritesexports/atlas-for-bot-<date>-<policy id>.zip(policy.json,solver.js,graph.js, a README with checksums). Unzip it into the bot'svendor/threshing-atlas/. - Bot → atlas: zip the bot's
data/andlogs/folders (folder names kept; a zip of the whole repo works too; screenshots are not needed) and send it. The importer readsdata/knowledge.jsonand, for every account,data/accounts/<account>/runs.jsonlandlogs/accounts/<account>/encounters.jsonl(with one folder per account, the top-leveldata/runs.jsonlandlogs/encounters.jsonlmirror the first account and are skipped). Run records that carry their own steps (the bot's schema 2) are used as they are, including what the bot saw (shadow, meadow dragons), its decision mode and the policy id; older runs are rebuilt from the decision log. Account names become salted hashes. Put it in the atlas'sinbox/and runpython -m collection refresh --bot inbox/<the zip>: it imports the runs (anonymised: no prose, no account names), rebuilds everything, and thenexport-bot-kitmakes the new zip to send back.
1. From the atlas to the bot
What is published
GitHub Pages serves these files (they update whenever new data is merged):
| File | What it is |
|---|---|
https://ekcschiano.github.io/threshing-atlas/data/policy.json |
The model: count tables, fitted shrinkage, allowed options, and for every colour the recommended decision tree under both objectives, with credible intervals. About 400 KB. Has an id (content hash). |
https://ekcschiano.github.io/threshing-atlas/solver.js |
The solver and the bot helper (advisor, recommendOption, solverHistory). No dependencies, CommonJS or browser. |
https://ekcschiano.github.io/threshing-atlas/graph.js |
trajectoryVariables(): turns the bot's step trail into the community form's variables. |
Getting them into the bot
Keep a pinned local copy, so a bad publish can never change the bot mid-run. A small sync script in the bot
repo (for example scripts/sync-atlas.js):
// node scripts/sync-atlas.js -> vendor/threshing-atlas/{solver.js,graph.js,policy.json}
const fs = require('node:fs');
const path = require('node:path');
const BASE = 'https://ekcschiano.github.io/threshing-atlas/';
const OUT = path.join(__dirname, '..', 'vendor', 'threshing-atlas');
(async () => {
fs.mkdirSync(OUT, { recursive: true });
for (const f of ['solver.js', 'graph.js', 'data/policy.json']) {
const res = await fetch(BASE + f);
if (!res.ok) throw new Error(`${f}: HTTP ${res.status}`);
const body = await res.text();
if (f.endsWith('.json')) JSON.parse(body); // refuse a broken file
fs.writeFileSync(path.join(OUT, path.basename(f)), body);
}
const { id } = JSON.parse(fs.readFileSync(path.join(OUT, 'policy.json'), 'utf8'));
console.log('atlas policy', id);
})();
Run it by hand, or once a day before the first attempt. Commit vendor/threshing-atlas/ in the bot repo if you
want the exact policy in its history.
What changed in November 2026
The calls above are unchanged, but solver.js is now a small advisor (about 250 lines) that reads the game itself
from policy.json (samples.*.model.game, from core/spec/game.yaml) instead of having it written into the code.
For the bot that means:
- Histories (
h) use the game's step names:company,leave,direction,fs,react,scream,clearing,fight,dagger,fateorwounded,post,hour,shadow,shadowColour,descend,red,valley,meadow,encounter.solverHistory()already produces these; the oldcadetandleftkeys are no longer read. - New choices the bot will be asked about: leaving your squadmates (
leave), how you react to the first dragon (react), and, below the tree, jumping onto the Red or letting it pass (red). The text the bot sees for each option is ingame.yamlunderbot_text, so new screens can be matched by editing that file. - If a history skips a decision but already has a later step (an older record, say), the recommended option is assumed for the skipped one.
- Re-sync
solver.js,graph.jsandpolicy.jsontogether: the newsolver.jsneeds the game inside the newpolicy.json.
Asking for advice on a screen
const Solver = require('../vendor/threshing-atlas/solver.js');
const Graph = require('../vendor/threshing-atlas/graph.js');
const policy = require('../vendor/threshing-atlas/policy.json');
// once per attempt: target colour from settings, "eventually" because the bot burns on purpose
const advisor = Solver.advisor(policy.samples.all, 'Black', 'eventually');
// on every decision screen
function atlasAdvice(run, offeredChoiceTexts, seen) {
const { vars } = Graph.trajectoryVariables({ steps: run.steps, outcome: {} });
const h = Solver.solverHistory(vars, seen); // seen: { shadow: 'yes'|'no', shadowColour, meadow }
return Solver.recommendOption(advisor, h, offeredChoiceTexts);
}
recommendOption returns null when the next step is chance (nothing to decide), or
{ index, decision, choice, margin, options, reason }:
indexis the option to click, ornullwhen the advice cannot be matched to this screen. Then use the bot's own rules.decision === 'encounter'comes without an index:choiceis"Attempt the bond"or"Die on purpose", and the bot already knows which of its options do each.marginis the gap in P(target) between the best and second-best option.optionshas every option's value.
seen is what only the bot can observe: whether the shadow was at the treetop (shadow: 'yes' | 'no'), its colour
(shadowColour), and the colour waiting in the meadow (meadow), all from the scene tint.
The advisor re-solves the model on the bot's machine (a few milliseconds), so it gives advice from any history, including runs that have already left the recommended route.
Where it goes in the decision order
The atlas is advice. The bot's own safety rules stay in charge:
- Account Lock Guard and the intentional-burn protection (never risk a non-target bond).
- Atlas advice, when
indexis not null and the margin is clear (see ties below). - The bot's PDF strategy and learned rules.
Log every atlas pick with rule: 'ATLAS_POLICY', source: 'atlas', and the run-level policyId: policy.id
(see docs/BOT_DATA_PROTOCOL.md), so we can tell which policy produced which runs.
Ties are free experiments
Many choices barely matter by the data we have (for Black, the first direction differs by a tenth of a percentage
point). When margin is below the tie threshold (start with 0.002, i.e. 0.2 percentage points), pick at random
among the tied options and log propensity (1 / number of tied options). That costs nothing in expected success,
and it is exactly the randomised data the atlas needs to tell real history effects from guide-copying.
Which numbers to trust
policy.json has two samples:
samples.all: every run. Use it for the advisor (more data, decisions are about relative differences).samples.lowBias: bulk logs and riders not chasing a rare dragon. Use it for absolute expectations, such as how many attempts a Blue should take. Rare sightings are over-reported in form posts, soallis optimistic for Blue.
Current headline (from analysis/reports/POLICY.md): Black about 1.7% per attempt (about 60 attempts), Blue 3.7–7% per attempt
(14–28 attempts), depending on the sample.
2. From the bot to the atlas
Already in place: DRAGONKIND_BOT_DIR=/path/to/DragonKind python -m collection update --source bot in the atlas repo converts the bot's
knowledge.json, runs.jsonl and logs/encounters.jsonl into anonymised files under data/bot/, and refuses to
write prose or account names. Commit them by pull request; CI rebuilds the graph and checks everything.
What would make the bot's data far more useful (details in docs/BOT_DATA_PROTOCOL.md):
- record the options on screen, what was seen (tint, shadow),
policyId,propensityanddecisionModeon every step; - split goal accounts (follow the advisor) from research accounts (run the tie experiments and the experiment list);
- add
accountKey(salted hash), and the reason for every deliberate burn.
3. Limits to keep in mind
- The community form does not record the answers inside each bonding encounter, so the bond chance at an encounter is the community average. The bot's own scene-level data will refine that over time.
- The model learns how much history matters from the data. Today it finds that the meadow colour does not depend on earlier choices at all, and the shadow only weakly. The bot's randomised runs are what can confirm or overturn that.
- The policy is only as good as the crosswalk between the bot's screen text and the form's variables. If the game
changes its wording,
OPTION_PATTERNSinsolver.jsand the crosswalk incollection/specs/bot.yaml(written intograph.jsbypython -m collection build) need updating.