Three closures of remaining PRD follow-ups, one merge:
1. Reflex scheduler now drives behaviour from the curriculum.
- reflex.js: replaced ad-hoc techTreeReflex + autonomousReflex with
curriculumReflex that dispatches the skill suggested by
snapshot.curriculum.plan via runSkill. Per-skill backoff for
missing_tool / missing_material / no_target / no_food_source /
unsupported_version. recover() hint with `{hint:"wander"}` swaps
the next tick to wander for 60 s.
- Chain is now: defend > eat > sleep > curriculum > idle.
- reflex.test.js: 11 new tests covering busy/disconnected,
defend/eat preemption, dispatch by id, unknown-skill fallback,
per-skill + wander-hint backoffs, onComplete updating backoff.
2. Pi escalation for ADDRESSED_BANTER with hard rate limit.
- bot.js: when generateReply returns {escalate:true}, spawn askPi
with bot state + last 5 lines from that speaker (redacted via
chatMemory). Reply capped at 200 chars, sent as one chat line.
- Rate cap: 6 calls/hour, 90 s min gap. Suppressed escalations
log once and silently drop.
3. Phase 4 substrate.
- runtime/locations.js: atomic JSON store
(state/<host>/locations.json) with setLocation / getLocation /
nearestLocation / removeLocation; 6 tests.
- runtime/base-site.js: scoreCurrentPosition(bot) + pure scoreSite
bundle (wood / stone / water / flatness / no-players /
no-foreign-builds, owned-blocks excluded from claim penalty);
6 tests.
- runtime/skills/choose-base.js: village.choose-base skill — scores
the current spot, writes locations.base if score ≥ 8, otherwise
returns code:"too_weak" with a wander recover hint.
- curriculum.js: new final milestone village.base-site fires
village.choose-base until a base location exists.
- bot.js: stamps snapshot.locations from listLocations() each tick
so the curriculum can read it without coupling to disk.
docs/runtime.md updated with three new sections.
npm test now 116/116.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
258 lines
9.4 KiB
JavaScript
258 lines
9.4 KiB
JavaScript
// Reflex layer: priority-ordered behaviours that decide what the bot does
|
|
// each tick. The LLM is NOT called here. If every reflex declines, the tick
|
|
// yields and we try again next interval. The bot.js layer tracks consecutive
|
|
// noops and escalates to Pi after a threshold (see ESCALATE_AFTER_NOOPS).
|
|
//
|
|
// Chain (top to bottom — first to dispatch wins):
|
|
//
|
|
// defend event-driven, hostile in melee or low HP + close
|
|
// eat event-driven, food bar low
|
|
// sleep event-driven, night without hostile in reach
|
|
// curriculum the new scheduler — reads snapshot.curriculum and dispatches
|
|
// via runtime/skills/runSkill. Replaces the old ad-hoc
|
|
// tech-tree + autonomous chop/wander branches.
|
|
// idle heartbeat logger
|
|
//
|
|
// Operator chat does NOT create tasks (Phase 0 pivot). TUI pause/stop is
|
|
// the only local override.
|
|
|
|
import { info, warn } from "./log.js";
|
|
import {
|
|
attackNearest,
|
|
fleeFrom,
|
|
eatBestFood,
|
|
sleepInBed,
|
|
wander,
|
|
} from "./actions.js";
|
|
import { runSkill, getSkill } from "./skills/index.js";
|
|
|
|
const REFLEX_LOG = "reflex";
|
|
|
|
// A reflex returns one of:
|
|
// { action: "noop" } — nothing to do
|
|
// { action: "dispatched", kind, label } — dispatched an async action
|
|
// { action: "completed", kind, detail } — fully sync, already done
|
|
// Reflexes must NEVER throw — they log and return noop on failure.
|
|
|
|
// ---- defend ----------------------------------------------------------------
|
|
|
|
function defendReflex(ctx) {
|
|
const s = ctx.snapshot;
|
|
if (!s.connected) return { action: "noop" };
|
|
if (!s.closestHostile) return { action: "noop" };
|
|
|
|
const dist = s.closestHostile.distance;
|
|
const lowHp = (s.health ?? 20) <= 8;
|
|
|
|
// Three regimes — tightened to avoid the "82 distant hostiles → constant
|
|
// flee" pathology observed at this spawn:
|
|
// - within 4m: melee attack
|
|
// - within 8m (and visibly hostile to us): flee
|
|
// - low-HP fallback: flee anything within 12m
|
|
// Anything beyond 8m with full HP is ignored regardless of how many
|
|
// hostiles the perceive snapshot enumerates.
|
|
if (dist <= 4) {
|
|
ctx.dispatch(
|
|
() => attackNearest(ctx.bot, s.closestHostile.name),
|
|
`attack ${s.closestHostile.name}`,
|
|
);
|
|
return { action: "dispatched", kind: "defend-attack", label: s.closestHostile.name };
|
|
}
|
|
const shouldFlee = (dist <= 8) || (lowHp && dist <= 12);
|
|
if (!shouldFlee) return { action: "noop" };
|
|
|
|
// Cooldown — if we just fled from this same mob type and it didn't work
|
|
// (timed out), don't immediately re-fire. Let other reflexes run.
|
|
const lastFlee = ctx.lastFleeAttempt;
|
|
if (lastFlee && lastFlee.name === s.closestHostile.name && Date.now() - lastFlee.ts < 60_000) {
|
|
return { action: "noop" };
|
|
}
|
|
ctx.lastFleeAttempt = { name: s.closestHostile.name, ts: Date.now() };
|
|
|
|
const fromEntity = Object.values(ctx.bot.entities).find(
|
|
(e) =>
|
|
e.name === s.closestHostile.name &&
|
|
e.position &&
|
|
Math.abs(e.position.distanceTo(ctx.bot.entity.position) - dist) < 1.5,
|
|
);
|
|
ctx.dispatch(
|
|
() => fleeFrom(ctx.bot, fromEntity, 16),
|
|
`flee from ${s.closestHostile.name}`,
|
|
);
|
|
return { action: "dispatched", kind: "defend-flee", label: s.closestHostile.name };
|
|
}
|
|
|
|
// ---- eat -------------------------------------------------------------------
|
|
|
|
function eatReflex(ctx) {
|
|
const s = ctx.snapshot;
|
|
if (!s.connected) return { action: "noop" };
|
|
if (s.food === undefined || s.food >= 16) return { action: "noop" };
|
|
// Don't eat if we just ate (the food bar refresh on the server has a
|
|
// small lag — re-firing within 5s would just fail bot.consume).
|
|
const since = Date.now() - (ctx.lastEatAt ?? 0);
|
|
if (since < 5000) return { action: "noop" };
|
|
|
|
ctx.dispatch(
|
|
() => eatBestFood(ctx.bot),
|
|
"eat",
|
|
{
|
|
onComplete: (res) => {
|
|
if (res.ok) ctx.lastEatAt = Date.now();
|
|
},
|
|
},
|
|
);
|
|
return { action: "dispatched", kind: "eat", label: `food=${s.food}` };
|
|
}
|
|
|
|
// ---- sleep -----------------------------------------------------------------
|
|
|
|
function sleepReflex(ctx) {
|
|
const s = ctx.snapshot;
|
|
if (!s.connected) return { action: "noop" };
|
|
if (s.isDay) return { action: "noop" };
|
|
if (s.closestHostile && s.closestHostile.distance < 8) return { action: "noop" }; // not safe
|
|
// Longer cooldown after a failure — if there's no bed nearby, retrying
|
|
// every 30s blocks autonomous behaviour without ever succeeding.
|
|
const since = Date.now() - (ctx.lastSleepAttemptAt ?? 0);
|
|
if (since < 5 * 60_000) return { action: "noop" };
|
|
|
|
ctx.lastSleepAttemptAt = Date.now();
|
|
ctx.dispatch(
|
|
() => sleepInBed(ctx.bot),
|
|
"sleep",
|
|
{
|
|
onComplete: (res) => {
|
|
if (res.ok) info(REFLEX_LOG, `sleep: success (${JSON.stringify(res.detail)})`);
|
|
else info(REFLEX_LOG, `sleep: declined (${res.detail})`);
|
|
},
|
|
},
|
|
);
|
|
return { action: "dispatched", kind: "sleep", label: "night" };
|
|
}
|
|
|
|
// ---- curriculum ------------------------------------------------------------
|
|
//
|
|
// The new scheduler. Reads snapshot.curriculum (produced by runtime/
|
|
// curriculum.js in bot.js's tick) and dispatches the suggested skill
|
|
// via runSkill. Falls back to wander when:
|
|
// * no curriculum result (curriculum says "everything done — late game"),
|
|
// * suggested skill is unknown to the registry,
|
|
// * recent recover() hint asked us to wander (e.g. no_target from
|
|
// gather.logs / gather.stone — same heuristic the old autonomous
|
|
// reflex used).
|
|
//
|
|
// Stone-tier locks: gather.stone needs a pickaxe; the skill's own
|
|
// preconditions will reject otherwise. When that happens we record a
|
|
// short backoff so we don't dispatch-and-fail every tick.
|
|
|
|
const CURRICULUM_COOLDOWN_MS = 4_000;
|
|
const SKILL_BACKOFF_MS = 60_000;
|
|
|
|
function curriculumReflex(ctx) {
|
|
const s = ctx.snapshot;
|
|
if (!s.connected) return { action: "noop" };
|
|
if (!ctx.bot) return { action: "noop" };
|
|
|
|
const since = Date.now() - (ctx.lastCurriculumAt ?? 0);
|
|
if (since < CURRICULUM_COOLDOWN_MS) return { action: "noop" };
|
|
|
|
const plan = s.curriculum?.plan;
|
|
const wanderHintUntil = ctx.skillBackoff?.["__wander_hint__"] ?? 0;
|
|
const wantWander = wanderHintUntil && Date.now() < wanderHintUntil;
|
|
|
|
// No skill plan from curriculum OR a recent skill asked us to wander —
|
|
// dispatch a wander fallback so we keep moving.
|
|
if (!plan?.skillId || wantWander) {
|
|
ctx.lastCurriculumAt = Date.now();
|
|
ctx.dispatch(() => wander(ctx.bot, 16), "wander", {});
|
|
return { action: "dispatched", kind: "curriculum-wander", label: "wander" };
|
|
}
|
|
|
|
const skillId = plan.skillId;
|
|
const skill = getSkill(skillId);
|
|
if (!skill) {
|
|
// Curriculum suggested a skill that isn't registered yet — fall back
|
|
// to wander rather than spinning. This is the right behaviour for
|
|
// future milestones we haven't wired (e.g. shelter blueprints).
|
|
ctx.lastCurriculumAt = Date.now();
|
|
ctx.dispatch(() => wander(ctx.bot, 16), "wander", {});
|
|
return { action: "dispatched", kind: "curriculum-wander", label: `wander (no skill ${skillId})` };
|
|
}
|
|
|
|
// Per-skill backoff: if this exact skill failed with a non-recoverable
|
|
// reason recently (missing_tool, missing_material, no_target) we give it
|
|
// breathing room rather than retrying every cooldown.
|
|
const backoffUntil = ctx.skillBackoff?.[skillId] ?? 0;
|
|
if (Date.now() < backoffUntil) return { action: "noop" };
|
|
|
|
ctx.lastCurriculumAt = Date.now();
|
|
ctx.dispatch(() => runSkill(skillId, ctx), skillId, {
|
|
onComplete: (res) => {
|
|
ctx.skillBackoff = ctx.skillBackoff ?? {};
|
|
if (res?.recovery?.hint === "wander") {
|
|
// Same fix the old autonomous reflex applied for "no reachable
|
|
// log" — switch to exploration for a minute.
|
|
ctx.skillBackoff["__wander_hint__"] = Date.now() + SKILL_BACKOFF_MS;
|
|
}
|
|
if (!res?.ok) {
|
|
// missing_tool / missing_material / no_target shouldn't be
|
|
// retried on the very next tick. Hold for SKILL_BACKOFF_MS.
|
|
const cooldownCodes = new Set(["missing_tool", "missing_material", "no_target", "no_food_source", "unsupported_version"]);
|
|
if (cooldownCodes.has(res?.code)) {
|
|
ctx.skillBackoff[skillId] = Date.now() + SKILL_BACKOFF_MS;
|
|
}
|
|
} else {
|
|
// Success clears the wander hint immediately.
|
|
ctx.skillBackoff["__wander_hint__"] = 0;
|
|
}
|
|
},
|
|
});
|
|
return { action: "dispatched", kind: "curriculum-skill", label: skillId };
|
|
}
|
|
|
|
// ---- idle ------------------------------------------------------------------
|
|
|
|
function idleReflex(ctx) {
|
|
const s = ctx.snapshot;
|
|
if (!s.connected) return { action: "noop" };
|
|
ctx.idleCounter = (ctx.idleCounter ?? 0) + 1;
|
|
if (ctx.idleCounter % 20 !== 0) return { action: "noop" };
|
|
info(
|
|
REFLEX_LOG,
|
|
`idle: hp=${s.health} food=${s.food} pos=${s.position?.x},${s.position?.y},${s.position?.z} time=${s.time}`,
|
|
);
|
|
return { action: "completed", kind: "idle-heartbeat" };
|
|
}
|
|
|
|
const REFLEXES = [
|
|
{ name: "defend", fn: defendReflex },
|
|
{ name: "eat", fn: eatReflex },
|
|
{ name: "sleep", fn: sleepReflex },
|
|
{ name: "curriculum", fn: curriculumReflex },
|
|
{ name: "idle", fn: idleReflex },
|
|
];
|
|
|
|
export function runTick(ctx) {
|
|
// Bot is in the middle of an async action — don't dispatch another.
|
|
if (ctx.busy) {
|
|
return { reflex: "busy", action: "skipped", label: ctx.currentActionLabel ?? "(?)" };
|
|
}
|
|
for (const reflex of REFLEXES) {
|
|
let outcome;
|
|
try {
|
|
outcome = reflex.fn(ctx);
|
|
} catch (e) {
|
|
warn(REFLEX_LOG, `reflex ${reflex.name} threw: ${e?.message ?? e}`);
|
|
continue;
|
|
}
|
|
if (!outcome || outcome.action === "noop") continue;
|
|
ctx.lastReflex = { name: reflex.name, label: outcome.label ?? outcome.kind, ts: Date.now() };
|
|
return { reflex: reflex.name, ...outcome };
|
|
}
|
|
return null;
|
|
}
|
|
|
|
// Exposed for tests.
|
|
export const _internal = { curriculumReflex, defendReflex, eatReflex, sleepReflex };
|