Closes a structural gap: the bot now actually REMEMBERS what it
discovered and what it tried. Two stores live under state/<host>/ and
are wired in automatically.
runtime/world-journal.js
- Append-only JSONL of discovered points (chopped, placed, base,
shelter, farm, dead_end). Indexed by 16-block spatial grid; O(neighbors)
nearest() lookups; 6 h age prune; 10k line ceiling with trim.
- leanestQuadrant({x,z}) reports the quadrant the bot has the FEWEST
markers in — used by explore.far to circle rather than retread.
- summary() exposed for the stuck-incident proposal body.
runtime/scenario-memory.js
- Sliding window of (skillId, situationHash, code, ok, detail) tuples.
- situationHash() is a coarse fingerprint (16x8x16 cell + day/night +
food/hp bucket + inv key set + closest hostile). So "same kind of
place + same kind of state" matches.
- shouldSkip({skillId, situation}) → true after ≥3 failures within 30
min UNLESS a more-recent success in the same situation un-locks it.
- recentTailFor() exposed for the stuck-incident body.
Wiring (runtime/bot.js):
- dispatchAction captures situationHash BEFORE the action runs and
records (skillId, situation, code, ok) after — failures are attributed
to the dispatch-time state, not the partial-effect state.
- worldDelta fields (choppedAt, minedAt, placedAt, baseAt, shelterAt,
plantedAt, harvestedAt, tilledAt) auto-flow into the journal.
- no_target + silent_dig_failure also write dead_end markers.
Scheduler / skills now consume memory:
- reflex.js curriculum reflex calls memory.shouldSkip — if the same
(skill, situation) failed 3+ times recently, auto-converts to a
wander hint so the bot leaves and tries elsewhere.
- explore.far calls journal.leanestQuadrant when multiple cardinal
directions are walkable and prefers the less-explored one.
- gather.logs walks to the nearest known "chopped" bucket within 96
blocks before falling through to findBlock — chunks with confirmed
trees are more likely to yield another.
stuck-incident body now includes journal byKind + last 12 scenario
entries so Pi can write a structural fix, not just a guard clause.
Architecturally: this is the foundation for "bot rewrites itself".
The proposals Pi now receives carry real signal about what was tried
and what's around, instead of a single snapshot in isolation.
10 new tests (world-journal × 5, scenario-memory × 5). npm test 134/134.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
142 lines
5.0 KiB
JavaScript
142 lines
5.0 KiB
JavaScript
// Stuck-incident detector. Today's failure-tracker in bot.js fires
|
|
// proposals on repeated *exception-class* failures (TypeError, timeout).
|
|
// This module fires on "no-progress" stagnation — the bot is healthy and
|
|
// the reflex loop hasn't crashed, but a single reason code (e.g.
|
|
// no_food_source, planner_empty) keeps coming back tick after tick.
|
|
//
|
|
// When the same reason persists past STUCK_THRESHOLD_MS we build a
|
|
// proposal body summarising the situation, including:
|
|
// - the no-progress reason
|
|
// - the active milestone + suggested skill
|
|
// - a slim snapshot
|
|
// - the last skill result
|
|
// - per-skill success/failure metrics (if available)
|
|
// - the allowed edit scope ("runtime/skills/<skill>.js" plus tests)
|
|
//
|
|
// The caller (bot.js) is responsible for actually writing the proposal —
|
|
// this module just produces the body string when the threshold trips.
|
|
|
|
const STUCK_THRESHOLD_MS = 5 * 60 * 1000;
|
|
const COOLDOWN_MS = 30 * 60 * 1000;
|
|
|
|
export function createStuckIncidentDetector({ thresholdMs = STUCK_THRESHOLD_MS, cooldownMs = COOLDOWN_MS } = {}) {
|
|
let currentReason = null;
|
|
let firstSeenAt = 0;
|
|
let lastFiredAt = 0;
|
|
|
|
function reset() {
|
|
currentReason = null;
|
|
firstSeenAt = 0;
|
|
}
|
|
|
|
// Returns { fire: true, body, kind, editScope } when an incident should
|
|
// be filed this tick; null otherwise.
|
|
function check({ snapshot, lastResult, metrics, journalSummary, scenarioTail, now = Date.now() }) {
|
|
const reason = snapshot?.noProgressReason ?? null;
|
|
if (!reason) {
|
|
reset();
|
|
return null;
|
|
}
|
|
if (reason !== currentReason) {
|
|
currentReason = reason;
|
|
firstSeenAt = now;
|
|
return null;
|
|
}
|
|
if (now - firstSeenAt < thresholdMs) return null;
|
|
if (lastFiredAt > 0 && now - lastFiredAt < cooldownMs) return null;
|
|
lastFiredAt = now;
|
|
|
|
const milestone = snapshot?.curriculum?.milestone;
|
|
const suggested = snapshot?.curriculum?.plan?.skillId;
|
|
const slim = {
|
|
runtimeState: snapshot.runtimeState,
|
|
noProgressReason: reason,
|
|
milestone: milestone?.title ?? null,
|
|
suggestedSkill: suggested ?? null,
|
|
position: snapshot.position,
|
|
health: snapshot.health,
|
|
food: snapshot.food,
|
|
isDay: snapshot.isDay,
|
|
inventoryCounts: Object.keys(snapshot.inventory ?? {}).length,
|
|
closestHostile: snapshot.closestHostile,
|
|
};
|
|
|
|
const editScope = suggested
|
|
? [`runtime/skills/${suggested.replace(/\./g, "-")}.js`, `runtime/skills/`]
|
|
: ["runtime/skills/", "runtime/"];
|
|
|
|
const metricsLine = metrics && Object.keys(metrics).length
|
|
? Object.entries(metrics)
|
|
.map(([id, m]) => `${id}: ok=${m.ok} fail=${m.fail}`)
|
|
.join(", ")
|
|
: "(none)";
|
|
|
|
const journalLine = journalSummary
|
|
? `byKind=${JSON.stringify(journalSummary.byKind ?? {})} buckets=${journalSummary.totalBuckets ?? 0}`
|
|
: "(no journal)";
|
|
|
|
const scenarioLines = Array.isArray(scenarioTail) && scenarioTail.length
|
|
? scenarioTail.map((e) =>
|
|
`- \`${e.skillId}\` ${e.ok ? "OK" : "FAIL"} code=${e.code ?? "?"} ${e.detail ? `(${e.detail.slice?.(0, 120) ?? ""})` : ""} situ=${e.situationHashShort ?? "?"}`,
|
|
).join("\n")
|
|
: "_(no scenario memory recorded yet)_";
|
|
|
|
const body = [
|
|
`# Stuck on \`${reason}\``,
|
|
"",
|
|
`The runtime has reported the same no-progress reason for >${Math.round(thresholdMs / 60000)} min without a productive action.`,
|
|
"",
|
|
"## Current state",
|
|
"",
|
|
"```json",
|
|
JSON.stringify(slim, null, 2),
|
|
"```",
|
|
"",
|
|
"## Last action result",
|
|
"",
|
|
lastResult
|
|
? `\`${lastResult.label}\` → ${lastResult.code ?? (lastResult.ok ? "ok" : "fail")}${lastResult.detail ? ` (${JSON.stringify(lastResult.detail).slice(0, 200)})` : ""}`
|
|
: "_(none recorded)_",
|
|
"",
|
|
"## Skill metrics so far (this process lifetime)",
|
|
"",
|
|
metricsLine,
|
|
"",
|
|
"## World journal (what we have discovered so far)",
|
|
"",
|
|
journalLine,
|
|
"",
|
|
"## Recent scenario memory (last attempts, what worked / failed in similar situations)",
|
|
"",
|
|
scenarioLines,
|
|
"",
|
|
"## Suggested fix",
|
|
"",
|
|
suggested
|
|
? `Improve \`${suggested}\` so the bot can clear the \`${reason}\` blocker, OR teach a NEW skill that handles this kind of situation if no single edit fixes it. Touch only the listed files (the test files under runtime/**/*.test.js are auto-allowed). Use the scenario-memory entries above to avoid re-introducing patterns that already failed.`
|
|
: `The curriculum has no suggested skill for this state. Either teach the curriculum a new milestone OR add a recovery skill that turns this reason code into a productive action. The scenario memory above shows what's been tried.`,
|
|
"",
|
|
"## Edit scope (auto-patch must obey this)",
|
|
"",
|
|
editScope.map((p) => `- ${p}`).join("\n"),
|
|
"",
|
|
"## Forbidden",
|
|
"",
|
|
"- Don't touch `.env`, `state/`, `extensions/`, `tui/` unless the scope above includes them.",
|
|
"- Don't add new npm dependencies.",
|
|
"- Don't change git history (no `--amend`, no `git reset --hard`).",
|
|
"",
|
|
].join("\n");
|
|
|
|
return {
|
|
fire: true,
|
|
kind: `stuck-${reason}`,
|
|
summary: `stuck on ${reason}${milestone ? ` (milestone: ${milestone.title})` : ""}`,
|
|
body,
|
|
editScope,
|
|
};
|
|
}
|
|
|
|
return { check, reset };
|
|
}
|