* docs(v0.3.1): PRD — LLM prompt cost optimization
Design-only commit; no runtime changes. Spec for the next patch iteration.
Goal: cut per-advise() input tokens from ~800 to ≤300, preserving the
LLM's ability to produce valid registered skill ids and useful rationale.
Five proposed changes ranked by impact:
P1 Compact registry format (saves ~350t/call) — group by namespace,
comma-list ids, drop human titles. Default mode for advisor;
verbose mode kept for postmortem/reflect.
P2 Need-scoped registry (~50t additional) — show LLM only skills
relevant to the active Maslow need + always-available safety
skills (survive.flee, pillar-up, recovery.tunnel-out, explore.*).
P3 Snapshot pruning (~50t) — drop weather/experience/dimension/biome/
players from the user prompt; the LLM doesn't consult them.
P4 Prompt caching probe — check if TimeWeb passes through
prompt_tokens_details.cached_tokens. If yes, restructure prefix
to maximize cache hits (cached input is ~10x cheaper at OpenAI).
P5 Per-trigger cost telemetry in scripts/list-improvements.js --stats:
avg_in / avg_out / cost_₽ / share% per trigger_reason, using
TIMEWEB_PRICE_IN_RUB_PER_M and TIMEWEB_PRICE_OUT_RUB_PER_M env.
Trigger: TimeWeb admin panel after first day of v0.3.0 live showed
34K tokens / day at low activity. At cap budget that projects to
~480₽/month (101₽/M in, 608₽/M out for gpt-5.4-mini). Manageable
but the savings are mostly free — repeated infra tokens, not signal.
All changes are additive; runtime behaviour stays the same. If the
LLM produces worse advice with the compact registry, flip back via a
single constant in fast-advisor.js.
Acceptance: re-run scripts/check-timeweb.js probe 3 — expect
tokens_in ≤ 300 (was ~800). Live for 1h, check --stats: avg_in ≤ 300
per trigger group. Existing 360 tests still green.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(v0.3.1): storyline — canonical Minecraft survival quest
The bot has been stuck in a loop for two days:
acquire-food (fail: no nearby food) → explore.far → pillar-up (fail) → repeat
Diagnosis: manifesto + LLM advisor both correctly identify "you need
food" but neither expresses *what concretely to do next*. Manifesto is
a priority ladder (need-detection), not a narrative arc.
This commit adds the missing narrative layer — an ordered list of
operational steps that mirror the vanilla Minecraft survival path:
1. orient_self — Понять где я
2. first_wood — Собрать 8 поленьев
3. crafting_basics — Сделать верстак и палки
4. first_tools — Деревянные орудия
5. first_food — Найти первую еду
6. shelter_minimal — Простой шелтер с кроватью
7. stone_tier — Каменные орудия
8. food_security — Запас еды на 16+
9. iron_age — Железо и печь
10. settle_base — Постоянная база
11. village_grow — Развивать деревню (ongoing)
Each step has:
- completed(snapshot) → bool — detects achievement from snapshot
- suggestSkill(snapshot) → { skillId, args? } — concrete next dispatch
- emergencyPause(snapshot) → bool — defers to manifesto L0 alive
emergencies (low HP near hostile, lava under foot, food = 0)
- narration_ru — chat-friendly Russian one-liner spoken on entry
Components:
- runtime/goal/storyline.js — 11-step canonical quest catalogue
- runtime/goal/state.js — pickCurrentStep(snapshot) walks the list,
returns first non-completed step + its suggestion. 3s cache.
Validates suggestSkill's skillId against the live registry.
- runtime/reflex.js — curriculumReflex dispatch priority is now:
1. manifesto (L0 alive emergencies always win)
2. storyline (concrete operational subgoal)
3. curriculum plan (legacy fallback)
Tests pass ctx.disableStoryline=true for isolation.
- runtime/bot.js — snapshot.storyStep populated each tick so
chatter/advisor/reflect observers see the same view.
- runtime/coach/fast-advisor.js — buildUserPrompt now embeds the
current step + its suggested skill, so LLM advice is anchored
("step 5 first_food, storyline wants survive.acquire-food, but
recent dispatches show it's failing — try explore.far + scout").
- runtime/coach/advisor-trigger.js — forwards ctx.storyStep into
advise() and logs step id at trigger time.
- runtime/coach/reflect.js — reflection prompt includes storyline
progress so 30-min self-assessment is anchored.
- runtime/persona/chatter.js — narrates step.narration_ru on
transition. Rate-limited via existing maybeNarrateRaw().
New operator CLI:
- scripts/show-story.js — fetches the live snapshot via IPC sock and
prints step progress with ✓/→/ markers, current skill, inventory.
Falls back to --plain catalogue view when bot offline.
Token cost impact: ~+30 input tokens per advise() call (one extra
line in user prompt). Trivial vs the value of grounding LLM advice
in a concrete narrative.
Operator usage:
node scripts/show-story.js # live progress + which step + why
node scripts/show-story.js --plain # static catalogue of all 11 steps
Tests: 376 green (was 360, +16 storyline tests).
Also in this branch (already committed): dev/v0.3.1/PRD.md —
LLM prompt cost optimization design doc.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(v0.3.1): storyline beats manifesto L1+ (only L0 alive emergencies override)
Found in live logs after the previous commit deployed:
storyline: step 1/11: orient_self → explore.wander
advisor-trigger: firing because wedged (planned=survive.acquire-food, ...)
Manifesto was still picking survive.acquire-food (L1 food) over the
storyline's orient_self → explore.wander. That's the wrong precedence —
storyline expresses a *concrete operational subgoal* and L1+ manifesto
needs are just "you'd benefit from food" priorities, not emergencies.
New dispatch precedence in curriculumReflex:
1. manifesto L0 (alive emergencies: lava, low-HP+hostile, food=0)
2. storyline (concrete narrative subgoal — beats L1+ manifesto)
3. manifesto L1+ (fallback when storyline has no concrete suggestion)
4. curriculum plan (legacy fallback)
This way the bot starts following the narrative arc even while
manifesto's L1 food is technically unsatisfied — orient_self runs to
completion before pursuing food explicitly. Storyline already handles
food as step 5 (first_food), so we're not skipping it.
Tests: 378 green (+2 priority-ordering tests):
- L0 manifesto emergency: upstream reflex (defend/modes) catches before
curriculum dispatch
- storyline beats manifesto when both have suggestions: well-fed bot
with logs → craft.planks (storyline crafting_basics), not gather.logs
(manifesto L2)
- updated "manifesto fallback" test to require disableStoryline=true
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(tui): fullscreen monitor-only TUI (opencode-style)
Replaces the old tui/tui.tsx hotkey-heavy dashboard with a read-only
observability screen. Operator actions live in scripts/* now —
TUI is for watching, not driving.
Layout (top to bottom, all auto-resizing to terminal):
1. Header — MC/IPC status, pos, HP, food, day/night, hostiles
2. Storyline — current step + 11-step quest map (✓/→/○)
3. Activity — last N skill dispatches (colour by outcome)
4. MC Chat — last N chat lines (cyan for bot, yellow for players)
5. Advisor — last N LLM recommendations (trigger + outcome + tokens)
6. Improvements — open requests from knowledge.improvement_requests
7. Footer — 24h token usage + cost in ₽ + q-to-quit
Data sources:
- IPC sock: snapshot frames, log frames, chat frames (push)
- SQLite knowledge.db: advisor_recommendations + improvement_requests
polled every 5s (pull)
Token cost displayed live using TIMEWEB_PRICE_IN_RUB_PER_M /
TIMEWEB_PRICE_OUT_RUB_PER_M env vars (defaults: 101 / 608 for
gpt-5.4-mini).
Switches:
- npm run tui → new monitor (this file)
- npm run tui:legacy → old action-driven tui/tui.tsx (kept for now)
Implementation notes:
- Uses ink + alternate-screen-buffer ANSI for proper "opencode-feel"
fullscreen behaviour; restores prior terminal contents on quit.
- Skips alt-screen and useInput when stdin/stdout isn't a TTY
(smoke tests, piped output) — both gracefully degrade.
- Stable React keys via per-event uid counter, avoids reconciler
duplicate-key warnings as logs/chat/dispatches stream in.
- Resize handled via 1s stdout-dimension poll, NOT direct
'resize' listener (which conflicts with ink's own listener and
triggers MaxListenersExceededWarning).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* ui(tui): compact 4-section monitor (was 6) — fits 1080p without zoom
Operator reported the TUI overflowed the screen unless terminal was
zoomed way out. The 11-step storyline list alone was eating ~13
rows, and each advisor/improvement entry took 2-3 rows. Now:
- Header + storyline collapsed into one panel (2 lines):
line 1: pepa · ●MC ●IPC · 1m50s · pepa_bot · (697,61,702) · HP 20 · food 5 · ☀ · ⚔60(creeper@58b)
line 2: story ▓▒░░░░░░░░░ 1/11 orient_self · Понять где я → explore.wander
The 11-step ladder is now a unicode progress bar (▓ done, ▒ current,
░ pending) — same info, fits in one row.
- Advisor entries: one line each instead of two.
✓ wedged_60s → survive.flee 802t 1900ms
(outcome mark / trigger / target skill / tokens / latency)
- Improvements entries: one line each instead of two.
#1 P2 ×3 Add craft.iron-pickaxe skill
Description dropped from the row — use `node scripts/list-improvements.js`
for full text.
- Sections: 4 (was 6).
[header+story] · [activity | chat] · [advisor | improvements] · [footer]
Tested on a typical 1080p terminal — fits comfortably without zoom.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(v0.3.1): real survival patterns — biome-aware scout, wedge-relocate, escape-pit-safe
Operator reported the bot wandered the same 50×50 patch for 2 hours
without making any progress toward food. Diagnosis showed three root
causes; this commit addresses all five open improvement_requests
the LLM (postmortem + tuner) flagged automatically.
Research basis (`Voyager`, `Plan4MC`, `GITM`, `Mindcraft`):
- Coverage / commit-to-cardinal exploration when local scan fails
- Biome-aware strategy switching using a static affordance table
- Wedge detector above the skill layer that triggers RELOCATE not
RETRY (per-skill stuck checks reset on re-entry — useless)
- Time-in-region bbox heuristic + need-duration AND skill-cycle gate
Concrete changes:
1. `runtime/goal/storyline.js`
- orient_self.completed: added timeout fallback (HP=full + session
>120s → done) so barren biomes don't block the bot on step 1.
Closes improvement #2 'Нет навыка оценки когда сменить район'.
- first_food.suggestSkill: now picks survive.scout-food (new) when
no passive mob is nearby; falls back to survive.acquire-food only
when something is in immediate range.
2. `runtime/biome-affordances.js` (new)
- Static table: 40+ biomes → {has_passive_mobs, has_trees,
has_water, has_crops, livable}.
- Unknown biomes return optimistic defaults to avoid regressions.
- Closes improvement #1 'Нет навыка целевого поиска еды по биому'.
3. `runtime/skills/scout-food.js` (new — survive.scout-food)
- Tiered strategy: biome check → scan 32 → scan 64 → commit a
cardinal for 200 blocks rescanning every 16. On cardinal
exhaustion, returns code:"exhausted" so the curriculum can
escalate to village.relocate.
- In barren biomes (desert/ocean/snowy_plains) the scan is
SKIPPED — bot walks straight toward the nearest neighbour
biome that affords passive mobs (8-direction biome probe at
radius 64).
4. `runtime/awareness/wedge-detector.js` (new)
- Rolling 10-min position bbox tracker. observe() called every
tick; isWedged() returns true when bbox<50 AND active need
unmet >5min AND skill cycles ≥3.
- markRelocationStarted() suppresses further wedge firings
until the bot has displaced ≥200b — prevents stack overflow
of relocate calls.
- Lives ABOVE the skill layer (in runtime/reflex.js), because
any per-skill stuck check resets on re-entry.
5. `runtime/skills/relocate.js` (new — village.relocate)
- 300-block walk in least-recently-used cardinal (per-incident
memory in ctx.recentRelocations).
- Re-paths every 32 blocks, soft-tolerates pathfinder failures
(3 consecutive throws → exit with code:"stuck_in_place").
- Closes improvement #2 + #4 ('low success rate trigger').
6. `runtime/skills/escape-pit-safe.js` (new — recovery.escape-pit-safe)
- Surveys 4 cardinals AND ceiling height before committing.
Picks the direction with most open blocks (≥3, no lava).
Falls through to pillar-up only if ceiling clear ≥4b. Returns
code:"no_strategy" if both blocked so curriculum can escalate
to relocate.
- Closes improvement #3 'Нет навыка для безопасного выхода'.
7. `runtime/reflex.js`
- Wedge detector wired before manifesto/storyline. If wedge.wedged
is true, dispatches village.relocate directly and returns —
bypasses every other branch.
- ctx.disableWedge flag for tests.
8. `runtime/coach/advisor-trigger.js`
- LLM provider outage backoff: 3 consecutive http_400 / timeout /
network_error → suppress advisor for 10 min. Today's TimeWeb
gpt-5.4-mini was 400'ing for an hour straight; we were spending
trigger budget on dead calls. Closes improvement implicit gap
in #5.
9. `runtime/bot.js`
- Tracks botSpawnedAt; snapshot._sessionMs exposed for storyline
orient_self timeout fallback.
Tests: 396 green (was 378, +18):
- runtime/biome-affordances.test.js — 8 tests
- runtime/awareness/wedge-detector.test.js — 9 tests
- runtime/goal/storyline.test.js — 1 new test (orient_self timeout)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(coach/trigger-tuner): crash after ~1h — runOnce is sync, not a Promise
The live bot died overnight with:
TypeError: runOnce(...).catch is not a function
at trigger-tuner.js:42 → [supervisor] child exited code=1
attach() wrapped the timer body as `runOnce().catch(...)` but
runOnce() returns a plain {ok, flagged, ...} object (pure SQL, no
await). The first tuner tick (60min after spawn) threw → killed the
whole bot process. Never surfaced before because the bot rarely ran
uninterrupted for a full hour during development.
Fix: guard the synchronous call with try/catch, matching how
persona/chatter.js already does its sync tick. (postmortem.drainOnce
and reflect.runOnce ARE async, so their .catch is correct — audited.)
Regression test added: captures the setInterval callback and invokes
it synchronously, asserting it does not throw.
Tests: 397 green.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(v0.3.1): mechanical food/stuck fixes — bot reaches the chicken now
The wedge wasn't only in the manifesto layer; several mechanical bugs
kept the bot in a dead random-walk:
- storyline / manifesto / curriculum: "local food" now means an edible
passive mob within <=32 blocks. A distant chicken or a cod no longer
fools the bot into dispatching acquire-food (which then fails on
no_path). Long-range food goes through scout-food instead.
- scout-food: partial approach to a target now counts as progress
(approached_target, e.g. moved:14); a blocked heading is NOT counted
as movement; added blind/tunnel fallback so it doesn't die when the
pathfinder can't route cleanly.
- acquire-food: on no_path it now also tries a blind/tunnel approach to
the animal; no_drop routes back into food scouting instead of giving
up.
- explore.far / relocate / flee: fewer false "done" results (micro-steps
no longer counted as success), more genuine escapes from stuck.
- scripts/show-story.js: live IPC now actually renders the current
storyline step.
Verification: scripts/lint-patch.js clean; npm test 404/404 green; bot
relaunched in tmux `pepa`. Live logs show real progress — bot switched
to survive.scout-food, approached the chicken (approached_target
moved:14), then reached survive.acquire-food: hunting chicken. Food
isn't fully closed yet but the remaining issue is concrete pickup/drop,
not dead random-walk.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(v0.3.1): sated bot stops chasing food + perf-leak + fuzzy improvement dedup
Third day of "bot just walks back and forth burning tokens". Root
causes were mechanical, not the manifesto:
1. SATED BOT CHASING FOOD (the big one)
Bot had food=17 (nearly full) but storyline first_food + manifesto
L1 required 2+ food ITEMS in inventory, so it looped scout-food /
acquire-food for hours instead of working. Now both treat a hunger
bar >= 14 (SATED_FOOD) as satisfied even with empty food inventory —
a full bot chops wood / makes tools and grabs food opportunistically,
only hard-pursuing food when actually hungry (< 14).
manifesto/needs.js foodDetect + goal/storyline.js first_food.completed.
2. perf_hooks MEMORY LEAK (overnight OOM suspect)
"MaxPerformanceEntryBufferExceededWarning: 1,000,001 measure entries".
mineflayer/pathfinder emit perf marks we never consume. Added a
60s reaper in bot.js (performance.clearMeasures/clearMarks). unref'd.
3. IMPROVEMENT QUEUE SELF-DUPLICATING
The LLM re-filed closed gaps with reworded titles (#5/#8/#9 were
dupes of implemented #1/#2/#3). Exact-title dedup missed them.
Replaced with token-set fuzzy match (isDuplicateTitle): jaccard>=0.75
OR >=3 shared meaningful tokens with jaccard>=0.5. Also: a re-filed
gap that's already implemented/rejected is NOT resurrected as a new
open row. Cleared all 5 open requests (now genuinely implemented).
Also confirmed (no change needed):
- canDig=true is a DELIBERATE codebase-wide choice ("without it the bot
gets permanently stuck", actions.js). The stale memory recommending
canDig=false is updated. ViaBackwards dig works partially (dug:1
moved:1.8 observed); false would trap the bot in every pit.
- scout-food already has blind/tunnel fallback + 12s step timeout
(operator's earlier edits) so trapped-pathfinder degrades instead of
hanging 30s.
Tests: 407 green (was 404). Updated needs/state/storyline tests for the
SATED_FOOD threshold; added fuzzy-dedup + tokenize/jaccard tests.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Yuriy Mayatnikov <mayatnikov@me.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
313 lines
11 KiB
JavaScript
313 lines
11 KiB
JavaScript
// Self-reflection loop. Every REFLECT_INTERVAL_MS (default 30 min) we ask
|
|
// Pi a meta-question: "Look at the last window of activity. Are you in a
|
|
// loop? Making progress? What should you do differently?"
|
|
//
|
|
// The answer is parsed into:
|
|
// - one short verdict ('progress' | 'loop' | 'recovering' | 'idle')
|
|
// - a paragraph of context (stored to state/<host>/reflections/<ts>.md)
|
|
// - optional new lessons (written to knowledge.lessons)
|
|
// - optional plan adjustment (queued, not auto-applied)
|
|
//
|
|
// This is the proactive counterpart to coach/postmortem (which is reactive
|
|
// — fires on death). Together they cover both "I just lost" and "I haven't
|
|
// gained anything in a while" failure modes.
|
|
|
|
import { existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs";
|
|
import { resolve } from "node:path";
|
|
|
|
import { isAvailable as knowledgeAvailable, record as recordLesson, createImprovementRequest } from "../knowledge/index.js";
|
|
import { isRegistered, skillRegistryPrompt } from "../skill-registry.js";
|
|
import { pickActiveNeed } from "../manifesto/state.js";
|
|
import { pickCurrentStep } from "../goal/state.js";
|
|
import { isAvailable as llmAvailable } from "../llm/provider.js";
|
|
import { askAnalytical } from "./llm-call.js";
|
|
import { info, warn } from "../log.js";
|
|
|
|
// Mode-name allow-list, mirrors postmortem.js (advice.js maps them to
|
|
// real skills at consult-time). Anything else is hallucination → dropped.
|
|
const KNOWN_MODE_NAMES = new Set([
|
|
"self_preservation", "night_shelter", "hunger", "shelter",
|
|
"flee", "sleep", "eat", "tunnel_out", "tunnel-out", "explore", "wander",
|
|
]);
|
|
function isLikelyModeName(s) {
|
|
if (!s || typeof s !== "string") return false;
|
|
return KNOWN_MODE_NAMES.has(s.toLowerCase().trim());
|
|
}
|
|
|
|
const DEFAULT_INTERVAL_MS = 30 * 60 * 1000;
|
|
const HOURLY_BUDGET = 2;
|
|
const HISTORY_TAIL_LINES = 80;
|
|
|
|
let _attached = null;
|
|
let _timer = null;
|
|
let _llmCallTimes = [];
|
|
|
|
export function attach({ bot, stateDir, getSnapshot, intervalMs = DEFAULT_INTERVAL_MS } = {}) {
|
|
if (_attached) {
|
|
warn("reflect", "attach called twice; ignoring");
|
|
return;
|
|
}
|
|
if (!stateDir || !getSnapshot) {
|
|
info("reflect", "attach: missing stateDir/getSnapshot — disabled");
|
|
return;
|
|
}
|
|
_attached = { bot, stateDir, getSnapshot };
|
|
_timer = setInterval(() => {
|
|
runOnce({ stateDir, getSnapshot }).catch((e) =>
|
|
warn("reflect", `tick err: ${e?.message ?? e}`),
|
|
);
|
|
}, intervalMs);
|
|
_timer.unref?.();
|
|
info("reflect", `attached; self-assess every ${Math.round(intervalMs / 60000)} min${llmAvailable() ? " (TimeWeb)" : " (LLM disabled — will skip)"}`);
|
|
}
|
|
|
|
export function detach() {
|
|
if (_timer) clearInterval(_timer);
|
|
_timer = null;
|
|
_attached = null;
|
|
}
|
|
|
|
export async function runOnce({ stateDir, getSnapshot, force = false, askAnalyticalFn = askAnalytical } = {}) {
|
|
const now = Date.now();
|
|
const hourAgo = now - 3600_000;
|
|
_llmCallTimes = _llmCallTimes.filter((t) => t > hourAgo);
|
|
if (!llmAvailable()) return { ok: false, reason: "llm not configured" };
|
|
if (!force && _llmCallTimes.length >= HOURLY_BUDGET) {
|
|
return { ok: false, reason: "budget exhausted", calls: _llmCallTimes.length };
|
|
}
|
|
|
|
const snap = getSnapshot();
|
|
const journal = readJournalTail(stateDir);
|
|
const scenarios = readScenarioTail(stateDir);
|
|
const diary = readDiaryTail(stateDir);
|
|
const plan = readPlan(stateDir);
|
|
const activeNeed = pickActiveNeed(snap);
|
|
const storyStep = pickCurrentStep(snap);
|
|
|
|
const { system, user } = buildPrompt({ snap, journal, scenarios, diary, plan, activeNeed, storyStep });
|
|
_llmCallTimes.push(now);
|
|
|
|
const parsed = await askAnalyticalFn({ system, user, json: true });
|
|
if (!parsed || typeof parsed !== "object") return { ok: false, reason: "no reply" };
|
|
const reply = JSON.stringify(parsed);
|
|
|
|
const path = writeReflection(stateDir, parsed, reply);
|
|
let rejectedPrefer = 0;
|
|
for (const l of asArray(parsed.lessons)) {
|
|
if (!l?.lesson) continue;
|
|
let preferSkill = l.prefer_skill ?? null;
|
|
if (preferSkill && !isRegistered(preferSkill) && !isLikelyModeName(preferSkill)) {
|
|
rejectedPrefer += 1;
|
|
preferSkill = null;
|
|
}
|
|
let avoidSkill = l.avoid_skill ?? null;
|
|
if (avoidSkill && !isRegistered(avoidSkill) && !isLikelyModeName(avoidSkill)) {
|
|
avoidSkill = null;
|
|
}
|
|
recordLesson({
|
|
text: l.lesson,
|
|
category: l.category ?? "self-improve",
|
|
triggerSkill: l.trigger_skill ?? null,
|
|
triggerHostile: l.trigger_hostile ?? null,
|
|
avoidSkill,
|
|
preferSkill,
|
|
confidence: clamp(Number(l.confidence) || 0.5, 0.1, 0.9),
|
|
source: "timeweb-reflect",
|
|
sourceRef: path,
|
|
});
|
|
}
|
|
if (rejectedPrefer > 0) {
|
|
warn("reflect", `dropped prefer_skill from ${rejectedPrefer} reflection lessons (not in registry)`);
|
|
}
|
|
|
|
// v0.3.0 — improvement requests from reflection. The LLM is asked
|
|
// to flag missing skills/features when self-reflection reveals a
|
|
// systemic gap (e.g. "I keep failing iron tools because there's no
|
|
// craft.iron-pickaxe skill").
|
|
let improvementsCount = 0;
|
|
for (const imp of asArray(parsed.improvements ?? [])) {
|
|
if (!imp?.title) continue;
|
|
createImprovementRequest({
|
|
source: "reflect",
|
|
category: imp.category ?? "skill",
|
|
title: String(imp.title).slice(0, 120),
|
|
description: imp.description ?? null,
|
|
context: { verdict: parsed.verdict, reflection_path: path },
|
|
priority: imp.priority ?? 3,
|
|
});
|
|
improvementsCount += 1;
|
|
}
|
|
|
|
info("reflect", `verdict=${parsed.verdict ?? "?"} ${parsed.summary?.slice(0, 80) ?? ""} lessons=${(parsed.lessons ?? []).length} improvements=${improvementsCount} (${path ?? "no file"})`);
|
|
return { ok: true, verdict: parsed.verdict, summary: parsed.summary, lessons: parsed.lessons ?? [], improvements: improvementsCount };
|
|
}
|
|
|
|
function readJournalTail(stateDir) {
|
|
const f = resolve(stateDir, "world-journal.jsonl");
|
|
if (!existsSync(f)) return [];
|
|
try {
|
|
return readFileSync(f, "utf8").split("\n").filter(Boolean).slice(-HISTORY_TAIL_LINES);
|
|
} catch { return []; }
|
|
}
|
|
|
|
function readScenarioTail(stateDir) {
|
|
const f = resolve(stateDir, "scenarios.jsonl");
|
|
if (!existsSync(f)) return [];
|
|
try {
|
|
return readFileSync(f, "utf8").split("\n").filter(Boolean).slice(-HISTORY_TAIL_LINES);
|
|
} catch { return []; }
|
|
}
|
|
|
|
function readDiaryTail(stateDir) {
|
|
const today = new Date().toISOString().slice(0, 10);
|
|
const f = resolve(stateDir, "diary", `${today}.md`);
|
|
if (!existsSync(f)) return "";
|
|
try {
|
|
const raw = readFileSync(f, "utf8");
|
|
return raw.split("\n").slice(-40).join("\n");
|
|
} catch { return ""; }
|
|
}
|
|
|
|
function readPlan(stateDir) {
|
|
const f = resolve(stateDir, "plan.md");
|
|
if (!existsSync(f)) return "";
|
|
try { return readFileSync(f, "utf8"); } catch { return ""; }
|
|
}
|
|
|
|
function buildPrompt({ snap, journal, scenarios, diary, plan, activeNeed, storyStep }) {
|
|
const pos = snap?.position;
|
|
const inv = snap?.inventory ? Object.keys(snap.inventory).slice(0, 12).join(", ") : "(empty)";
|
|
const lastResult = snap?.lastResult ? JSON.stringify(snap.lastResult).slice(0, 200) : "(none)";
|
|
const needLine = activeNeed
|
|
? `L${activeNeed.need.level} ${activeNeed.need.id} → ${activeNeed.skillId} (${activeNeed.need.title})`
|
|
: "(satisfied through L10 / no active need)";
|
|
const storyLine = storyStep
|
|
? `step ${storyStep.index + 1}/11 '${storyStep.step.id}' — ${storyStep.step.title}${storyStep.suggestion?.skillId ? ` (wants ${storyStep.suggestion.skillId})` : ""}${storyStep.emergency ? " [EMERGENCY PAUSE]" : ""}`
|
|
: "(no current step)";
|
|
|
|
const system = [
|
|
"You are pepa, an autonomous Minecraft survival bot, reflecting on your own progress.",
|
|
"Answer honestly: are you making progress, stuck in a loop, or facing a structural gap?",
|
|
"",
|
|
skillRegistryPrompt({ limit: 1800 }),
|
|
"",
|
|
"Reply with ONE JSON object (no markdown fences, no prose):",
|
|
'{',
|
|
' "verdict": "progress" | "loop" | "recovering" | "idle" | "emergency",',
|
|
' "summary": "<2-3 sentence honest assessment in Russian>",',
|
|
' "next_action": "<one-sentence directive>",',
|
|
' "lessons": [',
|
|
' { "lesson": "<≤30 words, generalised rule>",',
|
|
' "category": "combat|pathing|crafting|survival|self-improve",',
|
|
' "trigger_skill": "<skill id or null>",',
|
|
' "trigger_hostile": "<mob name or null>",',
|
|
' "avoid_skill": "<registered skill id or null>",',
|
|
' "prefer_skill": "<registered skill id or null>",',
|
|
' "confidence": 0.6 } ],',
|
|
' "improvements": [',
|
|
' { "title": "<≤80 chars: structural gap (e.g. \'No craft.iron-pickaxe skill\')>",',
|
|
' "description": "<concrete example showing why no registered skill helps>",',
|
|
' "category": "skill|tuning|perception|planning|social|other",',
|
|
' "priority": 1 } ]',
|
|
'}',
|
|
"",
|
|
"CRITICAL: avoid_skill and prefer_skill MUST be one of the registered ids above, or null.",
|
|
"Use 'improvements' ONLY when you identify a structural gap — a missing skill or feature that would unblock a class of situations. Skip it otherwise.",
|
|
].join("\n");
|
|
|
|
const user = [
|
|
"## Current state",
|
|
`- position: ${pos ? `(${Math.round(pos.x)}, ${Math.round(pos.y)}, ${Math.round(pos.z)})` : "?"}`,
|
|
`- hp: ${snap?.health ?? "?"} food: ${snap?.food ?? "?"} day: ${snap?.isDay ? "yes" : "no"}`,
|
|
`- runtimeState: ${snap?.runtimeState ?? "?"}`,
|
|
`- activeSkill: ${snap?.activeSkill ?? "(idle)"}`,
|
|
`- storylineStep: ${storyLine}`,
|
|
`- activeNeed (Maslow ladder L0-L10): ${needLine}`,
|
|
`- currentMilestone: ${snap?.currentMilestone ?? "?"}`,
|
|
`- noProgressReason: ${snap?.noProgressReason ?? "(none)"}`,
|
|
`- lastResult: ${lastResult}`,
|
|
`- inventory keys: ${inv}`,
|
|
"",
|
|
"## plan.md",
|
|
"```",
|
|
plan.slice(0, 1200),
|
|
"```",
|
|
"",
|
|
"## diary tail",
|
|
"```",
|
|
diary.slice(0, 1500),
|
|
"```",
|
|
"",
|
|
"## recent scenarios (tail)",
|
|
"```",
|
|
scenarios.slice(-30).join("\n"),
|
|
"```",
|
|
"",
|
|
"## world-journal tail",
|
|
"```",
|
|
journal.slice(-20).join("\n"),
|
|
"```",
|
|
].join("\n");
|
|
|
|
return { system, user };
|
|
}
|
|
|
|
function parseReply(text) {
|
|
if (!text) return null;
|
|
const cleaned = text.trim().replace(/^```(?:json)?/, "").replace(/```$/, "").trim();
|
|
try { return JSON.parse(cleaned); } catch {}
|
|
const m = cleaned.match(/\{[\s\S]*\}/);
|
|
if (!m) return null;
|
|
try { return JSON.parse(m[0]); } catch { return null; }
|
|
}
|
|
|
|
function writeReflection(stateDir, parsed, raw) {
|
|
try {
|
|
const dir = resolve(stateDir, "reflections");
|
|
mkdirSync(dir, { recursive: true });
|
|
const ts = new Date().toISOString().replace(/[:.]/g, "-");
|
|
const file = resolve(dir, `${ts}.md`);
|
|
const body = [
|
|
"---",
|
|
`verdict: ${parsed.verdict ?? "unknown"}`,
|
|
`ts: ${new Date().toISOString()}`,
|
|
"---",
|
|
"",
|
|
`## Summary`,
|
|
"",
|
|
parsed.summary ?? "(empty)",
|
|
"",
|
|
`## Next action`,
|
|
"",
|
|
parsed.next_action ?? "(none)",
|
|
"",
|
|
`## Lessons`,
|
|
"",
|
|
...(asArray(parsed.lessons).map((l, i) => [
|
|
`### ${i + 1}. ${l?.lesson ?? "(empty)"}`,
|
|
`category: ${l?.category ?? "?"}, confidence: ${l?.confidence ?? "?"}`,
|
|
l?.avoid_skill ? `avoid: ${l.avoid_skill}` : null,
|
|
l?.prefer_skill ? `prefer: ${l.prefer_skill}` : null,
|
|
"",
|
|
].filter(Boolean).join("\n"))),
|
|
"",
|
|
"## Raw response",
|
|
"",
|
|
"```",
|
|
raw.slice(0, 8000),
|
|
"```",
|
|
].join("\n");
|
|
writeFileSync(file, body);
|
|
return file;
|
|
} catch (e) {
|
|
warn("reflect", `writeReflection failed: ${e?.message ?? e}`);
|
|
return null;
|
|
}
|
|
}
|
|
|
|
function asArray(v) { return Array.isArray(v) ? v : v ? [v] : []; }
|
|
function clamp(v, lo, hi) { return Math.max(lo, Math.min(hi, v)); }
|
|
|
|
// Test exports
|
|
export const __testing = { buildPrompt, parseReply };
|