* 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>
295 lines
9.1 KiB
JavaScript
295 lines
9.1 KiB
JavaScript
// Skill substrate. A skill is a small, self-contained, composable unit of
|
|
// survival behaviour that the scheduler (today: reflex.js) can call with a
|
|
// uniform contract. The contract — required by every skill in this folder:
|
|
//
|
|
// {
|
|
// id: "namespace.action", // stable, machine-readable, e.g. "gather.logs"
|
|
// title: "Human label",
|
|
// timeoutMs: 45_000, // hard ceiling on execute()
|
|
// preconditions(ctx) -> { ok, code?, detail? }
|
|
// async execute(ctx, args) -> { ok, code, detail, worldDelta }
|
|
// validate?(ctx, result) -> boolean // optional gate after execute
|
|
// recover?(ctx, result) -> any | null // optional follow-up hint
|
|
// }
|
|
//
|
|
// The runSkill() wrapper enforces the timeout, normalises the result shape
|
|
// (so any caller can rely on the five required fields), runs validate(), and
|
|
// calls recover() on failure for the scheduler to consume.
|
|
//
|
|
// Skills are pure with respect to the runtime — they never read or write
|
|
// state-store directly; their `worldDelta` is the only way they communicate
|
|
// observed changes back to the scheduler, which then decides what to log.
|
|
|
|
import { info, warn } from "../log.js";
|
|
|
|
import { skill as chopLogs } from "./chop-logs.js";
|
|
import { skill as eat } from "./eat.js";
|
|
import { skill as wander } from "./wander.js";
|
|
import { skill as exploreFar } from "./explore-far.js";
|
|
import { skill as flee } from "./flee.js";
|
|
import { skill as sleep } from "./sleep.js";
|
|
import { skill as tunnelOut } from "./recovery-tunnel-out.js";
|
|
import { skill as pillarUp } from "./pillar-up.js";
|
|
import { skill as escapePitSafe } from "./escape-pit-safe.js";
|
|
import { skill as diagPhysics } from "./diagnose-physics.js";
|
|
import { skill as diagScan, matchSkill as diagMatch } from "./diagnose-scan.js";
|
|
import { skill as gatherStone } from "./gather-stone.js";
|
|
import { skill as gatherWool } from "./gather-wool.js";
|
|
import { skill as acquireFood } from "./acquire-food.js";
|
|
import { skill as scoutFood } from "./scout-food.js";
|
|
import { skill as relocate } from "./relocate.js";
|
|
import { skill as chooseBase } from "./choose-base.js";
|
|
import { skill as buildShelter } from "./build-shelter.js";
|
|
import { skill as placeChest } from "./place-chest.js";
|
|
import { skill as depositSurplus } from "./deposit-surplus.js";
|
|
import { skill as farmWheat } from "./farm-wheat.js";
|
|
import {
|
|
craftPlanksSkill,
|
|
craftSticksSkill,
|
|
craftWoodenAxeSkill,
|
|
craftWoodenPickaxeSkill,
|
|
craftWoodenSwordSkill,
|
|
craftStoneAxeSkill,
|
|
craftStonePickaxeSkill,
|
|
craftStoneSwordSkill,
|
|
craftFurnaceSkill,
|
|
craftChestSkill,
|
|
craftTorchSkill,
|
|
craftBedSkill,
|
|
} from "./craft.js";
|
|
|
|
const SKILLS = new Map();
|
|
|
|
function register(skill) {
|
|
if (!skill || typeof skill !== "object") throw new Error("skill: not an object");
|
|
if (!skill.id || typeof skill.id !== "string") throw new Error("skill: missing id");
|
|
if (typeof skill.execute !== "function") throw new Error(`skill ${skill.id}: missing execute`);
|
|
if (typeof skill.preconditions !== "function") throw new Error(`skill ${skill.id}: missing preconditions`);
|
|
if (SKILLS.has(skill.id)) throw new Error(`skill ${skill.id}: already registered`);
|
|
SKILLS.set(skill.id, skill);
|
|
}
|
|
|
|
register(chopLogs);
|
|
register(eat);
|
|
register(wander);
|
|
register(exploreFar);
|
|
register(flee);
|
|
register(sleep);
|
|
register(tunnelOut);
|
|
register(pillarUp);
|
|
register(escapePitSafe);
|
|
register(diagPhysics);
|
|
register(diagScan);
|
|
register(diagMatch);
|
|
register(gatherStone);
|
|
register(gatherWool);
|
|
register(acquireFood);
|
|
register(scoutFood);
|
|
register(relocate);
|
|
register(chooseBase);
|
|
register(buildShelter);
|
|
register(placeChest);
|
|
register(depositSurplus);
|
|
register(farmWheat);
|
|
register(craftPlanksSkill);
|
|
register(craftSticksSkill);
|
|
register(craftWoodenAxeSkill);
|
|
register(craftWoodenPickaxeSkill);
|
|
register(craftWoodenSwordSkill);
|
|
register(craftStoneAxeSkill);
|
|
register(craftStonePickaxeSkill);
|
|
register(craftStoneSwordSkill);
|
|
register(craftFurnaceSkill);
|
|
register(craftChestSkill);
|
|
register(craftTorchSkill);
|
|
register(craftBedSkill);
|
|
|
|
export function listSkills() {
|
|
return Array.from(SKILLS.values()).map((s) => ({
|
|
id: s.id,
|
|
title: s.title ?? s.id,
|
|
timeoutMs: s.timeoutMs ?? 30_000,
|
|
}));
|
|
}
|
|
|
|
export function getSkill(id) {
|
|
return SKILLS.get(id) ?? null;
|
|
}
|
|
|
|
// Stable failure codes the wrapper itself can emit. Skills may emit any
|
|
// additional codes — but these are the ones runSkill produces.
|
|
export const RUNNER_CODES = Object.freeze({
|
|
UNKNOWN_SKILL: "unknown_skill",
|
|
PRECONDITION_FAILED: "precondition_failed",
|
|
TIMEOUT: "timeout",
|
|
THREW: "threw",
|
|
VALIDATION_FAILED: "validation_failed",
|
|
PREEMPTED: "preempted",
|
|
DONE: "done",
|
|
});
|
|
|
|
function normaliseResult(res, fallbackCode) {
|
|
const ok = !!res?.ok;
|
|
return {
|
|
ok,
|
|
code: res?.code ?? (ok ? RUNNER_CODES.DONE : fallbackCode ?? "failed"),
|
|
detail: res?.detail ?? null,
|
|
worldDelta: res?.worldDelta ?? null,
|
|
};
|
|
}
|
|
|
|
function withTimeout(promise, ms, label) {
|
|
let timer;
|
|
const timeout = new Promise((_, reject) => {
|
|
timer = setTimeout(() => reject(new Error(`${label} timed out after ${ms}ms`)), ms);
|
|
});
|
|
return Promise.race([promise, timeout]).finally(() => clearTimeout(timer));
|
|
}
|
|
|
|
// v0.3.0-rc.3 — wrap execute() so that if ctx.abortSignal fires we
|
|
// stop awaiting (and surface code: "preempted"). The skill itself
|
|
// doesn't need to read the signal — the race below ensures runSkill
|
|
// returns control to the reflex within one microtask of abort(). The
|
|
// skill's own async work may continue in the background harmlessly,
|
|
// because the next dispatch will overwrite any shared state.
|
|
function raceWithAbort(promise, signal) {
|
|
if (!signal) return promise;
|
|
if (signal.aborted) {
|
|
return Promise.reject(Object.assign(new Error("preempted"), { _preempted: true }));
|
|
}
|
|
return new Promise((resolve, reject) => {
|
|
let settled = false;
|
|
const onAbort = () => {
|
|
if (settled) return;
|
|
settled = true;
|
|
reject(Object.assign(new Error("preempted"), { _preempted: true }));
|
|
};
|
|
signal.addEventListener("abort", onAbort, { once: true });
|
|
promise.then(
|
|
(v) => {
|
|
if (settled) return;
|
|
settled = true;
|
|
signal.removeEventListener?.("abort", onAbort);
|
|
resolve(v);
|
|
},
|
|
(e) => {
|
|
if (settled) return;
|
|
settled = true;
|
|
signal.removeEventListener?.("abort", onAbort);
|
|
reject(e);
|
|
},
|
|
);
|
|
});
|
|
}
|
|
|
|
// Drive one skill through its full lifecycle. The caller (typically reflex.js
|
|
// or, eventually, a higher-level scheduler) decides when to invoke; runSkill
|
|
// only owns the contract enforcement.
|
|
export async function runSkill(id, ctx, args = {}) {
|
|
const skill = SKILLS.get(id);
|
|
if (!skill) {
|
|
warn("skill", `unknown skill ${id}`);
|
|
return { ok: false, code: RUNNER_CODES.UNKNOWN_SKILL, detail: id, worldDelta: null };
|
|
}
|
|
|
|
let pre;
|
|
try {
|
|
pre = skill.preconditions(ctx, args) ?? { ok: true };
|
|
} catch (e) {
|
|
return {
|
|
ok: false,
|
|
code: RUNNER_CODES.PRECONDITION_FAILED,
|
|
detail: `preconditions threw: ${e.message}`,
|
|
worldDelta: null,
|
|
};
|
|
}
|
|
if (!pre.ok) {
|
|
const result = {
|
|
ok: false,
|
|
code: pre.code ?? RUNNER_CODES.PRECONDITION_FAILED,
|
|
detail: pre.detail ?? "preconditions failed",
|
|
worldDelta: null,
|
|
};
|
|
if (typeof skill.recover === "function") {
|
|
try {
|
|
result.recovery = skill.recover(ctx, result) ?? null;
|
|
} catch (e) {
|
|
warn("skill", `${id}.recover threw: ${e.message}`);
|
|
}
|
|
}
|
|
return result;
|
|
}
|
|
|
|
const timeoutMs = skill.timeoutMs ?? 30_000;
|
|
let raw;
|
|
try {
|
|
raw = await withTimeout(
|
|
raceWithAbort(skill.execute(ctx, args), ctx?.abortSignal),
|
|
timeoutMs,
|
|
`skill(${id})`,
|
|
);
|
|
} catch (e) {
|
|
const isTimeout = /timed out after/.test(e.message);
|
|
const isPreempted = e?._preempted === true;
|
|
const result = {
|
|
ok: false,
|
|
code: isPreempted
|
|
? RUNNER_CODES.PREEMPTED
|
|
: isTimeout ? RUNNER_CODES.TIMEOUT : RUNNER_CODES.THREW,
|
|
detail: e.message,
|
|
worldDelta: null,
|
|
};
|
|
if (typeof skill.recover === "function") {
|
|
try {
|
|
result.recovery = skill.recover(ctx, result) ?? null;
|
|
} catch (recoverErr) {
|
|
warn("skill", `${id}.recover threw: ${recoverErr.message}`);
|
|
}
|
|
}
|
|
return result;
|
|
}
|
|
|
|
const result = normaliseResult(raw);
|
|
if (result.ok && typeof skill.validate === "function") {
|
|
let valid;
|
|
try {
|
|
valid = skill.validate(ctx, result);
|
|
} catch (e) {
|
|
warn("skill", `${id}.validate threw: ${e.message}`);
|
|
valid = false;
|
|
}
|
|
if (!valid) {
|
|
const failed = {
|
|
ok: false,
|
|
code: RUNNER_CODES.VALIDATION_FAILED,
|
|
detail: result.detail,
|
|
worldDelta: result.worldDelta,
|
|
};
|
|
if (typeof skill.recover === "function") {
|
|
try {
|
|
failed.recovery = skill.recover(ctx, failed) ?? null;
|
|
} catch (e) {
|
|
warn("skill", `${id}.recover threw: ${e.message}`);
|
|
}
|
|
}
|
|
return failed;
|
|
}
|
|
}
|
|
if (!result.ok && typeof skill.recover === "function") {
|
|
try {
|
|
result.recovery = skill.recover(ctx, result) ?? null;
|
|
} catch (e) {
|
|
warn("skill", `${id}.recover threw: ${e.message}`);
|
|
}
|
|
}
|
|
info("skill", `${id} → ${result.code}${result.detail ? ` (${JSON.stringify(result.detail).slice(0, 80)})` : ""}`);
|
|
return result;
|
|
}
|
|
|
|
// For tests: lets a unit test register a synthetic skill without touching
|
|
// the production registry. Returns a teardown function.
|
|
export function _registerForTest(skill) {
|
|
register(skill);
|
|
return () => SKILLS.delete(skill.id);
|
|
}
|