Files
pepa-pi-bot/runtime/reflex.test.js
T
15b6c11002 v0.3.1: survival behaviour overhaul — storyline, biome-aware scout, wedge-relocate, food/perf fixes, monitor TUI (#28)
* 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>
2026-05-28 09:43:57 +03:00

550 lines
16 KiB
JavaScript

// Tests for the new curriculum-driven scheduler in runtime/reflex.js.
// We exercise runTick with synthetic snapshots + a recording ctx so we can
// assert which reflex fires and what gets dispatched.
import { test } from "node:test";
import assert from "node:assert/strict";
import { runTick } from "./reflex.js";
function vec(x, y, z) {
return {
x,
y,
z,
distanceTo(other) {
return Math.hypot(this.x - other.x, this.y - other.y, this.z - other.z);
},
offset(dx, dy, dz) {
return vec(this.x + dx, this.y + dy, this.z + dz);
},
};
}
function makeCombatBot({ removeOnAttack = false } = {}) {
return {
attacks: 0,
entity: { position: vec(0, 64, 0) },
entities: {
zombie1: { name: "zombie", height: 1.8, position: vec(3, 64, 0) },
},
inventory: { items: () => [] },
lookAt: async () => {},
attack() {
this.attacks++;
if (removeOnAttack) delete this.entities.zombie1;
},
};
}
function makeCtx({
snapshot,
busy = false,
bot = { entities: {}, entity: { position: { x: 0, y: 64, z: 0 } } },
skillBackoff,
lastEatAt = 0,
lastSleepAttemptAt = 0,
lastCurriculumAt = 0,
metrics,
disableManifesto = true, // curriculum branch tests don't construct
// full snapshots; manifesto is exercised by
// runtime/manifesto/state.test.js separately.
disableAdvisor = true, // advisor-trigger fires real async LLM calls,
// tested directly in advisor-trigger.test.js.
disableStoryline = true, // storyline tested in goal/storyline.test.js
disableWedge = true, // wedge tested in awareness/wedge-detector.test.js
} = {}) {
const dispatches = [];
const ctx = {
bot,
snapshot,
busy,
currentActionLabel: null,
lastEatAt,
lastSleepAttemptAt,
lastCurriculumAt,
skillBackoff,
metrics,
disableManifesto,
disableAdvisor,
disableStoryline,
disableWedge,
dispatch(fn, label, opts = {}) {
dispatches.push({ fn, label, opts });
},
};
return { ctx, dispatches };
}
test("busy ctx returns skipped without dispatching", () => {
const { ctx, dispatches } = makeCtx({
snapshot: { connected: true, curriculum: { plan: { skillId: "gather.logs" } } },
busy: true,
currentActionLabel: "chopping",
});
const out = runTick(ctx);
assert.equal(out.reflex, "busy");
assert.equal(out.action, "skipped");
assert.equal(dispatches.length, 0);
});
test("disconnected snapshot → no dispatch", () => {
const { ctx, dispatches } = makeCtx({ snapshot: { connected: false } });
const out = runTick(ctx);
assert.equal(out, null);
assert.equal(dispatches.length, 0);
});
test("mode hit dispatches the returned skill immediately", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 4,
food: 10,
hasFood: true,
inventory: { bread: 1 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "mode:self_preservation");
assert.equal(out.action, "dispatched");
assert.equal(dispatches[0].label, "survive.eat");
});
test("defend wins over curriculum when hostile in melee", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
closestHostile: { name: "zombie", distance: 3 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "defend");
assert.match(dispatches[0].label, /attack zombie/);
});
test("defend attack does not report success while hostile remains nearby", async () => {
const bot = makeCombatBot();
const { ctx, dispatches } = makeCtx({
bot,
snapshot: {
connected: true,
health: 20,
closestHostile: { name: "zombie", distance: 3 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
ctx.defendAttackMaxSwings = 2;
ctx.defendAttackSettleMs = 0;
const out = runTick(ctx);
assert.equal(out.reflex, "defend");
const res = await dispatches[0].fn();
assert.equal(res.ok, false);
assert.equal(res.code, "hostile_still_near");
assert.equal(bot.attacks, 2);
});
test("defend flees after a verified attack leaves hostile in reach", () => {
const bot = makeCombatBot();
const { ctx, dispatches } = makeCtx({
bot,
snapshot: {
connected: true,
health: 20,
closestHostile: { name: "zombie", distance: 3 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const first = runTick(ctx);
assert.equal(first.reflex, "defend");
dispatches[0].opts.onComplete({ ok: false, code: "hostile_still_near" });
const second = runTick(ctx);
assert.equal(second.reflex, "defend");
assert.equal(second.kind, "defend-flee");
assert.equal(dispatches[1].label, "flee from zombie");
});
test("defend flees after repeated attack successes still leave hostile in reach", () => {
const bot = makeCombatBot();
const { ctx, dispatches } = makeCtx({
bot,
snapshot: {
connected: true,
health: 20,
closestHostile: { name: "zombie", distance: 3 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const first = runTick(ctx);
assert.equal(first.kind, "defend-attack");
dispatches[0].opts.onComplete({ ok: true, code: "done" });
const second = runTick(ctx);
assert.equal(second.kind, "defend-attack");
dispatches[1].opts.onComplete({ ok: true, code: "done" });
const third = runTick(ctx);
assert.equal(third.reflex, "defend");
assert.equal(third.kind, "defend-flee");
assert.equal(dispatches[2].label, "flee from zombie");
});
test("eat wins over curriculum when food low and bot has food in inventory", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 10,
// 2026-05-26: eat reflex now requires actual food in inventory
// to avoid the eat-spam loop that fired every tick on empty
// inventory.
inventory: { bread: 1 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "eat");
assert.equal(dispatches[0].label, "eat");
});
test("eat reflex does NOT dispatch when no food in inventory (no spam)", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 10,
inventory: { dirt: 1 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
// Falls through to curriculum.
assert.equal(out.reflex, "curriculum");
});
test("curriculum dispatches suggested skill by id", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(dispatches[0].label, "gather.logs");
assert.ok(typeof dispatches[0].opts.onComplete === "function");
});
test("manifesto: hungry bot with no visible food drives survive.scout-food (manifesto fallback when storyline disabled)", () => {
const { ctx, dispatches } = makeCtx({
disableManifesto: false,
disableStoryline: true,
snapshot: {
connected: true,
health: 20,
food: 12,
hasFood: false,
inventory: {}, // no food, no tools
equipment: {},
nearbyBlocks: {},
hazards: { footBlock: "grass_block", belowBlock: "dirt", headBlock: "air" },
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(dispatches[0].label, "survive.scout-food", "manifesto L1 food took over");
assert.equal(ctx.activeNeed?.need?.id, "food");
});
test("L0 manifesto emergency: defend/modes layer catches the threat BEFORE curriculum", () => {
// HP=4 + creeper@3m fires `modes` (self_preservation) or defendReflex
// before curriculum even runs — which is the right outcome: alive
// emergencies don't reach the storyline/manifesto branch at all.
const { ctx, dispatches } = makeCtx({
disableManifesto: false,
disableStoryline: false,
bot: { entities: { z1: { name: "creeper", height: 1.7, position: { x: 3, y: 64, z: 0, distanceTo: () => 3 } } }, entity: { position: { x: 0, y: 64, z: 0 } } },
snapshot: {
connected: true,
health: 4,
food: 12,
hasFood: false,
inventory: { oak_log: 10 },
equipment: {},
nearbyBlocks: { logs: 4 },
hazards: { footBlock: "grass_block", belowBlock: "dirt", headBlock: "air" },
closestHostile: { name: "creeper", distance: 3 },
threats: [{ name: "creeper", distance: 3, position: { x: 3, y: 64, z: 0 } }],
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.notEqual(out?.kind, "curriculum-skill", "an upstream reflex caught the emergency before curriculum");
});
test("storyline beats manifesto L1+ when both have suggestions", () => {
// Snapshot: well-fed (food=20 + 8 bread → manifesto L1 satisfied, L2
// tools_wood unmet) AND storyline orient_self complete (HP=20, blocks
// visible). Storyline should drive a wood-tier crafting step, not
// manifesto's gather.logs (which would also be valid but less concrete).
const { ctx, dispatches } = makeCtx({
disableManifesto: false,
disableStoryline: false,
snapshot: {
connected: true,
health: 20,
food: 20,
hasFood: true,
inventory: { bread: 8, oak_log: 10 }, // logs done, no planks
equipment: {},
nearbyBlocks: { logs: 3 },
hazards: { footBlock: "grass_block", belowBlock: "dirt", headBlock: "air" },
isDay: true,
_sessionMs: 60_000,
curriculum: { plan: { skillId: "explore.far" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
// Storyline step crafting_basics suggests craft.planks (10 logs, no planks yet).
assert.equal(dispatches[0].label, "craft.planks");
assert.equal(ctx.storyStep?.step?.id, "crafting_basics");
});
test("manifesto: well-fed bot with all wood tools defers to curriculum plan", () => {
const { ctx, dispatches } = makeCtx({
disableManifesto: false,
snapshot: {
connected: true,
health: 20,
food: 20,
hasFood: true,
inventory: {
bread: 8,
wooden_pickaxe: 1, wooden_axe: 1, wooden_sword: 1,
white_bed: 1,
},
equipment: {},
nearbyBlocks: { beds: 1 },
hazards: { footBlock: "grass_block", belowBlock: "dirt", headBlock: "air" },
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
// L4 tools_stone unmet → gather.stone takes precedence even if curriculum says logs
assert.equal(dispatches[0].label, "gather.stone");
assert.equal(ctx.activeNeed?.need?.id, "tools_stone");
});
test("curriculum falls back to wander when no plan", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: null,
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(dispatches[0].label, "wander");
});
test("curriculum falls back to wander when skill id is unknown", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "shelter.assemble" } }, // not registered yet
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.match(dispatches[0].label, /^wander/);
});
test("curriculum honours per-skill backoff", () => {
const future = Date.now() + 30_000;
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.stone" } },
},
skillBackoff: { "gather.stone": future },
});
const out = runTick(ctx);
// Backoff blocks the curriculum reflex; idle still won't fire on this
// tick (idleCounter not at the 20-tick mark) so runTick yields.
assert.equal(out, null);
assert.equal(dispatches.length, 0);
});
test("wander-hint backoff swaps skill for wander on the next tick", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
skillBackoff: { __wander_hint__: Date.now() + 30_000 },
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(dispatches[0].label, "wander");
});
test("recent repeated skill timeouts trigger metric recovery", () => {
const now = Date.now();
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
metrics: {
snapshot: () => ({
"gather.logs": { ok: 0, fail: 3, lastTs: now, lastCode: "timeout" },
}),
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(out.kind, "curriculum-metric-recovery");
assert.equal(dispatches[0].label, "explore.far");
assert.ok((ctx.skillBackoff?.["gather.logs"] ?? 0) > Date.now());
});
test("recent movement timeouts trigger tunnel recovery", () => {
const now = Date.now();
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
metrics: {
snapshot: () => ({
"explore.far": { ok: 0, fail: 1, lastTs: now, lastCode: "timeout" },
}),
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(out.kind, "curriculum-metric-recovery");
assert.equal(dispatches[0].label, "recovery.tunnel-out");
});
test("successful tunnel recovery clears movement-timeout trigger", () => {
const now = Date.now();
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
metrics: {
snapshot: () => ({
"explore.far": { ok: 0, fail: 1, lastTs: now - 5_000, lastCode: "timeout" },
"recovery.tunnel-out": { ok: 1, fail: 0, lastTs: now, lastCode: "done" },
}),
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(out.kind, "curriculum-skill");
assert.equal(dispatches[0].label, "gather.logs");
});
test("onComplete sets wander hint when skill recovery says so", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
runTick(ctx);
const cb = dispatches[0].opts.onComplete;
cb({ ok: false, code: "no_target", recovery: { hint: "wander" } });
assert.ok((ctx.skillBackoff?.__wander_hint__ ?? 0) > Date.now());
});
test("onComplete clears wander hint on success", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
skillBackoff: { __wander_hint__: Date.now() + 30_000 },
});
// With wander hint active, first tick will choose wander, not gather.logs.
runTick(ctx);
// Simulate the wander completing and clearing the hint manually since
// wander is dispatched via actions.js directly (no recover hint).
ctx.skillBackoff.__wander_hint__ = 0;
// Next tick — past the curriculum cooldown.
ctx.lastCurriculumAt = 0;
const { ctx: ctx2, dispatches: dispatches2 } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
runTick(ctx2);
dispatches2[0].opts.onComplete({ ok: true, code: "done" });
assert.equal(ctx2.skillBackoff.__wander_hint__, 0);
});
test("onComplete sets per-skill backoff on cooldown-class failures", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.stone" } },
},
});
runTick(ctx);
const cb = dispatches[0].opts.onComplete;
cb({ ok: false, code: "missing_tool", detail: "no pickaxe" });
assert.ok((ctx.skillBackoff?.["gather.stone"] ?? 0) > Date.now());
});