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>
This commit is contained in:
@@ -30,6 +30,7 @@ import { tickAdvisor, consumeFreshRecommendation } from "./coach/advisor-trigger
|
||||
import { markRecommendationApplied, markRecommendationOutcome } from "./knowledge/index.js";
|
||||
import { pickActiveNeed } from "./manifesto/state.js";
|
||||
import { pickCurrentStep } from "./goal/state.js";
|
||||
import { observe as observeWedge, isWedged } from "./awareness/wedge-detector.js";
|
||||
import { situationHash } from "./scenario-memory.js";
|
||||
import { tickModes } from "./modes.js";
|
||||
|
||||
@@ -459,6 +460,29 @@ function curriculumReflex(ctx) {
|
||||
}
|
||||
const manifestoSkillId = activeNeed?.skillId ?? null;
|
||||
|
||||
// v0.3.1 — wedge detector. Feeds position into rolling-bbox tracker.
|
||||
// When bot has been stuck in a <50-block bbox for 10 minutes with
|
||||
// the same need cycling its skills, returns wedged=true and we
|
||||
// short-circuit to village.relocate which walks 300 blocks in a
|
||||
// fresh cardinal. Tests pass ctx.disableWedge=true to skip.
|
||||
if (!ctx.disableWedge && s.position) {
|
||||
observeWedge({
|
||||
x: s.position.x, z: s.position.z,
|
||||
activeNeedId: activeNeed?.need?.id ?? null,
|
||||
recentSkillIds: ctx.recentSkillIds ?? [],
|
||||
});
|
||||
const wedge = isWedged({
|
||||
activeNeedId: activeNeed?.need?.id ?? null,
|
||||
recentSkillIds: ctx.recentSkillIds ?? [],
|
||||
});
|
||||
if (wedge.wedged) {
|
||||
ctx.lastCurriculumAt = Date.now();
|
||||
info(REFLEX_LOG, `wedged: bbox=${Math.round(wedge.bboxDim)}b need=${activeNeed?.need?.id} for ${Math.round(wedge.needAgeMs / 1000)}s → village.relocate`);
|
||||
ctx.dispatch(() => runSkill("village.relocate", ctx), "village.relocate", {});
|
||||
return { action: "dispatched", kind: "wedge-relocate", label: "village.relocate" };
|
||||
}
|
||||
}
|
||||
|
||||
// v0.3.1 — storyline: the canonical Minecraft survival quest. Gives
|
||||
// the bot a concrete, narratable next-action ("collect 8 logs",
|
||||
// "place crafting table"). Storyline yields to manifesto on L0
|
||||
|
||||
Reference in New Issue
Block a user