21462dfdb1e82d704302b31596dfdaa1510ed5e1
8
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
  mayatnikovandClaude Opus 4.7
|
21462dfdb1 |
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> |
||
|
mayatnikovandClaude Opus 4.7
|
7f545723b5 |
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>
|
||
|
|
7d96e44804 |
v0.3.0: Maslow + Awareness — self-learning bot with needs ladder, event-driven reflex, and TimeWeb fast advisor (#27)
* v0.3.0-rc.1: live skill registry + fast advisor scaffold
Roots out the v0.2.x failure mode: Pi-extracted lessons routinely named
hallucinated skill ids (relocate.surface, choose.safe.surface,
survive.shelter, gather.visible_log, …). All 47 Pi-lessons in the live DB
had applied_count=0 because normalisePreferSkill couldn't find them.
Fix:
1. runtime/skill-registry.js — single source of truth derived from
skills/index.js. Exports listSkillIds, isRegistered, and a
prompt-ready block (skillRegistryPrompt) grouped by namespace.
2. Pi prompts (coach/postmortem, coach/reflect) embed the live registry
with a "USE ONLY THESE, never invent" instruction. Lessons are
filtered at write-time too — anything not in the registry and not a
known mode name gets dropped.
3. coach/advice.js — normalisePreferSkill now returns null for unknown
ids, hardening consult() against any hallucinations that slip
through. Warn-logged for visibility.
Also lays the LLM substrate for the rest of v0.3.0:
- runtime/llm/provider.js — OpenAI-compatible chat client. Configured
via PEPA_FAST_LLM_{BASE_URL,API_KEY,MODEL,TIMEOUT_MS}. Safe no-op
unless API_KEY is set. Supports JSON-mode.
- runtime/coach/fast-advisor.js — tactical advisor tier (scaffold).
Exposes advise() that asks the fast LLM what to do RIGHT NOW when
the reflex is wedged/stuck. Rejects hallucinated skill ids using the
registry. Rate-limited 6/h, 30s cooldown. Not auto-triggered yet —
wired into reflex in rc.3 (awareness layer).
Tests: 279 green (+24 vs rc.3): 5 registry, 9 provider, 10 advisor.
See dev/v0.3.0/PLAN.md for the full iteration design (manifesto needs
ladder, event-driven awareness, skill pre-emption) and STATUS.md for
shipped/pending tracking.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* v0.3.0-rc.2: manifesto / needs ladder L0-L10
Adds an explicit hierarchical needs catalogue that the reflex consults
on every tick. The bot now pursues tangible intermediate goals (food,
wood tools, shelter, stone tools, ...) instead of inheriting whatever
the curriculum thought was "next".
Ladder:
L0 alive HP>5, food>0, not in lava, not panic-near hostile
L1 food ≥6 food items in inventory (or sated + any food)
L2 tools_wood wooden_pickaxe + wooden_axe + wooden_sword
L3 shelter_basic bed placed nearby or in inventory
L4 tools_stone stone-tier triplet
L5 armor_basic any chestplate (pursue=null until craft.leather-*
lands; ladder gracefully skips)
L6 food_security ≥16 food items
L7 tools_iron iron-tier triplet (pursue=gather.stone for now)
L8 armor_iron iron chestplate (pursue=null for now)
L9 village_seed bed + chest in nearby blocks
L10 village_full never detected, falls through to curriculum
Each need has detect(snapshot) → bool and pursue(snapshot) →
{skillId, args} | null. The ladder picks the LOWEST unsatisfied
pursuable need. Needs whose pursue is null get recorded as
blockedNeeds and the walk continues — no stalling on missing skills.
Wired into curriculumReflex: manifesto takes precedence over
curriculum.plan when it has a concrete suggestion. Tests can pass
ctx.disableManifesto=true to exercise the curriculum branch
in isolation (existing reflex tests keep passing this way).
Pi self-reflection prompt now includes
"activeNeed (Maslow ladder L0-L10): L2 tools_wood → gather.logs"
so Pi advises at the right level instead of giving generic guidance.
skillId returned by pursue() is validated against the live registry
(rc.1 plumbing) — manifesto cannot accidentally dispatch a
hallucinated skill name.
Tests: 315 green (was 279 on rc.1, +36 new):
- runtime/manifesto/needs.test.js — 24 tests (per-need detect/pursue,
helper sums)
- runtime/manifesto/state.test.js — 10 tests (ladder walk, hostile
takeover at L0, armor skipping, caching)
- runtime/reflex.test.js — 2 integration tests (manifesto overrides
curriculum plan; well-fed bot pursues tools_stone)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* v0.3.0-rc.3: event-driven awareness + skill pre-emption
Adds a reactive layer on top of the polling reflex. The bot now
notices environmental shocks (forced moves, HP plunges, hostile
spawns) within ~100ms instead of waiting for the next DISPATCH tick,
and the in-flight skill is preempted so the next reflex cycle can
re-plan against the current world state.
This is the rc that wires the "rc.1 plumbing + rc.2 manifesto" into
a feedback loop:
- awareness fires preempt → dispatch aborts
- reflex tick re-evaluates → manifesto walks the ladder
- new dispatch picks the right skill for the new world state
Pieces:
- runtime/awareness/events.js (new) — bot.on listeners:
- move: single-tick Δposition ≥ 5 blocks → forced_move flag + preempt
- health: HP drop ≥ 2 → health_plunge flag + preempt
- entitySpawn: hostile mob within 12 blocks → hostile_added + preempt
- blockUpdate: nearby block change → env_changed flag (no preempt,
throttled 800ms; otherwise gather skills would self-preempt
every dig)
- runtime/skills/index.js — RUNNER_CODES.PREEMPTED + raceWithAbort()
wraps every execute() against ctx.abortSignal. Existing skills get
preemption for free; they don't have to check the signal manually.
- runtime/bot.js:
- dispatchAction creates a fresh AbortController per dispatch and
stores it on reflexCtx.currentAbort
- attachAwareness fires controller.abort() when something disrupts
the active skill; runSkill returns code: "preempted" and the
reflex moves on
- reflexCtx.lastPreempt records the most recent shock
Tests: 332 green (was 315 on rc.2, +17 new):
- runtime/awareness/events.test.js — 12 tests (each event type +
thresholds + throttling + passive-mob filter)
- runtime/skills/contract.test.js — 3 abortSignal tests
(mid-flight, pre-armed, clean signal)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* chore(.env): add PEPA_FAST_LLM_* placeholders for v0.3.0 fast advisor
Empty values keep the fast-advisor tier disabled (safe no-op). Fill
in BASE_URL + API_KEY + MODEL to enable. TimeWeb-style endpoint
example included.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* chore(v0.3.0): rename fast-LLM env vars to TIMEWEB_* (match other projects)
Aligns with the user's other repos (proso) which use TIMEWEB_API_GROK /
TIMEWEB_URL_GROK. Single naming convention across projects avoids the
'which env var was it for this repo' mental tax.
PEPA_FAST_LLM_BASE_URL → TIMEWEB_BASE_URL
PEPA_FAST_LLM_API_KEY → TIMEWEB_API_KEY
PEPA_FAST_LLM_MODEL → TIMEWEB_MODEL
PEPA_FAST_LLM_TIMEOUT_MS → TIMEWEB_TIMEOUT_MS
Provider still works with any OpenAI-compatible endpoint — TimeWeb is
the default but the variable name doesn't lock us in. Tests + docs +
.env / .env.example updated.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(scripts): TimeWeb smoke test + bump default LLM timeout to 20s
scripts/check-timeweb.js — three probes: plain text, JSON mode, full
fast-advisor stack (registry injection + skill validation). Loads .env,
prints {ok, latency, reply preview} for each. Doesn't touch bot state.
Bumped DEFAULT_TIMEOUT_MS 8s → 20s in runtime/llm/provider.js. TimeWeb's
hosted agent endpoint takes 5-15s for the fast-advisor prompt
(registry block + snapshot context), so 8s was producing spurious
timeouts. OpenAI direct returns much faster; env var TIMEWEB_TIMEOUT_MS
overrides if needed.
Smoke verified live (PR #27 branch):
probe 1: 6.3s, plain prompt → "pepa hears you"
probe 2: 5.4s, JSON mode → {"alive":true,"name":"pepa"}
probe 3: 14.9s, advise() → action=switch_skill, skill=recovery.tunnel-out
(correct registered skill, sensible rationale — registry
injection successfully prevents hallucination)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(v0.3.0): auto-trigger fast-advisor + token usage tracking
Closes the awareness → LLM → action loop that the rc.1/2/3 sequence
left as a followup. When the bot is wedged, looping, or just suffered
a preempt-then-retry, the reflex fires advise() in the background;
when the recommendation lands it overrides the next dispatch.
Async by design: advise() takes 5-15s on TimeWeb's hosted endpoint —
too slow for a synchronous reflex tick. tickAdvisor() is fire-and-
forget, the result lands on ctx.advisorRecommendation, and the *next*
tick reads and consumes it. Recommendations age out after 60s.
Components:
- runtime/coach/advisor-trigger.js — policy + async fire path
- tickAdvisor(ctx, {plannedSkillId}) checks three triggers:
1. wedged > 60s (no significant move)
2. last 4+ dispatches are the same skill AND it's planned again
3. preempt within last 30s + same skill being retried
- 90s trigger cooldown, single-in-flight guard
- consumeFreshRecommendation(ctx) reads/clears the cache
- runtime/reflex.js — curriculumReflex calls tickAdvisor() every tick
and consumes a fresh recommendation BEFORE dispatching. ctx flag
disableAdvisor=true for tests.
- runtime/bot.js — dispatchAction maintains a rolling 8-slot
reflexCtx.recentSkillIds for the loop-detection trigger.
Token usage:
- runtime/llm/provider.js — normaliseUsage() reads OpenAI/TimeWeb-
style {prompt_tokens, completion_tokens, total_tokens} from the
response. Returned on every complete() result and logged at info
level as "in=Nt/out=Mt".
- runtime/coach/fast-advisor.js — getUsageSnapshot() aggregates
total tokens across all calls in the session.
Measured on live TimeWeb endpoint (gpt-5.4-mini agent):
per call: ~705 input + 45 output = ~750 tokens
rate limit: 6 calls/hour
worst case at full budget: ~108K tokens/day
estimated cost (OpenAI gpt-5-mini reference price): ~$0.60/month
Well within any reasonable budget — model can run hot 24/7.
Smoke verified: scripts/check-timeweb.js probe 4 produces
trigger fired: true (wedged_90s)
recommendation: recovery.tunnel-out
rationale: "Stuck wedged for 90s; exploration is failing."
latency: 5302ms
Tests: 345 green (was 332, +13 advisor-trigger).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(v0.3.0): paradigm shift — TimeWeb-only LLM + persistent advisor trail + improvement queue
This is the rc.4 batch the user requested:
1. Emergency triggers (low HP + close hostile, lava-under-foot)
bypass the long cooldown so the LLM is consulted BEFORE the bot
dies, not after.
2. Active manifesto need is now included in the advisor user prompt
— the LLM picks suggestions that satisfy the bot's current
concrete need (L2 tools_wood → "gather logs nearby" not
"explore further").
3. Every advisor recommendation is persisted to SQLite
(advisor_recommendations table) with full token usage. The
reflex marks 'applied=1' when it dispatches and updates
outcome_ok/code when the dispatch completes. Ground truth for
"is the LLM actually helping" lives in the DB, not in logs.
4. Pi CLI is OUT of every background loop. coach/postmortem and
coach/reflect now go through the same TimeWeb endpoint
fast-advisor uses, via the shared coach/llm-call.js helper.
Pi is reserved for manual operator commands.
5. The LLM (postmortem, reflect, advisor) can flag "structural
gaps" — missing skills/features the operator should implement.
These land in the new improvement_requests table. Dedup by
title bumps `votes` instead of inserting duplicates so the
queue doesn't bloat. Operator views via
`node scripts/list-improvements.js`.
6. A deterministic trigger-tuner runs hourly: reads 24h of
recommendation stats, flags triggers whose success rate is
below 25% (sample ≥ 5) or whose prompts are expensive (>1000
input tokens) with mediocre payoff. Improvements get
source="tuner", category="tuning". No LLM call.
New files:
runtime/coach/llm-call.js — askAnalytical() helper
runtime/coach/trigger-tuner.js — stats → improvements
runtime/coach/trigger-tuner.test.js
scripts/list-improvements.js — operator CLI
Schema additions:
advisor_recommendations: id, ts, trigger_reason, planned_skill,
recommended_skill, action, rationale, active_need, tokens_in,
tokens_out, latency_ms, applied, outcome_ok, outcome_code, outcome_at
improvement_requests: id, ts, source, category, title, description,
context, priority, status, duplicate_of, votes, implemented_at, notes
Renamed env-var consumers:
Pi-coach drainOnce({ askPi }) → drainOnce({ askAnalyticalFn? })
Pi-reflect runOnce({ askPi }) → runOnce({ askAnalyticalFn? })
bot.js attachCoach/attachReflect no longer pass askPi
attachTuner() added to bot.js spawn handler
lessons.source 'pi-coach' → 'timeweb-coach'
lessons.source 'pi-reflect' → 'timeweb-reflect'
Token cost measured live:
~705 input + 45 output = ~750 total per advisor call
worst case @ 6 calls/hour rate cap = ~108K tokens/day
OpenAI gpt-5-mini reference price: ~$0.60/month
Operator usage:
node scripts/list-improvements.js # open queue
node scripts/list-improvements.js --stats # advisor performance
node scripts/list-improvements.js --done 17 "shipped in 0.3.1"
node scripts/list-improvements.js --reject 18 "duplicate"
Tests: 360 green (was 332, +28 new).
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>
|
||
|
mayatnikovandClaude Opus 4.7
|
86e5294bb8 |
chore: snapshot pre-v0.2.0 WIP (pathfinder/reflex/metrics/skills improvements)
Baseline for the v0.2.0 self-learning iteration. All 205 tests pass on this state. Subsequent commits in this branch layer the knowledge base, post-mortem coach, and persona narration on top. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
mayatnikov
|
f13799de28 | fix(runtime/reflex): retreat after repeated melee clears | ||
|
mayatnikov
|
b23aad2128 | fix(runtime/reflex): verify melee clears hostile | ||
|
mayatnikovandClaude Opus 4.7
|
19dc8e12c6 |
fix(runtime): unstick wander loop + chop radius + explore.far skill
Follow-up to the iteration-1 fixes. Live smoke on play.xmatic.team revealed the bot was spawning into a tree-less plain (no log within 32 blocks of spawn), looping wander→gather→no_target→wander forever inside a 16-block box. - runtime/actions.js: chopNearestTree search radius 32 → 64 (still no trees on this spawn, but a normal biome will be served well by it). wander now has a blind-walk fallback when pathfinder times out (look+forward+jump for 3 s) so the bot at least unsticks from leaves or pillars. Pathfinder timeout reduced 30 s → 15 s. - runtime/skills/explore-far.js: new explore.far skill — walks ~48 blocks in a quadrant (NE/SE/SW/NW, rotating per call) so successive hints actually circle the spawn instead of bouncing in place. Blind walk fallback included. - runtime/reflex.js: when the scheduler is told to wander twice in a row by gather.* recover hints, it now dispatches explore.far instead so the bot actually leaves the patch it's stuck in. Resets the consecutiveWanderHints counter on any success. - runtime/reflex.js (sleep): no longer dispatches when the bot has neither a bed in inventory NOR a known shelter/base location — saved one dispatch + 5-min cooldown per restart at night. - runtime/reflex.js (eat): inventory check + lastEatAt always updated fix the eat-spam loop observed live (every tick fired "eat" → "no food in inventory" → again). - runtime/skills/chop-logs.js: recognise "no log within ..." as no_target so the recover hint switches the bot to wander/explore. npm test 124/124. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
|
ea4f16a0da |
feat(runtime): scheduler-via-runSkill + Pi banter escalation + base-site (follow-ups) (#20)
Three closures of remaining PRD follow-ups, one merge:
1. Reflex scheduler now drives behaviour from the curriculum.
- reflex.js: replaced ad-hoc techTreeReflex + autonomousReflex with
curriculumReflex that dispatches the skill suggested by
snapshot.curriculum.plan via runSkill. Per-skill backoff for
missing_tool / missing_material / no_target / no_food_source /
unsupported_version. recover() hint with `{hint:"wander"}` swaps
the next tick to wander for 60 s.
- Chain is now: defend > eat > sleep > curriculum > idle.
- reflex.test.js: 11 new tests covering busy/disconnected,
defend/eat preemption, dispatch by id, unknown-skill fallback,
per-skill + wander-hint backoffs, onComplete updating backoff.
2. Pi escalation for ADDRESSED_BANTER with hard rate limit.
- bot.js: when generateReply returns {escalate:true}, spawn askPi
with bot state + last 5 lines from that speaker (redacted via
chatMemory). Reply capped at 200 chars, sent as one chat line.
- Rate cap: 6 calls/hour, 90 s min gap. Suppressed escalations
log once and silently drop.
3. Phase 4 substrate.
- runtime/locations.js: atomic JSON store
(state/<host>/locations.json) with setLocation / getLocation /
nearestLocation / removeLocation; 6 tests.
- runtime/base-site.js: scoreCurrentPosition(bot) + pure scoreSite
bundle (wood / stone / water / flatness / no-players /
no-foreign-builds, owned-blocks excluded from claim penalty);
6 tests.
- runtime/skills/choose-base.js: village.choose-base skill — scores
the current spot, writes locations.base if score ≥ 8, otherwise
returns code:"too_weak" with a wander recover hint.
- curriculum.js: new final milestone village.base-site fires
village.choose-base until a base location exists.
- bot.js: stamps snapshot.locations from listLocations() each tick
so the curriculum can read it without coupling to disk.
docs/runtime.md updated with three new sections.
npm test now 116/116.
Co-authored-by: Yuriy Mayatnikov <mayatnikov@me.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|