* 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>
472 lines
16 KiB
JavaScript
472 lines
16 KiB
JavaScript
// Public surface of the knowledge subsystem. Other runtime modules should
|
||
// import from here, not from store/seed/lessons directly.
|
||
//
|
||
// Wire-up:
|
||
// await initKnowledge({ stateDir })
|
||
// - opens the SQLite DB at state/<host>/knowledge.db
|
||
// - applies schema
|
||
// - seeds starter recipes/mobs/blocks/lessons (idempotent)
|
||
// isAvailable() — true once init succeeded
|
||
//
|
||
// All other helpers degrade gracefully when the store is unavailable
|
||
// (e.g. fresh checkout without `npm install`).
|
||
|
||
export { isAvailable, disabledReason, getStore, closeStore, runMaintenance } from "./store.js";
|
||
export { recall, record, markApplied, topAdvice } from "./lessons.js";
|
||
|
||
import { ensureStore, isAvailable as _isAvailable } from "./store.js";
|
||
import { seed } from "./seed.js";
|
||
import { warn, info } from "../log.js";
|
||
|
||
let _initialised = false;
|
||
|
||
export async function initKnowledge({ stateDir } = {}) {
|
||
if (_initialised) return _isAvailable();
|
||
_initialised = true;
|
||
const db = await ensureStore({ stateDir });
|
||
if (!db) {
|
||
warn("knowledge", "init: store not available; knowledge layer will be a no-op");
|
||
return false;
|
||
}
|
||
const seedResult = seed();
|
||
if (!seedResult.ok) {
|
||
warn("knowledge", `init: seed step failed (${seedResult.reason})`);
|
||
}
|
||
return true;
|
||
}
|
||
|
||
// Death/postmortem helpers — separate file would be overkill; they share
|
||
// the store and are only called from coach/postmortem.js.
|
||
import { getStore as _getStore } from "./store.js";
|
||
|
||
export function insertDeath({ ts, x, y, z, cause, hostile, lastSkill, lastSkillCode,
|
||
hp, food, inventoryLost, contextBlob } = {}) {
|
||
if (!_isAvailable()) return null;
|
||
try {
|
||
const stmt = _getStore().prepare(`
|
||
INSERT INTO deaths (ts, x, y, z, cause, hostile, last_skill, last_skill_code,
|
||
hp_at_death, food_at_death, inventory_lost, context_blob, analysed)
|
||
VALUES (@ts, @x, @y, @z, @cause, @hostile, @lastSkill, @lastSkillCode,
|
||
@hp, @food, @inventoryLost, @contextBlob, 0)
|
||
`);
|
||
const res = stmt.run({
|
||
ts: ts ?? Date.now(),
|
||
x: x ?? null, y: y ?? null, z: z ?? null,
|
||
cause: cause ?? "unknown",
|
||
hostile: hostile ?? null,
|
||
lastSkill: lastSkill ?? null,
|
||
lastSkillCode: lastSkillCode ?? null,
|
||
hp: hp ?? null,
|
||
food: food ?? null,
|
||
inventoryLost: inventoryLost ? JSON.stringify(inventoryLost) : null,
|
||
contextBlob: contextBlob ? JSON.stringify(contextBlob) : null,
|
||
});
|
||
return res.lastInsertRowid;
|
||
} catch (e) {
|
||
warn("knowledge", `insertDeath failed: ${e?.message ?? e}`);
|
||
return null;
|
||
}
|
||
}
|
||
|
||
export function unanalysedDeaths({ limit = 5 } = {}) {
|
||
if (!_isAvailable()) return [];
|
||
try {
|
||
return _getStore().prepare(`
|
||
SELECT * FROM deaths WHERE analysed = 0 ORDER BY ts ASC LIMIT @limit
|
||
`).all({ limit });
|
||
} catch (e) {
|
||
warn("knowledge", `unanalysedDeaths failed: ${e?.message ?? e}`);
|
||
return [];
|
||
}
|
||
}
|
||
|
||
export function markDeathAnalysed(deathId) {
|
||
if (!_isAvailable()) return;
|
||
try {
|
||
_getStore().prepare("UPDATE deaths SET analysed = 1 WHERE id = ?").run(deathId);
|
||
} catch (e) {
|
||
warn("knowledge", `markDeathAnalysed failed: ${e?.message ?? e}`);
|
||
}
|
||
}
|
||
|
||
export function insertPostmortem({ deathId, cause, lesson, nextAction, rawResponse, source = "pi" } = {}) {
|
||
if (!_isAvailable() || !deathId) return null;
|
||
try {
|
||
const res = _getStore().prepare(`
|
||
INSERT INTO postmortems (death_id, ts, cause, lesson, next_action, raw_response, source)
|
||
VALUES (@deathId, @ts, @cause, @lesson, @nextAction, @rawResponse, @source)
|
||
`).run({
|
||
deathId,
|
||
ts: Date.now(),
|
||
cause: cause ?? null,
|
||
lesson: lesson ?? null,
|
||
nextAction: nextAction ?? null,
|
||
rawResponse: rawResponse ?? null,
|
||
source,
|
||
});
|
||
return res.lastInsertRowid;
|
||
} catch (e) {
|
||
warn("knowledge", `insertPostmortem failed: ${e?.message ?? e}`);
|
||
return null;
|
||
}
|
||
}
|
||
|
||
// Recipe / mob / block lookups
|
||
export function lookupRecipe(name) {
|
||
if (!_isAvailable()) return null;
|
||
try {
|
||
const row = _getStore().prepare(`SELECT * FROM recipes WHERE name = ?`).get(name);
|
||
if (!row) return null;
|
||
return { ...row, shape: safeParse(row.shape) };
|
||
} catch (e) {
|
||
warn("knowledge", `lookupRecipe failed: ${e?.message ?? e}`);
|
||
return null;
|
||
}
|
||
}
|
||
|
||
export function lookupMob(name) {
|
||
if (!_isAvailable() || !name) return null;
|
||
try {
|
||
const row = _getStore().prepare(`SELECT * FROM mob_intel WHERE name = ?`).get(name);
|
||
if (!row) return null;
|
||
return { ...row, drops: safeParse(row.drops) };
|
||
} catch (e) {
|
||
warn("knowledge", `lookupMob failed: ${e?.message ?? e}`);
|
||
return null;
|
||
}
|
||
}
|
||
|
||
export function lookupBlock(name) {
|
||
if (!_isAvailable() || !name) return null;
|
||
try {
|
||
const row = _getStore().prepare(`SELECT * FROM block_intel WHERE name = ?`).get(name);
|
||
if (!row) return null;
|
||
return { ...row, drops: safeParse(row.drops) };
|
||
} catch (e) {
|
||
warn("knowledge", `lookupBlock failed: ${e?.message ?? e}`);
|
||
return null;
|
||
}
|
||
}
|
||
|
||
// POI helpers — spatially-keyed long-term memory.
|
||
const CELL = 16;
|
||
|
||
export function recordPOI({ kind, name, x, y, z, expiresAt, notes } = {}) {
|
||
if (!_isAvailable() || typeof x !== "number" || typeof z !== "number") return null;
|
||
try {
|
||
const stmt = _getStore().prepare(`
|
||
INSERT INTO poi (kind, name, x, y, z, cell_x, cell_z, ts, expires_at, notes)
|
||
VALUES (@kind, @name, @x, @y, @z, @cellX, @cellZ, @ts, @expiresAt, @notes)
|
||
`);
|
||
const cellX = Math.floor(x / CELL);
|
||
const cellZ = Math.floor(z / CELL);
|
||
const res = stmt.run({
|
||
kind, name: name ?? null,
|
||
x, y: y ?? 0, z,
|
||
cellX, cellZ,
|
||
ts: Date.now(),
|
||
expiresAt: expiresAt ?? null,
|
||
notes: notes ?? null,
|
||
});
|
||
return res.lastInsertRowid;
|
||
} catch (e) {
|
||
warn("knowledge", `recordPOI failed: ${e?.message ?? e}`);
|
||
return null;
|
||
}
|
||
}
|
||
|
||
export function poiNearby({ x, z, kind, radius = 64, limit = 8 } = {}) {
|
||
if (!_isAvailable() || typeof x !== "number" || typeof z !== "number") return [];
|
||
try {
|
||
const cellX = Math.floor(x / CELL);
|
||
const cellZ = Math.floor(z / CELL);
|
||
const cellRadius = Math.ceil(radius / CELL);
|
||
const sql = `
|
||
SELECT *, ((x - @x) * (x - @x) + (z - @z) * (z - @z)) AS dist2
|
||
FROM poi
|
||
WHERE cell_x BETWEEN @cxLo AND @cxHi
|
||
AND cell_z BETWEEN @czLo AND @czHi
|
||
${kind ? "AND kind = @kind" : ""}
|
||
AND (expires_at IS NULL OR expires_at > @now)
|
||
ORDER BY dist2 ASC
|
||
LIMIT @limit
|
||
`;
|
||
return _getStore().prepare(sql).all({
|
||
x, z,
|
||
cxLo: cellX - cellRadius, cxHi: cellX + cellRadius,
|
||
czLo: cellZ - cellRadius, czHi: cellZ + cellRadius,
|
||
kind: kind ?? null,
|
||
now: Date.now(),
|
||
limit,
|
||
}).filter((r) => r.dist2 <= radius * radius);
|
||
} catch (e) {
|
||
warn("knowledge", `poiNearby failed: ${e?.message ?? e}`);
|
||
return [];
|
||
}
|
||
}
|
||
|
||
// Chat log
|
||
export function logChat({ direction, speaker, text, intent, repliedWith } = {}) {
|
||
if (!_isAvailable() || !text) return null;
|
||
try {
|
||
const res = _getStore().prepare(`
|
||
INSERT INTO chat_log (ts, direction, speaker, text, intent, replied_with)
|
||
VALUES (@ts, @direction, @speaker, @text, @intent, @repliedWith)
|
||
`).run({
|
||
ts: Date.now(),
|
||
direction: direction ?? "in",
|
||
speaker: speaker ?? null,
|
||
text,
|
||
intent: intent ?? null,
|
||
repliedWith: repliedWith ?? null,
|
||
});
|
||
return res.lastInsertRowid;
|
||
} catch (e) {
|
||
warn("knowledge", `logChat failed: ${e?.message ?? e}`);
|
||
return null;
|
||
}
|
||
}
|
||
|
||
// ---- v0.3.0 advisor recommendations ----------------------------------------
|
||
//
|
||
// Every fast-advisor call that produced a usable answer is logged here.
|
||
// Rows are mutated post-hoc when reflex applies and when the dispatch
|
||
// finishes — this is the ground truth for "is the LLM advice actually
|
||
// helping" and the input to trigger-tuner.js.
|
||
|
||
export function insertRecommendation({
|
||
triggerReason, plannedSkill, recommendedSkill, action, rationale,
|
||
activeNeed, tokensIn, tokensOut, latencyMs,
|
||
} = {}) {
|
||
if (!_isAvailable()) return null;
|
||
try {
|
||
const res = _getStore().prepare(`
|
||
INSERT INTO advisor_recommendations
|
||
(ts, trigger_reason, planned_skill, recommended_skill, action, rationale,
|
||
active_need, tokens_in, tokens_out, latency_ms, applied)
|
||
VALUES
|
||
(@ts, @triggerReason, @plannedSkill, @recommendedSkill, @action, @rationale,
|
||
@activeNeed, @tokensIn, @tokensOut, @latencyMs, 0)
|
||
`).run({
|
||
ts: Date.now(),
|
||
triggerReason,
|
||
plannedSkill: plannedSkill ?? null,
|
||
recommendedSkill: recommendedSkill ?? null,
|
||
action,
|
||
rationale: rationale ?? null,
|
||
activeNeed: activeNeed ?? null,
|
||
tokensIn: tokensIn ?? null,
|
||
tokensOut: tokensOut ?? null,
|
||
latencyMs: latencyMs ?? null,
|
||
});
|
||
return res.lastInsertRowid;
|
||
} catch (e) {
|
||
warn("knowledge", `insertRecommendation failed: ${e?.message ?? e}`);
|
||
return null;
|
||
}
|
||
}
|
||
|
||
export function markRecommendationApplied(id) {
|
||
if (!_isAvailable() || !id) return;
|
||
try {
|
||
_getStore().prepare(`UPDATE advisor_recommendations SET applied = 1 WHERE id = ?`).run(id);
|
||
} catch (e) {
|
||
warn("knowledge", `markRecommendationApplied failed: ${e?.message ?? e}`);
|
||
}
|
||
}
|
||
|
||
export function markRecommendationOutcome(id, { ok, code } = {}) {
|
||
if (!_isAvailable() || !id) return;
|
||
try {
|
||
_getStore().prepare(`
|
||
UPDATE advisor_recommendations
|
||
SET outcome_ok = @ok, outcome_code = @code, outcome_at = @at
|
||
WHERE id = @id
|
||
`).run({ id, ok: ok ? 1 : 0, code: code ?? null, at: Date.now() });
|
||
} catch (e) {
|
||
warn("knowledge", `markRecommendationOutcome failed: ${e?.message ?? e}`);
|
||
}
|
||
}
|
||
|
||
export function recommendationStats({ sinceHours = 24 } = {}) {
|
||
if (!_isAvailable()) return [];
|
||
try {
|
||
const since = Date.now() - sinceHours * 3600_000;
|
||
return _getStore().prepare(`
|
||
SELECT trigger_reason,
|
||
COUNT(*) AS total,
|
||
SUM(applied) AS applied,
|
||
SUM(CASE WHEN outcome_ok = 1 THEN 1 ELSE 0 END) AS succeeded,
|
||
SUM(CASE WHEN outcome_ok = 0 THEN 1 ELSE 0 END) AS failed,
|
||
AVG(tokens_in) AS avg_in,
|
||
AVG(tokens_out) AS avg_out,
|
||
AVG(latency_ms) AS avg_latency_ms
|
||
FROM advisor_recommendations
|
||
WHERE ts >= @since
|
||
GROUP BY trigger_reason
|
||
ORDER BY total DESC
|
||
`).all({ since });
|
||
} catch (e) {
|
||
warn("knowledge", `recommendationStats failed: ${e?.message ?? e}`);
|
||
return [];
|
||
}
|
||
}
|
||
|
||
export function recentRecommendations({ limit = 20 } = {}) {
|
||
if (!_isAvailable()) return [];
|
||
try {
|
||
return _getStore().prepare(`
|
||
SELECT * FROM advisor_recommendations ORDER BY ts DESC LIMIT @limit
|
||
`).all({ limit });
|
||
} catch (e) {
|
||
warn("knowledge", `recentRecommendations failed: ${e?.message ?? e}`);
|
||
return [];
|
||
}
|
||
}
|
||
|
||
// ---- v0.3.0 improvement requests -------------------------------------------
|
||
//
|
||
// The LLM (postmortem / reflect / advisor) writes here when it sees the bot
|
||
// lack a needed skill or feature. Operator-readable via scripts/list-improvements.js.
|
||
|
||
export function createImprovementRequest({
|
||
source, category, title, description, context, priority = 3,
|
||
} = {}) {
|
||
if (!_isAvailable() || !title) return null;
|
||
try {
|
||
// Fuzzy dedup: the LLM re-files the same gap with reworded titles
|
||
// ("целевого поиска еды" vs "целевого дальнего поиска еды по биому").
|
||
// Exact-title match misses these, so we compare normalized token
|
||
// sets against ALL recent requests (any status — a closed/
|
||
// implemented one shouldn't reappear as a fresh open row). On a
|
||
// strong overlap we bump votes (if still open) and return, instead
|
||
// of inserting a near-duplicate.
|
||
const incoming = tokenize(title);
|
||
const candidates = _getStore().prepare(`
|
||
SELECT id, title, status, votes FROM improvement_requests
|
||
ORDER BY ts DESC LIMIT 60
|
||
`).all();
|
||
for (const c of candidates) {
|
||
if (isDuplicateTitle(incoming, tokenize(c.title))) {
|
||
// Re-flagged gap. If it's still open, count the vote. If it
|
||
// was implemented/rejected, do NOT resurrect it — just
|
||
// return its id so the caller treats it as "already known".
|
||
if (c.status === "open") {
|
||
_getStore().prepare(`UPDATE improvement_requests SET votes = votes + 1 WHERE id = ?`).run(c.id);
|
||
}
|
||
return c.id;
|
||
}
|
||
}
|
||
const res = _getStore().prepare(`
|
||
INSERT INTO improvement_requests
|
||
(ts, source, category, title, description, context, priority, status, votes)
|
||
VALUES
|
||
(@ts, @source, @category, @title, @description, @context, @priority, 'open', 1)
|
||
`).run({
|
||
ts: Date.now(),
|
||
source: source ?? "manual",
|
||
category: category ?? "other",
|
||
title,
|
||
description: description ?? null,
|
||
context: context ? JSON.stringify(context) : null,
|
||
priority: clamp(priority, 1, 5),
|
||
});
|
||
return res.lastInsertRowid;
|
||
} catch (e) {
|
||
warn("knowledge", `createImprovementRequest failed: ${e?.message ?? e}`);
|
||
return null;
|
||
}
|
||
}
|
||
|
||
export function listImprovements({ status, source, category, limit = 50 } = {}) {
|
||
if (!_isAvailable()) return [];
|
||
try {
|
||
const where = [];
|
||
const params = { limit };
|
||
if (status) { where.push("status = @status"); params.status = status; }
|
||
if (source) { where.push("source = @source"); params.source = source; }
|
||
if (category) { where.push("category = @category"); params.category = category; }
|
||
const sql = `
|
||
SELECT * FROM improvement_requests
|
||
${where.length ? "WHERE " + where.join(" AND ") : ""}
|
||
ORDER BY (status = 'open') DESC, priority ASC, votes DESC, ts DESC
|
||
LIMIT @limit
|
||
`;
|
||
return _getStore().prepare(sql).all(params).map((r) => ({
|
||
...r,
|
||
context: safeParse(r.context),
|
||
}));
|
||
} catch (e) {
|
||
warn("knowledge", `listImprovements failed: ${e?.message ?? e}`);
|
||
return [];
|
||
}
|
||
}
|
||
|
||
export function markImprovementStatus(id, { status, notes } = {}) {
|
||
if (!_isAvailable() || !id) return;
|
||
const validStatuses = ["open", "in_progress", "implemented", "rejected", "duplicate"];
|
||
if (!validStatuses.includes(status)) {
|
||
warn("knowledge", `markImprovementStatus: invalid status "${status}"`);
|
||
return;
|
||
}
|
||
try {
|
||
const fields = ["status = @status", "notes = @notes"];
|
||
const params = { id, status, notes: notes ?? null };
|
||
if (status === "implemented") {
|
||
fields.push("implemented_at = @implementedAt");
|
||
params.implementedAt = Date.now();
|
||
}
|
||
_getStore().prepare(`UPDATE improvement_requests SET ${fields.join(", ")} WHERE id = @id`).run(params);
|
||
} catch (e) {
|
||
warn("knowledge", `markImprovementStatus failed: ${e?.message ?? e}`);
|
||
}
|
||
}
|
||
|
||
function clamp(n, lo, hi) { return Math.max(lo, Math.min(hi, Number(n) || lo)); }
|
||
|
||
// Normalize a title into a set of meaningful tokens for fuzzy dedup.
|
||
// Lowercase, strip punctuation, drop short / stop words (RU + EN) that
|
||
// carry no signal ("нет", "навыка", "для", "the", "a", …).
|
||
const _STOP = new Set([
|
||
"нет", "навык", "навыка", "для", "из", "по", "в", "на", "и", "с", "к",
|
||
"когда", "нужно", "это", "что", "the", "a", "an", "to", "of", "for",
|
||
"no", "skill", "has", "is", "low", "rate",
|
||
]);
|
||
function tokenize(s) {
|
||
if (!s || typeof s !== "string") return new Set();
|
||
const words = s.toLowerCase()
|
||
.replace(/["'`(),.:;!?\/\\-]+/g, " ")
|
||
.split(/\s+/)
|
||
.filter((w) => w.length >= 3 && !_STOP.has(w));
|
||
return new Set(words);
|
||
}
|
||
function jaccard(a, b) {
|
||
if (a.size === 0 || b.size === 0) return 0;
|
||
let inter = 0;
|
||
for (const w of a) if (b.has(w)) inter++;
|
||
return inter / (a.size + b.size - inter);
|
||
}
|
||
function intersectionSize(a, b) {
|
||
let n = 0;
|
||
for (const w of a) if (b.has(w)) n++;
|
||
return n;
|
||
}
|
||
// Two titles are "the same gap" when they either overlap very strongly
|
||
// (jaccard ≥ 0.75) OR share at least 3 meaningful tokens with moderate
|
||
// overlap (≥ 0.5). The 3-token floor stops short titles with one or two
|
||
// generic words in common ("low-prio thing" vs "high-prio thing") from
|
||
// false-matching, while still catching reworded long titles.
|
||
function isDuplicateTitle(a, b) {
|
||
const j = jaccard(a, b);
|
||
if (j >= 0.75) return true;
|
||
return intersectionSize(a, b) >= 3 && j >= 0.5;
|
||
}
|
||
|
||
function safeParse(s) {
|
||
if (!s) return null;
|
||
try { return JSON.parse(s); } catch { return null; }
|
||
}
|
||
|
||
// Test exports
|
||
export const __testing = { tokenize, jaccard, isDuplicateTitle };
|