Operator feedback: "бот должен быть полностью автономным — сам себя
улучшать и чинить, в этом и есть смысл; все что я вижу пока что он
стоит на месте и кидает proposals на каждый чих — это кардинально не
то что я хочу". Acted on:
1. Trigger filter — proposals only on real bugs.
runtime/bot.js classifies failure detail into bug / timeout /
feature-gap / other. The 5-in-a-row trigger fires only when the run
contains a bug (TypeError / Cannot read / is not defined …) OR is
entirely timeouts on the same operation. Feature gaps like "no
reachable log within 32 blocks", "no food in inventory", "no bed in
range", "no target in reach" are SKIPPED — the reflex layer routes
around them (noTreesUntil → wander, etc). The LLM has no business
patching code for missing inventory.
Threshold raised 3 → 5 in a row. Cooldown unchanged (30 min).
2. Auto-apply, no operator-in-the-loop.
New runtime/auto-improve.js polls proposals/ every 2s. When it sees
a new .md and 10s have passed since first sighting (debounce),
spawns scripts/auto-patch.js detached.
New scripts/auto-patch.js: refuses on dirty tree, moves proposal
pending → approved/, branches `auto/<slug>` off main, runs `pi -p`
with 10-min timeout. If Pi committed AND every changed file is
under runtime/ → cherry-picks onto main. Otherwise discards the
branch. No push, no PR. Audit trail in state/<host>/proposals/approved/.
Rate limit: 15-min cooldown between finished runs + 4/hour hard cap.
3. Auto-rollback on bad patches.
runtime/supervisor.js: when MAX_RESTARTS_PER_MINUTE is exceeded
AND `git log -1 HEAD` is younger than 15 min AND HEAD touched
runtime/, runs `git reset --hard HEAD~1`. Up to MAX_ROLLBACKS=3
lifetime, then exits 1 for manual investigation. Restart counters
are reset after a successful rollback so the next attempt isn't
immediately killed.
4. current-task.json slim.
No longer stores the full perception snapshot (was ~3 KB per write
× every action). Position only — sufficient as a resume anchor.
Slim snapshot still goes into the proposal markdown for context.
docs/runtime.md — rewrote the self-improvement section: full flow
diagram, classification rules, all rate-limit knobs, manual escape
hatches kept but documented as rarely-needed.
Also cleared 5 stale proposals from previous smoke tests so the first
production run isn't burning Pi tokens on stale bugs that have since
been fixed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Updates docs/runtime.md and README.md to match what's actually shipped:
- reflex chain priorities and what each body now dispatches
- operator chat command list (status, come, pause, resume, stop)
- automatic + manual Pi escalation paths and the no-code-change rule
- the full self-improvement loop end-to-end (detector → TUI approval
→ propose:apply → supervisor restart) with the rationale for the
manual propose:apply step
- new state files layout (proposals/, proposals/approved/, etc.)
- supervisor.js + bot:bare script flags
No code changes.
Co-authored-by: Yuriy Mayatnikov <mayatnikov@me.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(mindcraft-skills): hard timeout on every skill call
mc_avoid_enemies (and 7 other tools) wrapped only in safeCall without a
withTimeout. When mindcraft's underlying pathfinder/pvp goal couldn't be
satisfied, the call never resolved — the Pi tick loop blocked forever.
Observed live: mc_avoid_enemies pending >10 minutes after one mc_observe.
safeCall now takes timeoutMs (default 30s) and wraps withTimeout itself,
so every tool gets a hard ceiling. Per-tool overrides:
- goToPosition / goToNearestBlock: 120s / 90s (unchanged from before)
- defendSelf / avoidEnemies: 45s
- stay: secs*1000 + 10s
- craft / consume / pickup / place: 30s
- equip: 15s
collectBlock still uses its bespoke per-iter 75s loop.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(runtime): script-driven reflex daemon + Ink TUI dashboard
Pure-Pi runtime had three failure modes in practice:
- slow: 20-60s per decision because LLM was in the hot path
- expensive: every tick (defend, eat, idle) paid for a reasoning pass
- invisible: required tmux capture-pane to know what the bot was doing
New runtime/ layer is a long-running Node daemon that owns the MC
connection, ticks a priority-ordered reflex chain (defend > eat > sleep
> idle) with NO LLM in the hot path, and exposes status + commands over
a Unix-socket IPC. tui/ is an Ink dashboard that attaches over IPC and
can detach freely — multiple TUI clients can connect at once.
Pi/Codex are still available, but as on-demand escalation: TUI hotkey
'a' spawns `pi -p "<prompt>"` as a subprocess and streams stdout into
the dashboard. The self-improvement loop (proposals → operator approval
→ Pi-driven patch → hot reload) is documented in docs/runtime.md but
not yet wired.
Reflex bodies are stubs today — they log decisions but don't drive
Mineflayer actions yet. The priority chain, IPC contract, and TUI are
fully working; subsequent commits will fill in defend/eat/sleep bodies
and wire automatic escalation.
Run with `npm run bot` + `npm run tui`. Pi-only fallback stays at
`npm run agent`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Yuriy Mayatnikov <mayatnikov@me.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
mayatnikovandClaude Opus 4.7