feat(runtime): hybrid script reflex + Ink TUI + Pi-on-demand escalation (#4)

* 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>
2026-05-25 16:04:48 +03:00
parent 989ddf335e
commit 1e3b36a9a1
16 changed files with 2464 additions and 75 deletions
@@ -0,0 +1,44 @@
+// Spawn `pi -p "<prompt>"` as a one-shot subprocess and stream stdout/stderr
+// to the caller. Used for headless escalation: the bot's reflex / TUI can ask
+// Pi a single question without keeping a long-lived TUI session open.
+
+import { spawn } from "node:child_process";
+import { info, warn } from "./log.js";
+
+// Resolve `pi` lazily — user has it on PATH via vite-plus shim.
+const PI_BIN = process.env.PI_BIN || "pi";
+
+export function askPi({ prompt, onChunk, onDone, cwd, signal }) {
+	const startedAt = Date.now();
+	info("pi-bridge", `spawning pi -p (${prompt.length} chars)`);
+
+	const child = spawn(PI_BIN, ["-p", prompt], {
+		cwd: cwd || process.cwd(),
+		env: { ...process.env, CI: "1" },
+		stdio: ["ignore", "pipe", "pipe"],
+		signal,
+	});
+
+	child.stdout.setEncoding("utf8");
+	child.stderr.setEncoding("utf8");
+
+	child.stdout.on("data", (chunk) => {
+		onChunk?.({ stream: "stdout", text: chunk });
+	});
+	child.stderr.on("data", (chunk) => {
+		onChunk?.({ stream: "stderr", text: chunk });
+	});
+
+	child.on("error", (err) => {
+		warn("pi-bridge", `pi subprocess failed to start: ${err?.message ?? err}`);
+		onDone?.({ code: -1, durationMs: Date.now() - startedAt, error: String(err) });
+	});
+
+	child.on("exit", (code) => {
+		const durationMs = Date.now() - startedAt;
+		info("pi-bridge", `pi exited code=${code} after ${durationMs}ms`);
+		onDone?.({ code: code ?? -1, durationMs });
+	});
+
+	return child;
+}