feat(runtime): fully autonomous self-healing — no operator approval (#10)
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: Yuriy Mayatnikov <mayatnikov@me.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit was merged in pull request #10.
This commit is contained in:
Yuriy Mayatnikov
@@ -0,0 +1,118 @@
|
||||
// Auto-improve watcher: when a new proposal file appears under
|
||||
// state/<host>/proposals/, debounce briefly (in case the writer is still
|
||||
// finishing), then spawn scripts/auto-patch.js as a detached background
|
||||
// process. The patcher creates a branch, runs Pi headless, and cherry-picks
|
||||
// any resulting commit onto main. The supervisor's runtime/*.js watcher
|
||||
// then triggers a child restart picking up the new code.
|
||||
//
|
||||
// One auto-improve in flight at a time; a 15-minute cooldown between
|
||||
// finished runs caps the Pi token burn rate. Failures keep the proposal
|
||||
// in approved/ (already auto-moved by the patcher) so a future run could
|
||||
// retry — but with the cooldown, this isn't a tight loop.
|
||||
|
||||
import { spawn } from "node:child_process";
|
||||
import fs from "node:fs";
|
||||
import path from "node:path";
|
||||
import { fileURLToPath } from "node:url";
|
||||
|
||||
import { stateDir } from "./config.js";
|
||||
import { info, warn } from "./log.js";
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = path.dirname(__filename);
|
||||
const REPO_ROOT = path.resolve(__dirname, "..");
|
||||
const PATCH_SCRIPT = path.join(REPO_ROOT, "scripts", "auto-patch.js");
|
||||
const PROPOSALS_DIR = path.join(stateDir, "proposals");
|
||||
|
||||
const DEBOUNCE_MS = 10_000;
|
||||
const COOLDOWN_MS = 15 * 60 * 1000;
|
||||
const MAX_TOTAL_PER_HOUR = 4;
|
||||
|
||||
let inFlight = false;
|
||||
let lastFinishedAt = 0;
|
||||
const recentRuns = []; // timestamps
|
||||
|
||||
function withinHourlyCap() {
|
||||
const now = Date.now();
|
||||
while (recentRuns.length && now - recentRuns[0] > 3600_000) recentRuns.shift();
|
||||
return recentRuns.length >= MAX_TOTAL_PER_HOUR;
|
||||
}
|
||||
|
||||
function listPendingProposals() {
|
||||
try {
|
||||
return fs
|
||||
.readdirSync(PROPOSALS_DIR)
|
||||
.filter((f) => f.endsWith(".md"))
|
||||
.sort();
|
||||
} catch (e) {
|
||||
if (e.code === "ENOENT") return [];
|
||||
throw e;
|
||||
}
|
||||
}
|
||||
|
||||
function spawnPatcher(filename) {
|
||||
info("auto-improve", `spawning auto-patch for ${filename}`);
|
||||
inFlight = true;
|
||||
const child = spawn(process.execPath, [PATCH_SCRIPT, filename], {
|
||||
cwd: REPO_ROOT,
|
||||
stdio: ["ignore", "pipe", "pipe"],
|
||||
env: { ...process.env },
|
||||
detached: false,
|
||||
});
|
||||
let stdoutBuf = "";
|
||||
let stderrBuf = "";
|
||||
child.stdout.on("data", (c) => {
|
||||
stdoutBuf += c.toString();
|
||||
});
|
||||
child.stderr.on("data", (c) => {
|
||||
stderrBuf += c.toString();
|
||||
});
|
||||
child.on("exit", (code) => {
|
||||
inFlight = false;
|
||||
lastFinishedAt = Date.now();
|
||||
recentRuns.push(lastFinishedAt);
|
||||
const tail = (stdoutBuf + "\n" + stderrBuf).trim().split("\n").slice(-3).join(" | ");
|
||||
if (code === 0) info("auto-improve", `patch applied for ${filename}: ${tail}`);
|
||||
else warn("auto-improve", `patch did not apply (code=${code}) for ${filename}: ${tail}`);
|
||||
// We do NOT trigger supervisor restart manually — the supervisor's
|
||||
// fs.watch on runtime/*.js fires the moment the cherry-pick lands.
|
||||
});
|
||||
}
|
||||
|
||||
function tick() {
|
||||
if (inFlight) return;
|
||||
if (withinHourlyCap()) return;
|
||||
if (Date.now() - lastFinishedAt < COOLDOWN_MS) return;
|
||||
|
||||
const pending = listPendingProposals();
|
||||
if (pending.length === 0) return;
|
||||
|
||||
// Pick the oldest pending proposal (sorted lexically — timestamps in name).
|
||||
const filename = pending[0];
|
||||
|
||||
// Debounce: ensure the file has been still for DEBOUNCE_MS so we don't
|
||||
// race a partial write. Track first-seen timestamp per filename.
|
||||
if (!debounceMap.has(filename)) {
|
||||
debounceMap.set(filename, Date.now());
|
||||
return;
|
||||
}
|
||||
const firstSeen = debounceMap.get(filename);
|
||||
if (Date.now() - firstSeen < DEBOUNCE_MS) return;
|
||||
|
||||
debounceMap.delete(filename);
|
||||
spawnPatcher(filename);
|
||||
}
|
||||
|
||||
const debounceMap = new Map();
|
||||
let pollTimer = null;
|
||||
|
||||
export function startAutoImprover() {
|
||||
if (pollTimer) return;
|
||||
info("auto-improve", `watching ${PROPOSALS_DIR} (cooldown=${COOLDOWN_MS / 1000}s, max ${MAX_TOTAL_PER_HOUR}/hr)`);
|
||||
pollTimer = setInterval(tick, 2000);
|
||||
}
|
||||
|
||||
export function stopAutoImprover() {
|
||||
if (pollTimer) clearInterval(pollTimer);
|
||||
pollTimer = null;
|
||||
}
|
||||
+87
-20
@@ -30,6 +30,7 @@ import {
|
||||
readProposal,
|
||||
approveProposal,
|
||||
} from "./state-store.js";
|
||||
import { startAutoImprover } from "./auto-improve.js";
|
||||
|
||||
fs.mkdirSync(stateDir, { recursive: true });
|
||||
const JOINED_FLAG = path.join(stateDir, "joined-before.flag");
|
||||
@@ -136,7 +137,9 @@ function dispatchAction(fn, label, opts = {}) {
|
||||
}
|
||||
reflexCtx.busy = true;
|
||||
reflexCtx.currentActionLabel = label;
|
||||
writeCurrentTask({ label, status: "in_progress", snapshot: lastSnapshot });
|
||||
// current-task is a resume anchor — keep it small. Embedding the full
|
||||
// perception snapshot blows the file up to ~3 KB per write × every action.
|
||||
writeCurrentTask({ label, status: "in_progress", position: lastSnapshot.position });
|
||||
info("dispatch", `→ ${label}`);
|
||||
Promise.resolve()
|
||||
.then(() => fn())
|
||||
@@ -170,14 +173,56 @@ function dispatchAction(fn, label, opts = {}) {
|
||||
}
|
||||
|
||||
// ---- failure tracking + proposal detection --------------------------------
|
||||
//
|
||||
// A proposal is a request to the LLM to patch the codebase. They cost tokens
|
||||
// and may produce risky patches that need rolling back. We file them ONLY for
|
||||
// failures that genuinely look like bugs the reflex layer can't handle on its
|
||||
// own. Everything else is a feature gap the script should solve via reflex
|
||||
// chain reordering, cooldowns, or new primitives.
|
||||
|
||||
const PROPOSAL_THRESHOLD = 3; // same labelled action fails 3+ times in a row
|
||||
const PROPOSAL_THRESHOLD = 5; // raised from 3 to dampen spam
|
||||
let lastProposalAt = 0;
|
||||
const PROPOSAL_COOLDOWN_MS = 30 * 60 * 1000; // don't spam proposal files
|
||||
const PROPOSAL_COOLDOWN_MS = 30 * 60 * 1000;
|
||||
|
||||
// Detail substrings that mean "this is a known feature gap, the bot handles
|
||||
// it via reflex routing already". Don't file a proposal — the bot will switch
|
||||
// strategies on its own. If something here is wrong, fix the routing.
|
||||
const NORMAL_FAILURE_SUBSTRINGS = [
|
||||
"no reachable log",
|
||||
"no log within",
|
||||
"no bed in range",
|
||||
"no food in inventory",
|
||||
"no target in reach",
|
||||
"rate-limited",
|
||||
"can't see you nearby",
|
||||
"returned false",
|
||||
"no result",
|
||||
];
|
||||
|
||||
// Detail substrings that look like a real bug — patch-worthy.
|
||||
const BUG_FAILURE_SUBSTRINGS = [
|
||||
"TypeError",
|
||||
"ReferenceError",
|
||||
"Cannot read properties",
|
||||
"is not a function",
|
||||
"is not iterable",
|
||||
"is not defined",
|
||||
"unknown block",
|
||||
"unknown item",
|
||||
];
|
||||
|
||||
function classifyFailure(detail) {
|
||||
const s = String(detail ?? "");
|
||||
if (BUG_FAILURE_SUBSTRINGS.some((sub) => s.includes(sub))) return "bug";
|
||||
if (NORMAL_FAILURE_SUBSTRINGS.some((sub) => s.includes(sub))) return "feature-gap";
|
||||
if (s.includes("timed out")) return "timeout";
|
||||
return "other";
|
||||
}
|
||||
|
||||
function recordFailure(label, detail) {
|
||||
reflexCtx.recentFailures.push({ ts: Date.now(), label, detail });
|
||||
if (reflexCtx.recentFailures.length > 10) reflexCtx.recentFailures.shift();
|
||||
const kind = classifyFailure(detail);
|
||||
reflexCtx.recentFailures.push({ ts: Date.now(), label, detail, kind });
|
||||
if (reflexCtx.recentFailures.length > 20) reflexCtx.recentFailures.shift();
|
||||
maybeFileProposal(label);
|
||||
}
|
||||
|
||||
@@ -186,7 +231,7 @@ function clearRecentFailures(label) {
|
||||
}
|
||||
|
||||
function maybeFileProposal(label) {
|
||||
// Count consecutive trailing failures with the same label.
|
||||
// Same-label trailing run.
|
||||
const trailing = [];
|
||||
for (let i = reflexCtx.recentFailures.length - 1; i >= 0; i--) {
|
||||
const f = reflexCtx.recentFailures[i];
|
||||
@@ -195,37 +240,58 @@ function maybeFileProposal(label) {
|
||||
}
|
||||
if (trailing.length < PROPOSAL_THRESHOLD) return;
|
||||
if (Date.now() - lastProposalAt < PROPOSAL_COOLDOWN_MS) return;
|
||||
|
||||
// Only file when the run is dominated by bug-class failures (any single
|
||||
// bug counts) OR persistent timeouts on the same operation. Feature gaps
|
||||
// are skipped — the reflex layer should re-route, not the LLM.
|
||||
const anyBug = trailing.some((f) => f.kind === "bug");
|
||||
const allTimeout = trailing.every((f) => f.kind === "timeout");
|
||||
if (!anyBug && !allTimeout) return;
|
||||
|
||||
lastProposalAt = Date.now();
|
||||
|
||||
const summary = `${label} failed ${trailing.length}× in a row`;
|
||||
const summary = `${label} failed ${trailing.length}× in a row (${anyBug ? "bug" : "persistent timeout"})`;
|
||||
const slimSnapshot = lastSnapshot && {
|
||||
position: lastSnapshot.position,
|
||||
health: lastSnapshot.health,
|
||||
food: lastSnapshot.food,
|
||||
inventory: lastSnapshot.inventory,
|
||||
isDay: lastSnapshot.isDay,
|
||||
closestHostile: lastSnapshot.closestHostile,
|
||||
dimension: lastSnapshot.dimension,
|
||||
};
|
||||
const body = [
|
||||
`# Repeated failure: ${label}`,
|
||||
"",
|
||||
`Class: **${anyBug ? "bug" : "persistent timeout"}**.`,
|
||||
"",
|
||||
"## What happened",
|
||||
"",
|
||||
`The reflex layer dispatched \`${label}\` ${trailing.length} times in succession without a single success.`,
|
||||
"",
|
||||
"## Most recent failures",
|
||||
"",
|
||||
...trailing.slice(0, 5).map(
|
||||
(f, i) => `${i + 1}. \`${new Date(f.ts).toISOString()}\` — ${JSON.stringify(f.detail).slice(0, 200)}`,
|
||||
),
|
||||
...trailing
|
||||
.slice(0, 5)
|
||||
.map(
|
||||
(f, i) =>
|
||||
`${i + 1}. \`${new Date(f.ts).toISOString()}\` [${f.kind}] ${JSON.stringify(f.detail).slice(0, 200)}`,
|
||||
),
|
||||
"",
|
||||
"## Snapshot at moment of last failure",
|
||||
"## Slim snapshot",
|
||||
"",
|
||||
"```json",
|
||||
JSON.stringify(lastSnapshot, null, 2),
|
||||
JSON.stringify(slimSnapshot, null, 2),
|
||||
"```",
|
||||
"",
|
||||
"## Suggested next step",
|
||||
"## Constraints for the patch",
|
||||
"",
|
||||
"Operator: review whether the reflex should:",
|
||||
"- back off (cooldown extension)",
|
||||
"- switch to a different action variant",
|
||||
"- escalate to Pi for situational reasoning",
|
||||
"- or whether the underlying primitive in `runtime/actions.js` needs work.",
|
||||
"",
|
||||
`Approve this proposal (move to \`proposals/approved/\`) and run \`npm run propose:apply <filename>\` to delegate a patch attempt to Pi headless.`,
|
||||
"- Touch only files under `runtime/`. Don't touch `extensions/`, `tui/`, or any docs.",
|
||||
"- Don't introduce new npm dependencies.",
|
||||
"- Don't change `.env` or anything in `state/`.",
|
||||
"- Don't push, don't open a PR. Commit on the current branch only.",
|
||||
"- Prefer the smallest viable fix. A 3-line guard is better than a 30-line refactor.",
|
||||
"- If the failure is genuinely irrecoverable (server-side, not code), document it in a code comment and exit 1.",
|
||||
].join("\n");
|
||||
|
||||
const { filename } = writeProposal({ kind: `repeated-fail-${label}`, summary, body });
|
||||
@@ -591,3 +657,4 @@ ipc = createIpcServer({
|
||||
});
|
||||
connect();
|
||||
startTickLoop();
|
||||
startAutoImprover();
|
||||
|
||||
+52
-1
@@ -11,7 +11,7 @@
|
||||
// Run via `npm run bot`. Falls back to plain `node runtime/bot.js` via
|
||||
// `npm run bot:bare` if you want to skip the supervisor.
|
||||
|
||||
import { spawn } from "node:child_process";
|
||||
import { spawn, spawnSync } from "node:child_process";
|
||||
import fs from "node:fs";
|
||||
import path from "node:path";
|
||||
import { fileURLToPath } from "node:url";
|
||||
@@ -21,11 +21,17 @@ import { stateDir } from "./config.js";
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = path.dirname(__filename);
|
||||
const RUNTIME_DIR = __dirname;
|
||||
const REPO_ROOT = path.resolve(RUNTIME_DIR, "..");
|
||||
const BOT_ENTRY = path.join(RUNTIME_DIR, "bot.js");
|
||||
|
||||
export const RELOAD_EXIT_CODE = 42;
|
||||
const WATCH_DEBOUNCE_MS = 800;
|
||||
const MAX_RESTARTS_PER_MINUTE = 5;
|
||||
// When a recent auto-patch breaks the bot, we roll it back. "Recent" =
|
||||
// landed on main within the last ROLLBACK_FRESHNESS_MS. The signal is
|
||||
// MAX_RESTARTS_PER_MINUTE exceeded — i.e. the patch reliably crashes.
|
||||
const ROLLBACK_FRESHNESS_MS = 15 * 60_000;
|
||||
const MAX_ROLLBACKS = 3; // hard ceiling per supervisor lifetime
|
||||
|
||||
// Pidfile prevents two supervisors from racing on the same MC nickname. The
|
||||
// Minecraft server refuses the second login ("Игрок с данным никнеймом уже
|
||||
@@ -37,6 +43,37 @@ const PID_FILE = path.join(stateDir, "supervisor.pid");
|
||||
let child = null;
|
||||
let restartingDueToWatch = false;
|
||||
const restartTimestamps = [];
|
||||
let rollbackCount = 0;
|
||||
|
||||
function lastCommitAgeMs() {
|
||||
const res = spawnSync("git", ["log", "-1", "--format=%ct", "HEAD"], { cwd: REPO_ROOT, encoding: "utf8" });
|
||||
if (res.status !== 0) return Number.POSITIVE_INFINITY;
|
||||
const epochSec = Number.parseInt(res.stdout.trim(), 10);
|
||||
if (!Number.isFinite(epochSec)) return Number.POSITIVE_INFINITY;
|
||||
return Date.now() - epochSec * 1000;
|
||||
}
|
||||
|
||||
function lastCommitTouchedRuntime() {
|
||||
const res = spawnSync("git", ["diff", "--name-only", "HEAD~1..HEAD"], { cwd: REPO_ROOT, encoding: "utf8" });
|
||||
if (res.status !== 0) return false;
|
||||
return res.stdout.split("\n").some((f) => f.startsWith("runtime/"));
|
||||
}
|
||||
|
||||
function rollbackLastCommit() {
|
||||
const sha = spawnSync("git", ["rev-parse", "HEAD"], { cwd: REPO_ROOT, encoding: "utf8" }).stdout.trim();
|
||||
console.log(`[supervisor] rolling back HEAD (${sha.slice(0, 8)})`);
|
||||
const reset = spawnSync("git", ["reset", "--hard", "HEAD~1"], {
|
||||
cwd: REPO_ROOT,
|
||||
encoding: "utf8",
|
||||
stdio: "inherit",
|
||||
});
|
||||
if (reset.status !== 0) {
|
||||
console.error(`[supervisor] git reset failed — operator intervention needed`);
|
||||
return false;
|
||||
}
|
||||
rollbackCount++;
|
||||
return true;
|
||||
}
|
||||
|
||||
function nowMs() {
|
||||
return Date.now();
|
||||
@@ -97,6 +134,20 @@ function spawnChild() {
|
||||
restartTimestamps.push(now);
|
||||
while (restartTimestamps.length && now - restartTimestamps[0] > 60_000) restartTimestamps.shift();
|
||||
if (restartTimestamps.length > MAX_RESTARTS_PER_MINUTE) {
|
||||
// Crash loop. If the last commit is young AND touched runtime/, it
|
||||
// probably broke us — roll it back and try once more.
|
||||
const ageMs = lastCommitAgeMs();
|
||||
if (
|
||||
ageMs < ROLLBACK_FRESHNESS_MS &&
|
||||
lastCommitTouchedRuntime() &&
|
||||
rollbackCount < MAX_ROLLBACKS &&
|
||||
rollbackLastCommit()
|
||||
) {
|
||||
console.log(`[supervisor] auto-rollback ${rollbackCount}/${MAX_ROLLBACKS} applied; restart counters reset`);
|
||||
restartTimestamps.length = 0;
|
||||
setTimeout(spawnChild, 500);
|
||||
return;
|
||||
}
|
||||
console.error(`[supervisor] too many restarts (${restartTimestamps.length} in 60s) — giving up`);
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user