Files
openclaw/scripts/embedded-run-abort-leak.ts
Peter Steinberger bb46b79d3c refactor: internalize OpenClaw agent runtime (#85341)
* refactor: extract agent core package

Introduce packages/agent-core as the OpenClaw-owned home for reusable agent loop, harness, session, prompt, and runtime dependency contracts.

* refactor: extract shared llm runtime

Move provider model registries, stream wrappers, OAuth helpers, and LLM utilities into src/llm with plugin-sdk barrels instead of depending on the old embedded runtime layout.

* refactor: remove pi runtime internals

Rename remaining Pi-shaped agent surfaces to OpenClaw agent runtime names, delete obsolete Pi docs and package graph checks, and add the third-party notice for incorporated code.

* refactor: tighten agent session runtime

Make agent-core/runtime dependencies explicit, consolidate compaction and session transcript helpers, and move model/session helpers behind OpenClaw-owned contracts.

* refactor: remove static model and pi auth paths

Drop static model catalogs and Pi auth bridges, move model/provider facts to manifest-owned runtime contracts, and harden internal embedded-agent utilities.

* refactor: remove legacy provider compat paths

* docs: remove agent parity notes

* fix: skip provider wildcard metadata parsing

* refactor: share session extension sdk loading

* refactor: inline acpx proxy error formatter

* refactor: fold edit recovery into edit tool

* fix: accept extension batch separator

* test: align startup provider plugin expectations

* fix: restore provider-scoped release discovery

* test: align static asset packaging expectations

* fix: run static provider catalogs during scoped discovery

* fix: add provider entry catalogs for scoped live discovery

* fix: load lightweight provider catalog entries

* fix: refresh provider-scoped plugin metadata

* fix: keep provider catalog entries on release live path

* fix: keep static manifest models in release live checks

* fix: harden release model discovery

* fix: reduce OpenAI live cache probe reasoning

* fix: disable OpenAI cache probe reasoning

* ci: extend OpenAI gateway live timeout

* fix: extend live gateway model budget

* fix: stabilize release validation regressions

* fix: honor provider aliases in model rows

* fix: stabilize release validation lanes

* fix: stabilize release memory qa

* ci: stabilize release validation lanes

* ci: prefer ipv4 for live docker node calls

* fix: restore shared tool-call stream wrapper

* ci: remove legacy pi test shard alias

* fix: clean up embedded agent test drift

* fix: stabilize runtime alias status

* fix: clean up embedded agent ci drift

* fix: restore release ci invariants

* fix: clean up post-rebase runtime drift

* fix: restore release ci checks

* fix: restore release ci after rebase

* fix: remove stale pi runtime path

* test: align compaction runtime expectations

* test: update plugin prerelease expectations

* fix: handle claude live tool approvals

* fix: stabilize release validation gates

* fix: finish agent runtime import

* test: finish post-rebase agent runtime mocks

* fix: keep codex compaction native

* fix: stabilize codex app-server hook tests

* test: isolate codex diagnostic active run

* test: remove codex diagnostic completion race

# Conflicts:
#	extensions/codex/src/app-server/run-attempt.test.ts

* ci: fix full release manifest performance run id

* refactor: narrow llm plugin sdk boundary

* chore: drop generated google boundary stamps

* fix: repair rebase fallout

* fix: clean up rebased runtime references

* fix: decode codex jwt payloads as base64url

* fix: preserve shipped pi runtime alias

* fix: add scoped sdk virtual modules

* fix: decode llm codex oauth jwt as base64url

* fix: avoid stale vertex adc negative cache

* fix: harden tool arg decoding and codeql path

* fix: keep vertex adc negative checks live

* refactor: consolidate codex jwt and edit helpers

* fix: await codex oauth node runtime imports

* fix: preserve sdk tool and notice contracts

* fix: preserve shipped compat config boundaries

* fix: align codex oauth callback host

* fix: terminate agent-core loop streams on failure

* fix: keep codex oauth callback alive during fallback

* ci: include session tools in critical codeql scans

* fix: keep Cloudflare Anthropic provider auth header

* docs: redirect legacy pi runtime pages

* fix: honor bundled web provider compat discovery

* fix: protect session output spill files

* fix: keep legacy agent dir env blocked

* fix: contain auto-discovered skill symlinks

* fix: harden agent core sdk proxy surfaces

* fix: restore approval reaction sdk compat

* fix: keep live docker runs bounded

* fix: keep codex oauth redirect host aligned

* fix: resolve post-rebase agent runtime drift

* fix: redact anthropic oauth parse failures

* fix: preserve responses strict tool shaping

* fix: repair agent runtime rebase cleanup

* docs: redirect retired parity pages

* fix: bound auto-discovered resources to roots

* fix: repair post-rebase agent test drift

* fix: preserve bundled provider allowlist migration

* fix: preserve manifest-owned provider aliases

* fix: declare photon image dependency

* fix: keep provider headers out of proxy body

* fix: preserve shipped env aliases

* fix: refresh control ui i18n generated state

* fix: quote read fallback paths

* fix: preview edits through configured backend

* test: satisfy core test typecheck

* fix: preserve ZAI usage auth fallback

* test: repair codex diagnostic test

* fix: repair agent runtime rebase drift

* test: finish embedded runner import rename

* fix: repair agent runtime rebase integrations

* test: align compaction oauth fallback expectations

* fix: allow sdk-auth session models

* fix: update doctor tool schema import

* fix: preserve bedrock plugin region

* fix: stream harmony-like prose immediately

* ci: include session runtime in codeql shards

* fix: repair latest rebase integrations

* fix: honor explicit codex websocket transport

* fix: keep openai-compatible credentials provider-scoped

* fix: refresh sdk api baseline after rebase

* fix: route cli runtime aliases through openclaw harness

* test: rename stale harness mock expectation

* test: rename embedded agent overflow calls

* test: clean embedded auth test wording

* test: use openclaw stream types in deepinfra cache test

* fix: refresh sdk api baseline on latest main

* fix: honor bundled discovery compat allowlists

* fix: refresh sdk api baseline after latest rebase

* fix: remove stale rebase imports

* test: rename stale model catalog mock

* test: mock renamed doctor runtime modules

* fix: map canonical kimi env auth

* fix: use internal model registry in bench script

* fix: migrate deepinfra provider catalog entry

* fix: enforce builtin tool suppression

* fix: route compaction auth and proxy payloads safely

* refactor: prune unused llm registry leftovers

* test: update codex hooks session import

* test: fix model picker ci coverage

* test: align model picker auth mock types
2026-05-27 19:24:04 +01:00

339 lines
10 KiB
TypeScript

/**
* Heap-leak harness for the runEmbeddedAttempt abort path. Loops aborted runs
* in a function-shaped scope that mimics the runner, snapshots the heap, and
* computes a PASS/FAIL verdict from RSS delta + tracked-instance retention.
*
* Usage:
* node --import tsx --expose-gc scripts/embedded-run-abort-leak.ts \
* --mode production --iters 50 --batches 5
*
* Modes:
* production (default): imports the real abortable from src; PASS proves the fix works.
* closure-extracted: self-contained module-scope helper (mirrors production shape).
* closure-inline: pre-fix shape (closure inside runner scope).
* synthetic-leak: deliberately retains via module-level bucket
* (sanity check that the harness detects leaks).
*
* Exit code: 0 if PASS, 1 if FAIL (leak detected).
*/
import * as fs from "node:fs";
import * as path from "node:path";
import * as v8 from "node:v8";
import { abortable as productionAbortable } from "../src/agents/embedded-agent-runner/run/abortable.js";
type Mode = "production" | "closure-extracted" | "closure-inline" | "synthetic-leak";
type Options = {
iters: number;
batches: number;
snapDir: string;
mode: Mode;
maxRssGrowthMb: number;
maxTrackedRetention: number;
scopeBytes: number;
quiet: boolean;
};
function parseArgs(argv: string[]): Options {
const opts: Options = {
iters: 50,
batches: 5,
snapDir: ".tmp/embedded-run-abort-leak",
mode: "production",
maxRssGrowthMb: 64,
maxTrackedRetention: 16,
scopeBytes: 2_000_000,
quiet: false,
};
for (let i = 0; i < argv.length; i += 1) {
const arg = argv[i];
const next = argv[i + 1];
switch (arg) {
case "--iters":
opts.iters = Number.parseInt(next ?? "", 10);
i += 1;
break;
case "--batches":
opts.batches = Number.parseInt(next ?? "", 10);
i += 1;
break;
case "--snap-dir":
opts.snapDir = next ?? opts.snapDir;
i += 1;
break;
case "--mode":
if (
next === "production" ||
next === "closure-extracted" ||
next === "closure-inline" ||
next === "synthetic-leak"
) {
opts.mode = next;
} else {
fail(
`--mode must be one of: production, closure-extracted, closure-inline, synthetic-leak`,
);
}
i += 1;
break;
case "--max-rss-growth-mb":
opts.maxRssGrowthMb = Number.parseInt(next ?? "", 10);
i += 1;
break;
case "--max-tracked-retention":
opts.maxTrackedRetention = Number.parseInt(next ?? "", 10);
i += 1;
break;
case "--scope-bytes":
opts.scopeBytes = Number.parseInt(next ?? "", 10);
i += 1;
break;
case "--quiet":
opts.quiet = true;
break;
case "--help":
case "-h":
printUsage();
process.exit(0);
break;
default:
fail(`Unknown arg: ${arg}`);
}
}
if (!Number.isFinite(opts.iters) || opts.iters <= 0) {
fail("--iters must be > 0");
}
if (!Number.isFinite(opts.batches) || opts.batches <= 0) {
fail("--batches must be > 0");
}
return opts;
}
function printUsage(): void {
process.stderr.write(
[
"Usage: node --import tsx --expose-gc scripts/embedded-run-abort-leak.ts [flags]",
" --mode <production|closure-extracted|closure-inline|synthetic-leak>",
" --iters N iterations per batch (default 50)",
" --batches B batches between snapshots (default 5)",
" --snap-dir DIR heap snapshot output dir (default .tmp/embedded-run-abort-leak)",
" --scope-bytes N simulated run-scope payload size (default 2_000_000)",
" --max-rss-growth-mb PASS threshold for RSS growth (default 64)",
" --max-tracked-retention PASS threshold for tracked finalizer retention (default 16)",
" --quiet only print final verdict",
"",
].join("\n"),
);
}
function fail(msg: string): never {
process.stderr.write(`error: ${msg}\n`);
process.exit(2);
}
const KEEP_ALIVE: Array<Promise<unknown>> = [];
const SYNTHETIC_LEAK_BUCKET: Uint8Array[] = [];
const FINALIZED = { count: 0 };
const finalizer = new FinalizationRegistry<number>(() => {
FINALIZED.count += 1;
});
function abortableExtracted<T>(signal: AbortSignal, promise: Promise<T>): Promise<T> {
if (signal.aborted) {
return Promise.reject(new Error("aborted"));
}
return new Promise<T>((resolve, reject) => {
const onAbort = () => {
signal.removeEventListener("abort", onAbort);
reject(new Error("aborted"));
};
signal.addEventListener("abort", onAbort, { once: true });
promise.then(
(value) => {
signal.removeEventListener("abort", onAbort);
resolve(value);
},
(err) => {
signal.removeEventListener("abort", onAbort);
reject(err);
},
);
});
}
function runOnce(mode: Mode, scopeBytes: number, iter: number): void {
const transcript = new Uint8Array(scopeBytes);
const toolMetas = [{ data: new Uint8Array(scopeBytes / 4) }];
const subscription = {
onPartialReply: (_text: string) => {
void transcript;
},
onAssistantMessageStart: () => {
void toolMetas;
},
};
finalizer.register(transcript, iter);
const ac = new AbortController();
const neverSettling = new Promise<unknown>(() => {});
KEEP_ALIVE.push(neverSettling);
if (mode === "production") {
void productionAbortable(ac.signal, neverSettling).catch(() => {});
} else if (mode === "closure-extracted") {
void abortableExtracted(ac.signal, neverSettling).catch(() => {});
} else if (mode === "closure-inline") {
const wrapped = new Promise<unknown>((resolve, reject) => {
const onAbort = () => reject(new Error("aborted"));
ac.signal.addEventListener("abort", onAbort, { once: true });
neverSettling.then(
(v) => {
void transcript;
void toolMetas;
void subscription;
resolve(v);
},
(e) => {
void transcript;
void toolMetas;
void subscription;
reject(e);
},
);
});
void wrapped.catch(() => {});
} else {
SYNTHETIC_LEAK_BUCKET.push(transcript);
}
ac.abort();
void transcript.length;
void toolMetas.length;
void subscription.onPartialReply;
}
async function settleAndGc(): Promise<void> {
for (let i = 0; i < 4; i += 1) {
await new Promise<void>((r) => setImmediate(r));
globalThis.gc?.();
}
await new Promise<void>((r) => setTimeout(r, 100));
globalThis.gc?.();
}
type SampleRow = {
label: string;
rssBytes: number;
heapUsedBytes: number;
totalIters: number;
trackedFinalized: number;
snapshotPath: string;
};
function takeSnapshot(snapDir: string, label: string): string {
fs.mkdirSync(snapDir, { recursive: true });
const filename = path.join(snapDir, `${label}-${process.pid}-${Date.now()}.heapsnapshot`);
v8.writeHeapSnapshot(filename);
return filename;
}
function fmtBytes(bytes: number): string {
return `${(bytes / 1024 / 1024).toFixed(1)}MB`;
}
async function main(): Promise<void> {
const opts = parseArgs(process.argv.slice(2));
if (typeof globalThis.gc !== "function") {
fail("--expose-gc is required (run with: node --expose-gc ...)");
}
const startedAt = Date.now();
const samples: SampleRow[] = [];
if (!opts.quiet) {
process.stdout.write(
`[harness] mode=${opts.mode} iters=${opts.iters} batches=${opts.batches} ` +
`scope=${fmtBytes(opts.scopeBytes)} pid=${process.pid}\n`,
);
}
await settleAndGc();
const baselinePath = takeSnapshot(opts.snapDir, "baseline");
const baseline: SampleRow = {
label: "baseline",
rssBytes: process.memoryUsage().rss,
heapUsedBytes: process.memoryUsage().heapUsed,
totalIters: 0,
trackedFinalized: FINALIZED.count,
snapshotPath: baselinePath,
};
samples.push(baseline);
if (!opts.quiet) {
process.stdout.write(
` baseline rss=${fmtBytes(baseline.rssBytes)} heap=${fmtBytes(baseline.heapUsedBytes)}\n`,
);
}
let totalIters = 0;
for (let b = 0; b < opts.batches; b += 1) {
for (let i = 0; i < opts.iters; i += 1) {
runOnce(opts.mode, opts.scopeBytes, totalIters);
totalIters += 1;
}
await settleAndGc();
const snapshotPath = takeSnapshot(opts.snapDir, `batch-${b}`);
const row: SampleRow = {
label: `batch-${b}`,
rssBytes: process.memoryUsage().rss,
heapUsedBytes: process.memoryUsage().heapUsed,
totalIters,
trackedFinalized: FINALIZED.count,
snapshotPath,
};
samples.push(row);
if (!opts.quiet) {
process.stdout.write(
` batch ${b} totalIters=${row.totalIters} ` +
`rss=${fmtBytes(row.rssBytes)} heap=${fmtBytes(row.heapUsedBytes)} ` +
`trackedFinalized=${row.trackedFinalized}/${row.totalIters}\n`,
);
}
}
const final = samples[samples.length - 1];
if (!final) {
fail("no samples collected");
}
const rssGrowthMb = (final.rssBytes - baseline.rssBytes) / 1024 / 1024;
// Tracked retention: how many iter-allocated transcripts are STILL alive
// (have not been finalized). Lower is better.
const trackedRetention = final.totalIters - final.trackedFinalized;
const durationSec = ((Date.now() - startedAt) / 1000).toFixed(1);
const verdict =
rssGrowthMb > opts.maxRssGrowthMb || trackedRetention > opts.maxTrackedRetention
? "FAIL"
: "PASS";
process.stdout.write(
`${verdict}: mode=${opts.mode} ` +
`rss_growth=${rssGrowthMb.toFixed(1)}MB ` +
`tracked_retention=${trackedRetention}/${final.totalIters} ` +
`duration=${durationSec}s ` +
`(thresholds: rss<${opts.maxRssGrowthMb}MB, tracked<${opts.maxTrackedRetention})\n`,
);
if (!opts.quiet) {
process.stdout.write(
`snapshots in ${opts.snapDir}/ — diff with:\n` +
` node .agents/skills/openclaw-test-heap-leaks/scripts/heapsnapshot-delta.mjs ` +
`${baseline.snapshotPath} ${final.snapshotPath} --top 30\n`,
);
}
process.exit(verdict === "PASS" ? 0 : 1);
}
main().catch((err) => {
process.stderr.write(`harness crashed: ${String(err)}\n${(err as Error)?.stack ?? ""}\n`);
process.exit(2);
});