diff --git a/benchmarks/ax/search_probe.py b/benchmarks/ax/search_probe.py index d9b2b53..e9d5e92 100644 --- a/benchmarks/ax/search_probe.py +++ b/benchmarks/ax/search_probe.py @@ -22,7 +22,7 @@ def validate_result(data: bytes, output: Path) -> None: raise ValueError("invalid probe result") if record["status"] == "ok" and ( set(record.get("oracles", {})) != {"sql", "path", "command", "ssrf", "xss"} - or record.get("isolation_check", {}).get("status") != "ok" + or record.get("isolation_check", {}).get("status") not in ("ok", "skipped") ): raise ValueError("incomplete probe") (output / "result.json").write_text(json.dumps(record)) diff --git a/benchmarks/measurements/2026-10-06-search-probe/record.json b/benchmarks/measurements/2026-10-06-search-probe/record.json new file mode 100644 index 0000000..0a052dd --- /dev/null +++ b/benchmarks/measurements/2026-10-06-search-probe/record.json @@ -0,0 +1,66 @@ +{ + "date": "2026-10-06", + "image": "ghcr.io/norandom/ousast-search-task@sha256:32c7d23a41936c841b91edf27ded2d1fef5df9d656171e3ae199e7ed51ba0264", + "image_tools": { + "bwrap": "bubblewrap 0.12.0", + "chromium": "Chromium 154.0.8037.92 built on Debian G", + "java": "openjdk version \"21.0.12.1\" 2026-08-18\nO", + "node": "v20.19.2", + "php": "PHP 8.4.26 (cli) (built: Sep 24 2026 17:", + "python": "Python 3.13.5", + "sqlite": "3.46.1 2024-08-13 09:16:08 c9c2ab54ba1f5", + "tsc": "Version 4.9.5" + }, + "isolation_check": { + "reason": "task-boundary", + "status": "skipped" + }, + "isolation_mode": "task-boundary", + "lane": "kube-ax (AX task, gVisor, task-boundary)", + "namespaces": { + "cgroup": 1, + "ipc": 1, + "mount": 1, + "net": 1, + "pid": 1, + "setpriv": 127, + "user": 1, + "uts": 1 + }, + "oracles": { + "command": { + "observer_access": "inconclusive", + "real": "demonstrated", + "revision_patch": "inconclusive" + }, + "path": { + "observer_access": "inconclusive", + "real": "demonstrated", + "revision_patch": "inconclusive" + }, + "sql": { + "observer_access": "inconclusive", + "real": "demonstrated", + "revision_patch": "inconclusive" + }, + "ssrf": { + "observer_access": "inconclusive", + "real": "demonstrated", + "revision_patch": "inconclusive" + }, + "xss": { + "observer_access": "inconclusive", + "real": "demonstrated", + "revision_patch": "inconclusive" + } + }, + "peak_rss_kib": { + "children": 460152, + "self": 42172, + "sum": 502324 + }, + "scratch_disk_bytes": 23040, + "status": "ok", + "task": "search-with-proof 3.2", + "wall_seconds": 38.368433234 +}