marius/Open_Ultra_SAST
1
0
Fork 0
mirror of https://github.com/norandom/OpenUltraSAST.git synced 2026-10-16 11:49:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

unseen-eval: calibrated replay deadline + native agreement check, docker-lane diagnostics, proof 4.4 record; engine runner cleans up fetched sources

Browse Source 
gVisor replays exhausted the hook's 30 s deadline in the snapshot step on a
1,725-file repository; cluster replays now use 30 s x a measured slowdown
factor, verified on a native sample. The engine runner deletes each pin's fetched
source (1.8 GB had accumulated), caps the cache at 500 MB and refuses below
1.5 GB free. Proof 4.4: two engine pins via the generic dispatcher match the VM
baseline exactly. Implemented with Codex.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
Marius Ciepluch
2026-10-05 08:14:57 +02:00
co-authored by Claude Opus 5.5
parent 5dc86c2f3f
commit 6d27c9bfcf
13 changed files with 976 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_unseen_proof.py
+30
View File
@@ -54,3 +54,33 @@ def test_engine_proof_counts_differences_without_names(tmp_path):
(baseline / f"{i}.json").write_text(json.dumps(record))
proof = p.engine_proof(current, baseline)
assert proof["differences"] == 0 and "synthetic" not in json.dumps(proof)
@pytest.mark.parametrize("executed", [2, 3])
def test_engine_proof_counts_only_executed_records(tmp_path, executed):
current, baseline = tmp_path / "current", tmp_path / "baseline"
current.mkdir()
baseline.mkdir()
(current / "progress.json").write_text(json.dumps({"completed": executed}))
for i in range(executed + 4):
record = {
"repo": "synthetic",
"pin": str(i),
"done": True,
"seconds": 20 if i < executed else 0,
"units": [{"unit": "unsupported", "status": "unsupported"}],
}
if i < executed:
record["units"].append(
{"unit": "executed", "status": "path", "instrument": {"bytes": 20, "jvm": [{"seconds": 8, "success": True}]}}
)
(baseline / f"{i}.json").write_text(json.dumps(record))
(current / f"{i}.json").write_text(json.dumps(record))
if executed == 3:
with pytest.raises(ValueError, match="engine proof requires exactly two pins"):
p.engine_proof(current, baseline)
else:
proof = p.engine_proof(current, baseline)
assert len(proof["pins"]) == 2
assert proof["differences"] == 0