test: final source recheck for V1 jet CV and V3 Taylor-Green runs

Both runners now re-derive the recorded source identity after the run
(source_provenance.final_source_check) and only then mark the receipt
complete. A changed source, or a recheck that fails, rewrites the receipt
as invalid and raises:
- V1: in-run receipts carry run_status=INCOMPLETE; finish_receipt sets
  COMPLETE or INVALID_SOURCE_CHANGED (+ source_recheck/source_after).
- V3: completed stays False, invalid=SOURCE_CHANGED_DURING_RUN, no
  screening_pass; the assessor requires source_recheck UNCHANGED (frozen
  mode still accepts receipts from before the field existed).
Interrupted runs keep INCOMPLETE / completed=False. Host tests cover
unchanged, changed and failed rechecks and incomplete runs. No threshold
or solver change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
ClaudeandClaude Opus 5.5 committed 2026-10-20 18:44:23 +00:00
1 parent 8cae58cdf1
commit df0f586331
7 files changed
+159 -15

No files matched your search

+35
View File
@@ -196,5 +196,40 @@ class Host(unittest.TestCase):
self.assertTrue(record["src_sha256"])
def test_final_source_recheck_completes_or_invalidates_receipt(self):
import json
import tempfile
import run_jet_circle_cv as v
recorded = dict(source_mode="current_checkout", checkout_revision="a" * 40,
checkout_dirty=False, src_tree="b" * 40)
payload = dict(status="PILOT_DIAGNOSTIC_ONLY", run_status="INCOMPLETE", windows=[1, 2])
with tempfile.TemporaryDirectory() as d:
path = Path(d) / "re100_s1.json"
path.write_text(json.dumps(payload))
done = v.finish_receipt(path, payload, recorded, lambda: dict(recorded))
self.assertEqual(json.loads(path.read_text()), done)
self.assertEqual((done["run_status"], done["source_recheck"]), ("COMPLETE", "UNCHANGED"))
for recheck, after in ((lambda: dict(recorded, checkout_dirty=True), True),
(lambda: v.verify(Path(d)), None)):
path.write_text(json.dumps(payload))
with self.assertRaisesRegex(RuntimeError, "Source changed during the run"):
v.finish_receipt(path, payload, recorded, recheck)
bad = json.loads(path.read_text())
self.assertEqual((bad["run_status"], bad["source_recheck"]),
("INVALID_SOURCE_CHANGED", "CHANGED"))
self.assertEqual(bad["source_after"] is None, after is None)
self.assertEqual(bad["windows"], [1, 2])
self.assertFalse(Path(str(path) + ".tmp").exists())
def test_receipts_written_during_the_run_are_incomplete(self):
"""Static check (run_case needs CUDA): the in-run payload is INCOMPLETE and only
main() -> finish_receipt can mark it COMPLETE."""
import inspect
import run_jet_circle_cv as v
self.assertIn('run_status="INCOMPLETE"', inspect.getsource(v.run_case))
self.assertNotIn("COMPLETE\"", inspect.getsource(v.run_case).replace("INCOMPLETE\"", ""))
self.assertIn("finish_receipt(", inspect.getsource(v.main))
if __name__ == "__main__":
unittest.main()
@@ -111,3 +111,20 @@ def test_historical_files_reports_unreadable_blob_as_history_unavailable(tmp_pat
with pytest.raises(HistoryUnavailable, match="blob not in this clone"):
source_provenance.historical_files(ROOT, ORIGIN, ["src/a.py"], tmp_path)
assert not (tmp_path / "src/a.py").exists()
def test_final_source_check_unchanged_changed_and_failed_recheck():
from source_provenance import final_source_check
recorded = dict(revision="a" * 40, dirty=False)
assert final_source_check(recorded, lambda: dict(recorded)) == dict(source_recheck="UNCHANGED")
changed = final_source_check(recorded, lambda: dict(recorded, dirty=True))
assert changed == dict(source_recheck="CHANGED", source_after=dict(recorded, dirty=True),
source_recheck_error=None)
def fails():
raise RuntimeError("Source hash mismatch: src/x.py")
failed = final_source_check(recorded, fails)
assert (failed["source_recheck"], failed["source_after"]) == ("CHANGED", None)
assert "Source hash mismatch" in failed["source_recheck_error"]