test: tighten historical-pin checks per review of 941eb28b

- test_refined_dfg::test_source_pin runs its mismatch negative controls
  first (now including window mode) so missing history cannot skip them.
- test_re100: renamed to test_manifest_matches_its_pinned_commit, plus an
  explicit record that today's src differs from the pin.
- Structural manifest checks run before any history-dependent check.
- Real tamper test: a flipped digest raises via verify_manifest, and a
  path absent at the commit raises ValueError.
- A blobless clone (tree present, blob missing) is reported as unavailable
  history, not as a missing path.
- All history skips go through history_unavailable(): fatal when
  CELERIS_REQUIRE_HISTORY=1.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
ClaudeandClaude Opus 5.5 committed 2026-10-20 18:28:09 +00:00
1 parent f02355a2b7
commit 8064834c37
6 files changed
+72 -37

No files matched your search

+19 -6
View File
@@ -34,15 +34,28 @@ def historical_sha256(repo, commit, paths):
raise HistoryUnavailable(f"commit {commit} is not available in {repo}") from error
digests = {}
for path in paths:
try:
blob = subprocess.run([*git, "show", f"{commit}:{path}"], check=True,
capture_output=True).stdout
except subprocess.CalledProcessError as error:
raise ValueError(f"{path} is not part of {commit}") from error
digests[path] = hashlib.sha256(blob).hexdigest()
listed = subprocess.run([*git, "ls-tree", "--name-only", commit, "--", path],
capture_output=True, text=True)
if listed.returncode:
raise HistoryUnavailable(f"tree of {commit} is not available in {repo}")
if listed.stdout.strip() != path:
raise ValueError(f"{path} is not part of {commit}")
shown = subprocess.run([*git, "show", f"{commit}:{path}"], capture_output=True)
if shown.returncode: # e.g. a blobless partial clone without network access
raise HistoryUnavailable(f"content of {path} at {commit} is not available in {repo}")
digests[path] = hashlib.sha256(shown.stdout).hexdigest()
return digests
def verify_manifest(repo, commit, digests):
"""Raise RuntimeError naming the first path whose recorded digest differs at `commit`."""
actual = historical_sha256(repo, commit, digests)
for path, digest in digests.items():
if actual[path] != digest:
raise RuntimeError(f"Historical manifest mismatch at {commit}: {path}")
return actual
def historical_tree(repo, commit, prefix="src"):
"""Tracked file names under `prefix` at `commit` (HistoryUnavailable if missing)."""
historical_sha256(repo, commit, [])