Skip to content

Harden verify_sources cache handling #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ikeige-coder merged 1 commit into from
Oct 5, 2026
Merged

Harden verify_sources cache handling #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 10 additions & 3 deletions excore/sources.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,8 +70,10 @@ def verify_sources(lock: dict, root: str | Path, *, cache: str | Path | None = N
seen: dict = {}
if cache and Path(cache).exists():
try:
seen = json.loads(Path(cache).read_text())
except (OSError, json.JSONDecodeError):
seen = json.loads(Path(cache).read_text(encoding="utf-8"))
except (OSError, ValueError):
seen = {}
if not isinstance(seen, dict): # valid JSON of the wrong shape is treated as empty
seen = {}
new_seen = {}
for f in lock["sources"]["base"]["files"]:
Expand All @@ -90,7 +92,12 @@ def verify_sources(lock: dict, root: str | Path, *, cache: str | Path | None = N
continue
new_seen[f["name"]] = key
if cache and not problems:
Path(cache).write_text(json.dumps(new_seen))
try:
tmp = Path(str(cache) + ".tmp")
tmp.write_text(json.dumps(new_seen), encoding="utf-8")
os.replace(tmp, cache)
except OSError:
pass # the cache only saves re-hashing; never fail verification over it
return problems


Expand Down
16 changes: 16 additions & 0 deletions tests/test_cli_plots_sources.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,6 +152,22 @@ def test_pin_verify_and_tamper(lock_and_model):
load_lock(lock, track="GPU-01")


@pytest.mark.parametrize("junk", ["[]", "null", "42", "not json", "\udcff"])
def test_verify_ignores_malformed_cache(lock_and_model, junk):
lock, models = lock_and_model
pin(lock, models, repo="org/m", revision="r1", files=["base-bf16.gguf"], llama_cpp_commit="a" * 40)
cache = lock.parent / "verified.json"
cache.write_bytes(junk.encode("utf-8", "surrogateescape"))
assert verify_sources(load_lock(lock), models, cache=cache) == []
assert isinstance(json.loads(cache.read_text(encoding="utf-8")), dict) # rewritten cleanly


def test_verify_survives_unwritable_cache(lock_and_model):
lock, models = lock_and_model
pin(lock, models, repo="org/m", revision="r1", files=["base-bf16.gguf"], llama_cpp_commit="a" * 40)
assert verify_sources(load_lock(lock), models, cache=lock.parent / "no-such-dir" / "verified.json") == []


def test_sources_cli(lock_and_model, tiny_config):
lock, models = lock_and_model
assert main(["--config", tiny_config, "sources", "verify", "--lock", str(lock), "--root", str(models)]) == 1
Expand Down
Loading