f08aef1804
* Rebuild Studio branch on top of main * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix security and code quality issues for Studio PR #4237 - Validate models_dir query param against allowed directory roots to prevent path traversal in /api/models/local endpoint - Replace string startswith() with Path.is_relative_to() for frontend path traversal check in serve_frontend - Sanitize SSE error messages to not leak exception details to clients (4 locations in inference.py) - Bind port-discovery socket to 127.0.0.1 instead of all interfaces in llama_cpp backend - Import datasets_root and resolve_output_dir in embedding training function to fix NameError and use managed output directory - Remove stale .gitignore entries for package-lock.json and test directories so tests can be tracked in version control - Add venv-reexecution logic to ui CLI command matching the studio command behavior * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Move models_dir path validation before try/except block The HTTPException(403) was inside the try/except Exception handler, so it would be caught and re-raised as a 500. Moving the validation before the try block ensures the 403 is returned directly and also makes the control flow clearer for static analysis (path is validated before any filesystem operations). * Use os.path.realpath + startswith for models_dir validation CodeQL py/path-injection does not recognize Path.is_relative_to() as a sanitizer. Switched to os.path.realpath + str.startswith which is a recognized sanitizer pattern in CodeQL's taint analysis. The startswith check uses root_str + os.sep to prevent prefix collisions (e.g. /app/models_evil matching /app/models). * Never pass user input to Path constructor in models_dir validation CodeQL traces taint through Path(resolved) even after a startswith barrier guard. Fix: the user-supplied models_dir is only used as a string for comparison against allowed roots. The Path object passed to _scan_models_dir comes from the trusted allowed_roots list, not from user input. This fully breaks the taint chain. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
77 lines
2 KiB
Python
77 lines
2 KiB
Python
#!/usr/bin/env python3
|
|
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
"""Relax strict metadata pins so pip check matches known working single-env stack.
|
|
|
|
Why:
|
|
- data-designer pins huggingface-hub>=1.0.1 and pyarrow<20.
|
|
- unsloth/transformers pins huggingface-hub<1.
|
|
- studio datasets pins pyarrow>=21.
|
|
|
|
Runtime works in this app with hub 0.36.x + pyarrow 23.x, but metadata conflicts.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import importlib.metadata as im
|
|
import re
|
|
from pathlib import Path
|
|
|
|
TARGETS = (
|
|
"data-designer",
|
|
"data-designer-engine",
|
|
"data-designer-config",
|
|
)
|
|
|
|
PATCHES: tuple[tuple[re.Pattern[str], str], ...] = (
|
|
(
|
|
re.compile(r"^Requires-Dist: huggingface-hub<2,>=1\.0\.1$", re.MULTILINE),
|
|
"Requires-Dist: huggingface-hub<2,>=0.34.0",
|
|
),
|
|
(
|
|
re.compile(r"^Requires-Dist: pyarrow<20,>=19\.0\.1$", re.MULTILINE),
|
|
"Requires-Dist: pyarrow>=21.0.0",
|
|
),
|
|
)
|
|
|
|
|
|
def metadata_path(dist_name: str) -> Path | None:
|
|
try:
|
|
dist = im.distribution(dist_name)
|
|
except im.PackageNotFoundError:
|
|
return None
|
|
for f in dist.files or []:
|
|
sf = str(f)
|
|
if sf.endswith(".dist-info/METADATA"):
|
|
return Path(dist.locate_file(f))
|
|
return None
|
|
|
|
|
|
def patch_file(path: Path) -> bool:
|
|
original = path.read_text(encoding = "utf-8")
|
|
updated = original
|
|
for pattern, repl in PATCHES:
|
|
updated = pattern.sub(repl, updated)
|
|
if updated == original:
|
|
return False
|
|
path.write_text(updated, encoding = "utf-8")
|
|
return True
|
|
|
|
|
|
def main() -> int:
|
|
changed = 0
|
|
checked = 0
|
|
for name in TARGETS:
|
|
p = metadata_path(name)
|
|
if p is None:
|
|
continue
|
|
checked += 1
|
|
if patch_file(p):
|
|
changed += 1
|
|
print(f"single-env metadata patch: checked={checked}, changed={changed}")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|