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>
89 lines
2.5 KiB
Python
89 lines
2.5 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
"""
|
|
Path utilities for model and dataset handling
|
|
"""
|
|
|
|
import os
|
|
from pathlib import Path
|
|
from typing import Optional
|
|
import structlog
|
|
from loggers import get_logger
|
|
|
|
logger = get_logger(__name__)
|
|
|
|
|
|
def normalize_path(path: str) -> str:
|
|
"""
|
|
Convert Windows paths to WSL format if needed.
|
|
|
|
Examples:
|
|
C:\\Users\\... -> /mnt/c/Users/...
|
|
/home/user/... -> /home/user/... (unchanged)
|
|
"""
|
|
if not path:
|
|
return path
|
|
|
|
# Handle Windows drive letters (C:\\ or c:\\)
|
|
if len(path) >= 3 and path[1] == ":" and path[2] in ("\\", "/"):
|
|
drive = path[0].lower()
|
|
rest = path[3:].replace("\\", "/")
|
|
return f"/mnt/{drive}/{rest}"
|
|
|
|
# Already Unix-style or relative
|
|
return path.replace("\\", "/")
|
|
|
|
|
|
def is_local_path(path: str) -> bool:
|
|
"""
|
|
Check if path is a local filesystem path vs HuggingFace model identifier.
|
|
|
|
Examples:
|
|
True: /home/user/model, C:\\models, ./model, ~/model
|
|
False: unsloth/llama-3.1-8b, microsoft/phi-2
|
|
"""
|
|
if not path:
|
|
return False
|
|
|
|
# If it exists on disk, treat as local (covers relative paths like "outputs/foo").
|
|
try:
|
|
if Path(normalize_path(path)).expanduser().exists():
|
|
return True
|
|
except Exception:
|
|
pass
|
|
|
|
# Obvious HF patterns
|
|
if path.count("/") == 1 and not path.startswith(("/", ".", "~")):
|
|
return False # Looks like org/model format
|
|
|
|
# Filesystem indicators
|
|
return (
|
|
path.startswith(("/", ".", "~")) # Unix absolute/relative
|
|
or ":" in path # Windows drive or URL
|
|
or "\\" in path # Windows separator
|
|
or os.path.isabs(path) # System-absolute
|
|
)
|
|
|
|
|
|
def get_cache_path(model_name: str) -> Optional[Path]:
|
|
"""Get HuggingFace cache path for a model if it exists."""
|
|
cache_dir = Path.home() / ".cache" / "huggingface" / "hub"
|
|
model_cache_name = model_name.replace("/", "--")
|
|
model_cache_path = cache_dir / f"models--{model_cache_name}"
|
|
|
|
return model_cache_path if model_cache_path.exists() else None
|
|
|
|
|
|
def is_model_cached(model_name: str) -> bool:
|
|
"""Check if model is downloaded in HuggingFace cache."""
|
|
cache_path = get_cache_path(model_name)
|
|
if not cache_path:
|
|
return False
|
|
|
|
# Check for actual model files
|
|
for suffix in [".safetensors", ".bin", ".json"]:
|
|
if list(cache_path.rglob(f"*{suffix}")):
|
|
return True
|
|
|
|
return False
|