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>
134 lines
4.1 KiB
Python
134 lines
4.1 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
|
|
|
|
"""
|
|
Unified core module for Unsloth backend
|
|
|
|
Imports are LAZY (via __getattr__) so that training subprocesses can
|
|
import core.training.worker without pulling in heavy ML dependencies
|
|
like unsloth, transformers, or torch before the version activation
|
|
code has a chance to run.
|
|
"""
|
|
|
|
__all__ = [
|
|
# Inference
|
|
"InferenceBackend",
|
|
"get_inference_backend",
|
|
# Training
|
|
"get_training_backend",
|
|
"TrainingBackend",
|
|
"TrainingProgress",
|
|
# Config
|
|
"ModelConfig",
|
|
"is_vision_model",
|
|
"scan_trained_loras",
|
|
"load_model_defaults",
|
|
"get_base_model_from_lora",
|
|
# Utils
|
|
"format_and_template_dataset",
|
|
"normalize_path",
|
|
"is_local_path",
|
|
"is_model_cached",
|
|
"without_hf_auth",
|
|
"format_error_message",
|
|
"get_gpu_memory_info",
|
|
"log_gpu_memory",
|
|
"get_device",
|
|
"is_apple_silicon",
|
|
"clear_gpu_cache",
|
|
"DeviceType",
|
|
]
|
|
|
|
|
|
def __getattr__(name):
|
|
# Inference
|
|
if name in ("InferenceBackend", "get_inference_backend"):
|
|
from .inference import InferenceBackend, get_inference_backend
|
|
|
|
globals()["InferenceBackend"] = InferenceBackend
|
|
globals()["get_inference_backend"] = get_inference_backend
|
|
return globals()[name]
|
|
|
|
# Training
|
|
if name in ("TrainingBackend", "get_training_backend", "TrainingProgress"):
|
|
from .training import TrainingBackend, get_training_backend, TrainingProgress
|
|
|
|
globals()["TrainingBackend"] = TrainingBackend
|
|
globals()["get_training_backend"] = get_training_backend
|
|
globals()["TrainingProgress"] = TrainingProgress
|
|
return globals()[name]
|
|
|
|
# Config (from utils.models)
|
|
if name in (
|
|
"is_vision_model",
|
|
"ModelConfig",
|
|
"scan_trained_loras",
|
|
"load_model_defaults",
|
|
"get_base_model_from_lora",
|
|
):
|
|
from utils.models import (
|
|
is_vision_model,
|
|
ModelConfig,
|
|
scan_trained_loras,
|
|
load_model_defaults,
|
|
get_base_model_from_lora,
|
|
)
|
|
|
|
globals()["is_vision_model"] = is_vision_model
|
|
globals()["ModelConfig"] = ModelConfig
|
|
globals()["scan_trained_loras"] = scan_trained_loras
|
|
globals()["load_model_defaults"] = load_model_defaults
|
|
globals()["get_base_model_from_lora"] = get_base_model_from_lora
|
|
return globals()[name]
|
|
|
|
# Paths
|
|
if name in ("normalize_path", "is_local_path", "is_model_cached"):
|
|
from utils.paths import normalize_path, is_local_path, is_model_cached
|
|
|
|
globals()["normalize_path"] = normalize_path
|
|
globals()["is_local_path"] = is_local_path
|
|
globals()["is_model_cached"] = is_model_cached
|
|
return globals()[name]
|
|
|
|
# Utils
|
|
if name in ("without_hf_auth", "format_error_message"):
|
|
from utils.utils import without_hf_auth, format_error_message
|
|
|
|
globals()["without_hf_auth"] = without_hf_auth
|
|
globals()["format_error_message"] = format_error_message
|
|
return globals()[name]
|
|
|
|
# Hardware
|
|
if name in (
|
|
"get_device",
|
|
"is_apple_silicon",
|
|
"clear_gpu_cache",
|
|
"get_gpu_memory_info",
|
|
"log_gpu_memory",
|
|
"DeviceType",
|
|
):
|
|
from utils.hardware import (
|
|
get_device,
|
|
is_apple_silicon,
|
|
clear_gpu_cache,
|
|
get_gpu_memory_info,
|
|
log_gpu_memory,
|
|
DeviceType,
|
|
)
|
|
|
|
globals()["get_device"] = get_device
|
|
globals()["is_apple_silicon"] = is_apple_silicon
|
|
globals()["clear_gpu_cache"] = clear_gpu_cache
|
|
globals()["get_gpu_memory_info"] = get_gpu_memory_info
|
|
globals()["log_gpu_memory"] = log_gpu_memory
|
|
globals()["DeviceType"] = DeviceType
|
|
return globals()[name]
|
|
|
|
# Datasets
|
|
if name == "format_and_template_dataset":
|
|
from utils.datasets import format_and_template_dataset
|
|
|
|
globals()["format_and_template_dataset"] = format_and_template_dataset
|
|
return format_and_template_dataset
|
|
|
|
raise AttributeError(f"module 'core' has no attribute {name!r}")
|