3e1469a55a* 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>
93 lines
3 KiB
Python
93 lines
3 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
|
|
|
|
"""Validation endpoints for data recipe."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
from fastapi import APIRouter, HTTPException
|
|
|
|
from core.data_recipe.service import (
|
|
build_config_builder,
|
|
create_data_designer,
|
|
validate_recipe,
|
|
)
|
|
from models.data_recipe import RecipePayload, ValidateError, ValidateResponse
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
def _collect_validation_errors(recipe: dict[str, Any]) -> list[ValidateError]:
|
|
try:
|
|
from data_designer.engine.compiler import (
|
|
_add_internal_row_id_column_if_needed,
|
|
_get_allowed_references,
|
|
_resolve_and_add_seed_columns,
|
|
)
|
|
from data_designer.engine.validation import (
|
|
ViolationLevel,
|
|
validate_data_designer_config,
|
|
)
|
|
except ImportError:
|
|
return []
|
|
|
|
try:
|
|
builder = build_config_builder(recipe)
|
|
designer = create_data_designer(recipe)
|
|
resource_provider = designer._create_resource_provider( # type: ignore[attr-defined]
|
|
"validate-configuration",
|
|
builder,
|
|
)
|
|
config = builder.build()
|
|
_resolve_and_add_seed_columns(config, resource_provider.seed_reader)
|
|
_add_internal_row_id_column_if_needed(config)
|
|
violations = validate_data_designer_config(
|
|
columns = config.columns,
|
|
processor_configs = config.processors or [],
|
|
allowed_references = _get_allowed_references(config),
|
|
)
|
|
except (TypeError, ValueError, AttributeError):
|
|
return []
|
|
|
|
errors: list[ValidateError] = []
|
|
for violation in violations:
|
|
if violation.level != ViolationLevel.ERROR:
|
|
continue
|
|
code = getattr(violation.type, "value", None)
|
|
path = violation.column if violation.column else None
|
|
message = str(violation.message).strip() or "Validation failed."
|
|
errors.append(
|
|
ValidateError(
|
|
message = message,
|
|
path = path,
|
|
code = code,
|
|
)
|
|
)
|
|
return errors
|
|
|
|
|
|
@router.post("/validate", response_model = ValidateResponse)
|
|
def validate(payload: RecipePayload) -> ValidateResponse:
|
|
recipe = payload.recipe
|
|
if not recipe.get("columns"):
|
|
return ValidateResponse(
|
|
valid = False,
|
|
errors = [ValidateError(message = "Recipe must include columns.")],
|
|
)
|
|
|
|
try:
|
|
validate_recipe(recipe)
|
|
except RuntimeError as exc:
|
|
raise HTTPException(status_code = 503, detail = str(exc)) from exc
|
|
except Exception as exc:
|
|
detail = str(exc).strip() or "Validation failed."
|
|
parsed_errors = _collect_validation_errors(recipe)
|
|
return ValidateResponse(
|
|
valid = False,
|
|
errors = parsed_errors or [ValidateError(message = detail)],
|
|
raw_detail = detail,
|
|
)
|
|
|
|
return ValidateResponse(valid = True)
|