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>
82 lines
2.3 KiB
Python
82 lines
2.3 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
|
|
|
|
"""
|
|
Pydantic schemas for Data Recipe (DataDesigner) API.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
|
|
class RecipePayload(BaseModel):
|
|
recipe: dict[str, Any] = Field(default_factory = dict)
|
|
run: dict[str, Any] | None = None
|
|
ui: dict[str, Any] | None = None
|
|
|
|
|
|
class PreviewResponse(BaseModel):
|
|
dataset: list[dict[str, Any]] = Field(default_factory = list)
|
|
processor_artifacts: dict[str, Any] | None = None
|
|
analysis: dict[str, Any] | None = None
|
|
|
|
|
|
class ValidateError(BaseModel):
|
|
message: str
|
|
path: str | None = None
|
|
code: str | None = None
|
|
|
|
|
|
class ValidateResponse(BaseModel):
|
|
valid: bool
|
|
errors: list[ValidateError] = Field(default_factory = list)
|
|
raw_detail: str | None = None
|
|
|
|
|
|
class JobCreateResponse(BaseModel):
|
|
job_id: str
|
|
|
|
|
|
class SeedInspectRequest(BaseModel):
|
|
dataset_name: str = Field(min_length = 1)
|
|
hf_token: str | None = None
|
|
subset: str | None = None
|
|
split: str | None = "train"
|
|
preview_size: int = Field(default = 10, ge = 1, le = 50)
|
|
|
|
|
|
class SeedInspectUploadRequest(BaseModel):
|
|
filename: str = Field(min_length = 1)
|
|
content_base64: str = Field(min_length = 1)
|
|
preview_size: int = Field(default = 10, ge = 1, le = 50)
|
|
seed_source_type: str | None = None
|
|
unstructured_chunk_size: int | None = Field(default = None, ge = 1, le = 20000)
|
|
unstructured_chunk_overlap: int | None = Field(default = None, ge = 0, le = 20000)
|
|
|
|
|
|
class SeedInspectResponse(BaseModel):
|
|
dataset_name: str
|
|
resolved_path: str
|
|
columns: list[str] = Field(default_factory = list)
|
|
preview_rows: list[dict[str, Any]] = Field(default_factory = list)
|
|
split: str | None = None
|
|
subset: str | None = None
|
|
|
|
|
|
class McpToolsListRequest(BaseModel):
|
|
mcp_providers: list[dict[str, Any]] = Field(default_factory = list)
|
|
timeout_sec: float | None = Field(default = None, gt = 0)
|
|
|
|
|
|
class McpToolsProviderResult(BaseModel):
|
|
name: str
|
|
tools: list[str] = Field(default_factory = list)
|
|
error: str | None = None
|
|
|
|
|
|
class McpToolsListResponse(BaseModel):
|
|
providers: list[McpToolsProviderResult] = Field(default_factory = list)
|
|
duplicate_tools: dict[str, list[str]] = Field(default_factory = dict)
|