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>
99 lines
3.2 KiB
Python
99 lines
3.2 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
|
|
|
|
"""
|
|
Dataset-related Pydantic models for API requests and responses.
|
|
"""
|
|
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
from pydantic import BaseModel, Field, model_validator
|
|
|
|
|
|
class CheckFormatRequest(BaseModel):
|
|
"""Request for dataset format check"""
|
|
|
|
dataset_name: str # HuggingFace dataset name or local path
|
|
is_vlm: bool = False
|
|
hf_token: Optional[str] = None
|
|
subset: Optional[str] = None
|
|
train_split: Optional[str] = "train"
|
|
|
|
@model_validator(mode = "before")
|
|
@classmethod
|
|
def _compat_split(cls, values: Any) -> Any:
|
|
"""Accept legacy 'split' field as alias for 'train_split'."""
|
|
if isinstance(values, dict) and "split" in values:
|
|
values.setdefault("train_split", values.pop("split"))
|
|
return values
|
|
|
|
|
|
class CheckFormatResponse(BaseModel):
|
|
"""Response for dataset format check"""
|
|
|
|
requires_manual_mapping: bool
|
|
detected_format: str
|
|
columns: List[str]
|
|
is_image: bool = False
|
|
is_audio: bool = False
|
|
multimodal_columns: Optional[List[str]] = None
|
|
suggested_mapping: Optional[Dict[str, str]] = None
|
|
detected_image_column: Optional[str] = None
|
|
detected_audio_column: Optional[str] = None
|
|
detected_text_column: Optional[str] = None
|
|
detected_speaker_column: Optional[str] = None
|
|
preview_samples: Optional[List[Dict]] = None
|
|
total_rows: Optional[int] = None
|
|
warning: Optional[str] = None
|
|
|
|
|
|
class AiAssistMappingRequest(BaseModel):
|
|
"""Request for LLM-assisted column classification (user-triggered)."""
|
|
|
|
columns: List[str]
|
|
samples: List[Dict[str, Any]] # Preview rows already loaded in the dialog
|
|
dataset_name: Optional[str] = None # For LLM context
|
|
hf_token: Optional[str] = None # For fetching dataset card
|
|
model_name: Optional[str] = None
|
|
model_type: Optional[str] = None
|
|
|
|
|
|
class AiAssistMappingResponse(BaseModel):
|
|
"""Response from LLM-assisted column classification and conversion advice."""
|
|
|
|
success: bool
|
|
suggested_mapping: Optional[Dict[str, str]] = None
|
|
warning: Optional[str] = None
|
|
# Conversion advisor fields
|
|
system_prompt: Optional[str] = None
|
|
label_mapping: Optional[Dict[str, Dict[str, str]]] = None
|
|
dataset_type: Optional[str] = None
|
|
is_conversational: Optional[bool] = None
|
|
user_notification: Optional[str] = None
|
|
|
|
|
|
class UploadDatasetResponse(BaseModel):
|
|
"""Response with stored dataset path for training."""
|
|
|
|
filename: str = Field(..., description = "Original filename")
|
|
stored_path: str = Field(..., description = "Absolute path stored on backend")
|
|
|
|
|
|
class LocalDatasetItem(BaseModel):
|
|
class Metadata(BaseModel):
|
|
actual_num_records: Optional[int] = None
|
|
target_num_records: Optional[int] = None
|
|
total_num_batches: Optional[int] = None
|
|
num_completed_batches: Optional[int] = None
|
|
columns: Optional[List[str]] = None
|
|
|
|
id: str
|
|
label: str
|
|
path: str
|
|
rows: Optional[int] = None
|
|
updated_at: Optional[float] = None
|
|
metadata: Optional[Metadata] = None
|
|
|
|
|
|
class LocalDatasetsResponse(BaseModel):
|
|
datasets: List[LocalDatasetItem] = Field(default_factory = list)
|