48740c2664
P1 #1: ``_gpu_workload_busy_for_helper`` in ``utils/datasets/llm_assist.py`` now also gates on the GGUF chat backend (llama-server) AND the safetensors chat backend. Round 23 extended it to training + export but missed Chat, so a helper / advisor GGUF could still race a loaded chat model for VRAM. Both checks fail closed when status is unverifiable. P1 #2 / #3 / #4 / #5: re-ordered the route-level GPU-handoff unloads so the diffusion release runs BEFORE the chat releases. A wedged diffusion unload used to fire AFTER chat was already gone, so the user lost both on a single failure. Drop chat last so an earlier failure preserves it. Applied to ``/training/start`` (training.py), ``/export/load`` (export.py), ``/chat/load`` GGUF branch and ``/chat/load`` safetensors branch (routes/inference.py). P1 #7 + P2 #13: ``/delete-finetuned`` body now hardens ``model_path`` and ``gguf_variant`` via the shared ``_validate_logged_identifier`` helper, so control characters and URL-form HF tokens can no longer log-line-smuggle. P1 #8 + #10: ``/delete-cached`` body hardens ``repo_id`` and ``variant`` the same way. P1 #9: ``/download-progress`` ``repo_id`` query parameter is also hardened; the value flows into log lines deep inside ``_get_repo_size_cached`` on lookup failure. P1 #11: ``CheckFormatRequest.dataset_name`` and ``AiAssistMappingRequest.{dataset_name, model_name}`` in ``models/datasets.py`` now apply the same control-char + embedded-HF-token validators, matching every other public request-body model. All 115 diffusion + training-validation + cached_gguf + export + inference model-validation tests pass locally. (P1 #6 native-path-lease enforcement for diffusion local paths and P1 #12 React Compiler frontend lint deferred -- both need focused design / frontend touchups separate from this batch.)
124 lines
4.2 KiB
Python
124 lines
4.2 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, field_validator, model_validator
|
|
|
|
# Round 24 P1 #11: reuse the chat / diffusion / export identifier
|
|
# hardening so dataset routes also reject control characters and
|
|
# URL-embedded HF tokens in user-controlled identifiers.
|
|
from models.inference import _no_control_chars, _reject_embedded_hf_token
|
|
|
|
|
|
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
|
|
|
|
@field_validator("dataset_name")
|
|
@classmethod
|
|
def _no_dataset_name_control_chars(cls, v, info):
|
|
return _no_control_chars(v, info.field_name)
|
|
|
|
@field_validator("dataset_name")
|
|
@classmethod
|
|
def _no_dataset_name_embedded_hf_tokens(cls, v, info):
|
|
return _reject_embedded_hf_token(v, info.field_name)
|
|
|
|
|
|
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
|
|
|
|
@field_validator("dataset_name", "model_name")
|
|
@classmethod
|
|
def _no_identifier_control_chars(cls, v, info):
|
|
return _no_control_chars(v, info.field_name)
|
|
|
|
@field_validator("dataset_name", "model_name")
|
|
@classmethod
|
|
def _no_identifier_embedded_hf_tokens(cls, v, info):
|
|
return _reject_embedded_hf_token(v, info.field_name)
|
|
|
|
|
|
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)
|