mirror of
https://github.com/langgenius/dify.git
synced 2026-11-12 14:21:29 +08:00
JyongandClaude Fable 5.2
7d6c1845b8
Add a shared file malware-scanning module and use it in the Classic Knowledge Base, RAG Pipeline local files and the Agent Knowledge Base. - core/file_scan: scanner adapters for ClamAV (deployment-configured), Cloudmersive, Scanii, OPSWAT MetaDefender Cloud and API-based extensions (new `file.malware_scan` extension point). - services/file_scan: FileScanService is the single entry point other modules call. Providers are workspace-wide; a policy belongs to a scope (dataset, knowledge_fs_space), so further modules can adopt scanning without schema changes. - Each file is scanned on its own: a rejected file fails only its own document. Malware always blocks and deletes the stored original; invalid credentials and exhausted quota stop processing regardless of the "allow" fallback. - Console: workspace scanner management and a per-knowledge-base policy section in both settings forms; the Agent Knowledge Base upload keeps going after a rejected file and explains each failure. - Off by default behind FILE_SCAN_ENABLED. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
38 lines
1.3 KiB
Python
38 lines
1.3 KiB
Python
import enum
|
|
from datetime import datetime
|
|
from uuid import uuid4
|
|
|
|
import sqlalchemy as sa
|
|
from sqlalchemy import DateTime, String, func
|
|
from sqlalchemy.orm import Mapped, mapped_column
|
|
|
|
from .base import TypeBase
|
|
from .types import LongText, StringUUID
|
|
|
|
|
|
class APIBasedExtensionPoint(enum.StrEnum):
|
|
APP_EXTERNAL_DATA_TOOL_QUERY = "app.external_data_tool.query"
|
|
PING = "ping"
|
|
APP_MODERATION_INPUT = "app.moderation.input"
|
|
APP_MODERATION_OUTPUT = "app.moderation.output"
|
|
FILE_MALWARE_SCAN = "file.malware_scan"
|
|
|
|
|
|
class APIBasedExtension(TypeBase):
|
|
__tablename__ = "api_based_extensions"
|
|
__table_args__ = (
|
|
sa.PrimaryKeyConstraint("id", name="api_based_extension_pkey"),
|
|
sa.Index("api_based_extension_tenant_idx", "tenant_id"),
|
|
)
|
|
|
|
id: Mapped[str] = mapped_column(
|
|
StringUUID, insert_default=lambda: str(uuid4()), default_factory=lambda: str(uuid4()), init=False
|
|
)
|
|
tenant_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
|
|
name: Mapped[str] = mapped_column(String(255), nullable=False)
|
|
api_endpoint: Mapped[str] = mapped_column(String(255), nullable=False)
|
|
api_key: Mapped[str] = mapped_column(LongText, nullable=False)
|
|
created_at: Mapped[datetime] = mapped_column(
|
|
DateTime, nullable=False, server_default=func.current_timestamp(), init=False
|
|
)
|