Merge commit '657eeb65' into sandboxed-agent-rebase

Made-with: Cursor

# Conflicts:
#	api/core/agent/cot_chat_agent_runner.py
#	api/core/agent/fc_agent_runner.py
#	api/core/memory/token_buffer_memory.py
#	api/core/variables/segments.py
#	api/core/workflow/file/file_manager.py
#	api/core/workflow/nodes/agent/agent_node.py
#	api/core/workflow/nodes/llm/llm_utils.py
#	api/core/workflow/nodes/parameter_extractor/parameter_extractor_node.py
#	api/core/workflow/workflow_entry.py
#	api/factories/variable_factory.py
#	api/pyproject.toml
#	api/services/variable_truncator.py
#	api/uv.lock
#	web/app/components/app/app-publisher/index.tsx
#	web/app/components/app/overview/settings/index.tsx
#	web/app/components/apps/app-card.tsx
#	web/app/components/apps/index.tsx
#	web/app/components/apps/list.tsx
#	web/app/components/base/chat/chat-with-history/header-in-mobile.tsx
#	web/app/components/base/features/new-feature-panel/conversation-opener/modal.tsx
#	web/app/components/base/features/new-feature-panel/file-upload/setting-content.tsx
#	web/app/components/base/features/new-feature-panel/moderation/moderation-setting-modal.tsx
#	web/app/components/base/features/new-feature-panel/text-to-speech/param-config-content.tsx
#	web/app/components/base/message-log-modal/index.tsx
#	web/app/components/base/switch/index.tsx
#	web/app/components/base/tab-slider-plain/index.tsx
#	web/app/components/explore/try-app/app-info/index.tsx
#	web/app/components/plugins/plugin-detail-panel/tool-selector/components/reasoning-config-form.tsx
#	web/app/components/workflow/nodes/llm/components/json-schema-config-modal/visual-editor/edit-card/required-switch.tsx
#	web/app/components/workflow/nodes/llm/panel.tsx
#	web/contract/router.ts
#	web/eslint-suppressions.json
#	web/i18n/fa-IR/workflow.json

api/core/agent/base_agent_runner.py

@@ -17,7 +17,6 @@ from core.app.entities.app_invoke_entities import (
 )
 from core.callback_handler.agent_tool_callback_handler import DifyAgentCallbackHandler
 from core.callback_handler.index_tool_callback_handler import DatasetIndexToolCallbackHandler
-from core.file import file_manager
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities import (
@@ -40,6 +39,7 @@ from core.tools.entities.tool_entities import (
 )
 from core.tools.tool_manager import ToolManager
 from core.tools.utils.dataset_retriever_tool import DatasetRetrieverTool
+from core.workflow.file import file_manager
 from extensions.ext_database import db
 from factories import file_factory
 from models.enums import CreatorUserRole

api/core/app/app_config/entities.py

@@ -5,9 +5,9 @@ from typing import Any, Literal
 from jsonschema import Draft7Validator, SchemaError
 from pydantic import BaseModel, Field, field_validator
 
-from core.file import FileTransferMethod, FileType, FileUploadConfig
 from core.model_runtime.entities.llm_entities import LLMMode
 from core.model_runtime.entities.message_entities import PromptMessageRole
+from core.workflow.file import FileTransferMethod, FileType, FileUploadConfig
 from models.model import AppMode
 
 

api/core/app/app_config/features/file_upload/manager.py

@@ -2,7 +2,7 @@ from collections.abc import Mapping
 from typing import Any
 
 from constants import DEFAULT_FILE_NUMBER_LIMITS
-from core.file import FileUploadConfig
+from core.workflow.file import FileUploadConfig
 
 
 class FileUploadConfigManager:

api/core/app/apps/base_app_generator.py

@@ -5,8 +5,8 @@ from sqlalchemy.orm import Session
 
 from core.app.app_config.entities import VariableEntityType
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.file import File, FileUploadConfig
 from core.workflow.enums import NodeType
+from core.workflow.file import File, FileUploadConfig
 from core.workflow.repositories.draft_variable_repository import (
     DraftVariableSaver,
     DraftVariableSaverFactory,

api/core/app/apps/base_app_queue_manager.py

@@ -2,7 +2,7 @@ import logging
 import queue
 import threading
 import time
-from abc import abstractmethod
+from abc import ABC, abstractmethod
 from enum import IntEnum, auto
 from typing import Any
 
@@ -31,7 +31,7 @@ class PublishFrom(IntEnum):
     TASK_PIPELINE = auto()
 
 
-class AppQueueManager:
+class AppQueueManager(ABC):
     def __init__(self, task_id: str, user_id: str, invoke_from: InvokeFrom):
         if not user_id:
             raise ValueError("user is required")
@@ -133,7 +133,7 @@ class AppQueueManager:
         self._publish(event, pub_from)
 
     @abstractmethod
-    def _publish(self, event: AppQueueEvent, pub_from: PublishFrom):
+    def _publish(self, event: AppQueueEvent, pub_from: PublishFrom) -> None:
         """
         Publish event to queue
         :param event:

api/core/app/apps/base_app_runner.py

@@ -22,7 +22,6 @@ from core.app.entities.queue_entities import (
 from core.app.features.annotation_reply.annotation_reply import AnnotationReplyFeature
 from core.app.features.hosting_moderation.hosting_moderation import HostingModerationFeature
 from core.external_data_tool.external_data_fetch import ExternalDataFetch
-from core.file.enums import FileTransferMethod, FileType
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
@@ -39,12 +38,13 @@ from core.prompt.advanced_prompt_transform import AdvancedPromptTransform
 from core.prompt.entities.advanced_prompt_entities import ChatModelMessage, CompletionModelPromptTemplate, MemoryConfig
 from core.prompt.simple_prompt_transform import ModelMode, SimplePromptTransform
 from core.tools.tool_file_manager import ToolFileManager
+from core.workflow.file.enums import FileTransferMethod, FileType
 from extensions.ext_database import db
 from models.enums import CreatorUserRole
 from models.model import App, AppMode, Message, MessageAnnotation, MessageFile
 
 if TYPE_CHECKING:
-    from core.file.models import File
+    from core.workflow.file.models import File
 
 _logger = logging.getLogger(__name__)
 

api/core/app/apps/chat/app_runner.py

@@ -11,12 +11,12 @@ from core.app.entities.app_invoke_entities import (
 )
 from core.app.entities.queue_entities import QueueAnnotationReplyEvent
 from core.callback_handler.index_tool_callback_handler import DatasetIndexToolCallbackHandler
-from core.file import File
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.message_entities import ImagePromptMessageContent
 from core.moderation.base import ModerationError
 from core.rag.retrieval.dataset_retrieval import DatasetRetrieval
+from core.workflow.file import File
 from extensions.ext_database import db
 from models.model import App, Conversation, Message
 

api/core/app/apps/common/workflow_response_converter.py

@@ -45,7 +45,6 @@ from core.app.entities.task_entities import (
     WorkflowPauseStreamResponse,
     WorkflowStartStreamResponse,
 )
-from core.file import FILE_MODEL_IDENTITY, File
 from core.plugin.impl.datasource import PluginDatasourceManager
 from core.tools.entities.tool_entities import ToolProviderType
 from core.tools.tool_manager import ToolManager
@@ -60,6 +59,7 @@ from core.workflow.enums import (
     WorkflowNodeExecutionMetadataKey,
     WorkflowNodeExecutionStatus,
 )
+from core.workflow.file import FILE_MODEL_IDENTITY, File
 from core.workflow.runtime import GraphRuntimeState
 from core.workflow.system_variable import SystemVariable
 from core.workflow.workflow_entry import WorkflowEntry

api/core/app/apps/completion/app_runner.py

@@ -10,11 +10,11 @@ from core.app.entities.app_invoke_entities import (
     CompletionAppGenerateEntity,
 )
 from core.callback_handler.index_tool_callback_handler import DatasetIndexToolCallbackHandler
-from core.file import File
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.message_entities import ImagePromptMessageContent
 from core.moderation.base import ModerationError
 from core.rag.retrieval.dataset_retrieval import DatasetRetrieval
+from core.workflow.file import File
 from extensions.ext_database import db
 from models.model import App, Message
 

api/core/app/entities/app_invoke_entities.py

@@ -7,8 +7,8 @@ from pydantic import BaseModel, ConfigDict, Field, ValidationInfo, field_validat
 from constants import UUID_NIL
 from core.app.app_config.entities import EasyUIBasedAppConfig, WorkflowUIBasedAppConfig
 from core.entities.provider_configuration import ProviderModelBundle
-from core.file import File, FileUploadConfig
 from core.model_runtime.entities.model_entities import AIModelEntity
+from core.workflow.file import File, FileUploadConfig
 
 if TYPE_CHECKING:
     from core.ops.ops_trace_manager import TraceQueueManager

api/core/app/task_pipeline/easy_ui_based_generate_task_pipeline.py

@@ -46,8 +46,6 @@ from core.app.entities.task_entities import (
 from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
 from core.app.task_pipeline.message_cycle_manager import MessageCycleManager
 from core.base.tts import AppGeneratorTTSPublisher, AudioTrunk
-from core.file import helpers as file_helpers
-from core.file.enums import FileTransferMethod
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from core.model_runtime.entities.message_entities import (
@@ -60,6 +58,8 @@ from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
 from core.prompt.utils.prompt_message_util import PromptMessageUtil
 from core.prompt.utils.prompt_template_parser import PromptTemplateParser
 from core.tools.signature import sign_tool_file
+from core.workflow.file import helpers as file_helpers
+from core.workflow.file.enums import FileTransferMethod
 from events.message_event import message_was_created
 from extensions.ext_database import db
 from libs.datetime_utils import naive_utc_now

api/core/app/workflow/file_runtime.py

@@ -0,0 +1,47 @@
+from __future__ import annotations
+
+from collections.abc import Generator
+
+from configs import dify_config
+from core.helper.ssrf_proxy import ssrf_proxy
+from core.tools.signature import sign_tool_file
+from core.workflow.file.protocols import HttpResponseProtocol, WorkflowFileRuntimeProtocol
+from core.workflow.file.runtime import set_workflow_file_runtime
+from extensions.ext_storage import storage
+
+
+class DifyWorkflowFileRuntime(WorkflowFileRuntimeProtocol):
+    """Production runtime wiring for ``core.workflow.file``."""
+
+    @property
+    def files_url(self) -> str:
+        return dify_config.FILES_URL
+
+    @property
+    def internal_files_url(self) -> str | None:
+        return dify_config.INTERNAL_FILES_URL
+
+    @property
+    def secret_key(self) -> str:
+        return dify_config.SECRET_KEY
+
+    @property
+    def files_access_timeout(self) -> int:
+        return dify_config.FILES_ACCESS_TIMEOUT
+
+    @property
+    def multimodal_send_format(self) -> str:
+        return dify_config.MULTIMODAL_SEND_FORMAT
+
+    def http_get(self, url: str, *, follow_redirects: bool = True) -> HttpResponseProtocol:
+        return ssrf_proxy.get(url, follow_redirects=follow_redirects)
+
+    def storage_load(self, path: str, *, stream: bool = False) -> bytes | Generator:
+        return storage.load(path, stream=stream)
+
+    def sign_tool_file(self, *, tool_file_id: str, extension: str, for_external: bool = True) -> str:
+        return sign_tool_file(tool_file_id=tool_file_id, extension=extension, for_external=for_external)
+
+
+def bind_dify_workflow_file_runtime() -> None:
+    set_workflow_file_runtime(DifyWorkflowFileRuntime())

api/core/app/workflow/node_factory.py

@@ -4,7 +4,6 @@ from typing import TYPE_CHECKING, final
 from typing_extensions import override
 
 from configs import dify_config
-from core.file.file_manager import file_manager
 from core.helper.code_executor.code_executor import CodeExecutor
 from core.helper.code_executor.code_node_provider import CodeNodeProvider
 from core.helper.ssrf_proxy import ssrf_proxy
@@ -12,10 +11,12 @@ from core.rag.retrieval.dataset_retrieval import DatasetRetrieval
 from core.tools.tool_file_manager import ToolFileManager
 from core.workflow.entities.graph_config import NodeConfigDict
 from core.workflow.enums import NodeType
+from core.workflow.file.file_manager import file_manager
 from core.workflow.graph.graph import NodeFactory
 from core.workflow.nodes.base.node import Node
 from core.workflow.nodes.code.code_node import CodeNode
 from core.workflow.nodes.code.limits import CodeNodeLimits
+from core.workflow.nodes.document_extractor import DocumentExtractorNode, UnstructuredApiConfig
 from core.workflow.nodes.http_request.node import HttpRequestNode
 from core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node import KnowledgeRetrievalNode
 from core.workflow.nodes.node_mapping import LATEST_VERSION, NODE_TYPE_CLASSES_MAPPING
@@ -44,7 +45,6 @@ class DifyNodeFactory(NodeFactory):
         self,
         graph_init_params: "GraphInitParams",
         graph_runtime_state: "GraphRuntimeState",
-        *,
         code_executor: type[CodeExecutor] | None = None,
         code_providers: Sequence[type[CodeNodeProvider]] | None = None,
         code_limits: CodeNodeLimits | None = None,
@@ -53,6 +53,7 @@ class DifyNodeFactory(NodeFactory):
         http_request_http_client: HttpClientProtocol | None = None,
         http_request_tool_file_manager_factory: Callable[[], ToolFileManager] = ToolFileManager,
         http_request_file_manager: FileManagerProtocol | None = None,
+        document_extractor_unstructured_api_config: UnstructuredApiConfig | None = None,
     ) -> None:
         self.graph_init_params = graph_init_params
         self.graph_runtime_state = graph_runtime_state
@@ -78,6 +79,13 @@ class DifyNodeFactory(NodeFactory):
         self._http_request_tool_file_manager_factory = http_request_tool_file_manager_factory
         self._http_request_file_manager = http_request_file_manager or file_manager
         self._rag_retrieval = DatasetRetrieval()
+        self._document_extractor_unstructured_api_config = (
+            document_extractor_unstructured_api_config
+            or UnstructuredApiConfig(
+                api_url=dify_config.UNSTRUCTURED_API_URL,
+                api_key=dify_config.UNSTRUCTURED_API_KEY or "",
+            )
+        )
 
     @override
     def create_node(self, node_config: NodeConfigDict) -> Node:
@@ -152,6 +160,15 @@ class DifyNodeFactory(NodeFactory):
                 rag_retrieval=self._rag_retrieval,
             )
 
+        if node_type == NodeType.DOCUMENT_EXTRACTOR:
+            return DocumentExtractorNode(
+                id=node_id,
+                config=node_config,
+                graph_init_params=self.graph_init_params,
+                graph_runtime_state=self.graph_runtime_state,
+                unstructured_api_config=self._document_extractor_unstructured_api_config,
+            )
+
         return node_class(
             id=node_id,
             config=node_config,

api/core/datasource/datasource_file_manager.py

@@ -213,6 +213,6 @@ class DatasourceFileManager:
 
 
 # init tool_file_parser
-# from core.file.datasource_file_parser import datasource_file_manager
+# from core.workflow.file.datasource_file_parser import datasource_file_manager
 #
 # datasource_file_manager["manager"] = DatasourceFileManager

api/core/datasource/utils/message_transformer.py

@@ -3,8 +3,8 @@ from collections.abc import Generator
 from mimetypes import guess_extension, guess_type
 
 from core.datasource.entities.datasource_entities import DatasourceMessage
-from core.file import File, FileTransferMethod, FileType
 from core.tools.tool_file_manager import ToolFileManager
+from core.workflow.file import File, FileTransferMethod, FileType
 from models.tools import ToolFile
 
 logger = logging.getLogger(__name__)

api/core/entities/mcp_provider.py

@@ -10,12 +10,12 @@ from pydantic import BaseModel
 
 from configs import dify_config
 from core.entities.provider_entities import BasicProviderConfig
-from core.file import helpers as file_helpers
 from core.helper import encrypter
 from core.helper.provider_cache import NoOpProviderCredentialCache
 from core.mcp.types import OAuthClientInformation, OAuthClientMetadata, OAuthTokens
 from core.tools.entities.common_entities import I18nObject
 from core.tools.entities.tool_entities import ToolProviderType
+from core.workflow.file import helpers as file_helpers
 
 if TYPE_CHECKING:
     from models.tools import MCPToolProvider

api/core/file/tool_file_parser.py

@@ -1,12 +0,0 @@
-from collections.abc import Callable
-from typing import TYPE_CHECKING
-
-if TYPE_CHECKING:
-    from core.tools.tool_file_manager import ToolFileManager
-
-_tool_file_manager_factory: Callable[[], "ToolFileManager"] | None = None
-
-
-def set_tool_file_manager_factory(factory: Callable[[], "ToolFileManager"]):
-    global _tool_file_manager_factory
-    _tool_file_manager_factory = factory

api/core/memory/token_buffer_memory.py

@@ -4,7 +4,6 @@ from sqlalchemy import select
 from sqlalchemy.orm import sessionmaker
 
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
-from core.file import file_manager
 from core.memory.base import BaseMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities import (
@@ -16,6 +15,7 @@ from core.model_runtime.entities import (
 )
 from core.model_runtime.entities.message_entities import PromptMessageContentUnionTypes
 from core.prompt.utils.extract_thread_messages import extract_thread_messages
+from core.workflow.file import file_manager
 from extensions.ext_database import db
 from factories import file_factory
 from models.model import AppMode, Conversation, Message, MessageFile

api/core/moderation/base.py

@@ -39,7 +39,7 @@ class Moderation(Extensible, ABC):
 
     @classmethod
     @abstractmethod
-    def validate_config(cls, tenant_id: str, config: dict):
+    def validate_config(cls, tenant_id: str, config: dict) -> None:
         """
         Validate the incoming form config data.
 

api/core/ops/tencent_trace/client.py

@@ -18,8 +18,7 @@ except ImportError:
     from importlib_metadata import version  # type: ignore[import-not-found]
 
 if TYPE_CHECKING:
-    from opentelemetry.metrics import Meter
-    from opentelemetry.metrics._internal.instrument import Histogram
+    from opentelemetry.metrics import Histogram, Meter
     from opentelemetry.sdk.metrics.export import MetricReader
 
 from opentelemetry import trace as trace_api

api/core/plugin/utils/converter.py

@@ -1,7 +1,7 @@
 from typing import Any
 
-from core.file.models import File
 from core.tools.entities.tool_entities import ToolSelector
+from core.workflow.file.models import File
 
 
 def convert_parameters_to_plugin_format(parameters: dict[str, Any]) -> dict[str, Any]:

api/core/prompt/advanced_prompt_transform.py

@@ -2,8 +2,6 @@ from collections.abc import Mapping, Sequence
 from typing import cast
 
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
-from core.file import file_manager
-from core.file.models import File
 from core.helper.code_executor.jinja2.jinja2_formatter import Jinja2Formatter
 from core.memory.base import BaseMemory
 from core.model_runtime.entities import (
@@ -18,6 +16,8 @@ from core.model_runtime.entities.message_entities import ImagePromptMessageConte
 from core.prompt.entities.advanced_prompt_entities import ChatModelMessage, CompletionModelPromptTemplate, MemoryConfig
 from core.prompt.prompt_transform import PromptTransform
 from core.prompt.utils.prompt_template_parser import PromptTemplateParser
+from core.workflow.file import file_manager
+from core.workflow.file.models import File
 from core.workflow.runtime import VariablePool
 
 

api/core/prompt/simple_prompt_transform.py

@@ -6,7 +6,6 @@ from typing import TYPE_CHECKING, Any, cast
 
 from core.app.app_config.entities import PromptTemplateEntity
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
-from core.file import file_manager
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_runtime.entities.message_entities import (
     ImagePromptMessageContent,
@@ -19,10 +18,11 @@ from core.model_runtime.entities.message_entities import (
 from core.prompt.entities.advanced_prompt_entities import MemoryConfig
 from core.prompt.prompt_transform import PromptTransform
 from core.prompt.utils.prompt_template_parser import PromptTemplateParser
+from core.workflow.file import file_manager
 from models.model import AppMode
 
 if TYPE_CHECKING:
-    from core.file.models import File
+    from core.workflow.file.models import File
 
 
 class ModelMode(StrEnum):

api/core/rag/datasource/vdb/vector_base.py

@@ -15,7 +15,7 @@ class BaseVector(ABC):
         raise NotImplementedError
 
     @abstractmethod
-    def create(self, texts: list[Document], embeddings: list[list[float]], **kwargs):
+    def create(self, texts: list[Document], embeddings: list[list[float]], **kwargs) -> list[str] | None:
         raise NotImplementedError
 
     @abstractmethod

api/core/rag/index_processor/processor/paragraph_index_processor.py

@@ -9,7 +9,6 @@ from typing import Any, cast
 logger = logging.getLogger(__name__)
 
 from core.entities.knowledge_entities import PreviewDetail
-from core.file import File, FileTransferMethod, FileType, file_manager
 from core.llm_generator.prompts import DEFAULT_GENERATOR_SUMMARY_PROMPT
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.llm_entities import LLMResult, LLMUsage
@@ -35,6 +34,7 @@ from core.rag.index_processor.index_processor_base import BaseIndexProcessor
 from core.rag.models.document import AttachmentDocument, Document, MultimodalGeneralStructureChunk
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
 from core.tools.utils.text_processing_utils import remove_leading_symbols
+from core.workflow.file import File, FileTransferMethod, FileType, file_manager
 from core.workflow.nodes.llm import llm_utils
 from extensions.ext_database import db
 from factories.file_factory import build_from_mapping

api/core/rag/models/document.py

@@ -4,7 +4,7 @@ from typing import Any
 
 from pydantic import BaseModel, Field
 
-from core.file import File
+from core.workflow.file import File
 
 
 class ChildDocument(BaseModel):

api/core/rag/retrieval/dataset_retrieval.py

@@ -23,7 +23,6 @@ from core.callback_handler.index_tool_callback_handler import DatasetIndexToolCa
 from core.db.session_factory import session_factory
 from core.entities.agent_entities import PlanningStrategy
 from core.entities.model_entities import ModelStatus
-from core.file import File, FileTransferMethod, FileType
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance, ModelManager
 from core.model_runtime.entities.llm_entities import LLMResult, LLMUsage
@@ -61,6 +60,7 @@ from core.rag.retrieval.template_prompts import (
 )
 from core.tools.signature import sign_upload_file
 from core.tools.utils.dataset_retriever.dataset_retriever_base_tool import DatasetRetrieverBaseTool
+from core.workflow.file import File, FileTransferMethod, FileType
 from core.workflow.nodes.knowledge_retrieval import exc
 from core.workflow.repositories.rag_retrieval_protocol import (
     KnowledgeRetrievalRequest,

api/core/tools/builtin_tool/providers/audio/tools/asr.py

@@ -2,14 +2,14 @@ import io
 from collections.abc import Generator
 from typing import Any
 
-from core.file.enums import FileType
-from core.file.file_manager import download
 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
 from core.plugin.entities.parameters import PluginParameterOption
 from core.tools.builtin_tool.tool import BuiltinTool
 from core.tools.entities.common_entities import I18nObject
 from core.tools.entities.tool_entities import ToolInvokeMessage, ToolParameter
+from core.workflow.file.enums import FileType
+from core.workflow.file.file_manager import download
 from services.model_provider_service import ModelProviderService
 
 

api/core/tools/custom_tool/tool.py

@@ -7,13 +7,13 @@ from urllib.parse import urlencode
 
 import httpx
 
-from core.file.file_manager import download
 from core.helper import ssrf_proxy
 from core.tools.__base.tool import Tool
 from core.tools.__base.tool_runtime import ToolRuntime
 from core.tools.entities.tool_bundle import ApiToolBundle
 from core.tools.entities.tool_entities import ToolEntity, ToolInvokeMessage, ToolProviderType
 from core.tools.errors import ToolInvokeError, ToolParameterValidationError, ToolProviderCredentialValidationError
+from core.workflow.file.file_manager import download
 
 API_TOOL_DEFAULT_TIMEOUT = (
     int(getenv("API_TOOL_DEFAULT_CONNECT_TIMEOUT", "10")),

api/core/tools/tool_engine.py

@@ -12,8 +12,6 @@ from yarl import URL
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.callback_handler.agent_tool_callback_handler import DifyAgentCallbackHandler
 from core.callback_handler.workflow_tool_callback_handler import DifyWorkflowCallbackHandler
-from core.file import FileType
-from core.file.models import FileTransferMethod
 from core.ops.ops_trace_manager import TraceQueueManager
 from core.tools.__base.tool import Tool
 from core.tools.entities.tool_entities import (
@@ -33,6 +31,8 @@ from core.tools.errors import (
 )
 from core.tools.utils.message_transformer import ToolFileMessageTransformer, safe_json_value
 from core.tools.workflow_as_tool.tool import WorkflowTool
+from core.workflow.file import FileType
+from core.workflow.file.models import FileTransferMethod
 from extensions.ext_database import db
 from models.enums import CreatorUserRole
 from models.model import Message, MessageFile

api/core/tools/tool_file_manager.py

@@ -243,7 +243,7 @@ class ToolFileManager:
 
 
 # init tool_file_parser
-from core.file.tool_file_parser import set_tool_file_manager_factory
+from core.workflow.file.tool_file_parser import set_tool_file_manager_factory
 
 
 def _factory() -> ToolFileManager:

api/core/tools/utils/message_transformer.py

@@ -8,9 +8,9 @@ from uuid import UUID
 import numpy as np
 import pytz
 
-from core.file import File, FileTransferMethod, FileType
 from core.tools.entities.tool_entities import ToolInvokeMessage
 from core.tools.tool_file_manager import ToolFileManager
+from core.workflow.file import File, FileTransferMethod, FileType
 from libs.login import current_user
 from models import Account
 

api/core/tools/workflow_as_tool/tool.py

@@ -8,7 +8,6 @@ from typing import Any, cast
 from sqlalchemy import select
 
 from core.db.session_factory import session_factory
-from core.file import FILE_MODEL_IDENTITY, File, FileTransferMethod
 from core.model_runtime.entities.llm_entities import LLMUsage, LLMUsageMetadata
 from core.tools.__base.tool import Tool
 from core.tools.__base.tool_runtime import ToolRuntime
@@ -19,6 +18,7 @@ from core.tools.entities.tool_entities import (
     ToolProviderType,
 )
 from core.tools.errors import ToolInvokeError
+from core.workflow.file import FILE_MODEL_IDENTITY, File, FileTransferMethod
 from factories.file_factory import build_from_mapping
 from models import Account, Tenant
 from models.model import App, EndUser

api/core/variables/segments.py

@@ -5,8 +5,8 @@ from typing import Annotated, Any, TypeAlias
 
 from pydantic import BaseModel, ConfigDict, Discriminator, Tag, field_validator
 
-from core.file import File
 from core.model_runtime.entities import PromptMessage
+from core.workflow.file import File
 
 from .types import SegmentType
 

api/core/variables/types.py

@@ -4,7 +4,7 @@ from collections.abc import Mapping
 from enum import StrEnum
 from typing import TYPE_CHECKING, Any
 
-from core.file.models import File
+from core.workflow.file.models import File
 
 if TYPE_CHECKING:
     pass

api/core/workflow/file/file_manager.py

@@ -1,9 +1,10 @@
+from __future__ import annotations
+
 import base64
 import logging
 from collections.abc import Mapping
 
 from configs import dify_config
-from core.helper import ssrf_proxy
 from core.model_runtime.entities import (
     AudioPromptMessageContent,
     DocumentPromptMessageContent,
@@ -15,12 +16,11 @@ from core.model_runtime.entities.message_entities import (
     MultiModalPromptMessageContent,
     PromptMessageContentUnionTypes,
 )
-from core.tools.signature import sign_tool_file
-from extensions.ext_storage import storage
 
 from . import helpers
 from .enums import FileAttribute
 from .models import File, FileTransferMethod, FileType
+from .runtime import get_workflow_file_runtime
 
 logger = logging.getLogger(__name__)
 
@@ -51,26 +51,7 @@ def to_prompt_message_content(
     *,
     image_detail_config: ImagePromptMessageContent.DETAIL | None = None,
 ) -> PromptMessageContentUnionTypes:
-    """
-    Convert a file to prompt message content.
-
-    This function converts files to their appropriate prompt message content types.
-    For supported file types (IMAGE, AUDIO, VIDEO, DOCUMENT), it creates the
-    corresponding message content with proper encoding/URL.
-
-    For unsupported file types, instead of raising an error, it returns a
-    TextPromptMessageContent with a descriptive message about the file.
-
-    Args:
-        f: The file to convert
-        image_detail_config: Optional detail configuration for image files
-
-    Returns:
-        PromptMessageContentUnionTypes: The appropriate message content type
-
-    Raises:
-        ValueError: If file extension or mime_type is missing
-    """
+    """Convert a file to prompt message content."""
     if f.extension is None:
         raise ValueError("Missing file extension")
     if f.mime_type is None:
@@ -83,15 +64,13 @@ def to_prompt_message_content(
         FileType.DOCUMENT: DocumentPromptMessageContent,
     }
 
-    # Check if file type is supported
     if f.type not in prompt_class_map:
-        # For unsupported file types, return a text description
         return TextPromptMessageContent(data=f"[Unsupported file type: {f.filename} ({f.type.value})]")
 
-    # Process supported file types
+    send_format = get_workflow_file_runtime().multimodal_send_format
     params = {
-        "base64_data": _get_encoded_string(f) if dify_config.MULTIMODAL_SEND_FORMAT == "base64" else "",
-        "url": _to_url(f) if dify_config.MULTIMODAL_SEND_FORMAT == "url" else "",
+        "base64_data": _get_encoded_string(f) if send_format == "base64" else "",
+        "url": _to_url(f) if send_format == "url" else "",
         "format": f.extension.removeprefix("."),
         "mime_type": f.mime_type,
         "filename": f.filename or "",
@@ -115,7 +94,7 @@ def _encode_file_ref(f: File) -> str | None:
     return None
 
 
-def download(f: File, /):
+def download(f: File, /) -> bytes:
     if f.transfer_method in (
         FileTransferMethod.TOOL_FILE,
         FileTransferMethod.LOCAL_FILE,
@@ -125,39 +104,26 @@ def download(f: File, /):
     elif f.transfer_method == FileTransferMethod.REMOTE_URL:
         if f.remote_url is None:
             raise ValueError("Missing file remote_url")
-        response = ssrf_proxy.get(f.remote_url, follow_redirects=True)
+        response = get_workflow_file_runtime().http_get(f.remote_url, follow_redirects=True)
         response.raise_for_status()
         return response.content
     raise ValueError(f"unsupported transfer method: {f.transfer_method}")
 
 
-def _download_file_content(path: str, /):
-    """
-    Download and return the contents of a file as bytes.
-
-    This function loads the file from storage and ensures it's in bytes format.
-
-    Args:
-        path (str): The path to the file in storage.
-
-    Returns:
-        bytes: The contents of the file as a bytes object.
-
-    Raises:
-        ValueError: If the loaded file is not a bytes object.
-    """
-    data = storage.load(path, stream=False)
+def _download_file_content(path: str, /) -> bytes:
+    """Download and return a file from storage as bytes."""
+    data = get_workflow_file_runtime().storage_load(path, stream=False)
     if not isinstance(data, bytes):
         raise ValueError(f"file {path} is not a bytes object")
     return data
 
 
-def _get_encoded_string(f: File, /):
+def _get_encoded_string(f: File, /) -> str:
     match f.transfer_method:
         case FileTransferMethod.REMOTE_URL:
             if f.remote_url is None:
                 raise ValueError("Missing file remote_url")
-            response = ssrf_proxy.get(f.remote_url, follow_redirects=True)
+            response = get_workflow_file_runtime().http_get(f.remote_url, follow_redirects=True)
             response.raise_for_status()
             data = response.content
         case FileTransferMethod.LOCAL_FILE:
@@ -167,8 +133,7 @@ def _get_encoded_string(f: File, /):
         case FileTransferMethod.DATASOURCE_FILE:
             data = _download_file_content(f.storage_key)
 
-    encoded_string = base64.b64encode(data).decode("utf-8")
-    return encoded_string
+    return base64.b64encode(data).decode("utf-8")
 
 
 def _to_url(f: File, /):
@@ -181,10 +146,9 @@ def _to_url(f: File, /):
             raise ValueError("Missing file related_id")
         return f.remote_url or helpers.get_signed_file_url(upload_file_id=f.related_id)
     elif f.transfer_method == FileTransferMethod.TOOL_FILE:
-        # add sign url
         if f.related_id is None or f.extension is None:
             raise ValueError("Missing file related_id or extension")
-        return sign_tool_file(tool_file_id=f.related_id, extension=f.extension)
+        return helpers.get_signed_tool_file_url(tool_file_id=f.related_id, extension=f.extension)
     else:
         raise ValueError(f"Unsupported transfer method: {f.transfer_method}")
 
@@ -315,12 +279,7 @@ def _build_file_from_ref(
 
 
 class FileManager:
-    """
-    Adapter exposing file manager helpers behind FileManagerProtocol.
-
-    This is intentionally a thin wrapper over the existing module-level functions so callers can inject it
-    where a protocol-typed file manager is expected.
-    """
+    """Adapter exposing file manager helpers behind FileManagerProtocol."""
 
     def download(self, f: File, /) -> bytes:
         return download(f)

api/core/workflow/file/helpers.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import base64
 import hashlib
 import hmac
@@ -5,20 +7,21 @@ import os
 import time
 import urllib.parse
 
-from configs import dify_config
+from .runtime import get_workflow_file_runtime
 
 
-def get_signed_file_url(upload_file_id: str, as_attachment=False, for_external: bool = True) -> str:
-    base_url = dify_config.FILES_URL if for_external else (dify_config.INTERNAL_FILES_URL or dify_config.FILES_URL)
+def get_signed_file_url(upload_file_id: str, as_attachment: bool = False, for_external: bool = True) -> str:
+    runtime = get_workflow_file_runtime()
+    base_url = runtime.files_url if for_external else (runtime.internal_files_url or runtime.files_url)
     url = f"{base_url}/files/{upload_file_id}/file-preview"
 
     timestamp = str(int(time.time()))
     nonce = os.urandom(16).hex()
-    key = dify_config.SECRET_KEY.encode()
+    key = runtime.secret_key.encode()
     msg = f"file-preview|{upload_file_id}|{timestamp}|{nonce}"
     sign = hmac.new(key, msg.encode(), hashlib.sha256).digest()
     encoded_sign = base64.urlsafe_b64encode(sign).decode()
-    query = {"timestamp": timestamp, "nonce": nonce, "sign": encoded_sign}
+    query: dict[str, str] = {"timestamp": timestamp, "nonce": nonce, "sign": encoded_sign}
     if as_attachment:
         query["as_attachment"] = "true"
     query_string = urllib.parse.urlencode(query)
@@ -27,57 +30,63 @@ def get_signed_file_url(upload_file_id: str, as_attachment=False, for_external:
 
 
 def get_signed_file_url_for_plugin(filename: str, mimetype: str, tenant_id: str, user_id: str) -> str:
-    # Plugin access should use internal URL for Docker network communication
-    base_url = dify_config.INTERNAL_FILES_URL or dify_config.FILES_URL
+    runtime = get_workflow_file_runtime()
+    # Plugin access should use internal URL for Docker network communication.
+    base_url = runtime.internal_files_url or runtime.files_url
     url = f"{base_url}/files/upload/for-plugin"
     timestamp = str(int(time.time()))
     nonce = os.urandom(16).hex()
-    key = dify_config.SECRET_KEY.encode()
+    key = runtime.secret_key.encode()
     msg = f"upload|{filename}|{mimetype}|{tenant_id}|{user_id}|{timestamp}|{nonce}"
     sign = hmac.new(key, msg.encode(), hashlib.sha256).digest()
     encoded_sign = base64.urlsafe_b64encode(sign).decode()
     return f"{url}?timestamp={timestamp}&nonce={nonce}&sign={encoded_sign}&user_id={user_id}&tenant_id={tenant_id}"
 
 
+def get_signed_tool_file_url(tool_file_id: str, extension: str, for_external: bool = True) -> str:
+    runtime = get_workflow_file_runtime()
+    return runtime.sign_tool_file(tool_file_id=tool_file_id, extension=extension, for_external=for_external)
+
+
 def verify_plugin_file_signature(
     *, filename: str, mimetype: str, tenant_id: str, user_id: str, timestamp: str, nonce: str, sign: str
 ) -> bool:
+    runtime = get_workflow_file_runtime()
     data_to_sign = f"upload|{filename}|{mimetype}|{tenant_id}|{user_id}|{timestamp}|{nonce}"
-    secret_key = dify_config.SECRET_KEY.encode()
+    secret_key = runtime.secret_key.encode()
     recalculated_sign = hmac.new(secret_key, data_to_sign.encode(), hashlib.sha256).digest()
     recalculated_encoded_sign = base64.urlsafe_b64encode(recalculated_sign).decode()
 
-    # verify signature
     if sign != recalculated_encoded_sign:
         return False
 
     current_time = int(time.time())
-    return current_time - int(timestamp) <= dify_config.FILES_ACCESS_TIMEOUT
+    return current_time - int(timestamp) <= runtime.files_access_timeout
 
 
 def verify_image_signature(*, upload_file_id: str, timestamp: str, nonce: str, sign: str) -> bool:
+    runtime = get_workflow_file_runtime()
     data_to_sign = f"image-preview|{upload_file_id}|{timestamp}|{nonce}"
-    secret_key = dify_config.SECRET_KEY.encode()
+    secret_key = runtime.secret_key.encode()
     recalculated_sign = hmac.new(secret_key, data_to_sign.encode(), hashlib.sha256).digest()
     recalculated_encoded_sign = base64.urlsafe_b64encode(recalculated_sign).decode()
 
-    # verify signature
     if sign != recalculated_encoded_sign:
         return False
 
     current_time = int(time.time())
-    return current_time - int(timestamp) <= dify_config.FILES_ACCESS_TIMEOUT
+    return current_time - int(timestamp) <= runtime.files_access_timeout
 
 
 def verify_file_signature(*, upload_file_id: str, timestamp: str, nonce: str, sign: str) -> bool:
+    runtime = get_workflow_file_runtime()
     data_to_sign = f"file-preview|{upload_file_id}|{timestamp}|{nonce}"
-    secret_key = dify_config.SECRET_KEY.encode()
+    secret_key = runtime.secret_key.encode()
     recalculated_sign = hmac.new(secret_key, data_to_sign.encode(), hashlib.sha256).digest()
     recalculated_encoded_sign = base64.urlsafe_b64encode(recalculated_sign).decode()
 
-    # verify signature
     if sign != recalculated_encoded_sign:
         return False
 
     current_time = int(time.time())
-    return current_time - int(timestamp) <= dify_config.FILES_ACCESS_TIMEOUT
+    return current_time - int(timestamp) <= runtime.files_access_timeout

api/core/workflow/file/models.py

@@ -1,16 +1,26 @@
+from __future__ import annotations
+
 from collections.abc import Mapping, Sequence
 from typing import Any
 
 from pydantic import BaseModel, Field, model_validator
 
 from core.model_runtime.entities.message_entities import ImagePromptMessageContent
-from core.tools.signature import sign_tool_file
 
 from . import helpers
 from .constants import FILE_MODEL_IDENTITY
 from .enums import FileTransferMethod, FileType
 
 
+def sign_tool_file(*, tool_file_id: str, extension: str, for_external: bool = True) -> str:
+    """Compatibility shim for tests and legacy callers patching ``models.sign_tool_file``."""
+    return helpers.get_signed_tool_file_url(
+        tool_file_id=tool_file_id,
+        extension=extension,
+        for_external=for_external,
+    )
+
+
 class ImageConfig(BaseModel):
     """
     NOTE: This part of validation is deprecated, but still used in app features "Image Upload".
@@ -122,7 +132,11 @@ class File(BaseModel):
         elif self.transfer_method in [FileTransferMethod.TOOL_FILE, FileTransferMethod.DATASOURCE_FILE]:
             assert self.related_id is not None
             assert self.extension is not None
-            return sign_tool_file(tool_file_id=self.related_id, extension=self.extension, for_external=for_external)
+            return sign_tool_file(
+                tool_file_id=self.related_id,
+                extension=self.extension,
+                for_external=for_external,
+            )
         return None
 
     def to_plugin_parameter(self) -> dict[str, Any]:
@@ -137,7 +151,7 @@ class File(BaseModel):
         }
 
     @model_validator(mode="after")
-    def validate_after(self):
+    def validate_after(self) -> File:
         match self.transfer_method:
             case FileTransferMethod.REMOTE_URL:
                 if not self.remote_url:
@@ -160,5 +174,5 @@ class File(BaseModel):
         return self._storage_key
 
     @storage_key.setter
-    def storage_key(self, value: str):
+    def storage_key(self, value: str) -> None:
         self._storage_key = value

api/core/workflow/file/protocols.py

@@ -0,0 +1,43 @@
+from __future__ import annotations
+
+from collections.abc import Generator
+from typing import Protocol
+
+
+class HttpResponseProtocol(Protocol):
+    """Subset of response behavior needed by workflow file helpers."""
+
+    @property
+    def content(self) -> bytes: ...
+
+    def raise_for_status(self) -> object: ...
+
+
+class WorkflowFileRuntimeProtocol(Protocol):
+    """Runtime dependencies required by ``core.workflow.file``.
+
+    Implementations are expected to be provided by integration layers (for example,
+    ``core.app.workflow.file_runtime``) so the workflow package avoids importing
+    application infrastructure modules directly.
+    """
+
+    @property
+    def files_url(self) -> str: ...
+
+    @property
+    def internal_files_url(self) -> str | None: ...
+
+    @property
+    def secret_key(self) -> str: ...
+
+    @property
+    def files_access_timeout(self) -> int: ...
+
+    @property
+    def multimodal_send_format(self) -> str: ...
+
+    def http_get(self, url: str, *, follow_redirects: bool = True) -> HttpResponseProtocol: ...
+
+    def storage_load(self, path: str, *, stream: bool = False) -> bytes | Generator: ...
+
+    def sign_tool_file(self, *, tool_file_id: str, extension: str, for_external: bool = True) -> str: ...

api/core/workflow/file/runtime.py

@@ -0,0 +1,58 @@
+from __future__ import annotations
+
+from collections.abc import Generator
+from typing import NoReturn
+
+from .protocols import HttpResponseProtocol, WorkflowFileRuntimeProtocol
+
+
+class WorkflowFileRuntimeNotConfiguredError(RuntimeError):
+    """Raised when workflow file runtime dependencies were not configured."""
+
+
+class _UnconfiguredWorkflowFileRuntime(WorkflowFileRuntimeProtocol):
+    def _raise(self) -> NoReturn:
+        raise WorkflowFileRuntimeNotConfiguredError(
+            "workflow file runtime is not configured, call set_workflow_file_runtime(...) first"
+        )
+
+    @property
+    def files_url(self) -> str:
+        self._raise()
+
+    @property
+    def internal_files_url(self) -> str | None:
+        self._raise()
+
+    @property
+    def secret_key(self) -> str:
+        self._raise()
+
+    @property
+    def files_access_timeout(self) -> int:
+        self._raise()
+
+    @property
+    def multimodal_send_format(self) -> str:
+        self._raise()
+
+    def http_get(self, url: str, *, follow_redirects: bool = True) -> HttpResponseProtocol:
+        self._raise()
+
+    def storage_load(self, path: str, *, stream: bool = False) -> bytes | Generator:
+        self._raise()
+
+    def sign_tool_file(self, *, tool_file_id: str, extension: str, for_external: bool = True) -> str:
+        self._raise()
+
+
+_runtime: WorkflowFileRuntimeProtocol = _UnconfiguredWorkflowFileRuntime()
+
+
+def set_workflow_file_runtime(runtime: WorkflowFileRuntimeProtocol) -> None:
+    global _runtime
+    _runtime = runtime
+
+
+def get_workflow_file_runtime() -> WorkflowFileRuntimeProtocol:
+    return _runtime

api/core/workflow/file/tool_file_parser.py

@@ -0,0 +1,9 @@
+from collections.abc import Callable
+from typing import Any
+
+_tool_file_manager_factory: Callable[[], Any] | None = None
+
+
+def set_tool_file_manager_factory(factory: Callable[[], Any]):
+    global _tool_file_manager_factory
+    _tool_file_manager_factory = factory

api/core/workflow/node_events/node.py

@@ -4,11 +4,11 @@ from enum import StrEnum
 
 from pydantic import Field
 
-from core.file import File
 from core.model_runtime.entities.llm_entities import LLMUsage
 from core.rag.entities.citation_metadata import RetrievalSourceMetadata
 from core.workflow.entities import ToolCall, ToolResult
 from core.workflow.entities.pause_reason import PauseReason
+from core.workflow.file import File
 from core.workflow.node_events import NodeRunResult
 
 from .base import NodeEventBase

api/core/workflow/nodes/agent/agent_node.py

@@ -11,7 +11,6 @@ from sqlalchemy.orm import Session
 
 from core.agent.entities import AgentToolEntity
 from core.agent.plugin_entities import AgentStrategyParameter
-from core.file import File, FileTransferMethod
 from core.memory.base import BaseMemory
 from core.memory.node_token_buffer_memory import NodeTokenBufferMemory
 from core.memory.token_buffer_memory import TokenBufferMemory
@@ -42,6 +41,7 @@ from core.workflow.enums import (
     WorkflowNodeExecutionMetadataKey,
     WorkflowNodeExecutionStatus,
 )
+from core.workflow.file import File, FileTransferMethod
 from core.workflow.node_events import (
     AgentLogEvent,
     NodeEventBase,

api/core/workflow/nodes/datasource/datasource_node.py

@@ -14,13 +14,13 @@ from core.datasource.entities.datasource_entities import (
 from core.datasource.online_document.online_document_plugin import OnlineDocumentDatasourcePlugin
 from core.datasource.online_drive.online_drive_plugin import OnlineDriveDatasourcePlugin
 from core.datasource.utils.message_transformer import DatasourceFileMessageTransformer
-from core.file import File
-from core.file.enums import FileTransferMethod, FileType
 from core.plugin.impl.exc import PluginDaemonClientSideError
 from core.variables.segments import ArrayAnySegment
 from core.variables.variables import ArrayAnyVariable
 from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionStatus
 from core.workflow.enums import NodeExecutionType, NodeType, SystemVariableKey
+from core.workflow.file import File
+from core.workflow.file.enums import FileTransferMethod, FileType
 from core.workflow.node_events import NodeRunResult, StreamChunkEvent, StreamCompletedEvent
 from core.workflow.nodes.base.node import Node
 from core.workflow.nodes.base.variable_template_parser import VariableTemplateParser

api/core/workflow/nodes/document_extractor/__init__.py

@@ -1,4 +1,4 @@
-from .entities import DocumentExtractorNodeData
+from .entities import DocumentExtractorNodeData, UnstructuredApiConfig
 from .node import DocumentExtractorNode
 
-__all__ = ["DocumentExtractorNode", "DocumentExtractorNodeData"]
+__all__ = ["DocumentExtractorNode", "DocumentExtractorNodeData", "UnstructuredApiConfig"]

api/core/workflow/nodes/document_extractor/entities.py

@@ -1,7 +1,14 @@
 from collections.abc import Sequence
+from dataclasses import dataclass
 
 from core.workflow.nodes.base import BaseNodeData
 
 
 class DocumentExtractorNodeData(BaseNodeData):
     variable_selector: Sequence[str]
+
+
+@dataclass(frozen=True)
+class UnstructuredApiConfig:
+    api_url: str | None = None
+    api_key: str = ""

api/core/workflow/nodes/document_extractor/node.py

@@ -5,7 +5,7 @@ import logging
 import os
 import tempfile
 from collections.abc import Mapping, Sequence
-from typing import Any
+from typing import TYPE_CHECKING, Any
 
 import charset_normalizer
 import docx
@@ -20,20 +20,23 @@ from docx.oxml.text.paragraph import CT_P
 from docx.table import Table
 from docx.text.paragraph import Paragraph
 
-from configs import dify_config
-from core.file import File, FileTransferMethod, file_manager
 from core.helper import ssrf_proxy
 from core.variables import ArrayFileSegment
 from core.variables.segments import ArrayStringSegment, FileSegment
 from core.workflow.enums import NodeType, WorkflowNodeExecutionStatus
+from core.workflow.file import File, FileTransferMethod, file_manager
 from core.workflow.node_events import NodeRunResult
 from core.workflow.nodes.base.node import Node
 
-from .entities import DocumentExtractorNodeData
+from .entities import DocumentExtractorNodeData, UnstructuredApiConfig
 from .exc import DocumentExtractorError, FileDownloadError, TextExtractionError, UnsupportedFileTypeError
 
 logger = logging.getLogger(__name__)
 
+if TYPE_CHECKING:
+    from core.workflow.entities import GraphInitParams
+    from core.workflow.runtime import GraphRuntimeState
+
 
 class DocumentExtractorNode(Node[DocumentExtractorNodeData]):
     """
@@ -47,6 +50,23 @@ class DocumentExtractorNode(Node[DocumentExtractorNodeData]):
     def version(cls) -> str:
         return "1"
 
+    def __init__(
+        self,
+        id: str,
+        config: Mapping[str, Any],
+        graph_init_params: "GraphInitParams",
+        graph_runtime_state: "GraphRuntimeState",
+        *,
+        unstructured_api_config: UnstructuredApiConfig | None = None,
+    ) -> None:
+        super().__init__(
+            id=id,
+            config=config,
+            graph_init_params=graph_init_params,
+            graph_runtime_state=graph_runtime_state,
+        )
+        self._unstructured_api_config = unstructured_api_config or UnstructuredApiConfig()
+
     def _run(self):
         variable_selector = self.node_data.variable_selector
         variable = self.graph_runtime_state.variable_pool.get(variable_selector)
@@ -64,7 +84,10 @@ class DocumentExtractorNode(Node[DocumentExtractorNodeData]):
 
         try:
             if isinstance(value, list):
-                extracted_text_list = list(map(_extract_text_from_file, value))
+                extracted_text_list = [
+                    _extract_text_from_file(file, unstructured_api_config=self._unstructured_api_config)
+                    for file in value
+                ]
                 return NodeRunResult(
                     status=WorkflowNodeExecutionStatus.SUCCEEDED,
                     inputs=inputs,
@@ -72,7 +95,7 @@ class DocumentExtractorNode(Node[DocumentExtractorNodeData]):
                     outputs={"text": ArrayStringSegment(value=extracted_text_list)},
                 )
             elif isinstance(value, File):
-                extracted_text = _extract_text_from_file(value)
+                extracted_text = _extract_text_from_file(value, unstructured_api_config=self._unstructured_api_config)
                 return NodeRunResult(
                     status=WorkflowNodeExecutionStatus.SUCCEEDED,
                     inputs=inputs,
@@ -103,7 +126,12 @@ class DocumentExtractorNode(Node[DocumentExtractorNodeData]):
         return {node_id + ".files": typed_node_data.variable_selector}
 
 
-def _extract_text_by_mime_type(*, file_content: bytes, mime_type: str) -> str:
+def _extract_text_by_mime_type(
+    *,
+    file_content: bytes,
+    mime_type: str,
+    unstructured_api_config: UnstructuredApiConfig,
+) -> str:
     """Extract text from a file based on its MIME type."""
     match mime_type:
         case "text/plain" | "text/html" | "text/htm" | "text/markdown" | "text/xml":
@@ -111,7 +139,7 @@ def _extract_text_by_mime_type(*, file_content: bytes, mime_type: str) -> str:
         case "application/pdf":
             return _extract_text_from_pdf(file_content)
         case "application/msword":
-            return _extract_text_from_doc(file_content)
+            return _extract_text_from_doc(file_content, unstructured_api_config=unstructured_api_config)
         case "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
             return _extract_text_from_docx(file_content)
         case "text/csv":
@@ -119,11 +147,11 @@ def _extract_text_by_mime_type(*, file_content: bytes, mime_type: str) -> str:
         case "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" | "application/vnd.ms-excel":
             return _extract_text_from_excel(file_content)
         case "application/vnd.ms-powerpoint":
-            return _extract_text_from_ppt(file_content)
+            return _extract_text_from_ppt(file_content, unstructured_api_config=unstructured_api_config)
         case "application/vnd.openxmlformats-officedocument.presentationml.presentation":
-            return _extract_text_from_pptx(file_content)
+            return _extract_text_from_pptx(file_content, unstructured_api_config=unstructured_api_config)
         case "application/epub+zip":
-            return _extract_text_from_epub(file_content)
+            return _extract_text_from_epub(file_content, unstructured_api_config=unstructured_api_config)
         case "message/rfc822":
             return _extract_text_from_eml(file_content)
         case "application/vnd.ms-outlook":
@@ -140,7 +168,12 @@ def _extract_text_by_mime_type(*, file_content: bytes, mime_type: str) -> str:
             raise UnsupportedFileTypeError(f"Unsupported MIME type: {mime_type}")
 
 
-def _extract_text_by_file_extension(*, file_content: bytes, file_extension: str) -> str:
+def _extract_text_by_file_extension(
+    *,
+    file_content: bytes,
+    file_extension: str,
+    unstructured_api_config: UnstructuredApiConfig,
+) -> str:
     """Extract text from a file based on its file extension."""
     match file_extension:
         case (
@@ -203,7 +236,7 @@ def _extract_text_by_file_extension(*, file_content: bytes, file_extension: str)
         case ".pdf":
             return _extract_text_from_pdf(file_content)
         case ".doc":
-            return _extract_text_from_doc(file_content)
+            return _extract_text_from_doc(file_content, unstructured_api_config=unstructured_api_config)
         case ".docx":
             return _extract_text_from_docx(file_content)
         case ".csv":
@@ -211,11 +244,11 @@ def _extract_text_by_file_extension(*, file_content: bytes, file_extension: str)
         case ".xls" | ".xlsx":
             return _extract_text_from_excel(file_content)
         case ".ppt":
-            return _extract_text_from_ppt(file_content)
+            return _extract_text_from_ppt(file_content, unstructured_api_config=unstructured_api_config)
         case ".pptx":
-            return _extract_text_from_pptx(file_content)
+            return _extract_text_from_pptx(file_content, unstructured_api_config=unstructured_api_config)
         case ".epub":
-            return _extract_text_from_epub(file_content)
+            return _extract_text_from_epub(file_content, unstructured_api_config=unstructured_api_config)
         case ".eml":
             return _extract_text_from_eml(file_content)
         case ".msg":
@@ -312,14 +345,15 @@ def _extract_text_from_pdf(file_content: bytes) -> str:
         raise TextExtractionError(f"Failed to extract text from PDF: {str(e)}") from e
 
 
-def _extract_text_from_doc(file_content: bytes) -> str:
+def _extract_text_from_doc(file_content: bytes, *, unstructured_api_config: UnstructuredApiConfig) -> str:
     """
     Extract text from a DOC file.
     """
     from unstructured.partition.api import partition_via_api
 
-    if not dify_config.UNSTRUCTURED_API_URL:
-        raise TextExtractionError("UNSTRUCTURED_API_URL must be set")
+    if not unstructured_api_config.api_url:
+        raise TextExtractionError("Unstructured API URL is not configured for DOC file processing.")
+    api_key = unstructured_api_config.api_key or ""
 
     try:
         with tempfile.NamedTemporaryFile(suffix=".doc", delete=False) as temp_file:
@@ -329,8 +363,8 @@ def _extract_text_from_doc(file_content: bytes) -> str:
                 elements = partition_via_api(
                     file=file,
                     metadata_filename=temp_file.name,
-                    api_url=dify_config.UNSTRUCTURED_API_URL,
-                    api_key=dify_config.UNSTRUCTURED_API_KEY,  # type: ignore
+                    api_url=unstructured_api_config.api_url,
+                    api_key=api_key,
                 )
             os.unlink(temp_file.name)
         return "\n".join([getattr(element, "text", "") for element in elements])
@@ -420,12 +454,20 @@ def _download_file_content(file: File) -> bytes:
         raise FileDownloadError(f"Error downloading file: {str(e)}") from e
 
 
-def _extract_text_from_file(file: File):
+def _extract_text_from_file(file: File, *, unstructured_api_config: UnstructuredApiConfig) -> str:
     file_content = _download_file_content(file)
     if file.extension:
-        extracted_text = _extract_text_by_file_extension(file_content=file_content, file_extension=file.extension)
+        extracted_text = _extract_text_by_file_extension(
+            file_content=file_content,
+            file_extension=file.extension,
+            unstructured_api_config=unstructured_api_config,
+        )
     elif file.mime_type:
-        extracted_text = _extract_text_by_mime_type(file_content=file_content, mime_type=file.mime_type)
+        extracted_text = _extract_text_by_mime_type(
+            file_content=file_content,
+            mime_type=file.mime_type,
+            unstructured_api_config=unstructured_api_config,
+        )
     else:
         raise UnsupportedFileTypeError("Unable to determine file type: MIME type or file extension is missing")
     return extracted_text
@@ -517,12 +559,14 @@ def _extract_text_from_excel(file_content: bytes) -> str:
         raise TextExtractionError(f"Failed to extract text from Excel file: {str(e)}") from e
 
 
-def _extract_text_from_ppt(file_content: bytes) -> str:
+def _extract_text_from_ppt(file_content: bytes, *, unstructured_api_config: UnstructuredApiConfig) -> str:
     from unstructured.partition.api import partition_via_api
     from unstructured.partition.ppt import partition_ppt
 
+    api_key = unstructured_api_config.api_key or ""
+
     try:
-        if dify_config.UNSTRUCTURED_API_URL:
+        if unstructured_api_config.api_url:
             with tempfile.NamedTemporaryFile(suffix=".ppt", delete=False) as temp_file:
                 temp_file.write(file_content)
                 temp_file.flush()
@@ -530,8 +574,8 @@ def _extract_text_from_ppt(file_content: bytes) -> str:
                     elements = partition_via_api(
                         file=file,
                         metadata_filename=temp_file.name,
-                        api_url=dify_config.UNSTRUCTURED_API_URL,
-                        api_key=dify_config.UNSTRUCTURED_API_KEY,  # type: ignore
+                        api_url=unstructured_api_config.api_url,
+                        api_key=api_key,
                     )
                 os.unlink(temp_file.name)
         else:
@@ -543,12 +587,14 @@ def _extract_text_from_ppt(file_content: bytes) -> str:
         raise TextExtractionError(f"Failed to extract text from PPTX: {str(e)}") from e
 
 
-def _extract_text_from_pptx(file_content: bytes) -> str:
+def _extract_text_from_pptx(file_content: bytes, *, unstructured_api_config: UnstructuredApiConfig) -> str:
     from unstructured.partition.api import partition_via_api
     from unstructured.partition.pptx import partition_pptx
 
+    api_key = unstructured_api_config.api_key or ""
+
     try:
-        if dify_config.UNSTRUCTURED_API_URL:
+        if unstructured_api_config.api_url:
             with tempfile.NamedTemporaryFile(suffix=".pptx", delete=False) as temp_file:
                 temp_file.write(file_content)
                 temp_file.flush()
@@ -556,8 +602,8 @@ def _extract_text_from_pptx(file_content: bytes) -> str:
                     elements = partition_via_api(
                         file=file,
                         metadata_filename=temp_file.name,
-                        api_url=dify_config.UNSTRUCTURED_API_URL,
-                        api_key=dify_config.UNSTRUCTURED_API_KEY,  # type: ignore
+                        api_url=unstructured_api_config.api_url,
+                        api_key=api_key,
                     )
                 os.unlink(temp_file.name)
         else:
@@ -568,12 +614,14 @@ def _extract_text_from_pptx(file_content: bytes) -> str:
         raise TextExtractionError(f"Failed to extract text from PPTX: {str(e)}") from e
 
 
-def _extract_text_from_epub(file_content: bytes) -> str:
+def _extract_text_from_epub(file_content: bytes, *, unstructured_api_config: UnstructuredApiConfig) -> str:
     from unstructured.partition.api import partition_via_api
     from unstructured.partition.epub import partition_epub
 
+    api_key = unstructured_api_config.api_key or ""
+
     try:
-        if dify_config.UNSTRUCTURED_API_URL:
+        if unstructured_api_config.api_url:
             with tempfile.NamedTemporaryFile(suffix=".epub", delete=False) as temp_file:
                 temp_file.write(file_content)
                 temp_file.flush()
@@ -581,8 +629,8 @@ def _extract_text_from_epub(file_content: bytes) -> str:
                     elements = partition_via_api(
                         file=file,
                         metadata_filename=temp_file.name,
-                        api_url=dify_config.UNSTRUCTURED_API_URL,
-                        api_key=dify_config.UNSTRUCTURED_API_KEY,  # type: ignore
+                        api_url=unstructured_api_config.api_url,
+                        api_key=api_key,
                     )
                 os.unlink(temp_file.name)
         else:

api/core/workflow/nodes/http_request/executor.py

@@ -11,10 +11,10 @@ import httpx
 from json_repair import repair_json
 
 from configs import dify_config
-from core.file.enums import FileTransferMethod
-from core.file.file_manager import file_manager as default_file_manager
 from core.helper.ssrf_proxy import ssrf_proxy
 from core.variables.segments import ArrayFileSegment, FileSegment
+from core.workflow.file.enums import FileTransferMethod
+from core.workflow.file.file_manager import file_manager as default_file_manager
 from core.workflow.runtime import VariablePool
 
 from ..protocols import FileManagerProtocol, HttpClientProtocol
@@ -366,7 +366,9 @@ class Executor:
                 **request_args,
                 max_retries=self.max_retries,
             )
-        except (self._http_client.max_retries_exceeded_error, self._http_client.request_error) as e:
+        except self._http_client.max_retries_exceeded_error as e:
+            raise HttpRequestNodeError(f"Reached maximum retries for URL {self.url}") from e
+        except self._http_client.request_error as e:
             raise HttpRequestNodeError(str(e)) from e
         return response
 

api/core/workflow/nodes/http_request/node.py

@@ -4,12 +4,12 @@ from collections.abc import Callable, Mapping, Sequence
 from typing import TYPE_CHECKING, Any
 
 from configs import dify_config
-from core.file import File, FileTransferMethod
-from core.file.file_manager import file_manager as default_file_manager
 from core.helper.ssrf_proxy import ssrf_proxy
 from core.tools.tool_file_manager import ToolFileManager
 from core.variables.segments import ArrayFileSegment
 from core.workflow.enums import NodeType, WorkflowNodeExecutionStatus
+from core.workflow.file import File, FileTransferMethod
+from core.workflow.file.file_manager import file_manager as default_file_manager
 from core.workflow.node_events import NodeRunResult
 from core.workflow.nodes.base import variable_template_parser
 from core.workflow.nodes.base.entities import VariableSelector

api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py

@@ -30,7 +30,7 @@ from .exc import (
 )
 
 if TYPE_CHECKING:
-    from core.file.models import File
+    from core.workflow.file.models import File
     from core.workflow.runtime import GraphRuntimeState
 
 logger = logging.getLogger(__name__)

api/core/workflow/nodes/list_operator/node.py

@@ -1,10 +1,10 @@
 from collections.abc import Callable, Sequence
 from typing import Any, TypeAlias, TypeVar
 
-from core.file import File
 from core.variables import ArrayFileSegment, ArrayNumberSegment, ArrayStringSegment
 from core.variables.segments import ArrayAnySegment, ArrayBooleanSegment, ArraySegment
 from core.workflow.enums import NodeType, WorkflowNodeExecutionStatus
+from core.workflow.file import File
 from core.workflow.node_events import NodeRunResult
 from core.workflow.nodes.base.node import Node
 

api/core/workflow/nodes/llm/file_saver.py

@@ -4,10 +4,10 @@ import typing as tp
 from sqlalchemy import Engine
 
 from constants.mimetypes import DEFAULT_EXTENSION, DEFAULT_MIME_TYPE
-from core.file import File, FileTransferMethod, FileType
 from core.helper import ssrf_proxy
 from core.tools.signature import sign_tool_file
 from core.tools.tool_file_manager import ToolFileManager
+from core.workflow.file import File, FileTransferMethod, FileType
 from extensions.ext_database import db as global_db
 
 

api/core/workflow/nodes/llm/llm_utils.py

@@ -7,7 +7,6 @@ from sqlalchemy.orm import Session
 from configs import dify_config
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
 from core.entities.provider_entities import ProviderQuotaType, QuotaUnit
-from core.file.models import File
 from core.memory import NodeTokenBufferMemory, TokenBufferMemory
 from core.memory.base import BaseMemory
 from core.model_manager import ModelInstance, ModelManager
@@ -25,6 +24,7 @@ from core.model_runtime.model_providers.__base.large_language_model import Large
 from core.prompt.entities.advanced_prompt_entities import MemoryConfig, MemoryMode
 from core.variables.segments import ArrayAnySegment, ArrayFileSegment, FileSegment, NoneSegment, StringSegment
 from core.workflow.enums import SystemVariableKey
+from core.workflow.file.models import File
 from core.workflow.nodes.llm.entities import LLMGenerationData, ModelConfig
 from core.workflow.runtime import VariablePool
 from extensions.ext_database import db

api/core/workflow/nodes/llm/node.py

@@ -18,7 +18,6 @@ from sqlalchemy import select
 from core.agent.entities import AgentEntity, AgentLog, AgentResult, AgentToolEntity, ExecutionContext
 from core.agent.patterns import StrategyFactory
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
-from core.file import File, FileTransferMethod, FileType, file_manager
 from core.helper.code_executor import CodeExecutor, CodeLanguage
 from core.llm_generator.output_parser.errors import OutputParserError
 from core.llm_generator.output_parser.file_ref import (
@@ -91,6 +90,7 @@ from core.workflow.enums import (
     WorkflowNodeExecutionMetadataKey,
     WorkflowNodeExecutionStatus,
 )
+from core.workflow.file import File, FileTransferMethod, FileType, file_manager
 from core.workflow.node_events import (
     AgentLogEvent,
     ModelInvokeCompletedEvent,
@@ -144,7 +144,7 @@ from .exc import (
 from .file_saver import FileSaverImpl, LLMFileSaver
 
 if TYPE_CHECKING:
-    from core.file.models import File
+    from core.workflow.file.models import File
     from core.workflow.runtime import GraphRuntimeState
 
 logger = logging.getLogger(__name__)

api/core/workflow/nodes/loop/loop_node.py

@@ -71,9 +71,9 @@ class LoopNode(LLMUsageTrackingMixin, Node[LoopNodeData]):
         if self.node_data.loop_variables:
             value_processor: dict[Literal["constant", "variable"], Callable[[LoopVariableData], Segment | None]] = {
                 "constant": lambda var: self._get_segment_for_constant(var.var_type, var.value),
-                "variable": lambda var: self.graph_runtime_state.variable_pool.get(var.value)
-                if isinstance(var.value, list)
-                else None,
+                "variable": lambda var: (
+                    self.graph_runtime_state.variable_pool.get(var.value) if isinstance(var.value, list) else None
+                ),
             }
             for loop_variable in self.node_data.loop_variables:
                 if loop_variable.value_type not in value_processor:

api/core/workflow/nodes/parameter_extractor/parameter_extractor_node.py

@@ -6,7 +6,6 @@ from collections.abc import Mapping, Sequence
 from typing import Any, cast
 
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
-from core.file import File
 from core.memory.base import BaseMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities import ImagePromptMessageContent
@@ -28,6 +27,7 @@ from core.prompt.simple_prompt_transform import ModelMode
 from core.prompt.utils.prompt_message_util import PromptMessageUtil
 from core.variables.types import ArrayValidation, SegmentType
 from core.workflow.enums import NodeType, WorkflowNodeExecutionMetadataKey, WorkflowNodeExecutionStatus
+from core.workflow.file import File
 from core.workflow.node_events import NodeRunResult
 from core.workflow.nodes.base import variable_template_parser
 from core.workflow.nodes.base.node import Node

api/core/workflow/nodes/protocols.py

@@ -2,7 +2,7 @@ from typing import Any, Protocol
 
 import httpx
 
-from core.file import File
+from core.workflow.file import File
 
 
 class HttpClientProtocol(Protocol):

api/core/workflow/nodes/question_classifier/question_classifier_node.py

@@ -39,7 +39,7 @@ from .template_prompts import (
 )
 
 if TYPE_CHECKING:
-    from core.file.models import File
+    from core.workflow.file.models import File
     from core.workflow.runtime import GraphRuntimeState
 
 

api/core/workflow/nodes/tool/tool_node.py

@@ -8,7 +8,6 @@ logger = logging.getLogger(__name__)
 from sqlalchemy.orm import Session
 
 from core.callback_handler.workflow_tool_callback_handler import DifyWorkflowCallbackHandler
-from core.file import File, FileTransferMethod
 from core.model_runtime.entities.llm_entities import LLMUsage
 from core.tools.__base.tool import Tool
 from core.tools.entities.tool_entities import ToolInvokeMessage, ToolParameter
@@ -23,6 +22,7 @@ from core.workflow.enums import (
     WorkflowNodeExecutionMetadataKey,
     WorkflowNodeExecutionStatus,
 )
+from core.workflow.file import File, FileTransferMethod
 from core.workflow.node_events import NodeEventBase, NodeRunResult, StreamChunkEvent, StreamCompletedEvent
 from core.workflow.nodes.base.node import Node
 from core.workflow.nodes.base.variable_template_parser import VariableTemplateParser

api/core/workflow/nodes/trigger_webhook/node.py

@@ -2,12 +2,12 @@ import logging
 from collections.abc import Mapping
 from typing import Any
 
-from core.file import FileTransferMethod
 from core.variables.types import SegmentType
 from core.variables.variables import FileVariable
 from core.workflow.constants import SYSTEM_VARIABLE_NODE_ID
 from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionStatus
 from core.workflow.enums import NodeExecutionType, NodeType
+from core.workflow.file import FileTransferMethod
 from core.workflow.node_events import NodeRunResult
 from core.workflow.nodes.base.node import Node
 from factories import file_factory

api/core/workflow/runtime/variable_pool.py

@@ -8,7 +8,6 @@ from typing import Annotated, Any, Union, cast
 
 from pydantic import BaseModel, Field
 
-from core.file import File, FileAttribute, file_manager
 from core.variables import Segment, SegmentGroup, VariableBase
 from core.variables.consts import SELECTORS_LENGTH
 from core.variables.segments import FileSegment, ObjectSegment
@@ -19,6 +18,7 @@ from core.workflow.constants import (
     RAG_PIPELINE_VARIABLE_NODE_ID,
     SYSTEM_VARIABLE_NODE_ID,
 )
+from core.workflow.file import File, FileAttribute, file_manager
 from core.workflow.system_variable import SystemVariable
 from factories import variable_factory
 

api/core/workflow/system_variable.py

@@ -7,8 +7,8 @@ from uuid import uuid4
 
 from pydantic import AliasChoices, BaseModel, ConfigDict, Field, model_validator
 
-from core.file.models import File
 from core.workflow.enums import SystemVariableKey
+from core.workflow.file.models import File
 
 
 class SystemVariable(BaseModel):

api/core/workflow/utils/condition/processor.py

@@ -2,9 +2,9 @@ import json
 from collections.abc import Mapping, Sequence
 from typing import Literal, NamedTuple
 
-from core.file import FileAttribute, file_manager
 from core.variables import ArrayFileSegment
 from core.variables.segments import ArrayBooleanSegment, BooleanSegment
+from core.workflow.file import FileAttribute, file_manager
 from core.workflow.runtime import VariablePool
 
 from .entities import Condition, SubCondition, SupportedComparisonOperator

api/core/workflow/workflow_entry.py

@@ -9,11 +9,11 @@ from core.app.apps.exc import GenerateTaskStoppedError
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.app.workflow.layers.observability import ObservabilityLayer
 from core.app.workflow.node_factory import DifyNodeFactory
-from core.file.models import File
 from core.sandbox import Sandbox
 from core.workflow.constants import ENVIRONMENT_VARIABLE_NODE_ID
 from core.workflow.entities import GraphInitParams
 from core.workflow.errors import WorkflowNodeRunFailedError
+from core.workflow.file.models import File
 from core.workflow.graph import Graph
 from core.workflow.graph_engine import GraphEngine, GraphEngineConfig
 from core.workflow.graph_engine.command_channels import InMemoryChannel

api/core/workflow/workflow_type_encoder.py

@@ -4,8 +4,8 @@ from typing import Any, overload
 
 from pydantic import BaseModel
 
-from core.file.models import File
 from core.variables import Segment
+from core.workflow.file.models import File
 
 
 class WorkflowRuntimeTypeConverter: