refactor(workflow-file): move core.file to core.workflow.file (#32252)

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>

api/core/workflow/file/__init__.py

@@ -0,0 +1,19 @@
+from .constants import FILE_MODEL_IDENTITY
+from .enums import ArrayFileAttribute, FileAttribute, FileBelongsTo, FileTransferMethod, FileType
+from .models import (
+    File,
+    FileUploadConfig,
+    ImageConfig,
+)
+
+__all__ = [
+    "FILE_MODEL_IDENTITY",
+    "ArrayFileAttribute",
+    "File",
+    "FileAttribute",
+    "FileBelongsTo",
+    "FileTransferMethod",
+    "FileType",
+    "FileUploadConfig",
+    "ImageConfig",
+]

api/core/workflow/file/constants.py

@@ -0,0 +1,11 @@
+from typing import Any
+
+# TODO(QuantumGhost): Refactor variable type identification. Instead of directly
+# comparing `dify_model_identity` with constants throughout the codebase, extract
+# this logic into a dedicated function. This would encapsulate the implementation
+# details of how different variable types are identified.
+FILE_MODEL_IDENTITY = "__dify__file__"
+
+
+def maybe_file_object(o: Any) -> bool:
+    return isinstance(o, dict) and o.get("dify_model_identity") == FILE_MODEL_IDENTITY

api/core/workflow/file/enums.py

@@ -0,0 +1,57 @@
+from enum import StrEnum
+
+
+class FileType(StrEnum):
+    IMAGE = "image"
+    DOCUMENT = "document"
+    AUDIO = "audio"
+    VIDEO = "video"
+    CUSTOM = "custom"
+
+    @staticmethod
+    def value_of(value):
+        for member in FileType:
+            if member.value == value:
+                return member
+        raise ValueError(f"No matching enum found for value '{value}'")
+
+
+class FileTransferMethod(StrEnum):
+    REMOTE_URL = "remote_url"
+    LOCAL_FILE = "local_file"
+    TOOL_FILE = "tool_file"
+    DATASOURCE_FILE = "datasource_file"
+
+    @staticmethod
+    def value_of(value):
+        for member in FileTransferMethod:
+            if member.value == value:
+                return member
+        raise ValueError(f"No matching enum found for value '{value}'")
+
+
+class FileBelongsTo(StrEnum):
+    USER = "user"
+    ASSISTANT = "assistant"
+
+    @staticmethod
+    def value_of(value):
+        for member in FileBelongsTo:
+            if member.value == value:
+                return member
+        raise ValueError(f"No matching enum found for value '{value}'")
+
+
+class FileAttribute(StrEnum):
+    TYPE = "type"
+    SIZE = "size"
+    NAME = "name"
+    MIME_TYPE = "mime_type"
+    TRANSFER_METHOD = "transfer_method"
+    URL = "url"
+    EXTENSION = "extension"
+    RELATED_ID = "related_id"
+
+
+class ArrayFileAttribute(StrEnum):
+    LENGTH = "length"

api/core/workflow/file/file_manager.py

@@ -0,0 +1,143 @@
+from __future__ import annotations
+
+import base64
+from collections.abc import Mapping
+
+from core.model_runtime.entities import (
+    AudioPromptMessageContent,
+    DocumentPromptMessageContent,
+    ImagePromptMessageContent,
+    TextPromptMessageContent,
+    VideoPromptMessageContent,
+)
+from core.model_runtime.entities.message_entities import PromptMessageContentUnionTypes
+
+from . import helpers
+from .enums import FileAttribute
+from .models import File, FileTransferMethod, FileType
+from .runtime import get_workflow_file_runtime
+
+
+def get_attr(*, file: File, attr: FileAttribute):
+    match attr:
+        case FileAttribute.TYPE:
+            return file.type.value
+        case FileAttribute.SIZE:
+            return file.size
+        case FileAttribute.NAME:
+            return file.filename
+        case FileAttribute.MIME_TYPE:
+            return file.mime_type
+        case FileAttribute.TRANSFER_METHOD:
+            return file.transfer_method.value
+        case FileAttribute.URL:
+            return _to_url(file)
+        case FileAttribute.EXTENSION:
+            return file.extension
+        case FileAttribute.RELATED_ID:
+            return file.related_id
+
+
+def to_prompt_message_content(
+    f: File,
+    /,
+    *,
+    image_detail_config: ImagePromptMessageContent.DETAIL | None = None,
+) -> PromptMessageContentUnionTypes:
+    """Convert a file to prompt message content."""
+    if f.extension is None:
+        raise ValueError("Missing file extension")
+    if f.mime_type is None:
+        raise ValueError("Missing file mime_type")
+
+    prompt_class_map: Mapping[FileType, type[PromptMessageContentUnionTypes]] = {
+        FileType.IMAGE: ImagePromptMessageContent,
+        FileType.AUDIO: AudioPromptMessageContent,
+        FileType.VIDEO: VideoPromptMessageContent,
+        FileType.DOCUMENT: DocumentPromptMessageContent,
+    }
+
+    if f.type not in prompt_class_map:
+        return TextPromptMessageContent(data=f"[Unsupported file type: {f.filename} ({f.type.value})]")
+
+    send_format = get_workflow_file_runtime().multimodal_send_format
+    params = {
+        "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 "",
+    }
+    if f.type == FileType.IMAGE:
+        params["detail"] = image_detail_config or ImagePromptMessageContent.DETAIL.LOW
+
+    return prompt_class_map[f.type].model_validate(params)
+
+
+def download(f: File, /) -> bytes:
+    if f.transfer_method in (
+        FileTransferMethod.TOOL_FILE,
+        FileTransferMethod.LOCAL_FILE,
+        FileTransferMethod.DATASOURCE_FILE,
+    ):
+        return _download_file_content(f.storage_key)
+    elif f.transfer_method == FileTransferMethod.REMOTE_URL:
+        if f.remote_url is None:
+            raise ValueError("Missing file remote_url")
+        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, /) -> 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, /) -> str:
+    match f.transfer_method:
+        case FileTransferMethod.REMOTE_URL:
+            if f.remote_url is None:
+                raise ValueError("Missing file remote_url")
+            response = get_workflow_file_runtime().http_get(f.remote_url, follow_redirects=True)
+            response.raise_for_status()
+            data = response.content
+        case FileTransferMethod.LOCAL_FILE:
+            data = _download_file_content(f.storage_key)
+        case FileTransferMethod.TOOL_FILE:
+            data = _download_file_content(f.storage_key)
+        case FileTransferMethod.DATASOURCE_FILE:
+            data = _download_file_content(f.storage_key)
+
+    return base64.b64encode(data).decode("utf-8")
+
+
+def _to_url(f: File, /):
+    if f.transfer_method == FileTransferMethod.REMOTE_URL:
+        if f.remote_url is None:
+            raise ValueError("Missing file remote_url")
+        return f.remote_url
+    elif f.transfer_method == FileTransferMethod.LOCAL_FILE:
+        if f.related_id is None:
+            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:
+        if f.related_id is None or f.extension is None:
+            raise ValueError("Missing file related_id or 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}")
+
+
+class FileManager:
+    """Adapter exposing file manager helpers behind FileManagerProtocol."""
+
+    def download(self, f: File, /) -> bytes:
+        return download(f)
+
+
+file_manager = FileManager()

api/core/workflow/file/helpers.py

@@ -0,0 +1,92 @@
+from __future__ import annotations
+
+import base64
+import hashlib
+import hmac
+import os
+import time
+import urllib.parse
+
+from .runtime import get_workflow_file_runtime
+
+
+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 = 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: dict[str, str] = {"timestamp": timestamp, "nonce": nonce, "sign": encoded_sign}
+    if as_attachment:
+        query["as_attachment"] = "true"
+    query_string = urllib.parse.urlencode(query)
+
+    return f"{url}?{query_string}"
+
+
+def get_signed_file_url_for_plugin(filename: str, mimetype: str, tenant_id: str, user_id: str) -> str:
+    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 = 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 = 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()
+
+    if sign != recalculated_encoded_sign:
+        return False
+
+    current_time = int(time.time())
+    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 = 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()
+
+    if sign != recalculated_encoded_sign:
+        return False
+
+    current_time = int(time.time())
+    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 = 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()
+
+    if sign != recalculated_encoded_sign:
+        return False
+
+    current_time = int(time.time())
+    return current_time - int(timestamp) <= runtime.files_access_timeout

api/core/workflow/file/models.py

@@ -0,0 +1,178 @@
+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 . 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".
+    """
+
+    number_limits: int = 0
+    transfer_methods: Sequence[FileTransferMethod] = Field(default_factory=list)
+    detail: ImagePromptMessageContent.DETAIL | None = None
+
+
+class FileUploadConfig(BaseModel):
+    """
+    File Upload Entity.
+    """
+
+    image_config: ImageConfig | None = None
+    allowed_file_types: Sequence[FileType] = Field(default_factory=list)
+    allowed_file_extensions: Sequence[str] = Field(default_factory=list)
+    allowed_file_upload_methods: Sequence[FileTransferMethod] = Field(default_factory=list)
+    number_limits: int = 0
+
+
+class File(BaseModel):
+    # NOTE: dify_model_identity is a special identifier used to distinguish between
+    # new and old data formats during serialization and deserialization.
+    dify_model_identity: str = FILE_MODEL_IDENTITY
+
+    id: str | None = None  # message file id
+    tenant_id: str
+    type: FileType
+    transfer_method: FileTransferMethod
+    # If `transfer_method` is `FileTransferMethod.remote_url`, the
+    # `remote_url` attribute must not be `None`.
+    remote_url: str | None = None  # remote url
+    # If `transfer_method` is `FileTransferMethod.local_file` or
+    # `FileTransferMethod.tool_file`, the `related_id` attribute must not be `None`.
+    #
+    # It should be set to `ToolFile.id` when `transfer_method` is `tool_file`.
+    related_id: str | None = None
+    filename: str | None = None
+    extension: str | None = Field(default=None, description="File extension, should contain dot")
+    mime_type: str | None = None
+    size: int = -1
+
+    # Those properties are private, should not be exposed to the outside.
+    _storage_key: str
+
+    def __init__(
+        self,
+        *,
+        id: str | None = None,
+        tenant_id: str,
+        type: FileType,
+        transfer_method: FileTransferMethod,
+        remote_url: str | None = None,
+        related_id: str | None = None,
+        filename: str | None = None,
+        extension: str | None = None,
+        mime_type: str | None = None,
+        size: int = -1,
+        storage_key: str | None = None,
+        dify_model_identity: str | None = FILE_MODEL_IDENTITY,
+        url: str | None = None,
+        # Legacy compatibility fields - explicitly handle known extra fields
+        tool_file_id: str | None = None,
+        upload_file_id: str | None = None,
+        datasource_file_id: str | None = None,
+    ):
+        super().__init__(
+            id=id,
+            tenant_id=tenant_id,
+            type=type,
+            transfer_method=transfer_method,
+            remote_url=remote_url,
+            related_id=related_id,
+            filename=filename,
+            extension=extension,
+            mime_type=mime_type,
+            size=size,
+            dify_model_identity=dify_model_identity,
+            url=url,
+        )
+        self._storage_key = str(storage_key)
+
+    def to_dict(self) -> Mapping[str, str | int | None]:
+        data = self.model_dump(mode="json")
+        return {
+            **data,
+            "url": self.generate_url(),
+        }
+
+    @property
+    def markdown(self) -> str:
+        url = self.generate_url()
+        if self.type == FileType.IMAGE:
+            text = f"![{self.filename or ''}]({url})"
+        else:
+            text = f"[{self.filename or url}]({url})"
+
+        return text
+
+    def generate_url(self, for_external: bool = True) -> str | None:
+        if self.transfer_method == FileTransferMethod.REMOTE_URL:
+            return self.remote_url
+        elif self.transfer_method == FileTransferMethod.LOCAL_FILE:
+            if self.related_id is None:
+                raise ValueError("Missing file related_id")
+            return helpers.get_signed_file_url(upload_file_id=self.related_id, for_external=for_external)
+        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 None
+
+    def to_plugin_parameter(self) -> dict[str, Any]:
+        return {
+            "dify_model_identity": FILE_MODEL_IDENTITY,
+            "mime_type": self.mime_type,
+            "filename": self.filename,
+            "extension": self.extension,
+            "size": self.size,
+            "type": self.type,
+            "url": self.generate_url(for_external=False),
+        }
+
+    @model_validator(mode="after")
+    def validate_after(self) -> File:
+        match self.transfer_method:
+            case FileTransferMethod.REMOTE_URL:
+                if not self.remote_url:
+                    raise ValueError("Missing file url")
+                if not isinstance(self.remote_url, str) or not self.remote_url.startswith("http"):
+                    raise ValueError("Invalid file url")
+            case FileTransferMethod.LOCAL_FILE:
+                if not self.related_id:
+                    raise ValueError("Missing file related_id")
+            case FileTransferMethod.TOOL_FILE:
+                if not self.related_id:
+                    raise ValueError("Missing file related_id")
+            case FileTransferMethod.DATASOURCE_FILE:
+                if not self.related_id:
+                    raise ValueError("Missing file related_id")
+        return self
+
+    @property
+    def storage_key(self) -> str:
+        return self._storage_key
+
+    @storage_key.setter
+    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

@@ -3,10 +3,10 @@ from datetime import datetime
 
 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.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.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance, ModelManager
 from core.model_runtime.entities.llm_entities import LLMUsage, LLMUsageMetadata
@@ -33,6 +32,7 @@ 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/node.py

@@ -21,11 +21,11 @@ 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
 

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

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.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance, ModelManager
 from core.model_runtime.entities.llm_entities import LLMUsage
@@ -16,6 +15,7 @@ from core.model_runtime.model_providers.__base.large_language_model import Large
 from core.prompt.entities.advanced_prompt_entities import MemoryConfig
 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 ModelConfig
 from core.workflow.runtime import VariablePool
 from extensions.ext_database import db

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

@@ -12,7 +12,6 @@ from typing import TYPE_CHECKING, Any, Literal
 from sqlalchemy import select
 
 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.structured_output import invoke_llm_with_structured_output
@@ -65,6 +64,7 @@ from core.workflow.enums import (
     WorkflowNodeExecutionMetadataKey,
     WorkflowNodeExecutionStatus,
 )
+from core.workflow.file import File, FileTransferMethod, FileType, file_manager
 from core.workflow.node_events import (
     ModelInvokeCompletedEvent,
     NodeEventBase,
@@ -101,7 +101,7 @@ 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.token_buffer_memory import TokenBufferMemory
 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

@@ -5,7 +5,6 @@ from sqlalchemy import select
 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
@@ -20,6 +19,7 @@ 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

@@ -9,10 +9,10 @@ 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.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: