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/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,