fix: 依赖更新

Misuse of ServerConfig.PublicKeyCallback may cause authorization bypass in golang.org/x/crypto
Unstructured has Path Traversal via Malicious MSG Attachment that Allows Arbitrary File Write #106
@isaacs/brace-expansion has Uncontrolled Resource Consumption #107
jwt-go allows excessive memory allocation during header parsing #24
golang.org/x/crypto Vulnerable to Denial of Service (DoS) via Slow or Incomplete Key Exchange #29
部分文件修复

api/core/app/workflow/node_factory.py

@@ -4,13 +4,14 @@ from typing import TYPE_CHECKING, final
 from typing_extensions import override
 
 from configs import dify_config
-from core.file import file_manager
-from core.helper import ssrf_proxy
+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
 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.graph import NodeFactory
+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
@@ -22,7 +23,6 @@ from core.workflow.nodes.template_transform.template_renderer import (
     Jinja2TemplateRenderer,
 )
 from core.workflow.nodes.template_transform.template_transform_node import TemplateTransformNode
-from libs.typing import is_str, is_str_dict
 
 if TYPE_CHECKING:
     from core.workflow.entities import GraphInitParams
@@ -47,9 +47,9 @@ class DifyNodeFactory(NodeFactory):
         code_providers: Sequence[type[CodeNodeProvider]] | None = None,
         code_limits: CodeNodeLimits | None = None,
         template_renderer: Jinja2TemplateRenderer | None = None,
-        http_request_http_client: HttpClientProtocol = ssrf_proxy,
+        http_request_http_client: HttpClientProtocol | None = None,
         http_request_tool_file_manager_factory: Callable[[], ToolFileManager] = ToolFileManager,
-        http_request_file_manager: FileManagerProtocol = file_manager,
+        http_request_file_manager: FileManagerProtocol | None = None,
     ) -> None:
         self.graph_init_params = graph_init_params
         self.graph_runtime_state = graph_runtime_state
@@ -68,12 +68,12 @@ class DifyNodeFactory(NodeFactory):
             max_object_array_length=dify_config.CODE_MAX_OBJECT_ARRAY_LENGTH,
         )
         self._template_renderer = template_renderer or CodeExecutorJinja2TemplateRenderer()
-        self._http_request_http_client = http_request_http_client
+        self._http_request_http_client = http_request_http_client or ssrf_proxy
         self._http_request_tool_file_manager_factory = http_request_tool_file_manager_factory
-        self._http_request_file_manager = http_request_file_manager
+        self._http_request_file_manager = http_request_file_manager or file_manager
 
     @override
-    def create_node(self, node_config: dict[str, object]) -> Node:
+    def create_node(self, node_config: NodeConfigDict) -> Node:
         """
         Create a Node instance from node configuration data using the traditional mapping.
 
@@ -82,23 +82,14 @@ class DifyNodeFactory(NodeFactory):
         :raises ValueError: if node type is unknown or configuration is invalid
         """
         # Get node_id from config
-        node_id = node_config.get("id")
-        if not is_str(node_id):
-            raise ValueError("Node config missing id")
+        node_id = node_config["id"]
 
         # Get node type from config
-        node_data = node_config.get("data", {})
-        if not is_str_dict(node_data):
-            raise ValueError(f"Node {node_id} missing data information")
-
-        node_type_str = node_data.get("type")
-        if not is_str(node_type_str):
-            raise ValueError(f"Node {node_id} missing or invalid type information")
-
+        node_data = node_config["data"]
         try:
-            node_type = NodeType(node_type_str)
+            node_type = NodeType(node_data["type"])
         except ValueError:
-            raise ValueError(f"Unknown node type: {node_type_str}")
+            raise ValueError(f"Unknown node type: {node_data['type']}")
 
         # Get node class
         node_mapping = NODE_TYPE_CLASSES_MAPPING.get(node_type)

api/core/file/__init__.py

@@ -17,3 +17,4 @@ __all__ = [
     "FileUploadConfig",
     "ImageConfig",
 ]
+

api/core/file/file_manager.py

@@ -104,6 +104,8 @@ def download(f: 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 = ssrf_proxy.get(f.remote_url, follow_redirects=True)
         response.raise_for_status()
         return response.content
@@ -134,6 +136,8 @@ def _download_file_content(path: str, /):
 def _get_encoded_string(f: File, /):
     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.raise_for_status()
             data = response.content
@@ -164,3 +168,18 @@ def _to_url(f: File, /):
         return sign_tool_file(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.
+
+    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.
+    """
+
+    def download(self, f: File, /) -> bytes:
+        return download(f)
+
+
+file_manager = FileManager()

api/core/helper/ssrf_proxy.py

@@ -4,8 +4,10 @@ Proxy requests to avoid SSRF
 
 import logging
 import time
+from typing import Any, TypeAlias
 
 import httpx
+from pydantic import TypeAdapter, ValidationError
 
 from configs import dify_config
 from core.helper.http_client_pooling import get_pooled_http_client
@@ -18,6 +20,9 @@ SSRF_DEFAULT_MAX_RETRIES = dify_config.SSRF_DEFAULT_MAX_RETRIES
 BACKOFF_FACTOR = 0.5
 STATUS_FORCELIST = [429, 500, 502, 503, 504]
 
+Headers: TypeAlias = dict[str, str]
+_HEADERS_ADAPTER = TypeAdapter(Headers)
+
 _SSL_VERIFIED_POOL_KEY = "ssrf:verified"
 _SSL_UNVERIFIED_POOL_KEY = "ssrf:unverified"
 _SSRF_CLIENT_LIMITS = httpx.Limits(
@@ -76,7 +81,7 @@ def _get_ssrf_client(ssl_verify_enabled: bool) -> httpx.Client:
     )
 
 
-def _get_user_provided_host_header(headers: dict | None) -> str | None:
+def _get_user_provided_host_header(headers: Headers | None) -> str | None:
     """
     Extract the user-provided Host header from the headers dict.
 
@@ -92,7 +97,7 @@ def _get_user_provided_host_header(headers: dict | None) -> str | None:
     return None
 
 
-def _inject_trace_headers(headers: dict | None) -> dict:
+def _inject_trace_headers(headers: Headers | None) -> Headers:
     """
     Inject W3C traceparent header for distributed tracing.
 
@@ -125,7 +130,7 @@ def _inject_trace_headers(headers: dict | None) -> dict:
     return headers
 
 
-def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+def make_request(method: str, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
     # Convert requests-style allow_redirects to httpx-style follow_redirects
     if "allow_redirects" in kwargs:
         allow_redirects = kwargs.pop("allow_redirects")
@@ -142,10 +147,15 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
 
     # prioritize per-call option, which can be switched on and off inside the HTTP node on the web UI
     verify_option = kwargs.pop("ssl_verify", dify_config.HTTP_REQUEST_NODE_SSL_VERIFY)
+    if not isinstance(verify_option, bool):
+        raise ValueError("ssl_verify must be a boolean")
     client = _get_ssrf_client(verify_option)
 
     # Inject traceparent header for distributed tracing (when OTEL is not enabled)
-    headers = kwargs.get("headers") or {}
+    try:
+        headers: Headers = _HEADERS_ADAPTER.validate_python(kwargs.get("headers") or {})
+    except ValidationError as e:
+        raise ValueError("headers must be a mapping of string keys to string values") from e
     headers = _inject_trace_headers(headers)
     kwargs["headers"] = headers
 
@@ -198,25 +208,63 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
     raise MaxRetriesExceededError(f"Reached maximum retries ({max_retries}) for URL {url}")
 
 
-def get(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+def get(url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
     return make_request("GET", url, max_retries=max_retries, **kwargs)
 
 
-def post(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+def post(url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
     return make_request("POST", url, max_retries=max_retries, **kwargs)
 
 
-def put(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+def put(url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
     return make_request("PUT", url, max_retries=max_retries, **kwargs)
 
 
-def patch(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+def patch(url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
     return make_request("PATCH", url, max_retries=max_retries, **kwargs)
 
 
-def delete(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+def delete(url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
     return make_request("DELETE", url, max_retries=max_retries, **kwargs)
 
 
-def head(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
+def head(url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
     return make_request("HEAD", url, max_retries=max_retries, **kwargs)
+
+
+class SSRFProxy:
+    """
+    Adapter exposing SSRF-protected HTTP helpers behind HttpClientProtocol.
+
+    This is intentionally a thin wrapper over the existing module-level functions so callers can inject it
+    where a protocol-typed HTTP client is expected.
+    """
+
+    @property
+    def max_retries_exceeded_error(self) -> type[Exception]:
+        return max_retries_exceeded_error
+
+    @property
+    def request_error(self) -> type[Exception]:
+        return request_error
+
+    def get(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
+        return get(url=url, max_retries=max_retries, **kwargs)
+
+    def head(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
+        return head(url=url, max_retries=max_retries, **kwargs)
+
+    def post(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
+        return post(url=url, max_retries=max_retries, **kwargs)
+
+    def put(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
+        return put(url=url, max_retries=max_retries, **kwargs)
+
+    def delete(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
+        return delete(url=url, max_retries=max_retries, **kwargs)
+
+    def patch(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> httpx.Response:
+        return patch(url=url, max_retries=max_retries, **kwargs)
+
+
+ssrf_proxy = SSRFProxy()

api/core/workflow/entities/graph_config.py

@@ -0,0 +1,24 @@
+from __future__ import annotations
+
+import sys
+
+from pydantic import TypeAdapter, with_config
+
+if sys.version_info >= (3, 12):
+    from typing import TypedDict
+else:
+    from typing_extensions import TypedDict
+
+
+@with_config(extra="allow")
+class NodeConfigData(TypedDict):
+    type: str
+
+
+@with_config(extra="allow")
+class NodeConfigDict(TypedDict):
+    id: str
+    data: NodeConfigData
+
+
+NodeConfigDictAdapter = TypeAdapter(NodeConfigDict)

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

@@ -115,7 +115,7 @@ class DefaultValue(BaseModel):
     @model_validator(mode="after")
     def validate_value_type(self) -> DefaultValue:
         # Type validation configuration
-        type_validators = {
+        type_validators: dict[DefaultValueType, dict[str, Any]] = {
             DefaultValueType.STRING: {
                 "type": str,
                 "converter": lambda x: x,

api/core/workflow/nodes/node_mapping.py

@@ -5,5 +5,33 @@ from core.workflow.nodes.base.node import Node
 
 LATEST_VERSION = "latest"
 
-# Mapping is built by Node.get_node_type_classes_mapping(), which imports and walks core.workflow.nodes
-NODE_TYPE_CLASSES_MAPPING: Mapping[NodeType, Mapping[str, type[Node]]] = Node.get_node_type_classes_mapping()
+
+class _LazyNodeTypeClassesMapping(Mapping[NodeType, Mapping[str, type[Node]]]):
+    """
+    Lazy wrapper so the mapping is built on first access, not at import time.
+    Avoids circular import when modules under core.workflow.nodes (e.g. node_factory)
+    import from node_mapping.
+    """
+
+    _cache: Mapping[NodeType, Mapping[str, type[Node]]] | None = None
+
+    def _get(self) -> Mapping[NodeType, Mapping[str, type[Node]]]:
+        if self._cache is None:
+            self._cache = Node.get_node_type_classes_mapping()
+        return self._cache
+
+    def __getitem__(self, key: NodeType) -> Mapping[str, type[Node]]:
+        return self._get().__getitem__(key)
+
+    def __iter__(self):
+        return iter(self._get())
+
+    def __len__(self) -> int:
+        return len(self._get())
+
+    def __contains__(self, key: object) -> bool:
+        return key in self._get()
+
+
+# Built on first access to avoid circular import with node_factory and other dependents.
+NODE_TYPE_CLASSES_MAPPING: Mapping[NodeType, Mapping[str, type[Node]]] = _LazyNodeTypeClassesMapping()

api/migrations_extend/versions/2025_04_01_0001-add_system_integration_extend_fields.py

@@ -21,19 +21,39 @@ def upgrade():
     conn = op.get_bind()
     inspector = Inspector.from_engine(conn)
     tables = inspector.get_table_names()
-    
-    if 'system_integration_extend' in tables:
+
+    if 'system_integration_extend' not in tables:
+        return
+
+    existing_columns = {c['name'] for c in inspector.get_columns('system_integration_extend')}
+    columns_to_add = []
+
+    if 'test' not in existing_columns:
+        columns_to_add.append(
+            sa.Column('test', sa.Boolean(), server_default=sa.text('false'), nullable=True, comment='是否测试链接联通性')
+        )
+    if 'config' not in existing_columns:
+        columns_to_add.append(sa.Column('config', sa.Text(), nullable=True, comment='其他配置'))
+    if 'app_id' not in existing_columns:
+        columns_to_add.append(sa.Column('app_id', sa.Text(), nullable=True, comment='应用ID'))
+
+    if columns_to_add:
         with op.batch_alter_table('system_integration_extend', schema=None) as batch_op:
-            batch_op.add_column(sa.Column('test', sa.Boolean(), server_default=sa.text('false'), nullable=True, comment='是否测试链接联通性'))
-            batch_op.add_column(sa.Column('config', sa.Text(), nullable=True, comment='其他配置'))
-            batch_op.add_column(sa.Column('app_id', sa.Text(), nullable=True, comment='应用ID'))
+            for col in columns_to_add:
+                batch_op.add_column(col)
     # ### end Alembic commands ###
 
 
 def downgrade():
     # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table('system_integration_extend', schema=None) as batch_op:
-        batch_op.drop_column('app_id')
-        batch_op.drop_column('config')
-        batch_op.drop_column('test')
+    conn = op.get_bind()
+    inspector = Inspector.from_engine(conn)
+    if 'system_integration_extend' not in inspector.get_table_names():
+        return
+    existing_columns = {c['name'] for c in inspector.get_columns('system_integration_extend')}
+    columns_to_drop = [c for c in ('app_id', 'config', 'test') if c in existing_columns]
+    if columns_to_drop:
+        with op.batch_alter_table('system_integration_extend', schema=None) as batch_op:
+            for col_name in columns_to_drop:
+                batch_op.drop_column(col_name)
     # ### end Alembic commands ### 

api/pyproject.toml

@@ -81,7 +81,6 @@ dependencies = [
     "starlette==0.49.1",
     "tiktoken~=0.9.0",
     "transformers~=4.56.1",
-    "unstructured[docx,epub,md,ppt,pptx]~=0.16.1",
     "yarl~=1.18.3",
     "webvtt-py~=0.5.1",
     "sseclient-py~=1.8.0",
@@ -100,7 +99,9 @@ dependencies = [
     "alibabacloud-dingtalk~=2.1.32",
     "ldap3~=2.9.1",
     "pypinyin~=0.53.0",
-    "flask-restful~=0.3.10"
+    "flask-restful~=0.3.10",
+    # Unstructured has Path Traversal via Malicious MSG Attachment that Allows Arbitrary File Write #106
+    "unstructured[docx,epub,md,ppt,pptx]~=0.18.18"
     ##### stop extend ######
 ]
 # Before adding new dependency, consider place it in

api/uv.lock

@@ -1690,7 +1690,7 @@ requires-dist = [
     { name = "tiktoken", specifier = "~=0.9.0" },
     { name = "tokenizers", specifier = "~=0.22.0" },
     { name = "transformers", specifier = "~=4.56.1" },
-    { name = "unstructured", extras = ["docx", "epub", "md", "ppt", "pptx"], specifier = "~=0.16.1" },
+    { name = "unstructured", extras = ["docx", "epub", "md", "ppt", "pptx"], specifier = "~=0.18.18" },
     { name = "validators", specifier = ">=0.34.0" },
     { name = "weave", specifier = ">=0.52.16" },
     { name = "weaviate-client", specifier = "==4.17.0" },
@@ -6866,12 +6866,12 @@ wheels = [
 
 [[package]]
 name = "unstructured"
-version = "0.16.25"
+version = "0.18.31"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "backoff" },
     { name = "beautifulsoup4" },
-    { name = "chardet" },
+    { name = "charset-normalizer" },
     { name = "dataclasses-json" },
     { name = "emoji" },
     { name = "filetype" },
@@ -6879,6 +6879,7 @@ dependencies = [
     { name = "langdetect" },
     { name = "lxml" },
     { name = "nltk" },
+    { name = "numba" },
     { name = "numpy" },
     { name = "psutil" },
     { name = "python-iso639" },
@@ -6891,9 +6892,9 @@ dependencies = [
     { name = "unstructured-client" },
     { name = "wrapt" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/64/31/98c4c78e305d1294888adf87fd5ee30577a4c393951341ca32b43f167f1e/unstructured-0.16.25.tar.gz", hash = "sha256:73b9b0f51dbb687af572ecdb849a6811710b9cac797ddeab8ee80fa07d8aa5e6", size = 1683097, upload-time = "2025-03-07T11:19:39.507Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a9/5f/64285bd69a538bc28753f1423fcaa9d64cd79a9e7c097171b1f0d27e9cdb/unstructured-0.18.31.tar.gz", hash = "sha256:af4bbe32d1894ae6e755f0da6fc0dd307a1d0adeebe0e7cc6278f6cf744339ca", size = 1707700, upload-time = "2026-01-27T15:33:05.378Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/12/4f/ad08585b5c8a33c82ea119494c4d3023f4796958c56e668b15cc282ec0a0/unstructured-0.16.25-py3-none-any.whl", hash = "sha256:14719ccef2830216cf1c5bf654f75e2bf07b17ca5dcee9da5ac74618130fd337", size = 1769286, upload-time = "2025-03-07T11:19:37.299Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/4a/9c43f39d9e443c9bc3f2e379b305bca27110adc653b071221b3132c18de5/unstructured-0.18.31-py3-none-any.whl", hash = "sha256:fab4641176cb9b192ed38048758aa0d9843121d03626d18f42275afb31e5b2d3", size = 1794889, upload-time = "2026-01-27T15:33:03.136Z" },
 ]
 
 [package.optional-dependencies]