refactor(workflow): inject http request node config through factories and defaults (#32365)

Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
-LAN-
2026-02-25 16:29:59 +08:00
committed by GitHub
parent 6f2c101e3c
commit 0964fc142e
15 changed files with 565 additions and 78 deletions

View File

@ -1,4 +1,3 @@
from collections.abc import Callable, Sequence
from typing import TYPE_CHECKING, final
from typing_extensions import override
@ -17,14 +16,10 @@ 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.http_request import HttpRequestNode, build_http_request_config
from core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node import KnowledgeRetrievalNode
from core.workflow.nodes.node_mapping import LATEST_VERSION, NODE_TYPE_CLASSES_MAPPING
from core.workflow.nodes.protocols import FileManagerProtocol, HttpClientProtocol
from core.workflow.nodes.template_transform.template_renderer import (
CodeExecutorJinja2TemplateRenderer,
Jinja2TemplateRenderer,
)
from core.workflow.nodes.template_transform.template_renderer import CodeExecutorJinja2TemplateRenderer
from core.workflow.nodes.template_transform.template_transform_node import TemplateTransformNode
if TYPE_CHECKING:
@ -45,23 +40,12 @@ 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,
template_renderer: Jinja2TemplateRenderer | None = None,
template_transform_max_output_length: int | None = None,
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
self._code_executor: type[CodeExecutor] = code_executor or CodeExecutor
self._code_providers: tuple[type[CodeNodeProvider], ...] = (
tuple(code_providers) if code_providers else CodeNode.default_code_providers()
)
self._code_limits = code_limits or CodeNodeLimits(
self._code_executor: type[CodeExecutor] = CodeExecutor
self._code_providers: tuple[type[CodeNodeProvider], ...] = CodeNode.default_code_providers()
self._code_limits = CodeNodeLimits(
max_string_length=dify_config.CODE_MAX_STRING_LENGTH,
max_number=dify_config.CODE_MAX_NUMBER,
min_number=dify_config.CODE_MIN_NUMBER,
@ -71,20 +55,24 @@ class DifyNodeFactory(NodeFactory):
max_string_array_length=dify_config.CODE_MAX_STRING_ARRAY_LENGTH,
max_object_array_length=dify_config.CODE_MAX_OBJECT_ARRAY_LENGTH,
)
self._template_renderer = template_renderer or CodeExecutorJinja2TemplateRenderer()
self._template_transform_max_output_length = (
template_transform_max_output_length or dify_config.TEMPLATE_TRANSFORM_MAX_LENGTH
)
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 or file_manager
self._template_renderer = CodeExecutorJinja2TemplateRenderer()
self._template_transform_max_output_length = dify_config.TEMPLATE_TRANSFORM_MAX_LENGTH
self._http_request_http_client = ssrf_proxy
self._http_request_tool_file_manager_factory = ToolFileManager
self._http_request_file_manager = 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 "",
)
self._document_extractor_unstructured_api_config = UnstructuredApiConfig(
api_url=dify_config.UNSTRUCTURED_API_URL,
api_key=dify_config.UNSTRUCTURED_API_KEY or "",
)
self._http_request_config = build_http_request_config(
max_connect_timeout=dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT,
max_read_timeout=dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT,
max_write_timeout=dify_config.HTTP_REQUEST_MAX_WRITE_TIMEOUT,
max_binary_size=dify_config.HTTP_REQUEST_NODE_MAX_BINARY_SIZE,
max_text_size=dify_config.HTTP_REQUEST_NODE_MAX_TEXT_SIZE,
ssl_verify=dify_config.HTTP_REQUEST_NODE_SSL_VERIFY,
ssrf_default_max_retries=dify_config.SSRF_DEFAULT_MAX_RETRIES,
)
@override
@ -146,6 +134,7 @@ class DifyNodeFactory(NodeFactory):
config=node_config,
graph_init_params=self.graph_init_params,
graph_runtime_state=self.graph_runtime_state,
http_request_config=self._http_request_config,
http_client=self._http_request_http_client,
tool_file_manager_factory=self._http_request_tool_file_manager_factory,
file_manager=self._http_request_file_manager,

View File

@ -1,4 +1,22 @@
from .entities import BodyData, HttpRequestNodeAuthorization, HttpRequestNodeBody, HttpRequestNodeData
from .config import build_http_request_config, resolve_http_request_config
from .entities import (
HTTP_REQUEST_CONFIG_FILTER_KEY,
BodyData,
HttpRequestNodeAuthorization,
HttpRequestNodeBody,
HttpRequestNodeConfig,
HttpRequestNodeData,
)
from .node import HttpRequestNode
__all__ = ["BodyData", "HttpRequestNode", "HttpRequestNodeAuthorization", "HttpRequestNodeBody", "HttpRequestNodeData"]
__all__ = [
"HTTP_REQUEST_CONFIG_FILTER_KEY",
"BodyData",
"HttpRequestNode",
"HttpRequestNodeAuthorization",
"HttpRequestNodeBody",
"HttpRequestNodeConfig",
"HttpRequestNodeData",
"build_http_request_config",
"resolve_http_request_config",
]

View File

@ -0,0 +1,33 @@
from collections.abc import Mapping
from .entities import HTTP_REQUEST_CONFIG_FILTER_KEY, HttpRequestNodeConfig
def build_http_request_config(
*,
max_connect_timeout: int = 10,
max_read_timeout: int = 600,
max_write_timeout: int = 600,
max_binary_size: int = 10 * 1024 * 1024,
max_text_size: int = 1 * 1024 * 1024,
ssl_verify: bool = True,
ssrf_default_max_retries: int = 3,
) -> HttpRequestNodeConfig:
return HttpRequestNodeConfig(
max_connect_timeout=max_connect_timeout,
max_read_timeout=max_read_timeout,
max_write_timeout=max_write_timeout,
max_binary_size=max_binary_size,
max_text_size=max_text_size,
ssl_verify=ssl_verify,
ssrf_default_max_retries=ssrf_default_max_retries,
)
def resolve_http_request_config(filters: Mapping[str, object] | None) -> HttpRequestNodeConfig:
if not filters:
raise ValueError("http_request_config is required to build HTTP request default config")
config = filters.get(HTTP_REQUEST_CONFIG_FILTER_KEY)
if not isinstance(config, HttpRequestNodeConfig):
raise ValueError("http_request_config must be an HttpRequestNodeConfig instance")
return config

View File

@ -1,5 +1,6 @@
import mimetypes
from collections.abc import Sequence
from dataclasses import dataclass
from email.message import Message
from typing import Any, Literal
@ -7,9 +8,10 @@ import charset_normalizer
import httpx
from pydantic import BaseModel, Field, ValidationInfo, field_validator
from configs import dify_config
from core.workflow.nodes.base import BaseNodeData
HTTP_REQUEST_CONFIG_FILTER_KEY = "http_request_config"
class HttpRequestNodeAuthorizationConfig(BaseModel):
type: Literal["basic", "bearer", "custom"]
@ -59,9 +61,27 @@ class HttpRequestNodeBody(BaseModel):
class HttpRequestNodeTimeout(BaseModel):
connect: int = dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT
read: int = dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT
write: int = dify_config.HTTP_REQUEST_MAX_WRITE_TIMEOUT
connect: int | None = None
read: int | None = None
write: int | None = None
@dataclass(frozen=True, slots=True)
class HttpRequestNodeConfig:
max_connect_timeout: int
max_read_timeout: int
max_write_timeout: int
max_binary_size: int
max_text_size: int
ssl_verify: bool
ssrf_default_max_retries: int
def default_timeout(self) -> "HttpRequestNodeTimeout":
return HttpRequestNodeTimeout(
connect=self.max_connect_timeout,
read=self.max_read_timeout,
write=self.max_write_timeout,
)
class HttpRequestNodeData(BaseNodeData):
@ -91,7 +111,7 @@ class HttpRequestNodeData(BaseNodeData):
params: str
body: HttpRequestNodeBody | None = None
timeout: HttpRequestNodeTimeout | None = None
ssl_verify: bool | None = dify_config.HTTP_REQUEST_NODE_SSL_VERIFY
ssl_verify: bool | None = None
class Response:

View File

@ -10,7 +10,6 @@ from urllib.parse import urlencode, urlparse
import httpx
from json_repair import repair_json
from configs import dify_config
from core.helper.ssrf_proxy import ssrf_proxy
from core.variables.segments import ArrayFileSegment, FileSegment
from core.workflow.file.enums import FileTransferMethod
@ -20,6 +19,7 @@ from core.workflow.runtime import VariablePool
from ..protocols import FileManagerProtocol, HttpClientProtocol
from .entities import (
HttpRequestNodeAuthorization,
HttpRequestNodeConfig,
HttpRequestNodeData,
HttpRequestNodeTimeout,
Response,
@ -78,10 +78,13 @@ class Executor:
node_data: HttpRequestNodeData,
timeout: HttpRequestNodeTimeout,
variable_pool: VariablePool,
max_retries: int = dify_config.SSRF_DEFAULT_MAX_RETRIES,
http_request_config: HttpRequestNodeConfig,
max_retries: int | None = None,
ssl_verify: bool | None = None,
http_client: HttpClientProtocol | None = None,
file_manager: FileManagerProtocol | None = None,
):
self._http_request_config = http_request_config
# If authorization API key is present, convert the API key using the variable pool
if node_data.authorization.type == "api-key":
if node_data.authorization.config is None:
@ -99,14 +102,20 @@ class Executor:
self.method = node_data.method
self.auth = node_data.authorization
self.timeout = timeout
self.ssl_verify = node_data.ssl_verify
self.ssl_verify = ssl_verify if ssl_verify is not None else node_data.ssl_verify
if self.ssl_verify is None:
self.ssl_verify = self._http_request_config.ssl_verify
if not isinstance(self.ssl_verify, bool):
raise ValueError("ssl_verify must be a boolean")
self.params = None
self.headers = {}
self.content = None
self.files = None
self.data = None
self.json = None
self.max_retries = max_retries
self.max_retries = (
max_retries if max_retries is not None else self._http_request_config.ssrf_default_max_retries
)
self._http_client = http_client or ssrf_proxy
self._file_manager = file_manager or default_file_manager
@ -319,9 +328,9 @@ class Executor:
executor_response = Response(response)
threshold_size = (
dify_config.HTTP_REQUEST_NODE_MAX_BINARY_SIZE
self._http_request_config.max_binary_size
if executor_response.is_file
else dify_config.HTTP_REQUEST_NODE_MAX_TEXT_SIZE
else self._http_request_config.max_text_size
)
if executor_response.size > threshold_size:
raise ResponseSizeError(

View File

@ -3,7 +3,6 @@ import mimetypes
from collections.abc import Callable, Mapping, Sequence
from typing import TYPE_CHECKING, Any
from configs import dify_config
from core.helper.ssrf_proxy import ssrf_proxy
from core.tools.tool_file_manager import ToolFileManager
from core.variables.segments import ArrayFileSegment
@ -18,19 +17,16 @@ from core.workflow.nodes.http_request.executor import Executor
from core.workflow.nodes.protocols import FileManagerProtocol, HttpClientProtocol
from factories import file_factory
from .config import build_http_request_config, resolve_http_request_config
from .entities import (
HTTP_REQUEST_CONFIG_FILTER_KEY,
HttpRequestNodeConfig,
HttpRequestNodeData,
HttpRequestNodeTimeout,
Response,
)
from .exc import HttpRequestNodeError, RequestBodyError
HTTP_REQUEST_DEFAULT_TIMEOUT = HttpRequestNodeTimeout(
connect=dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT,
read=dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT,
write=dify_config.HTTP_REQUEST_MAX_WRITE_TIMEOUT,
)
logger = logging.getLogger(__name__)
if TYPE_CHECKING:
@ -48,6 +44,7 @@ class HttpRequestNode(Node[HttpRequestNodeData]):
graph_init_params: "GraphInitParams",
graph_runtime_state: "GraphRuntimeState",
*,
http_request_config: HttpRequestNodeConfig,
http_client: HttpClientProtocol | None = None,
tool_file_manager_factory: Callable[[], ToolFileManager] = ToolFileManager,
file_manager: FileManagerProtocol | None = None,
@ -58,12 +55,18 @@ class HttpRequestNode(Node[HttpRequestNodeData]):
graph_init_params=graph_init_params,
graph_runtime_state=graph_runtime_state,
)
self._http_request_config = http_request_config
self._http_client = http_client or ssrf_proxy
self._tool_file_manager_factory = tool_file_manager_factory
self._file_manager = file_manager or default_file_manager
@classmethod
def get_default_config(cls, filters: Mapping[str, object] | None = None) -> Mapping[str, object]:
if not filters or HTTP_REQUEST_CONFIG_FILTER_KEY not in filters:
http_request_config = build_http_request_config()
else:
http_request_config = resolve_http_request_config(filters)
default_timeout = http_request_config.default_timeout()
return {
"type": "http-request",
"config": {
@ -73,15 +76,15 @@ class HttpRequestNode(Node[HttpRequestNodeData]):
},
"body": {"type": "none"},
"timeout": {
**HTTP_REQUEST_DEFAULT_TIMEOUT.model_dump(),
"max_connect_timeout": dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT,
"max_read_timeout": dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT,
"max_write_timeout": dify_config.HTTP_REQUEST_MAX_WRITE_TIMEOUT,
**default_timeout.model_dump(),
"max_connect_timeout": http_request_config.max_connect_timeout,
"max_read_timeout": http_request_config.max_read_timeout,
"max_write_timeout": http_request_config.max_write_timeout,
},
"ssl_verify": dify_config.HTTP_REQUEST_NODE_SSL_VERIFY,
"ssl_verify": http_request_config.ssl_verify,
},
"retry_config": {
"max_retries": dify_config.SSRF_DEFAULT_MAX_RETRIES,
"max_retries": http_request_config.ssrf_default_max_retries,
"retry_interval": 0.5 * (2**2),
"retry_enabled": True,
},
@ -98,7 +101,9 @@ class HttpRequestNode(Node[HttpRequestNodeData]):
node_data=self.node_data,
timeout=self._get_request_timeout(self.node_data),
variable_pool=self.graph_runtime_state.variable_pool,
http_request_config=self._http_request_config,
max_retries=0,
ssl_verify=self.node_data.ssl_verify,
http_client=self._http_client,
file_manager=self._file_manager,
)
@ -142,16 +147,17 @@ class HttpRequestNode(Node[HttpRequestNodeData]):
error_type=type(e).__name__,
)
@staticmethod
def _get_request_timeout(node_data: HttpRequestNodeData) -> HttpRequestNodeTimeout:
def _get_request_timeout(self, node_data: HttpRequestNodeData) -> HttpRequestNodeTimeout:
default_timeout = self._http_request_config.default_timeout()
timeout = node_data.timeout
if timeout is None:
return HTTP_REQUEST_DEFAULT_TIMEOUT
return default_timeout
timeout.connect = timeout.connect or HTTP_REQUEST_DEFAULT_TIMEOUT.connect
timeout.read = timeout.read or HTTP_REQUEST_DEFAULT_TIMEOUT.read
timeout.write = timeout.write or HTTP_REQUEST_DEFAULT_TIMEOUT.write
return timeout
return HttpRequestNodeTimeout(
connect=timeout.connect or default_timeout.connect,
read=timeout.read or default_timeout.read,
write=timeout.write or default_timeout.write,
)
@classmethod
def _extract_variable_selector_to_variable_mapping(