chore(api): adapt Graphon 0.2.2 upgrade (#35377)

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

api/core/workflow/node_runtime.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from collections.abc import Callable, Generator, Mapping, Sequence
 from dataclasses import dataclass
-from typing import TYPE_CHECKING, Any, cast
+from typing import TYPE_CHECKING, Any, Literal, cast, overload
 
 from sqlalchemy import select
 from sqlalchemy.orm import Session
@@ -41,7 +41,7 @@ from graphon.model_runtime.entities.llm_entities import (
 )
 from graphon.model_runtime.entities.message_entities import PromptMessage, PromptMessageTool
 from graphon.model_runtime.entities.model_entities import AIModelEntity
-from graphon.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
+from graphon.model_runtime.model_providers.base.large_language_model import LargeLanguageModel
 from graphon.nodes.human_input.entities import HumanInputNodeData
 from graphon.nodes.llm.runtime_protocols import (
     PreparedLLMProtocol,
@@ -64,7 +64,7 @@ from models.dataset import SegmentAttachmentBinding
 from models.model import UploadFile
 from services.tools.builtin_tools_manage_service import BuiltinToolManageService
 
-from .human_input_compat import (
+from .human_input_adapter import (
     BoundRecipient,
     DeliveryChannelConfig,
     DeliveryMethodType,
@@ -173,6 +173,28 @@ class DifyPreparedLLM(PreparedLLMProtocol):
     def get_llm_num_tokens(self, prompt_messages: Sequence[PromptMessage]) -> int:
         return self._model_instance.get_llm_num_tokens(prompt_messages)
 
+    @overload
+    def invoke_llm(
+        self,
+        *,
+        prompt_messages: Sequence[PromptMessage],
+        model_parameters: Mapping[str, Any],
+        tools: Sequence[PromptMessageTool] | None,
+        stop: Sequence[str] | None,
+        stream: Literal[False],
+    ) -> LLMResult: ...
+
+    @overload
+    def invoke_llm(
+        self,
+        *,
+        prompt_messages: Sequence[PromptMessage],
+        model_parameters: Mapping[str, Any],
+        tools: Sequence[PromptMessageTool] | None,
+        stop: Sequence[str] | None,
+        stream: Literal[True],
+    ) -> Generator[LLMResultChunk, None, None]: ...
+
     def invoke_llm(
         self,
         *,
@@ -190,6 +212,28 @@ class DifyPreparedLLM(PreparedLLMProtocol):
             stream=stream,
         )
 
+    @overload
+    def invoke_llm_with_structured_output(
+        self,
+        *,
+        prompt_messages: Sequence[PromptMessage],
+        json_schema: Mapping[str, Any],
+        model_parameters: Mapping[str, Any],
+        stop: Sequence[str] | None,
+        stream: Literal[False],
+    ) -> LLMResultWithStructuredOutput: ...
+
+    @overload
+    def invoke_llm_with_structured_output(
+        self,
+        *,
+        prompt_messages: Sequence[PromptMessage],
+        json_schema: Mapping[str, Any],
+        model_parameters: Mapping[str, Any],
+        stop: Sequence[str] | None,
+        stream: Literal[True],
+    ) -> Generator[LLMResultChunkWithStructuredOutput, None, None]: ...
+
     def invoke_llm_with_structured_output(
         self,
         *,