Chore/API for AgentflowV2 (#4696)

* Enhancement: Introduce prepended chat history handling in Agent and LLM nodes.

- Added support for `prependedChatHistory` in both `Agent` and `LLM` classes to allow for initial message context.
- Implemented validation for history schema in execution flow to ensure proper format.
- Refactored utility functions to include JSON sanitization and validation methods for improved data handling.

* update prediction swagger

packages/components/nodes/agentflow/Agent/Agent.ts

@@ -3,6 +3,7 @@ import {
     ICommonObject,
     IDatabaseEntity,
     IHumanInput,
+    IMessage,
     INode,
     INodeData,
     INodeOptionsValue,
@@ -696,6 +697,7 @@ class Agent_Agentflow implements INode {
             const state = options.agentflowRuntime?.state as ICommonObject
             const pastChatHistory = (options.pastChatHistory as BaseMessageLike[]) ?? []
             const runtimeChatHistory = (options.agentflowRuntime?.chatHistory as BaseMessageLike[]) ?? []
+            const prependedChatHistory = options.prependedChatHistory as IMessage[]
             const chatId = options.chatId as string
 
             // Initialize the LLM model instance
@@ -730,6 +732,18 @@ class Agent_Agentflow implements INode {
             // Use to keep track of past messages with image file references
             let pastImageMessagesWithFileRef: BaseMessageLike[] = []
 
+            // Prepend history ONLY if it is the first node
+            if (prependedChatHistory.length > 0 && !runtimeChatHistory.length) {
+                for (const msg of prependedChatHistory) {
+                    const role: string = msg.role === 'apiMessage' ? 'assistant' : 'user'
+                    const content: string = msg.content ?? ''
+                    messages.push({
+                        role,
+                        content
+                    })
+                }
+            }
+
             for (const msg of agentMessages) {
                 const role = msg.role
                 const content = msg.content

packages/components/nodes/agentflow/LLM/LLM.ts

@@ -1,5 +1,5 @@
 import { BaseChatModel } from '@langchain/core/language_models/chat_models'
-import { ICommonObject, INode, INodeData, INodeOptionsValue, INodeParams, IServerSideEventStreamer } from '../../../src/Interface'
+import { ICommonObject, IMessage, INode, INodeData, INodeOptionsValue, INodeParams, IServerSideEventStreamer } from '../../../src/Interface'
 import { AIMessageChunk, BaseMessageLike, MessageContentText } from '@langchain/core/messages'
 import { DEFAULT_SUMMARIZER_TEMPLATE } from '../prompt'
 import { z } from 'zod'
@@ -359,6 +359,7 @@ class LLM_Agentflow implements INode {
             const state = options.agentflowRuntime?.state as ICommonObject
             const pastChatHistory = (options.pastChatHistory as BaseMessageLike[]) ?? []
             const runtimeChatHistory = (options.agentflowRuntime?.chatHistory as BaseMessageLike[]) ?? []
+            const prependedChatHistory = options.prependedChatHistory as IMessage[]
             const chatId = options.chatId as string
 
             // Initialize the LLM model instance
@@ -382,6 +383,18 @@ class LLM_Agentflow implements INode {
             // Use to keep track of past messages with image file references
             let pastImageMessagesWithFileRef: BaseMessageLike[] = []
 
+            // Prepend history ONLY if it is the first node
+            if (prependedChatHistory.length > 0 && !runtimeChatHistory.length) {
+                for (const msg of prependedChatHistory) {
+                    const role: string = msg.role === 'apiMessage' ? 'assistant' : 'user'
+                    const content: string = msg.content ?? ''
+                    messages.push({
+                        role,
+                        content
+                    })
+                }
+            }
+
             for (const msg of llmMessages) {
                 const role = msg.role
                 const content = msg.content