Usar Memória do Agente com o WayFlow

Neste artigo, você aprenderá a conectar a Memória do Agente a um agente do WayFlow para que o agente possa reutilizar fatos duráveis entre as sessões.

Dica: Para configurar o pacote, consulte Conceitos Básicos da Memória do Agente. Se você precisar de um Oracle AI Database local para este exemplo, consulte Executar o Oracle AI Database Localmente. Para saber mais sobre o WayFlow, consulte (https://github.com/oracle/wayflow).

Configurar Memória do Agente e WayFlow

Crie um thread de Memória do Agente para o usuário, exponha uma ferramenta search_memory ao WayFlow e construa o WayFlow Agent com uma OpenAIModel. A ferramenta search_memory consulta a API de Memória do Agente por usuário e ID do agente para que ele possa recuperar fatos duráveis de sessões anteriores, em vez de se limitar ao thread atual. O cliente de Memória do Agente também usa seu próprio LLM para extrair periodicamente memórias duráveis de mensagens de thread recentes, enquanto o WayFlow Agent continua a usar seu próprio OpenAIModel para respostas e chamadas de ferramenta.

import oracledb

from oracleagentmemory.core.embedders.embedder import Embedder
from oracleagentmemory.core.llms.llm import Llm
from oracleagentmemory.core.oracleagentmemory import OracleAgentMemory
from wayflowcore.agent import Agent
from wayflowcore.models import OpenAIModel
from wayflowcore.tools import tool

embedder = Embedder(
    model="YOUR_EMBEDDING_MODEL",
    api_base="YOUR_EMBEDDING_API_BASE",
    api_key="YOUR_EMBEDDING_API_KEY",
)
llm = Llm(
    model="gpt-4.1-mini",
    api_key="YOUR_OPENAI_API_KEY",
)
db_pool = oracledb.SessionPool(
    user="YOUR DB USER",
    password="YOUR DB PASSWORD",
    dsn="YOUR DB CONNECT STRING",
)
wayflow_llm = OpenAIModel(
    model_id="gpt-4.1-mini",
    api_key="YOUR_OPENAI_API_KEY",
)


#Keep these identifiers stable for the same assistant and end user so memory
#is scoped consistently across threads and sessions.
agent_id = "support_agent"
user_id = "user_123"
memory = OracleAgentMemory(
    connection=db_pool,
    embedder=embedder,
    llm=llm,
)
memory_thread = memory.create_thread(
    thread_id="wayflow_memory_demo",
    user_id=user_id,
    agent_id=agent_id,
)

from typing import Annotated


@tool
def search_memory(
    query: Annotated[str, "Question to search in Oracle Agent Memory"],
) -> Annotated[str, "Top matching memory content"]:
    """Search Oracle Agent Memory for durable user facts relevant to the current request."""
    results = memory.search(
        query=query,
        user_id=user_id,
        agent_id=agent_id,
        max_results=1,
        record_types=["memory"],
    )
    if not results:
        return "No relevant memory found."
    return results[0].content

assistant = Agent(
    llm=wayflow_llm,
    agent_id=agent_id,
    custom_instruction=(
        "You are a support agent. When the user asks about durable facts from "
        "prior sessions, call the search_memory tool before answering."
    ),
    tools=[search_memory],
)

Persistir Contexto do Usuário Após uma Sessão

Após cada sessão do WayFlow, anexe as mensagens trocadas à Memória do Agente e armazene qualquer fato durável que deva ser reutilizado posteriormente.

session_1 = assistant.start_conversation()
user_message = (
    "I am John, a Python developer and I need help debugging a payment service."
)
session_1.append_user_message(user_message)
session_1.execute()
assistant_reply = session_1.get_last_message().content

print(assistant_reply)
#I can help with that. What error are you seeing?

#add_messages will add messages to the DB and extract memories automatically
memory_thread.add_messages(
    [
        {"role": "user", "content": user_message},
        {"role": "assistant", "content": assistant_reply},
    ]
)
#add_memory adds memory to the DB
memory_thread.add_memory("The user is John, a Python developer.")

Reutilizar Memória em uma Nova Sessão do WayFlow

Quando uma sessão posterior for iniciada, reabra o mesmo thread de Memória do Agente e deixe que o agente do WayFlow chame search_memory para recuperar o contexto do usuário anterior.

memory_thread = memory.get_thread("wayflow_memory_demo")
assistant = Agent(
    llm=wayflow_llm,
    agent_id=agent_id,
    custom_instruction=(
        "You are a support agent. When the user asks about durable facts from "
        "prior sessions, call the search_memory tool before answering."
    ),
    tools=[search_memory],
)

session_2 = assistant.start_conversation()
session_2.append_user_message("Who am I?")
session_2.execute()
remembered_reply = session_2.get_last_message().content

print(remembered_reply)

Saída:

The user is John, a Python developer.

Uso Avançado

Para uma integração mais rígida, você pode registrar um listener de eventos do WayFlow que armazena entradas ConversationMessageAddedEvent e as grava na Memória do Agente no final de uma execução. Isso mantém o caminho de atualização da Memória do Agente desacoplado do código do thread principal enquanto persiste as mensagens finais trocadas.

from wayflowcore.events.event import ConversationMessageAddedEvent
from wayflowcore.events.eventlistener import GenericEventListener, register_event_listeners

pending_messages: list[dict[str, str]] = []


def _buffer_thread_message(event: ConversationMessageAddedEvent) -> None:
    if event.streamed:
        return
    pending_messages.append(
        {
            "role": event.message.role,
            "content": event.message.content,
        }
    )


message_listener = GenericEventListener(
    [ConversationMessageAddedEvent],
    _buffer_thread_message,
)

with register_event_listeners([message_listener]):
    session_3 = assistant.start_conversation()
    session_3.append_user_message("Please remember that I prefer concise code reviews.")
    session_3.execute()

if pending_messages:
    memory_thread.add_messages(pending_messages)

Desativar extração automática

Se você quiser apenas persistir mensagens e adicionar memórias duráveis manualmente, crie o cliente de Memória do Agente com extract_memories=False e insira as linhas de memória duráveis você mesmo.

manual_memory = OracleAgentMemory(
    connection=db_pool,
    embedder=embedder,
    extract_memories=False,
)
manual_memory_thread = manual_memory.create_thread(
    thread_id="wayflow_manual_memory_demo",
    user_id=user_id,
    agent_id=agent_id,
)
manual_memory_thread.add_messages(
    [
        {
            "role": "user",
            "content": "Please remember that I prefer concise code reviews.",
        },
        {
            "role": "assistant",
            "content": "Understood. I will keep responses concise.",
        },
    ]
)
manual_memory_thread.add_memory("The user prefers concise code reviews.")

Conclusão

Neste artigo, aprendemos a conectar a Memória do Agente a um agente do WayFlow, persistir mensagens trocadas e memórias duráveis após cada sessão e reutilizar o contexto anterior do usuário em execuções posteriores.

Dica: Depois de aprender a integrar a Memória do Agente ao WayFlow, você também pode se interessar em Integrar Memória do Agente ao LangGraph.

Código Inteiro

#Copyright © 2026 Oracle and/or its affiliates.
#This software is under the Apache License 2.0
#(LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0) or Universal Permissive License
#(UPL) 1.0 (LICENSE-UPL or https://oss.oracle.com/licenses/upl), at your option.
#Agent Memory Code Example - Integration with WayFlow
#-----------------------------------------------------

##Configure Oracle Memory and WayFlow

import oracledb

from oracleagentmemory.core.embedders.embedder import Embedder
from oracleagentmemory.core.llms.llm import Llm
from oracleagentmemory.core.oracleagentmemory import OracleAgentMemory
from wayflowcore.agent import Agent
from wayflowcore.models import OpenAIModel
from wayflowcore.tools import tool

embedder = Embedder(
    model="YOUR_EMBEDDING_MODEL",
    api_base="YOUR_EMBEDDING_API_BASE",
    api_key="YOUR_EMBEDDING_API_KEY",
)
llm = Llm(
    model="gpt-4.1-mini",
    api_key="YOUR_OPENAI_API_KEY",
)
db_pool = oracledb.SessionPool(
    user="YOUR DB USER",
    password="YOUR DB PASSWORD",
    dsn="YOUR DB CONNECT STRING",
)
wayflow_llm = OpenAIModel(
    model_id="gpt-4.1-mini",
    api_key="YOUR_OPENAI_API_KEY",
)

#Keep these identifiers stable for the same assistant and end user so memory
#is scoped consistently across threads and sessions.
agent_id = "support_agent"
user_id = "user_123"
memory = OracleAgentMemory(
    connection=db_pool,
    embedder=embedder,
    llm=llm,
)
memory_thread = memory.create_thread(
    thread_id="wayflow_memory_demo",
    user_id=user_id,
    agent_id=agent_id,
)

from typing import Annotated

@tool
def search_memory(
    query: Annotated[str, "Question to search in Oracle Agent Memory"],
) -> Annotated[str, "Top matching memory content"]:
    """Search Oracle Agent Memory for durable user facts relevant to the current request."""
    results = memory.search(
        query=query,
        user_id=user_id,
        agent_id=agent_id,
        max_results=1,
        record_types=["memory"],
    )
    if not results:
        return "No relevant memory found."
    return results[0].content

assistant = Agent(
    llm=wayflow_llm,
    agent_id=agent_id,
    custom_instruction=(
        "You are a support agent. When the user asks about durable facts from "
        "prior sessions, call the search_memory tool before answering."
    ),
    tools=[search_memory],
)

##Persist user context after a session

session_1 = assistant.start_conversation()
user_message = (
    "I am John, a Python developer and I need help debugging a payment service."
)
session_1.append_user_message(user_message)
session_1.execute()
assistant_reply = session_1.get_last_message().content

print(assistant_reply)
#I can help with that. What error are you seeing?

memory_thread.add_messages(
    [
        {"role": "user", "content": user_message},
        {"role": "assistant", "content": assistant_reply},
    ]
)
memory_thread.add_memory("The user is John, a Python developer.")

##Reuse memory in a new WayFlow session

memory_thread = memory.get_thread("wayflow_memory_demo")
assistant = Agent(
    llm=wayflow_llm,
    agent_id=agent_id,
    custom_instruction=(
        "You are a support agent. When the user asks about durable facts from "
        "prior sessions, call the search_memory tool before answering."
    ),
    tools=[search_memory],
)

session_2 = assistant.start_conversation()
session_2.append_user_message("Who am I?")
session_2.execute()
remembered_reply = session_2.get_last_message().content

print(remembered_reply)
#The user is John, a Python developer.

##Advanced use event listeners

from wayflowcore.events.event import ConversationMessageAddedEvent
from wayflowcore.events.eventlistener import GenericEventListener, register_event_listeners

pending_messages: list[dict[str, str]] = []

def _buffer_thread_message(event: ConversationMessageAddedEvent) -> None:
    if event.streamed:
        return
    pending_messages.append(
        {
            "role": event.message.role,
            "content": event.message.content,
        }
    )

message_listener = GenericEventListener(
    [ConversationMessageAddedEvent],
    _buffer_thread_message,
)

with register_event_listeners([message_listener]):
    session_3 = assistant.start_conversation()
    session_3.append_user_message("Please remember that I prefer concise code reviews.")
    session_3.execute()

if pending_messages:
    memory_thread.add_messages(pending_messages)

##Disable automatic memory extraction

manual_memory = OracleAgentMemory(
    connection=db_pool,
    embedder=embedder,
    extract_memories=False,
)
manual_memory_thread = manual_memory.create_thread(
    thread_id="wayflow_manual_memory_demo",
    user_id=user_id,
    agent_id=agent_id,
)
manual_memory_thread.add_messages(
    [
        {
            "role": "user",
            "content": "Please remember that I prefer concise code reviews.",
        },
        {
            "role": "assistant",
            "content": "Understood. I will keep responses concise.",
        },
    ]
)
manual_memory_thread.add_memory("The user prefers concise code reviews.")