Passaggio 4: Memoria e persistenza

Per impostazione predefinita, gli agenti archivieranno la cronologia delle chat in un InMemoryChatHistoryProvider o nel servizio di intelligenza artificiale sottostante, a seconda delle esigenze del servizio sottostante.

L'agente seguente usa OpenAI Chat Completion, che non supporta né richiede l'archiviazione della cronologia delle chat nel servizio, quindi crea e usa automaticamente un oggetto InMemoryChatHistoryProvider.

using System;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;

var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")
    ?? throw new InvalidOperationException("Set AZURE_OPENAI_ENDPOINT");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";

AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
    .AsAIAgent(
        model: deploymentName,
        instructions: "You are a friendly assistant. Keep your answers brief.",
        name: "MemoryAgent");

Per usare un personalizzato ChatHistoryProvider , è possibile passarne uno alle opzioni dell'agente:

using System;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;

var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")
    ?? throw new InvalidOperationException("Set AZURE_OPENAI_ENDPOINT");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";

AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
    .AsAIAgent(model: deploymentName, options: new ChatClientAgentOptions()
    {
        ChatOptions = new() { Instructions = "You are a helpful assistant." },
        ChatHistoryProvider = new CustomChatHistoryProvider()
    });

Usare una sessione per condividere il contesto tra le esecuzioni:

AgentSession session = await agent.CreateSessionAsync();

Console.WriteLine(await agent.RunAsync("Hello! What's the square root of 9?", session));
Console.WriteLine(await agent.RunAsync("My name is Alice", session));
Console.WriteLine(await agent.RunAsync("What is my name?", session));

Definire un provider di contesto che archivia le informazioni utente nello stato sessione e inserisce istruzioni di personalizzazione:

class UserMemoryProvider(ContextProvider):
    """A context provider that remembers user info in session state."""

    DEFAULT_SOURCE_ID = "user_memory"

    def __init__(self):
        super().__init__(self.DEFAULT_SOURCE_ID)

    async def before_run(
        self,
        *,
        agent: Any,
        session: AgentSession | None,
        context: SessionContext,
        state: dict[str, Any],
    ) -> None:
        """Inject personalization instructions based on stored user info."""
        user_name = state.get("user_name")
        if user_name:
            context.extend_instructions(
                self.source_id,
                f"The user's name is {user_name}. Always address them by name.",
            )
        else:
            context.extend_instructions(
                self.source_id,
                "You don't know the user's name yet. Ask for it politely.",
            )

    async def after_run(
        self,
        *,
        agent: Any,
        session: AgentSession | None,
        context: SessionContext,
        state: dict[str, Any],
    ) -> None:
        """Extract and store user info in session state after each call."""
        for msg in context.input_messages:
            text = msg.text if hasattr(msg, "text") else ""
            if isinstance(text, str) and "my name is" in text.lower():
                state["user_name"] = text.lower().split("my name is")[-1].strip().split()[0].capitalize()

Creare un agente con il fornitore di dati di contesto:

client = FoundryChatClient(
    project_endpoint="https://your-project.services.ai.azure.com",
    model="gpt-4o",
    credential=AzureCliCredential(),
)

agent = Agent(
    client=client,
    name="MemoryAgent",
    instructions="You are a friendly assistant.",
    context_providers=[UserMemoryProvider()],
)

Eseguilo — l'agente ora ha accesso al contesto

session = agent.create_session()

# The provider doesn't know the user yet — it will ask for a name
result = await agent.run("Hello! What's the square root of 9?", session=session)
print(f"Agent: {result}\n")

# Now provide the name — the provider stores it in session state
result = await agent.run("My name is Alice", session=session)
print(f"Agent: {result}\n")

# Subsequent calls are personalized — name persists via session state
result = await agent.run("What is 2 + 2?", session=session)
print(f"Agent: {result}\n")

# Inspect session state to see what the provider stored
provider_state = session.state.get("user_memory", {})
print(f"[Session State] Stored user name: {provider_state.get('user_name')}")

from agent_framework import InMemoryHistoryProvider
from agent_framework.mem0 import Mem0ContextProvider

memory_store = InMemoryHistoryProvider(load_messages=True) # add a history provider for persistence across sessions
agent_memory = Mem0ContextProvider("user-memory", api_key=..., agent_id="my-agent")  # add Mem0 provider for agent memory
audit_store = InMemoryHistoryProvider(
    "audit",
    load_messages=False,
    store_context_messages=True,  # include context added by other providers
)

agent = client.as_agent(
    name="MemoryAgent",
    instructions="You are a friendly assistant.",
    context_providers=[memory_store, agent_memory, audit_store],  # audit store last
)