Steg 4: Minne och beständighet

Som standard lagrar agenter chatthistorik i en InMemoryChatHistoryProvider eller i den underliggande AI-tjänsten, beroende på vad den underliggande tjänsten kräver.

Följande agent använder OpenAI Chat Completion, som varken stöder eller kräver lagring av chatthistorik i tjänsten, så skapar och använder därför automatiskt en 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");

Om du vill använda en anpassad ChatHistoryProvider kan du skicka en till agentalternativen:

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()
    });

Använd en session för att dela kontext mellan körningar:

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));

Det fullständiga exemplet definierar en kontextprovider, lägger till den i en agent och använder en session för att bevara anpassningstillståndet:

import asyncio
from typing import Any

from agent_framework import Agent, AgentSession, ContextProvider, SessionContext
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential


class UserMemoryProvider(ContextProvider):
    def __init__(self) -> None:
        super().__init__("user_memory")

    async def before_run(
        self,
        *,
        agent: Any,
        session: AgentSession | None,
        context: SessionContext,
        state: dict[str, Any],
    ) -> None:
        user_name = state.get("user_name")
        instructions = (
            f"The user's name is {user_name}. Address them by name." if user_name else "Ask for the user's name."
        )
        context.extend_instructions(self.source_id, instructions)

    async def after_run(
        self,
        *,
        agent: Any,
        session: AgentSession | None,
        context: SessionContext,
        state: dict[str, Any],
    ) -> None:
        for message in context.input_messages:
            text = message.text
            if not isinstance(text, str):
                continue
            _, marker, name = text.lower().partition("my name is")
            if marker and name.strip():
                state["user_name"] = name.split()[0].capitalize()


async def main() -> None:
    agent = Agent(
        client=FoundryChatClient(
            project_endpoint="https://your-account.services.ai.azure.com/api/projects/your-project",
            model="gpt-6-luna",
            credential=AzureCliCredential(),
        ),
        instructions="You are a friendly assistant.",
        context_providers=[UserMemoryProvider()],
    )
    session = agent.create_session()

    print(await agent.run("Hello! What's the square root of 9?", session=session))
    print(await agent.run("My name is Alice", session=session))
    print(await agent.run("What is 2 + 2?", session=session))


if __name__ == "__main__":
    asyncio.run(main())

from agent_framework import InMemoryHistoryProvider
from agent_framework.foundry import FoundryMemoryProvider

history = InMemoryHistoryProvider(load_messages=True)
memory = FoundryMemoryProvider(
    project_client=project_client,
    memory_store_name="user-memory",
    scope="user-123",
)
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=[history, memory, audit_store],  # audit store last
)

Som standard använder agenter antingen lokal minnesintern historik eller tjänsthanterad historik beroende på provider och session.

Följande Foundry-agent använder en projektbaserad modelldistribution. Lägg till en kontextprovider när du vill ha programspecifikt minne eller anpassningstillstånd utöver konversationshistoriken.

a := foundryprovider.NewAgent(
    endpoint,
    token,
    foundryprovider.ModelDeployment(model),
    foundryprovider.AgentConfig{
        Instructions: "You are a friendly assistant. Keep your answers brief.",
        Config: agent.Config{
            Name: "MemoryAgent",
        },
    },
)

Definiera en kontextprovider som lagrar användarinformation i sessionstillstånd och matar in anpassningsinstruktioner:

import (
    "context"
    "fmt"
    "strings"

    "github.com/microsoft/agent-framework-go/agent"
    "github.com/microsoft/agent-framework-go/message"
)

const userMemorySourceID = "user_memory"

type providerState struct {
    UserName string `json:"user_name,omitempty"`
}

func newUserMemoryProvider() agent.ContextProvider {
    return agent.NewContextProvider(agent.ContextProviderConfig{
        SourceID: userMemorySourceID,
        Provide:  provideUserMemory,
        Store:    storeUserMemory,
    })
}

func provideUserMemory(ctx context.Context, invoking agent.InvokingContext) ([]*message.Message, []agent.Option, error) {
    session, _ := agent.GetOption(invoking.Options, agent.WithSession)
    var state providerState
    _, _ = session.Get(userMemorySourceID, &state)

    instructions := "You don't know the user's name yet. Ask for it politely."
    if state.UserName != "" {
        instructions = fmt.Sprintf("The user's name is %s. Always address them by name.", state.UserName)
    }
    return nil, []agent.Option{agent.WithInstructions(instructions)}, nil
}

func storeUserMemory(ctx context.Context, invoked agent.InvokedContext) error {
    session, _ := agent.GetOption(invoked.Options, agent.WithSession)
    var state providerState
    _, _ = session.Get(userMemorySourceID, &state)
    for _, msg := range invoked.RequestMessages {
        text := strings.TrimSpace(msg.Contents.Text())
        lower := strings.ToLower(text)
        if idx := strings.Index(lower, "my name is"); idx >= 0 {
            parts := strings.Fields(text[idx+len("my name is"):])
            if len(parts) == 0 {
                continue
            }
            state.UserName = strings.Trim(parts[0], ".,!?")
            session.Set(userMemorySourceID, state)
            break
        }
    }
    return nil
}

Skapa en agent med kontextprovidern:

a := foundryprovider.NewAgent(
    endpoint,
    token,
    foundryprovider.ModelDeployment(model),
    foundryprovider.AgentConfig{
        Instructions: "You are a friendly assistant.",
        Config: agent.Config{
            Name:             "MemoryAgent",
            ContextProviders: []agent.ContextProvider{newUserMemoryProvider()},
        },
    },
)

Kör det – agenten har nu åtkomst till kontexten:

ctx := context.Background()
session, err := a.CreateSession(ctx)
if err != nil {
    panic(err)
}

// The provider doesn't know the user yet.
resp, err := a.RunText(ctx, "Hello, what is the square root of 9?", agent.WithSession(session)).Collect()
fmt.Println(resp, err)

// Teach the provider the user's name.
resp, err = a.RunText(ctx, "My name is Alice", agent.WithSession(session)).Collect()
fmt.Println(resp, err)

// Subsequent calls are personalized using session state.
resp, err = a.RunText(ctx, "What is 2 + 2?", agent.WithSession(session)).Collect()
fmt.Println(resp, err)