Azure AI Agents Persistent SDK for Java

Low-level SDK for creating and managing persistent AI agents with threads, messages, runs, and tools.

Installation

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-agents-persistent</artifactId>
    <version>1.0.0-beta.1</version>
</dependency>

Environment Variables

PROJECT_ENDPOINT=https://<resource>.services.ai.azure.com/api/projects/<project> # Required for project configuration
MODEL_DEPLOYMENT_NAME=gpt-4o-mini # Required for agent model selection
AZURE_TOKEN_CREDENTIALS=prod  # Required only if DefaultAzureCredential is used in production

Authentication

import com.azure.ai.agents.persistent.PersistentAgentsClient;
import com.azure.ai.agents.persistent.PersistentAgentsClientBuilder;
import com.azure.core.credential.TokenCredential;
import com.azure.identity.AzureIdentityEnvVars;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.azure.identity.ManagedIdentityCredentialBuilder;

String endpoint = System.getenv("PROJECT_ENDPOINT");
TokenCredential credential = new DefaultAzureCredentialBuilder()
    .requireEnvVars(AzureIdentityEnvVars.AZURE_TOKEN_CREDENTIALS)
    .build();
// Or use a specific credential directly in production:
// See https://learn.microsoft.com/java/api/overview/azure/identity-readme?view=azure-java-stable#credential-classes
// TokenCredential credential = new ManagedIdentityCredentialBuilder().build();

PersistentAgentsClient client = new PersistentAgentsClientBuilder()
    .endpoint(endpoint)
    .credential(credential)
    .buildClient();

Key Concepts

The Azure AI Agents Persistent SDK provides a low-level API for managing persistent agents that can be reused across sessions.

Client Hierarchy

Core Workflow

1. Create Agent

// Create agent with tools
PersistentAgent agent = client.createAgent(
    modelDeploymentName,
    "Math Tutor",
    "You are a personal math tutor."
);

2. Create Thread

PersistentAgentThread thread = client.createThread();

3. Add Message

client.createMessage(
    thread.getId(),
    MessageRole.USER,
    "I need help with equations."
);

4. Run Agent

ThreadRun run = client.createRun(thread.getId(), agent.getId());

// Poll for completion
while (run.getStatus() == RunStatus.QUEUED || run.getStatus() == RunStatus.IN_PROGRESS) {
    Thread.sleep(500);
    run = client.getRun(thread.getId(), run.getId());
}

5. Get Response

PagedIterable<PersistentThreadMessage> messages = client.listMessages(thread.getId());
for (PersistentThreadMessage message : messages) {
    System.out.println(message.getRole() + ": " + message.getContent());
}

6. Cleanup

client.deleteThread(thread.getId());
client.deleteAgent(agent.getId());

Best Practices

1. Use DefaultAzureCredential for production authentication
2. Poll with appropriate delays — 500ms recommended between status checks
3. Clean up resources — Delete threads and agents when done
4. Handle all run statuses — Check for RequiresAction, Failed, Cancelled
5. Use async client for better throughput in high-concurrency scenarios

Error Handling

import com.azure.core.exception.HttpResponseException;

try {
    PersistentAgent agent = client.createAgent(modelName, name, instructions);
} catch (HttpResponseException e) {
    System.err.println("Error: " + e.getResponse().getStatusCode() + " - " + e.getMessage());
}

Reference Links