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.2</version>
</dependency>

Environment Variables

export PROJECT_ENDPOINT="https://<resource>.services.ai.azure.com/api/projects/<project>"
export MODEL_DEPLOYMENT_NAME="gpt-4o-mini"

Authentication

import com.azure.ai.agents.persistent.PersistentAgentsClient;
import com.azure.ai.agents.persistent.PersistentAgentsClientBuilder;
import com.azure.ai.agents.persistent.*;
import com.azure.ai.agents.persistent.models.*;
import com.azure.core.http.rest.PagedIterable;
import com.azure.identity.DefaultAzureCredentialBuilder;

String endpoint = System.getenv("PROJECT_ENDPOINT");
PersistentAgentsClient client = new PersistentAgentsClientBuilder()
    .endpoint(endpoint)
    .credential(new DefaultAzureCredentialBuilder().build())
    .buildClient();
String modelDeploymentName = System.getenv("MODEL_DEPLOYMENT_NAME");
PersistentAgentsAdministrationClient administration = client.getPersistentAgentsAdministrationClient();
ThreadsClient threads = client.getThreadsClient();
MessagesClient messageClient = client.getMessagesClient();
RunsClient runs = client.getRunsClient();

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 = administration.createAgent(
    new CreateAgentOptions(modelDeploymentName)
        .setName("Math Tutor")
        .setInstructions("You are a personal math tutor.")
);

2. Create Thread

PersistentAgentThread thread = threads.createThread();

3. Add Message

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

4. Run Agent

ThreadRun run = runs.createRun(new CreateRunOptions(thread.getId(), agent.getId()));

// Bound polling; a terminal non-success state is not a completed answer.
long deadline = System.nanoTime() + java.util.concurrent.TimeUnit.SECONDS.toNanos(60);
while (run.getStatus() == RunStatus.QUEUED || run.getStatus() == RunStatus.IN_PROGRESS) {
    if (System.nanoTime() > deadline) {
        throw new IllegalStateException("Run polling timed out; inspect/cancel the owned run separately");
    }
    Thread.sleep(500);
    run = runs.getRun(thread.getId(), run.getId());
}

Check the resulting status before reading a final response: requires_action needs an authorized tool-output handler; failed, cancelled, expired or other non-success states must be reported explicitly. A polling timeout does not cancel the cloud run.

5. Get Response

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

6. Cleanup

threads.deleteThread(thread.getId());
administration.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 exampleAgent = administration.createAgent(
        new CreateAgentOptions(modelDeploymentName).setName("Example").setInstructions("Answer briefly"));
} catch (HttpResponseException e) {
    System.err.println("Error: " + e.getResponse().getStatusCode() + " - " + e.getMessage());
}

Reference Links

…