Agent Loop

The agent stores conversation state in memory for the lifetime of the Agent instance.

For each prompt, it:

1. Adds the prompt as a user message.
2. Calls the configured model client.
3. Emits the assistant response.
4. Executes any tool_use blocks.
5. Adds tool_result blocks as a user message.
6. Repeats until the assistant returns no tool calls.
7. Emits a final result message.

const agent = createAgent({
  apiKey: process.env.DEEPSEEK_API_KEY,
  baseURL: "https://api.deepseek.com/anthropic",
  model: "deepseek-v4-flash",
  maxTurns: 10,
});

await agent.prompt("Remember that my project is an SDK.");
const result = await agent.prompt("What kind of project is this?");

maxTurns protects the host application from infinite tool loops. When the limit is reached, the SDK emits a result with subtype: "error_max_turns".