}

  /**
   * Wrapper around {@link Stopwatch} which also contains an "expected completion time." Creating a
   * {@code Completion} starts the underlying stopwatch.
   */
  private static final class Completion {
    final Stopwatch stopwatch;
    final long expectedCompletionWaitMillis;

    Completion(long expectedCompletionWaitMillis) {
      this.expectedCompletionWaitMillis = expectedCompletionWaitMillis;

    }

    /**
     * Gets the number of completion tokens.
     *
     * @return the completion tokens count
     */
    public Integer getCompletionTokens() {
        return completionTokens;
    }

    /**
     * Sets the number of completion tokens.
     *
     * @param completionTokens the completion tokens count
     */

  }

  /**
   * Wrapper around {@link Stopwatch} which also contains an "expected completion time." Creating a
   * {@code Completion} starts the underlying stopwatch.
   */
  private static final class Completion {
    final Stopwatch stopwatch;
    final long expectedCompletionWaitMillis;

    Completion(long expectedCompletionWaitMillis) {
      this.expectedCompletionWaitMillis = expectedCompletionWaitMillis;

   * Runnable}, and arrange that {@code get} will return the given result on successful completion.
   *
   * @param runnable the runnable task
   * @param result the result to return on successful completion. If you don't need a particular
   *     result, consider using constructions of the form: {@code ListenableFuture<?> f =

* Give you the received data in the parameter `item`.
    * As you declared it in the function to be of type `Item`, you will also have all the editor support (completion, etc) for all of the attributes and their types.
* Generate [JSON Schema](https://json-schema.org) definitions for your model, you can also use them anywhere else you like if it makes sense for your project.

* production (meaning production software or environment): продакшн (do not change the ending, for example, translate `in production` as `в продакшн` (not `в продакшене`))
* completion (meaning code auto-completion): автозавершение
* editor (meaning component of IDE): редактор кода
* adopt (meaning start to use): использовать (or `начать использовать`)
* headers (meaning HTTP-headers): HTTP-заголовки

If you install Typer CLI, you can install completion with:

<div class="termy">

```console
$ typer --install-completion

zsh completion installed in /home/user/.bashrc.
Completion will take effect once you restart the terminal.
```

</div>

### Docs Structure

public interface LlmClient {

    /**
     * Performs a chat completion request.
     *
     * @param request the chat request containing messages and parameters
     * @return the chat response from the LLM
     * @throws LlmException if an error occurs during the request
     */
    LlmChatResponse chat(LlmChatRequest request);

    /**
     * Performs a streaming chat completion request.

  /**
   * Converts the given ThreadPoolExecutor into an ExecutorService that exits when the application
   * is complete. It does so by using daemon threads and adding a shutdown hook to wait for their
   * completion.
   *
   * <p>This is mainly for fixed thread pools. See {@link Executors#newFixedThreadPool(int)}.
   *
   * @param executor the executor to modify to make sure it exits when the application is finished

* in [Visual Studio Code](https://code.visualstudio.com/):

![editor support](https://fastapi.tiangolo.com/img/vscode-completion.png)

* in [PyCharm](https://www.jetbrains.com/pycharm/):

![editor support](https://fastapi.tiangolo.com/img/pycharm-completion.png)