final LlmChatRequest result = request.addSystemMessage("System prompt");

        assertSame(request, result);
        assertEquals(1, request.getMessages().size());
        assertEquals(LlmMessage.ROLE_SYSTEM, request.getMessages().get(0).getRole());
        assertEquals("System prompt", request.getMessages().get(0).getContent());
    }

    @Test
    public void test_addUserMessage() {

Si no lo recibe, devuelve un error HTTP 401 "Unauthorized".

Y devuelve un header `WWW-Authenticate` con un valor de `Basic`, y un parámetro `realm` opcional.

Eso le dice al navegador que muestre el prompt integrado para un nombre de usuario y contraseña.

Luego, cuando escribes ese nombre de usuario y contraseña, el navegador los envía automáticamente en el header.

## Simple HTTP Basic Auth { #simple-http-basic-auth }

  override fun getPasswordAuthentication(): PasswordAuthentication? {
    calls.add(
      "host=$requestingHost port=$requestingPort site=${requestingSite.hostName} " +
        "url=$requestingURL type=$requestorType prompt=$requestingPrompt " +
        "protocol=$requestingProtocol scheme=$requestingScheme",
    )
    return authentication
  }

  companion object {
    /** base64("username:password")  */

## Context

The Gradle core platform provides many services to the Gradle platforms and builds logic. One such group of services allows logic to interact with the build user, to provide diagnostics, progress information, prompt for questions, and so on. Currently, these services are part of the core platform runtime architecture module.

A downside of this structure is that it is difficult to do focused work on the Gradle UI.

## Decision

{* ../../docs_src/stream_json_lines/tutorial001_py310.py ln[33:36] hl[34] *}

## Événements envoyés par le serveur (SSE) { #server-sent-events-sse }

       * we're copying into a `contents` array whose type allows it to contain nulls. Still, it's
       * worth noting that we promise not to put nulls into the array in the first `size` elements.
       * We uphold that promise here because our callers promise that `elements` will not contain
       * nulls in its first `n` elements.
       */
      System.arraycopy(elements, 0, contents, size, n);
      size += n;

    requirements {
        requiresOs(Os.LINUX)
    }

    params {
        text(
            "wrapperVersion",
            "should-be-overridden",
            display = ParameterDisplay.PROMPT,
            allowEmpty = false,
            description =
                "The version of Gradle to update to. " +
                    "Can be a specific version or one of 'latest', 'release-candidate', 'release-milestone'",

 * such as Ollama, OpenAI, and Google Gemini.
 *
 * In addition to low-level chat operations, this interface defines
 * high-level RAG workflow methods that allow each provider to optimize
 * prompt construction, parameter tuning, and response parsing.
 */
public interface LlmClient {

    /**
     * Performs a chat completion request.
     *

      call.call.cancel()
    }
    for (call in runningAsyncCalls) {
      call.call.cancel()
    }
    for (call in runningSyncCalls) {
      call.cancel()
    }
  }

  /**
   * Promotes eligible calls from [readyAsyncCalls] to [runningAsyncCalls] and runs them on the
   * executor service. Must not be called with synchronization because executing calls can call
   * into user code.
   *

This policy protects our limited review budget, allowing us to invest our attention wisely.

A pull request is not a finished product—it is the start of a conversation, and an implied contract: we promise to provide thoughtful feedback, and we expect the contributor to engage with us in return.

## What we expect from contributors