}

    @Test
    public void test_constructorWithRoleAndContent() {
        final LlmMessage message = new LlmMessage("system", "You are a helpful assistant.");
        assertEquals("system", message.getRole());
        assertEquals("You are a helpful assistant.", message.getContent());
    }

    @Test
    public void test_systemFactory() {
        final LlmMessage message = LlmMessage.system("System prompt");

   *
   * @param url the URL to read from
   * @param charset the charset used to decode the input stream; see {@link StandardCharsets} for
   *     helpful predefined constants
   * @return a string containing all the characters from the URL
   * @throws IOException if an I/O error occurs.
   */
  public static String toString(URL url, Charset charset) throws IOException {

start by opening a new issue describing the bug or feature you're intending to
fix. Even if you think it's relatively minor, it's helpful to know what people
are working on. And as mentioned above, API changes should be discussed
thoroughly before moving to code.

Some examples of types of pull requests that are immediately helpful:

  - Fixing a bug without changing a public API.
  - Fixing or improving documentation.

   * java.nio.file.Files#newBufferedReader(java.nio.file.Path, Charset)}.
   *
   * @param file the file to read from
   * @param charset the charset used to decode the input stream; see {@link StandardCharsets} for
   *     helpful predefined constants
   * @return the buffered reader
   */
  public static BufferedReader newReader(File file, Charset charset) throws FileNotFoundException {
    checkNotNull(file);
    checkNotNull(charset);

    steps:
    - name: Checkout code
      uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
      with:
        ref: ${{ github.event.inputs.release_branch }}
    - name: Get some helpful info for formatting
      id: cherrypick
      run: |
          git config --global user.name "TensorFlow Release Automation"
          git config --global user.email "******@****.***"
          git fetch origin master

TFCI_WHL_SIZE_LIMIT=450M
TFCI_WHL_SIZE_LIMIT_ENABLE=1
TFCI_WHL_IMPORT_TEST_ENABLE=1
TFCI_PYTHON_VERIFY_PIP_INSTALL_ARGS=""

# Used to simulate a T:\ drive within the container, to a limited extent,
# via a symlink.
# Helpful since the internal CI utilizes a T:\ drive, part of which is mounted
# to the container, and would result in C:\<path> != T:\<path> mismatches,
# when using variables like `TFCI_OUTPUT_DIR` in `docker exec commands,

        programmers everywhere. If you can give enough detail such that any of us can imagine coming
        across a similar need in our own work, that's extremely helpful in studying how broadly
        useful the proposed change will be.

  - type: textarea
    attributes:
      label: Concrete Use Cases
      description: Please provide use cases that actually came up in the real world.

        assertTrue(request.isStream());
    }

    @Test
    public void test_fluentBuilding() {
        final LlmChatRequest request = new LlmChatRequest().addSystemMessage("You are a helpful assistant")
                .addUserMessage("Hello!")
                .addAssistantMessage("Hi there!")
                .addUserMessage("How are you?")
                .setModel("llama3")

[guava.dev/ImmutableList](https://guava.dev/ImmutableList)!

## Learn about Guava

-   Our users' guide, [Guava Explained]
-   [A nice collection](https://www.tfnico.com/presentations/google-guava) of
    other helpful links

## Links

-   [GitHub project](https://github.com/google/guava)
-   [Issue tracker: Report a defect or feature request](https://github.com/google/guava/issues/new)

        everywhere. If you can give enough detail such that any of us can imagine coming across
        a similar need in our own work, that's extremely helpful in studying how broadly useful the
        feature will be.

  - type: textarea
    attributes:
      label: Concrete Use Cases
      description: Please provide use cases that actually came up in the real world.