[CI] fix test: use minimum supported layered output count

[david6666666]

PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.

Purpose

fix CI

__________________________________________________ test_layered_output_image_count[layers_guard_001_layers2] ___________________________________________________
omni_server = <tests.conftest.OmniServer object at 0x77460033d400>, openai_client = <tests.conftest.OpenAIClientHandler object at 0x77460033fbc0>
expected_layers = 2
    @pytest.mark.advanced_model
    @pytest.mark.diffusion
    @pytest.mark.parametrize(
        "omni_server, expected_layers",
        LAYERS_GUARD_CASES,
        indirect=["omni_server"],
    )
    def test_layered_output_image_count(
        omni_server: OmniServer,
        openai_client: OpenAIClientHandler,
        expected_layers: int,
    ):
        """Guard for https://github.com/vllm-project/vllm-omni/issues/1969
        The bug: API flattened the multi-layer output into a single image.
        Expected: API response content must be a list containing exactly
        `layers image_url items, one per decomposed layer.
        """
        image_data_url = f"data:image/jpeg;base64,{generate_synthetic_image(512, 512)['base64']}"
        messages = dummy_messages_from_mix_data(image_data_url=image_data_url, content_text=EDIT_PROMPT)
        request_config = {
            "model": omni_server.model,
            "messages": messages,
            "extra_body": {
                "num_inference_steps": 2,
                "negative_prompt": NEGATIVE_PROMPT,
                "true_cfg_scale": 4.0,
                "seed": 42,
                "layers": expected_layers,
            },
        }
>       image_items = _collect_image_url_items(openai_client, request_config)
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
tests/e2e/online_serving/test_qwen_image_layered_expansion.py:180:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
tests/e2e/online_serving/test_qwen_image_layered_expansion.py:119: in _collect_image_url_items
    chat_completion = openai_client.client.chat.completions.create(
/usr/local/lib/python3.12/dist-packages/openai/_utils/_utils.py:286: in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
/usr/local/lib/python3.12/dist-packages/openai/resources/chat/completions/completions.py:1204: in create
    return self._post(
/usr/local/lib/python3.12/dist-packages/openai/_base_client.py:1297: in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <openai.OpenAI object at 0x77460033ef00>, cast_to = <class 'openai.types.chat.chat_completion.ChatCompletion'>
options = FinalRequestOptions(method='post', url='/chat/completions', params={}, headers=NOT_GIVEN, max_retries=NOT_GIVEN, timeo...erence_steps': 2, 'negative_prompt': 'blurry, low quality, distorted', 'true_cfg_scale': 4.0, 'seed': 42, 'layers': 2})
    def request(
        self,
        cast_to: Type[ResponseT],
        options: FinalRequestOptions,
        *,
        stream: bool = False,
        stream_cls: type[_StreamT] | None = None,
    ) -> ResponseT | _StreamT:
        cast_to = self._maybe_override_cast_to(cast_to, options)
        # create a copy of the options we were given so that if the
        # options are mutated later & we then retry, the retries are
        # given the original options
        input_options = model_copy(options)
        if input_options.idempotency_key is None and input_options.method.lower() != "get":
            # ensure the idempotency key is reused between requests
            input_options.idempotency_key = self._idempotency_key()
        response: httpx.Response | None = None
        max_retries = input_options.get_max_retries(self.max_retries)
        retries_taken = 0
        for retries_taken in range(max_retries + 1):
            options = model_copy(input_options)
            options = self._prepare_options(options)
            remaining_retries = max_retries - retries_taken
            request = self._build_request(options, retries_taken=retries_taken)
            self._prepare_request(request)
            kwargs: HttpxSendArgs = {}
            if self.custom_auth is not None:
                kwargs["auth"] = self.custom_auth
            if options.follow_redirects is not None:
                kwargs["follow_redirects"] = options.follow_redirects
            log.debug("Sending HTTP Request: %s %s", request.method, request.url)
            response = None
            try:
                response = self._client.send(
                    request,
                    stream=stream or self._should_stream_response_body(request=request),
                    **kwargs,
                )
            except httpx.TimeoutException as err:
                log.debug("Encountered httpx.TimeoutException", exc_info=True)
                if remaining_retries > 0:
                    self._sleep_for_retry(
                        retries_taken=retries_taken,
                        max_retries=max_retries,
                        options=input_options,
                        response=None,
                    )
                    continue
                log.debug("Raising timeout error")
                raise APITimeoutError(request=request) from err
            except Exception as err:
                log.debug("Encountered Exception", exc_info=True)
                if remaining_retries > 0:
                    self._sleep_for_retry(
                        retries_taken=retries_taken,
                        max_retries=max_retries,
                        options=input_options,
                        response=None,
                    )
                    continue
                log.debug("Raising connection error")
                raise APIConnectionError(request=request) from err
            log.debug(
                'HTTP Response: %s %s "%i %s" %s',
                request.method,
                request.url,
                response.status_code,
                response.reason_phrase,
                response.headers,
            )
            log.debug("request_id: %s", response.headers.get("x-request-id"))
            try:
                response.raise_for_status()
            except httpx.HTTPStatusError as err:  # thrown on 4xx and 5xx status code
                log.debug("Encountered httpx.HTTPStatusError", exc_info=True)
                if remaining_retries > 0 and self._should_retry(err.response):
                    err.response.close()
                    self._sleep_for_retry(
                        retries_taken=retries_taken,
                        max_retries=max_retries,
                        options=input_options,
                        response=response,
                    )
                    continue
                # If the response is streamed then we need to explicitly read the response
                # to completion before attempting to access the response text.
                if not err.response.is_closed:
                    err.response.read()
                log.debug("Re-raising status error")
>               raise self._make_status_error_from_response(err.response) from None
E               openai.BadRequestError: Error code: 400 - {'error': {'message': 'Invalid layers value 2. layers must be between 3 and 10 inclusive.', 'type': 'BadRequestError', 'param': None, 'code': 400}}
/usr/local/lib/python3.12/dist-packages/openai/_base_client.py:1070: BadRequestError
======================================================================= warnings summary =======================================================================
<frozen importlib._bootstrap>:488
  <frozen importlib._bootstrap>:488: DeprecationWarning: builtin type SwigPyPacked has no __module__ attribute
<frozen importlib._bootstrap>:488
  <frozen importlib._bootstrap>:488: DeprecationWarning: builtin type SwigPyObject has no __module__ attribute
../../../usr/local/lib/python3.12/dist-packages/torch/jit/_script.py:362: 14 warnings
  /usr/local/lib/python3.12/dist-packages/torch/jit/_script.py:362: DeprecationWarning: torch.jit.script_method is deprecated. Please switch to torch.compile or torch.export.
    warnings.warn(
vllm_omni/__init__.py:29
  /workspace/build/buildkite/vllm_omni/__init__.py:29: RuntimeWarning: Failed to import version from _version.py: No module named 'vllm_omni._version'
  This typically happens in development mode before building.
  Using fallback version 'dev'.
    from .version import __version__, __version_tuple__  # isort:skip
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
=================================================================== short test summary info ====================================================================
FAILED tests/e2e/online_serving/test_qwen_image_layered_expansion.py::test_layered_output_image_count[layers_guard_001_layers2] - openai.BadRequestError: Error code: 400 - {'error': {'message': 'Invalid layers value 2. layers must be between 3 and 10 inclusive.', 'type': 'BadRequestError', 'param': None, 'code': 400}}
============================================ 1 failed, 38 passed, 61 deselected, 17 warnings in 5765.57s (1:36:05) =============================================

Test Plan

pytest tests/e2e/online_serving/test_qwen_image_layered_expansion.py -v

Test Result

======================================================= test session starts =======================================================
platform linux -- Python 3.12.3, pytest-9.0.2, pluggy-1.6.0 -- /workspace/c00580271/cwq_branch/.venv/bin/python3
cachedir: .pytest_cache
rootdir: /workspace/c00580271/cwq_branch/vllm-omni
configfile: pyproject.toml
plugins: anyio-4.12.1
collected 4 items                                                                                                                 

tests/e2e/online_serving/test_qwen_image_layered_expansion.py::test_feature[sp_001] PASSED                                  [ 25%]
tests/e2e/online_serving/test_qwen_image_layered_expansion.py::test_empty_prompt[prompt_001] PASSED                         [ 50%]
tests/e2e/online_serving/test_qwen_image_layered_expansion.py::test_feature[cfg_parallel_001] PASSED                        [ 75%]
tests/e2e/online_serving/test_qwen_image_layered_expansion.py::test_layered_output_image_count[layers_guard_001_layers3] PASSED [100%]

---

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan. Please provide the test scripts & test commands. Please state the reasons if your codes don't require additional test scripts. For test file guidelines, please check the test style doc
• The test results. Please paste the results comparison before and after, or the e2e results.
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model. Please run mkdocs serve to sync the documentation editions to ./docs.
• (Optional) Release notes update. If your change is user-facing, please update the release notes draft.

BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)

[gcanlin]

Please confirm https://github.com/vllm-project/vllm-omni/pull/2349/changes#r3013474695

[gcanlin]

LGTM