openai/gpt-oss-20b · With openai harmony response, I cannot generate response.

Thanks for your excellence contributions for open source. I'm trying to follow the official "How to run gpt-oss with Transformers" tutorials.

Here is my codes and error.

encoding = load_harmony_encoding(HarmonyEncodingName.HARMONY_GPT_OSS)
 
# Build conversation
convo = Conversation.from_messages([
    Message.from_role_and_content(Role.SYSTEM, SystemContent.new()),
    Message.from_role_and_content(Role.DEVELOPER, DeveloperContent.new().with_instructions(system_prompt)),
    Message.from_role_and_content(Role.USER, user_prompt),
])

# Render prompt
prefill_ids = encoding.render_conversation_for_completion(convo, Role.ASSISTANT)
stop_token_ids = encoding.stop_tokens_for_assistant_actions()

# Load model
model_name = "openai/gpt-oss-20b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")

# Generate outputs
outputs = model.generate(
    prefill_ids,
    eos_token_id=stop_token_ids,
    temperature=1e-4,
    max_new_tokens=2000,
)

>>>---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[48], line 2
      1 # Generate
----> 2 outputs = model.generate(
      3     input_ids=[prefill_ids],
      4     max_new_tokens=2000,
      5     eos_token_id=stop_token_ids,
      6 )

File /opt/conda/envs/gpt-oss/lib/python3.11/site-packages/torch/utils/_contextlib.py:120, in context_decorator.<locals>.decorate_context(*args, **kwargs)
    117 @functools.wraps(func)
    118 def decorate_context(*args, **kwargs):
    119     with ctx_factory():
--> 120         return func(*args, **kwargs)

File /opt/conda/envs/gpt-oss/lib/python3.11/site-packages/transformers/generation/utils.py:2290, in GenerationMixin.generate(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, assistant_model, streamer, negative_prompt_ids, negative_prompt_attention_mask, use_model_defaults, custom_generate, **kwargs)
   2286 # 3. Define model inputs
   2287 inputs_tensor, model_input_name, model_kwargs = self._prepare_model_inputs(
   2288     inputs, generation_config.bos_token_id, model_kwargs
   2289 )
-> 2290 batch_size = inputs_tensor.shape[0]
   2292 device = inputs_tensor.device
   2293 self._prepare_special_tokens(generation_config, kwargs_has_attention_mask, device=device)

AttributeError: 'list' object has no attribute 'shape'

Of course, i could use "tokenizer method" but that is not a open harmony usecases, isn't it?
I think my issues is a very small thing... Can you help me?