Access enable_thinking flag for langchain_huggingface models

### Checked other resources - [x] This is a feature request, not a bug report or usage question. - [x] I added a clear and descriptive title that summarizes the feature request. - [x] I used the GitHub search to find a similar feature request and didn't find it. - [x] I checked the LangChain documentation and API reference to see if this feature already exists. - [x] This is not related to the langchain-community package. ### Feature Description I would like to be able to access the huggingface enable_thinking flag in apply_chat_template ([https://github.com/langchain-ai/langchain/blob/7aef3388d9be54d7a96f3fb7d93c53ab9509f35f/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py#L739](https://github.com/langchain-ai/langchain/blob/7aef3388d9be54d7a96f3fb7d93c53ab9509f35f/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py#L739)) ### Use Case ``` python llm = HuggingFacePipeline.from_model_id( model_id="Qwen/Qwen3-0.6B", task="text-generation", device_map="auto", pipeline_kwargs={ "max_new_tokens": 512, "do_sample":False, "repetition_penalty": 1.1, "framework":"pt"}, # enable_thinking=False? model_kwargs={"quantization_config": quantization_config, "trust_remote_code": True, "cache_dir":None}, ) ``` ### Proposed Solution ```python llm = HuggingFacePipeline.from_model_id( model_id="Qwen/Qwen3-0.6B", task="text-generation", device_map="auto", pipeline_kwargs={ "max_new_tokens": 512, "do_sample":False, "repetition_penalty": 1.1, "framework":"pt","chat_template_kwargs": {"enable_thinking": False},}, model_kwargs={"quantization_config": quantization_config, "trust_remote_code": True, "cache_dir":None}, ) ``` ### Alternatives Considered Alternatively, just use huggingface without langchain. ### Additional Context _No response_