bug: nemoguardrails server api streaming is not working

Did you check docs and existing issues?

• I have read all the NeMo-Guardrails docs
• I have updated the package to the latest version before submitting this issue
• (optional) I have used the develop branch
• I have searched the existing issues of NeMo-Guardrails

Python version (python --version)

3.11

Operating system/version

15

NeMo-Guardrails version (if you must use a specific version and not the latest

0.11.0

Describe the bug

I started a server with the following command, but streaming mode is not working

python -m nemoguardrails server --config=./config --default-config-id=config

config.yml

models:
  - type: main
    engine: openai
    model: gpt-4o-mini

Steps To Reproduce

my test code

from dotenv import load_dotenv
from openai import OpenAI

load_dotenv()

client = OpenAI(
    base_url="http://localhost:8000/v1"
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant"},
        {"role": "user", "content": "Hello"},
    ],
    stream=True,
    extra_body={
        "config_id": "config"
    }
)

for chunk in response:
    print(chunk.choices[0].delta.content)

Expected Behavior

print stream chunks

Actual Behavior

print nothing

Start by running python -m nemoguardrails server --config=./config --default-config-id=config with the provided config and OpenAI client example. Trace the server's streaming response path and compare it with the non-streaming behavior. Done means the client receives and prints response chunks; the issue does not name a source file or test.