feat(responses): add output_text delta events to responses

[ashwinb]

This adds initial streaming support to the Responses API.

This PR makes sure that the first inference call made to chat completions streams out.

There's more to be done:

• tool call output tokens need to stream out when possible
• we need to loop through multiple rounds of inference and they all need to stream out.

Test Plan

Added a test. Executed as:

FIREWORKS_API_KEY=... \
  pytest -s -v 'tests/verifications/openai_api/test_responses.py' \
  --provider=stack:fireworks --model meta-llama/Llama-4-Scout-17B-16E-Instruct

Then, started a llama stack fireworks distro and tested against it like this:

OPENAI_API_KEY=blah \
   pytest -s -v 'tests/verifications/openai_api/test_responses.py' \
   --base-url http://localhost:8321/v1/openai/v1 \
  --model meta-llama/Llama-4-Scout-17B-16E-Instruct 

[ehhuang]

Few questions. Also, if you haven't run the verification tests with OpenAI's impl, would be good to do so just to verify that the tests are correctly checking for the official behavior.

[ehhuang]

should we just name this function like _execute_tools or something more descriptive?

[ashwinb]

@ehhuang I think we need to simplify further because this function is muddled in how it thinks of itself :) the next set of PRs which do multi-turn execution will refactor it to be better, thanks for the feedback.

[ehhuang]

llama-stack/llama_stack/providers/utils/inference/stream_utils.py

Line 24 in e7e9ec0

async def stream_and_store_openai_completion(

Looks like we're doing these delta accumulations more (I recall seeing another instance somewhere, but can't recall the exact location), maybe some of the above can be reused. Could be a follow-up.

[ashwinb]

Tested against OpenAI client too. See updated test plan.