[Bugfix] Remove unsupported enable_force_include_usage param from stream generator

[wonjerry]

Purpose

Fix streaming chat completion error when using stream: true.

The parent class OpenAIServingChat.chat_completion_stream_generator() does not accept enable_force_include_usage as a parameter in vLLM 0.12.0. The method accesses this value via self.enable_force_include_usage internally.

Reference: vLLM v0.12.0 serving_chat.py

Fixes error:
OpenAIServingChat.chat_completion_stream_generator() got an unexpected keyword argument 'enable_force_include_usage'

Test Plan

  curl http://localhost:8000/v1/chat/completions \
      -H "Content-Type: application/json" \
      -d '{"model": "Qwen3-Omni-30B-A3B-Instruct", "messages": [{"role": "user", "content": "Hello"}], "modalities": ["text"], "stream": true}'

Test Result

Before: 500 Internal Server Error (unexpected keyword argument)

{"error":{"message":"OpenAIServingChat.chat_completion_stream_generator() got an unexpected keyword argument 'enable_force_include_usage'","type":"Internal Server Error","param":null,"code":500}}

After: Another error...

 {"error": {"message": "'OmniRequestOutput' object has no attribute 'prompt_token_ids'", "type": "BadRequestError", "param": null, "code": 400}}

---

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, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
• (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)

[hsliuustc0106]

@tzhouam PTAL

[wonjerry]

I've checked #350 and #367. I'll follow up on these PRs.

[hsliuustc0106]

I've checked #350 and #367. I'll follow up on these PRs.

I will get PR #350 merged first and wait for #367 ready, sorry for the misleading streaming error.

[wonjerry]

@hsliuustc0106 Thanks! I'm going to close this one.