[Router][Bugfix]: make sure to extend full_response

[max-wittig]

If the code only collects the first chunk, the full_response will be incomplete. For example:

If the JSON response is:

{"key": "value", "another_key": "another_value"}

And it's split into two chunks:

chunk1 = b'{"key": "value", "'
chunk2 = b'another_key": "another_value"}'

Then full_response will only contain chunk1, and the end (chunk2) is missing so then we had incomplete json responses in the callback

class PostRequestCallbackHandler(CustomCallbackHandler):
    async def post_request(self, request: Request, response_content: bytes) -> Any:
        request_json: dict = await request.json()
        if request_json.get("stream"):
            # currently we can't act on streaming responses
            return
        try:
            response_json = json.loads(response_content.decode("utf-8"))  # this used to crash
            logger.debug(response_json)
        except Exception as e:
            logger.error(
                f"Could not parse response content. {response_content} {e}"  and output incomplete data here
            )

BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE

---

• Make sure the code changes pass the pre-commit checks.
• Sign-off your commit by using -s when doing git commit
• Try to classify PRs for easy understanding of the type of changes, such as [Bugfix], [Feat], and [CI].

Detailed Checklist (Click to Expand)

Thank you for your contribution to production-stack! Before submitting the pull request, please ensure the PR meets the following criteria. This helps us maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Please try to classify PRs for easy understanding of the type of changes. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

• [Bugfix] for bug fixes.
• [CI/Build] for build or continuous integration improvements.
• [Doc] for documentation fixes and improvements.
• [Feat] for new features in the cluster (e.g., autoscaling, disaggregated prefill, etc.).
• [Router] for changes to the vllm_router (e.g., routing algorithm, router observability, etc.).
• [Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

• Pass all linter checks. Please use pre-commit to format your code. See README.md for installation.
• The code need to be well-documented to ensure future contributors can easily understand the code.
• Please include sufficient tests to ensure the change is stay correct and robust. This includes both unit tests and integration tests.

DCO and Signed-off-by

When contributing changes to this project, you must agree to the DCO. Commits must include a Signed-off-by: header which certifies agreement with the terms of the DCO.

Using -s with git commit will automatically add this header.

What to Expect for the Reviews

We aim to address all PRs in a timely manner. If no one reviews your PR within 5 days, please @-mention one of YuhanLiu11
, Shaoting-Feng or ApostaC.

[gemini-code-assist]

Summary of Changes

Hello @max-wittig, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a bug in the request processing logic where the full_response was not being correctly aggregated. The change ensures that all data chunks are appended to the full_response object, which is crucial for accurately collecting complete responses from non-streaming requests.

Highlights

• Bug Fix: Corrected an indentation error in src/vllm_router/services/request_service/request.py to ensure that the full_response object is consistently extended with all received chunks for non-streaming requests.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request addresses a critical bug in how full responses were collected for non-streaming requests. The indentation fix ensures that all response chunks are correctly accumulated, which is essential for the semantic caching mechanism. The change significantly improves the correctness of the request processing logic.

[max-wittig]

@YuhanLiu11 FYI. This will also fix the behavior when using the semantic_cache

[max-wittig]

@YuhanLiu11 I've tried to write a test for process_request, but I haven't figured out how to mock async with request.app.state.httpx_client_wrapper().stream( properly. Let me know, if you have any pointers so that I can make a follow-up MR.

For testing this I just deployed the hash to our dev environment, but for the longterm stability that would be good to have.