Fix SSE parser to handle delta.reasoning tokens from reasoning models

[flexwang]

Summary

• The extract_content lambda in the chat SSE parser only read delta.content, causing reasoning models (GLM-5.2, DeepSeek-R1) to report output_len≈0 and meaningless TPOT/ITL/TTFT metrics
• Updated the lambda to fall through content → reasoning → reasoning_content so all generated tokens are counted
• Added tests covering both delta.reasoning and delta.reasoning_content field names

Fixes #592

Test plan

• Existing streaming parser tests pass
• New test: test_parse_sse_stream_reasoning_tokens — verifies delta.reasoning tokens are extracted
• New test: test_parse_sse_stream_reasoning_content_field — verifies delta.reasoning_content (DeepSeek-R1 style) tokens are extracted
• Manual validation against a reasoning model endpoint (GLM-5.2 or DeepSeek-R1)

🤖 Generated with Claude Code

[kubernetes-prow]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: flexwang
Once this PR has been reviewed and has the lgtm label, please assign wangchen615 for approval. For more information see the Code Review Process.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[kubernetes-prow]

Welcome @flexwang!

It looks like this is your first PR to kubernetes-sigs/inference-perf 🎉. Please refer to our pull request process documentation to help your PR have a smooth ride to approval.

You will be prompted by a bot to use commands during the review process. Do not be afraid to follow the prompts! It is okay to experiment. Here is the bot commands documentation.

You can also check if kubernetes-sigs/inference-perf has its own contribution guidelines.

You may want to refer to our testing guide if you run into trouble with your tests not passing.

If you are having difficulty getting your pull request seen, please follow the recommended escalation practices. Also, for tips and tricks in the contribution process you may want to read the Kubernetes contributor cheat sheet. We want to make sure your contribution gets all the attention it needs!

Thank you, and welcome to Kubernetes. 😃

[linux-foundation-easycla]

• ❌ - login: @flexwang / name: flexwang. The commit (1906e9e) is not authorized under a signed CLA. Please click here to be authorized. For further assistance with EasyCLA, please visit our EasyCLA portal and chat with our support bot.

[Bslabe123]

@flexwang Is this one ready for review?

[Bslabe123]

Closing due to inactivity