[BugFix] Add field constraints to /v1/omni/sleep and /v1/omni/wakeup

[Shaun-Walsh]

Summary

• Add min_length=1 to stage_ids on both OmniSleepRequest and OmniWakeupRequest to reject empty lists
• Add ge=0 to OmniSleepRequest.level to reject negative sleep levels
• Unskip sleep_empty_stage_ids, sleep_negative_level, and wakeup_empty_stage_ids tests

Partial fix for #3649.

Test plan

• Verified validators locally with Pydantic v2 — invalid inputs rejected, valid inputs pass
• CI passes on existing test suite
• Live validation with Qwen/Qwen-Image (requires H100)

[chatgpt-codex-connector]

Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits.
Credits must be used to enable repository wide code reviews.

[NickCao]

Claude:

The min_length=1 constraint on stage_ids will break two existing unit tests in tests/entrypoints/openai_api/test_omni_sleep_wakeup.py:

• test_sleep_empty_stage_ids — expects stage_ids: [] to return 200 with {"status": "SUCCESS", "acks": []}
• test_wakeup_empty_stage_ids — expects stage_ids: [] to return 200 with {"status": "SKIPPED"}

With min_length=1, Pydantic rejects empty lists with 422 before the handler runs, so both tests fail with assert 422 == 200.

These tests need to be updated to expect 422, or removed since the dfx tests in test_invalid_server_control.py now cover the same validation.

[Shaun-Walsh]

Already fixed — updated both tests to expect 422 in aa309ae.

[Shaun-Walsh]

Hi — just pushed a fix for the failing check. This PR (along with a few related ones from our team) is a dependency for the Red Hat Midstream build of vllm-omni. Could we get a review and merge when you have a chance? Happy to address any feedback quickly. Thanks!

[vllm-omni-review-bot]

Omni ReviewBot: no human activity for 48 days

@Shaun-Walsh this pull request has had no human commit, comment or review since 2026-07-21. Per repository policy it may be closed if it stays inactive.

To keep it moving, any one of these is enough: push an update, reply to the open blocker, or post the current plan and timeline.

[Shaun-Walsh]

Hi @alex-jw-brooks & @yenuo26 just flagging this PR for review when you get a chance.

[yenuo26]

@Shaun-Walsh please fix conflicts

[Shaun-Walsh]

Hey @yenuo26 conflicts resolved :)

[vllm-omni-review-bot]

Omni ReviewBot: no human activity for 7 days

@Shaun-Walsh this pull request has had no human commit, comment or review since 2026-09-21. Please confirm the current plan and next step. The author or a maintainer decides whether to change the PR state.

To keep it moving, any one of these is enough: push an update, reply to the open blocker, or post the current plan and timeline.

[Shaun-Walsh]

Hi @NickCao @yenuo26 @alex-jw-brooks @tzhouam @linyueqian looking to get this merged so I don't have as many pr's open per the new guidelines :)

[alex-jw-brooks]

LGTM, thanks