[Yunnglin]

Summary

• add a standalone DashServing Native HTTP adapter with POST /api and GET /health
• forward generic HTTP JSON requests to a fixed internal runtime for both Twinkle and Tinker APIs
• expose a dedicated adapter launcher and declare server-side HTTP dependencies
• add an end-to-end mock covering Client -> ModelScope -> DashServing -> Adapter -> runtime

Validation

• conda run -n twinkle python -m pytest -vv -s tests/dashserving/test_mock_e2e.py (5 passed)
• pre-commit run for all changed files (all hooks passed)

Draft follow-up

• validate body passthrough and the 600-second request path against a real DashServing runtime

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.