Daoyuan Li 61ce6d2b96
fix(vllm): normalize thinking switches without mutating request bodies (#6496)
* fix(vllm): preserve caller-owned thinking request bodies

* test(vllm): cover reused thinking bodies in sync and async streams

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-08 20:41:40 +08:00
..