Files
deerflow-code/offline-backend-20260512/backend/tests
董宏凯andCursor f4c7d41a60 fix: accept vLLM thinking in reasoning or reasoning_content
Newer vLLM parsers put CoT in reasoning; older builds and DeepSeek still use reasoning_content. Canonicalize to the UI field and echo only the original wire field so other ChatOpenAI models stay unchanged. Point qwen3.6 at VllmChatModel.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-09 22:46:08 +08:00
..
2026-06-24 15:40:56 +08:00
2026-08-24 20:47:31 +08:00
@
2026-05-18 14:34:22 +08:00
2026-08-30 01:25:20 +08:00