mirror of
https://github.com/hellodigua/ChatLab.git
synced 2026-10-26 10:14:35 +08:00
DeepSeek API requires reasoning_content to be retransmitted on assistant messages that precede tool results. Add ReplayOptions to history replay so thinking blocks are included as ThinkingContent when the model uses DeepSeek-format thinking, preventing 400 errors in multi-turn tool-call conversations. Co-authored-by: Cursor <cursoragent@cursor.com>