fix(llm-deepseek): pass reasoning content back on every reasoned turn

An assistant turn that answered without calling a tool serialized no reasoning_content, so a gateway re-encoding the conversation for another vendor had no chai

Fix

An assistant turn that answered without calling a tool serialized no reasoning_content, so a gateway re-encoding the conversation for another vendor had no chain of thought to hash and lost that turn's upstream thinking signature.

Date
2026-08-19
Version
master@583894f
commit
583894f

View commit on GitHub

An assistant turn that answered without calling a tool serialized no reasoning_content, so a gateway re-encoding the conversation for another vendor had no chain of thought to hash and lost that turn's upstream thinking signature.