Open sourceNov 4, 2026, 10:50 AM EST
LangChain core 1.7.5 adds standardized model refusal blocks
The release adds standardized refusal content blocks, so a model declining a request is represented in one shared format, and it translates Gemini safety blocks into those refusal blocks. It also ends a tool run when a request is cancelled and fixes loading of RemoveMessage objects that were serialized by LangChain.js.
Sources
- PrimaryLangChain
Written by AIToolMaps from the source above and checked against it sentence by sentence.