LangChain Updates Deep Agents Skill Tool Control
The story so far
LangChain updated Deep Agents, adding three control features: binding tools to skills, fixing required skills before the first model call, and reloading the skill library within running threads. LangChain states that the schema of bound tools will not enter the context until needed; models that support tool calls during a conversation can retain the cached prompt prefix.
AI-written from the reports · Updated 28 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- LangChainFeaturedDeep Agents loads tools only when the relevant skill is read
LangChain updated Deep Agents with three controls: bind tools to a skill, pin requested skills before the first model call, and reload a skill library during a running thread. Bound tool schemas stay outside the context until needed; models supporting mid-conversation tools can retain the cached prompt prefix.