context management
The technique of managing conversation history, memory, and tool-call context within an AI Agent, ensuring that state is correctly passed between interaction turns and persisted.
Timeline (last 90 days)
The context sent with each model call typically includes the system prompt, the tool definition list, memories and files, and the full conversation record.
LangGraph categorizes context window management as a separate class, distinct from the two types of memory.
Common strategies for handling overly long contexts include sliding windows, summary compression, and semantic retrieval, each with its own precision loss and latency trade-offs
All Facts (3)
The context sent with each model call typically includes the system prompt, the tool definition list, memories and files, and the full conversation record.
50%UnverifiedLangGraph categorizes context window management as a separate class, distinct from the two types of memory.
50%UnverifiedCommon strategies for handling overly long contexts include sliding windows, summary compression, and semantic retrieval, each with its own precision loss and latency trade-offs
50%