LangChain Reference home page

GitHub
Main Docs

LangChain

Universal
Hub
Node
Load
Serializable
Encoder Backed
File System
In Memory

LangChain Core

Text Splitters

MCP Adapters

⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

Universal Hub Node Load Serializable Encoder Backed File System In Memory

Agents Caches Base Dispatch Web Manager Promises Chat History Context Base Langsmith Documents Embeddings Errors Example Selectors Indexing Base Chat Models Llms Profile Load Serializable Memory Messages Tool Output Parsers Openai Functions Openai Tools Outputs Prompt Values Prompts Retrievers Document Compressors Runnables Graph Singletons Stores Structured Query Tools Base Console Log Stream Run Collector Tracer Langchain Stream Async Caller Chunk Array Context Env Event Source Parse Format Function Calling Hash Json Patch Json Schema Math Ssrf Stream Testing Tiktoken Types Vectorstores

Language

Theme

JavaScriptlangchainindexContextEditingMiddlewareConfig

Interface●Since v1.1

ContextEditingMiddlewareConfig

Copy

interface ContextEditingMiddlewareConfig

Properties

View source on GitHub

property

edits: ContextEdit[]

property

tokenCountMethod: "model" | "approx"

Configuration for the Context Editing Middleware.

Sequence of edit strategies to apply. Defaults to a single ClearToolUsesEdit mirroring Anthropic defaults.

Whether to use approximate token counting (faster, less accurate) or exact counting implemented by the chat model (potentially slower, more accurate). Currently only OpenAI models support exact counting.