langchain-middleware
Originally fromlangchain-ai/langchain-skills
Installation
SKILL.md
- HumanInTheLoopMiddleware / humanInTheLoopMiddleware: Pause before dangerous tool calls for human approval
- Custom middleware: Intercept tool calls for error handling, logging, retry logic
- Command resume: Continue execution after human decisions (approve, edit, reject)
Requirements: Checkpointer + thread_id config for all HITL workflows.
Human-in-the-Loop
Related skills
More from langchain-ai/skills-benchmarks
react-components
Modern React component patterns with hooks and TypeScript
34api-docs
OpenAPI documentation and REST API design patterns
22langsmith-trace
INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the langsmith CLI tool.
22testing-patterns
Unit testing and integration testing best practices
22langchain-rag
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).
22langchain-fundamentals
Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
22