langchain-middleware

Name: langchain-middleware
Availability: InStock
Author: reofdev07

Pauses LangChain agent tool calls for human approval via middleware.

Updated Jul 13, 2025

Search Tags:#middleware #langchain #resume #human-in-the-loop #hitl #tool-approval #checkpointer

Ready to run

npx skills add https://github.com/Reofdev07/osai --skill langchain-middleware-reofdev07

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: langchain-middleware
Source: https://github.com/Reofdev07/osai/tree/main/.windsurf/skills/langchain-middleware
Command: npx skills add https://github.com/Reofdev07/osai --skill langchain-middleware-reofdev07

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Human-in-the-loop supervision is essential to prevent unsafe, costly, or unintended actions by LangChain agents, enabling controlled decision-making through middleware.

Core Features & Use Cases

Pause before dangerous tool calls with HumanInTheLoopMiddleware for human approval
Create custom middleware with hooks for before_model, after_model, wrap_tool_call, before_agent, and after_agent
Support command resume patterns and structured output formatting with Pydantic/Zod
Per-tool interrupt policies and thread_id tracking to ensure deterministic, auditable workflows

Quick Start

Configure an agent with HITL middleware and a MemorySaver checkpointer to require human approval before executing risky actions.

Frequently Asked Questions about langchain-middleware

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I add human-in-the-loop approval to LangChain agents?▼

Add human-in-the-loop approval to LangChain agents by configuring HumanInTheLoopMiddleware to pause execution before risky tool calls, requiring manual review before proceeding.

What are per-tool interrupt policies in LangChain human-in-the-loop workflows?▼

Per-tool interrupt policies allow you to specify which tools require human approval before execution. This ensures deterministic and auditable workflows by setting distinct approval rules for different actions.

Do I need a checkpointer to pause LangChain agents for human approval?▼

Yes, a checkpointer like MemorySaver is required to pause LangChain agents for human approval. It maintains thread_id tracking to save the agent state while waiting for manual decisions.

How to create custom middleware hooks for LangChain agents?▼

Create custom middleware hooks for LangChain agents using configurable lifecycle events like before_model, after_model, wrap_tool_call, before_agent, and after_agent to inject custom logic.

How do I resume a LangChain agent after a human-in-the-loop interrupt?▼

Resume a LangChain agent after a human-in-the-loop interrupt by using command resume patterns, which route the human's decision back into the agent to continue execution from the paused state.

When should I use human-in-the-loop middleware for LangChain?▼

Use human-in-the-loop middleware for LangChain when agents perform cautious executions like sending emails, reading sensitive data, or modifying external systems where unintended actions are unsafe or costly.