langchain-middleware
langchain middleware
What it does
- 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)
- Which tools require approval (per-tool policies)
- Allowed decisions per tool (approve, edit, reject)
- Custom middleware hooks: beforemodel, aftermodel, wraptoolcall, beforeagent, afteragent
- Tool-specific middleware (apply only to certain tools)
Requirements & configuration
- Step 1: Agent runs until it needs to call tool
- // Step 1: Agent runs until it needs to call tool
- Edit the tool arguments before approving when the original values need correction.
- Which tools require approval (per-tool policies)
- HITL middleware requires a checkpointer to persist state.
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
langchain-middleware FAQ
What does the langchain-middleware skill do?
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod. HumanInTheLoopMiddleware / humanInTheLoopMiddleware: Pause before dangerous tool calls for human approval Custom middleware: Intercept tool calls for error handling, logging, retry logic
What does langchain-middleware require?
Step 1: Agent runs until it needs to call tool // Step 1: Agent runs until it needs to call tool Edit the tool arguments before approving when the original values need correction. Which tools require approval (per-tool policies) HITL middleware requires a checkpointer to persist state.
How do I install langchain-middleware?
Run: npx -y skills add https://github.com/langchain-ai/langchain-skills --skill langchain-middleware --agent claude-code — the source lives at github.com/langchain-ai/langchain-skills.
Maintain langchain-middleware?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/skills/langchain-ai-langchain-skills-langchain-middleware?ref=badge) npx agentictools info skills/langchain-ai-langchain-skills-langchain-middleware The second line is the CLI lookup for this page — handy in READMEs and docs.
