Files
langchain/libs/langchain_v1/tests
Sydney Runkle 35b89b8b10 fix: shell tool middleware (#33589)
the fact that this was broken showcases that we need significantly
better test coverage, this is literally the most minimalistic usage of
this middleware there could be 😿

will document these two gotchas better for custom middleware

```py
from langchain.agents.middleware.shell_tool import ShellToolMiddleware
from langchain.agents import create_agent

agent = create_agent(model="openai:gpt-4",middleware = [ShellToolMiddleware()])
agent.invoke({"messages":[{"role": "user", "content": "hi"}]})
```
2025-10-17 16:48:30 -04:00
..