## TL;DR

It uses a keyless default reasoner that emits one RuntimeWarning and returns the input unprocessed. If you build an Agent without llm=, it does not call a model.

## Fix

1. It uses a keyless default reasoner that emits one RuntimeWarning and returns the input unprocessed.
   Expected: You get the expected result; the problem is gone.

## When to use

- You are setting up or using this Julep Agent does nothing feature.
- The symptom matches: returns input unprocessed.

## When NOT to use

- Unrelated Julep Agent does nothing issues (different feature, different failure).
- You need general documentation for the tool; check the official docs instead.

## Compatibility

Reported against Julep Agent does nothing.

## Variant phrasings

### returns input unprocessed

## Why it happens

My Julep Agent runs without errors but does nothing: it just returns the input unprocessed. No LLM call seems to happen. What is going on?

## Edge cases

- If your error message differs even slightly, this is probably a different issue; search the exact text.
- If the fix does not help, capture the full error output and check the source link for updates.