# Self‑Correcting LangGraph Agent

## Overview

This project implements a **self‑correcting agent** using LangGraph. The agent
performs a task, asks an LLM to judge the result, and retries automatically until
the result is judged **success** or the maximum number of attempts is reached.

The key components are:

| Component | Purpose |
|-----------|---------|
| `AgentState` | Typed state that tracks the task, result, attempts, status, error and max_attempts |
| `unreliable_tool` | Simulates a tool that fails 30 % of the time (used to demonstrate retry logic) |
| `verify_result` | LLM judge that must reply with the single word `success` or `failed` |
| `handle_error` | Resets the error and sets the status back to `pending` for a retry |
| `execute_task` | Runs the unreliable tool and updates the state |
| `create_agent` | Builds the LangGraph with the above nodes and a retry loop |
| `create_agent_executor` | Compiles the graph into a runnable executor |
| CLI | Run the agent from the command line: `python agent.py "2+2" --max 5` |

## How It Works

1. **Start** – The graph begins at `execute_task`.
2. **Execute** – The tool runs. If it throws an exception, the state status becomes `failed`.
3. **Check attempts** – If the number of attempts is >= `max_attempts`, the graph ends with status `max_attempts`.
4. **Verify** – The LLM judges the result. If the verdict is `success`, the graph ends. If `failed`, it goes to `handle_error`.
5. **Retry** – `handle_error` clears the error and sets status to `pending`, then the graph loops back to `execute_task`.

## Usage

```bash
# Install dependencies
pip install -r requirements.txt

# Run the agent
python agent.py "2+2" --max 5
```

The console will show the final state, e.g.:

```
--- Final State ---
result: 4
attempts: 2
status: success
error: None
max_attempts: 5
``` 

## Requirements

```text
langchain>=1.0.0
langgraph>=1.0.0
langchain-openai>=1.0.0
```

## Note

The agent uses the OpenAI API. Make sure the environment variable `OPENAI_API_KEY` is set.