# LangGraph Reflection Agent

This project demonstrates a simple LangGraph agent that:

1. Generates a concise answer to a user‑supplied question.
2. Critiques the answer using an LLM.
3. Rewrites the answer if the critic says *needs_revision*, up to a maximum number of rounds.

The agent is implemented in Python 3.10+ and uses the `langgraph` framework together with `langchain-openai`.

## Features

- **Draft generation** – 5–10 sentence answer.
- **LLM critic** – returns a verdict (`ok` or `needs_revision`) and 2–3 critique points.
- **Rewrite loop** – rewrites the draft until the verdict is `ok` or the maximum number of rounds is reached.
- **CLI** – run the agent from the command line.

## Installation

```bash
# Create a virtual environment (optional but recommended)
python -m venv .venv
source .venv/bin/activate   # On Windows use `.venv\Scripts\activate`

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

### OpenAI API Key

The agent uses OpenAI’s GPT‑3.5‑Turbo by default.  
Set your API key in the environment:

```bash
export OPENAI_API_KEY="sk-..."
```

If you prefer to use a local LLM via Ollama, replace the `langchain-openai` dependency with `langchain-ollama` and adjust the LLM initialization in `src/graph.py`.

## Usage

```bash
python -m src.main "Explain the difference between a tool and a resource in MCP to a student."
```

Optional arguments:

- `--max_rounds N` – maximum number of rewrite rounds (default: 2).

Example:

```bash
python -m src.main "Explain the difference between a tool and a resource in MCP." --max_rounds 3
```

The script will print:

```
=== Final Answer ===
<rewritten answer>

=== Verdict ===
ok

```

If the final verdict is `needs_revision`, the critique points will also be shown.

## Project Structure

```
src/
├── main.py      # CLI entry point
├── graph.py     # LangGraph graph definition
└── state.py     # TypedDict for the agent state
requirements.txt
README.md
```

## License

MIT License