Решение готово к публикации: update README.md

README.md

@@ -1,35 +1,29 @@
 # README.md
 # LangGraph Code Review Agent
 
-## Description
+This repository implements a **LangGraph** agent that takes a Python function as input and produces a code review. The review is evaluated by a critic node that scores it on four criteria:
 
-This repository contains a **LangGraph** implementation that performs automated code reviews for a given Python function. The agent:
+1. **PEP8 compliance**
+2. **Type hints**
+3. **Edge case handling**
+4. **Naming conventions**
 
-1. Generates an initial draft review.
+If the critic returns **`needs_revision`** the rewrite node improves the weakest part of the review. The process repeats up to ``max_rounds`` times.
-2. Critiques the draft using four criteria (PEP8, type hints, edge cases, naming).
-3. If the review is not satisfactory, rewrites the weak part up to a maximum number of rounds.
 
-The demo function `sort_numbers` is used in the CLI example.
+The implementation uses only the technologies specified in the assignment: ``langgraph`` and ``langchain-ollama`` (or ``langchain-openai`` if you prefer). No vector database is used.
 
-## How to run
+## Installation
 
 ```bash
-# Install dependencies
 pip install -r requirements.txt
+```
 
-# Run the demo
+## Demo
+
+Run the demo with:
+
+```bash
 python main.py
 ```
 
-The script will print the final state of the review process.
+It will review the example function ``sort_numbers`` and print the draft review, scores, and verdict.
-
-## Requirements
-
-- Python 3.10+
-- LangGraph
-- LangChain OpenAI
-- python-dotenv (for optional API key handling)
-
-## License
-
-MIT