docs: reformat README.md by removing emojis and standardizing table alignment

README.md

@@ -15,26 +15,22 @@ short_description: The AI Courtroom That Exposes Bad Freelance Code
 
 <div align="center">
 
-# ⚖️ CodeTribunal
+# CodeTribunal
 
 ### The AI Courtroom That Exposes Bad Freelance Code
 
-**Multi-Agent Forensic Investigation Powered by GLM 5 + GritQL + CrewAI**
-
-Built using GLM 5.1 for long-horizon reasoning and orchestrated tool use via CrewAI.
+**Built using GLM 5.1 for long-horizon reasoning and orchestrated tool use via CrewAI.**
 
 [![Tests](https://github.com/amineyagoub/CodeTribunal/actions/workflows/tests.yml/badge.svg)](https://github.com/amineyagoub/CodeTribunal/actions/workflows/tests.yml)
 [![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Built for GLM 5.1 Hackathon](https://img.shields.io/badge/Built%20for-GLM%205.1-ff69b4)](https://build-with-glm-5-1-challenge.devpost.com)
 
-[How It Works](#-how-it-works) • [Architecture](#-architecture) • [Install](#-install) • [Usage](#-usage) • [Demo](#-demo)
-
 </div>
 
 ---
 
-## 🎬 The Problem
+## The Problem
 
 A freelancer delivers code. The client can't tell if it's professional work or a security nightmare. Traditional linters find syntax errors. Code reviews miss architectural flaws. Nobody puts it all together and tells you:
 
@@ -46,7 +42,7 @@ Upload a `.zip` of code and watch a full courtroom trial unfold — evidence gat
 
 ---
 
-## 🏛️ How It Works
+## How It Works
 
 CodeTribunal runs a **6-phase pipeline**, each building on the last:
 
@@ -92,9 +88,9 @@ Each agent **autonomously decides which tools to call**, observes the results, a
 
 A courtroom debate between AI agents:
 
-1. **⚖️ The Prosecutor** — builds the case for negligence, cites specific evidence
-2. **🛡️ The Defense Attorney** — challenges claims, argues context and proportionality
-3. **⚖️ Rebuttal** — the prosecutor responds to the defense
+1. ** The Prosecutor** — builds the case for negligence, cites specific evidence
+2. ** The Defense Attorney** — challenges claims, argues context and proportionality
+3. ** Rebuttal** — the prosecutor responds to the defense
 
 Agents use CrewAI's `context` parameter to chain arguments: prosecution output feeds into defense context, both feed into rebuttal.
 
@@ -117,7 +113,7 @@ Agents use CrewAI's `context` parameter to chain arguments: prosecution output f
 
 ---
 
-## 🏗️ Architecture
+## Architecture
 
 ```
                           ┌──────────────┐
@@ -161,7 +157,7 @@ Agents use CrewAI's `context` parameter to chain arguments: prosecution output f
 
 ---
 
-## 🧰 Tech Stack
+## Tech Stack
 
 | Component            | Technology               | Purpose                                              |
 | -------------------- | ------------------------ | ---------------------------------------------------- |
@@ -175,7 +171,7 @@ Agents use CrewAI's `context` parameter to chain arguments: prosecution output f
 
 ---
 
-## 📦 Install
+## Install
 
 ```bash
 # Clone
@@ -190,7 +186,7 @@ npm install -g @getgrit/cli
 
 # Configure
 cp .env.example .env
-# Edit .env: set ZAI_API_KEY
+# Edit .env: set ZAI_API_KEY (get one at https://open.bigmodel.cn/)
 ```
 
 ### Requirements
@@ -201,7 +197,7 @@ cp .env.example .env
 
 ---
 
-## 🚀 Usage
+## Usage
 
 ### Web UI (Recommended)
 
@@ -284,32 +280,7 @@ Test fixtures in `tests/fixtures/locale/` contain deliberately bad Python and Ja
 
 ---
 
-## 📁 Project Structure
-
-```
-CodeTribunal/
-├── src/code_tribunal/
-│   ├── config.py          # Centralized configuration
-│   ├── evidence.py        # GritQL forensic scanning (17 patterns)
-│   ├── code_graph.py      # AST code dependency graph
-│   ├── tools.py           # 4 custom CrewAI tools
-│   ├── agents.py          # 8 agent definitions
-│   ├── react.py           # ReACT engine (LiteLLM function calling)
-│   ├── courtroom.py       # 6-phase pipeline orchestrator
-│   ├── pipeline.py        # State machine + persistence
-│   ├── app.py             # Gradio UI + export
-│   └── cli.py             # CLI entry point
-├── tests/
-│   ├── fixtures/locale/   # Deliberately bad code samples
-│   └── bad_code.zip       # Zip fixture for UI testing
-├── assets/
-│   └── logo.png           # 3D courtroom logo
-└── pyproject.toml
-```
-
----
-
-## 🎓 What Makes This a Strong Hackathon Entry
+## What Makes This a Strong Hackathon Entry
 
 1. **System Complexity** — 6-phase pipeline with 8 agents, 4 custom tools, code graph, and streaming
 2. **Effective Tool Use** — Agents use BaseTool with Pydantic schemas to read files, search patterns, and trace calls