update my all files

Dockerfile

@@ -1,12 +1,21 @@
 FROM python:3.11-slim
 
+# Create non-root user
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
 WORKDIR /app
 
+# Copy requirements first
 COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
-COPY . .
+# Copy all files
+COPY --chown=user . /app
 
+# Expose port 7860 (Hugging Face default)
 EXPOSE 7860
 
-CMD ["uvicorn", "server.app:app", "--host", "0.0.0.0", "--port ", "7860"]
+# Run the server
+CMD ["uvicorn", "server.app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -8,9 +8,10 @@ An OpenEnv-compliant environment that tests AI agents on financial data analysis
 Quant-Gym is a benchmark environment where AI agents can practice:
 - Fetching real-time market data
 - Analyzing financial news sentiment
+- Executing buy/sell trades
 - Evaluating trading strategies with risk metrics
 
-This is a **research benchmark** for evaluating AI reasoning in financial contexts, not a trading tool.
+**This is a research benchmark for evaluating AI reasoning in financial contexts, not a trading tool.**
 
 ## 📊 Environment Tasks
 
@@ -24,55 +25,67 @@ This is a **research benchmark** for evaluating AI reasoning in financial contex
 
 | Endpoint | Method | Description |
 |----------|--------|-------------|
+| `/` | GET | Welcome message |
 | `/health` | GET | Health check |
 | `/reset` | POST | Reset environment to initial state |
-| `/step` | POST | Execute an action (BUY/SELL/GET_PRICE/BACKTEST) |
+| `/step` | POST | Execute an action (BUY/SELL/GET_PRICE/BACKTEST/GET_NEWS) |
 | `/state` | GET | Get current environment state |
 | `/tasks` | GET | List all available tasks |
+| `/docs` | GET | Interactive API documentation (FastAPI) |
 
 ## 🔧 Installation
 
 ### Prerequisites
 - Python 3.10+
-- Docker (for containerized deployment)
+- Docker (optional, for containerized deployment)
 
 ### Local Setup
 
 ```bash
 # Clone the repository
-git clone https://github.com/Samikshacode934/quant-gym-openenv.git
+git clone https://github.com/Astocoder/quant-gym-openenv.git
 cd quant-gym-openenv
 
 # Install dependencies
 pip install -r requirements.txt
 
-# Download market data
-python download_data.py
+# Set up Hugging Face token (optional, for LLM features)
+echo 'HF_TOKEN=your_hf_token_here' > .env
 
 # Start the server
-python -m uvicorn server.app:app --host 0.0.0.0 --port 8000
+python -m uvicorn server.app:app --host 0.0.0.0 --port 8000 --reload
 
 
 🎮 Action Schema
 The agent can take the following actions:
+
+json
 {
-  "type": "BUY | SELL | GET_PRICE | BACKTEST",
+  "type": "BUY | SELL | GET_PRICE | BACKTEST | GET_NEWS",
   "amount": 10,
   "explanation": "RSI indicates oversold condition",
   "strategy": "momentum"
 }
 
+Action Examples
+Action	Description
+{"type": "GET_PRICE"}	Get current stock price
+{"type": "BUY", "amount": 10}	Buy 10 shares
+{"type": "SELL", "amount": 5}	Sell 5 shares
+{"type": "GET_NEWS", "explanation": "your analysis"}	Get news with analysis
+{"type": "BACKTEST", "strategy": "momentum"}	Backtest momentum strategy
 
 
 👁️ Observation Schema
 The environment returns:
 
+json
 {
-  "timestamp": "2026-03-31 14:30:00",
-  "price": 248.45,
+  "timestamp": "step_5",
+  "price": 155.00,
   "balance": 8500.00,
   "holdings": 10,
-  "portfolio_value": 10984.50,
+  "portfolio_value": 10050.00,
   "last_news": {
     "headline": "Apple announces new AI chip",
     "sentiment": "positive"
@@ -84,23 +97,76 @@ The environment returns:
   }
 }
 
+🏃 Running the Baseline Agent
+# Set your Hugging Face token 
+export HF_TOKEN="your_hf_token_here"
+
+# Run inference
+python inference.py
+
+Expected Output:-
+[INFO] HF_TOKEN found (length: 37 chars)
+[START] task=quant-gym env=quant-gym model=meta-llama/Llama-3.2-3B-Instruct
+[STEP] step=1 action=BUY 5 reward=0.15 done=false error=null
+[STEP] step=2 action=GET_PRICE reward=0.05 done=false error=null
+[STEP] step=3 action=SELL 5 reward=0.20 done=false error=null
+...
+[END] success=true steps=10 score=0.650 rewards=...
+
+
+🐳 Docker Deployment
+Build and run with Docker:
+# Build the image
+docker build -t quant-gym .
 
+# Run the container
+docker run -p 7860:7860 quant-gym
 
+Then access the API at http://localhost:7860
 
-Architecture
+🌐 Hugging Face Space
+Live demo: https://huggingface.co/spaces/Astocoder/quant-gym
+
+📁 Project Structure
 quant-gym-openenv/
-├── models.py              # Pydantic schemas
-├── openenv.yaml           # OpenEnv configuration
-├── inference.py           # Baseline agent
-├── requirements.txt       # Dependencies
+├── Dockerfile              # Container configuration
+├── inference.py            # Baseline agent script
+├── models.py               # Pydantic schemas
+├── openenv.yaml            # OpenEnv configuration
+├── requirements.txt        # Python dependencies
+├── README.md               # This file
 ├── server/
-│   ├── app.py            # FastAPI server
-│   ├── environment.py    # Trading logic
-│   ├── Dockerfile        # Container config
+│   ├── app.py             # FastAPI server
+│   ├── environment.py     # Trading logic
 │   └── data/
-│       ├── prices.csv    # Market data
-│       └── news.json     # News headlines
+│       ├── prices.csv     # Market data
+│       └── news.json      # News headlines
 └── graders/
-    ├── task1_grader.py
-    ├── task2_grader.py
-    └── task3_grader.py
+    ├── task1_grader.py    # Price fetch grader
+    ├── task2_grader.py    # News analysis grader
+    └── task3_grader.py    # Backtest grader
+
+
+🔐 Environment Variables
+Variable	Description	Default
+HF_TOKEN	Hugging Face API token	None (optional)
+API_BASE_URL	HF API endpoint	https://api-inference.huggingface.co/v1
+MODEL_NAME	LLM model name	meta-llama/Llama-3.2-3B-Instruct
+BASE_URL	Quant-Gym API URL	http://localhost:8000
+
+
+📈 Evaluation Criteria
+OpenEnv Compliance: Full implementation of step()/reset()/state() APIs
+
+Task Completion: All 3 tasks return scores between 0.0-1.0
+
+Reward Function: Partial progress signals for meaningful learning
+
+Reproducibility: Static data ensures consistent results
+
+
+⚠️ Disclaimer
+This is a research benchmark environment for evaluating AI agent reasoning. It does not provide financial advice or real trading recommendations. All data is for simulation purposes only.
+
+
+

server/app.py

@@ -2,11 +2,15 @@ import sys
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from fastapi import FastAPI, HTTPException, Request
+from fastapi import FastAPI, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
 from typing import Optional, Dict, Any, List
 from enum import Enum
+from server.app import app as quant_gym_app
+
+
+app = quant_gym_app
 
 # Simple models for the API
 class ActionType(str, Enum):