FROM python:3.12-slim

# Install X virtual framebuffer and UI automation dependencies
RUN apt-get update && apt-get install -y 
    xvfb 
    x11-utils 
    scrot 
    python3-tk 
    python3-dev 
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Start virtual display on port :99 before executing the Python agent
CMD ["sh", "-c", "Xvfb :99 -screen 0 1920x1080x24 & export DISPLAY=:99 && python agent_core.py"]
  

import mss
import base64
import logging
from PIL import Image
import io# Initialize enterprise logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - [AGENT-VISION] - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)def capture_visual_context():
"""Captures the virtual display and encodes it for Claude 4.5 ingestion."""
try:
with mss.mss() as sct:
monitor = sct.monitors[1] # Target the Xvfb primary display
sct_img = sct.grab(monitor)
# Convert to PIL Image for optimization
img = Image.frombytes("RGB", sct_img.size, sct_img.bgra, "raw", "BGRX")
# Downscale to 1280x720 to optimize token consumption while preserving UI text legibility
img.thumbnail((1280, 720))
buffered = io.BytesIO()
img.save(buffered, format="JPEG", quality=85)
logger.info(f"Visual context captured at resolution: {img.size}")
return base64.b64encode(buffered.getvalue()).decode('utf-8')
except Exception as e:
logger.error(f"Visual telemetry failure: {e}")
...
تابع القراءة
سجل دخولك مجاناً لقراءة المقال كاملاً والوصول إلى أدوات الذكاء الاصطناعي.
تسجيل الدخول / إنشاء حساب