Skip to main content

Automation browser error detection and screen detection with AI fallback and cache

Project description

Automation Error Detector

🚀 Automation Error Detector là một Python package giúp bạn phát hiện và phân loại lỗi màn hình trình duyệt trong automation, sử dụng OpenAI API chỉ một lần, sau đó cache kết quả để tái sử dụng mà không cần AI nữa.

Package được thiết kế theo DDD + Clean Architecture, cho phép bạn tự do lưu cache ở bất kỳ đâu (Redis, PostgreSQL, file, cloud, v.v.) thông qua callback.


✨ Features

  • ✅ Phát hiện lỗi từ text trên màn hình trình duyệt
  • 🤖 AI fallback (OpenAI) chỉ dùng khi cache miss
  • ⚡ Cache thông minh bằng signature từ keywords
  • 🔌 Pluggable cache callback (Redis, Postgres, JSON, custom)
  • 🧱 Kiến trúc DDD + Clean Architecture
  • 📦 Sẵn sàng publish & reuse qua PyPI
  • 🧪 Dễ test, dễ mở rộng, production-ready

📦 Installation

pip install automation-error-detector

🔐 Environment Variables

Name Required Description
OPENAI_API_KEY OpenAI API key
OPENAI_MODEL Model name (default: gpt-4.1-mini)
ERROR_CACHE_FILE Cache file path (JSON adapter)
export OPENAI_API_KEY="sk-xxxx"

🚀 Quick Start

from application.use_cases.detect_error_use_case import DetectErrorUseCase
from infrastructure.ai.openai_client import OpenAIClient
from infrastructure.cache.json_cache_callback import JsonCacheCallback

cache = JsonCacheCallback()
ai = OpenAIClient()

use_case = DetectErrorUseCase(
    cache_callback=cache,
    ai_client=ai
)

screen_text = """
Your session has expired.
Please log in again.
"""

result = use_case.execute(screen_text)
print(result.to_dict())

🌐 OpenAI Proxy (Instance-based)

Package KHÔNG dùng HTTP_PROXY / HTTPS_PROXY của OS. Proxy được inject theo từng OpenAIClient instance.

HTTP / HTTPS Proxy

proxy = {
    "https": "http://127.0.0.1:8080"
}

ai = OpenAIClient(proxy=proxy)

SOCKS5 Proxy

proxy = {
    "socks": "socks5://127.0.0.1:1080"
}

ai = OpenAIClient(proxy=proxy)

🔌 Custom Cache Callback

Bạn có thể lưu cache ở bất kỳ đâu bằng cách implement callback.

from domain.services.cache_callback import CacheSaveCallback

class CacheSaveCallback:
    def load(self, signature: str) -> dict | None:
        pass

    def save(self, signature: str, data: dict) -> None:
        pass

⚙️ Configuration API

from config import AppConfig

AppConfig.openai_api_key
AppConfig.openai_model
AppConfig.cache_file

🔒 Security Notes

  • Không hard-code API key
  • Không commit .env
  • Luôn dùng ENV variables

📄 License

MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

automation_error_detector-1.1.0.tar.gz (9.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

automation_error_detector-1.1.0-py3-none-any.whl (14.1 kB view details)

Uploaded Python 3

File details

Details for the file automation_error_detector-1.1.0.tar.gz.

File metadata

File hashes

Hashes for automation_error_detector-1.1.0.tar.gz
Algorithm Hash digest
SHA256 ccc0e2dc48a594da9d987930d7da52d89dd64aec311ea6e166ca698b8c8d3e1f
MD5 6450a6ba72ca9eb590b613f0a36725a6
BLAKE2b-256 1fac88c9316a960db0cd6286b850091fc4beaf6ad9eb71391a2d8d9f1727b7e0

See more details on using hashes here.

File details

Details for the file automation_error_detector-1.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for automation_error_detector-1.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 cbd835c94fc53879c4953e4057f7ab46e26c3037f05c858afc32ae6124b07dcd
MD5 290e236606f23b5e57b046283ad390ec
BLAKE2b-256 28917b0118ac2058494c275a26176451279a9eaf34ff464c27cef1e3b1cfd163

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page