Fix screenshot capture and add multi-provider support

- Fix adb exec-out binary pipe for screenshot capture
- Add XAI, Azure, and any OpenAI-compatible endpoint support
- Add rate limit retry logic
- Document all supported provider configurations
This commit is contained in:
Ubuntu
2026-05-19 02:17:23 +00:00
parent 4f39967606
commit e08a4a7a36
3 changed files with 10041 additions and 2 deletions

View File

@@ -15,8 +15,30 @@ Requirements:
ADB in PATH with a connected device/emulator.
Usage:
export OPENAI_API_KEY=...
python scripts/android-cua-smoke.py --goal "Connect to server 100.108.64.76:4096 and send 'ping'"
# OpenAI
export OPENAI_API_KEY=sk-...
python scripts/android-cua-smoke.py
# Azure OpenAI (with deployment)
export OPENAI_API_KEY=<key>
export OPENAI_BASE_URL=https://<resource>.openai.azure.com/openai/deployments/<deployment>/
python scripts/android-cua-smoke.py --model gpt-4o
# Google Gemini (via OpenAI-compat)
export GEMINI_API_KEY=AIza...
python scripts/android-cua-smoke.py
# xAI Grok
export XAI_API_KEY=xai-...
python scripts/android-cua-smoke.py
# Any OpenAI-compatible endpoint (LiteLLM, Ollama, etc.)
export OPENAI_API_KEY=dummy
export OPENAI_BASE_URL=http://localhost:4000/v1
python scripts/android-cua-smoke.py --model gpt-4o
# Custom goal
python scripts/android-cua-smoke.py --goal "Open settings and toggle dark mode"
"""
import argparse