Add Web Dashboard with multi-device control and callback hooks

Features:
- Web Dashboard: FastAPI-based dashboard with Vue.js frontend
  - Multi-device support (ADB, HDC, iOS)
  - Real-time WebSocket updates for task progress
  - Device management with status tracking
  - Task queue with execution controls (start/stop/re-execute)
  - Detailed task information display (thinking, actions, completion messages)
  - Screenshot viewing per device
  - LAN deployment support with configurable CORS

- Callback Hooks: Interrupt and modify task execution
  - step_callback: Called after each step with StepResult
  - before_action_callback: Called before executing action
  - Support for task interruption and dynamic task switching
  - Example scripts demonstrating callback usage

- Configuration: Environment-based configuration
  - .env file support for all settings
  - .env.example template with documentation
  - Model API configuration (base URL, model name, API key)
  - Dashboard configuration (host, port, CORS, device type)
  - Phone agent configuration (delays, max steps, language)

Technical improvements:
- Fixed forward reference issue with StepResult
- Added package exports for callback types and configs
- Enhanced dependencies with FastAPI, WebSocket support
- Thread-safe task execution with device locking
- Async WebSocket broadcasting from sync thread pool

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
let5sne.win10
2026-01-09 02:20:06 +08:00
parent 9fe189a8f8
commit 3552df23d6
31 changed files with 4221 additions and 8 deletions

View File

@@ -11,6 +11,9 @@ Environment Variables:
PHONE_AGENT_API_KEY: API key for model authentication (default: EMPTY)
PHONE_AGENT_MAX_STEPS: Maximum steps per task (default: 100)
PHONE_AGENT_DEVICE_ID: ADB device ID for multi-device setups
Configuration Files:
.env: Automatically loaded from current directory or project root
"""
import argparse
@@ -20,8 +23,12 @@ import subprocess
import sys
from urllib.parse import urlparse
from dotenv import load_dotenv
from openai import OpenAI
# Load .env file if exists (search in current directory and project root)
load_dotenv()
from phone_agent import PhoneAgent
from phone_agent.agent import AgentConfig
from phone_agent.agent_ios import IOSAgentConfig, IOSPhoneAgent