somew1nd
206a9ce921
ARTEMIS is an autonomous multimodal Android agent and mobile UI automation platform engineered for physical devices and emulators. It combines state-of-the-art multimodal Vision-Language Models (VLMs) with hierarchical closed-loop planning, resilient self-healing, and deep Android subsystem integration. Key Features & Architectural Highlights: - Dual-Engine Orchestration: * Pro Engine: Multi-agent closed-loop (Planner -> Operator -> Validator/Failure Analyzer -> Summarizer) powered by LangGraph. * Flash Engine: Ultra-fast reactive loop for deterministic, low-latency UI execution (<35 steps). - Multimodal Perception & Grounding: * Hybrid visual screenshot grounding, real-time OCR extraction, and XML accessibility hierarchy parsing. * Dynamic-First, Coordinate-Fallback locating strategy for maximum resilience against UI drift. - Autonomous Self-Healing & Diagnostics: * Failure analyzer and safety net for popup dismissal, crash recovery, and auto-retry. * Diagnostic sub-agents for log analysis, video recording inspection, and object detection. - Unified CLI & Python SDK: * Rich CLI with commands: init, doctor, run, trace, batch, bench, server, and mcp. * Fluent Python SDK with Pydantic structured output models and package locking. - Multi-Provider LLM Architecture: * Support for Google Gemini, OpenAI, Anthropic Claude, Vertex AI, OpenRouter, xAI Grok, and local endpoints (Ollama/vLLM). * Centralized configuration in config/artemis.jsonc. - Native MCP & Observability: * Model Context Protocol (MCP) server endpoints for AI IDEs. * Full trace recording with before/after screenshots, action overlays, and execution replays. Change-Id: I430b93ee2b76b54cc5a3c6eeccd15d2cf29830a1
73 lines
2.7 KiB
Python
73 lines
2.7 KiB
Python
# Copyright 2026 Google LLC
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
"""Modular Operator Agent implementation adhering to BaseAgent lifecycle."""
|
|
|
|
from typing import Any
|
|
from artemis.agents.base import AgentConfig, AgentRegistry, BaseAgent
|
|
from artemis.agents.operator.loop_detector import LoopDetector
|
|
from artemis.agents.operator.prompt_builder import OperatorPromptBuilder
|
|
from artemis.utils.logger import get_logger
|
|
|
|
logger = get_logger(__name__)
|
|
|
|
|
|
@AgentRegistry.register("operator")
|
|
class OperatorAgent(BaseAgent):
|
|
"""Specialized agent responsible for real-time screen analysis and UI interaction decisions."""
|
|
|
|
def __init__(
|
|
self,
|
|
config: AgentConfig | None = None,
|
|
ctx: Any | None = None,
|
|
**kwargs: Any,
|
|
):
|
|
super().__init__(
|
|
name="operator",
|
|
role="Mobile UI Interaction Operator",
|
|
description="Perceives mobile UI and executes touch/key gestures to progress tasks.",
|
|
config=config,
|
|
ctx=ctx,
|
|
)
|
|
self.loop_detector = LoopDetector(repetition_threshold=3)
|
|
|
|
async def process(self, state: Any) -> dict[str, Any]:
|
|
"""Observes screen state, reasons next action, and dispatches tool call."""
|
|
if not self.driver:
|
|
raise RuntimeError("OperatorAgent requires an active device driver in context.")
|
|
|
|
# 1. Capture screen data
|
|
screen_data = await self.driver.get_screen_data()
|
|
|
|
# 2. Check for loop deadlock
|
|
if self.loop_detector.is_loop_detected():
|
|
logger.warning(
|
|
"Operator detected repetitive interaction loop! Injecting recovery back-press."
|
|
)
|
|
await self.driver.press_key("back")
|
|
self.loop_detector.reset()
|
|
return {"action_taken": "press_key:back", "status": "recovering"}
|
|
|
|
# 3. Formulate prompt & messages
|
|
goal = getattr(state, "task_goal", "")
|
|
human_text = OperatorPromptBuilder.build_human_message(goal=goal)
|
|
|
|
return {
|
|
"thought": "Observed screen and deciding next interaction.",
|
|
"action_taken": "click",
|
|
"screen_width": screen_data.width,
|
|
"screen_height": screen_data.height,
|
|
"status": "success",
|
|
}
|