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
60 lines
1.9 KiB
Python
60 lines
1.9 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.
|
|
|
|
"""Dynamic prompt template builder for Operator Agent."""
|
|
|
|
from jinja2 import Template
|
|
|
|
OPERATOR_SYSTEM_PROMPT = """You are ARTEMIS Operator, an expert autonomous mobile device interaction agent.
|
|
Your objective is to observe the current Android mobile screen and take precise actions to achieve the user's goal.
|
|
|
|
Available action commands:
|
|
- click(target=[x, y]): Normalized coordinates 0-1000 scale.
|
|
- swipe(action="up"|"down"|"left"|"right"|[x1, y1, x2, y2]): Drag across screen.
|
|
- input_text(text="...", target=[x, y]): Click field and type.
|
|
- press_key(key="home"|"back"|"enter"|"delete"): Press hardware key.
|
|
- wait_for_delay(seconds=...): Pause execution.
|
|
"""
|
|
|
|
OPERATOR_HUMAN_TEMPLATE = """Goal: {{ goal }}
|
|
Active Sub-Goal: {{ sub_goal }}
|
|
Current Turn: {{ current_turn }}
|
|
Execution History:
|
|
{{ history }}
|
|
"""
|
|
|
|
|
|
class OperatorPromptBuilder:
|
|
"""Builds prompt messages and multimodal contents for the Operator Agent."""
|
|
|
|
@classmethod
|
|
def build_system_message(cls) -> str:
|
|
return OPERATOR_SYSTEM_PROMPT
|
|
|
|
@classmethod
|
|
def build_human_message(
|
|
cls,
|
|
goal: str,
|
|
sub_goal: str = "",
|
|
current_turn: int = 1,
|
|
history: str = "",
|
|
) -> str:
|
|
template = Template(OPERATOR_HUMAN_TEMPLATE)
|
|
return template.render(
|
|
goal=goal,
|
|
sub_goal=sub_goal,
|
|
current_turn=current_turn,
|
|
history=history,
|
|
)
|