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
148 lines
5.0 KiB
Python
148 lines
5.0 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.
|
|
|
|
from typing import Any, Literal
|
|
from collections.abc import AsyncGenerator, Callable
|
|
from artemis.engine.pipeline import Pipeline
|
|
from artemis.interfaces.sdk.task import StreamEvent, StreamEventType, TaskResult
|
|
from artemis.utils.logger import get_logger
|
|
|
|
logger = get_logger(__name__)
|
|
|
|
|
|
class ArtemisClient:
|
|
"""The official high-level developer entrypoint for interacting with ARTEMIS."""
|
|
|
|
def __init__(
|
|
self, device_id: str = "default-device", default_profile: Literal["flash", "pro"] = "pro"
|
|
):
|
|
self.device_id = device_id
|
|
self.default_profile = default_profile
|
|
|
|
async def run(
|
|
self,
|
|
goal: str,
|
|
profile: Literal["flash", "pro"] | None = None,
|
|
max_turns: int = 30,
|
|
**kwargs: Any,
|
|
) -> TaskResult:
|
|
"""Executes a single autonomous task and returns the final TaskResult."""
|
|
target_profile = profile or self.default_profile
|
|
logger.info(f"ArtemisClient running task '{goal}' with profile '{target_profile}'...")
|
|
|
|
state = await Pipeline.execute(
|
|
goal=goal,
|
|
profile=target_profile,
|
|
device_id=self.device_id,
|
|
)
|
|
|
|
return TaskResult(
|
|
trace_id=state.trace_id,
|
|
status=state.status.value,
|
|
turns=state.current_turn,
|
|
error=state.error_message,
|
|
)
|
|
|
|
async def stream_run(
|
|
self,
|
|
goal: str,
|
|
profile: Literal["flash", "pro"] | None = None,
|
|
max_turns: int = 30,
|
|
callbacks: list[Callable[[StreamEvent], Any]] | None = None,
|
|
**kwargs: Any,
|
|
) -> AsyncGenerator[StreamEvent, None]:
|
|
"""Executes an autonomous task while yielding real-time StreamEvents asynchronously."""
|
|
target_profile = profile or self.default_profile
|
|
logger.info(f"ArtemisClient streaming task '{goal}' with profile '{target_profile}'...")
|
|
|
|
# 1. Emit initial starting event
|
|
start_event = StreamEvent(
|
|
event_type=StreamEventType.STATUS,
|
|
step_number=0,
|
|
payload={
|
|
"status": "starting",
|
|
"goal": goal,
|
|
"profile": target_profile,
|
|
"device_id": self.device_id,
|
|
},
|
|
)
|
|
if callbacks:
|
|
for cb in callbacks:
|
|
try:
|
|
cb(start_event)
|
|
except Exception as e:
|
|
logger.debug(f"Callback error: {e}")
|
|
yield start_event
|
|
|
|
# 2. Execute task pipeline
|
|
try:
|
|
state = await Pipeline.execute(
|
|
goal=goal,
|
|
profile=target_profile,
|
|
device_id=self.device_id,
|
|
)
|
|
|
|
# 3. Emit intermediate step events
|
|
for step in state.steps:
|
|
ev = StreamEvent(
|
|
event_type=StreamEventType.STEP_END,
|
|
step_number=step.step_number,
|
|
payload={
|
|
"thought": step.thought,
|
|
"action": step.action_name,
|
|
"params": step.action_params,
|
|
"result": step.result,
|
|
"duration": step.duration_seconds,
|
|
},
|
|
)
|
|
if callbacks:
|
|
for cb in callbacks:
|
|
try:
|
|
cb(ev)
|
|
except Exception as e:
|
|
logger.debug(f"Callback error: {e}")
|
|
yield ev
|
|
|
|
# 4. Emit completion event
|
|
final_ev = StreamEvent(
|
|
event_type=StreamEventType.STATUS,
|
|
step_number=state.current_turn,
|
|
payload={
|
|
"status": state.status.value,
|
|
"turns": state.current_turn,
|
|
"error": state.error_message,
|
|
},
|
|
)
|
|
if callbacks:
|
|
for cb in callbacks:
|
|
try:
|
|
cb(final_ev)
|
|
except Exception as e:
|
|
logger.debug(f"Callback error: {e}")
|
|
yield final_ev
|
|
|
|
except Exception as e:
|
|
err_ev = StreamEvent(
|
|
event_type=StreamEventType.ERROR,
|
|
step_number=0,
|
|
payload={"error": str(e)},
|
|
)
|
|
if callbacks:
|
|
for cb in callbacks:
|
|
try:
|
|
cb(err_ev)
|
|
except Exception:
|
|
pass
|
|
yield err_ev
|