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
103 lines
3.3 KiB
Python
103 lines
3.3 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.
|
|
|
|
import time
|
|
from typing import Any
|
|
from uuid import UUID
|
|
from pydantic import BaseModel, ConfigDict, Field
|
|
|
|
|
|
class SessionMetadata(BaseModel):
|
|
model_config = ConfigDict(arbitrary_types_allowed=True)
|
|
session_id: UUID | str
|
|
initial_goal: str
|
|
start_time: float = Field(default_factory=time.time)
|
|
end_time: float | None = None
|
|
status: str = "running" # running, success, failed
|
|
device_info: dict[str, Any] = Field(default_factory=dict)
|
|
pid: int | None = None
|
|
video_filepath: str | None = None
|
|
|
|
|
|
class ImageRecord(BaseModel):
|
|
model_config = ConfigDict(arbitrary_types_allowed=True)
|
|
image_name: str # SHA-256 hash
|
|
timestamp: float = Field(default_factory=time.time)
|
|
ocr_result: Any | None = None
|
|
ui_tree: Any | None = None
|
|
extra_metadata: dict[str, Any] = Field(default_factory=dict)
|
|
|
|
|
|
class StepRecord(BaseModel):
|
|
model_config = ConfigDict(arbitrary_types_allowed=True)
|
|
step_id: UUID | str
|
|
session_id: UUID | str
|
|
step_number: int
|
|
timestamp: float = Field(default_factory=time.time)
|
|
pre_image_name: str | None = None
|
|
post_image_name: str | None = None
|
|
summary: str | None = None
|
|
action_taken: Any | None = None
|
|
operator_raw_thinking: str | None = None
|
|
operator_native_thinking: str | None = None
|
|
last_execution_result: Any | None = None
|
|
extra_metadata: dict[str, Any] = Field(default_factory=dict)
|
|
|
|
|
|
class TraceRecord(BaseModel):
|
|
model_config = ConfigDict(arbitrary_types_allowed=True)
|
|
trace_id: UUID | str
|
|
session_id: UUID | str
|
|
step_id: UUID | str | None = None
|
|
parent_trace_id: UUID | str | None = None
|
|
type: str # "agent", "tool", "log"
|
|
name: str
|
|
timestamp: float = Field(default_factory=time.time)
|
|
duration: float | None = None
|
|
status: str = "success" # success, failed, running
|
|
payload: dict[str, Any] = Field(default_factory=dict)
|
|
|
|
|
|
class FailedOutputRecord(BaseModel):
|
|
model_config = ConfigDict(arbitrary_types_allowed=True)
|
|
session_id: UUID | str
|
|
trace_id: UUID | str
|
|
model_name: str
|
|
prompt: str
|
|
raw_output: str
|
|
error_message: str
|
|
timestamp: float = Field(default_factory=time.time)
|
|
|
|
|
|
class BackgroundTaskRecord(BaseModel):
|
|
model_config = ConfigDict(arbitrary_types_allowed=True)
|
|
task_id: str
|
|
session_id: UUID
|
|
summary: str
|
|
status: str = "running" # running, completed, failed
|
|
start_time: float = Field(default_factory=time.time)
|
|
end_time: float | None = None
|
|
trace_id: str | None = None
|
|
logs: str | None = None
|
|
|
|
|
|
class VideoRecordingRecord(BaseModel):
|
|
model_config = ConfigDict(arbitrary_types_allowed=True)
|
|
video_id: UUID
|
|
session_id: UUID | None = None
|
|
device_id: str
|
|
start_time: float
|
|
end_time: float | None = None
|
|
local_video_path: str | None = None
|