q792602257andClaude Sonnet 5
635ed91041
Documents moving the repo from Windows/other dev machines to macOS and driving a real iPhone end-to-end via Appium + WebDriverAgent: Xcode/Appium toolchain setup, WDA signing (using the extra_capabilities passthrough already supported by WDADriverConfig), minimal real-device verification, and starting a Runtime API that explicitly registers and connects the device (neither the Console nor REST API currently expose a connect/disconnect endpoint). Also covers multi-device port allocation, common failure modes, and a completion checklist. README gains a pointer to it under a new "Operator Guides" section. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
1.4 KiB
1.4 KiB
Device Agent Runtime
Device Agent Runtime is a device-agnostic runtime for LLM-driven automation. It gives agents a stable way to observe, decide, and act against real devices through a small set of domain models, driver contracts, tools, perception providers, and runtime orchestration.
iPhone automation through WebDriverAgent/Appium is the first driver, not the platform boundary. Future drivers can target Android, browsers, desktop environments, or other device surfaces without changing the runtime's core contracts.
Current Shape
core/: shared domain models and runtime errors.driver/: theDrivercontract, concrete driver adapters, and driver-type registry.device/: device lifecycle and active driver management.tools/: device capabilities exposed to runtime and API layers.perception/: screen-to-Sceneperception behindPerceptionProvider.runtime/: planning and execution orchestration.api/: REST/MCP transport adapters.storage/: timeline, task, and device configuration persistence.
Project Direction
The durable roadmap is in docs/ROADMAP.md. The architecture invariants future changes must preserve are in docs/CONSTITUTION.md.
Operator Guides
- macOS migration and real iPhone setup: install Xcode, Appium/XCUITest, sign WebDriverAgent, verify a real device, and start a connected Runtime API.