Localize the web console and persist custom model and capability settings.
Use OpenAI Responses exclusively and move runtime limits into environment configuration.
Bootstrap uv and the virtual environment on Windows, support optional China mirrors,
and package source distributions without environments, build output, or credentials.
Update regression tests and repository quality checks for the new behavior.
This reverts commit 54fcef9887.
Please do not submit unrelated docs and codes in the same commit. I am reverting this commit so that the related files can be submitted in better-organized future commits.
- Add NOTICE file and README license references for mobile-use and finalrun-agent
- Add derivative attribution headers to 17 files derived from mobile-use
- Rename hopper agent to entity_extractor across prompts, tools, and configs
- Remove obsolete adb_tunnel, ApiBaseUrl, and legacy CLI utility scripts
- Replace legacy examples with native Artemis diagnostic and workflow examples
- Update unit and tool tests to validate entity_extractor and SDK builders
Preserve user guidance through history compression, stabilize Flash index targets, and retire withdrawn checks without applying stale verdicts.
Improve runtime diagnostics, tool responses, and history rendering. Simplify documentation and comments.
Validation: 2076 tests passed in the full suite; 381 affected tests and 26 frontend tests passed after cleanup. Ruff and the quality ratchet passed.
Report device actions as dispatched and preserve full failure details. Route
Flash through McpActionExecutor and use ToolFailure across helper tools and
agent loops instead of inferring failure from response text.
Require model-provided descriptions for coordinate targets. Keep observed
element metadata separate from those descriptions in safety checks, visual
summaries, history, and frontend labels.
Add Gemini Interactions API video analysis with configurable processing mode,
chunk size, and timeouts. Centralize Google provider capabilities and token
usage normalization, and update google-genai to 2.22.0.
Preserve system instructions on follow-up interactions, replan pending chunks
when falling back to static processing, and reject unanswered native video
and audio segments instead of caching placeholder results. Keep helper-tool
failure status intact through history tools and committee calls.
Validation: 1,762 Python unit tests passed (3 skipped), 40 frontend formatter
tests passed, and the production UI build completed. Ruff lint, formatting,
the quality ratchet, and git diff checks passed.
Add execution incidents, action bursts and shared Flash history.
Expose verification and Explorer settings with streamed check results.
Support graceful cancellation, recording recovery and bundled UI resources.
Add CI quality checks and clean up comments and documentation.
- Set stdin=subprocess.DEVNULL across runtime, client, and utility subprocess calls to avoid hijacking the parent process's stdin.
- Run awake service initialization asynchronously on a daemon thread in MCP server startup.
- Redirect logger header printing to stderr to ensure stdio JSON-RPC purity.
- Add unit and lifecycle tests for MCP stdio protocol handshake and stdin isolation.
- Implement DevicePool and DeviceExecutionLock concurrency modes (per-device FIFO vs global serialization)
- Extend ArtemisClient SDK and CLI with explicit device targeting and concurrency strategy configuration
- Add server lifecycle management (artemis restart, stop, status) with cross-platform PID discovery
- Update MCP server tools to support multi-device dispatch, trace tagging, and per-device execution
- Enhance Showcase UI with step-by-step visual replay, playback speed controls, and device serial badges
- Add comprehensive unit test coverage and edge-case verification scripts
- UI: Implement dual-mode playback in FloatingVideoPlayer supporting video and step-by-step frame replay with scrub controls and auto-fallback
- Runtime: Prevent asyncio event loop hangs on Darwin and Linux by avoiding psutil.wait_procs on direct child processes
- Task Queue: Add worker exit watchdog and automatic recording recovery for completed or interrupted sessions
- Recording: Add ffmpeg ultrafast transcode fallback, shield recording finalization against cancellation, and handle on-the-fly MP4 conversion
- Docs: Polish README_CN styling and streamline flash runner agent prompt
Roll scrcpy recordings by device rotation and duration, and publish timeline manifests for playback and analysis.
Add seamless segmented playback in the showcase UI and configurable stay-awake strategies for Android automation.
chenmingxuan
somew1nd