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
Regenerate uv.lock against PyPI without changing dependency versions or hashes. Check Python and npm dependency sources before CI installation and enforce a current lockfile.
Fixes#28
- Introduce ArtemisAccessibilityHelper APK (API 24 to 37+) as a conflict-free, high-performance replacement for UiAutomator:
* Eliminates native UiAutomator waitForIdle() timeouts, reducing DOM dump latency from ~3s to ~15ms and maintaining resilience against infinite animations.
* Implements a multi-tier fallback hierarchy discovery strategy (multi-window layer enumeration -> active window fallback -> input/accessibility focus backtracking) with adaptive progressive backoff for seamless page transition capture.
* Resolves node drop defect caused by 32-bit hash collisions on recurring virtual view IDs in long lists and WebViews by utilizing bounded recursion (MAX_DEPTH=75, MAX_NODES=8000).
* Strict W3C XML 1.0 character sanitization filtering invalid ASCII control codes and escaping attribute whitespace ( , , 	) to preserve multiline text formatting.
* Enriches semantic parsing with stateDescription (API 30+ Jetpack Compose), screenReaderFocusable, paneTitle, heading, error, and tooltip attributes.
* Multi-window metadata propagation tagging each node with window-id, window-type, and window-layer.
* Adds dual-path standalone build script (build_apk.sh) producing a clean 29KB APK without Gradle daemon overhead alongside standard Gradle Kotlin DSL.
- Integrate AccessibilityClient into Artemis Python runtime with automatic bundled APK detection, self-healing installation, and port forwarding.
- Add unit test suite covering AccessibilityClient endpoints and atomic snapshot parsing.
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.
- Rewrite generate_banner.py with Pillow supersampling, Montserrat font caching, seamless background extension, and ambient glow
- Add horizontal offset (--offset-x, default +160px) to balance visual weight against the crescent moon
- Add raw background asset artemis-banner-raw.jpg
- Regenerate and synchronize artemis-banner.png, artemis-banner-cn.png, and artemis-banner-en.png
- Bump banner image cache version in README.md and README_CN.md
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.
- Handle Debian/Ubuntu apt-get lock contention with DPkg::Lock::Timeout
- Decouple apt update from apt install so locks on update do not block installation
- Add official portable scrcpy v4.1 fallback download for Linux (x64/arm64) and Windows (win64)
- Add scrcpy user directories to standard PATH discovery
- Auto-patch Angular CLI 22.1.6 node-version.js requirement from ^22.22.3 to 22.22.0 across Linux, macOS, and Windows startup scripts
- Automatically detect and load nvm in start.sh and install_deps.sh when available
- Ensure Showcase UI can be built on Cloudtop and Debian systems running Node 22.22.x without requiring root privileges
- Backend (LLM Gateway):
- Record structured 'llm_stream_reset' event with discard action, failure reason, and retry messaging on mid-stream generation errors.
- Add unit test verifying stream reset event payload on mid-stream errors.
- Frontend (Showcase UI):
- Handle 'llm_stream_reset' events in agent service and stream aggregator, discarding interrupted chunks while showing retry indicators.
- Establish a single source of truth for tool and action events in the timeline to eliminate duplicated action rows while retaining ADB and explorer tools.
- Add @angular/cdk dependency and update agent stream component styling and layout.
- Add unit tests for stream aggregation and tool display filtering.
Fix queue cancellation, concurrency limits and worker status updates.
Use direct Explorer imports, split the Diagnoser loop into helpers and remove unused tool registration and prompt-builder code.
Correct model caching, endpoint selection and retry handling.
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.
chenmingxuan
somew1nd