Default Flash final review to off and persist the setting across the UI,
MCP, SDK and queued tasks. Keep execution separate from test verdicts.
Bundle UI fonts and licenses to remove Google Fonts from startup builds.
Align backend/frontend versions and document installation and upgrades.
Install and update artemis-use with task diagnostics and plugin guidance. Preserve cross-device file receipts, review canonical reports, guard stage transitions and reduce small history summaries. Improve exploration lifecycle, request recovery and browser live connections.
Align Responses cache affinity across execution and summary calls, preserve required checks and evidence uncertainty, and allow safe deletion of inactive explorations while retaining independent reruns.
Validation: backend suite passed except intentional prompt golden drift, then all 17 transcript tests passed after snapshot refresh; 268 frontend tests and production build passed; Ruff, quality ratchet and core type checks passed.
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
- 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.
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.
chenmingxuan
somew1nd