Open
Conversation
A unified GUI Agent task execution framework has been added, supporting multiple models (MobiAgent, UI-TARS, etc.) Access and execute mobile automation tasks. It includes the following main components: - Unify the entry script run.py The basic task class base_task.py defines a unified task execution interface Task Manager task_manager.py - Configuration file config.json - Model Adapter (MobiAgent, UI-TARS) - Complete User Guide RUNNER_README.md This framework supports: - Single task and batch task execution - Step loop mode and one-time execution mode - Motion visualization drawing - Task planning function - Detailed records of the execution results docs(e2e_qwen3): Fixed the quotation mark format in the prompt Uniformly correct the quotation mark format of the status parameter description in the done action to ensure consistency.
Added support for AutoGLM provider Added new sample script Introduce the ACTION_TYPE_ALIASES mapping table to unify the specific action names of each model to the standard format. Including mappings of action types such as clicking, long pressing, double-clicking, inputting, and swiping. Improve the app_package_names mapping tables for AndroidDevice and HarmonyDevice and add multiple categories
…ntation content RUNNER_README.md has been updated to provide more detailed instructions for use, including - Added more usage examples of models (Qwen, AutoGLM) The parameter description table has been improved, including basic parameters, task parameters, and general model parameters It provides a detailed description of the output result format and directory structure - Expanded the development guidelines for integrating new models - Optimized the project structure description and the quick start section feat(runner): Unify log configuration and enhance logging functionality Remove the duplicate logger-level Settings in each module and uniformly configure them with setup_logging() - Improved the log configuration function to support the configuration of all module loggers
8f9cdea to
571efb6
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
A new usage framework integrating multiple models has been added.
Currently, it supports MobiAgent, UI-TARS, Qwen, and AutoGLM, and enables quick configuration and operation of various mobile GUI agents through line commands