AgentScopeV1.0 WebSearch Workflow(simple react + search api)

[garyzhang99]

Description

As the title says.

Checklist

Please check the following items before code is ready to be reviewed.

• Code has passed all tests
• Docstrings have been added/updated in Google Style
• Documentation has been updated
• Code is ready for review

[gemini-code-assist]

Summary of Changes

Hello @garyzhang99, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a new, dedicated workflow designed to perform web searches using an AI agent. It leverages the AgentScope V1 framework's ReAct capabilities to interact with external search tools, expanding the system's ability to gather information from the internet and providing a structured way to evaluate the agent's performance.

Highlights

• New Workflow for Web Search: A new workflow, AgentScopeV1ReactSearchWorkflow, has been introduced to enable ReAct-based web search capabilities using the AgentScope V1 framework.
• AgentScope Integration: This workflow integrates AgentScope's ReAct agent, allowing it to perform web searches via the Tavily API, enhancing the system's ability to gather external information.
• Workflow System Registration: The new workflow is properly imported and registered within the trinity workflow system, making it discoverable and available for use.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a new AgentScopeV1ReactSearchWorkflow for web search capabilities. The changes are well-structured, primarily adding a new workflow file and registering it. My review focuses on improving robustness, maintainability, and adherence to best practices. I've identified a critical import error that would prevent the code from running, along with opportunities to reduce code duplication, prevent potential resource leaks with better error handling, and clarify the code's intent.

[Copilot]

Pull Request Overview

This PR implements a web search workflow using AgentScope V1.0 framework with ReAct (Reasoning and Acting) paradigm. The workflow enables agents to perform multi-turn web searches to answer questions using external search tools.

Key changes include:

• New AgentScopeV1ReactSearchWorkflow class supporting Tavily and SearXNG search clients
• Complete example setup with dataset generation from WebWalkerQA
• Configuration and documentation for training multi-turn web search agents

Reviewed Changes

Copilot reviewed 6 out of 8 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
trinity/common/workflows/envs/agentscope/agentscopev1_search_workflow.py	Core workflow implementation with ReAct agent, MCP client integration, and LLM-based evaluation
trinity/common/workflows/envs/agentscope/agentscopev0_react_workflow.py	Comment update to clarify file purpose
trinity/common/workflows/init.py	Registration of new workflow class in module exports
examples/agentscope_websearch/get_webwalkerQA_data.py	Dataset generation script for WebWalkerQA preprocessing
examples/agentscope_websearch/agentscopev1_websearch_agent.yaml	Training configuration with GRPO algorithm and model parameters
examples/agentscope_websearch/README.md	Documentation for setup, usage, and results

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}