Feat/fin app

[alcholiclg]

Change Summary

1. adds full support for the fin_research app, enabling local deployment through Gradio.
2. adds LocalCodeExecutionTool support for notebook_executor (Jupyter kernel), python_executor, shell_executor, reset_executor, get_executor_info, and file operations, and introduces environment-variable isolation for Jupyter kernel sessions.
3. fixes the ArXiv schema format issue caused by recent API changes.
4. updates the search engine to support reading thread-isolated environment variables and global configuration.
5. adds a configurable option in deep research to enable or disable follow-up questions.
6. updates the README documentation.
7. improves working-directory awareness for the Analyst and Collector agents.

Related issue number

Checklist

• [ ] The pull request title is a good summary of the changes - it will be used in the changelog
• [ ] Unit tests for the changes exist
• [ ] Run pre-commit install and pre-commit run --all-files before git commit, and passed lint check.
• [ ] Documentation reflects the changes where applicable

[gemini-code-assist[bot]]

Summary of Changes

Hello @alcholiclg, I'm Gemini Code Assist[^1]! 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 significantly expands the platform's capabilities by introducing a dedicated financial research application, fin_research, which can be deployed locally via Gradio. It enhances the underlying code execution infrastructure with a new local code executor, providing more flexible and isolated environments for Python and shell commands. Additionally, it refines existing search functionalities, improves agent prompt handling for better working directory awareness, and adds a configurable option for user feedback in research workflows, making the system more robust and user-friendly for specialized research tasks.

Highlights

• New Financial Research Application: Introduced a new fin_research application with full support for local deployment through Gradio, enabling multi-agent financial research workflows.
• Enhanced Local Code Execution: Added a LocalCodeExecutionTool that supports stateful execution in a Jupyter kernel environment (notebook_executor), stateless Python execution (python_executor), shell commands (shell_executor), and file operations, with environment-variable isolation for Jupyter sessions.
• Dynamic Code Executor Selection: The tool_manager now dynamically selects between the existing sandbox-based CodeExecutionTool and the new LocalCodeExecutionTool based on the implementation configuration.
• Search Engine Improvements: Updated the search engine to support thread-isolated environment variables for API keys and engine types, and fixed an ArXiv schema format issue caused by recent API changes.
• Configurable Follow-up Questions: Added a configurable option (use_feedback) in the deep research workflow to enable or disable the generation of follow-up questions.
• Agent Working Directory Awareness: Improved working-directory awareness for the Analyst and Collector agents by introducing a <DATA_ROOT> placeholder in their system prompts, which is dynamically replaced with the actual output directory.
• Tool Renaming for Clarity: Renamed reset_sandbox to reset_executor and get_sandbox_info to get_executor_info in the CodeExecutionTool for better clarity and consistency.
• Documentation Updates: Updated README documentation for both doc_research and fin_research projects, including new CLI command examples and instructions for launching the financial research app.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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 :thumbsup: and :thumbsdown: 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.

[^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.