Refactor video gen

[tastelikefeet]

Change Summary

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]

Summary of Changes

Hello @tastelikefeet, 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 undertakes a substantial refactoring of the video generation system, transitioning from a monolithic structure to a highly modular, agent-based architecture. This change introduces specialized components for each stage of video production, from script generation and asset creation (audio, images, animations) to code analysis, rendering, and final composition. The goal is to enhance the system's robustness, scalability, and the quality of the generated video content, while also integrating a secure shell execution tool.

Highlights

• Modular Refactoring of Video Generation: The core video generation logic, previously centralized in workflow.py, has been extensively refactored into numerous specialized Python files, each representing a distinct step or component of the video creation pipeline. This significantly improves modularity and maintainability.
• Introduction of New Agents and Tools: Several new agents have been introduced, including GenerateScript, Segment, GenerateAudio, GenerateIllustrationPrompts, GenerateImages, GeneratePrompt, AnalyzeCode, Render, CreateBackground, ComposeVideo, and Animate. A new Shell tool with comprehensive safety checks for command execution has also been added.
• Enhanced Shell Command Safety: The new Shell tool includes robust safety mechanisms to prevent dangerous operations, path traversal, malicious redirections, and critical environment variable modifications, ensuring secure execution of shell commands within the system.
• Updated Configuration for LLM and Workflow: YAML configuration files (step1_script_agent.yaml, step2_assets_agent.yaml) have been updated to reflect the new modular structure, including changes to LLM models (e.g., claude-sonnet-4-5-20250929) and a new voices.yaml file for Text-to-Speech configurations.
• Advanced Manim Code Analysis and Fixing: A new AnalyzeCode agent has been implemented to detect and suggest fixes for layout issues (e.g., boundary violations, overlaps, crowding, complexity, timing) in Manim animation code, aiming to improve the quality and visual appeal of generated animations.

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 👍 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 undertakes a significant refactoring of the video generation pipeline, breaking it down into more modular agents. This is a good direction for maintainability. However, the refactoring appears to be a work-in-progress and has introduced a number of issues across the new files, including undefined variables, missing imports, incorrect method signatures, and logical errors. Many of the new agent classes are incomplete. I've provided specific comments on the most critical issues that need to be addressed to make the new pipeline functional.

[gemini-code-assist]

Warning

Gemini encountered an error creating the review. You can try again by commenting /gemini review.

[wangxingjun778]

“复杂的信息文件” -> “复杂的文档”？