Character direct control API #295

[hgenru]

This PR adds a character direct control API. This code was written using codex, but I reviewed it and tested it as best I could.

UPD: I tested all of this in production and discovered several issues:

1. The system prompt update handle sometimes glitches and completely overwrites the system prompt.
2. The respond handle does not have access to the camera, etc.

I am not fixing this PR yet. Please let me know if you are interested, and I will fix these issues.

[gemini-code-assist[bot]]

Summary of Changes

Hello @hgenru, 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 enhances the character interaction capabilities by introducing a direct control API. This allows for programmatic manipulation of the character's output and behavior, such as making the character speak specific text, modifying its system prompt, or forcing an LLM response. The changes are complemented by a new section in the web tool, offering a convenient interface to manage these new control features for active chat sessions.

Highlights

• New Direct Control API: Introduced a new set of REST API endpoints for direct control over character interactions, including speaking text, applying system instructions, and triggering LLM responses.
• Web Tool Integration: The existing web tool has been updated with a new 'Direct Control' panel, providing a user interface to interact with the new API endpoints for testing and management.
• Shared WebSocket Handler: A shared WebSocketHandler instance is now used across routes, and it tracks the last active client UID to facilitate targeting actions to the most recently active session.
• TTS Functionality: A new speak_text function handles the text-to-speech process, including emotion extraction for Live2D models and sending conversation signals.

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.

[hslater95]

have you tested this yourself? I ran your pr and there is no "Direct Control" section on the client-side like the documentation suggests