fix(server): fix and improve conversation title generation

[jezekra1]

Summary

Resolves #1703

Linked Issues

Documentation

• No Docs Needed:

If this PR adds new feature or changes existing. Make sure documentation is adjusted accordingly. If the docs is not needed, please explain why.

[gemini-code-assist]

Summary of Changes

Hello @jezekra1, 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 refines the conversation title generation process by introducing a mechanism to provide hints to the title generation model, making the generated titles more accurate and relevant. It also includes minor fixes for title validation and ensures that empty titles generated by the model are properly handled.

Highlights

• Enhanced Title Generation Prompt: The conversation title generation prompt now supports an optional titleHint and the full rawMessage object, allowing for more contextual and guided title creation.
• Improved Title Extraction Logic: The internal logic for extracting content for title generation has been updated to specifically look for and utilize a title_hint from DataPart message components.
• Robust Title Validation and Error Handling: The title update mechanism now only validates the title length if a title is actually provided, and a new check has been added to raise an error if the generated title from the LLM is empty.

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 improves conversation title generation by adding support for a titleHint, making the response handling from the LLM more robust, and adding error checking for empty titles. The changes are well-implemented. I have one suggestion to fix a minor bug in the title truncation logic to ensure it correctly enforces the maximum character limit.

[gemini-code-assist]

The current title truncation logic can result in a title longer than 100 characters. For example, if the original title is 101 characters long, it will be truncated to 100 characters and ... will be appended, resulting in a 103-character string. This may violate the 'max 100 characters' constraint mentioned in the prompt and potentially cause issues with database field length limits.

To fix this, you can adjust the truncation to account for the length of the ellipsis.

Suggested change

	title = f"{title[:100]}..." if len(title) > 100 else title
	title = (title[:97] + "...") if len(title) > 100 else title