Feature:Add End Flag in run_sse API Response to Indicate LLM Model Completion #2919
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @stonyme, 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 enhances the run_sse API by adding an explicit completion signal, {"done": true}, to the stream. This change aims to simplify frontend development by providing a reliable method to detect the end of an LLM's response, improving the handling of streaming data.
Highlights
- LLM Response Completion Signal: Introduces a {"done": true} Server-Sent Event (SSE) message at the end of the run_sse API response stream.
- Frontend Development Facilitation: This new flag provides a clear, programmatic indicator for frontend applications to determine when an LLM's response is complete, removing reliance on SSE connection termination.
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
-
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. ↩
adk-bot
added
bot triaged
|
Response from ADK Triaging Agent Hello @stonyme, thank you for creating this PR! To help us review your contribution, could you please:
This information will help reviewers to review your PR more efficiently. Thanks! |
There was a problem hiding this comment.
Code Review
This pull request introduces a {"done": true} message at the end of the SSE stream in run_sse API responses, which is a helpful addition for frontend clients to detect the end of the stream. The implementation in adk_web_server.py is straightforward.
The PR also includes unrelated changes in fast_api.py to allow injecting a memory_service instance, which is a good refactoring for testability and flexibility.
I have a couple of suggestions to improve code readability and maintainability in both files. Please see the detailed comments.
#2920 I add it on issue |
When the LLM finishes its response, add a {"done": true} identifier to the corresponding interface to facilitate frontend development judgment. Without this identifier, the frontend can only rely on the disconnection of the SSE interface as a judgment basis.