[bugfix] harden llm infer streaming and runtime parsing

[mshicom]

Summary

• add an API key field to the llm infer page and reuse the selected deployment credentials for chat requests
• make running task parsing and runtime log handling tolerate non-standard task labels
• surface streaming HTTP errors correctly and preserve iterator exceptions in the infer client path
• render reasoning-only streaming chunks in the UI without crashing on delta.content = None

Verification

• reproduced the web UI crashes locally before the change
• verified the updated code paths with local py_compile and targeted request checks against the deployed service

[gemini-code-assist]

Summary of Changes

Hello, 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 significantly enhances the robustness and user experience of the LLM inference system. It addresses several stability issues related to streaming responses, improves the reliability of task management and log parsing, and integrates an API key field into the UI for more flexible deployment credential management. These changes collectively lead to a more resilient and user-friendly application.

Highlights

• API Key Integration: An API key field has been added to the LLM inference UI, allowing the reuse of selected deployment credentials for chat requests.
• Robust Task Parsing: The system for parsing running tasks and handling runtime logs has been made more tolerant of non-standard task labels.
• Improved Streaming Error Handling: The LLM inference client now correctly surfaces streaming HTTP errors and preserves iterator exceptions.
• UI Stability for Streaming: The UI can now render reasoning-only streaming chunks without crashing when delta.content is None.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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.

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 significantly enhances the robustness and functionality of the inference engine and its user interface. Key improvements include more resilient stream data parsing and comprehensive error handling for streaming API responses in infer_client.py. The infer_engine.py file refines exception handling to ensure proper resource cleanup and timely exception raising. The UI (llm_infer.py) now supports an API key input, validates the presence of a port before inference, and introduces advanced logic for parsing and displaying structured chat responses with reasoning content. Furthermore, runtime.py features a major refactor of command-line argument parsing using shlex and more robust task killing logic, improving overall system stability. I have no feedback to provide.