feat(console): implement /console/chat endpoint for streaming agent r…

[zhijianma]

…esponses

Description

[Describe what this PR does and why]

Related Issue: Fixes #(issue_number) or Relates to #(issue_number)

Security Considerations: [If applicable, e.g. channel auth, env/config handling]

Type of Change

• Bug fix
• New feature
• Breaking change
• Documentation
• Refactoring

Component(s) Affected

• Core / Backend (app, agents, config, providers, utils, local_models)
• Console (frontend web UI)
• Channels (DingTalk, Feishu, QQ, Discord, iMessage, etc.)
• Skills
• CLI
• Documentation (website)
• Tests
• CI/CD
• Scripts / Deploy

Checklist

• I ran pre-commit run --all-files locally and it passes
• If pre-commit auto-fixed files, I committed those changes and reran checks
• I ran tests locally (pytest or as relevant) and they pass
• Documentation updated (if needed)
• Ready for review

Testing

[How to test these changes]

Local Verification Evidence

pre-commit run --all-files
# paste summary result

pytest
# paste summary result

Additional Notes

[Optional: any other context]

[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 introduces a significant enhancement to the console's chat functionality by implementing a new streaming API endpoint. This change allows for real-time, interactive agent responses in the console, moving away from a traditional request-response model to a more dynamic streaming experience. The update involves both frontend adjustments to consume the new endpoint and backend modifications to handle the streaming logic and session management.

Highlights

• New Streaming Chat Endpoint: A new API endpoint, /console/chat, has been implemented to support streaming agent responses, enabling real-time chat interactions in the console.
• Frontend Integration: The console's chat page (console/src/pages/Chat/index.tsx) has been updated to utilize the new /console/chat endpoint for sending messages and receiving streaming responses.
• Backend Streaming Logic: The ConsoleChannel in the backend has been refactored to include a stream_one method, which processes agent events and yields them as Server-Sent Events (SSE) for the new streaming endpoint. A new resolve_session_id method was also added to manage chat sessions.

🧠 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.

Changelog

• console/src/pages/Chat/index.tsx
  • Updated the API endpoint for chat interactions from /agent/process to /console/chat.
• src/copaw/app/channels/console/channel.py
  • Updated the module docstring to reflect the new /console/chat endpoint.
  • Added json and AsyncGenerator imports.
  • Introduced a resolve_session_id method to determine session IDs based on provided metadata or default values.
  • Refactored the consume_one method into stream_one to process payloads and yield SSE-formatted events.
  • Modified stream_one to serialize event objects to JSON for streaming.
  • Re-implemented consume_one to act as a consumer for stream_one for non-streaming contexts.
• src/copaw/app/routers/console.py
  • Updated the module docstring to include 'chat' functionality.
  • Added necessary imports for streaming, including json, logging, AsyncGenerator, HTTPException, Request, StreamingResponse, and AgentRequest.
  • Implemented a new POST /console/chat endpoint.
  • The new endpoint handles incoming chat requests (either AgentRequest or dict format), extracts relevant data, and uses the ConsoleChannel's stream_one method to deliver responses as a StreamingResponse using Server-Sent Events.

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 Generative AI Prohibited Use Policy, 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 introduces a new /console/chat endpoint to enable streaming agent responses to the web UI. The changes are well-structured, involving a new streaming endpoint in FastAPI, refactoring the ConsoleChannel to support Server-Sent Events (SSE), and updating the frontend to use this new endpoint. The implementation is generally solid, but I've identified a potential issue in the new endpoint's logic concerning how the channel_id is handled, which could lead to inconsistent behavior. My review includes a specific suggestion to address this for improved robustness and clarity.

[xieyxclack]

LGTM