Git paid app#146
Conversation
|
Important Review skippedAuto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Repository UI Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
simantak-dabhade
left a comment
There was a problem hiding this comment.
Hey @tanmaysainighy — nice work on the architecture here, the 3-tier agent system is a solid design and the SDK usage is correct. A couple of things to address before we can merge:
1. Split up index.html (1,057 lines)
The single-file frontend is too large for a cookbook example — people will reference this to understand how things work, and a 1,000+ line file is hard to navigate. You don't need to add React or any framework, but please split it into separate files:
static/
├── index.html ← markup only
├── styles.css ← all the CSS
└── app.js ← all the JavaScript
This makes the code scannable and easier to learn from.
2. Show live agent preview with streaming_url
Right now you only listen for CompleteEvent in agents.py and ignore the StreamingUrlEvent that the SDK sends back. This is a missed opportunity — the streaming_url gives you a live browser session URL that you can render as an iframe in the UI.
Imagine: user hits search, and as each agent starts working, they see a live preview of the browser navigating the site in real time. This would massively improve the UX and make the app way more impressive as a showcase.
Here's roughly what to do:
In agents.py — capture the streaming URL event and send it through the queue:
from tinyfish import StreamingUrlEvent
async for event in stream:
if isinstance(event, StreamingUrlEvent):
# Send the live URL to the frontend
await queue.put({"type": "streaming_url", "source_id": source_id, "url": event.streaming_url})
elif isinstance(event, CompleteEvent):
...In the frontend — when you receive a streaming_url event, render an iframe:
<iframe src="${event.url}" style="width:100%;height:400px;border-radius:8px;border:1px solid var(--border)"></iframe>This is one of TinyFish's best features — showing the agent at work live. Would love to see it in this app.
Let me know if you have questions on either of these!
No description provided.