Ryan H. Tran
Ryan H. Tran
Will be completed when #10502 is merged!
> Seems like there is pageX, pageY but also clientX, clientY https://michaelwornow.net/2024/01/02/display-x-y-coords-chrome-debugger From the blog seems like clientX/clientY is relative to viewport, and pageX/pageY is relative to the whole webpage....
Yeah, this idea is cool! I'm thinking about how can we facilitate meaningful and effective collaboration between the head agent and sub-agent. Specifically, for an `OmniscientAgent` that has complete knowledge...
Thank you for the details, that's a good use case. We can try implementing such an agent and see how it performs!
Hi @amirshawn, do you mean you're using OpenHands v0.17.0 instead of 0.1.7? I've made a fix for it in [this PR](https://github.com/All-Hands-AI/OpenHands/pull/5808), which goes into release 0.18.0, can you upgrade and...
I think we may want to first try to use `computer use` as another approach to implement browsing capability -- currently it's based on text-based observation only. If it helps...
I looked into OpenRouter pricing and seems like it's $4.8 / 1k images for Sonnet-3.5 🤔
This one: https://openrouter.ai/anthropic/claude-3.5-sonnet
Reference implementation: https://github.com/invariantlabs-ai/playwright-computer-use
> just fyi, the integration tests seem to fail because of some > > ``` > "action_suffix": "browse" > ``` > > in some results. Thanks, still waiting for reviews...