fix(agent-tars): skip browser_vision_control screenshot on empty pages#1835
Open
Br1an67 wants to merge 1 commit intobytedance:mainfrom
Open
fix(agent-tars): skip browser_vision_control screenshot on empty pages#1835Br1an67 wants to merge 1 commit intobytedance:mainfrom
Br1an67 wants to merge 1 commit intobytedance:mainfrom
Conversation
When the browser page is about:blank (no URL loaded), the agent would take a screenshot and send it to the LLM, which then uselessly invoked browser_vision_control on the empty page. Now detects about:blank and sends a text-only environment input instead, instructing the agent to navigate to a URL first before attempting visual browser control. Fixes bytedance#902
✅ Deploy Preview for agent-tars-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
✅ Deploy Preview for tarko ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
14 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fixes #902
When the browser page is
about:blank(no URL loaded), the agent would take a screenshot and send it to the LLM, which then uselessly invokedbrowser_vision_controlon the empty page. This wasted resources and confused users.Changes:
onEachAgentLoopStart(), detect when the current URL isabout:blankor emptyenvironment_inputevent instructing the agent to navigate to a URL first before attempting visual browser controlChecklist