increase default consecutive failure to 5#4080
Merged
Merged
Conversation
Agent Task Evaluation Results: 2/2 (100%)View detailed results
Check the evaluate-tasks job for detailed task execution logs. |
Contributor
There was a problem hiding this comment.
2 issues found across 2 files (changes from recent commits).
Prompt for AI agents (all issues)
Check if these issues are valid — if so, understand the root cause of each and fix them.
<file name="browser_use/agent/service.py">
<violation number="1" location="browser_use/agent/service.py:170">
P2: Default max_failures is set to 7, which conflicts with the PR’s stated goal of increasing the threshold to 5. If the intent is 5, this change will silently allow more consecutive failures than planned.</violation>
</file>
<file name="browser_use/agent/views.py">
<violation number="1" location="browser_use/agent/views.py:65">
P2: Default max_failures is set to 7, which conflicts with the PR’s stated intent to raise the default to 5. If the intent is truly 5, this will overshoot the expected retry threshold.</violation>
</file>
Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.
Contributor
There was a problem hiding this comment.
1 issue found across 1 file (changes from recent commits).
Prompt for AI agents (all issues)
Check if these issues are valid — if so, understand the root cause of each and fix them.
<file name="browser_use/agent/service.py">
<violation number="1" location="browser_use/agent/service.py:1188">
P2: Multi-action steps with errors no longer increment consecutive_failures, so repeated failures in multi-action steps can bypass the failure threshold entirely. If the intent is to count any action error as a step failure, restore the previous check that counts any error in the step.</violation>
</file>
Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.
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 by cubic
Increase the default consecutive failure threshold from 3 to 5 and restore the original guard so only single-action step errors increment consecutive failures (multi-action steps are handled by loop detection). Improve browser-closed detection to trigger only on real CDP/WebSocket connection failures, reducing false positives.
Written for commit ae3b8be. Summary will update on new commits.