Add 4 new mock eval sites + full-eval observation report#55
Closed
softpudding wants to merge 5 commits intomainfrom
Closed
Add 4 new mock eval sites + full-eval observation report#55softpudding wants to merge 5 commits intomainfrom
softpudding wants to merge 5 commits intomainfrom
Conversation
Adds four new browser-agent eval sites targeting interaction primitives not yet covered by the existing suite: panel-state navigation and icon-only transport buttons (MapQuest); dual-handle price slider drag, segmented search popovers, and two-step booking checkout (StayBnB); HTML5 drag-and-drop with hover-reveal inline editing (TaskFlow); auto-hide player controls, thin-bar timeline scrub, nested settings popup, and hover-reveal volume slider (VidHub). Each site ships with 2 test-case YAMLs under eval/dataset/ scored against tracker events, for 8 new tests total. eval/README.md documents each site with main challenges. eval/AGENTS.md captures non-obvious implementation gotchas learned during the build (stacking context with header popovers, default-state event anti-pattern, tracker case normalization, dual-handle drag, deep-link entry points). eval/SPEC_NEW_SITES.md is the design brief the sites were generated from. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Captures findings from a 105-run benchmark pass across qwen3.5-flash, qwen3.5-plus, and qwen3.6-plus on the full 35-test dataset. Documents seven recurring OpenBrowser agent issues (missing drag primitive, stale DOM disorientation, terminal error interpretation, feedback-loop blindness, instruction-precision drift, missing completion signal, 8765 HTTP channel fragility) with per-test evidence and proposed fixes. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Brings in the 6 hard mock eval sites and supporting infrastructure from the codex/mock-eval-sites branch (Amazon, Booking, Drive, GitHub, Gmail, plus 12 test YAMLs and tracker/server plumbing) so the full eval PR includes both rounds of codex-authored mock sites alongside the follow-up 4 sites (MapQuest, StayBnB, TaskFlow, VidHub). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> # Conflicts: # eval/server.py
Owner
Author
|
Closing — re-opening from /Users/yangxiao/git/OpenBrowser on a proper branch that matches the exact state the eval was run against. |
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
eval/AGENTS.mdwith non-obvious implementation gotchas (stacking contexts, default-state event anti-pattern, tracker case normalization).Test plan
🤖 Generated with Claude Code