feat(harbor): add Kernel browser control arm - #330
Merged
Perry2004 merged 6 commits intoSep 8, 2026
Conversation
Perry2004
self-requested a review
September 8, 2026 05:09
Perry2004
requested changes
Sep 8, 2026
| echo "$!" > /tmp/clawbench-run/runtime-server.pid | ||
| sleep 1 | ||
|
|
||
| if [ "$REMOTE_MODE" = true ]; then |
Collaborator
There was a problem hiding this comment.
This should be moved to before runtime-server start since the server starts the ffmpeg in local mode, which depends on x11y display.
| "- Do not launch a separate browser. Complete the task through the existing browser session.\n" | ||
| "---\n" | ||
| ) | ||
| if browser_runtime == "local": |
Collaborator
There was a problem hiding this comment.
Please do not change the prompt to the agent. These additional info will have potential impact on agent performance.
Contributor
Author
|
thanks for the review @Perry2004! Just addressed your comments |
Perry2004
approved these changes
Sep 8, 2026
Perry2004
left a comment
Perry2004
left a comment
Collaborator
There was a problem hiding this comment.
LGTM🫡
Thanks for the contribution.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Extend
clawbench-harbor-adaptwith a Kernel-backed browser runtime so Harbor agents can run ClawBench tasks against one managed remote browser per trial.--browser-runtime kernelwith validated runtime optionsWhy
The native ClawBench runner supports Kernel browsers after #311, while the Harbor adapter currently supports only container-local Chromium. This adds the corresponding Harbor control arm so the same task corpus can be compared across local and managed browser runtimes without changing task semantics or scoring.
The implementation is rebased on the Harbor correctness changes merged in #324. This PR contains only the remaining remote-browser Harbor integration.
Design
Each generated Kernel task:
/my-info/recording.mp4, deletes the browser, and verifies deletionThe existing local Chromium path remains the default and does not require Kernel credentials.
Validation
uv run pytest -q— 232 passeduv run ruff check src/clawbench testsuv run ruff format --check src/clawbench testsuv run --frozen pyright src/clawbench tests— 0 errors