Add GAIA image build workflow #129
Merged
Conversation
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
This workflow builds a universal agent server image for GAIA benchmark evaluation.
Unlike SWE-bench which requires per-instance images with specific repository
environments, GAIA uses a single universal image for all instances since they
share the same Python+Node.js environment (nikolaik/python-nodejs:python3.12-nodejs22).
Workflow features:
- Minimal configuration: only requires sdk-commit and optional target parameter
- Builds one universal image tagged as: ghcr.io/openhands/eval-agent-server:{SDK_SHA}-gaia-binary-minimal
- Can be triggered via workflow_dispatch or by adding 'build-gaia' label to PRs
- Posts build status to issue #81 for tracking
Note: Workflow filename is singular (build-gaia-image.yml) to reflect that it
builds a single universal image, unlike SWE-bench which uses plural
(build-swe-bench-images.yml) for its many per-instance images.
This is a prerequisite for enabling GAIA benchmark evaluation on the
Kubernetes evaluation infrastructure.
simonrosenberg
force-pushed
the
add-gaia-build-workflow
branch
from
1749c49 to
7d8ec59
Compare
|
Looks like there are a few issues preventing this PR from being merged!
If you'd like me to help, just leave a comment, like Feel free to include any additional details that might help me get this PR into a better state. You can manage your notification settings |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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
This PR adds the GitHub Actions workflow for building GAIA benchmark agent server images.
Background
GAIA (General AI Assistants) benchmark evaluation requires agent server images, similar to SWE-bench. However, unlike SWE-bench which builds per-instance images (one per repository), GAIA uses a single universal image for all instances.
What's Included
Workflow Features
sdk-commitand optionaltargetparameternikolaik/python-nodejs:python3.12-nodejs22ghcr.io/openhands/eval-agent-server:{SDK_SHA}-gaia-binary-minimalTriggering
Can be triggered in two ways:
build-gaialabel to any PRNext Steps
Once this is merged to main:
Related
Note
This PR intentionally only includes the workflow file to enable quick merging. The actual GAIA evaluation implementation code is in PR #125.