feat(core): Docker workspace execution environments#971
Merged
Conversation
Implements Docker-based workspace type for coding benchmarks (SWE-bench). Agent runs on host, grader runs inside container. Closes #965 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Deploying agentv with
|
| Latest commit: |
22888f2
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://3a8c15b4.agentv.pages.dev |
| Branch Preview URL: | https://feat-965-docker-workspace.agentv.pages.dev |
Add support for running code-grader evaluations inside Docker containers,
enabling benchmarks like SWE-bench to run in isolated container environments.
New YAML schema:
workspace:
docker:
image: <docker-image>
timeout: 1800 # seconds
memory: 4g # optional
cpus: 2 # optional
Changes:
- Add DockerWorkspaceConfig type and Zod schema
- Create DockerWorkspaceProvider with full container lifecycle management
(pull, create, start, cp, exec, rm) using execFile for security
- Update CodeEvaluator to run graders inside Docker when configured
- Thread dockerConfig through orchestrator evaluation pipeline
- Pull Docker image once during eval setup phase
- Add comprehensive unit tests with mock executor (28 test cases)
- Add docker-workspace example with EVAL.yaml
- Regenerate eval-schema.json
The provider uses a CommandExecutor interface for testability and always
cleans up containers in finally blocks, even on errors.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This was referenced Apr 8, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Implements Docker-based workspace type for coding benchmarks (SWE-bench).
Design: Agent runs on host, grader runs inside container.
workspace.docker.imagefield in EVAL.yaml schemacode-graderevaluatorCloses #965
Acceptance Signals
bun run testpasses with new Docker workspace tests