gepa integration #359
Merged
gepa integration #359
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
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
xzrderek
commented
Dec 12, 2025
| """ | ||
| from eval_protocol.pytest.default_single_turn_rollout_process import SingleTurnRolloutProcessor | ||
| from eval_protocol.pytest.execution import execute_pytest | ||
| from eval_protocol.logging import default_logger |
Contributor
Author
There was a problem hiding this comment.
im getting a type error on this. also can we move this to top.
"default_logger" is unknown import symbolbasedpyrightreportAttributeAccessIssue
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Outdated suggestions cannot be applied.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.
Note
Adds EPParameters model and attaches it to @evaluation_test, introduces a DSPy-based GEPA trainer/utilities, updates OpenEnv vLLM integration to consume EPParameters, and includes tests plus dspy dependency.
GEPATrainerand helpers (gepa_utils.py,trainer.py,utils.py) to optimize/system-prompt via GEPA, convert EP datasets to DSPyExamples, and evaluate via EP.@evaluation_testnow attaches fullEPParametersmetadata (__ep_params__) built from invocation args/env; wrapper stores it on the callable.EPParametersPydantic model encapsulating eval/config fields (completion, datasets, loaders, rollout processor, concurrency, etc.).__ep_params__asEPParametersvia attribute access (rollout processor, kwargs,mcp_config_path).dspyto project dependencies.EPParametersdefaults/type flexibility andbuild_ep_parameters_from_testutility.Written by Cursor Bugbot for commit 7b3c420. This will update automatically on new commits. Configure here.