feat(sdk): add baseten-hosted models to evals workflow#1682
Merged
Eugene Yurtsev (eyurtsev) merged 2 commits intomainfrom Mar 6, 2026
Merged
feat(sdk): add baseten-hosted models to evals workflow#1682Eugene Yurtsev (eyurtsev) merged 2 commits intomainfrom
Eugene Yurtsev (eyurtsev) merged 2 commits intomainfrom
Conversation
github-actions
bot
added
github_actions
# Conflicts: # .github/scripts/get_eval_models.py # .github/workflows/evals.yml
Contributor
There was a problem hiding this comment.
Pull request overview
Adds Baseten-hosted models as additional eval targets by routing baseten: model specs through Baseten’s OpenAI-compatible endpoint in the eval harness, and wiring the required secret + model entries into the GitHub Actions eval workflow.
Changes:
- Add a
baseten:model prefix handler in the evalmodelfixture that instantiatesChatOpenAIwithbase_url=https://inference.baseten.co/v1. - Extend the evals GitHub Actions workflow matrix/options and environment to include Baseten models and
BASETEN_API_KEY. - Update the model-matrix generator script to include the Baseten models in both
MODELSandSET1.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
libs/deepagents/tests/evals/conftest.py |
Adds Baseten-specific model initialization via ChatOpenAI using Baseten’s OpenAI-compatible base_url. |
.github/workflows/evals.yml |
Adds Baseten models to workflow input options/matrix and injects BASETEN_API_KEY into the eval job environment. |
.github/scripts/get_eval_models.py |
Registers Baseten models in the “all” and “set1” model selections used to build the workflow matrix. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
You can also share your feedback on Copilot code review. Take the survey.
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
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.
Adds GLM-5 (zai-org/GLM-5) and MiniMax-M2.5 (MiniMaxAI/MiniMax-M2.5) via Baseten's OpenAI-compatible inference endpoint as eval targets, mirroring the existing Ollama Cloud entries for these models. Uses ChatOpenAI with
base_url=https://inference.baseten.co/v1following the same pattern as the NVIDIA special case in conftest.py. Requires aBASETEN_API_KEYrepo secret.Created with Deep Agents CLI.