Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Add weekly SDK evals workflow#1828

Draft
khandrew1 wants to merge 1 commit into
canaryfrom
codex/add-weekly-sdk-evals
Draft

Add weekly SDK evals workflow#1828
khandrew1 wants to merge 1 commit into
canaryfrom
codex/add-weekly-sdk-evals

Conversation

@khandrew1

Copy link
Copy Markdown
Contributor

Summary

Adds a weekly/manual GitHub Actions workflow for running the private mcp-use-evals SDK readiness suite from this repo.

The workflow:

  • checks out mcp-use and private mcp-use-evals
  • uses EVALS_REPO_TOKEN to read the private eval repo
  • points MCP_USE_SKILL_DIR at skills/mcp-apps-builder
  • runs the eval harness in the Docker sandbox backend
  • uploads results/ and appends the generated report to the job summary

Notes

This expects mcp-use-evals@main to include the Docker sandbox backend, which is now on mcp-use-evals main.

Validation

  • Parsed .github/workflows/weekly-sdk-evals.yml with Ruby YAML loader
  • Docker sandbox backend was smoke-tested in mcp-use-evals

@khandrew1 khandrew1 changed the title [codex] Add weekly SDK evals workflow Add weekly SDK evals workflow Jun 30, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant