feat(benchmark): add OpenMontage context benchmark MVP

[yeyitech]

Summary

• add a repo-local OpenMontage benchmark fixture and stage-scoped evaluation set
• add import/eval/scorer scripts for a deterministic context-handoff benchmark MVP
• add a smoke test and track benchmark fixture assets in git

Testing

• python -m pytest -q benchmark/openmontage/test_smoke.py

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.

---

Codex seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[github-actions]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 2 🔵🔵⚪⚪⚪

🏅 Score: 92

🧪 PR contains tests

🔒 No security concerns identified

✅ No TODO sections

🔀 No multiple PR themes

⚡ No major issues detected

[github-actions]

PR Code Suggestions ✨

No code suggestions found for the PR.

[chenjw]

Thank you very much for your contribution. May I ask if you have any evaluation results available?