add max_tokens arg to server method

[grossjct]

Closes #446

Changes proposed in this pull request:

• add a max_tokens argument to the server method (run_server.py) instead of using a fixed value

Before submitting

• I've read and followed all steps in the Making a pull request
  section of the CONTRIBUTING docs.
• I've updated or added any relevant docstrings following the syntax described in the
  Writing docstrings section of the CONTRIBUTING docs.
• If this PR fixes a bug, I've added a test that will fail without my fix.
• If this PR adds a new feature, I've added tests that sufficiently cover my new functionality.

[Copilot]

Pull request overview

This PR addresses #446 by making the OpenAI-compatible server runner configurable for output length, replacing a hard-coded max_tokens value with a function argument.

Changes:

• Added a max_tokens parameter to run_server(...) with a default of 8000.
• Wired the request payload to use the provided max_tokens value instead of a fixed constant.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[grossjct]

@jakep-allenai any comment on this?