optional opt-out of env server in evals

[mikasenghaas]

Description

Allows skipping env server startup/shutdown during evaluation, useful for debugging (e.g. attack debugger to env execution)

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Test improvement

Testing

• All existing tests pass when running uv run pytest locally.
• New tests have been added to cover the changes

Checklist

• My code follows the style guidelines of this project as outlined in AGENTS.md
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published

Additional Notes

---

Note

Low Risk
Small, gated control-flow change around env server lifecycle; default behavior remains unchanged and impacts only evaluation execution.

Overview
Adds an opt-out flag to evaluation runs (--disable-env-server / disable_env_server) that prevents environment server startup and shutdown.

Threads this new config field through CLI/TOML config parsing (eval.py), EvalConfig (types.py), and the evaluation runner (eval_utils.run_evaluation) so evals can run against an already-managed environment process (e.g., for debugging).

^{Written by Cursor Bugbot for commit b32220b. This will update automatically on new commits. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{Bugbot Autofix is OFF. To automatically fix reported issues with Cloud Agents, enable Autofix in the Cursor dashboard.}