CliAgentEnv: teardown sandboxes via bulk delete

[rasdani]

Description

adds teardown method and sandbox bulk deletion to CliAgentEnv

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

Ensures sandboxes are reliably cleaned up after runs and during teardown.

• Track created sandbox IDs via self.active_sandboxes in verifiers/envs/experimental/cli_agent_env.py
• New @vf.teardown teardown_sandboxes uses synchronous SandboxClient(APIClient()) to bulk_delete remaining sandboxes in batches of 100 (avoids event loop shutdown issues)
• Add sandbox ID to the active set on creation and discard on per-rollout delete in destroy_sandbox
• Minor imports added: SandboxClient, APIClient

^{Written by Cursor Bugbot for commit d10a4d1. 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.}