OpenHands / OpenHands/benchmarks

Track strict offline isolation for ProgramBench inference

Open
#706 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
124
Forks
90
Avg merge
1d 6h
Merged PRs (30d)
1

Description

ProgramBench leaderboard-faithful inference requires agents to run without internet access. The initial integration currently uses Docker's default bridge network so the SDK control channel can reach the agent-server; strict isolation will require in-container egress filtering or an equivalent design that preserves the control channel.

Follow-up scope:

  • Implement strict egress blocking for ProgramBench Docker workspaces while preserving the SDK control path.
  • Evaluate an init-step approach using CAP_NET_ADMIN + iptables or an equivalent network namespace strategy.
  • Update documentation and metadata once --allow-network can distinguish real strict-offline runs.

This issue was created by an AI agent (OpenHands) on behalf of the user while addressing PR review feedback.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing the ProgramBench Docker workspace integration and how the SDK control channel reaches the agent-server. Evaluate the mentioned init-step approach with CAP_NET_ADMIN and iptables, or an equivalent network namespace strategy, then verify that --allow-network distinguishes strict-offline runs and update the related documentation and metadata.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker, python
Domain
devops, security, testing-qa
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.