NVIDIA-NeMo / NVIDIA-NeMo/Gym

[checkpoint] Restore pinchbench sandbox runs

Open
#3,286 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

area:sandbox feature
Dominant language
Python
Stars
1.2k
Forks
349
Avg merge
1d 21h
Merged PRs (30d)
318

Description

Parent

Child of #3222 and #3024. Depends on #3275.

Runtime state

responses_api_agents/pinchbench/app.py owns sandbox filesystem, transcript/session tree, run/work directories, and result cursor.

Adapter requirements

Persist the logical execution-to-runtime mapping, provider/version and physical generation, sandbox snapshot/reference, image/spec and mount fingerprints, agent or verifier cursor, and result-manifest identity. Rebind a replacement runtime atomically and fence the old handle. Never claim that a filesystem-only copy restores unsupported live process state.

Acceptance criteria

  • Transcript and workspace restore under stable identity and the final result is neither lost nor emitted twice.
  • Mutate runtime state, commit, replace both application and runtime process where supported, restore, and compare the next operation/result.
  • Stale handles and delayed old-runtime results are rejected.
  • Partial restore activates no execution mapping.
  • Duplicate retirement and failed-provider cleanup release the restored runtime exactly once.

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

Read responses_api_agents/pinchbench/app.py first, then review the parent issues #3222 and #3024 and dependency #3275 for the runtime boundaries. The work is done when transcript and workspace identity, mappings, cursors, and result manifests survive supported replacement, while stale or partial restores are rejected and cleanup occurs exactly once.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.