DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to check that a Python bug fix really fixes the bug with No Human

Require the offered tests to fail on the old code and pass on the new tree.

Who it is forA Python maintainer reviewing an AI-written bug fix who wants evidence that the test would have caught the bug.

The problemA fix can look right while the test offered as proof passes on the old code too, so the bug was never actually reproduced.

The outcomeA bug-fix pull request is refused when its evidence test passes on the merge base, and accepted only when the reproduction gate shows the expected pass and fail.

What you need first

  • Python 3.12+
  • uv
  • git
  • Node with npm, for the board build from source
  • An Anthropic credential: an ANTHROPIC_API_KEY or a Claude subscription OAuth token from claude setup-token
  • A git repository you want changed, and a GitHub or GitLab issue URL or a configured tracker

Steps

  1. Run uv tool install no-human and then nh init && nh doctor.
  2. Run nh start to open the board and worker.
  3. Run nh task add <issue-url> --repo <local-repo-path> for the Python bug report. (inferred, check the README)
  4. Run nh review and check the reproduction gate result in the event log.
  5. Run nh reject --reason "..." if the evidence test passed on the old code. (inferred, check the README)

Prompt for your agent

In the no_human repo, add the Python bug issue <issue-url> for the repo at <local-repo-path> and run nh review. Report whether the reproduction gate passed, and state which test was offered as evidence.

Caveat. Out of the box the reproduction gate binds only Python bug fixes, and setting repro_gate.mode to required is needed to apply it to every kind of change.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page