Agents In Use
What’s new todayLast update
108 use cases added today

Watch Codex repair a Datasette plugin compatibility failure

Transcript reviewed · recording and outcomes not independently reproduced

@swillisonSource published Added to Agents In Use Open on YouTube ↗

What the transcript explains

Simon Willison upgrades datasette-checkbox after a permissions API change. He first reproduces a real page failure that the existing tests miss, adds a failing page test and gives Codex the runner plus upgrade guide. After the agent changes the permission call, Willison checks the interactive feature and adds separate assertions for root and non-root users.

Limits and human checks

  • Human work establishes the reproduction, improves coverage and releases the package; this is not an unattended upgrade.
  • The review covers the recorded transcript, not a fresh installation or security audit of the plugin.

Our notes are based on the caption transcript, reviewed 2026-10-15. Caption errors and differences from what appears on screen remain possible.

OUR ADAPTATION

Suggested prompt

Suggested prompt written by Agents In Use, not the source author. Replace bracketed inputs and review tool permissions first.

Run [test command] against [new version] in a sandbox. Confirm the test catches the real compatibility failure. Read [upgrade guide], make the smallest fix and rerun the suite. Report changed behavior and test results; stop before release.

Steps from the account

  1. Run the plugin with the newer Datasette version and reproduce the page error.
  2. Strengthen the test so it catches the missing permission method.
  3. Have Codex read the upgrade notes, apply the compatibility fix and rerun tests.

Evidence at a glance

Transcript reviewed
Source author
@swillison
Original account
Read the source ↗
Published
Source link checked
Transcript reviewed
. Recording not visually reviewed; results not independently reproduced.
Reported result
Willison documents the plugin upgrade and the verification process in a recorded walkthrough.
Human involvement
Willison exposed the real failure and improved the test before delegation. His bypass-approval command is not recommended by this entry.
Report an issue with this caseOpen correction email

Opens your email app with the case link included. Nothing is sent automatically.

About this source

Companion article fetched; YouTube oEmbed confirms the recording and author. Exact duration not verified, so omitted.

More cases using Codex