Changelog missing breaking changes
You ask an AI to generate the changelog for a library release by diffing the last two git tags. It produces a clean list grouped into Features / Fixes / Chores. Before you publish it to npm and your docs site, how do you confirm the changelog is complete — especially that no breaking changes were quietly omitted or mislabeled?
Implement
classify_release_bump(old_api: list[str], new_api: list[str]) → strExamples
in
[["createClient(url,options)","query(sql,params)","close()"],["createClient(url,options)","query(sql,params,timeout)","close()"]]out"major"in
[["query(sql,params)"],["query(sql,params)","stream(sql,params)"]]out"minor"in
[["query(sql,params)"],["query(sql,params)"]]out"patch"What a strong answer looks like
Treat the AI’s output as a draft to verify, not an answer to trust. Name the specific flaw and the input that triggers it, say how you’d catch it (tests, edge cases, reading critically), and how you’d re-prompt or decompose to get it right.
0:00 of about 15 min
Vibe & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.
Which questions mattered is sealed until you submit. Telling you now would just be handing over the edge cases.
Run or narrate your approach, then ask the coach.