poolprobe: A doctor for OpenAI-compatible model pools: probes…

A developer released poolprobe, an MIT-licensed, standard-library-only Python tool that probes every model in an OpenAI-compatible pool and classifies each failure as ALIVE, TRANSIENT, CREDENTIAL or PERMANENT. The tool refuses to prune any model deemed alive, requiring five independent guards to agree before issuing a death verdict. The author cautions that any such checker can produce false positives and should be used to surface candidates for review rather than to grade output.

Most poolprobe write-ups stop at the README: here is what the tool does, here is how you run it. This one covers what it refuses to do, and where it breaks. A doctor for OpenAI-compatible model pools: probes every model, classifies each failure ALIVE, TRANSIENT, CREDENTIAL, PERMANENT and refuses to prune anything alive — five independent guards must agree before a death verdict. Stdlib only. In Russian: Доктор для OpenAI-совместимых пулов моделей: прогоняет каждую модель, классифицирует отказ ALIVE, TRANSIENT, CREDENTIAL, PERMANENT и не даёт снести живое — смерть подтверждают пять независимых проверок. Только stdlib. pip install poolprobe stdlib engine, generic gateway lane Python. MIT licensed. Standard library first: the tool reads the data you point it at and sends nothing anywhere. Every rule in a checker like this can produce a false positive. Use it to find candidates for a rewrite, not to grade a writer, and not where the voice is the point. Source, issue tracker and documentation: https://gitlab.com/ameobius-ai/poolprobe https://gitlab.com/ameobius-ai/poolprobe Other tools from the same author: https://ameobius-ai.gitlab.io https://ameobius-ai.gitlab.io