Armin Ronacher Flags an 'Aggravating' Tool-Calling Regression in Newer Claude Models

Armin Ronacher (lucumr.pocoo.org)·medium signal

On July 4 the Flask creator documented a concrete, reproducible tool-calling regression in newer Claude models — the kind of primary-source bug report that saves other builders days of confusion. Coming from someone whose 'The Coming Loop' essay defined the agent-loop-vs-harness-loop framing, it's a reminder that model updates can silently degrade the exact tool-use behavior agent harnesses depend on. Actionable now for anyone running Claude in production loops: pin behavior, add tool-call regression tests, and watch for silent version drift.