Summary
Anthropic published a detailed postmortem saying recent Claude Code quality complaints came from three separate changes: lower default reasoning effort on March 4, a March 26 idle-session bug that repeatedly cleared older thinking, and an April 16 verbosity prompt change that hurt coding quality. Anthropic said all three issues were resolved by April 20 and that it is resetting subscriber usage limits.
What changed
Anthropic publicly traced Claude Code quality regressions to three product changes and said it reverted or fixed them by April 20 in v2.1.116.
Why it matters
The signal here is not just the fixes. Anthropic is treating coding-agent quality drift as an operational issue worth explaining with dated root causes, reversions, and customer remediation, which is still unusual transparency for a frontier AI product.
Evidence excerpt
Anthropic says the three issues were resolved as of April 20, that the API was unaffected, and that it is resetting usage limits for all subscribers.