Anthropic: Claude Code Performance Issues Fixed and All Subscriber Usage Limits Reset

Odaily Planet Daily News According to official sources, the feedback regarding degraded Claude Code quality that Anthropic previously received stemmed from three independent changes involving Claude Code, Claude Agent SDK, and Claude Cowork. Specific issues included: On March 4, the default reasoning intensity was reduced from high to medium, leading to a decline in intelligence levels; this setting was restored on April 7. A cache optimization feature launched on March 26 contained a bug that incorrectly cleared old reasoning records, causing the model to exhibit forgetfulness and repetition; this was fixed on April 10. On April 16, system prompts added to reduce redundancy harmed programming quality and were rolled back on April 20. Currently, all affected models have returned to normal, and Anthropic has reset all subscribers' usage limits.