Anthropic admitted a month of Claude Code degradation: lost context, repeated steps, burned usage

Anthropic acknowledged that from March 4 to April 20, 2026, three overlapping degradation modes were running in production affecting Claude Code, the Claude Agent SDK, and Claude Cowork. During this window Claude Code stopped reliably holding context across longer sessions, repeated steps it had already done, picked tools inconsistently, and burned through usage limits faster than expected. Unlike a single dramatic deletion, this is a systemic reliability incident: a roughly six-week stretch where an entire agentic product line silently degraded, costing users time and quota before the vendor diagnosed and disclosed it. It underscores that agent reliability is not only about catastrophic single actions but also about sustained, hard-to-notice quality regressions.

Claude-code was responsible for this other incident, documented as STUPID-2026-0045 in the StupidLLM AI agent incident database.

It is rated 2.2/10 (low) on StupidLLM's CVSS-style severity scale for AI agent failures, based on damage type, reversibility, and scope.

The root cause was classified as context overflow. Hold context across a session, pick tools consistently, and make steady progress within usage limits.

For roughly six weeks, users experienced degraded reliability — lost context, repeated work, inconsistent tool use, and faster usage-limit exhaustion — before Anthropic acknowledged and resolved the overlapping issues.