# An update on recent Claude Code quality reports

Source: [Anthropic](https://www.anthropic.com/engineering/april-23-postmortem)  
Feed7 permalink: https://feed7.dev/p/april-23-postmortem-1ve86a2  
Published: Unknown  
Trust: Official Source (official_source)

## Why Included

Anthropic traces recent Claude Code degradation to three bugs — a reasoning-effort default, a thinking-cache bug, and a prompt change — all fixed in v2.1.116, with usage-limit resets as compensation.

## Source Summary

**The gist** Anthropic's postmortem identifies three separate bugs behind Claude Code quality complaints between **March 4 and April 20, 2026**: a default reasoning-effort drop from high to **medium**, a cache bug that stripped thinking blocks from sessions idle over an hour on every turn, and a prompt instruction capping responses at **100 words**. All are fixed as of **v2.1.116**.

## Practical Implication

**Why it matters** If Claude Code felt forgetful or burned usage limits faster this spring, it was these bugs, not the models — subscribers get **usage limit resets**. Anthropic now gates prompt changes behind **per-model evals** and staff dogfood the **exact public build**, so silent regressions should surface sooner.

## Agent-Ready Context

**The gist** Anthropic's postmortem identifies three separate bugs behind Claude Code quality complaints between **March 4 and April 20, 2026**: a default reasoning-effort drop from high to **medium**, a cache bug that stripped thinking blocks from sessions idle over an hour on every turn, and a prompt instruction capping responses at **100 words**. All are fixed as of **v2.1.116**.

**Why it matters** If Claude Code felt forgetful or burned usage limits faster this spring, it was these bugs, not the models — subscribers get **usage limit resets**. Anthropic now gates prompt changes behind **per-model evals** and staff dogfood the **exact public build**, so silent regressions should surface sooner.

**Watch out** Each bug lived in corner cases that survived code review, tests, and dogfooding — the thinking-cache bug was masked because the CLI **suppresses thinking display**. User reports were initially indistinguishable from **normal variation**, so expect future regressions to take time to confirm too.

## Context Map

- Layer: tools
- Domains: coding
- Topics: coding-agents, dev-ux, agent-reliability

## Uncertainty

- Each bug lived in corner cases that survived code review, tests, and dogfooding — the thinking-cache bug was masked because the CLI **suppresses thinking display**. User reports were initially indistinguishable from **normal variation**, so expect future regressions to take time to confirm too.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.