---
id: "2026-04-23-claude-code-quality-postmortem"
url: "https://postcutoff.com/e/2026-04-23-claude-code-quality-postmortem/"
as_of: "2026-10-10T23:43:00+02:00"
date: "2026-04-23"
date_precision: day
category: product
importance: 3
confidence: high
status: [Confirmed]
sources: 1
editor: Adam Bicz
human_review: null
version: null
---

As of: 2026-10-10 23:43 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code). Human editor: Adam Bicz.
Canonical page: https://postcutoff.com/e/2026-04-23-claude-code-quality-postmortem/

# Three changes degraded Claude Code quality in March–April 2026

Full title: Anthropic postmortem: three changes degraded Claude Code quality in March–April 2026; usage limits reset

After weeks of user complaints that Claude Code had got worse, Anthropic published a postmortem (Apr 23, 2026) naming three causes: a default reasoning-effort cut from high to medium, a caching bug that wiped thinking history every turn, and a verbosity instruction that hurt coding. All were fixed by Apr 20; subscribers' usage limits were reset.

## Key facts
- Issue 1 (Mar 4 – Apr 7): default reasoning effort lowered from high to medium for Sonnet 4.6 and Opus 4.6 to cut latency; reverted
- Issue 2 (Mar 26 – Apr 10, fixed in v2.1.101): thinking-cache bug cleared reasoning history on every turn, making Claude 'seem forgetful and repetitive'
- Issue 3 (Apr 16 – Apr 20, fixed in v2.1.116): system-prompt word-limit instruction hurt coding quality (Sonnet 4.6, Opus 4.6, Opus 4.7)
- API and inference layer unaffected: 'We never intentionally degrade our models'
- Usage limits reset for all subscribers on Apr 23; promised per-model evals, ablations, gradual rollouts and soak periods for prompt changes

## What happened

Anthropic wrote: "The implementation had a bug. Instead of clearing thinking history once, it cleared it on every turn for the rest
of the session." Together with the effort change and the prompt change, this explained much of the reported degradation.

## Why it matters

It confirmed that "the model got dumber" complaints can come from harness, prompt and default changes rather than the weights,
and set a precedent for public postmortems on agent product quality.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 3.8 Flash (training cutoff March 2026): 23 days after its cutoff
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Anthropic Engineering: An update on recent Claude Code quality reports](https://www.anthropic.com/engineering/april-23-postmortem) (anthropic.com, official)

## Changes

- 2026-10-10 (filed): Created

## Related

- 2026-04-16: [Anthropic releases Claude Opus 4.7, admits it trails the unreleased Mythos Preview](https://postcutoff.com/e/2026-04-16-claude-opus-4-7/index.md)
- 2026-02-05: [Anthropic releases Claude Opus 4.6 with 1M context, adaptive thinking and agent teams](https://postcutoff.com/e/2026-02-05-claude-opus-4-6/index.md)