Skip to content
TopicTracker
From HackerNewsView original
TranslationTranslation

Beware, Claude Code deletes >30 day old transcripts. Anthropic won't fix it

A GitHub issue reports that Claude Code automatically deletes transcripts older than 30 days, and Anthropic has indicated it will not fix this behavior, causing concern among users who rely on longer-term transcript retention.

Background

- Claude Code is Anthropic's command-line coding agent — a tool that lets developers write code by giving AI instructions directly in the terminal. - This issue reports that Claude Code automatically deletes conversation transcripts (chat logs) that are more than 30 days old, with no way to disable this behavior. - Anthropic has indicated it will not fix or change this deletion policy, which has alarmed developers who rely on transcripts for debugging, documentation, or legal/compliance reasons. - The issue raises broader concerns about AI coding tool vendors unilaterally deleting user data without offering opt-out or local-first storage options.

Related stories

  • Newer Claude models sometimes invent extra keys in tool call arguments, breaking validation in Pi's edit tool. The author suspects post-training for Claude Code's forgiving harness makes alternative schemas fail. This suggests closed RL training can degrade general tool-use reliability.

  • Simon Willison released llm-coding-agent 0.1a0, an experimental coding agent built on his LLM library. The agent provides tools for reading, editing, searching files and executing commands, and ships with a Python API and CLI. It was developed using Claude Code (Fable 5) via TDD with a spec-first approach, and is available as a slop-alpha on PyPI.

  • Truth Social remains an outlet primarily for Trump's own posts, while other administration officials continue using X. The platform functions as a blog-like channel for Trump's messages rather than a genuine social network competitor.