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

The best mitigation I've found against this is training Claude to collate what it does within the project dir, specifically a CLAUDE.md vision file and .claude/changelog that documents the changes it makes. The biggest pain point though is remembering to force it to do that between sessions (man is that contextual memory unreliable sometimes).

[flagged]

That Claude can't retain and reference these in the future, SQLite could do this trivially, is wild.

idk if it's broken.

I think it's more like, "We don't want our harness to need to be able to interpret every version of our conversation format indefinitely."

Isn’t “Anthropic won’t fix it” a little sensational for barely month old issue with little activity(two upvotes, one of which is me), in backlog of 5k+? Agree that it’s a real issue that need fixing however

So it's a config setting you can change? What would you expect them to fix, that sounds like a feature?

It's on your computer you can literally just make a crontab to copy them somewhere else.

Wow good timing, I’ve been working on a session hub of sorts for devs. Check it out, you can store your sessions on here. https://joe-store-frontend.onrender.com

"Why this is more than an inconvenience. For paying users who treat their sessions as intellectual property — design reasoning, prompt history, hard-won context — this is silent, unconsented destruction of user-owned data. The transcripts are the user's record of their own thinking and work; deleting them by default, silently, with no recovery, inverts the expected ownership relationship. A 30-day default that quietly discards months of accumulated reasoning is a poor default for that audience, however reasonable it is for disk hygiene in the general case."

Those users would be wise to back those files up if they consider them valuable intellectual property. If they're important enough that you'd miss them after a disk failure, then they should have been being backed up already.

There are several third party tools which can assist with transparently aggregating and archiving sessions across projects

Ccrider is the one I use: https://github.com/neilberkman/ccrider

Session backups live outside of ~.claude so are not deleted and can be resumed.

I thought this was a feature that they tidied up your data

This is clearly shown in the settings/config (or at least was last time I looked), if people are surprised by this I recommend asking claude code what settings you can tweak

"Evil Anthropic implements rolling log files."

Film at 11.

Probably a better practice to devise your own record/docs history to rely on rather than depending on Anthropic.

This literally hit me just last night. Went to continue a project I haven't touched in a while and couldn't find the session, which I wanted to continue from as it's a cheap way to track token cost at the project level. Many missing sessions, then Claude told me what was up and I had it configure retention for 10,000 years.

raw transcripts can expire, but decisions shouldn’t. i’d rather keep durable project facts separately than depend on old chat logs.

[dead]