Codex CLI history: sharing across a team
How does the rest of the team see what I asked the AI?
Why this is hard
AI coding history is private by construction. Every tool writes it to the machine it ran on, under the account that ran it, in a location no colleague will ever open. That is a reasonable default for a cache and a poor one for the only written account of why a change looks the way it does.
What Codex CLI specifically does to you here
Rollout files are the most complete transcripts of any tool here — prompts, responses, tool calls and their results — and they are plain JSONL, so sharing one is genuinely possible. What is missing is anywhere to share it to.
find ~/.codex/sessions -name 'rollout-*.jsonl' | wc -l
Where Codex CLI keeps this in the first place: ~/.codex/sessions/YYYY/MM/DD/rollout-*.jsonl. Nothing prunes ~/.codex/sessions, so it grows until a person deletes it — usually all of it, usually in a hurry.
What a working answer looks like
A working answer means one place where a lead can read what the team asked and what came back, without asking anyone to export anything by hand.
Start by measuring what you have. npx promptwake doctor reports what every AI tool on the machine is holding and how much of it sits inside a deletion window — no account, writes nothing, sends nothing anywhere. If the conclusion is that the record should not depend on one laptop, that is what PromptWake captures: prompt, response and the resulting diff, local by default and synced into a shared timeline on the paid tiers.
