You'll see a lot of advanced users advising against compact. The truth is that you have the entire transcripts in your ~/.claude/transcripts (I give claude permission to look there) so when there is some important discussion I don't want to lose, I use claude extract the notes from the transcript. If it's a long transaction it can be big so it might miss things on the first go around - but if you ask it specifically about the topic you're interested in it'll usually find it.
I’ve run into a similar issue, compacting is pretty much worthless and leads to a lot of churn.
I have started having Claude pay constant attention to usage and assess whether the next batch of tasks flirts with compaction.
If we’re anywhere close I have Claude create a next steps doc with meticulous notes along with a prompt that I can give to the next llm to hit the ground running.
Then kill the session and start fresh.
At least this way I know there’s a fighting chance of not falling into a death spiral of the llm guessing about what it’s supposed to be doing as if it hasn’t just had a self inflicted stroke.
You'll see a lot of advanced users advising against compact. The truth is that you have the entire transcripts in your ~/.claude/transcripts (I give claude permission to look there) so when there is some important discussion I don't want to lose, I use claude extract the notes from the transcript. If it's a long transaction it can be big so it might miss things on the first go around - but if you ask it specifically about the topic you're interested in it'll usually find it.
I’ve run into a similar issue, compacting is pretty much worthless and leads to a lot of churn. I have started having Claude pay constant attention to usage and assess whether the next batch of tasks flirts with compaction. If we’re anywhere close I have Claude create a next steps doc with meticulous notes along with a prompt that I can give to the next llm to hit the ground running.
Then kill the session and start fresh. At least this way I know there’s a fighting chance of not falling into a death spiral of the llm guessing about what it’s supposed to be doing as if it hasn’t just had a self inflicted stroke.