Show HN: Claude-thermos – keeps your Claude session warm for you (github.com)
26 points by s0ck_r4w 3 hours ago
unholiness an hour ago
I've directly inspected calls for pro/Max plans and as of today they have 1hr cache expiries. This has definitely degraded to 5 min in the past but that's the behavior today.
If you're paying API rates, you can choose 5m or 1hr yourself (and pay different rates).
Keeping a 1hr cache warm could still be useful, sure, but outside that, I don't see much use of this today.
s0ck_r4w an hour ago
When using API keys the default is still 5 minutes. Setting 1 hour for the entire session is actually a lot more wasteful considering the 2x rate that it comes with
alukin 2 hours ago
Feels like will be shut down real quick
gogobio 2 hours ago
Yes, this wastes cycle. They dump your cache and deallocate the VMs so that others can use it. This will result in tokens wasted and downtime for others.
l1n 2 hours ago
Why? Seems fine if people want to burn more cache reads.
agluszak 2 hours ago
Because it makes Anthropic earn less money
cadamsdotcom an hour ago
munk-a an hour ago
jonas21 an hour ago
Is the 5-minute expiration correct? I thought it was more like ~1 hour.
s0ck_r4w an hour ago
You can set the retention globally (whole session) to 1 hour which will actually make it more expensive. The default is 5 minutes.
*UPD:* actually it appears the default is authentication-dependent. API key gets 5 minutes, subscriptions - 1 hour.
cosmotic 37 minutes ago
How will this not lead to tragedy of the commons?
davesque 29 minutes ago
Exactly. I really wish people wouldn't use this. If this becomes popular, anthropic will just modify their cache policy to be much less fair. It's not like they have infinite cache.
ATMLOTTOBEER an hour ago
Glad this exists. It will force anthropic to fix their flawed cache mechanism.
cortesoft an hour ago
How should they fix it?
s0ck_r4w 30 minutes ago
Make the cache TTL more adaptive. Have more tiers than just 5m and 1h. Long-running subagents become increasingly ubiquitous. There's no reason for Anthropic to not do a better job for this use case.
razodactyl an hour ago
Don't we pay for cache input though?
broodbucket an hour ago
You can send and receive 1 byte and refresh the cache. Keeping the cache alive isn't free, but it's close.
cortesoft an hour ago
The idea is this keeps it in cache so you don’t have to pay to re-input.
j45 an hour ago
This is a good idea if it could manage it in an acceptable way.
For example, there might be something I intended to complete in one sitting, but took two sittings in the same day unexpectedly. Maybe it could just be a few cache delays per day or something, tagged in advance somehow.