I'm ok using a limited resource _if_ I know how much of it I am using. The lack of visible progress towards limits is annoying.

▲

blalezarian 5 days ago | parent | next [-]

Totally agree with this. I live in constant anxiety not knowing how far into my usage I am in all the time.

▲

steveklabnik 5 days ago | parent | prev | next [-]

npx ccusage@latest

I'm assuming it'll get updated to include these windows as well. Pass in "blocks --live" to get a live dashboard!

▲

data-ottawa 5 days ago | parent | next [-]

Oh wow, this showed me the usage stats for the period before ccusage was installed, that’s very helpful especially considering this change.

ETA: You don’t need to authenticate or share your login with this utility, basically zero setup.

▲

mtmail 5 days ago | parent | prev | next [-]

Package page (with screenshot) https://www.npmjs.com/package/ccusage

▲

bravura 5 days ago | parent | prev [-]

Does ccusage (or claude code with subscription) actually tell you what the limits are or how close you are too them?

	▲	steveklabnik 5 days ago \| parent [-]
		https://ccusage.com/guide/live-monitoring See that screenshot. It certainly shows you when your 5 hour session is set to refresh, in my understanding it also attempts to show you how you're doing with other limits via projection.

▲

flkiwi 5 days ago | parent | prev | next [-]

It's not exactly the same thing, but imagine my complete surprise when, in the middle of a discussion with Copilot and without warning, it announced that the conversation had reached its length limit and I had to start a new one with absolutely no context from the current one. Copilot has many, many usability quirks, but that was the first that actually made me mad.

	▲	jononor 5 days ago \| parent \| next [-]
		ChatGPT and Claude do the same. And I have noticed that model performance can often degrade a lot before such a hard limit. So even when not hitting the hard limit, splitting out to a new session can be useful. Context management is the new prompt engineering...
	▲	stronglikedan 5 days ago \| parent \| prev [-]
		The craziest thing to me is that it actually completely stopped you in your tracks instead of upselling you on the spot to continue.

▲

mvieira38 5 days ago | parent | prev [-]

You can't really predict usage of output tokens, too, so this is especially concerning

	▲	qiller 5 days ago \| parent [-]
		Like when Claude suddenly decides it's not happy with a tiny one-off script and generates 20 refined versions :D