Claude Code 今天上线了一个新功能：agent view，让开发者可以在一个界面里统管所有正在运行的 AI 编程会话。 过去用 Claude Code 同时跑多个任务，只能靠一堆终端标签页和 tmux 分屏拼凑，脑子里还得记着每个任务跑到哪了。现在不用这么折腾了。 在任意会话里按左箭头，或者直接在终端跑 claude agents，就能打开 agent view 的总览界面。每一行显示一个会话的状态：在等你回复、还在跑、还是已经完成，一眼能看清。 最实用的一点是不用切换上下文就能回复。选中某个会话可以先"偷看"最新进展，如果它在等你做决定，直接在那里打回复，它就接着跑。不用打开完整会话窗口，不打断你手头在做的事。 想把某个会话扔到后台？在会话内输入 /bg。想直接起一个后台任务？claude --bg [任务描述]，连前台都不用经过。 目前 agent view 以“研究预览”状态上线，Pro、Max、Team、Enterprise 和 API 用户今天就可以用，直接跑 claude agents 即可激活。

I've published a new, general-purpose terminal specification that gives any program a way to tell the terminal what it's doing: idle, working, waiting, finished, or failed, and why. It is easy to implement on both sides. I've written more about why: mitchellh.com/writing/progra… The problem this solves is generic and applies in compelling ways to all sorts of use cases (e.g. package managers, build tools), but it really rears a hideous head when it comes to AI and the "agentic inbox" problem. I found over 250 different agent orchestrators (with various goals) that all individually implement a heuristic based approach to detecting whether things like Claude Code are working, blocked, done, etc. If you look at @herdrdev's commit history, you can see around 10 compatibility changes to detect Claude Code within just the past 3 months. (This isn't a dig at Herdr! They're doing great work with what they have, and everyone else is doing the same thing). Heuristics are not the way. And over-indexing on agentic use cases isn't the way, because this problem is really interesting for other tools too: Homebrew, Terraform, Cargo, etc. etc. Proprietary protocols and out of band APIs are not the way. They have an O(N) integration problem and require extra work to work over SSH or within local VMs/containers. The program status specification (OSC 7501) solves this in a reliable, deterministic way that is general-purpose and can be easily adopted by the entire industry. Read more: mitchellh.com/writing/progra…

I've published a new, general-purpose terminal specification that gives any program a way to tell the terminal what it's doing: idle, working, waiting, finished, or failed, and why. It is easy to implement on both sides. I've written more about why: mitchellh.com/writing/progra… The problem this solves is generic and applies in compelling ways to all sorts of use cases (e.g. package managers, build tools), but it really rears a hideous head when it comes to AI and the "agentic inbox" problem. I found over 250 different agent orchestrators (with various goals) that all individually implement a heuristic based approach to detecting whether things like Claude Code are working, blocked, done, etc. If you look at @herdrdev's commit history, you can see around 10 compatibility changes to detect Claude Code within just the past 3 months. (This isn't a dig at Herdr! They're doing great work with what they have, and everyone else is doing the same thing). Heuristics are not the way. And over-indexing on agentic use cases isn't the way, because this problem is really interesting for other tools too: Homebrew, Terraform, Cargo, etc. etc. Proprietary protocols and out of band APIs are not the way. They have an O(N) integration problem and require extra work to work over SSH or within local VMs/containers. The program status specification (OSC 7501) solves this in a reliable, deterministic way that is general-purpose and can be easily adopted by the entire industry. Read more: mitchellh.com/writing/progra…

This is brilliant. opusfived.dev

A\的OSS免费订阅今天就到期了…回头提交一波新的申请，不知道还能不能通过。最近各种三个AI换着用，这要能给我续上的话岂不是好歹得叫A\一声义父…🤣

人设这段会不会影响到代码注释喵～

给我看懵了。有位开发者觉得，现在苹果电脑顶部的菜单栏，空着也是空着，不如开发个插件，让顶部显示广告。 这样广告商也能付费做投放，而安装这插件，看广告的人也能获得收入。 没想到在这个产品上线后，前几小时就获得超过 1.2 万次展示，平均广告点击率 4.4%，点击成本 0.09 美金。经核算，远比普通的互联网横幅广告投放，点击率要高不少。 不过这也让评论区的人吵疯了，因为多数人本来就是受不了 Windows 上各流氓广告软件，才买的苹果 Mac，结果这个产品一下倒退了。

Hey Anthropic. You guys have given me a lot of subsidized compute. In return, I'll give you an example of how to make announcements like this without burning all your good will with developers. "Back in May, we did a one-month promotion where we increased the weekly rate limits for Claude Code by 50%. We've extended this promotion multiple times since, but sadly, it must come to an end on September 14th. We know that this will impact the work of many users. We've run the numbers and found that we are able to make a permanent increase of 25%. This nets out to a 17% decrease from the limits as they are today. We understand this is a big hit for a lot of users. We hate making changes like this. We're doing everything in our power to secure more compute to improve availability of Claude. We do have some good news. When these changes go live on September 14th, we will be removing the separate weekly limit for Fable, so you will now be able to use your full limit with your preferred Claude model."

？？？这也行吗

這兩天玩了一下這個終端機，還頂 fancy 的。不過我覺得我已經離不開 @onevcat 的 Prowl…。