Still interactive (conforms to spirit of Anthropic's new rule), and runs Claude Code via the actual CLI (conforms to letter of Anthropic's rule), without even using the JSON output flag. It would just read the outputs directly from the terminal like a user would, and then translates the user's actions directly into actions to the Claude Code TUI.
Tradeoffs: the thinking blocks are lost, and file changes from edit tools might have to be reconstructed after-the-fact using VCS commands because the TUI doesn't display them when accept-edits mode is enabled. Requires underlying terminal to have a giant width/height in order to reliably capture the outputs by reading the terminal alone. Interactive tools like AskUserQuestion will need to work via detecting that such a prompt is open and exposing the original CLI interface to the user temporarily.
But overall it seems like it could give users most of the benefits of an interactive GUI interface (scrollable history, much higher info density, easy to copy text, browse features with mouse) while staying compliant with Anthropic's new rules both in letter and spirit. You can then build a worktree manager or whatever above this agent GUI layer. This way us interactive users can have our good tools back (and leverage the new claude -p credit for occasional automation features) while the people who are actually abusing the plan with 24/7 dark factories or openclaw are still locked out.
(the only way Anthropic would not agree to this is if they had the ulterior motive of lock-in in mind...)
> Tradeoffs [...]
Sounds like you're thinking of scraping the raw terminal output. Consider using a terminal library (pyte[0] comes to mind) for interaction and processing the session files for tool use data, etc.
Also I managed to get a VSCode Claude Code wrapper working last night. It launches instances of browser-based VSCode (via Coder's code-server) with Claude Code plugin pre-installed, then hides all toolbars and opens the CC window using another bundled custom plugin. Still have a few integration problems to solve, but in theory this should be perfectly allowed by Anthropic, give you a pretty good UI, and still allow integration into an agent orchestrator using hooks/session files to get the agent data.
99% of my max plan usage is non-interactive, and this post-June 15 pricing will far, far exceed what I can afford. I assume this applies to a great deal of us.
If you're an active `claude -p` user, it will now cost you API rates vs being able to user your subscription.
UPDATE: https://x.com/lydiahallie/status/2054650920768807313?s=20
Still confused.
this is the original thread https://x.com/ClaudeDevs/status/2054610152817619388?s=20
https://x.com/ClaudeDevs/status/2054610152817619388
You can claim a monthly credit that covers programmatic (`claude -p`, etc) usage.
So a Claude subscription does cover it, but at a lesser amount.
But inevitably, this will end, ultimately making AI a bit less accessible for consumers.
Hoping the Zed team will clarify.
https://github.com/agentclientprotocol/claude-agent-acp/blob...
Considering what kind of fuckups happened up until now everytime Anthropic vibe codes a horrible anti-automation "fix" (like billing extra usage just because the string "hermes" exists somewhere in the prompt), this will get funny/horrible really fast. After all, you can very easily script tmux to use Claude Code "interactively".
What crazy shenanigans are gonna happen? Are people that type too fast, or people that copy paste too much, or people that output to markdown/json too often going to wake up to a 800$ extra usage bill or a banned account?
This is a nothing burger.
Subscription usage refills every five hours. API billing doesn't.
$200 of on-demand usage credits is much, much, much less than what they were getting with $200 subscription.
Maybe "good," maybe "bad," but definitely, definitely not a nothing burger.
Stuff like gas town is dead in the water
My understanding is that now with this workflow I will pay the same amount but get much less usage before getting to 100% for the week. How is that not bad?
Well..........
That was the point of the subscription. It gave you extremely discounted pricing, in exchange for recurring revenue.
For a normal subscription user, they would get multiple X of what they would if paying on-demand usage.
I assume that with API pricing it will run out in the first week and I might as well unsubscribe.
It's one thing for Anthropic to ban subscription usage of OpenCode etc of their backend.
It's another thing to use their tools and still not get the full usage.
Claude's recent one 9 of uptime [1] might have something to do with it.
That is not sustainable for me. I understand that Anthropic can't subsidize all of us forever, but this will force me away from claude which is unfortunate. A number of the people I work with are similarly affected.
But like I said, this is something for those users. I launch many review processes locally with `claude -p`
The Pro plan is barely enough for this after the doubling of usage limits.
If anything you might be an outlier if you do this and are actually producing something of reasonable value down the line.
They know if the value provided by subsidized usage is too low, they're literally burning dollars for nothing: people won't feel any great pain losing it one day and definitely won't convert.
I’ve been happily single-homed on Anthropic for the last year, but I’ll be spending the next month rewriting projects off it to take advantage of better value elsewhere. I suspect that’s a one way door.