What’s new in Playcode

When the agent hands work to a background task, you now follow it and answer it in the chat:

• The task's card stays in sight in the chat while the task works or waits, instead of folding into the agent's steps.
• When a task pauses at its credit budget, the chat shows a pause card: what the task finished, what is left, and one Continue button. Before, you had to open the task and find the button inside it.
• A task's own view is now read-only, with a Back to chat button. To change a task, write to the agent in the chat. Before, words typed inside a task never reached the agent, and it could undo what you asked for.

When you archive a Cloud project, its computers now stop. Its live site goes offline, and its Cloud slot frees up for another project. The code, the database and the files stay, and their storage is still billed.

Playcode asks before it archives a Cloud project, wherever you archive it from.

Restore brings the project back:

• With a free Cloud slot, its computers start and the site comes back online.
• With every slot taken, Playcode shows your Cloud projects, so you can free a slot or move up to a bigger plan.

Open an archived project and nothing starts until you choose Restore. Cloud projects you archived earlier stop too.

On a hard request, Claude Opus 5.5, the Standard model, can think for several minutes before it writes anything. Until now the chat showed nothing in that time, and after four minutes it said the chat had stalled.

• Now: a Thinking line appears within seconds. Open it to read a summary of what the agent is working through, while it works.
• No false stall notice: while the agent writes - a long answer, a big file, a long think - the chat no longer says it stalled.

In a Browser project, the agent's file search sometimes found nothing, and the agent said the project had no files. The files were there.

• Before: the agent could tell you it found no files, and work as if the project were new.
• Now: the agent's search finds every file of the project.

The Invite a friend program has ended. The invite row is gone from the menu, and invite-a-friend links now open the Playcode home page. Links that invite people to a workspace work as before.

Credits you or your friends already received stay in your account. Inviting no longer earns credits when a friend subscribes.

Sometimes the chat still showed the agent at work after its reply had ended. A message you sent then waited for an answer that never came.

• Before: the message stayed unanswered until you edited it or sent it again.
• Now: before such a message goes, the chat checks with Playcode whether the agent still works on a reply. If the reply has ended, your message starts a new one.

When you deleted a file from a static project, such as an image or a page, it stayed on your published site after the next Publish. Its old address kept working, on your own domain too.

Now each Publish puts exactly the files of your project live. A file you delete leaves your site the next time you publish.

Published before this change? Publish once more to clear the files that earlier publishes left behind.

GPT-6.1 Terra, OpenAI's new everyday model between GPT-6 Luna and GPT-6.1 Sol, joins the Standard level: open its model list and find it under More models…. It holds a 1M-token context window and reads images.

• For your apps too. Apps you host on Playcode can call GPT-6.1 Terra through Playcode AI Gateway, and choose how much it reasons, from none to maximum effort.

The agent can now search inside a large file you attach or paste, instead of reading it from the start.

• Big data files. Ask what is in a large JSON, CSV or exported page, and the agent searches it for the parts you need. It does not have to read the whole file, or copy it into your project first.
• Everything on one line. When a file keeps its data on one long line, like minified code or an export, the agent now sees every match on that line, not just its beginning.

This works for text files up to 10 MB.

When the agent tries to change a file and the change does not go through, the chat now marks that step Failed in red.

• Before: a failed edit looked like a finished one, with line counts and a preview of the change, while the file stayed the same.
• Now: the step shows Failed and no line counts. Open it and it says the step did not go through. Steps that worked look as before.

When the agent replaces an image in a static project and keeps its file name, the preview and the next Publish now use the new image.

• Before: the editor kept the old image until you reloaded the page. A publish in that time put the old image on your live site, though the project already held the new one.
• Now: the preview shows the new image at once, and the next publish puts it live.

The same holds when you undo the agent's change to an image: the preview and the next publish use the restored one.

The agent can now open one file of a ZIP you attach, without unpacking the whole archive.

• Just the files you need. Ask for a README, a config file or one page, and the agent reads it straight from the archive and copies it into your project exactly as it is.
• When the images do not fit. If an archive's images need more storage than you have left, the agent can still bring over its text files: they do not count toward your storage.

The agent opens text files this way. Images and other binary files still come in with an unpack.

Apps you host on Playcode can now call Kimi K3.1 Pro, Moonshot's newest model, and Kimi K3.1 Pro Highspeed, the same model served about two to three times faster at twice the price, through Playcode AI Gateway. Both hold a 1M-token context window and always reason before they answer.

• Kimi leaves the Standard model picker. Under More models… you now find Grok 4.7 and Gemini 3.8 Flash. A chat already set to Kimi K3 keeps working on it.

On a paid plan, every finished answer in the chat now shows what it used, in credits, right under it.

• The same number as your Usage page. It counts the work behind that answer the way the Usage page counts it.
• The agent knows it too. Ask what the last change used, and it tells you the same number.

Economy builds now run on GPT-6 Luna. On the customer tasks we tested side by side, it completed more of what we asked than Gemini 3 Flash and used far fewer credits, so the same credits go further. It is not in a hurry: a build can take longer than you are used to.

• Your saved choice moves with it. If you had picked Gemini 3 Flash as your Economy model, that pick now points at GPT-6 Luna.
• Economy has one model now. Its card shows GPT-6 Luna and no longer opens a list of models. Standard and Ultra still let you pick a model.
• The summaries that keep long chats going now run on GPT-6 Luna too.

Tailwind classes that hold a CSS variable, a function or quotes now get their styles, in the preview and on your published site.

• Before: classes such as bg-[var(--accent)], text-[clamp(2rem,5vw,4rem)], shadow-[04px12px_rgba(0,0,0,0.1)], bg-[url('/hero.jpg')] and data-[state=open]:bg-red-500 had no effect, and nothing said so. A band could lose its color, or a title its size.
• Now: these classes work as written. The preview shows them the next time you open your project.
• Your published site changes when you publish again. If it uses such classes, look at the preview first: it shows the design your code describes, which can differ from what is live now.

A static site with many pages publishes again. Before, a large site could stop at the build: Publish showed "transaction timed out" or a memory error, and the live site kept its old version.

• Now: a site with dozens of pages builds and publishes.
• Shared styles are one file. Pages that use the same stylesheets now share one CSS file. A visitor's browser loads it once, not again on every page, and each publish uploads less.
• A large file no longer holds up the rest. Other files upload while a video is still on its way.

Pages that share stylesheets get the shared file the next time you publish.

When your page links a file that your project does not have, such as a stylesheet, a script or an image, the page now shows without that file, as a browser shows it.

• Before: one missing file stopped the whole page, and the preview went white.
• Now: the page shows, and a small note at the bottom of the preview says what is missing. Click it to see every problem in the console, with the file and the line. Click Fix it to hand the problems to the agent.
• A broken change keeps your page. If your last change breaks the code, the preview keeps the page that worked and tells you so.
• Publishing works too. A site with a missing file publishes, and it looks the same as in the preview.
• Files in public load. A stylesheet or a script in your public folder that your page links to now loads, in the preview and on your published site.

When the agent reads a very long web page, a PDF from the web or a large file, it now takes the first part of it, and the chat goes on.

• No more stuck chats. Before, one very large document could fill the whole conversation. The chat then stopped and asked you to click Continue, and every Continue stopped again.
• The agent knows the rest is missing. It sees that the text was cut and how much was left out.

@playcode/sdk 0.7 (npm) is out, and 0.7.1 is the latest. New Cloud apps start on it. In an older app, ask the agent to update the SDK: it reads the upgrade steps in the SDK's changelog first.

• The next run keeps the model's reasoning. A model's turn now carries its private parts, Claude's thinking and Gemini's thought signatures, sealed as replay. The next run of a conversation sends them back where the model's maker accepts them, so the model keeps its reasoning and the prompt cache reads the repeated part. Before, every new run dropped them.
• Keep each message whole in your store. A store that keeps only the fields it knows drops replay, and the next run goes without the thinking. agentStoreContract checks it. Pages never receive replay.
• A long conversation stays inside its limit. The SDK measures each call before it goes out, Claude's earlier thinking included. It clears old tool results first, then a brief stands in for the older part. A call that still does not fit is not sent, and the run ends with the new finish: "context-limit".
• A brief has room to think. Its request carries the run's thinking and up to 16,384 output tokens, or the model's own cap when lower, so a model that always thinks no longer spends its room before it writes the brief.
• Fewer writes to your database. With the new optional appendRunMessages, a store writes each step once: 142 KB for a 50-step test run, against 7 MB without it.

What goes back to which model: Private parts.

When a task or a command the agent started in the background finishes just as the agent ends its reply, the agent now picks up the result on its own.

• No more silent stops. Before, such a result could wait until you wrote again, and the chat looked stuck.

When the agent asks you a question, the answer form now stays in the chat until you answer it.

• Background work no longer closes the form. If a task the agent started in the background finished right after the question, the form showed "Questions answered" though you had not answered, and the chat looked stuck.
• Approval cards keep their buttons. A card that asks you to approve a purchase or a change no longer loses its buttons when a background command finishes.

When you move a domain's DNS to Playcode, Playcode now checks whether DNSSEC is still on at your registrar. Your old DNS provider may have turned it on, and it does not work with Playcode's nameservers.

• Before the switch, the app and Playcode AI tell you to turn DNSSEC off at your registrar first, then wait a day before you change the nameservers.
• After a switch with DNSSEC still on, the domain's status says so and names the one setting to change, instead of showing the domain as connected.
• It clears by itself. Once DNSSEC is off, Playcode sees the change on its own.

Before, nothing warned you. A domain moved with DNSSEC still on stopped working for many people, its site and its email, while Playcode showed it as connected.

The steps are on My domain does not work.

Open preview in a new window in the preview toolbar now shows your project in its own tab.

• Before: in some browsers, most often Safari, the new tab stayed blank

and showed only your page's title.

• Now: the tab shows your project, the same as the preview in the editor.

When the DNS of your domain already runs at Playcode, a name under it, like shop.example.com, now connects in one step when you connect it to a project.

• Playcode adds the setting itself. There is nothing to copy to another provider.
• The finish says what is true. It shows that the address is being secured until its padlock is ready, then that it is live.

Before, the flow could end on a card that said the name was live, and the name was not connected.

Two fixes for domains bought at Playcode.

Moving a domain away works. Unlock & get transfer code gives the code once the domain's first 60 days after its registration, or its move to Playcode, have passed. Until then, the app says which lock holds the domain and the day it ends.

• Only an Admin of the workspace gets the code. In your Personal workspace, that is you. Playcode's agent can get it too, when an Admin asks.
• The registrant gets an email each time. It says who got the code and when, never the code itself.
• Auto-renew turns off with the code, so Playcode charges no renewal for a domain on its way out. If you keep the domain at Playcode, turn Auto-renew back on.

Resend verification sends the email again. Before, the app said the email was sent, and none went out. If a domain still shows Verify your email, choose Resend verification once more.

Every rule for moving a domain away is on Domain renewals and fees.

A domain you buy at Playcode now renews at the price shown when you bought it, or lower.

• A higher renewal price never arrives as a surprise. It applies only after an email at least 30 days before the renewal.
• A lower price still reaches you. If the Renew price in the fee table is lower than the price you bought at, your domain renews at the lower one.

The fees for every ending are on Renewals and fees.

When the agent writes code with HTML entities such as &, <, " or  , your files now keep them exactly as written.

• Pages that escape text keep working. A helper that turns ' into ' could be saved with the entity replaced by the character itself. The page's script then failed to load, and its buttons stopped working.
• Code shown as text stays text. A tag written as <div> on a page no longer turns into a real tag.
• Non-breaking spaces stay.   is no longer saved as a plain space.
• Edits find the text they quote. An edit to a line with & in it now finds that line instead of failing.

playcode vm cat, playcode vm ls and the project file operations (projectFileGet, projectFileUpdate, projectFileDelete, projectFileSearch) now work on static sites as they do on Cloud apps.

• A file is found with or without a leading slash. index.html and /index.html are the same file. Before, most files the editor and the agent made answered "no such file".
• A write replaces the file you named. It no longer adds a second copy of it, and a new file is named the way the rest of the project is.
• playcode vm ls lists folders by name. Before, a static site's first level showed one folder with no name.
• In a Cloud app, a relative path is inside your app's folder. src/App.tsx means /workspace/src/App.tsx, as it does for the agent.

Click or tap a card in the message box to see what it holds, on a computer and on a phone.

• A pasted page or code opens in full, line by line, exactly as you pasted it. Copy puts it back on your clipboard, and Remove takes it out of your message.
• A picture opens in the same window, with its size. Remove takes it out.
• On the homepage too. The box on Playcode's homepage opens its cards the same way, before you sign up.