Rin Chat Update Notes - Version: 1.0.5
21 November 2026
🔎 Web search
Replies can look things up on the web. Turn on Web Search in Settings and, before a reply, a small model reads your message and decides whether a search would help. The results go into that one reply's prompt and are never saved into the chat. Let it decide every turn, or search only when your message says something like "look up" or "search for". Search through your Rin Chat subscription (25 searches a day, with what is left shown in Settings), or with your own NanoGPT, Serper or Brave key, or your own SearXNG server. Messages sent from your phone search too: your computer runs the search with its own keys, and they never reach the phone.
Replies show their sources. A reply that used a search has a Sources line under it: open it to see what was searched and every page it drew on, each a link that opens in your browser. It works on the phone too.
Characters can check their canon. Web search can also read Wikipedia, in the language you pick, and a character's own Fandom wiki, both free and with no key. Set a character's wiki from the chat's Session info menu, under Fandom wiki.
Links you paste are read. Paste a link into a message and the page is fetched and given to the model with that message, up to two links by default, each cut to a length you choose.
🌐 Browse AICC
Find cards on aicharactercards.com without leaving the app. With your aicharactercards.com account linked, the Library has a Browse AICC tab: search, pick tags, sort by newest, downloads or rating, and page through the site's cards with their grade, rating and download count. Add to library brings one in exactly like a card file you import yourself, and View on AICC opens its page in your browser.
Cards you already have say so. A card you added from Browse AICC shows Edit in Rin Chat instead of Add to library, and when the site has a newer version it says Update available and opens the update review.
Cards look as they do on the site, and open in place. Browse AICC tiles carry the site's AI Grade and NSFW or SFW badges, and clicking one opens its page right in the app: the picture, creator, rating, downloads, tokens, tags and description, with Add to library and View on AICC beside them.
Trending and most-downloaded sorts. Sort by Trending yesterday, this week or this month, or by Most downloads this week, this month, this year or of all time, the same choices the site offers.
Keep scrolling for more. More cards load as you near the end of the list, with no pages to step through. If a load fails, Load more tries again.
The occasional sponsored tile. Free accounts may see a tile marked Sponsored among the cards. It is never a card: it opens the sponsor's page in your browser and nothing else. Paid plans see none.
📚 Library
All chats leaves out chats from hidden folders. A chat with a character in a folder you hid from All cards no longer shows in All chats, just as the character does not show in All cards. A line at the top says how many are hidden, and Show them lists them until you leave All chats. To always see them, turn off Hide chats from hidden folders in All chats in Settings → Chat Display; the (i) on that line opens it. Your phone's Chats list, which always left them out, now follows the same setting and has the same line.
Rename a chat or give it a note right from All chats. The pencil on a chat's row (or F2) lets you change its name and add a short note for yourself, like "left off at the heist". The note shows under the chat's name, is never sent to the model, and the search box finds it too. Inside a chat it is under Session info → Chat note, and your phone's Chats list shows it.
🎲 Adventure Mode
- Adventure Mode is no longer experimental. It has grown into a full part of the app, so the Guide drops the experimental label from Adventure mode and from being the DM yourself.
🐛 Fixes
On your phone, Regenerate works on the first tap with the keyboard open. Over Remote Access, tapping Regenerate, a reply's version arrows, Message actions or a choice while you were typing only closed the keyboard, and you had to tap again. Those buttons now work on the first tap and leave the keyboard up.
The phone's import box takes every aicharactercards.com link. Over Remote Access, paste a card's SillyTavern download link, or any of the site's other download addresses, and the card imports, always as the full Rin Chat version.
The context bar is easier to read. Its breakdown opens only when you point at a colored part of the bar, not the empty rest of it or the label, the smallest parts are now wide enough to see and point at, and the label shows how full the context is as a percentage.
Cards from other tools open in the editor even after their generators were added to your library. A card whose generators were written without fields still crashed Edit in 1.0.4 if you had added those generators to your Generators library: the editor refreshed the card from the library copy, which was never repaired. The library is now repaired when it loads, so the card opens with no need to delete and import it again.
Rin Chat Update Notes - Version: 1.0.4
20 November 2026
🎨 Chat styles
Characters can bring their own chat style. A card can now carry CSS that restyles its chat window while you chat with it: bubbles, names, avatars, choices, dice rolls, the Adventure Mode HUD, the message box and every color. Set a few colors and the whole window follows, reply bubbles, accents, button edges and the text on buttons included. It stays inside the chat window, never touches the top bar, sidebars or menus, and never loads anything from the web.
The story can change the look. A chat style can react to the card's own story variables and to Adventure Mode, so the window can turn stormy at night, close in red when your health runs low, or mark the message box during a fight. A single reply can also wear a look of its own, like a whisper, a flashback or a shout: the chat tells the character which looks the style has, and the mark never shows.
Chat styles can use the card's own pictures and fonts. The card's backgrounds and pictures can dress its chat window, and up to eight font files added in the card editor give it its own lettering. Both load from the card itself, never from the web. Card fonts load on Windows and Android; elsewhere the chat falls back to another font.
Write one in the card editor, with the Card Forge, or start from a starter. The card editor's new Chat style section takes the CSS, lists every part of the chat you can style, shows exactly what the chat will skip, and previews it all on a sample chat in light, dark and phone width, with .css import and export. Try a state shows how the style reacts to the story. Eight starters, from a fantasy tavern and a starship console to noir, a 16-bit RPG and a visual novel, are drawn with your own character, ready to use as they are or change. In the Card Forge, ask your guide for one or press Write a chat style: it shows the proposal on the same sample chat before you accept, and Fix the chat style rewrites anything the chat would skip.
Chat styles in group chats. One member's style dresses the window and every other styled member keeps its own look on its own messages. Pick whose style sets the window, or none, in the Group chat dialog, and turn the members' own looks off there too.
You decide whether you see them. Turn chat styles off for every card in Settings, Chat Display, or for one card from the Session info menu at the top of its chat (on a phone, Chat options). Both switches sit outside the styled window, so a style can never hide them. The first time a card's style dresses a chat, a short notice above it says so, with a button to turn it off for that card.
Chat styles travel with their cards. Exports, PNGs, SillyTavern files, bundles and uploads keep each card's style, and bundles also carry its pictures and fonts. Importing a card or bundle names the characters that bring a chat style, and Import & overwrite and card updates bring a card's new chat style along with the rest of it.
📄 Document styles
The aurora-sky title no longer jumps as it appears. Its fade-in widened the letters, so a long place name could wrap onto two lines and then snap back to one, jerking everything under it. It now fades in from a slight zoom that keeps the layout still.
Stream chat badges line up with the names beside them. The mod, sub and VIP badges sat a little low next to each username. They're now centered on the name and scale with the text size.
A document style can no longer reach the web or break other styles. A card's style could slip a web address past the check by spelling it with CSS escapes, an
@importin it was fetched the moment the app read it, and a style that ended mid-value could switch off every style after it. All three are closed: a style's CSS is now read without loading anything, escaped addresses are caught, and an unfinished rule is dropped on its own.
📚 Library
Post your themes, document styles and generators to aicharactercards.com. Post to aicharactercards.com now sits beside Export in the theme manager, a document style's editor and the Generators library. It sends the same file Export saves and opens the site's submit form in your browser with it attached, so you only add a description and tags there. It shows for your own themes, styles and generators while your account is linked, never for the built-ins.
Cards without art now show a holo card. A character, lorebook or generator with no picture of its own shows a card in the same style aicharactercards.com uses: its name, its type (Adventure Mode cards in their own colors), who made it, and art for its kind. You see it in the library, the card editor, the Card Forge and the tag picker, and it follows the card's name as you edit it.
Give a generator your own cover. Set cover image, in a generator's editor, puts your picture on its tile in place of the holo card, cropped to the card shape and made small enough to share. It travels in the generator's exports, bundles and posts to aicharactercards.com. Remove cover brings the holo card back. A card that uses the generator doesn't carry the picture, so cards stay small.
Exported and uploaded cards carry that cover instead of the old placeholder. Saving an art-less card as a PNG, or uploading it to aicharactercards.com, puts its holo card in the file, labeled Rin Chat or SillyTavern to match the format. Import one of those files, from the app or from the site, and the card is treated as having no art, so it keeps showing a fresh cover with its current name instead of a picture of the old one.
🎲 Adventure Mode
A tidier character sheet. The sheet now splits into tabs, Character, Inventory (with your money) and Other, plus DM when spoilers are on, so you see one group at a time. Bars like health sit at the top whatever tab is open, with the current value and its maximum side by side instead of a bar tucked under half the grid and the maximum listed as a stat of its own. Long names wrap instead of being cut off, the number boxes are narrower, and a stat that holds words gets a whole line. New stats land in the tab you have open.
Inventory reads like a list, and items can have descriptions. Each item gets a line of its own with its full name and its count at the right. Click an item's name to give it a description, which shows under it and which the GM reads too.
The DM tab is grouped by who each stat is about. Every NPC gets its own heading with its stats and health bar under it, followed by the turn order and the rest of the world, instead of one long mixed list.
The GM keeps a roster of the people you meet. When someone matters enough to meet again, the GM writes them down: what they look like, what they want, how they talk, and what has happened between you since. It marks who is with you, who has left and where they went, and who has died, so a smuggler who walked out three scenes ago comes back as the same person with the same grudge, and a dead guard stays dead. Someone who has left costs the GM a single line each turn instead of their whole sheet, and gets their full entry back the moment you mention them. A death also clears that person's stats, and like every other sheet change it is undone when you regenerate or delete the reply. A campaign's opening cast starts on the roster too.
See and edit the roster in the DM tab. With spoilers on, each person gets a card with their status, description, history, health bar and stats: who is here first, then who has left and who has died, each folded away. Change anyone's status, rewrite their description or history, add someone from the add row, or right-click a name to delete that person and their stats. In DM mode it's your roster to keep.
Optional: sync the sheet after each reply. Turn on Sync sheet after each reply in the sheet's Adventure settings, and after every GM reply one extra short call reads what happened and catches what the GM narrated but never wrote down: someone walking out, someone dying, hp lost, gold spent. It also files a lasting fact the reply established, like a named place, a faction or a binding deal, in the chat's lorebook, at most two at a time and never one the lorebook already has. Every eighth reply it reads the last several turns together and fixes what slipped past since. Its changes belong to that reply, so regenerating or deleting the reply undoes them too. It runs in the background, on the Fast model if you use the Rin Chat subscription and on the chat's own model otherwise, never holds up your next message, and stays quiet if it fails. Off by default, set per chat.
The GM hears about its own contradictions. After each reply, Rin Chat checks it against the roster and the sheet, with no extra call: someone on the roster as dead who speaks or acts, someone who left who is back in the scene without being marked back, an enemy left at 0 health with no word on whether they died, money spent that you did not have, or an item used up that you never carried. The GM gets a one-line note about it on the next turn, and the note goes away once a newer reply is in.
👥 Group chats
- Characters only know what they were there for. A character you add to a group partway through used to be sent the whole chat on its turn, so it knew secrets told before it walked in, and smaller models in particular would repeat them. Each member is now sent only the messages from while it was in the group, and a member you remove and add back misses what happened while it was gone. Chats whose cast was set before your first message are unchanged. If you added someone who was meant to have been there all along, open their chip in the group bar and send them the whole chat from there.
🔨 Card Forge
- Your guide can now clean up a card by removing entries. Ask it to merge redundant lorebook entries, drop a duplicate greeting or retire an old rule, and it proposes the change as one set: the entry it keeps, rewritten, plus a row for each entry it would remove, shown struck through with the tokens it frees. Nothing is removed until you accept that row, you can accept the rewrite and reject a removal, and undo puts a removed entry back exactly as it was, settings included. Works for the character's own lorebook, shared lorebooks, greetings and the card's other lists.
🐛 Fixes
Card files written by other tools open in the editor. A card whose generators listed their options directly, or whose lorebook entries had no id, crashed Edit into the "Something went wrong" screen. Those generators are now read as one field each and still roll, lorebook entries get their ids and titles, and the creator, display name and creator notes are picked up from where those files put them. A card already imported is repaired the next time it opens.
Your own messages are readable in the light theme. The bubble was a mid purple under dark text, which was hard to read. It is now a pale purple, so the text stands out clearly, and a theme made from a picture gets a pale bubble in light mode too.
Text boxes use the same font as everything else. Multi-line boxes, the message box and the message editor among them, showed a typewriter-style font while one-line fields used the normal one. They now match, and only the boxes meant for code, like the chat style CSS, stay in a code font.
Dialogs no longer throw away what you typed. Pressing Escape, clicking outside, the X or the phone's Back on a dialog holding unsaved text (directions, instructions, a temporary persona, an Edit with AI request, a Forge guide, image styles, the phone's message editor and more) closed it and lost the text. Now it asks first, with Keep editing and Discard; a dialog with nothing changed still closes straight away.
Dialogs put Cancel first and the action last, everywhere. About forty confirmations and edit boxes, from deleting a forge session to clearing the import log, had the action button first while the rest of the app put Cancel first. They now all match, so the button you are reaching for is always in the same place. The phone's delete sheets keep the phone's own order, with Cancel at the bottom.
Closing the card generator editor asks before throwing away your edits. Its X closed the editor at once, even with unsaved changes. It now asks "Discard changes?" first, and closes straight away when nothing changed.
Unlinking your aicharactercards.com account and removing the Discord bot token now ask first. Either one happened on a single click. Each now asks you to confirm, so a stray click can't stop sync or take your bot offline.
Menu names read the same everywhere. Library buttons such as "Bulk Organize" and "Assign Tag", and "Generate New First Message" in a new chat, used Title Case unlike the rest of the app; they are now in sentence case, and the Guide names menu items exactly as they appear, without the old "…".
Generators keep their chains when you export and import them. Importing a generator, or overwriting one from a file, used to drop the generators it chains to along with each chain's chance and condition; all three now come back.
Duplicated generators and new fields get names of their own. Duplicating twice used to make two "NPC (copy)", and adding a field after deleting one could repeat a field's name; copies are now "(copy 2)" and on up, and a new field takes the first free number.
A generator saved after a failed save no longer shows the old error. "Couldn't save" stayed on screen next to "Saved"; it now clears once a save works. Exports also keep names written in other alphabets, and screen readers now name the field and option boxes.
Switching Card Forge sessions starts the lorebook fresh. Contradiction results, macro warnings, the open entry, the filter, the sort and tester text used to carry over from the session you left; each session now has its own.
Duplicating a style with a long name makes a valid copy. A second copy of a 25-character style used to get a name too long to use, and the error didn't mention length; copies now fit, the name box stops at 30 characters, and the message says so.
Renaming a style onto another style's name now warns you. On the Document styles page, giving a style the name of another of yours used to save with no warning, and only one of them would ever draw; the editor now says the name is taken.
Lorebook pictures survive export and import. An entry's Picture used to be dropped when a lorebook was exported, imported or carried in a bundle, and a book that differed only by a picture was called a duplicate; the picture now travels with the entry.
The lorebook list holds still while you edit an entry. Typing in an open entry used to re-sort the list, so the row jumped under Smallest first or a title sort, and with a filter on it could vanish along with its editor; rows now stay put until you close the entry.
Audit and Test in the lorebook editor point at the right entry. Clicking an audit finding now clears a filter that hides the entry and scrolls to it, and the tester names untitled entries the way the list does instead of "entry 7".
Edits in a chat's card panel are saved when you close the app. Closing the app within a moment of typing in the card panel used to lose the edit; it is now saved first.
Session info keeps a chat's last calls when you close the app. Closing the app within a few seconds of a reply used to drop those calls from Session info; they are now saved before the window closes.
The custom "Words per reply" count is saved reliably. A count changed just before closing the app, or leaving the chat, could be lost, and a popped-out Settings could put the old count back; it now saves right away and every window follows it.
Clicking through the DM roll boxes no longer moves the chat. Clicking into and out of the dice, target or "more dice" box saved the chat and moved it to the top of the list; it now saves only when you change something.
Removing a formatting shortcut sticks. The trash button only removed the row from the screen, so the shortcut came back the next time Settings opened; it now saves at once.
Quick reply checkboxes save the moment you click them. On Mac and on the iPhone remote, "insert only" and "disabled" could be lost, and closing a window right after a click lost them on Windows too.
Adding an image or voice provider and walking away saves nothing. "+ Add" followed by leaving Settings or opening another provider used to save an empty provider and, as the first one, make it active; now only a provider you actually changed is saved.
Provider edits survive closing the window. Flipping a toggle on an LLM, image or voice provider and then closing the window could lose the change; it is saved on close now.
Edits made right before you close the window are kept. The card editor, Notes, Image Studio prompts, saved themes in Theme & Colors and story entries in the chat lorebook each held your last few keystrokes on a short timer that closing the window skipped; they are now saved before it closes.
Saving a Card Forge rename without changing the name leaves the session where it was. It used to count as an edit and jump to the top of the list.
Error messages read as plain sentences in more places. The library, lorebooks, remote access, the recovery kit, the screen lock and setup no longer put "Error:" in front of a message, and a malformed Card Forge reply no longer shows "SyntaxError:".
The card picker's folder list works from the keyboard. Tab reaches each folder, and Enter or Space picks it, as in the Library sidebar.
Delete in Compare cards is quieter. The button repeated on each card is now a red outline, so the merge controls stand out.
Card editor errors read as one plain sentence. Failed imports, exports, image changes and site update checks used to show a raw "Error:" prefix; they now say what went wrong in one sentence. The folder dropdown also works from the keyboard now.
Escape in Card Forge closes only what you opened. Pressing Escape in a message edit or in the slash, macro or tag suggestions could also close the window behind it; now only the edit or the list closes. The Depth box also keeps what you type and checks it when you leave the box.
Image Studio number boxes let you type. Backspacing in How many or the sweep Seeds box used to snap it to 1, so typing 3 gave 13; Width, Height, How many and Seeds now check the number when you leave the box. The Sends line and the copyable picture details also work from the keyboard.
More number boxes take what you type. In generators, the lorebook editor, Story Maker, Character's Note depth, Proactive messaging, Turn order and the Playground seed, backspacing used to snap the box to its minimum and new digits were added on to it, so a lorebook group weight of 100 became 1005 when you tried to type 5; now you type the number and it is checked when you leave the box. A generator's Min and Max and a lorebook entry's advanced Order also take negative numbers now.
Escape closes only the thing in front of you. Escape in the font list, a composer suggestion popup, a sheet stat or a clock editor also closed the dialog or message editor behind it and lost your edit; now it closes only that.
The Guide's Export menu and Manage Tags menus work from the keyboard. Their rows were mouse-only and Escape did nothing; they can now be reached with Tab, picked with Enter, and closed with Escape.
Hints point to Settings pages by their real names. Messages still sent you to "Image providers", "Remote access", "Memory" and other old names; they now match the Settings list.
A chat's dialogs stay with their chat. Session info, Chat memory and the other chat dialogs stayed on screen after you went to Library or Tools; now they hide with the chat and come back as you left them.
Leaving a chat no longer leaves its fullscreen editor, tour or avatar popover on top of Library or Tools. The editor and tour now hide with the chat and come back as you left them, and the avatar popover closes.
A PIN typed during the wait isn't called wrong any more. After a few wrong PINs, a PIN entered before the wait ended used to say "Wrong PIN", shake and clear the box; now it says how long to wait, keeps what you typed, and Unlock stays off until the wait ends.
Lost connections on the phone read as plain sentences. Errors such as "Couldn't delete the chat: Failed to fetch" or "Request failed (500)" now say "Couldn't reach your PC." or "Your PC didn't answer."
Back on the phone goes to a clean Chats list. Back from Characters or More used to land on Chats still filtered by your old search, with no search box to clear it, and Back from an open chat search left the app. Now it clears the search, the same as tapping Chats.
Show older chats on the phone recovers from a dropped connection. A failed request used to hide the button for good; it now says what went wrong and stays, so you can try again.
An f: search on the phone waits for your PC. It used to say "No characters match that." while it was still searching, and forever if the search failed. It now shows the list loading, and on failure says so and offers Try again.
Deleting from a phone message menu always hits the right message. If the chat changed on your PC while the menu was open, coming back could delete a different message; the menu now closes when the chat reloads.
The phone message editor works with a keyboard. In a narrow app window, Escape now cancels the edit and Ctrl+Enter saves it.
The phone model picker says when a search matches nothing. It used to show an empty sheet; it now says no models match.
Escape closes the folder dropdown in the card editor. It used to close only when you clicked outside it.
A lorebook's Characters count updates when you delete a character. A lorebook left open in Lorebooks kept counting cards you had just deleted from Characters until you reopened it; the count now drops as soon as they're deleted.
The Library sidebar's fixed rows work from the keyboard. All cards, Favorites, All chats, All images, Not in Folder and Personas couldn't be reached with Tab like folder rows can; they now take focus and open on Enter or Space.
Lorebook, generator and style edits in Card Forge now save when you leave. Closing the Forge tab or switching session within a few seconds of an edit used to lose it, and two sessions on the same lorebook could overwrite each other's saves; edits now save as you leave, and each session reloads the current copy when you switch to it.
Card Forge waits for the reply before starting a fresh session for the same card. "New session for this card" and deleting the open session used to go ahead mid-reply and carry the half-written reply into the new session; they now ask you to wait or press Stop, like New session already did.
Card Forge errors read as one plain sentence. A failed save, open or delete used to show a raw "Error:" prefix; it now shows just the message.
Import folder offers the cards' generators and styles. Cards brought in with Import folder never offered the generators or document styles they carry; they now do, the same as importing files or a link.
Import errors are plain sentences. Failed imports showed raw "Error: …" text, and a bad link gave two sentences around the error; each now reads as one sentence, such as "Couldn't import from that link: …".
Import progress counts read right for one card. The import and thumbnail screens said "Generating 1 thumbnails…"; they now say "1 thumbnail" and "1 card". Folder name warnings are also ready for translation now.
Setup hints point at the right Settings pages. Messages that sent you to "Settings → Providers" now name "LLM Providers", and voice messages name "Voice Providers", matching the Settings sidebar.
Deleting a theme asks first. Delete in the Theme & Colors menu used to remove a saved theme with one click; it now asks before deleting.
The Theme & Colors menu works from the keyboard. Its items could not be reached with Tab and Escape closed all of Settings; now Tab and Enter work and Escape closes just the menu. Theme name errors also show inside the naming dialog now.
The folder badge menu works from the keyboard. Its folders could not be picked with the keyboard and Escape often did nothing; now Tab, Enter and Escape all work.
Escape in a voice name box cancels only that box. Pressing Escape while renaming a saved voice closed all of Settings; now it just cancels the rename, and each row's Delete is quieter.
Match again really matches again. Pressing it while a check was already running joined that check and reported 0 cards linked; it now waits and runs a new pass. A Skip pressed during a check now sticks, too.
Clearer errors in setup, Account and Theme & Colors. These errors no longer start with a raw "Error:" prefix, a failed vault restore is one sentence, and setup now names the LLM Providers page.
Persona sheet numbers keep what you type. The Level, XP and HP boxes used to snap on every keystroke, so changing HP from 12 to 8 by backspacing gave 1 and then 18; the number is now checked when you leave the box or press Enter.
Switching Direct Chat conversations stops the voice. A message being read aloud used to keep playing after you switched, made a new conversation or cleared, and the other conversation showed Stop speaking on the same message; speech now stops. The Clear dialog also says it clears this conversation, not all of Direct Chat.
Errors on the phone library, in Direct Chat and on the persona sheet read as one plain sentence. A failed delete on the phone used to show "Couldn't delete the chat: RemoteRpcError: …"; the internal label is gone.
The phone's Model and Persona lists check only the one in use. Two configs with the same name, or a temporary persona named like a saved one, used to both show the check; now only the active one does.
Pressing Escape in a small edit box no longer closes the window behind it. Cancelling a Discord memory fact edit used to close all of Settings, and cancelling a variable rename closed the chat inspector; now Escape only cancels the edit.
Model lists now always match the config you picked. Switching quickly between configs could show the previous provider's models under the new one, and a server without a model list kept offering the last server's models; each picker now shows only the current endpoint's list.
Memory counts and recall snippets read properly. Counts said things like "excerpt(s)" and every test recall snippet ended in "…" even when nothing was cut; counts now use proper singular and plural forms, and the ellipsis appears only on trimmed text.
Cancel on a new provider discards it. Pressing Cancel used to save the half-typed provider, give it a generation config and make that active; now nothing is saved.
A provider's Test result stays with that provider. Opening another provider kept the last result on screen, and a test still running could land under the wrong one; now opening a provider clears it.
Regex script checkboxes save the moment you click them. On Mac and on the iPhone remote a toggle could be lost, and closing a pop-out right after one lost it on Windows too.
Generation Configs keeps up with changes made elsewhere. Switching config from the chat header, then editing a sampler in Settings, used to switch back to the old one; the screen now reloads the latest list.
Custom macro edits survive closing the window. An edit made in the last half second before closing used to be lost; it is saved on close now.
New configs get distinct names. Every new generation or prompt config was called "New config"; a second one is now "New config 2".
Looking at Chat memory no longer moves the chat up the list. Closing the dialog used to save the chat every time, and the Close button threw away text typed in the Scene tab; now it saves only when you changed the scene, whichever way you close it.
Ending the Story Director stays ended. A run you paused and then ended used to come back, paused, the next time you opened the chat; ending it now saves the chat.
Escape cancels a chat rename. It used to save the half-typed name and also close the window underneath, such as an open message edit; now it only cancels the rename.
Closing Impersonate with instructions stops the draft. Pressing Escape while a draft was still writing closed the window but left the model generating; now it stops.
Chat errors read as one plain sentence. Several messages used to start with "Error:"; they now just say what went wrong.
Number boxes in the chat take what you type. The group auto count, Story Director Continue and the image history box used to jump to the minimum on backspace and add on to it as you typed; now you can type the number and it is checked when you leave the box.
The Author's Note keeps your edits however you close it. Only Done used to save, so closing with Escape, X or the backdrop kept the change for that session and lost it when you switched chats. Every way out saves it now.
Story setup and Author's Note number boxes let you type. They clamped on every keystroke, so a value could jump while you were typing it, and clearing Depth saved 0 at once. They now accept what you type and clamp when you leave the box.
Searching one exchange in Session info no longer fills another. Exchanges from earlier sessions shared numbers with this session's, so a search or the Raw JSON toggle could show up on a different exchange. Each exchange keeps its own now.
Playground errors show as plain text. An error that quoted a pattern containing HTML was drawn as markup. It now shows exactly as written.
The lorebook picker shows entry counts the same way everywhere. Attached books said "12 entries", books in the attach list showed a bare number and global books showed nothing. All three now say "12 entries".
Opening a card in Card Forge no longer saves it. Simply opening a card used to write it back to the library a few seconds later with nothing changed, moving it to the top of Recently updated and adding a History entry; now only a real edit saves it, and History records the card as it was just before that edit.
The card editor's menus close on Escape and work from the keyboard. Import / Export, Tools and Chats used to close only when you clicked outside them, and the Tools and Chats rows couldn't be reached with Tab; Escape now closes them, and Tab with Enter or Space picks a row.
An empty Notes panel no longer shows search and sort. A chat with no notes used to show a search box and sort buttons with nothing to search or sort; they now show up once there are notes.
Library tiles show their token counts again. Some tiles could stay at "~… tok" for the whole visit; counts saved from earlier visits now fill in at once.
Clear all in the Image Studio gallery asks first. One click used to clear every picture at once, even ones your search or filters were hiding; it now asks and clears only the pictures shown.
The provider tooltip names the model once. Hovering the provider in the title bar could read "Rin Chat · Smart · Smart"; it now says each part once.
Sidebar chat buttons work from the keyboard. The delete X on each chat could not be reached with Tab, and a focused pin or X stayed invisible once the mouse had been used; both now take focus, show while focused and act on Enter. Results under "Found in messages" also open with Enter.
Chat notices no longer replace each other. A warning such as "lorebook entries did not fit the lore budget" used to disappear in seconds when the next notice arrived, such as "Updating chat memory…"; notices now stack, so each one stays on screen long enough to read, and progress lines update in place.
Escape closes only the menu you opened. Pressing Escape in a right-click menu used to close whatever it was opened over as well, so Image Studio's Compare view or the full-screen editor closed with it; now only the menu closes, and the text cursor stays where it was.
The turn order arrows have names for screen readers. The move up and down buttons in Turn order used to have only a hover tooltip; screen readers now read them as "Move earlier" and "Move later".
Errors in Story Maker, the persona builder and image styles read as one plain sentence. They used to start with a raw "Error:"; now they say what went wrong, and Story Maker's provider hint points to Settings → LLM Providers. A failed "Save as persona card" also now says why instead of showing nothing.
The Guide's adventure sheet section matches the sheet. It now describes the tabs, the bars pinned above them, item descriptions, the ⋯ menu on touch screens, and Shift-click on the mask.
Hiding an update download no longer hides how it ended. Pressing Hide while an update downloaded used to keep "Restart now" or "Update failed" from ever showing; now the result appears when the install finishes.
A called check in DM mode picks the ability that fits the skill. Typing "Stealth" used to leave the roll on the first ability; it now switches to Dexterity, unless you already picked an ability yourself.
The Level box in DM mode saves when you leave it. It used to save on every keystroke, so clearing it saved 1 and typing 4 gave 14; it now saves on Enter or when you click away, and takes +1 or -1 like HP and XP.
Adding or renaming a stat no longer replaces one with the same name. Adding "hp" used to reset your existing hp to 0, and renaming into a section that already had that stat deleted one of them; now Add and Save are turned off and the sheet says there is already a stat with that name.
Escape closes a stat's right-click menu on the character sheet. It used to stay open until you clicked somewhere else.
Looking at Session info no longer moves a chat up the list. Closing it saved the chat every time, which counted as chatting; now it saves only when you edited the scene, and closing with Escape saves that edit too.
Escape cancels a message edit on desktop, and Ctrl+Enter saves it. Before, only the Cancel button closed the editor; an open format menu inside it still closes first.
Library pages stay put when a scrollbar appears. Expanding a lorebook's entries used to nudge the whole page sideways by a few pixels.
Opening lines in the guide editor keep what you type. Spaces and new lines used to vanish on every keystroke, so "Hey there" came out as "Heythere" and Enter couldn't start a new line; the text is now cleaned up only when you save.
Deleting a guide now asks first. Delete used to remove a custom guide at once and said nothing if it failed; it now asks you to confirm and shows an error if the delete fails. Escape also no longer throws away unsaved guide edits.
Deleting the last lorebook entry in Card Forge keeps the lorebook's name. Removing the final entry used to blank the name; the name now stays.
Import settings now refuses files that are not settings. Picking a character card or a non-JSON file used to write junk settings and report success; now it says plainly what the file is and restores nothing.
Closing Settings right after a change now updates every window. A theme or chat style change made just before closing a popped-out Settings window used to leave the main window on the old look until a reload; it now updates at once.
Settings errors read as one plain sentence. Messages such as a failed model list used to start with "Error:" and sometimes run to two sentences; they now say what went wrong in one.
Clearing a card's version history asks first. One click used to delete every snapshot at once; now it asks you to confirm, and if clearing fails, the editor says why.
Escape closes only the window on top in the card editor. In Improve presets and in the new-folder box, Escape used to close the window behind as well; now only the top one closes.
A failed autosave no longer leaves "Saving…" on screen. The toolbar used to say "Saving…" forever after an error; now it clears and the error explains what went wrong in one plain sentence.
Greeting previews stay on the right greeting. Removing or moving a greeting used to swap which one was in preview, and macro warnings could land on the wrong greeting; both now move with the greeting they belong to.
Lorebook entries open from the keyboard. The arrow on each entry is now a real button, so Tab and Enter open and close it.
Deleting a lorebook entry names it the way the list does. An entry with no title or keys used to be called "Entry 12", a number shown nowhere else; the dialog now uses the entry's name from the list.
The lorebook order box takes negative numbers. Typing "-" or clearing the box used to snap it to 0 straight away; the number is now saved when you leave the box or press Enter.
Escape in a small name or link box closes only that box. In Move to folder, pressing Escape in the "New folder name" box used to close the whole dialog and lose your selection, and the image link box in the card editor did the same; now only the box closes.
Per-row Delete buttons are quieter. Delete in Find duplicates and the trash button in Model groups are now red outlines instead of filled red buttons, and Detach in the chat's lorebook picker is now a plain button because detaching deletes nothing. Screen readers also now name the model group name box and the background Dim slider.
Bookmarks show how long ago they were made. Every bookmark used to say "just now"; each one now shows its real age, and the list works from the keyboard.
Deleting several cards at once now tidies up after them. Bulk delete used to leave the deleted cards counted under a lorebook's Characters; they now drop out, just as with a single delete, and a failed delete shows one plain sentence instead of a stack of raw errors.
The All chats list and a card's Chat menu work from the keyboard. Rows, "+ New chat" and the pin were mouse-only and Escape didn't close the menu; Tab and Enter now reach them, and Escape closes the menu.
Clicking the chat that's already open no longer reloads it. It used to stop a reply that was still being written and throw away a message edit you had open; now nothing happens.
Only the chat on screen shows its notices. Chats open in other tabs used to show their notices on top of the one you were reading, and some notices appeared once per open chat; now each chat shows its own when you are looking at it.
Deleting an earlier message keeps the edit you're typing. With a later message open in the editor, deleting an earlier one used to put the message's old text back, so saving lost your changes; your typed text now stays.
The full-screen message editor can send after a reply finishes. Opened while a reply was still being written, its Send button used to stay refused for as long as it was open; it now sends once the reply is done.
Switching chats no longer carries results into the new one. A list of models to switch to after an overload error, or a picture drawn for your last message, could arrive late and show up in the chat you had switched to; both now stay with the chat they belong to.
Error notices in chats read as one plain sentence. A failed background request used to show an internal label such as "sheet-sync failed", and a failed chat save showed two sentences plus a raw error; both are now one sentence.
Chat search results show messages as they were written. Snippets under "Found in messages" used to appear all lowercase and always ended in "…"; they now keep their capitals and only end in "…" when the text was cut.
You can edit the instructions while Impersonate or Continue with instructions is writing. The instructions box locked until the draft finished. It stays editable now, so the next try's instructions are ready the moment this one ends; only sending waits.
Card Forge's Tags field suggests the tags you already use. Typing a tag there only ever offered to add it as a new one, even when your library already had it, so the same tag could end up spelled two ways. It now suggests your existing tags as you type, like the card editor does.
Card Forge shows what a proposed change costs in tokens. Each proposed field or new entry shows its approximate token count beside its name, and a rewrite also shows how much it adds to or takes off the field as it is now, so you can see what accepting it does to the card's size. The count follows your edits if you change the text before accepting. The folded A new chat carries section also splits its total into permanent tokens, sent with every reply, and temporary ones, the greeting and dialogue examples that drop out as the chat grows, and hovering a row lists the fields in it with their share. A long run of app notes in the chat, like several Applied and Discarded lines in a row, folds to the oldest and newest with a Show more link between them.
Ask again in Card Forge now starts from your original request. The box under a proposed change opened empty, so a retry meant retyping what you had asked for. It now opens holding that request, or your last reworded one for that change: send it as it is for another try, or reword it first. An Edit with AI preset chip adds to the request instead of replacing it. The new version is written in the same row as you watch, with Stop there too, instead of in a second block under the proposal.
Card Forge no longer brings up changes you already turned down. Regenerating a reply sent the guide an earlier proposal in full, even one you had discarded, and the guide would ask about it ("that last discarded lorebook entry, was it the wrong shape?"). Earlier proposals were also kept in full as examples for the guide to copy. Now the guide only sees a short note of what it proposed and what you did with it.
Regenerating an older reply after restarting Rin Chat now puts the story's variables back correctly. Undoing a reply that had changed a story variable or a chat lorebook entry worked until you closed the app. After a restart, the undo put the old value into a new sheet stat instead, so the variable kept the reply's change and a stray stat appeared on the sheet. The undo now restores the right thing after a restart too.
A brief connection drop to the Rin Chat subscription no longer interrupts your chat. When the connection to Rin Chat's server dropped for a moment, a reply failed with "HTTP 522" after one quick retry. Rin Chat now waits it out quietly and retries up to three times. If a retry works, you see only the reply; the red "chat failed" notice that used to appear first is gone too.
Importing no longer waits on thumbnails that can never be made. A card's voice clips and fonts were counted as pictures still waiting for a thumbnail, so the Generating thumbnails step could count files it would never finish. Only pictures count now.
A server update no longer signs you out of your Rin Chat account. If the sign-in check hit a maintenance or outage page instead of the server, the app took that as a sign-out and asked you to sign in again. Now only the server's own refusal signs you out; anything else is retried in the background a few times over the next few minutes, even while you're away. A request that fails that way says it couldn't reach Rin Chat instead of saying you were signed out, and an outage on aicharactercards.com no longer marks that link as expired either.
Every part of the context bar has a color. Interactive elements, the Author's Note and lorebook entries drew as black gaps in the bar and its hover breakdown. Each now has a color of its own.
Model & generation shows only what you can change. With a Rin Chat subscription config, the window also asked Fast, Balanced or Smart, which the config you picked had already decided, and showed a grayed-out reasoning effort on the presets Rin Chat keeps up to date. Both are gone; duplicate a preset to change its settings.
A stat check no longer looks like it counted the bonus twice. A check named after its own stat read "Wits (wits +2) check" on the dice card, which next to "4 + 2 = 6 + 2 = 8" looked like the +2 was added twice. The math was always right; the card now reads "Wits (+2) check".
The card editor's section list no longer loses its first letter. On a window just wide enough to show the list beside the card, it sat a few pixels past the window's edge and its header read "ECTIONS". It now moves beside the card only when there is room for all of it.
The app tour's box always fits in the window. At a raised UI scale on Linux, a step that pointed at something low on the screen could open its box partly below the window, out of reach of Next and Skip tour, however the window was resized. The box is now placed inside the space the window really has, moves back inside when the window is resized, and is never taller than the window: a long step scrolls inside the box, with its buttons always showing. Esc still leaves the tour at any step.
Rin Chat Update Notes - Version: 1.0.3
18 November 2026
This is a big one. The developer posted a personal note about what changed and why in the #rin-chat-updates channel on the Rin Chat Discord. Give it a read before you dig in.
🎲 Adventure Mode
Editing a stat on the character sheet no longer deletes it halfway through. Clearing a value to retype it used to remove the whole row the moment the box was empty. Now a change saves when you press Enter or click away, Escape puts the old value back, and on a number you can type +3 or -3 to add or subtract, or =-1 to set it outright. A negative number typed into any stat also used to turn into 0; now only health, stats with a maximum and progress clocks stop at 0, the same rule the game master's changes follow, so a PbtA cool can sit at -1.
The character sheet now looks like your game's sheet. It used to be one flat list in lowercase, with die scores as bare numbers. In a game with its own sheet, like Cortex, abilities now sit under the game's own groups, in its order and spelling, and dice show as d12. Stats the game doesn't name follow underneath, and vitals stay above.
Adventure sheets now handle negative hp, undone clock reveals and misspelled roll stats. Setting hp, a capped stat or a clock below 0 used to store the negative number, so soft revive and hard-mode death never fired; it now stops at 0, while stats that really go negative, like a PbtA -1, keep their value. Undoing a reply that revealed a hidden clock used to lose the game master's clock; it now comes back. A roll whose
modorbonusnamed a stat the sheet does not have used to roll without the modifier and say nothing; the roll report now names the missing stat.Leveling up now follows your game's own sheet. In a die-scale game a point turned a d8 into a "9", every game capped scores at 18, and games without HP were still promised extra max HP. Now a point steps a die up one size, to d12 at most, point-buy and dealt scores stop at their game's limit, scores show as dice, and the HP line only appears when the game has HP.
The Roll button now shows what you need to roll. The target used to appear only when you hovered over the button, so it never showed on a phone, and it always said "DC" even in a Fate or roll-under game. The button now shows it directly, as DC 13, target 3 or under 65, and a game whose skills roll under a number now really counts a roll at or under that number as a success.
Dice can explode now. Add
!after a die, as in[[roll: 1d6! vs 4 | Fight]]or2d10!, and every time it lands on its highest face it rolls again and adds, which is Savage Worlds acing and World of Darkness 10-again. The roll shows each step, like6!+6!+2 = 14, an ace counts as a max roll on the dice record, and{{roll::1d6!}}works the same way in cards.The combat bar now shows your own health, and cards can add their own meters. During a fight the turn order used to show health for everyone except you; your hp bar now sits at the top of the list. Card creators can give a stat named
meter_<name>a matchingmeter_<name>_max, and it shows as a labeled bar under the reply the whole time: affection, sanity, heat, anything that fills up. The dice record's "Nat 20 · Nat 1" row now reads "Max roll · Rolled 1", because it counts a top-face roll on any single die from d6 up, not just a d20.Loading a saved character now respects the game you're in. The saved-character list shows the ones made for this game first, then the rest under "Other games". Pick one from another game and it keeps its name, role, story, notes and portrait, but its abilities start fresh with this game's own, instead of bringing Strength 14 into a Cortex game.
Roll buttons stay put after a picture. A picture the character drew under a reply used to remove that reply's Roll, character and generator buttons, its combat tracker and its choice timer, and stop its document animations. They now stay with the reply until the story actually moves on.
Choice costs and generators follow the sheet's rules. A choice cost could raise an ability score the game master is not allowed to change, and stat changes from a generator skipped reviving at zero health and leveling up. Both now follow the same rules as the game master's replies.
💬 Chat
Choices can now carry a tone. Add
| tone danger,| tone good,| tone warnor| tone quietto a choice and its button gets a red, green, amber or muted edge and arrow, so a risky option looks risky before anyone clicks it. It follows your theme colors, and an unknown tone word is simply ignored.Choices can stop offering themselves once they're done. Add
| onceto a choice that sets something, as in[[choice: Take the ember shard | set shard_ember = true | once]], and it disappears as soon as everything it sets is already true, so the story stops offering the kiln after the shard is taken. Adding to or taking from a number, likegold -= 5, doesn't count, so a shop choice can still be bought again.Choice conditions can be grouped. Wrap part of a condition in brackets to decide what goes together, as in
[[choice: Bribe the guard | if has_coin && (charm >= 3 || knows_name)]], and put!in front of a group to mean "not all of this", as in| if !(guard_awake || alarm). A bracket left open locks the choice instead of guessing, and conditions without brackets work exactly as before.Story variables can hold a list now. A choice or the story can write
inventory += ropeto add rope to a list andinventory -= ropeto take it out, and| if inventory has ropechecks for that exact item. Before, writing a word this way did nothing, andcontainsalso matched "keycard" when you asked about "key";containsstill works that way when you want it.Pick a choice with the number keys. When you're not typing in a box, press 1 to 9 to pick that choice in the newest reply, the same as clicking it. Locked and hidden choices are skipped, and small numbers show on the buttons while you use the keyboard. Nothing happens if your message box has text in it.
Choices that share a name, and choices a card's display script draws, now work. Two choices with the same label but different conditions used to run the first one, so clicking the one you could see checked the wrong condition and silently did nothing, and choices drawn by a display regex script were dead buttons. Each button now runs its own line. On a phone or tablet, holding a choice opens the same menu right-click does, so "Act it out" and "with directions" are reachable there too.
Story changes the model dresses up now count. When a reply wrote
[[set: has_key = true]]in bold, as a bullet, ending in a period, or tacked onto the end of a sentence, the change was never saved and the raw line showed in the chat. Now those are saved and hidden like a plain one, and the sentence keeps its period; one in code formatting at the end of a sentence is an example, so it stays as text. Choices can also sit inside a reveal without its closing[[/reveal]]showing as text, and screen readers announce the question on ask boxes and pick lists.Lore marks the model dresses up are now saved. A
[[lore: Mira | ...]]written in bold, as a bullet, ending in a period, or tacked onto the end of a sentence was never saved, and the raw mark showed in the chat. Now it is saved to the chat's lorebook and hidden like a plain mark; one in the middle of a sentence, or in code formatting at the end of one, is left alone.A timed choice waits while you answer a question in the reply. The countdown used to keep running while you typed into an ask or form in the same reply; it now pauses while one of those boxes has focus or has something in it. A regenerated reply's timed choice also starts its countdown now, where before it never ran.
Clicking Roll, a choice or a generator keeps what you were typing. Any of these clicks used to erase the message you had half written in the box; now the draft and any pictures attached to it stay where they were.
Tab no longer stops on old replies' choices and widgets. Choices and ask, pick and form boxes in earlier replies were grayed out but still took focus, so Tab walked through every dead button in the history and Enter did nothing. They're now skipped until the reply is the live one again, and screen readers still read them as part of the history.
Choices marked
| hidestay hidden. A choice written with| if has_key | hideshowed grayed out with its lock instead of staying out of sight until it was available. Now it stays hidden until then.A locked timed choice no longer stalls the countdown. A reply's countdown always followed its first timed choice, even one that was locked or hidden and could never be sent. It now times the first one you can actually pick.
Auto-continue stops at a choice on every card. When a reply was cut off right after its choices, an ask, a pick or a form, auto-continue kept writing on ordinary cards and played on past the decision. It now stops there on every card, card menus included.
Continue keeps a story change at the cut. A reply cut off right after a
[[set:]]line or the end of a document used to have the rest glued onto that line, so the change was lost and the raw line showed. Continue and auto-continue now start the rest on a new line.
📄 Document styles
Document styles have their own page, with folders. They moved out of Settings to a Document styles tab in the Library, next to Lorebooks and Generators. Each of your styles is a tile with a live sample and Edit, Duplicate, Export and Delete buttons, and the built-in styles are listed below them to duplicate. The folder sidebar sorts your styles the same way as lorebooks: drag a tile onto a folder, or use the folder button on its corner on a phone. A folder only sorts the page, so a style works the same wherever it is filed. The phone has it too, under More.
Describe a document style and let the AI design it. The Document styles tab has a "Design one with AI" box. Type what you want, like "a green CRT terminal for ship logs", and Card Forge opens a style session where the guide writes it with your model. Keep asking for changes in the same thread, and the finished style shows up in your list.
Document styles can tell the model when to use them, and fill their own fields. The model used to learn only a style's name, so it had to guess what a style was for. A style's use note now reaches it beside the name, along with any fields the style asks for. A
{{field:reward}}in a style's HTML is filled from aReward: ...line at the top of the block, and that line drops out of the text. A document note also no longer reads "In ," when none of your styles draws message lines.Document style fields fill from natural names and can have defaults. A field named
due_dateused to ignore a "Due date: Friday" line, so it stayed blank; spaces, dashes and underscores now count as the same, and "Due date:", "Due-date:" and "due_date:" all fill it. A field can also carry a default, as in{{field:reward|Unknown}}, which shows when the block has no Reward line or an empty one.The document style editor is now a workbench. You can type your own sample title and text into the preview, switch it between light and dark, narrow it to phone width, and see a short list of any CSS the chat will skip, such as nested rules,
@layeror a selector that reaches outside the block. Remove now asks first, a warning shows when two of your styles share a name (only the first one is ever used), and a new optional box tells the AI when to use the style.Check a document style in light, dark and on a phone before you keep it. Every style preview, in the style editor and under each change Card Forge proposes, has Theme and Width buttons above it. Current shows your own theme; Light and Dark show the style as someone on the other theme sees it, without changing yours. Phone narrows it to the width a chat has on a phone, framed so you can tell. The sample now sits in a reply bubble on the chat background, the way a reader sees it, and your choice stays for the next proposal and the next time you open the app. Proposals that revise the same style each show their own CSS now, instead of mixing in the newest proposal's.
Document styles now come with starters. The Document styles tab and the card editor have an "Add a starter" list with eight ready-made styles: a notice board, a letter, a status window that follows your theme colors, a quest log that changes color for new, finished and failed quests, a chat log, an animated alert, an achievement banner with a gold, silver or bronze medal and a reward box, and an item card colored by rarity, from common to legendary. The last two fill in from "Tier:", "Reward:", "Rarity:" and "Type:" lines the AI writes at the top of the block, so they double as working examples of style fields. Each one adds an ordinary copy you can edit, and it doesn't reach the model until you add it.
Six new built-in document styles. Alongside paper, newspaper, terminal and sms, every chat now has a diary page on ruled paper, an email with sender and recipient, a social media thread where each line is a post, a classified case file with a rubber stamp and blacked-out redactions, an incoming comm transmission with a scanline sweep, and a tarot card that can be drawn reversed. Each one tells the AI when it fits, so a found journal or a radio call shows up as the real thing without any setup, and each reads the same in a light or dark theme and on a phone. They're also worked examples: duplicate one to see how it's built and make it your own.
Six more built-in document styles, animated. A stream chat where every chatter keeps their own name color and badges and new messages slide up from the bottom, a full phone with the status bar, Dynamic Island, blue and gray bubbles with tails, Delivered or Read under your last message and a typing bubble while they owe you a reply, a split-flap departure board whose title flips into place, a radar scope whose sweep lights up each contact as it passes, a neon sign that stutters on and flickers, and an old TV broadcast with scanlines, grain and a glitching headline. Each one tells the AI when it fits, holds still with a finished look when your device asks for reduced motion, and only moves while it's the newest message.
Fourteen more built-in document styles. A spellbook whose cover swings open onto the spell, a hacked terminal over falling code rain, a retro RPG text box with a pixel portrait and typed-out lines, a vinyl record sliding out of its sleeve, a turning hologram data cube, a ransom note cut letter by letter from magazines, a bubbling potion flask, a place name under drifting northern lights, a stock screen that rallies or crashes with the price, a heart monitor that beats at the patient's real heart rate and flatlines on cue, a cursed scroll burning from the bottom, a sealed envelope the player clicks to break the seal and read, a spirit board whose planchette glides to yes, no or goodbye, and a boss entrance with an HP bar. Each one tells the AI when it fits, fits a phone and a wide window, looks finished when it holds still, and rests after a few rounds wherever motion would keep the computer busy.
Eleven built-in document styles change shape between a phone and a wide window. On a desktop the email lays out like a mail client, with Reply and Forward and the From and To fields side by side; the stream chat becomes a player beside its chat; the departure board grows and shows every field as a row of flap tiles; the phone grows to a real phone's size instead of a small one in a wide column; the diary and case file become full pages; the radar scope and comm waveform scale up; and the terminal, text messages and social thread use the room. On a phone each one tightens its margins so more of the text fits, and the radar sits beside its readings. The comm transmission also gained a voice waveform.
The built-in document styles look better on a phone and in a wide window. Paper has a soft page and styled lists and quotes, the newspaper's headline grows with the window and opens on a drop cap, the terminal has a title bar and a blinking cursor, and the gray bubbles in sms stand out in a dark theme. The tarot card and radar scope center themselves on a phone, the departure board's rows span the full board, the neon sign and broadcast headline grow on a wide screen, and styles that used Windows-only fonts now pick a matching font on macOS, Linux and Android. The notes that tell the AI when each style fits are shorter, so having thirty costs less than it would have.
Every document style previews with text that fits it. Previews used to show the same road-closed notice in every style, so a case file, an email and a stream chat all looked alike in the library. A style can now carry its own sample title and text, edited in the Sample boxes under the editor's preview, and every preview of it uses them: library tiles, the editor, a card's styles and the import offer. The built-in styles all have one, a sample travels with the style in files, bundles and cards, and it is never sent to the AI. Card Forge writes a sample with every style it designs, so its proposals preview the way the style is meant to be used.
Document styles can move between cards and computers. In a card's Document styles, "Add one of yours" copies one of your own styles into the card, so everyone you share it with sees it styled instead of as a plain box. A style can be exported as a
.jsonfile and imported into your Document styles or a card, and a name that's already taken gets a-copyname. A style's note for the AI travels with it, in a file or an.aiccbundle.Importing a card offers to save its document styles. When a card or bundle you import comes with its own document styles, the library shows a sample of each one and asks whether to save a copy to your styles, so you can use it with other cards. A card that also brings generators asks about both at once. Save styles one at a time or all at once, or skip them; the card keeps its own copy either way. A style you already have exactly isn't offered, and one whose name is taken is saved under a new name instead of replacing yours.
A card can link one of your document styles, and save its own to your library. In a card's Document styles, "Link from library" shows a sample of each of your styles, and the one you pick stays in step: edit it on the Document styles tab and the card's chats and exports use the new version. A linked style is marked Linked and edited in your library; Unlink makes it the card's own copy again. The card keeps a copy, so it still works if the style is deleted or the card is opened on another computer, where it offers Relink. Anyone you share the card with gets an ordinary copy. "Save to library" does the reverse, saving a copy of one of the card's styles to your own under a new name when the name is taken.
Document styles are sturdier and lighter to edit. An animation named
title-glowin a style that also hadglowwas pointed at the wrong keyframes, an apostrophe in a title could break out of a single-quoted attribute, and sms lines written as**Kisa:** hishowed stray asterisks and put**You:**on the wrong side. All three work now, and typing in the style editor no longer re-renders every open chat on each keystroke: a CSS-only change restyles in place.Document styles can fit the space they're in. A style can now ask how wide its own block is, so it can lay itself out one way on a phone, another in a side-by-side or pop-out window and another in a wide chat:
@container doc (max-width: 420px)and thecqiunit measure the block, not the window. A reply holding only a short document now shows it at its full width instead of squeezed around its text.Document styles can use SVG filters and animated custom properties. A style's HTML can carry a small SVG of filters, such as turbulence for a burned edge or a blur for a gooey liquid, and its CSS applies one with
filter: url(#burn). Each block gets its own copy, and everything else an SVG could do, like loading pictures, linking or running scripts, is still removed.@propertyworks now too, so a gradient's angle or color can animate smoothly, and its name stays private to the style, like an animation's.Built-in document styles open to read, sorted by kind, and previews can replay. Clicking a built-in on the Document styles tab used to duplicate it on the spot; it now opens the style read-only, so you can read its HTML, CSS and use note and try it in the preview before you keep a copy, and Duplicate sits in its header. The built-ins are grouped into paper and print, messages, screens, fantasy, games, and signs and scenes, and a search still narrows each group. Every style preview has a Replay button that plays its animations again from the start; when motion is off on your device, it says so instead. The header of a document style, lorebook or generator you're editing is now a bar that stays at the top while you scroll, with the name taking the free room and the buttons beside it.
A card's AI now hears only about the document styles that card uses. Every turn of a card with documents used to describe all thirty-one built-ins and every style in your library to the model, about 1,500 tokens whether the card used them or not. Now the model is told about the card's own styles, the ones linked to it, and any style its greeting, description, examples, lorebook or prompts already write in a
[[doc: name]]block, so existing cards keep working: a card with two styles of its own costs about 130 tokens, and one whose greeting uses the newspaper about 100. To give a card one of the built-ins, use "Link from library" in its Document styles, which now lists the built-ins too: the card follows the built-in, marks it Built-in and linked, and exports it as an ordinary copy. Any built-in still draws when a reply uses it.The Document styles tab opens quickly. It used to draw the sample of every style at once, yours and the built-ins together, and keep all of their animations running, so the tab took most of a second to appear and kept the computer busy while it was open. A sample now draws as you scroll near it, and one that is off screen holds still until you scroll back. The card editor's "Link from library" list and the import offer work the same way.
✏️ Card editor
Cards can carry their own menus. Write a shop, a list of places to travel or a "talk to" list once in the card editor's new Menus section, and the AI offers it by writing
[[menu: shop]]: the chat shows your choice lines exactly as written, with their conditions, costs, tones and timers, instead of the AI retyping them every turn and getting them a little wrong each time. One "talk to" menu can serve every character: write{{arg}}in its lines and the AI offers it as[[menu: talk | Mira]], which fills in Mira. Each menu also has an optional "When the AI should offer it" box, so the AI knows the shop is for when the player is in a store. The phone's reply suggestions leave out what a menu already offers.Menus come with starters. In the card editor's Menus section, "Add a starter" adds a ready-made shop, travel or talk menu: costs, a one-time purchase, a locked route with its hint, and a talk menu that fills in whoever you're speaking to. Each comes with a note telling the AI when to offer it. Next to each menu, the editor now shows exactly how the AI calls it,
[[menu: talk | <name>]]included.Cards can give you buttons that stay above the message box. A card's new Action bar holds choice lines like "Look around" or "Check my bag | if has_bag", and they sit above the message box for the whole chat. They follow the same rules as choices in a reply, so a locked one opens as soon as the story sets what it needs, an insert button fills your message box instead of sending, and a card menu can go in the bar too.
Cards can show a live status panel above the message box. Write it once in the card editor's new Status panel section: health bars, hunger, gold or a styled status window redraw whenever a variable changes, and the AI never sees it.
The card editor now helps you write choices, rolls and the rest. Type
[[in a greeting, example dialogue, system prompt, lorebook entry or the Playground and a menu lists every interactive line Rin Chat understands: choices with their set, lock, hide, once, ask, insert, timer and tone options, ask, pick, form, reveal, documents, bars, set (with+=for lists), lore, roll, stat and the card's own menus. Each one has a short note on what it does. Keep typing to narrow the list; pick one and it drops in ready to fill, with the cursor on the first blank.The Playground can test choice conditions. In the Inspector's Playground, set "As" to the character's reply and type test values like
gold = 3, has_key = trueinto the new Test variables box. The "Shown in chat" side then locks, hides and opens each choice as a chat with those values would, with its hint, tone and| once, so you can check a shop or a locked door without playing up to it. Nothing is saved, and macros like{{getvar::gold}}still show the chat's real values.The health check stops flagging variables a pick or an ask choice saves, and points out greeting lines that won't work. A card that read
{{getvar::weapon}}after[[pick: Sword | Bow | as weapon]], or after a choice with| ask … | as guess, was told nothing sets it; those count now, and a[[bar:]]naming a variable counts as reading it. A greeting line that can never draw also gets a warning that says why: a pick with one option, a form with no fields, an ask with a bad variable name, a roll with dice Rin Chat can't roll, or an empty choice.The health check now catches styles, tones and pictures that quietly don't work. A greeting's
[[doc: name]]naming a style that isn't built in or in the card's Document styles gets a warning, because it would only draw a plain box. If the style lives only in your own styles, you get a tip to add it to the card, since everyone you share the card with would see a plain box. A choice's| toneword that isn't danger, good, warn or quiet, and an| imgname the card has no picture for, are now pointed out instead of being ignored.
🛠️ Card Forge
Card Forge designs document styles that fit a phone and a wide window, and checks that they do. The guide now knows how wide a document is on a phone and on a desktop and lays a style out to fit both, and it can use the new container queries, SVG filters and animated properties. Each style it proposes is measured at phone and desktop width, and one that runs past the edge or cuts its text off says so under the preview, as in "Overflows at phone width by 46px". A Fix for phone button asks the guide to repair it with those numbers; it only asks when you click.
Start a lorebook, generator or document style in Card Forge from its own tab. The Lorebooks, Generators and Document styles tabs in the Library now have the same wand button as Characters. It opens a new Card Forge session that makes one of those, ready for you to describe it, and nothing is sent until you do.
A new lorebook, generator or style no longer stops saving when you come back to its session. Starting one, chatting before anything was saved, then reopening the session later said it was "no longer in your library" and refused to save anything after that. It now picks up where you left off, and the first change saves it.
Styles written in Card Forge keep all of their HTML and CSS. The Forge used to cut a style's layout and CSS at the first line break, and kept names like
Dcc_Lootthat[[doc: name]]could never call. A style's full HTML and CSS now come through intact, names become valid lowercase-and-dash names of up to 30 characters, and editing a style no longer drops settings the Forge doesn't show.Card Forge shows your document style while you work on it. A style session's sidebar now holds the whole style, its name, note for the AI, HTML and CSS, editable in place with the same preview as the Document styles tab. Each change the guide proposes is also drawn in the chat right under the proposal, so you see what it looks like before you accept it.
📚 Library
One Library, with tabs. Characters, Lorebooks, Generators, Document styles and My listings now open from one Library button, as tabs along the top, instead of separate entries in the header and its menu. Every tab is laid out like Characters: folders in the sidebar, search, sort and a grid or list switch along the top, and the same tiles with Edit up front. Each tab keeps its folder, search and sort while you switch, and the Library reopens on the tab you used last. My listings shows once an aicharactercards.com account is linked. F3, F4 and F5 still open Characters, Lorebooks and Generators, and on a phone the Lorebooks and Document styles entries under More open the same tabs, with Generators beside them.
Lorebooks and generators can go in folders. The Lorebooks and Generators tabs have a folder sidebar, like Characters: make folders and subfolders, rename or delete them, and drag a lorebook or generator onto one. Each tile also has a folder button on its corner, which is how you move one from a phone. Everything you already have starts at the top level, deleting a folder never deletes what's in it, and a folder only sorts the page, so books and generators work exactly as before.
Choose where a card's Display name shows. A card's Display name replaced its Name in the library and on every chat message, so a label like "Fantasy - Mira" that sorts your library also showed on each reply. Three new settings in Settings → Chat Display → Character names pick Display name or Name for the library, the chat, and the file name of an export. By default the library and the whole chat, title and tabs included, show the Display name, and exports, bundles included, are named after the Name. The model always gets the Name, and an exported card keeps both names whatever its file is called. The phone follows the same choices.
My listings looks like the rest of the library. Your posted cards now show as tiles with their art, grouped by where they stand, with the same buttons as before.
Card Forge, Image Studio, Story Maker and Direct Chat are now tabs under one Tools button. They used to be separate entries in the header and its menu. Tools opens on the tool you used last, and resting the pointer on it lists the four so you can jump straight to one. Each tool now keeps going while you're somewhere else: a Direct Chat reply keeps streaming, an Image Studio render keeps rendering, a Story Maker draft and your Card Forge sessions stay as you left them, and a half-typed message is still there when you come back. Image Studio shows once an image provider is set up, as before. If any of the four was pinned to your header, Tools is pinned in its place, and your other header choices stay as they were.
The Library and Tools menus wait for you. Resting the pointer on Library, Tools or the remote access icon opens its menu after a moment instead of the instant the pointer touches it, so heading for the button to click it no longer drops a menu in the way, and the menu stays open while you move down to it. The remote access menu now says whether remote access is on and how many devices are connected at the top, where a tooltip used to cover the menu, and its items no longer wrap onto several lines.
📱 Remote access
Scan a QR code to open Rin Chat on your phone. Each address your phone can use now has a QR code under it in Settings → Remote access, so there is nothing to type.
The
localhostaddress no longer looks like the one to use. It sat between the others with the same "open this on the other device" hint, but on a phonelocalhostis the phone itself, so it never connected. It now comes last and says it only works on this computer.A Tailscale address that connects after Rin Chat started now shows up. The address list was only read when serving started, so connecting Tailscale afterward added nothing, and reopening Settings didn't help. Settings → Remote access now notices a new address and offers Restart serving to add it.
🤖 Discord bot
- Card menus now show on Discord. A reply that offers a menu, like
[[menu: shop]], lists that menu's choices in Discord the same way it lists any other choices.
🔌 Providers
- Z.AI is a built-in provider, with three free models. Pick Z.AI as the Type under Settings → LLM Providers and paste a Standard API key from z.ai. GLM-4.7-Flash, GLM-4.5-Flash and GLM-4.6V-Flash cost nothing to use and show up marked Free in the model list, even though Z.AI's own list leaves them out. A new Z.AI config starts on GLM-4.7-Flash with its context size, a reply length with room for its thinking, and Z.AI's recommended temperature. Z.AI lets an account run only one request at a time on GLM-4.7-Flash and GLM-4.6V-Flash, and two on GLM-4.5-Flash, so a summary or title on the same model now waits for your reply instead of failing, and a "busy" answer from Z.AI is retried quietly a few times. The Guide's new Free models on Z.AI section walks through signing up and which model to use for what.
⚙️ Settings
Choose whether animations play. Rin Chat followed your system's reduce motion setting with no way around it, so on a computer that turns it on, such as one used over Remote Desktop, every animation was off, the app's own and those in document styles. The new Motion setting in Settings → Sizing & Layout keeps Match system as the default and adds Always reduce and Always animate. Each device keeps its own choice, so a phone on Remote access can differ from the computer.
UI scale works on Linux. In the Linux AppImage at any UI scale but 100%, menus could open away from where you clicked or partly off screen, tooltips sat in the wrong place, and dragging to resize a panel or move an image in the cropper ran ahead of the pointer. The AppImage's web engine measures zoomed pages differently from other systems, and Rin Chat now accounts for it.
📖 Guide
- Every example in the Guide has a Copy button. Paste a
[[form:]], a menu or a document style straight into your card instead of retyping it.
Rin Chat Update Notes - Version: 1.0.2
17 November 2026
💬 Chat
- Find in chat can replace too, across the whole chat. Press Ctrl+F, then the Replace toggle: Replace changes the highlighted match and moves to the next, and Replace all changes every match in one go, with Undo on the bar to put it all back. Find now also reads thinking, hidden text and the words on choice buttons, forms, rolls, reveals and documents, and counts matches in Adventure Mode's DM stats, the player character, the party, the chat's own lorebook, memory and the Author's Note. Replace all covers all of those and every swipe, says where the matches were, and renames a stat named after the old word (
odette_hptomaisey_hp) everywhere the chat refers to it. Directive and tag names, options, generator and picture names, macros and the card itself are never changed, and it is off while a reply is being written.
🧩 Regex scripts and macros
- Global variables can be shared across all your chats. Cards that use
{{$name}}or{{getglobalvar}}keep those values per chat by default, as before. Settings, Macros & Regex now has Scope of global variables: pick Shared across all chats and every chat reads and writes one list, the way SillyTavern does. A shared value is written once, when the message that sets it first appears, so a swipe, regenerate or rewind never undoes it, and replaying the chat never adds to a counter twice.
🛠️ Card Forge
You can pick the Card type before the character is built. A new Card Forge session shows Card type (Character, User Persona, Adventure Mode Game Master) above "No card yet", so a game or narrator card no longer has to be asked for in words to avoid coming back as a personified character. The guide brainstorms with that choice in mind, and Build character sets the type. Character forces nothing, so asking for Adventure Mode in the chat still works as before.
Card Forge can now see and change every field of the card, not just the character. The system prompt, post-history instructions, depth prompt (with its depth and role), group-only greetings, display name, creator, version, tags, creator notes, the image prompt prefixes, spoiler mode, the lorebook's name, regex scripts, document styles and what each picture shows are in the sidebar under the card editor's own sections, and the guide can propose changes to any of them, in both engines, reviewed and undone like any other change. A build may also write a system prompt, tags and the image prefixes; the rest are changed only when you ask for them by name, and All fields in Edit character leaves them unticked. The guide can add, change or remove regex scripts and document styles, and a script whose pattern is not a valid regular expression is flagged and never saved. Images themselves, the card type, verbosity, the Adventure Mode game master layers, the character sheet and voices stay in the card editor, and the guide says so when asked.
The guide's comment after it builds a character costs about half as much. That short reply used to send the whole new card to the model twice; it now sends it once.
Brainstorming before there is a character no longer makes a hidden extra call or a "contained none" note. When the guide said something like "Here are three ideas for her backstory" with no card yet, the app asked it again for an edit it could not have applied, then told you nothing had been proposed. Once a card exists, that check works as before.
Apply on a proposal in the chat now gets the same checks as Review. Before, the format checks and their safe fixes (the character's literal name swapped for
{{char}}, a stray speaker label removed) ran only when you opened Review, so Apply in the message put the text in as written. Now the message shows the fixed text, and a field with a real problem, such as a rewrite that dropped most of the detail, starts unticked with the reason beside it. Tick it to apply it anyway; the transcript note names any field that was left out.Proposals that are the AI talking instead of the text are caught before they reach the card. A field that comes back as a refusal ("I'm sorry, I can't write that") or wrapped in chat ("Sure! Here is the new greeting:", "Let me know if you want changes") now starts unticked with the reason, in the message and in Review. A line the character says in quotes is never flagged. A greeting that decides what you do or feel ("You blush and look away") gets a note, and stays ticked.
Edit selection with AI in Card Forge uses the session's provider and model. It used to run on the app's active provider, whatever the session was set to. The card editor's Edit with AI is unchanged.
You can read a proposed change while the guide is still writing it. The new text of each field appears under the reply as it arrives, instead of showing up only once the reply is finished. The same goes for the sidebar's Improve and Edit fields, which used to show only a status line. You still review it as before once it is done.
The grade button shows what the app can find on its own, for free. After every change, Card Forge checks the card without asking a model: empty fields, the character's literal name where
{{char}}belongs, a greeting that decides what you do or feel, and the other format checks proposals already get. The grade button shows how many it found, and opens them as Card checks, each with Fix. Grade with AI is still there for a score, and a card that was already graded opens its grade as before.Generate character is now called Build character, and Regenerate character is Rebuild character. They do exactly what they did.
/buildworks as well as/create, and the guide is told about the new names, including a guide you duplicated whose own instructions still say Generate character.Two new ways to start from the "+" beside the forge tabs. Open a card from my library picks a card and opens it in the Forge, or goes to its tab if it is already open. Build from one line takes a sentence about the character and builds it straight away in a new tab.
A new Card Forge engine you can try, in Settings > Card Forge. With Card Forge engine set to New, Improve, Edit character, a smart command that runs and Fix on a grade finding are written by a separate call that is sent only the parts of the card it needs and none of the guide's own personality, so it is much smaller and answers with just the text. When the model refuses, answers in the wrong shape or runs out of length, the forge says so and offers Ask again, Continue and Change model. Classic stays the default and works exactly as before.
Every proposed change is in the Card Forge chat, and each field can be answered on its own. Whatever asked for it (a reply, Edit character, a field's Improve, Fix on a grade finding, Make this a change, Rebuild character), the proposal shows in the reply that made it, or at the end of the conversation when it came from a button, and the chat scrolls to it. Each field reads in place with Compare, which opens the current and proposed text side by side with the changed words marked (View for a new entry), Edit to change the wording, and Accept, Reject or Ask again for that field alone, in the row or from the Compare window. Ask again lets you say what should change first, or pick one of your Edit with AI presets; send it empty to simply try again; Apply all takes every field with no flagged problem. Asking again keeps the earlier try as a version you can step back to ("1 of 2"), and so does a second proposal for a field that already has one waiting. A field with a change waiting says so in the sidebar; click it to go to the proposal. Improve and Edit character no longer pop the review window over your work. It still opens by itself for Rebuild character, lorebook entries and generators.
A change that fails or is stopped says so in the chat. The row says why in one sentence with Ask again, and Continue for a reply cut off at its length limit.
With the New Card Forge engine, the guide decides what to change and the writer writes it, in chat too. The guide's reply ends with the fields to change and what to do, instead of the whole new text, so replies are shorter and the guide's prompt is much smaller. Unless your message only asked a question, or the guide's reply is still asking you something, the change starts right away, however you worded it: the reply shows one line saying what is being changed, the new text is written under it with Stop, and the proposal lands in that reply for your Accept, Reject or Ask again. Nothing is put on the card until you accept it. The line always says what really happened (working, proposed, not written, stopped), and if the writing fails the guide is told so too. A change the guide volunteers shows as Suggested with Write it, and saying yes to it in any language runs it too. Clicking one of the guide's choice buttons runs a change only when the button names that change; answering a brainstorming question never does. Building the whole card never starts by itself: the guide offers it as a Build the card button, and it runs when you press that, Build character, or type
/build. When the guide names a greeting or lorebook entry the card does not have, the forge asks which one you meant instead of guessing. A model that still writes a proposal the old way gets a proposal as before. Smart commands are not used by the New engine, so their settings are hidden while it is on.Card Forge catches more of the usual card problems on its own. A greeting that says what you will feel or have decided ("You'll feel her eyes on you", "You've decided to stay") is now flagged like one that says what you do, while a character acting on you ("she grabs your wrist") is still fine. Card checks now notice the same long passage pasted into several fields. A new or rewritten lorebook entry says when one of its keywords is already on another entry, so both would fire together. The guide is also told up front that a greeting never speaks or acts for you, and is asked for example dialogue where the character refuses or disagrees and one where the mood shifts.
The Card Forge guide asks one question at a time when it gives you buttons. It used to ask three things in one reply and offer buttons that answered only the last. Now the buttons sit right under the one question they answer, and the next question comes after you reply.
The Card Forge guide can ask with a text box, a tick list or a form, as a chat can. When it needs a name or your own idea it gives you a box to type in, and when it needs several answers before it can go on it asks them all in one small form instead of a string of questions. They work on the newest reply only, and what you fill in is sent as your next message, each question with its answer. Answering is never taken as a request to change or build the card.
When the Card Forge guide lists several questions in plain text, you get a form to answer them anyway. It draws one box per question under the newest reply, every box optional, and sends your answers the way its own forms do. The guide is also reminded of this every turn, so it happens less often.
Every guide reply in Card Forge has a Make this a change action. It opens Edit character with the fields the reply and your last message mention already ticked and the reply as the instruction, so when the guide describes a change without proposing it, one click turns it into one, in any language. It is hidden in Draft only and before there is a character.
A proposal you have not answered survives closing the app. It used to come back as "Proposed, never applied" with no way to accept it; it now comes back live, with its Apply and Review buttons.
Card Forge is tidier and easier to follow. The sidebar folds into the same sections as the card editor, session settings and the token split included, each remembered per session; field list buttons show on hover; Send stands alone and Edit character moves to the preset row; the guide's name reads cleanly over its replies; a field's name in a proposal opens and jumps to that field in the card, and Apply highlights what it changed.
📚 Lorebooks
Importing a lorebook you already have asks first, the way importing a character does. A file whose name matches one of your shared lorebooks (ignoring case and spaces at the ends) no longer quietly lands as a second copy. With the same entries, it is skipped as already in your library. With different entries, it is listed with Replace, New or Skip, plus Replace all, New for all and Skip all. Replace puts the imported entries into your existing lorebook, so every character, chat and Global setting that uses it keeps using it; New adds it beside yours as "Name (2)". Replace can't be undone, and the list says so. If that lorebook is open in its editor or in a Card Forge session, the open copy is reloaded instead of being saved back over the import. This works on the phone and over remote access too, and
.aiccbundles use the same name rule.Click an underlined lorebook word to see its entry. It opens Session info on the Lorebook tab, scrolled to the entry that word triggered and briefly highlighted. If the entry is not in the next prompt, for example because the lorebook budget left it out, the tab opens without a highlight. Selecting text across the word still just selects it. On the phone, tapping the word now does this too instead of showing the entry's name.
🖼️ Images
The character can send a picture of its own in a chat. Switch on Character can send pictures in Settings > Images (it appears once you have an image provider) and, when the scene calls for it, a reply can come with a newly drawn picture under it, in the character's look, the way a picture you ask for does. At most one per reply, with Wait between pictures (60 seconds by default, 0 for no wait) setting how often; one that comes too soon shows Picture skipped under the reply, with Draw it to draw it anyway. It is off by default, because each picture costs a generation.
Auto-prompt from card can take directions. Shift-click it in the card art generator to say what the picture should show ("at a cafe at night, rain on the window, close-up"); the prompt is still written from the card, with your directions first.
📱 Phone
Press and hold a character in the Characters tab for its options. Start chat, View character, Edit character, Add to favorites, and Delete character. Delete asks first, as the desktop library does, and takes the character's chats with it unless you switch that off. It works in the Android app and over remote access.
The All key above the keyboard is Select all, and looks off while the box is empty. It used to look like a key that did nothing. A screen reader now reads it as Select all.
🎲 Adventure Mode
A game master card can set the stats a new character starts with. Add
"start"to the Character sheet box, such as{ "health_bar": 10, "health_bar_max": 10, "floor": 1 }, and clicking Use in the character builder sets each one as if the game master had written it, so a starting health bar no longer depends on the model remembering it. Re-running the builder mid-game only fills in the ones the sheet does not have.Complete sheet for me asks what you want first. In the in-chat character builder and in a persona card's editor, it opens a box for what the character should be ("a sneaky ex-accountant, low strength, high charm"). Your wishes come ahead of the AI's own ideas, though the game's rules and the scores already on the sheet still win. Leave it empty to let the AI decide; your text stays in the box if you try again.
The create-your-character button grays out once you have one. A greeting's character button no longer reopens the builder after the character is made; change it from the character sheet instead.
📖 Guide
Document styles: a border or background drawn with a theme color keeps all its sides. A style that set
border: 1px solid var(--x)and then changed one side drew only that side; the rest now stay. A style can also no longer reach the text after its block, and its animations wait until a reply has finished arriving instead of restarting all the way through it. Animations now run only in the newest message, so a style can loop one without old blocks still moving further up the chat.The Guide has a new Document styles section. It shows how to make your own look for
[[doc: …]]blocks in Settings or a card's editor: the HTML and CSS with a worked example, how to get the AI to use a style, and what to watch for.
🐛 Fixes
Grading a card on the Rin Chat subscription no longer fails on Balanced. The grade was held to a chat reply's length, which cut its answer off partway, and the error that followed asked you to report a problem. It now gets the same room as Card Forge's other tools.
A card whose greetings were written as separate parts now opens with its greetings. Some AI tools write each greeting as action, dialogue and thought instead of one text, and a new chat with such a card started empty. Those parts are now joined into one greeting, and the same goes for other lists and text fields in an unexpected shape, for cards already in your library too, and for SillyTavern cards. Importing such a card, or replacing a card with it, says which fields were converted, and a card fixed this way is not tagged as edited by you.
Deleting a chat no longer freezes the window. Deleting a chat that had pictures in it could leave Rin Chat "Not Responding" for several seconds on a big library, and deleting a character or renaming, merging or removing a tag across many cards could do the same. The row now disappears at once, and the work happens in the background.
Adventure Mode: Complete sheet for me now follows the game's own rules for making a character. It used to see only the game master card's name, description and setting, so a game that lists its backgrounds, classes, skills or starting gear in the Ruleset box got generic answers. It now also reads the start of the Ruleset box and any lorebook entries keyed to one of the sheet's note headings, "character creation" or "intake". The same goes for AI party members statted in DM mode (and Re-stat), and for Complete sheet for me in a persona card's editor when the card is linked to a game.
The Guide and the Variables panel no longer say global variables are shared by every chat when they are kept per chat, which is the default.
Uploading a card with large art to aicharactercards.com just works. A card whose file came out over the site's 2MB limit was refused, and the message could read "2.0MB, accepts up to 2MB". The app now redraws the art smaller for the upload until the card fits, without touching the card's own image. Only a card whose text and lorebook are too big on their own, or an animated image over 5.5MB, is still refused, with a message that says which.
Windows: an update into a folder your account can't change now asks for administrator access instead of failing with "Error opening file for writing". This happened when Rin Chat had once been installed as administrator, which leaves its files owned by Administrators, so the normal update had no permission to replace them. The updater now shows a Windows administrator prompt and finishes the update. If you decline it, it says so plainly: run the installer as administrator, or give your account Modify permission on the install folder (that also stops the prompt on future updates). A file that is merely still in use gets its own message with Retry. Rin Chat now also checks this itself: Settings → Updates says when it is installed in such a folder, the update offer warns that Windows will ask for approval, and a Fix permissions button gives your account Modify permission on that one folder (after a Windows administrator prompt), so later updates need no prompt. The command it runs is shown for anyone who would rather run it themselves. Inside Program Files, Windows or at the top of a drive it offers no fix, since changing permissions there is the wrong answer.
Rin Chat Update Notes - Version: 1.0.1
15 November 2026
🐛 Fixes
- Remote Access no longer fails with "Couldn't load the certificate: KeyMismatch". Its security certificate and key are saved as two files, and two starts at once could each save one of their own, leaving a pair that never matched again. Only one start writes them now, and a saved pair that won't load is replaced with a fresh one. Your phone shows its one-time certificate warning again after that, as it does when your PC's address changes.
Rin Chat Update Notes - Version: 1.0.0
15 November 2026
🛠 Card Forge
- The guide writes the change when you ask for one. A guide would sometimes answer an edit request with "There! Done" and no edit at all, even when told to use edit blocks. The Forge now notices more of those empty claims, and any reply to a request that names the blocks, and asks the model once more for the actual edit, so it reaches your review. Clicking one of the guide's suggested choices that names a change ("Add another dialogue example") now counts as asking for it, so the reply comes back as an edit to review; a choice like "Nah, this card's done" stays a plain reply.
- Card Forge keeps each example dialogue separate. When a model ignores the format and writes several examples into one entry with
<START>markers between them, the Forge now splits them into their own entries. An example with several back-and-forths stays whole, blank lines and all. - Edit selection with AI works in Card Forge. Highlight part of a field, or of a greeting in the full-screen editor, right-click and choose Edit selection with AI to rewrite just that part, as you already could in the card editor. Card Forge's fields used to show only the browser's own menu.
- Grade a card before you publish it. The new award button in Card Forge's toolbar grades the card on the same scale as aicharactercards.com: five categories out of 20, a bonus for varied alternate greetings and a token penalty, for a total out of 105 and a letter from S to F, so you can see whether it clears the B that Verified Creator needs. Each category gets a short note, and every problem found comes with a Fix button that opens the change in the Forge's editor for you to review, with undo in Card history. It uses your session's own model unless you pick one for grading in Settings, Card Forge, Card grading, so it can differ from the site's grade unless that model is GLM 4.7. The hard rules are checked by the app rather than left to the model: blank fields, a missing first message, a greeting that speaks or feels for the user and an oversized card always cost what the site's rubric says they cost. Only a greeting in which the user is the one acting or feeling counts as speaking for the user: a character pulling you close, or a line that just places you in the scene, is never marked down, and example dialogue is not judged for it at all. Reopening it on an unchanged card shows the last grade without a new request. The same grade is in the card editor too, as Tools, Grade card, on your active model or the one picked for grading: there a Fix opens Edit with AI on that field with the fix filled in, and Fix all opens AI Restructure's Improve with every fix as its instruction. Persona cards are not graded, in either place, since a persona has no greeting to judge.
📖 Lorebooks
- See which words in a chat activated a lorebook entry. A word that fired an entry gets a faint dotted underline, and hovering or tapping it names the entry and its lorebook. Only words that actually fired are marked, not every keyword in the text, and entries that are always on or pulled in by another entry leave no mark. Turn it off in Settings, Chat Display, Lorebook words.
🐾 Meet Rin
- Rin is in your library. The Card Gremlin herself now ships as a character you can chat with on the desktop app: bratty, playful, very funny and happy to talk about your day, trade jokes or poke at a character you're making. She comes with her own apartment to hang out in, named outfits with pictures she shows when she changes, and an adult, filthy sense of humor, so expect swearing and crude banter. She arrives in every desktop library, new and existing, and deleting her keeps her deleted.
- Ask Rin about the app right in her chat. When you ask her how to do something in Rin Chat, such as "how do I change my theme?" or "where are lorebooks?", she gets the parts of the in-app Guide that answer it and explains in her own voice, and says when she isn't sure instead of making up a feature. Only a question that clearly matches the Guide does this, so ordinary chat with her costs no extra tokens, and the Guide text goes with that one reply only: it is never saved in the chat. It works in group chats when she is the one replying, and the prompt inspector shows it as Guide reference. Only the Rin that ships with the app does this, not a copy of her.
🎨 Theme & Colors
A new built-in theme, Rin, for 1.0. Deep violet panels, her orange for the action buttons, glowing accents, and her own pictures behind the library, lorebooks and chats. Pick Rin in Settings, Theme & Colors. Like Dark and Light it can't be changed or deleted, so choose Duplicate to edit and make your own version of it. If you already had a theme of your own called Rin, it keeps its look under the name Rin 2.
The character's replies have their own color. A new Character replies swatch colors only the reply bubble. It used to share Cards & replies with the library's cards, menus and toasts, so one could not change without the other. That swatch is now called Cards & panels. Until you set Character replies it follows Cards & panels, so every existing theme looks the same.
📱 Phone
- Make a character from scratch on a phone. The Characters tab has a + button that opens a blank character in the editor, in the Android app and over remote access. Until now a phone could only import one. The import button next to it now shows a download arrow, so the two are easy to tell apart.
- Make a new persona from Settings, Personas. A New persona button opens a blank persona in the editor. A phone had no way to make one before, and on a computer it saves a trip to the library's Personas tab.
🖼 Images
- The default image style is in Settings. Settings, Images in Chat is now Settings, Images, and it holds the Default style and an Edit styles button beside the common prompt prefix and negative prompt. The default style goes first in every picture drawn in a chat, so a default left on Photograph put "realistic high quality photograph" ahead of an anime card's own prefix; until now it could only be changed from a card's image generator or Image Studio. The page also says the order a picture's prompt is joined in: the style, the common prefix, the character's image prefix, then what the picture shows.
- Pictures can include your persona's look. Turn on Include your persona's look in Settings, Images, and pictures of your persona and of the whole story add your persona card's image prompt prefix after the character's, and its negative prefix to the negative. It is off unless you turn it on.
🐛 Fixes
Updating on Windows no longer stops at "Error opening file for writing: rin-chat.exe". When the old program file was still held, the installer moves it aside under a fixed name, and a copy left there by an earlier update blocked that move, so the install failed anyway. It now uses a new name each time and cleans up every leftover it can.
Card Forge no longer says "No provider configured" while your chats work. A Forge session remembers the model config it was set to, and when that config had been deleted or set up again, the Forge refused to run instead of using your active one. Its model button even kept showing the old model. It now falls back to your active config, as chats do. Direct Chat had the same problem and is fixed too. And when nothing can run, the message now says which step is missing: a provider that has no generation config is pointed to Settings, Generation Configs, where the model is picked, instead of being told to add a provider it already has.
Importing an aicharactercards.com link or card ID works in the Android app. The import sheet asked a PC for the card, which only exists over remote access, so every link failed with "doesn't look like a character card". The app now downloads it itself.
Remember me works on Android. The app said it was saved, but the phone forgot it by the next launch, so it asked for your password every time. It is now kept in Android's own secure key store.
Linking your AICC account on a phone waits until you are back in the app. Some phones cut off an app's network while the browser is in front, so the check right after signing in failed. When a link or sign-in does fail, the message now says why (no network, a refused connection, a certificate problem or a timeout) instead of only "error sending request".
A document ends where the model closes it, even mid-line. When a reply put more text on the same line after [[/doc]], the close wasn't recognized and the rest of the reply was drawn inside the document. The text after it now starts below the document.
Editing a message no longer lags in a long chat. Every key you typed in a message's edit box redrew the whole chat, so the longer the chat, the further the text fell behind your typing. The edit box now keeps its own text until you save. The phone's edit screen had the same problem and is fixed too.
Document styles show again. Since 0.9.8, a [[doc:]] block showed as plain text, with no paper, newspaper, terminal or SMS styling and none of your own, unless you had saved a style of your own. The styles' CSS was never put on the page at startup. It now is.
The provider button at the top now opens Generation Configs. It took you to the LLM provider list, but the model and settings you are chatting with live in Generation Configs, which is where you usually want to go from there.
A reply no longer pins your CPU while it streams in. Every frame of a streaming reply redrew the whole reply so far, macros, regex scripts, Markdown and all, up to 60 times a second, so a long reply kept a processor core busy until it finished. The live reply now redraws only as often as it can afford to, so a long one updates a few times a second instead of every frame, and the finished reply looks exactly the same.
Open my library, at the end of setup, now shows it's working. It adds the starter characters first, which can take a few seconds, and until now the button gave no sign anything was happening. It now reads Opening your library… until the library appears.
Edit a generated first message before you accept it. Once Generate New First Message finishes, the draft opens in an edit box with the same right-click formatting menu as Edit with AI, and both Accept buttons use your edited text. Highlight part of the draft, right-click and choose Edit selection with AI to rewrite just that part in the character's voice, with or without instructions; the rest of the draft, your edits included, stays as it is. Regenerate replaces your edit with the new result.
Rin Chat Update Notes - Version: 0.9.9
13 November 2026
📚 Library
- Import cards from Chub, RisuRealm, Pygmalion and Perchance. Paste a character's page link into Import from a card ID or link, as you would in SillyTavern, and Rin Chat downloads the card with its art.
- Cards remember where they came from. A card imported from a link keeps that link, shown as Imported from under Metadata, so you can find its page again. It stays on your computer and isn't included when you export or share the card. Cards from Chub, RisuRealm, Pygmalion and Perchance show it even when they came in as a file or before this update, since those sites write the card's ID into the file.
🐛 Fixes
The Discord bot no longer makes Rin Chat lag while you type. It used to do all its work in the window you chat in: reading the channel's chat, building the prompt and saving the whole chat back, twice per reply. It now runs in a hidden window of its own, which has its own thread, so answering someone on Discord can't stall the app.
Sending a message in a long chat no longer stutters. Every call a reply made, the reply itself and then each chat memory call, saved the chat's whole request log again, several megabytes on a long chat, up to five times per message. It now saves once when the reply is done, and does a third of the work when it does. A send also skips preparing history too old to reach the model.
Shift-click acts out a choice on any card, not only in Adventure Mode. Choice buttons in an ordinary chat ignored Shift and sent the choice as plain text. Shift-click, or right-click and Act it out, now writes your next message in your character's voice for every card's choices.
Rin Chat no longer freezes on Linux systems with newer color emoji fonts. On Bazzite, Fedora and similar systems, opening Lorebooks could freeze the app while drawing an emoji in the system's emoji font. Rin Chat for Linux now brings its own copy of Noto Color Emoji and uses it in place of the system's color fonts, so emoji look the same as before and can't crash it.
Creator notes written in Markdown preview cleanly on library tiles. A Markdown image showed as its raw code in the preview, while an HTML image was already left out. Images now drop out either way, links keep their text, and bold and heading marks no longer show.
Rin Chat on a phone shows its own icon. The browser tab, and a home screen shortcut made from it, showed the logo of a tool the app is built with. If you added Rin Chat to your home screen, remove the shortcut and add it again to get the right icon.
A character you delete from your phone leaves the Characters list right away. It stayed listed for up to a minute, and tapping it said the card was not found.
A popped-out Settings window no longer overwrites the debug log. Anything it logged, such as a connection test, saved its own short copy of the log over the main window's. Its entries now go into the main window's log.
Rin Chat Update Notes - Version: 0.9.8
11 November 2026
📱 Phone Layout
- Rin Chat on a Windows tablet held upright now gets the phone layout that remote access uses on a phone: Chats, Characters and More along the bottom, and chats full screen. Any window narrower than a phone's (767 pixels) switches to it, and widening the window brings the desktop layout back. It keeps its own title bar, so minimize, maximize and close are still there, and so are Card Forge and Image Studio in its menu. It used to get a squeezed version of the desktop layout.
📚 Library
- Filtering by a tag now finds cards in hidden folders too. A folder hidden from All cards used to hide its cards from every tag filter as well, so a tag showed fewer cards than it was on. The same goes for Untagged, Missing art and Never chatted, and Library stats now counts every card, so its numbers match the lists they open.
📱 Remote Access
- Phone search works like the PC's library search. It used to match names only. It now matches name, creator and tags, and starting with
f:searches every field of a card, its description, personality and scenario included. - Folders on the phone open like the PC's sidebar. The row of folders shows only the top level; opening one adds a second row with its subfolders and the way back up, instead of one long row of every folder by path.
- A character's page on the phone has an Edit button along the bottom, beside the chat buttons. Editing used to be only a small pencil on the picture, easy to miss.
💬 Chat
- Continue adds to the reply you're reading instead of making a new version of it. The version counter used to jump to 2/2, which looked like a new reply. If you don't like where a continuation went, Undo puts the reply back as it was; on the phone it's Undo continue in the + menu. Whatever the model thought before continuing is kept too, added to the reply's thinking block below a line, where it used to be dropped.
- Continue no longer pastes a quoted copy of the reply onto itself. Some models answer a Continue by starting over and quoting the reply, once even under a Chinese forum header with
>on every line, and that was glued on as the continuation. Rin Chat now spots it, switches that model to the continue instruction for good, and continues properly on the same click. The same goes for a continuation that trails off into the model's own control markup (<|ref|>,<|im_end|>and the like): that markup and everything after it is dropped. A continuation that starts a new sentence also no longer runs into the last one with no space.
🐛 Fixes
A big library no longer fills memory. The library kept a full copy of every character it had shown you for the rest of the session, even while you were in a chat; with a few thousand characters that reached about a gigabyte. It now keeps only the few numbers its tiles show, and saves them, so sorting by tokens or by fields filled is instant from the first click after a restart instead of measuring every card again. Pictures in creator notes are also kept for only the most recent 60.
The Discord bot no longer makes Rin Chat stutter when it replies. Each reply read the channel's whole chat back from disk three times, cleaned every message in it even though only the recent ones reach the model, and loaded your whole card list, all on the same thread you type on; with a long channel and a big library that was a visible hitch. It now keeps its own copy of the chat between replies, works only on the history that fits, and checks the bot's name and picture every couple of minutes rather than on every reply. The library no longer reloads on each bot reply, a Discord chat left open in a hidden tab waits until you look at it, and the debug log saves less often.
Clicking back into Rin Chat no longer makes it stutter. Every time the window got focus, each open chat re-read your document styles and regex scripts and, even when nothing had changed, redrew its whole history from scratch. It now only redraws when something actually changed, and switching to a chat tab no longer redraws it just because its character was re-read.
Updates no longer fail with "Error opening file for writing". When Rin Chat took a moment to close, or antivirus was still scanning it, the installer could not replace the old app, and choosing Ignore left a broken install that looked like a good one. The installer now closes the app itself, waits for it to let go, and moves the old file aside if it is still held.
Your theme looks the same on the phone as on the PC. Your own messages were filled with the theme's highlighted border color, bright green in a green theme, and Chat bubble opacity was ignored. Send, Start chat and New chat now use Action buttons, chosen tabs, chips and options use Selected items, buttons get Button borders and Button glow, and the Library background image shows behind the Chats and Characters lists.
The back and edit buttons on a phone character page stay visible in every theme. With a light accent color their icons turned dark on the dark circle behind them.
Send works on the first tap on an Android phone. The first tap only closed the keyboard, so a message took two. The keyboard now stays up after sending, as it does in a messaging app.
Creator notes written in HTML render on the phone. A character's page showed them as raw markup. They now follow the same per-card choice and Always render HTML setting as the PC, and a Render HTML button switches between the two.
The remote access menu in the title bar opens fully in a narrow window. Below 768 pixels wide it was cut off at the bottom of the title bar, leaving only a sliver.
Rin Chat Update Notes - Version: 0.9.7
10 November 2026
📱 Remote Access on a Phone
It feels more like an app. Menus slide up from the bottom and pull down to close, a chat or a character's page slides in, and every button answers a press. Coming back from a chat, a character or another tab finds each list where you left it, and tapping the tab you are already on goes back to the top. Lists show placeholder rows while they load instead of "No chats yet", and chats without a name show how many messages they have instead of the date they were made.
Make a picture, set the Author's Note, and open a chat's Memory, variables, lorebook and Adventure character sheet from a phone. Picture making and the chat's pictures are in the + menu, and the rest are in the chat's options, each opening full screen; all of them were only on desktop toolbars and side panels the phone didn't show. On any touch screen, a character sheet's stats have a ⋯ for renaming or deleting them, which was right-click only.
Share a message to another app through the phone's own share sheet, from the message's ⋯ menu.
Swipe the newest reply sideways for its other versions: left for the next, right for the one before, and left past the last writes a new one, as the arrows under it do. A new chat's greeting swipes through its alternate greetings.
Press and hold a chat to open it, view its character or delete it, in the Chats list or on a character's page, and press and hold a character to start a chat straight away. Deleting asks first.
A character's page carries on your latest chat with them, with Continue chat, and New chat beside it. Tap the character's name at the top of a chat to see their page from there too, pencil included: Back from the editor returns to the chat. Rename a chat from the top of its options, and edit a character from the pencil on their page.
A reply that finishes while you're elsewhere marks its chat as new and moves it to the top of the Chats list, whether you were on the list or in another chat. From another tab, a dot on Chats says there is something new. The mark stays until you open the chat, even if the phone closes the app in the background, and coming back from another app brings the list up to date with anything you did on your PC.
A button to jump to the newest message appears when you scroll more than a screen up in a chat.
Back works everywhere. Lorebooks and the Guide have a Back button, and Back closes Find, a note, Notes, a text selection, an enlarged avatar, a full-screen text editor, a lorebook you are editing and the character page before it leaves the screen. On an iPhone home screen install, which has no browser Back, you can also swipe in from the left edge.
Lock with PIN, under More, puts the phone back on the PIN pad at once, for when you hand it to someone. Unlike Log out, the PIN is all it takes to come back. More also shows which version of Rin Chat your PC is running.
Add to Home Screen gives Rin Chat its own icon and name, and the browser bar takes your theme's color. More → Add to Home Screen installs it where the browser offers that, and shows the steps where it doesn't, as on an iPhone. On Android the icon keeps its whole outline instead of being cropped to a circle.
It notices straight away when your PC locks and shows the unlock screen, instead of lists it can no longer open. Waiting for your PC has its own full screen, the Chats list says when it loses your PC and refreshes when it's back, a wrong PIN shakes and clears the box, and a keyboard plugged into the phone types into it too.
Faster. Opening a chat used to download your whole character list five times over, which was slow with a big library; going back to the Chats list fetched it again; and every launch downloaded the whole app from your PC. The phone now keeps the app's files, asks for the library once, opens a chat in under half the requests it took, and its first visit downloads about a fifth less.
It reopens the chat you were in. An iPhone often closes a home screen app in the background, which used to start it again on the Chats list every time you came back from another app. A message you had started typing is still in the box.
The screen stays on while a reply is being written. A reply is written by the phone's browser, so a phone that dimmed and locked partway through cut it off. Switching to another app still pauses it, and the chat now says that is what stopped the reply, instead of telling you to check the provider's address.
A phone left open while your PC updates reloads by itself the next time it opens a screen, instead of showing an error.
Held sideways, nothing sits under the notch, the bars go compact so the chat keeps its height, the PIN pad fits without scrolling, and text no longer grows on an iPhone.
A PIN with letters in it works on a phone. The PIN pad could only type digits, so a PIN like that couldn't be entered at all. The key in the PIN box now swaps the number pad for the phone's own keyboard and back, and Settings → Remote access → PIN entry picks which one a phone starts on. The PIN screen's logo and heading are bigger too. The box also no longer shows four dots before you type: it fills with one per character, so it never hints at how long your PIN is.
A chat's options fit on a shorter phone. On a screen the size of an iPhone SE, the menu stopped halfway through its row of tools.
Notes and Send with directions open full screen, with the text box taking the room.
Favorites and folders on a phone. Star a character from their page, and the Characters tab gets a row of chips over the list: All, Favorites, and each of your library's folders. A folder hidden from All on your PC is still there to open, as it is on your PC. It's the same star and the same folders as in your PC's library.
Every chat is reachable. Searching looks through all of them by title and character name, and Show older chats at the end of the list goes past the 200 most recent.
The Characters list shows the start of each character's notes under their name, in place of the creator, so you can tell similar cards apart. Which notes follow Settings → Card library → Notes on card tiles, as your PC's library does.
The card editor is laid out for a phone. The creator notes run the full width instead of down a narrow strip beside the picture, text boxes use the app's font, the header's buttons are quieter, and the section strip is bigger and stays in view under the header instead of sliding behind it. Greetings, examples and other lists give their text the whole width with their buttons in one row over it, and scroll with the page instead of inside a box of their own. The image buttons sit under their headings.
After importing one character, Open takes you to their page instead of leaving you to find them in the list.
Search boxes and the card link box work with the phone keyboard: Go imports the card, Search puts the keyboard away so you can see the results, the Chats search box is ready to type in as soon as it opens, the tab bar steps aside while you type instead of riding up on the keyboard, and an ✕ clears the box.
Empty lists say what to do next, with a button for it: browse characters, import one, or try again when your PC didn't answer.
A chat's options say what is set: whether the Author's Note is on, and that reply length is Auto (or a custom length from your PC) when none of Short, Medium and Long is lit.
Search settings on a phone. Type what a setting does at the top of Settings, and a result opens its page at that setting.
Message text size steps up and down a size at a time with a sample beside it, across the same range as on your PC. The three presets couldn't show a size set there, and lit none of them.
The lorebook editor and card editor fit a finger better: the lorebook toolbar's buttons and entry switches are easier to hit, and the card art's Generate and Replace no longer cut each other off.
An Android phone no longer asks to show notifications. Its browser can't show them for remote access, so saying yes never led to any.
The first-chat feature tour waits for your PC. On a phone it pointed at toolbar buttons the phone doesn't have.
The Guide reads better: its search box fills the width, the file export buttons on every section are left to the desktop, and tapping a chapter in its contents on a touch screen opens that chapter. It often opened the one after it.
💾 Exports
- Choose where exports are saved. Settings → Data & Backup → Export folder sends exported cards, chats, lorebooks, backups and saved pictures to a folder of your choice, such as another drive when C: is short on space. It's your Downloads folder until you change it, and the save buttons name whichever folder is in use.
🐛 Fixes
A chat left open on your phone no longer overwrites what you wrote on your PC. Carry a chat on at your PC and then pick the phone up again, and its next message saved the phone's older copy over the PC's new messages. Coming back to the phone now brings the chat up to date first.
Replies from a phone could be sent without your API key. If your PC had a second entry for the same provider address with no key in it (a duplicate provider, or an image or voice provider on that address), remote access could pick that one, and the provider answered that the key was missing, while the PC itself worked fine. It now uses whichever entry for that address has a key.
A provider refusing your key no longer bounces a phone back to the PIN screen. The phone mistook it for its own sign-in running out: the message you'd just sent vanished from the screen, the next one started yet another new chat, and no error was shown. The chat now stays put and says what the provider said.
A card with only a core personality no longer shows its Personality section as empty in the card editor's section headers and its section list.
The guide at rin.chat/guide jumps where it says. Links between sections all work now; 21 of them were plain text. While you search, the contents list shows only the sections that match, and clicking a link to a section the search was hiding ends the search and goes there instead of doing nothing. On a phone, a jump no longer lands with the section's title under the top bar.
A model picked for a deleted provider no longer causes errors. If you had chosen a separate model for chat memory, the scene tracker, a group member or another background job and then deleted that model's provider, Rin Chat sent the old model's name to your current provider instead, which rejected it every few replies with "memory failed". Those jobs now use your chat's own config, as Settings already showed.
Rin Chat Update Notes - Version: 0.9.6
10 November 2026
🕘 Card History
- History now covers changes made outside the card editor. The editor always kept a checkpoint when you started changing a card, but edits from a chat's card panel, the Lorebooks page or a library merge could replace it with nothing to go back to. Now, if a card has no checkpoint from the last day, its current version goes into Tools → History before the change is saved.
- History keeps more and opens faster. Each card now keeps 200 snapshots instead of 50. The list shows the newest 20 straight away and loads the rest as you scroll.
🚚 Migrate from SillyTavern
- Bring your whole SillyTavern setup across. Point Rin Chat at your SillyTavern user folder, from onboarding or Settings → Data & Backup, and choose which characters, chats, group chats, lorebooks, personas and presets to bring. Your SillyTavern folder isn't changed, cards you already have are skipped while their chats still come across, and running it again adds nothing new. API keys aren't copied; it shows you the file they're in.
⚙️ Settings
- Import your SillyTavern presets. Import from SillyTavern, under the list in Generation Configs and System Prompts, reads Chat Completion and Text Completion presets, context templates, system prompts, reasoning templates and Master Export files. It adds them as new configs, shows what came across and what didn't, and lets you tick which prompt blocks to keep.
📱 Phone
- A new phone layout for remote access. Chats, Characters and More are now three tabs, the chat is one clean screen with a compact header, and every menu is a bottom sheet. Continue and Impersonate are in the + menu, and you can import a character from a card file or an AICC card ID on the Characters tab. A row above the keyboard offers Paste, All, narration, speech and OOC, the Back button closes what you opened instead of leaving the app, and selecting text no longer gets covered by the app. Every settings page you can safely change from a phone is there too, one at a time under More, with the same Basic and Advanced switch as the desktop, and Usage is new to remote access. Some other desktop features are hidden on the phone for now and will return as they are rebuilt for it.
💬 Chat
- Text boxes on a phone keep the phone's own Copy and Paste menu. Long-pressing selected text in the message box or an editor opened Rin Chat's menu on top of the selection, and the phone's menu didn't appear.
- The card panel in a chat opens read-only. Press Edit at the top when you want to change something, so a stray keystroke can't alter a card while you're reading it. To have it always ready for editing, turn on Always open the card panel for editing in Settings → Chat Display.
Rin Chat Update Notes - Version: 0.9.5
9 November 2026
🐛 Fixes
- Update persona card saves what you wrote under "Who they are". The button said it had updated the card, but text only went in if the card's description was empty, so edits to any existing character were dropped. The builder also showed the chat's older copy of that text, so a card edited in the library looked unchanged. It now opens on the card's own text and saves your changes back to it.
- Import stops bringing in cards you already have. A card with a display name different from its character name was never recognized as already being in your library, so importing a folder added it again, while Find duplicate cards spotted it straight away. Import now finds those too.
- Phone remote no longer says "Wrong PIN" when the PIN was right. If a browser doesn't keep Rin Chat's sign-in cookie, as Brave can with Shields up, the app refused the attempt and called it a wrong PIN. It now tells you it's the cookie. Having two browsers that identify themselves the same way on the PIN screen at once, such as Chrome and Brave, could also refuse a correct PIN at random, and that now retries.
- The Linux AppImage opens on systems with Mesa 26. On Fedora 44, Bazzite, Nobara, Arch and others with current graphics drivers, the app showed an empty gray window and stopped, with "Could not create default EGL display" in the terminal. The AppImage's bundled Wayland library was too old for those drivers, so it now uses the system's copy. An AppImage stuck on that gray window can't update itself, so download 0.9.5 from the website, or start the old one once from a terminal with
LD_PRELOAD=/usr/lib64/libwayland-client.so.0 ./RinChat_0.9.4_amd64.AppImageand update from there.
Rin Chat Update Notes - Version: 0.9.4
5 November 2026
🖼️ Card Images
- Animated PNGs become animated WebP in bundles and in a card's image library. Sprites, pictures and backgrounds you add now convert when they come in, and a bundle converts anything still in PNG when you export it, including the card's art, so the same animation takes far less room. Your card's own art stays an animated PNG in your library, because a PNG card file needs it to stay animated.
- A bundle keeps animated WebP card art animated. Exporting a bundle used to flatten that art to a still PNG.
📖 Lorebooks
- The lorebook tester says where a chained keyword was found. "Pulled in by Scarlett on Louise" read as if Louise were one of Scarlett's keywords, when the word was actually in Scarlett's text. It now says: found "Louise" in the text of "Scarlett".
🐛 Fixes
- Adult pictures from Venice aren't blurred. Venice blurs anything it classes as adult unless the app asks it not to, and the filter in Venice's own app doesn't apply to API requests, so these pictures came back as a smear with no error and nothing you could change. Rin Chat now asks for them unblurred.
- A tilde no longer crosses out your text. Two single tildes in a reply, as in "so naughty!~", struck out everything between them. Strikethrough now takes two tildes on each side, so a sing-song ~ stays a ~.
- A card's regex scripts no longer teach the model the interactive syntax. A
[[choice:]]that only appeared in a script's replacement still counted as the card using choices, so the model was told how to write buttons the card never asked it for. Only the card's own text counts now, and the buttons a script makes still work. - The model is told how to read story variables. The instructions for
[[set:]], questions and forms said "Read variables with true", because the app filled in its own example macro before sending it. The model now sees{{getvar::name}}as intended.
Rin Chat Update Notes - Version: 0.9.3
3 November 2026
🐛 Fixes
- The Linux AppImage starts on Fedora, Arch, openSUSE and similar distributions again. 0.9.2 crashed at launch there with an "undefined symbol: g_free_sized" error. An AppImage that updated itself to 0.9.2 can't open to update again, so download 0.9.3 from the website, or start 0.9.2 once from a terminal with
RINCHAT_ENCHANT_PRELOAD= ./RinChat_0.9.2_amd64.AppImageand update from there.
Rin Chat Update Notes - Version: 0.9.2
3 November 2026
📚 Library
- Update several cards at once. Card updates had only a review per card, so a long list meant opening every card in turn. Each row now has a checkbox, with Select all above the list, and Update checked updates every ticked card without the field-by-field review: every change and the new picture. Each card keeps a History checkpoint from before the update, so Tools → History puts the old version back.
📖 Lorebooks
- The lorebook tester traces chains. When one entry pulled in another, through Recursive Scan or a
[recursion: KEY]token, the tester said only "key matched", often naming no key at all, so a large book that cascaded was hard to untangle. It now says "pulled in by" with that entry's name and the key it matched, and an entry fired by the test text still shows its own key.
🎨 Image Studio
- OpenRouter models can start from a picture. Start from a picture and Expression sprites only appeared for local backends, NanoGPT and the built-in proxy. They now also appear for an OpenRouter provider whose model both takes and makes images, such as the Gemini image models. The picture goes along as a reference, so there is no strength slider, and an expression set shares one seed where the model supports it. Pictures from these providers are also now asked for in the shape you picked, where the request always said portrait before.
🔊 Voice
- Your persona has a voice. A persona's Voice section did nothing: your messages were always read in the provider's default voice. The speaker button on your own messages now uses your persona's voice, and the new Read my messages too setting in Voice Providers makes a chat with auto-read speak each message as you send it. The reply waits for your line to finish instead of cutting it off.
💬 Chat
- Old buttons stop costing tokens. Every choice, question box and form a reply ever offered went back to the model on every turn, long after you had moved on. Now only the newest reply's set is sent, while the older ones stay on screen as they were. Send only the newest buttons in Settings → Memory & Context turns this off.
- The card panel can take as much of the window as you want. Dragging the card panel beside a chat stopped at a fixed 640px, about a quarter of an ultrawide window. It now grows until the conversation is down to 420px, whatever the window's size, and if you shrink the window afterward the panel gives the room back.
🐛 Fixes
The Linux AppImage runs on older distributions. It was built on a very new system, so on Linux Mint 22, Ubuntu 24.04 and other older releases it failed to start with a "GLIBC_2.43 not found" error. It now runs on Ubuntu 22.04 and newer, Mint 21 and newer, and Debian 12.
Pictures on image services with a fixed list of sizes. Rin Chat chose an allowed size only for OpenAI itself, so another service with a fixed list refused the request with an "Invalid enum value" error. It now reads the sizes the service offers and asks again with the closest one.
A busy Discord bot gets in the way of your chat less. With a very long channel history, each bot reply froze the app for a moment while it processed every message the channel had ever seen, even though only the most recent can fit in the prompt. It now processes just those. Each reply also made the chat you had open save its whole request log again, and a failed bot reply showed up as an error in that chat. Bot calls now leave the open chat alone.
Cards that only use
[[set:]]stop growing buttons. A card with a[[set:]]line was also taught the[[choice:]]syntax, so some models ended their replies with buttons the card never asked for. Such a card now gets only the[[set:]]instructions, unless it uses choices itself or the chat is in Adventure Mode.Quick AI tasks on models that think anyway. Auto-prompt from card came back blank with no error on DeepSeek V4 Pro, because the model spent the short budget for the job on thinking, even though it had been asked not to think. The same could hit every short task, such as suggested replies, scene tracking and tag suggestions. They now retry once with more room, and if that also comes back empty you get a message saying so.
Chat titles on the subscription. Naming a chat always failed with a temporary provider problem, because the model spent the whole short reply budget thinking and came back empty. Titles now always use the Fast slot, and on your own providers the call leaves room for a model that thinks.
Rin Chat Update Notes - Version: 0.9.1
28 October 2026
🎨 Image Studio
Start from a picture. With a provider and model that can work from an image (A1111 and Forge, SwarmUI, and the NanoGPT models that support it), a Start from a picture box appears under the model. Drop or paste a picture, drag one in from the gallery, choose a file, or use a card's art, then set how far the result may move from it with the Strength slider. Any picture in the gallery can also become the start image from its Use as menu.
Upscale pictures. The Upscale menu beside a picture makes a bigger copy of it in the gallery. 2× and 4× on this PC are free and use your graphics card when it can; the first time downloads the upscaler. With A1111 or Forge, or NanoGPT, the provider's own upscaler is offered as well.
Crop pictures. Point at a picture and press Crop, or use Crop in the full-size view. Pick a standard shape (1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16) or crop freely, drag the frame and its corners, and the cropped picture lands beside the original at full resolution, with its new size in its details. Undo crop (or Ctrl+Z) takes it back.
Delete from the gallery in one click. Shift-click a picture's X in the Image Studio gallery to delete it everywhere, All images included, instead of only taking it off the list.
LoRAs, sampler and scheduler for local backends. With A1111, Forge or SwarmUI, the form lists the server's own LoRAs, samplers and schedulers to pick from. Add LoRAs with a weight each; they are saved in presets and in each picture's settings.
Improve your prompt. The new Improve button above the prompt has your text AI turn a short idea such as "cozy cabin, night" into a detailed image prompt you can edit before using. Wildcards and LoRA tags are kept as written.
Describe a picture as a prompt. The new Describe button above the prompt, or Describe as a prompt on any picture's right-click menu, has your text AI look at a picture and write a prompt for one like it. Use the picture you are viewing, choose a file, or pick a character's art. It needs a text model that takes images, and says so when yours doesn't.
Weight words with the keyboard. Select words in the prompt or negative prompt and press Ctrl+↑ or Ctrl+↓ to wrap them as
(words:1.1)and raise or lower the weight; with nothing selected it weights the word under the cursor. Back at 1, the brackets come off.Swap width and height, and save your own sizes. Swap flips the picture between portrait and landscape, and Save size adds the current width and height as a button beside Square, Portrait and the rest.
Wildcard lists. Save named lists under Wildcards, one option per line, and write
__name__in a prompt to pick one line at random for each picture. A line can use other wildcards too.Stars, collections and selecting several. Star a picture to keep it, or file it in a named collection; the gallery can show only starred pictures or one collection. Select picks several pictures at once to compare, star, file, save or delete together.
Right-click a picture. Image Studio's pictures and gallery thumbnails have their own menu: copy the full picture, save it, crop it, upscale it, star it, load its settings, take it off the list or delete it. Ctrl+C copies the picture you are looking at.
Keyboard for the picture you are looking at. S saves it, F stars it, Delete takes it off the list and Shift+Delete deletes it everywhere.
Know your prompt fits. A count beside the prompt's label shows how many characters are sent, styles included, against what the chosen model takes, and turns red past it.
How long each picture took. A picture's details now include how long it took to make and when it was made, and the running entry in the queue counts up while it works.
Click a detail to copy it. Click the prompt, seed or any other line in a picture's details to copy it.
Arrange the gallery. Sort newest first, oldest first or starred first, and pick small, medium or large thumbnails. The gallery keeps your sort, size and filters the next time you open Image Studio.
Compare two pictures with a slider. With two pictures in Compare, switch to Slider to lay one over the other and drag the divider across, with the setting that differs labeled on each side.
Rename and tidy collections. The new button beside the collection filter lists your collections with how many pictures each holds. Rename one, give two the same name to merge them, or remove one; its pictures stay where they are.
See and cancel the queue. Runs waiting behind the one in progress are listed under Generate, each with its own cancel. Stop all still ends everything.
More Use as targets. Besides a character's card image, a picture can become a persona's avatar, one of a character's expression sprites, or the background behind every chat.
Settings travel inside saved pictures. Save writes the prompt, seed, size, model and the rest into the PNG the way A1111 does, so Civitai and A1111's PNG Info read them, plus Rin Chat's own copy so styles and LoRA weights come back exactly. Saved JPEG and WebP pictures are turned into PNG to carry them.
Load settings from a picture. Drop a PNG on the prompt, or use Load settings from a picture beside the presets, to fill the form from a picture made in Rin Chat, A1111, Forge, SwarmUI or ComfyUI.
Picture family. A cropped or upscaled picture shows the picture it was made from under its details, and the original lists what was made from it. Click one to jump to it.
Export a collection. Each collection in Manage collections has an Export button that saves the whole collection as one ZIP, every picture with its settings inside and a settings.json listing them all.
Know when the queue is done. When the last queued picture lands while you are in another app, a notification says how many are ready.
Share pictures without their prompt. A new switch under Keep in All images, Settings in saved pictures, turns off the prompt and settings that Save writes into pictures. With it off, pictures save exactly as they came, and a collection's ZIP carries no settings either.
Save a comparison as one picture. In Compare, Save as one image puts the pictures side by side in a single PNG with the settings that differ written under each and the shared prompt across the top, ready to post in one go. A sweep keeps its rows and columns.
Watch a picture take shape. With A1111 or Forge, SwarmUI or ComfyUI, the picture being made shows in the gallery as it renders, with a bar along its foot, and the queue shows how far along it is and the time left. ComfyUI shows the picture itself only when its previews are turned on (
--preview-method auto).Hires fix for A1111 and Forge. Turn on Hires fix to draw the picture, then redraw it bigger for finer detail, with its own scale, upscaler, denoise and steps. The picture's details and the settings saved into it say how it was made, the way A1111 writes them.
See the price before you generate. With NanoGPT, the cost of what Generate will make shows beside the button, from NanoGPT's own price list for the model and size, and the queue totals what is still to come.
Expression sprite sets. Tools, Expression sprites makes a character's whole set of expressions from its card picture: each line (joy, anger, sadness and the rest, with the words each adds to the prompt) becomes one picture made from it on one shared seed, and is saved to the character as it lands. It needs a provider and model that can start from a picture.
Match your colors to a background. After Use as, Chats background, Image Studio offers to take the picture's colors for your buttons, links, messages and selections in Theme & Colors, with a preview of the colors it found. Undo puts yours back. A picture without strong colors isn't offered.
A Tools menu above the prompt. Prompt from character, Expression sprites, Generate from a list and Wildcards now sit in one Tools menu beside Improve, Describe and Recent, so the prompt's controls fit on one row.
Generate from a list. Tools, Generate from a list takes prompts one per line and queues each as its own run with the current settings, styles and batch size, up to 100 at a time.
Notes on pictures. Write a short note under any picture's details, and the gallery search finds it along with the prompt. A picture with a note is kept, like a starred one.
🔨 Card Forge
- Quick prompts when rewriting a field. The dialog for rewriting a field with your guide now has the same one-tap quick prompts as the card editor's Edit with AI (Concise, Vivid, Grammar and your own), and Manage to add or reorder them.
- Proposals survive swiping. Moving between versions of a regenerated reply used to drop that reply's proposed changes for good. Each version now keeps its own: one still open comes back with its Apply and Review, and one already applied or discarded comes back as the record of what happened.
💬 Chats
- Impersonate with instructions keeps your draft. Closing the window used to throw away the directions and every draft. Reopening it now brings them all back, edits included, until you send a message in that chat.
- See which model wrote a reply. Hover a reply's time to see the model behind the version on screen, handy when you switch models mid-chat. Replies written from now on carry it; older ones don't know.
- Preview a greeting while you write it. In the character editor, the eye button beside each greeting shows it formatted as it will look in chat; the pencil goes back to editing.
- A question above a pick. Write the first part of a pick in quotes, as in
[[pick: "What defines you?" | Strong | Agile | as trait]], and it shows as the question above the boxes instead of as one more box. The model is told the question along with the answer. - Scroll the chat from the keyboard. Page Up and Page Down scroll the chat, even while you type a message. With no text box focused, the arrow keys, Home and End scroll it too.
🐛 Fixes
Generators on your persona work in chat. Generators saved in a persona's Generators section were ignored: calling one did nothing, and they were missing from the chat's Generators tab. They now join the character's, listed as persona, and can be called, auto-fire and be triggered by the model the same way. When the character has one with the same name, the character's is used.
Choices with brackets in them. A choice whose text held a single
], such asbehavior_rules[new], showed as raw text instead of a button. It is a button now, in chats, Adventure Mode and Card Forge.Card Forge's preset buttons in light mode. The edit-presets and attach buttons were white on white. They show in light mode now.
Notes without pictures just render. A card's notes written in plain HTML, such as paragraphs and bold text, asked whether to render them and warned about remote images they did not have. Now only notes that show a picture ask first.
Generate and Replace stay on the character's picture. With a long note open beside it, the two buttons slid down below the picture into empty space. They sit on its bottom edge now.
One phone is one device in Remote access. A phone whose browser didn't keep its sign-in was added to Approved devices again on every visit, until the list ran past 40. It is now recognized by its address and browser and keeps its one row; it still asks for the PIN as before.
The resize corner stays in the corner. Shrinking a window until its contents scrolled carried the resize corner up with the text, away from the bottom edge. It stays on the bottom-right corner now.
🤖 Discord bot
- Spoiler drawn pictures and expressions separately. The one Spoiler pictures switch also blurred the character's expression pictures, so a channel could not spoiler what the bot draws while showing the card's own art plainly. Each channel now has Spoiler drawn pictures and Spoiler expression pictures. A channel that had the old switch on keeps both on until you change one.
Rin Chat Update Notes - Version: 0.9.0
24 October 2026
💬 Chats
- Add emojis from a picker. A new smiley button in the row above the message box opens an emoji picker with every emoji, search, skin tones and a row of your 20 most used, which scrolls sideways. You can also right-click in the message box and choose Insert emoji. Click as many as you like and each goes in where your cursor is. Search works in each of the app's languages, and on a phone the picker spans the screen without raising the keyboard.
- Pick your own reply length. The Length menu above the message box has a new Custom choice. Pick it and a box appears beside the menu for the number of words you want, from 20 to 3000. Replies aim for that length and end cleanly, the same way Short, Medium and Long do, and the number is remembered for every chat. Story setup offers Custom too.
🎨 Image Studio
A new Image Studio layout. The picture you're looking at now shows large in the middle, with everything that made it beside it: provider, model, styles, prompt, size, steps, CFG and seed, plus Save to Downloads, Delete, Use as card image, Reuse seed and Copy seed. Everything you've made sits in a gallery on the right that scrolls by itself; click one to look at it. On a narrower window the gallery moves under the picture.
Keep everything you make in Image Studio. A new Keep in All images switch sits at the foot of the Image Studio form. Turn it on and every picture you generate is stored with your other images, shows up in Library → All images under its own Image Studio group, and is waiting in Image Studio the next time you open it. Turning it on also keeps the pictures already on screen. Removing one from the Image Studio list only clears it from there; to delete it for good, open it in All images, where you can also save it to Downloads or use it as a character's card image. Kept pictures are included in full backups.
Keep generating while a run is going. Generate now queues: change the prompt, press it again, and the new run waits its turn behind the one in progress. Stop ends the current run and clears the queue. Ctrl+Enter generates from anywhere in Image Studio.
Regenerate, Vary and Use these settings. Beside any picture, Regenerate runs its exact settings and seed again, Vary runs them with a new seed, and Use these settings loads its prompt, styles, size, steps, CFG, seed and model back into the form.
Wildcards in prompts. Write
{red|blonde|black} hairand each picture picks one of the options at random. Each picture's details show the prompt it actually got.Recent prompts. A Recent menu beside the prompt brings back any of the last 20 prompts you generated with, as you typed them.
Compare pictures side by side. Press Compare in the gallery and pick pictures; the settings that differ show under each one and the ones they share are listed once below. Escape or Done goes back.
Sweeps on local backends. With A1111, Forge, SwarmUI or ComfyUI, the new Sweep fields render several seeds across a list of CFG and steps values in one go, such as 4 seeds × CFG 4, 6, 8, and lay the results out as a grid with one row per seed.
Find pictures in the gallery. The gallery has a search box for prompts and a filter for today, the past week or the past month. The arrow keys step through it.
Drag pictures out. Drag a picture from Image Studio into a folder, Discord or another app, and it arrives as a named image file.
Switch image providers from Image Studio. With more than one image provider set up, an Image provider menu at the top of the form switches between them. It changes the same setting as Settings → Image providers, so chats draw with your choice too.
⬆️ Updates
- Turn off the automatic update check. Settings → Updates has a new Check for updates automatically switch. Turn it off and Rin Chat no longer checks when it starts; Check now still works whenever you want.
- Package managers can leave updates to themselves. When Rin Chat is started with the environment variable
DISABLE_UPDATE_CHECKSset, it never checks for or offers updates, and Settings says your package manager handles them. This is for Linux distributions and package managers that install and update Rin Chat themselves.
🧹 Fixes
The Discord bot no longer posts picture prompts as text instead of drawing. Every picture the bot sends is kept in the channel's history so the character knows what it sent, but it was kept as a line in the character's own words. After a run of pictures, some models started ending replies with a line like that themselves, so the prompt was posted as text, nothing was drawn, and only the character's expression picture came through. The history now marks those as notes about what was sent, and a line the model copies anyway is taken out; in a channel where the character may send pictures, it is drawn instead.
The license and third-party credits now come with the app. Rin Chat said its full license shipped with the app, but no package included it. Every download now installs the license and the third-party credits next to the program.
Rin Chat Update Notes - Version: 0.8.9
23 October 2026
🎲 Adventure Mode
- Guided character creation fills in the written parts of the sheet too. A game whose sheet has written sections, such as Playbook, Moves or Gear, now tells the game master which ones are still empty and their exact names. It settles each with you as the story starts, records it in the sidebar sheet under that name, and keeps that same entry up to date as it changes in play. Before, only the numbers were filled in, and written details ended up scattered under made-up names.
🧹 Fixes
- Phone buttons no longer repeat when several chats are open. On a phone, each chat open in the background added its own copy of the chat-list, New chat, expand and microphone buttons to the one on screen, so three open chats showed three of each. Only the chat you are looking at shows its buttons now.
- Security updates. Updated the components Rin Chat uses for secure connections and for showing replies, picking up this month's security fixes.
Rin Chat Update Notes - Version: 0.8.8
22 October 2026
✍️ Story Maker
Story Maker is very experimental. It is a first version, shared early so you can try it and tell us what works. Expect it to change significantly over the next few releases: how stories are planned and written, the screen itself, and the way stories are stored. Export anything you want to keep as Markdown, since a story made now may not carry over unchanged.
- Story Maker turns a plot into a story, a page at a time. Find it in the ☰ menu (you can pin it to the bar). Give it a plot, a point of view, a length and a rating, SFW, Mature or Explicit, plus anything you want kept or avoided. It plans the story first, a cast, a setting and an outline you can edit, then writes it a page of about 1000 words at a time. Approve a page, edit it, or rewrite it with directions (the old version is kept), or let it write several pages on its own. Export the finished story as Markdown.
- Turn a chat into a story. Choose Turn into a story from a chat's Export menu, or start one from a chat in the Story Maker, and pick the stretch of the chat to adapt. Each page retells its part of the chat closely, keeping what was said, and a long chat is read through its memory summaries so the plan covers all of it. An adventure's game master is treated as the narrator, and the game's own markers are left out.
🎲 Adventure Mode
- Let the GM choose builds a character with the game master. In the character builder, give your character a name and leave the scores unplaced, and the main button reads Let the GM choose. The game master then picks each score with you as the story starts, from the dice the game deals, and once a score is set it is yours. Before, a game that deals dice would not start until every die was placed.
- The game master no longer plays past your choice. Some models offered choices, then carried on as if you had picked one, sometimes answering a pick for you, and offered a second set. The reply now ends at the first set of choices or the first question for you.
🛠️ Card Forge
- Closing the What are you making? picker can't wipe a session any more. Left open while work went on, closing it reset the session, losing the conversation and the card. It now leaves a session alone once it has a message or a card.
💬 Chats
- A reply that repeats an earlier one is tried again by itself. When a model answered with an earlier message word for word, such as the greeting, Rin Chat now retries once on its own, whether or not auto-swipe is on. The repeated reply stays as a swipe.
- Every open chat follows the model setting you switch. Changing the generation config in one chat now reaches chats that were already open in other tabs, which kept the old one until Settings was closed.
- Choose whether avatars start small or large. Settings → Chat Display has a new Avatar size. Clicking an avatar in a chat still switches that chat between the two, and the Guide now mentions the click.
🧹 Fixes
Card Forge's proposed text box can be resized again. In "Apply this change?", dragging the corner of the Proposed box did nothing. It now grows and shrinks with the drag, as far as you like.
Right-click a picture to save it again. 0.8.7 removed the right-click menu on pictures, which also took away Save image, including for a freshly generated card image you had not applied yet. Right-clicking any picture now gives Save image, which saves it to your Downloads folder, and Copy image.
A reply no longer opens with an empty bullet after a thinking block. With Auto-close italics on, the asterisks in the model's thinking were counted together with the reply's, so a thought ending on a
*bullet with no blank line after it put an empty bullet at the top of the reply, and could leave a stray*at its end. The reply is counted on its own now.Qwen models in LM Studio no longer fail with "System message must be at the beginning". Rin Chat already caught that error and retried, but only fixed the system messages at the top, so a card with an Author's Note or a lorebook entry placed deeper in the chat failed again. For a model that gives this error, those notes now ride inside a nearby message of yours, marked as not your words, and no edit to the model's chat template is needed. Every other model is unchanged.
AI Restructure translates the whole card. Translate sent every passage in one go, and a long card could not come back in one reply, so only the first passage or two were translated. It now works through the card in parts and asks again for anything left out. A long card that translated one passage of 27 now comes back complete.
AI Restructure's Improve applies your instruction to the rest of the card again. Some models answered the second pass in a format it could not read, so the greetings and examples were left unchanged with an error. That reply is read now, and so is a reply missing a closing bracket.
Rin Chat Update Notes - Version: 0.8.7
19 October 2026
🎲 Adventure Mode
- The game master can walk a new player through building their character. Leave the sheet's abilities blank, or ask only some of them in an
as sheetform, and the game master may choose the rest with you as the story starts, recording each one once. After that the score is yours, and the game master can't change it, as before. - The character sheet you open now shows the numbers you play with. Abilities changed on the sheet in the sidebar or by a later form didn't reach the character builder, and the game master was told both the old and the new numbers. Reopening the builder or leveling up could also put the old scores back. The builder, the game master and level-ups now all read the sheet.
🛠️ Card Forge
- Card Forge moves on when a model gets stuck repeating itself. A model that started repeating one passage kept going until it ran out of room, which could take close to a minute before the Forge tried another way. It now stops as soon as the same passage repeats four times and tries the next way, and an empty reply is no longer accepted as a blank card.
⚙️ Settings
- The usage statistics now count a day the app was left open and used. Rin Chat already reported each launch. An app left unlocked for days sent nothing after that, so it looked unused. Now the first click or key press of a day that had no report sends one, with the same fields as a launch and nothing about what you did. Settings, Onboarding and the Guide say so where they list what is always sent.
🧹 Fixes
- AI Restructure no longer blanks the core personality or fails on a stray quote. Some models write the core personality as a list of sentences, which came back empty, and a quotation mark the model forgot to escape made the whole reply fail as invalid JSON. Both are read correctly now, in Card Forge too.
- Ctrl+Z undoes typing on Linux. On Linux, Ctrl+Z did nothing in any text box, so text deleted by mistake in a card or anywhere else had to be retyped. It now undoes, and Ctrl+Shift+Z or Ctrl+Y redoes.
- Spellcheck works in the Linux AppImage on Fedora, Arch and other non-Ubuntu systems. The AppImage only looked for spelling dictionaries where Ubuntu keeps them, so elsewhere no word was ever underlined. It now uses your system's own spellchecker when there is one.
- A reply cut off by a dropped connection is no longer saved as finished. When a provider's connection closed partway through a reply, Rin Chat saved the fragment as if the model had stopped there, with no sign anything went wrong. A long enough fragment is now kept with a note that it may be cut short, and a short one shows an error so you can try again.
- Replace all, New for all and Skip all act at once. When an import matched cards already in your library, those buttons only changed every row's choice and you still had to press Apply, so they looked like they did nothing. They now apply the choice to every card straight away. Apply still applies the choices you set row by row.
Rin Chat Update Notes - Version: 0.8.6
18 October 2026
📝 Prompts
- Compare your prompts with a card's. A Compare with mine button on a card's System prompt field, and Compare with a card in Settings, System Prompts, put your main system prompt and jailbreak next to the card's system prompt and post-history instructions. Lines that say the same thing are marked on both sides, a note says which one is actually sent (by default a card's own system prompt replaces yours), and you can trim either side right there and save.
- Card Forge can see your prompts. A new Show the guide my prompts switch gives the guide your system prompt and jailbreak as reference, so you can ask it to trim what a card repeats. It never copies them into the card unless you ask.
- A prompt saved from Settings reaches open screens. Editing a card's prompt from Settings while its editor was open could be undone by the editor's next autosave, and open chats kept using the old prompt config. Both now pick up the change.
📘 Guide
- Rin fits beside the Guide on ordinary screens. She only appeared next to the Guide in a very wide window, so on a 1920-wide screen with Windows scaling she never showed up. She now measures the room actually beside the article and shrinks to fit, and when a window is too narrow even for that, a new button in the Guide's header pops her out to float over your desktop.
🗣️ Voice
- Chatterbox reads the narration too. Chatterbox skipped everything written between asterisks, so in a roleplay reply, where the narration is usually in italics, it read only the quoted dialogue. It now reads the narration and only leaves out short actions like laughs or sighs softly, which it would otherwise say out loud as words.
🌐 AI Character Cards
- Animated cards up to 5.5MB can be uploaded. aicharactercards.com takes animated card PNGs up to 5.5MB, but uploading from Rin Chat stopped every card at 2MB. An animated card can now be up to 5.5MB; a still card is still limited to 2MB.
🛠️ Card Forge
- Card Forge notices clear themselves. "Saved to your library" and the other notes under the conversation stayed until the next message. They now go away after 15 seconds, and each has a Dismiss link to close it sooner. An error that offers a fix button stays until you use it or dismiss it.
⚙️ Settings
- Continue truncated replies is off by default. Each continuation sends the whole prompt again for the rest of the reply, so it now only runs if you turn it on in Settings, Automation. If you never changed it, it is off after this update; if you turned it on or off yourself, your choice is kept. When replies keep stopping mid-sentence, raising Max response tokens in your generation config is usually the better fix.
Rin Chat Update Notes - Version: 0.8.5
17 October 2026
💬 Chats
- Find in chat. Press Ctrl+F (Cmd+F on macOS), or the new search button in the chat header, to search every message in the chat, including ones far up the history. It shows how many matches there are, steps through them with Enter and Shift+Enter, highlights each one and scrolls to it, and can match case. Handy for checking whether a name has stayed the same all chat.
- Delete a chat from All chats. Each chat in the list has a trash can now, after asking, so clearing out old chats no longer means opening each character first. Shift-click it to skip the question. The trash can only shows when you point at a chat, so the list stays calm, and a chat you delete there also closes if it is open in a tab.
🔎 Search
- Ask from the search box, and land on the setting. A question typed after
?:in the search box (Ctrl+K) now gets the same answer Rin gives: from the Guide and from Settings, appearing as it is written. When the answer names a setting, its link opens Settings right at that row.
🎲 Generators
- Roll how many, too.
[Create Party Member x1-3]now rolls a count from 1 to 3 and creates that many. A count could only be a fixed number before, and a macro in its place, likex{{roll::d3}}, was ignored, because tags roll before macros are read. Withas=, a ranged count always saves numbered results and a.count, even when it rolls one.
🖼️ Images
- A Negative prompt box. The chat picture prompt, the card art generator and the card images generator each have a Negative prompt box. What you type is added to the style's negative instead of replacing it, and is remembered for next time. It shows for A1111/Forge, SwarmUI and ComfyUI, and for the NanoGPT image models that accept a negative prompt, such as Bria Fibo, Qwen Image, Z Image Turbo and HiDream; with those models the style and card negatives are sent too.
- Style negatives reach every picture. The card art generator sent no negative prompt at all, a style edited while a chat was open only applied after reopening the chat, and SwarmUI replaced a preset's own negative instead of adding to it. All three are fixed.
🧹 Fixes
- Documents right after the thinking render. A reply that started its first
[[doc:]]or[[reveal:]]block on the same line its thinking ended on showed the whole block as raw text. It is drawn as the document now. - The Thinking block opens and scrolls while a reply streams. On a fast stream, clicking Thinking often did nothing and its scroll bar would not drag, because every new word rebuilt the block under the pointer. The block now stays in place while its text grows.
- Calmer delete buttons in lists. Behavior rules, speech patterns, generator fields, generators, custom macros, shared lorebooks, tags, memory pins, card images and group members each carried a glowing red button on every row, the loudest thing on the page. They are red outlines now, and red only fills in when you point at one.
- Card Forge keeps both halves of a request. "Make her colder and add a generator for her moods", or a lorebook entry plus a change to her, now keeps the change too instead of quietly leaving it out. A message that only mentions her name ("make her hate her name") no longer goes straight to a Name rewrite, and "rename her to Mara" after a lorebook reply keeps the new name.
- Enter adds the tag you typed. Typing a tag that already exists, like "smut" or "elf", and pressing Enter added a longer tag containing it. It adds the one you typed now, and a tag you delete from the chat's card drawer stays gone.
- Quick start no longer builds from an old request. Edit Your request on the plan and Create waits until you Regenerate, so the character matches what you asked for. Cancel while the character is being saved no longer leaves you able to create it a second time.
📖 Lorebooks
- The lorebook budget keeps your most important entries. When there was more lore than room, the lowest-priority entries were the ones kept. Always-on entries and the highest order now go in first.
- Regex keys from SillyTavern files work. A
/pattern/key in an imported World Info file was matched as plain text and never fired. Regex keys also follow their own flags now, as in SillyTavern:/AI/matches only "AI", and/ai/imatches any case. - Before and after Author's Note mean what they say. Entries set to those positions now sit around the Author's Note instead of in the system prompt.
- Smaller fixes. An entry can belong to several inclusion groups (
weather, mood). A regex with commas in it, like{1,2}, is no longer split apart when you edit Keys. Whole-word keys work with Devanagari and other scripts that use combining marks. Character lorebooks imported from cards place SillyTavern's example and outlet positions the way shared lorebooks do. The lorebook Test panel follows your global matching settings. The Audit now warns about a key written as/pattern/in an entry where "Keys are regex" is off, since it would match as plain text. - Story-written entries stay put. Editing an entry the story wrote could delete entries the story added while you typed, or bring back ones a rewind had removed. Entries whose names contain a comma can be edited and deleted again.
💾 Backups and import
- Backups hold everything they should. Chats you kept after deleting their character were left out of every full backup, and voice provider settings were left out of backups and settings exports. Both are included now, with API keys removed.
- Restoring keeps what you added since. A restore or settings import replaced your providers, Direct Chats and saved voices with the backup's copies, so anything added on this device after the backup was lost, API keys included. They are merged now.
- Exported settings are safe to share. The settings file no longer carries your Direct Chat conversations, notes, usage history or card version history. Full backups still do.
- Clear failures instead of quiet ones. One unreadable setting no longer stops a whole backup; it is listed as skipped. A library too large for one backup file says so, instead of writing a backup that restores only a few cards, and a damaged backup file is reported instead of restoring nothing.
- Smaller fixes. Importing many cards no longer leaves the app stuck behind the progress window when a file cannot be read, and dropping cards twice in quick succession no longer imports them twice. After cancelling an import, picking the same file again works. On Windows the import dialog remembers your last folder. Exported chats keep their names in non-Latin scripts, and backups are written to disk more safely.
🧩 Regex scripts and macros
- Dice and random picks in a regex script roll fresh. A script that adds
{{roll:d20}}or{{random::...}}to every message wrote the same value into every reply. Each message and each token now rolls its own. - Replacements understand full macros.
{{if}}...{{else}}...{{/if}}blocks printed both branches, and nested macros like{{setvar::who::{{user}}}}showed up as raw text. Both work now. - Scripts from SillyTavern behave as they did there. An imported script uses the flags it was written with, so
/cat/replaces only the first match, as in SillyTavern.$0inserts the whole match, trim strings apply to groups, and scripts that change the saved message also run on continued replies, on messages further back in the chat, and in the Discord bot. They no longer touch the thinking block. Scripts you made in Rin Chat behave as before. - Safer scripts. A regex script can no longer break
[code]blocks or insert buttons, more slow patterns that could freeze the app are blocked with a warning, and a damaged saved script no longer crashes the chat screen. - Smaller fixes. The Discord bot no longer posts raw
{{macros}}. Streaming replies show the same script results as the saved message.{{datetimeformat}}handles month and day names such asMMM. Group-only greetings use the right character's details and keep the variables they set. Markdown and text chat exports show filled-in macros.
⚡ Prompt caching
- Replies can reuse the start of the prompt. Providers that cache prompts skip work they already did when a request starts the same way as the last one, but triggered lorebook entries, recalled memories, the Adventure sheet and the scene sat near the top and changed it almost every turn. With the new Cache-friendly prompt order setting (Settings, Memory & Context, Advanced) they sit near the end of the chat instead. In testing, most of each new prompt was reused.
- Changing notes no longer move your chat to another server. The provider picks which of its servers answers from the system part of the prompt, so a lorebook entry, game state or recalled memory that changed between turns sent the chat to a server without the cache. With Prompt caching on, those notes are sent as context instead, and the system part stays the same.
- Long chats trim in steps. Once a chat fills the context, older messages are now dropped several at a time every so often instead of one every turn, so the rest of the prompt stays the same between turns.
- The macro check points out macros that change every turn.
{{time}}or{{lastMessage}}in a card's description, personality, scenario or system prompt changes the start of every prompt. The check suggests the Author's Note or post-history instructions instead. - No repeat requests when the model runs out while thinking. When a reply used its whole token limit on thinking, auto-swipe asked again up to three times, and each time ran out the same way. It now stops after the first and tells you how to raise the limit.
🧠 Memory
- Long chats keep room for the reply. Once a chat filled the model's whole window, every request asked for more than the window held, and providers that refuse an over-long request failed on every turn. History is now trimmed to leave room for the reply.
- Memory sees what the model sees. The context meter and the line between what is sent in full and what memory covers now count attached files and pictures, so the messages around an attachment are no longer missed by both.
- Deleted and edited messages leave memory right away. They used to stay searchable until a whole memory rebuild finished. Memory now also keeps up with edits and with changes to its settings, recalls correctly in group chats, and stops building when you clear the index or delete the chat.
- Recalled memory stays a fair share. It can no longer take more than a quarter of the context.
- A summary no longer skips a message. Deleting a message while a chat summary was being written could leave a message out of every later summary. That summary is now set aside and written again.
🤖 Discord bot
- A slow picture no longer holds up the channel. When A1111 or SwarmUI took too long, the reply waited with it, for up to ten minutes. Now the reply goes out without the picture once the image timeout passes, and Settings says why.
- A turned-down picture no longer replaces the reply. In channels where people can ask for pictures in conversation, a request the model refused swapped the character's answer for "I can't make that picture." That answer is kept for
draw:now, and the character replies as usual otherwise. - The right image provider, and a channel that keeps its chat. A channel whose own image provider was deleted drew with your active provider, which could be a paid one. It uses the bot's image provider now. Two settings changes landing at once could erase each other and make a channel lose track of its chat, and a message deleted in Discord could reappear in the channel's history. Both are fixed.
- Long replies split cleanly. A reply long enough to be split could fail when the cut landed inside an emoji. Splits now fall between sentences in Chinese and Japanese too, and code blocks stay intact across messages.
🗣️ Voice
- Rin Chat has its own name in the Windows volume mixer. Voice and TTS audio showed up as "Microsoft Edge WebView2", so it was hard to tell which slider was Rin Chat's. It is called "Rin Chat" now, on every output device. The classic mixer (
sndvol) also shows the Rin icon; the Settings mixer keeps the Edge icon, which Windows takes from the process playing the sound. - Dictation that runs on your computer. Choose On this computer (Whisper) as the dictation engine in Settings → Voice Providers. Whisper runs inside Rin Chat, offline, so your voice never leaves the computer, and your words appear each time you pause. The model downloads once on first use: Tiny is smaller and faster, Base is more accurate. It detects the language you speak, or follows the provider's language setting.
- When Windows hears nothing, one click fixes it. Windows' own dictation hears only silence on many Windows 10 computers. When it ends without hearing you, the composer now offers Use Whisper on this computer, which switches dictation over and downloads the model. New installs on Windows 10 and on Linux, which has no built-in dictation, start with Whisper.
Rin Chat Update Notes - Version: 0.8.4
16 October 2026
⚙️ Settings
Basic and advanced settings. Settings now starts in Basic on a new install, showing what you need to set up a provider, chat with your characters and make the app look the way you like. Sampler tuning, reasoning protocol, prompt plumbing, memory and lorebook tuning, and the Macros & Regex and Document Styles pages wait behind a Show advanced settings switch under the search box. If you already use Rin Chat, nothing moves: you start with advanced settings on. Search and Ask Rin still find every setting, tagged Advanced where it is hidden, and opening one turns advanced settings on. An advanced setting you changed stays visible in Basic with a small changed tag, so a tweak you forgot about is never hidden.
Ask Rin finds settings for you. While Settings is open, an Ask Rin button waits in the corner of the window; press it and Rin appears, ready for your question. Ask her something like "how do I set the context limit?" and she opens the right page, scrolls to the setting and highlights it, with a line on what it does. If nothing fits she offers the closest matches to jump to, and without an AI provider she still goes straight to the best match. Drag her anywhere; she stays where you leave her.
One Rin, one memory. Beside the Guide, floating over the desktop and in Settings, Rin now reads the guide and every setting together. She explains from the guide and can point you at the setting that does it; a link in her answer opens Settings right at that row. She also knows the choices inside dropdowns, so asking about something like Chatterbox, Kokoro or LM Studio takes you to the page where it lives.
Rin answers faster, and lands in the right place more often. Her answer now appears as she writes it instead of all at once. She knows every setting in the app, not just the dozen closest to your words, so a question phrased your own way, or asked in another language, still opens the right row. She reads the exact paragraphs of the guide that answer you, and a link under her answer scrolls the Guide to that paragraph. She also knows your setup (which model you use, its context size, whether voice or pictures are set up), never your keys, chats or characters, so her advice fits.
Tell Rin when she got it wrong. A finished answer has a thumbs up and a thumbs down. Either one only notes the question in your own debug log, so you can include it when you report a problem; nothing is sent anywhere.
A Settings map in the Guide. Every page and setting, grouped the way Settings is, with a line on what each one does. Click any of them to open Settings right at it. It is built from the app itself, so it never goes out of date.
The Guide covers the rest of Settings. Chatterbox, the Local app card for LM Studio, Ollama and KoboldCpp, every advanced sampler (DRY, XTC, Mirostat and the rest, each explained plainly), the reasoning formats, smart commands in Card Forge, response language, the Adventure Mode GM prompt, every Chat Display card, card updates from aicharactercards.com, and a new Diagnostics & usage section. Rin answers from all of it.
Rin glances at your pointer instead of staring. While the pointer kept moving she held one still pose for as long as it moved; a look now lasts a few seconds before she goes back to her animation.
🔨 Card Forge
- Turn off the hidden-thinking notice for good. If you picked a reasoning model on purpose, the notice that it is spending tokens on hidden thinking came back on every reply. It now has Don't show again next to Dismiss, and Settings, Card Forge has a switch to turn it back on.
🧹 Fixes
Settings search finds every setting. Every setting on the Lorebook Activation page, the sampler dials such as Temperature and Mirostat, and the new-card defaults were missing from the search box. They all turn up now.
Rin animates even when Windows turns animations off. She stood frozen whenever Windows' Show animations setting was off, which Remote Desktop does for the whole session. She now always animates, and Settings, Sizing & Layout has an Animate Rin switch to keep her still.
No more "speech recognition: network" from the mic button. With the Built-in recognizer, dictation could stop at once with that error. A recent update to Windows' web view started offering a speech service that does not actually work, and Rin Chat picked it over Windows' own dictation. It now always uses Windows' dictation on the desktop app; a phone or browser using Rin Chat remotely still uses its own. And when Windows' dictation hears nothing at all from your microphone, the mic says so instead of quietly switching off. On some PCs Windows' speech service gets only silence from a working microphone; if Win+H in Notepad doesn't hear you either, pick another dictation engine in Voice Providers.
Rin Chat Update Notes - Version: 0.8.3
15 October 2026
🖥️ Local models
- Install Ollama on Linux in one click, without your password. An Ollama provider's page now downloads Ollama from its GitHub releases, about 1.4 GB, or 2.5 GB with AMD's ROCm libraries when an AMD card is your graphics card, and keeps it only if it matches the checksums Ollama publishes. It goes into Rin Chat's own folder rather than the system, so there is no terminal and no sudo. Start and Stop work as they do for KoboldCpp, Start Ollama with Rin Chat starts it whenever the app opens, and it stops when Rin Chat closes. It starts with a 16k context, so your characters fit. Models go to Ollama's usual folder, so a system-wide Ollama installed later finds them. If Ollama is already installed system-wide, Rin Chat keeps using that one.
🏷️ Tags
- Delete a tag from the tag box. In the card editor and the chat's card drawer, each suggested tag has a trash can that removes that tag from every card that has it, after asking. Shift-click it to skip the question.
🧹 Fixes
- Adding a new tag works in the chat's card drawer. The + Add new tag option sat at the bottom of the suggestions, out of reach in the drawer, and Enter added the first suggestion containing what you typed instead of the tag itself: "Smut" became "#CanBeWholesomeOrSmut". It is now first in the list, and Enter adds exactly what you typed, in the drawer and the full editor alike.
- Card Forge changes a built card's name when you ask. Once a card existed, the guide could still tell you to press Generate character, a button that is not there at that point. And a short "ok, update her name" right after it talked about lorebook entries was read as a lorebook request, so the new name never reached the review. The guide now knows the card is built and proposes the change itself, a field you name, like her name or appearance, is always kept, a change asked for in the same message as new lorebook entries is no longer dropped in favor of the entries, and anything left out is plainly marked as filtered by the app, not turned down by you.
- You can see at a glance whether a persona is your default for a character. The button beside the persona picker in a chat looked the same either way, and in some themes the highlight that marked it on was the same color as every other button. It now shows a broken link while the persona is not the default and a whole link once it is.
- Long provider names fit in the provider list. The Active tag sat beside the name and cut it short. It now sits at the right end of the line below, next to the config count.
Rin Chat Update Notes - Version: 0.8.2
14 October 2026
🚀 Quick start
Describe a character and start chatting. The new Quick start button beside New character in the Library opens one box: type the character and the scenario you want, and Rin Chat writes the whole card with Card Forge's own machinery, saves it to a Quick starts folder, and opens a chat on its first greeting. There is no back and forth: it plans the story and shows you the plan, which you can edit, regenerate from a tweaked request, or go back from, then writes the card from it and goes over it once more to deepen every field and fix format slips.
Choose who you play. Pick one of your personas (your default is already selected) or describe who you are in this story, such as "I'm a smuggler who owes her money", which becomes a temporary persona for that chat only. The card itself always calls you {{user}} and never takes your persona's name or looks, so it works with any persona later.
Real cards, nothing extra. The card is an ordinary one you can edit, reuse or delete, and Edit card works from the chat as usual. It has no lorebook and no generators, and it is an Adventure Mode card only when you ask for Adventure Mode. With an image provider set up, a checkbox also makes card art: once the character is written you see its image prompt to edit, regenerate or skip, and the picture arrives once the chat is open and never holds it up.
Every detail you typed makes it in. The plan opens with a list of everything your request states, the card is written with your own words beside the plan, and the last pass checks the card against both. Asking for a number of greetings or particular scenes gets exactly those.
Uses your Card Forge model. It writes three long replies, so a cheap model gives a thinner card. Each step shows how much it has written, and while the card is being deepened, Use the draft starts the chat with the card as it already is. Cancel stops it at any step and leaves nothing behind; cancelling while the card is written goes back to the plan.
📚 Library
- Keep personas out of All cards. A new switch in Settings → Card library, Hide personas from All cards, leaves persona cards out of All cards and its count. They still show under Personas, in Favorites and in any folder you put them in.
🖼️ Images
- Pick the checkpoint for Automatic1111 and Forge. The provider's Model box now lists the server's checkpoints, and the one you pick is what that provider draws with, in chats, the Discord bot and everywhere else. Add a provider per checkpoint, such as one anime and one realistic, and switch between them. The chosen checkpoint stays loaded afterwards, so the next picture doesn't reload it. Leave the box blank to keep drawing with whatever is loaded.
- Each Discord channel can draw its own way. A channel with pictures on can use its own image provider and its own picture prompt prefix, so one channel can draw on an anime checkpoint with its LoRAs and another on a realistic one. Blank uses the bot's.
🧹 Fixes
- A short reply's buttons stay off the character's picture. While a reply had only just started, its hover buttons were wider than the message and spilled left over the character's picture. They now spill to the right, into the empty side.
- New card art shows everywhere at once. After regenerating a character's art, the library showed the new picture but the card editor and chats opened afterward kept the old one until the app restarted. Every screen now shows the new art, including ones opened after the change and an editor already open on that card.
- OpenRouter names Rin Chat in its activity log. Requests from Rin Chat showed up there as an Unknown app. They now carry OpenRouter's app headers, so its logs and rankings list them as Rin Chat. Nothing is sent to other providers.
Rin Chat Update Notes - Version: 0.8.1
13 October 2026
🖥️ Local models
See which models fit on your computer. Settings → Diagnostics now measures your RAM and graphics card, lists GGUF models from Hugging Face, and shows the largest version of each that will run on the card, partly in RAM, or not at all. Copy the Ollama command or open the model in LM Studio straight from the list.
Set up a local model on its provider page. In Settings → LLM Providers → Add provider, choose LM Studio, Ollama or KoboldCpp as the Type, or open a local provider you already have: its Local app section shows whether the app is installed and running and what to do next, even before you save. The Type list notes which of them are running or installed. It also warns when this computer is too weak for a local model, when Ollama's context is too short for your characters, and when the provider points at an address where nothing answers.
Install Ollama and download models without a terminal. On Windows, one click downloads Ollama's official installer, checks it is signed by Ollama, and opens it. Once Ollama runs, download any model by name, or use Download in Ollama in the model finder, with progress and a Cancel button.
Download and run KoboldCpp from Rin Chat. On Windows and Linux, a KoboldCpp provider's page downloads the latest KoboldCpp from GitHub, the CUDA build for NVIDIA cards or the Vulkan one otherwise, and keeps it only if it matches the checksum GitHub publishes. Start KoboldCpp starts it in the background with a model, a context size and GPU layers chosen for your hardware, shows when it is loading and when it is ready, and points that provider at it. It stops when you click Stop or close Rin Chat, even if Rin Chat crashes.
Models for KoboldCpp in one click. In the model finder, Run with KoboldCpp downloads the version that fits your computer, every part of a split model, after checking the drive has room, then offers to run it. You can also use a GGUF file you already have.
Start KoboldCpp with Rin Chat. An opt-in switch loads your last model every time the app opens. If KoboldCpp stops on its own, its last lines of output are shown. Updates download beside the old version, and nothing is deleted unless you click Remove.
Start and stop LM Studio's server and Ollama from Rin Chat. Their provider page shows a Start button when either is installed but not running and a Stop button while it runs, and an opt-in switch starts it whenever Rin Chat opens. They are your own apps, so Rin Chat only stops them when you click Stop, never when it closes. On Linux, an Ollama that runs as a system service still needs the one terminal command shown, because it asks for your password.
Share one models folder with LM Studio. Choose any folder for model downloads, or use LM Studio's in one click, so the same multi-GB files serve both apps instead of being downloaded twice. Downloads are saved the way LM Studio arranges them, and KoboldCpp can run any GGUF in your models folder, Rin Chat's own folder or LM Studio's. Changing the folder moves nothing, and Remove never touches LM Studio's models unless that is the folder you chose.
Load and unload models from Rin Chat. An LM Studio or Ollama provider's page lists the models you have downloaded, with their size and whether each is loaded, and loads or unloads one in a click. Use in Rin Chat makes a loaded model the one your config for that provider asks for, and asks which config when there are several. A KoboldCpp provider marks the model it is running, and Switch to this restarts it on another one with the same settings.
🤖 Discord bot
- Export the bot's debug log for a bug report. Settings → Discord bot → Debug log saves just the bot's part of the app's debug log: its requests and replies, errors, connection changes, skipped and dropped messages, and when it posted, with a summary of its settings on top. It never includes the bot's token or any API key, and memory changes are logged by kind, not by what was remembered.
- The bot can draw pictures. Turn it on per channel under Settings → Discord bot → Channels: Only with draw: answers a message like "@Rin draw: a cat on a roof", draw: and requests also answers "send me a picture of you", and Also when the character wants lets the character send one with a reply, at most 2 per channel every 10 minutes. The bot's generation config turns each request into an image prompt, and turns down anything illegal with one plain sentence instead of drawing it. The picture goes under the character's reply, as the bot or with the channel's own identity. Choose which of your image providers it draws with under Pictures, along with a per-user cooldown, 60 seconds unless you change it, and a prompt prefix for the bot's own style. A channel with pictures on can also post every picture as a spoiler, blurred until someone clicks it. Each picture is also kept in the channel's chat in Rin Chat, with what it shows, so the character remembers what it sent. A picture that fails leaves the reply as it was and shows on the Last reply failed line.
🗣️ Voice
Install Chatterbox, a local voice cloner, from Rin Chat. Settings → Voice Providers has a Chatterbox section: pick Original, Turbo or Flash, each with how much graphics memory it needs, how fast it speaks and which style controls it has, and click Install. Rin Chat downloads uv from GitHub, checks it against the checksum GitHub publishes, then installs Python, PyTorch, Chatterbox and the model into its own folder, with progress, a Cancel button and the installer's output. It warns first when the drive is short of space or there is no NVIDIA graphics card, and nothing is deleted unless you click Remove.
Run it in the background. Start loads the model and Stop ends it; it also stops when Rin Chat closes, even if Rin Chat crashes, and an opt-in switch starts it with Rin Chat. It can unload the model after 5 to 60 minutes without speech to free graphics memory, and loads it again with the next line. Half precision, the default, uses about 1 GB less graphics memory.
Characters read their replies aloud in their own voice. Choose Chatterbox as the read-aloud backend and each character with a reference clip in its card's Voice section speaks in that voice; others use Chatterbox's built-in voice, except on Flash, which has none. If Chatterbox is stopped, Rin Chat starts it and says so while the model loads. Replies are spoken sentence by sentence, the next one generated while the current one plays, so speech starts about half a second after you press play once the model is loaded. Actions between asterisks and tags like (laughs) are skipped, since Chatterbox would read them out as words. Exaggeration, pacing and temperature appear only for the variants that use them, and a phone hears it through the computer.
Pocket TTS, a built-in voice that can sound like your characters. Choose Bundled Pocket TTS in Settings → Voice Providers. Kyutai's Pocket TTS runs inside Rin Chat on your processor, so there is nothing to install and no graphics card is needed: a reply starts speaking about a fifth of a second after you press play and is generated about twice as fast as it plays. It speaks English, German, Italian, Portuguese or Spanish with eight built-in voices. Each language downloads once, about 200 MB, and is checked against its published checksum before it is used.
Give a character their own voice. A card's new Voice section holds a short reference clip: a WAV or MP3 with about 10 seconds of clean speech, best part first. Set Pocket TTS's voice to This character's reference clip and each character speaks in their own; characters without a clip use Alba. Rin Chat learns each clip once and remembers it, and the clip travels with the card in bundle exports. Use a clip of your own voice, or of someone who has agreed to it.
Higher quality, if you want it. Pocket TTS's Quality setting offers Higher quality: a little clearer, about 490 MB per language, and about a third slower, still faster than real time.
Saved voices, a default voice, and a Test a voice box for Pocket TTS and Chatterbox. Settings → Voice Providers now keeps a library of voices for Pocket TTS and Chatterbox: add one from a WAV or MP3 file, the clip you just tested, or a character's clip from its Voice section, then play, rename or delete them. Any character can speak with a saved voice, picked in its Voice section, and a voice many characters share is learned only once. Mark one as the provider's default and characters with no voice of their own speak with it instead of Alba or the built-in voice, and Test a voice starts on it. Saved voices stay on this computer and travel in full backups; a card exports only a reference, so elsewhere it speaks with its own clip.
Every character can have their own voice, on any read-aloud backend. A card's Voice section now has a Voice picker for the backend you read aloud with: Kokoro's voices, Piper's (yours included), the voices Windows has installed, or the voices of an OpenAI-compatible, ofox or NanoGPT model. The provider's voice is the default. Each backend keeps its own pick, so switching backends never loses one, and group chats speak each character in theirs. The picks are only voice names, so they travel with the card in every export; a voice another computer doesn't have falls back to its provider's voice. Chatterbox and Pocket TTS still speak with the character's clip or saved voice.
💬 Chat
- Make Continue and Impersonate ask for instructions first. Two new switches in Settings → Chat Display swap what a click does: a plain click opens the instructions box, and Shift-click (or a long press on a phone) acts straight away.
🎨 Themes
- See-through library tiles. Settings → Theme & Colors has Card Library Tile opacity and Card Library Tile picture opacity sliders, like Bubble opacity, so your background shows through the character tiles and their pictures. Both are saved in exported themes.
🔄 Updates
- Read what's new before you update. The banner that offers an update now has a Version notes button, which opens that version's notes on rin.chat.
🧹 Fixes
- Settings messages no longer cover each other. Two notices at once, such as Saved. and a copied command, used to show only the last one. They now stack in the corner, and each stays for its own time.
- The Discord bot's nickname follows its character. In a server where every channel uses its own identity, the bot's nickname in the member list kept the name of a character that no longer answered there. It now takes the name and picture of a character that does.
- Read aloud skips forms, buttons and pictures. Every voice read a reply's interactive markup out loud, so a form was spoken field by field and a scene change read as "background: bar". Forms, choices, rolls, pictures, backgrounds, gauges, memory and expression markers, generator tags and the controls inside card HTML are now left out, on every voice engine.
- A reply that spent its token limit thinking says so. When a reasoning model used every token on thinking and never started its answer, the chat said it returned an empty reply, or kept a reply that was only a Thinking block, and quietly retried twice at the same cost. It now says the limit went to thinking and how to fix it, and offers Retry without reasoning. The Discord bot's Last reply failed line says the same.
- Updates survive a shaky connection. A download cut off partway, such as on a mobile hotspot, failed with "error decoding response body" until you pressed Retry. The app now tries again by itself, and if the connection keeps dropping it says so in plain words.
- A moderator's note on an approved card isn't shown as a rejection. My Listings now labels it Note from the moderators, in normal text instead of the red used for a rejected card's reason.
Rin Chat Update Notes - Version: 0.8.0
12 October 2026
🌐 Languages
- Rin Chat speaks Russian. Choose Русский under Settings → Sizing & Layout → Language. The whole app is translated, and the models answer in Russian too, from chat replies to titles and summaries, unless you set a different Response language under Settings → System Prompts.
🤖 Discord bot
- Characters can show how they feel. A character with expression images can now put one under a Discord reply when the moment calls for it, picked by the character itself from its own expressions, at most two per channel every ten minutes. Turn it off under Settings → Discord bot → Expression pictures. The bot needs the Embed Links and Attach Files permissions, so open the invite link again for a server it is already in.
- See what each bot reply costs. Under the bot's Generation config, a line now shows that config's max context, and warns when it is over 15,000 tokens: every reply sends up to that much of the card and the channel's history, so in a busy channel a large context uses a lot of tokens over time. About 10,000 is plenty for Discord.
- Write the bot's memory note yourself. Settings → Discord bot → Memory note holds what a character is told about the person it is replying to, and how to keep notes about them. Placeholders fill in that person's facts, how the character feels about them, a feeling score from -3 to 4, and the character's and person's names. If an edit drops something memory needs, such as
[[remember: …]], a warning says so, and Reset brings the original back.
🎨 Themes
- Resetting Chat tabs sticks. A theme with its own Your messages color put that color back on Chat tabs every time it loaded, so resetting Chat tabs never lasted past a restart.
- Buttons can have their own border color. Theme & Colors has a new Button borders color, so a theme can outline its buttons apart from the panels' Borders. Until you set it, buttons keep the darker shade of Buttons & accents they always had, and it follows that color.
- Backgrounds no longer slow down unlocking. Background images used to be saved inside the theme itself, so every one of them, in every saved theme, was read before the app opened. They are kept as separate files now and load only when the screen showing them is open. Existing themes are moved over the first time you unlock.
- Sharper animated backgrounds, converted faster. Animated WebP backgrounds are converted at a higher quality and in a little over half the time, and can be up to 7 MB once converted, up from 3 MB, from a file of up to 25 MB.
- Setting a background shows its progress. Converting an animation takes a while, and nothing on screen used to say so: the thumbnail now shows a spinner with the seconds elapsed, then a note with the size once it is set. If it fails, the reason is shown instead of nothing happening. You can leave the page while it converts; it is still set when it finishes, and the result is waiting when you come back.
📚 Library
- Find any chat picture without remembering where it was. All images, under All chats in the Library's sidebar, shows every picture generated in any chat, grouped by character with the chat it came from. Click one to open that chat at that picture.
📖 Guide
- Pocket Rin / Ask Rin. Rin now stands beside the Guide as a little animated sprite. Ask her anything about Rin Chat and she answers from the guide in a bubble, with links to the sections she used, reading while she works and reacting to the answer. When she has nothing else to do, she follows your pointer. On a window too narrow for her, the question box at the top of the Guide takes her place.
- Rin can float over your desktop. The arrow in her bar pops her out into a little window that stays on top of everything, so you can ask about Rin Chat from any app. Drag her wherever you like; she stays there, comes back at launch if you left her out, and steps away while the app is locked. The × in her bar puts her back in the Guide.
🧹 Fixes
A pinned chat's pin stays out of the way. In a chat's header, a pinned name showed its pin icon all the time; it now appears on hover like the other title tools.
The side panel's header no longer bounces. Scrolled a little way down the card editor or story sidebar, the header could flick between its full and condensed size, more so at some UI scales. It now settles.
Every message rolls its own dice.
{{roll}}and{{random}}came up with the same result in every message of a chat, so rolling{{roll:1d20}}each turn gave the same number each turn. Each message now rolls on its own, keeps its result whenever it is shown or sent, and a new swipe rolls again. Rolls already showing in older chats change once. The Playground's Reroll now rerolls these too.{{random::a,b,c}}picks one. Written with two colons and a comma list, as many imported cards do, it printed the whole list; it now picks one of them, as SillyTavern does.\,keeps a comma inside an option.A shared theme can't freeze the app. An animated background that claimed an enormous size could take gigabytes of memory to convert. Animations larger than 4096 pixels on a side are now turned away with a note before conversion starts.
A dropped connection is not sent twice. When a connection broke while a provider was still working on a reply, the app could send the same request again from its own side, costing a second reply, and then wrongly say the provider refuses in-app requests. Only a refusal that comes back at once is retried now. Several app windows learning these fixes at once also no longer erase each other's.
Chat pictures are only deleted with their chat. The weekly cleanup added in 0.7.8 also removed a picture whose message you had deleted from a chat you kept. It is gone: pictures now go only when you delete the whole chat, or a character together with its chats, and any picture a branch of that chat still shows is kept.
Clear history in the Discord bot stays cleared. A reply that was still being written when you cleared a channel's history brought the old history back as a separate chat. And a character's picture that failed to load once no longer removes the bot's avatar in that channel; it is tried again a few minutes later.
Discord memory is more careful.
[[forget: it]]or another very short request could delete a note that only happened to contain those letters; it now deletes nothing. A note cut off in the middle of an emoji could make every later reply to that person fail with some local servers, a memory marker cut off by the reply length cap was posted to Discord,[[feel: warmer because...]]and[[feel: +1]]were ignored, and two channels replying at once could lose one's note. All fixed, and Escape in a note's editor no longer saves the edit it cancels.Editing the chat lorebook's story entries is safe. Clearing an entry's text to rewrite it deleted the entry, retyping a name could replace another entry along the way ("Old Bob" to "Bob Jr" passed through "Bob"), and the panel could keep showing entries an undo, swipe or chat switch had removed, then write them back on the next edit. Edits now save when you leave the field, an empty box keeps the entry, and the panel always shows the chat as it is. A generator re-rolling into a renamed entry keeps its name and keywords, and a reply that auto-swipe, the Story Director or Continue rejected no longer leaves its lore behind on cards outside Adventure Mode.
Exports never replace an earlier file. Exporting a card, lorebook, theme, chat or backup whose name was already in your Downloads folder overwrote that file. The new one now gets a number instead, like
Ada (2).png.Closing the app no longer undoes lorebook edits. A lorebook, generator or document style open in Card Forge was saved back when the app closed even if you hadn't changed it there, so an edit made in its library in the meantime was lost, and one you had deleted came back.
Undoing a settings fix changes the right config. After switching generation configs, Undo wrote the old values into the one now active and left the fix on the other.
Card notes ask before showing outside pictures, every time. Notes that pulled in a picture through a reference-style markdown link skipped the question and loaded it straight away.
Pick lists and questions at the end of a sentence still appear. A reply that ended a sentence with
[[pick 2: …]]or[[ask: …]], which Continue often does, showed the raw text instead of the checkboxes or the answer box.A provider that can't be reached says so plainly. Direct Chat, Ask Rin, the AI edit buttons and Image Studio showed "TypeError: Failed to fetch"; they now say the provider couldn't be reached and what to check, as chats already did.
A zoomed chat picture fits the window. A tall picture ran past the bottom of the screen and sat under the maximize and close buttons. It now fills the window's height below them, with its prompt in small text a scroll below.
Theme & Colors labels fit in every language. A longer label, such as Bubble opacity in Russian, ran into the slider or the font field beside it. The labels now take the room they need.
An ofox image provider lists its models while you set it up. Before it was saved, its model list stayed empty and said it couldn't list models; it now fills in straight away.
Asking the guide finds the right answer more often. Questions in everyday words ("make Rin bigger", "move my chats to a new computer", "connect LM Studio", "roll dice") now reach the section that answers them, the macro reference can be searched and asked about at last, and in the search box (Ctrl+K) a plain
?asks the guide as well as?:.Guide search finds every word. It used to look for your words as one exact phrase, so "animated background" found nothing in a section about animated WebP backgrounds. Each word can now appear anywhere in a section.
The Guide is up to date. Its Discord section covers memory, generators, expression pictures and the seven invite permissions, Appearance covers button borders, glow and animated backgrounds, and there is a section on Ask Rin.
Rin Chat Update Notes - Version: 0.7.9
8 October 2026
🔌 Providers
ofox is a built-in provider, for chat, pictures and voice. Pick it from the Type list under LLM Providers or Image Providers, or as the read-aloud or dictation backend under Voice Providers, and paste your key; the address is filled in. Each place lists only the ofox models that do that job: chat models for chat, image models for pictures, speech and transcription models for voice. ofox refuses requests from inside an app, so Rin Chat sends them itself from the very first one.
Gemini and ElevenLabs voices work through OpenAI-compatible speech. Read-aloud always asked for mp3, which Gemini voices refuse, so they failed with "unsupported response_format". It now switches to wav for a model that refuses mp3 and remembers that. The Voice field also offers each model's own speakers: Gemini's named voices, ElevenLabs' default voices by ID and OpenAI's voices. Left empty, it uses the first of them instead of OpenAI's "alloy", which Gemini and ElevenLabs do not have.
Model lists show only chat models. A provider that lists everything it offers, as ofox and OpenRouter do, filled the chat model picker with image, video, speech and embedding models that cannot answer a chat. Those are left out now, wherever the provider says what each model is for.
Providers that block in-app requests now work. Some hosted APIs, ofox among them, refuse any request made from inside an app's browser view because they send no CORS headers. Nothing on the user's side could fix that, so chat, the model list and the Test button all failed with "Failed to fetch" and advice meant for LM Studio. The app now notices when a provider is blocked this way but reachable, sends that provider's requests itself instead, and remembers it under Learned fixes in the generation config, where it can be cleared. The first blocked request is retried with no error shown. A local server without its CORS switch turned on now works the same way.
🤖 Discord bot
Characters remember the people they talk to. In Discord, a character now keeps up to 20 short notes about each person, written by itself as it learns things, and recalls them only when it replies to that same person. It also forms a feeling about each person that warms or cools a step at a time and fades back toward neutral over the following weeks. Each character keeps its own. Settings → Discord bot lists everyone it remembers, where you can read, edit, add and delete notes, set or reset how it feels, or clear a person entirely, and a Remember people switch turns it all off. The notes stay on this computer and are left out of backups.
Generators work in Discord. A card's
[Create …]generators now roll for the bot as they do in a chat: tags in the card and its lorebooks give the same result every turn of that channel's chat, a tag in the bot's own reply rolls once and is saved with it, and a tag someone types in the channel rolls into what the character reads while Discord still shows what was typed. Hidden results reach the character but are never posted.
🎨 Themes
Buttons can glow. Turn on Button glow in Theme & Colors and the accent and action buttons get a lit edge and a soft halo in their own color, made for neon and other bright themes. It saves with the theme and travels in a shared .rctheme file.
Backgrounds can move. An animated WebP now plays as a background instead of freezing on its first frame, and it keeps playing after a shared .rctheme is imported. It is downscaled and compressed like a still background, frame by frame, and can be up to 3 MB once converted. Animated backgrounds are set from the desktop app.
Background images say what size to use. The background picker now names the shape that fits the default window (3:2, 1920 × 1280 suggested, 1280 × 860 at least), and its previews are drawn at that shape, so the crop you see is the crop you get.
⚙️ Settings
- Card Forge has its own settings page. Smart commands, which decide how the forge reads what you type to its guide, were tucked away under Chat Display. They now live in Settings → Card Forge, and searching for them lands there.
🔧 Fixes
The Discord bot goes by the character's name. Set to use the character's name, the bot took the card's Display name instead, the label meant only for your card lists. A card whose display name said something like "DISCORD- Bimbot" put that on the bot, and Discord refuses any name containing "discord". It now uses the plain Name, the one the character writes as.
The Active badge in settings lists is whole again. Next to the active provider, config or prompt, its bottom edge was cut off. It now fits its row.
The Lorebooks background fills the window. It was painted only behind the centered list, and stretched to the list's full length, so most of the picture was lost. It now covers the whole window and stays put while the list scrolls.
Roll buttons and highlights take on your theme. The soft tint behind Adventure Mode roll buttons, the selected model in a list and a few hover states was a fixed purple, so it stayed purple on any theme. On a theme with a light accent color, such as brass, the roll buttons also drew dark text on that dark tint and were hard to read. The tint now follows your theme's Buttons & accents color, and the roll buttons use your normal text color.
Rin Chat Update Notes - Version: 0.7.8
8 October 2026
🎲 Making and sharing games
- A game can have its own point buy. A card's character sheet could deal a fixed set of scores, or keep D&D's 27 points across 8 to 15, but not give players a budget of their own to spend.
"points": { "total": 10, "min": 0, "max": 4 }on the abilities (or on any group) now gives the character builder a point buy with that budget and range, one point per step, and party members the app builds for you are kept to it too. A game with a deal can offer both.
✨ New
Your creator notes on every card. The New cards settings could already fill in your creator name on new characters. They have moved to Settings → Automation, and now also take your creator notes, a short bio and your links, which every new character and every card Card Forge writes starts with in Public Creator Notes. Turn off Fill them in on new cards to keep new cards empty. On any card with an empty Creator or Public Creator Notes field, an Insert yours button beside the field fills it in.
A Usage page shows what every model call has cost. Chat statistics only counted the chat they belong to, so Card Forge, AI Restructure, image prompts and everything run with no chat open were never counted anywhere. Settings → Usage now totals every request on this device for today, the last 30 days and all time: tokens sent and received, tokens read from and written to the provider's cache with the share of the prompt the cache answered, and cost in each provider's own currency. It breaks them down by model, by provider and by what they were for, draws a bar for each of the last 30 days, and says how much was reported by the providers and how much is estimated. Requests made from a phone through Remote Access count too. Clear usage history starts it over.
A character can answer in your Discord server. Make a bot in Discord's developer portal, paste its token into Settings → Discord bot, and invite it with the link that appears there. Turn on the channels it should answer in, pick a character for each, and choose whether it answers when @mentioned, when @mentioned or replied to, or to every message except people replying to each other. The bot writes with your own provider and key, using your active generation config or one you pick just for it, and it is online only while Rin Chat is open and unlocked on this computer. A per-user cooldown, a reply length cap and a Pause switch keep it in check. People in Discord can only talk to the character: no tools, no image generation and no access to your settings, files or other chats, and a reply never pings anyone except, in a channel with its own identity, the person it answers. Its replies show as their own purpose on the Usage page.
The bot looks and remembers like the character. In each server it takes the character's name and picture, and a channel can have an identity of its own, posting through a webhook, so different channels can be different characters. Names can be the character's or one you type, and changes reach Discord on their own. The invite link asks for Change Nickname and Manage Webhooks; open it again for a bot you already invited. Each channel keeps an ordinary chat with every message under the name of the person who wrote it: open it from the channel's row to read it or delete single messages, or clear it to start fresh. It follows Discord, so a message deleted or edited there is deleted or edited in the chat too.
🔌 Providers
- Token counts come from more providers. Most OpenAI-compatible providers only report how many tokens a streamed reply used when asked, and the app never asked, so chat statistics showed estimates for them. Every streamed request now asks. Cache figures are read in both spellings providers use, so a provider that reports tokens written to its cache now shows them in chat statistics as Written to cache. An endpoint that refuses the request is retried once without it, with no error shown, and remembered under Learned fixes in its generation config, where it can be cleared.
💬 Chat
The context meter matches what the provider counts. The meter estimated tokens as four characters each, which undercounts most languages other than English: a chat in French read about 8,900 tokens while the provider billed 13,000 or more for every request. Once a provider reports how many tokens a chat's request really used, the meter scales its total and every segment to match, and its breakdown shows the last request's count as reported by the provider, with how much of it came from the cache. Trimming uses the same correction, so a chat that counts heavier than the estimate drops old messages in time instead of sending more than the context limit. The meter also counts the lorebook entries that fired by keyword on the last reply, which it used to leave out.
No false error when a provider refuses the seed. Some endpoints reject the random seed the app sends with each request. The app already retried without it and the reply arrived, but the chat still opened with a "failed" notice for the first attempt. A refused seed is now handled quietly, like the other fields the app retries without.
🔧 Fixes
Deleted chats give back the space their pictures used. A picture generated in a chat stayed on disk after the chat or the message was deleted, so the image folder only ever grew. Once a week the app now removes generated pictures that nothing refers to any more. A picture still used by a branch of the chat, or less than a week old, is kept.
The import log shows every import. Two imports that started in the same millisecond, which a bulk import makes likely, listed only one of them once you loaded more of the log. Both appear now.
A party sheet edit survives switching chats. An edit to a Dungeon Master party sheet made just before switching to another chat could be lost. It is now saved to the chat it was made in.
Card Forge keeps "rock 'n' roll" intact. When it turned single-quoted speech into double quotes, a lone quoted letter such as the 'n' in "rock 'n' roll" was treated as a spoken line. It is left alone now.
Find & replace shows where the match is. Jumping to a match selected it in its text box, but in the app's faint selection color, which barely showed on a dark theme, so it looked as if nothing had been found. While Find & replace is open, the match is now selected in bright orange. Matches in an Adventure Mode card's Ruleset, GM style, Extra GM guidance and character sheet template were also listed only as "Metadata"; the list names each field now. Three kinds of match went to the wrong place: one in a regex script or a document style scrolled to the top of the editor, a document style other than the one on screen was never opened, and a lorebook key could land in the entry's title when the two read the same. Each one goes to its own box now.
Settings opens cleanly in the first seconds after signing in. Opening Settings before the app had finished loading it in the background showed a "Loading" panel filling the bottom half of the window, with the card library squashed into the top half. The loading panel now sits over the window where Settings is about to appear, and nothing behind it moves. The search window had the same problem.
Links inside Settings and other windows open again. A plain link inside a dialog, such as the Discord developer portal link in Settings, did nothing when clicked: the dialog kept the click from reaching the part of the app that opens links in your browser. Links open in your browser from anywhere in the app now.
Imported card names drop stray HTML. A card named with markup, such as
<b>Luna</b>, came in with the tags in its name, which then showed up around the app. Paired tags are taken out on import, so it comes in as Luna. Cards already in your library are left as they are.
Rin Chat Update Notes - Version: 0.7.7
7 October 2026
🔒 Safety
A message can only draw inside itself. Card and model text could already not cover the top bar, Settings or the message box, but a single element in one reply could still be drawn over the whole conversation: every other message and every real choice button. What a message shows now stays inside that message. A wide table in a reply scrolls sideways instead of running off the edge.
The app's windows only ever show the app. If anything ever tried to take a Rin Chat window to another website (a link or a form that got past the other safeguards), the app now refuses, so a foreign page can never appear inside Rin Chat looking like part of it. Links you click still open in your browser as before.
The phone remote page tells the browser what it may not do. It can no longer be shown inside another website's page, and no form on it can send anything anywhere.
✨ New
Forms in a reply. A card or a reply can ask several questions at once:
[[form: Your character | Name: text | Age: number 18-99 | Class: Fighter, Mage, Rogue | Has a pet: checkbox | as hero]]draws a form with a text box, a number box, a list to choose from and a checkbox. Fields can be long text and can be marked optional; Send points at anything missing or out of range. The answers arrive as your message, and withas heroeach one is also saved as a variable (hero_name,hero_age). Forms are drawn by the app itself, so there are no password or file fields, and nothing in one ever leaves the chat. The Guide's Choices section has the details.A form can fill in your character sheet. On an Adventure Mode card, a form ending in
as sheetputs its answers on your character sheet as your own stats, beside what the builder and the game master put there, where you can edit them and the game master reads them every turn. On an ordinary card, a reply can show a form's answers back as a sheet in a document block, and the values stay current as they change.Import a chat, into any character. A chat exported as JSONL could not be brought back in: the import existed, but nothing in the app opened it. A character's page now has Tools → Import a chat, which adds a JSONL file (Rin Chat's own export or SillyTavern's) as a new chat on that character and opens it, under the chat's own title. That also carries a conversation over to a duplicated or reworked character: export it from the old one, import it into the new one.
Fixes from the developer, applied for you. When the developer gives you a fix code for a problem, paste it into Settings → Diagnostics → Apply a settings fix. A window shows every change beside what is set now, you choose which to keep, and Undo puts them back. Only codes signed by the developer work, and a fix can only change generation, connection and display settings, never your keys, the provider or model you use, or your data.
🔧 Fixes
Your character's stats sit in the Character section even without an Adventure Persona. In a chat with no Adventure Persona, the stats the game master kept under your name were listed under Stats as "the man agility", and a roll's
modorbonuscould not find them. The sheet now files them under your name in the Character section, and rolls read them from there.An escaped macro in a card reaches the model as a macro. Writing
\{\{.name\}\}in a card's description or rules is how a card shows the model a macro to copy without it being filled in first. The model received it with the backslashes still on, and copied those into its replies, where the macro then printed as text. The backslashes now come off on the way, the same as they always did everywhere else.Card Forge lorebook entries are no longer lost over a missing label. Some models, GLM among them, write an entry's text straight under its keywords without the CONTENT label. The Forge could not read those entries, dropped them when you applied them, and then said nothing had changed because the rewrites matched what the card already held, which was not true. Those entries are read and added now. When a change really cannot be applied, the Forge says so and names it, instead of saying it matched.
Open a lorebook, generator or style from inside the Card Forge. Choosing Open… for a lorebook in a new session sent you to the Lorebooks screen to find that book's forge button, which looked like there was no way in at all. It now lists the ones you already have right there, with a search box once there are a few, and picking one starts the session on it.
A fresh session for the same lorebook. The sessions menu offered "New session for this card" only to card sessions. A lorebook, generator or style session now gets "New session for this lorebook" (or generator, or style), which starts a clean conversation on the same one and keeps the old session in the list.
The app says when you opened an older copy of itself (Windows). With Rin Chat installed in two folders, an update went to the folder the installer last used while your shortcut kept opening the other one, so every launch was the old version asking to update again, however many times you updated. The app now notices it is not the copy updates go to, says where the updated one is, and Settings → Updates lists every copy it finds with a button to show each in its folder.
Closing the window no longer loses what you were typing. Settings fields save when you click away from them, and several panels save a moment after you stop typing. Closing the app window (or a popped-out Settings window) did neither, so a Game Master ruleset typed into its box and closed with the X was gone. The window now saves everything pending before it closes. If something hangs, it still closes after a few seconds, and a second click on the X closes it straight away.
Copying from a chat works on a phone. Pressing and holding on a message to select text opened the app's "regenerate this part" menu on top of the selection, which hid the phone's own Copy button and covered the handles you drag to widen it. On a touchscreen that hold now selects and copies text the normal way. With a mouse, right-clicking a selection still opens the regenerate menu.
The card health check helps with variables.
{{test_var}}was reported only as a macro Rin Chat does not know. When it is a plain name, the check now says it is probably a variable and shows how to write one:{{.test_var}}for this chat's,{{$test_var}}for a global. A name one or two letters off a real macro gets a "did you mean", such as{{random}}for{{randm}}. And a variable the card reads but nothing in the card ever sets is flagged as a tip, since it stays empty (and any condition on it is false) until something sets it. That tip stays off on Adventure Mode cards and cards that use story variables, where the model sets them during play.One card with an oddly saved field can no longer crash the library. A card whose example dialogue was saved as one block of text instead of a list (the SillyTavern shape, written by hand) stopped the Characters screen from opening at all, with "parts.map is not a function". The library now reads every card through the same clean-up the editor uses, and that clean-up keeps such text: example dialogue is split into its separate examples, and any other list field keeps the text as its one item instead of dropping it.
The sprite panel's edge only shows when you point at it. The line down the side of the character expressions panel cut through the chat background all the time. It now appears, with the resize handle, only while you hover the panel or drag it wider.
Choices show as buttons when the model spaces the colon. Some models, often when replying in French, write
[[choice : Go]]with a space before the colon. The app did not recognize that as a choice, so the options sat in the reply as raw text with no buttons. A space there is accepted now, for choices and every other directive.
Rin Chat Update Notes - Version: 0.7.6
4 October 2026
🔒 Safety
Card and model text can no longer draw a working form, or cover the chat. Text from a card is shown with its formatting, and two things were getting through that have no place in a message. One was a real form, with a password box and a button that sent what you typed to another website. The other was a block pinned over the whole chat, which could hide everything under it. Together those could imitate the app's own lock screen. Forms, text boxes and buttons written into a card or a reply are now shown as plain text, a pinned block stays inside its message, and a clickable image map opens in your browser like any other link instead of replacing the app. A card's own choices, questions and pickers are unaffected: those are drawn by the app.
A card can no longer crash a chat with a runaway variable. A variable can be set from its own value, and one that doubles itself a few dozen times is larger than a program is allowed to hold. Reaching that limit took a second and a half and then failed in a way that brought up the app's error page, each time the message was drawn. Since cards are downloaded, that was a card that could make its own chat unusable. A variable now holds at most 100,000 characters, and a macro that goes wrong for any reason is shown as written instead of taking the screen with it.
A card with a broken character note no longer breaks its chat. A card file can carry a note with a depth that is not a number or a role the model's API has never heard of. The first put the note above the system prompt, the second made every message in that chat fail. Both are now read as the defaults when the card is opened.
🧠 Thinking models
A short answer from a thinking model no longer disappears. With "trim incomplete sentences" on, a reply that did not end in punctuation, a single word, a name, a number, a plain "Yes", was being erased whenever the model had thought first. The trim looks for the last period and cuts after it, and it was looking through the thinking as well as the reply, so with no period in the answer it found one in the thinking and cut there, taking the answer with it. What was left showed as a "Thinking…" that never finished, and auto-swipe then rerolled it several times for being empty. The trim only reads the reply now.
Continue no longer prints the model's thinking into the reply. A thinking model thinks again before it continues, and that second round of thinking was being stored in the middle of the message. Only the thinking a reply opens with is folded away, so the second lot was shown as part of the answer: the model's own deliberation, read out mid-reply. The same happened when a reply cut off by the length limit was continued automatically. A continuation is now kept without its thinking, nothing appears while it is still thinking, and the two halves are joined with a space where the model, having stopped to think, picked up without one. Chats that already have this in them are cleaned up on screen as well, without changing what is stored.
Long-term memory, pins and the context meter stop counting the model's thinking. Three things read a reply with its thinking still attached. Memory indexed and summarized the thinking and then recalled it into later prompts. Pinning a reply pinned its first 300 characters, which on a thinking model is the thinking, not the reply. And the context meter counted thinking that is never sent, so it reported older messages as out of context sooner than they were. All three read the reply alone now, and so do the Markdown and plain text exports. One thing to expect: in a chat that uses the memory tree with a thinking model, the affected parts of the memory rebuild once, the next time the chat is open.
A character that messages you first no longer rereads its own thinking. When a character reaches out on its own, the earlier messages were sent to the model with their thinking still attached, which the chat screen never does. It also carries over a short excerpt of your last conversation, the first 300 characters of each message, and on a thinking model those 300 characters were the thinking: the reply that had actually been said never made it in. Both now use the reply alone.
A generator no longer fires from the model's thinking. A thinking model plans out loud, and a plan that mentions a generator tag, "I should use [Create Outcome] here", is the same text as the tag itself. It was being run: a generator rolled that nobody had asked for, and if it kept its result as chat variables, those were written too. Generators now fire only from the reply.
{{lastMessage}}and{{lastCharMessage}}no longer include the model's thinking. They returned the stored message whole, thinking block and all, so a quick reply or a generator built on one handed the model its own scratchpad back as if it had been said aloud. They now give the reply as it reads in the chat.Searching a character's chats searches what was said. The search box above a character's chat list was matching words the model had only thought, and showing a line of that thinking as the result.
Copy copies the reply, and chat statistics count it. Copying a message from a thinking model put its thinking and the markers around it on the clipboard along with the reply, in a character chat and in Direct Chat alike. The statistics counted the same way, so the word totals were mostly words nobody had read and the "longest reply" was the longest stretch of thinking.
Text in a code block wraps. Some models put their thinking, or whole paragraphs, in a code block, and a code block kept every line whole and scrolled sideways, so each paragraph was one line too long to read. Long lines in a code block now wrap. A block with no language, or one marked as plain text, always wraps; turn off "Wrap long lines in code blocks" in Chat Display to keep real code on one line and scrolling.
📱 Phones and narrow windows
Editing a provider, a voice or a generation config on a phone gives you the screen. Open one of these in Settings and its title, description and buttons stayed fixed at the top, on top of the settings header and the row of section chips. On a phone that left about 250 pixels to scroll the actual settings in. The whole pane scrolls now, so the heading moves out of the way and the buttons are one flick back up.
The card editor no longer scrolls sideways on a phone. The bar at the top holds the card's name and token count on one row and its buttons on the next. On a phone neither row would shrink: the name never shortened, the buttons never wrapped, the token count and the Chats button ran off the right edge, and the whole editor slid sideways to reach them. It got worse as a card collected chats, since "Chats (54)" is wider than "Chats (5)".
Direct Chat keeps the message box on screen. The conversation was given a fixed share of the window's height, under the heading and the model picker. On a phone, and in a desktop window that was not tall, that left no room for the box you type in: it sat below the bottom edge and you scrolled the page down to reach it, then back up to read the reply. The conversation now takes whatever space is left, so the message box is always at the bottom of the window.
Settings, Search and dialogs fill a narrow window at any UI scale. With the window narrower than about 770 pixels and the UI scale set to anything but 100%, these stopped short or ran long: at 90% the sheet ended a tenth of the way up from the bottom with the page behind showing through under it, and above 100% the bottom of the sheet was off the screen. They were sized with a unit that ignores the UI scale, on the assumption that only a phone is ever that narrow.
A section title in Settings no longer breaks in the middle of a word on a phone. Where a section has a button beside its title, the title was squeezed into whatever the button left, which in German split "Generierungskonfigurationen" across two lines mid-word. The button now drops below the title when both do not fit.
The Adventure Mode character builder fits a phone. Its title and the Complete sheet for me button each broke onto two lines, the class field shrank to a sliver beside the name, and on any screen the button ran under the window's expand and close buttons. Each field now has its own line on a phone, and nothing in the header wraps or overlaps.
The Rin (3D) page fits a phone. The page was wider than the screen and scrolled sideways, with the character's stage running off the right edge.
♿ Accessibility
Fields have names a screen reader can read. In Settings and in the card editor, a field's label sat beside it without being attached to it, so a screen reader announced the field as an unnamed text box or list and left you to guess which one. Every field in the card editor and every control in Settings now announces its own label.
Dialogs say what they are, and Settings takes the keyboard. A screen reader announced every dialog as just "dialog"; each now reads its own heading. Opening Settings also left the keyboard on the page underneath, so Tab moved through the chat behind it. Settings now takes focus when it opens, keeps Tab inside itself while it is open, and returns focus to where you were when it closes.
🌍 Languages
More of the app is translated. Several labels were English whatever language you had chosen: "Thinking" on every reply from a thinking model, the Card Forge's starter chips (Deepen, Add a flaw, Tighten greeting and the rest), the function-key list in Settings, the section headings on the Adventure Mode character sheet, and "Unknown device" under Remote Access. A chip you have renamed yourself is left as you wrote it.
The lorebook audit stops flagging Chinese and Japanese keys as too short. A key of one or two letters is flagged because it turns up inside ordinary words. That rule was counting characters, so a single character such as 龍 was reported as firing on almost everything, with advice to tick "Whole words only". One such character is a whole word. A lone kana or Hangul syllable is still flagged, since that really is in everything.
🎲 Making and sharing games
A game card can bring its own character sheet. The character builder made every character the D&D way: six D&D abilities, then 4d6 or a 27-point buy. A game master card can now describe its own sheet in a new Character sheet box under the ruleset: the abilities' names, a heading for them, and a fixed set of scores to deal, such as d12, d8, d6, d6, d4 and d4, which the player places one to an ability by clicking or dragging. It can add more groups beside the first, each dealt on its own (Cortex's Values beside its Attributes), say the game has no HP or give a fixed starting HP, say it has no levels or XP, and list headings for the written parts of a sheet, which a new character's "Who they are" starts with and Complete sheet for me writes under. The game master is then told about the character in the game's own terms every turn, a d12 as a d12, rather than on D&D's 3 to 18 scale with D&D's ability modifiers. A character built this way keeps the game's sheet on its persona card, and a persona card made by hand can pick a game in the card editor. In DM mode the party is statted on it too. It travels with the card, and the Guide's new "Building your own game" walks through making a game from start to finish, with examples for Fate, Powered by the Apocalypse, Cortex Prime and percentile games.
The character builder stops putting D&D's range over other games' numbers. The ability heading read "Abilities (3–18, 10 = average)" whatever the sheet held, including a Fate character's 2, 1 and 0. The range now shows only while you are rolling or buying scores.
Name a bundle when you export it. The export window has a Name field now. It names the file, and for a bundle of several cards it is also the folder they go into when someone imports it. A multi-card bundle used to be saved as "bundle.aicc" and import into a folder called after its first card with "+1" on the end, and renaming the file did not change that.
In DM mode the roll box rolls the way your game does. When you run the game yourself, the box under a party member's attempt only knew D&D: a d20 plus a D&D modifier against a DC, which made a Cortex d12 worth +1 and a Fate +2 worth -4. A game card's character sheet can now say how its checks roll: Fate's 4dF plus the skill, a Cortex pool where you pick an Attribute and a Value and add other dice by hand, keeping the best two, or rolling under a percentile skill. Without that it picks one from the sheet, and a card with no sheet of its own still rolls the d20. Every roll box also takes any dice you type. A pool follows Cortex's rules, in DM mode and when the game master rolls one in ordinary Adventure Mode: a 1 is a hitch and does not count, the largest die left over is the effect die, and all 1s is a botch, each shown on the dice card. And a game that is not D&D reads Target on its dice card instead of DC.
A bundle of several cards shows its creator notes after you import it. The main card's Public Creator Notes open in an "About" window once the cards are in, so how to play a game reaches the player instead of waiting to be found in the card editor.
🔧 Fixes
{{roll}}understands Fate dice and keeping the best of a pool.{{roll::4dF}}and{{roll::3d6kh1}}both answered 0. For Fate that is an ordinary result, so a card rolling Fate dice in a macro looked like it was working while it rolled nothing at all. The macro now reads the same dice the Adventure Mode roll button does:4dF,3d6kh1,2d20kl1, with modifiers.Chat titles, summaries and the story director read the chat the way you do. A greeting is stored with its placeholders in it,
{{user}},{{char}}, any variables it sets, and filled in when it is shown. The helpers that read the chat on the side were handed the stored version: the AI chat title, the scene note, the running summary, the story director, the suggested replies and the pick of who speaks next in a group. So they saw the placeholders rather than the names, and several also saw a game master's bookkeeping lines. They now read each message as it appears in the chat.The dice record only shows what applies to your game. On a card whose rolls are judged by the game master, or that never rolls a d20, the record sat showing "Success 0/0" and "Nat 20 · Nat 1: 0 · 0" for the whole campaign. Each line now appears once there is something to put on it.
A generator's number range rolls the whole range. Two ways it did not. A range with a decimal step, 0 to 0.3 in steps of 0.1, never rolled its own maximum. And a range entered backwards, Min 10 and Max 1, rolled 10 every time instead of something between the two.
Deleting a Direct Chat conversation asks first. Delete sits beside Clear in the header. Clear asked before it emptied a conversation; Delete removed the whole conversation on one click, with no way back.
Image Studio corrects an impossible size. Width and Height took anything typed into them, a negative number, a fraction, nothing at all, and sent it to the image provider as written, which answered with whatever error it had for that. A size is now brought back inside 64 to 4096 whole pixels when you leave the field, and again when you press Generate. Steps and CFG are held to their own ranges the same way, there and in an image provider's own settings.
A regex script that is blocked now says so. A pattern that repeats a group which already repeats, such as
(a+)+, is refused because it can take hours to run. It was reported as an invalid pattern, which sends you looking for a typo that is not there.A button that fills in your message no longer acts before you use it. A choice can put text in the message box instead of sending, and that text can set variables when you send it. The variables in every such button were being set anyway, when the chat opened and again on every turn, whether or not anyone clicked it. A greeting offering several of them ended up with all of their values, the last one winning. Only what you actually send sets anything now.
An exported card can always be imported again. Export as Rin Chat JSON copied the card's stored format tag into the file. A card that reached the library some way other than the importer could carry a tag the importer does not know, and the file it exported was then refused with "Unrecognized character card" on every other copy of the app. The export now always writes the right tag.
The Guide catches up with the Card Forge. It still said the Forge does not write lorebooks. It does: a new session asks what you are making, a character, a user persona, a lorebook, a generator or a document style, and a character session can write its own lorebook entries. The Guide now says how to get to each.
A wrong password on the lock screen is selected, ready to retype. It stayed in the box after the error, so typing again added to the end of it. Now it is selected, and the first key you press replaces it.
A provider's error message no longer ends in two periods. Small, and on every failed request where the provider punctuates its own message.
Personas stay out of Not in Folder. Personas have their own row in the library sidebar, but every one without a folder was also listed, and counted, under Not in Folder, so that view never emptied however carefully you filed your characters. Not in Folder, its count and the Library statistics now leave personas out. They still show under All cards and in any folder you put them in.
Selected items and chat tabs have their own colors. "Your messages & tabs" in Theme & Colors also colored every selected toggle, tab and chip, which nothing on the screen said, so a theme with a black message bubble on black panels hid which option was picked, such as Replace, New or Skip when importing cards that are already in your library. It is now three colors: Your messages, Selected items and Chat tabs. A theme you already made looks the same, since both new colors start from the one you picked. A selected toggle or chip is also outlined in your text color now, so the choice shows whatever colors a theme uses.
A slow local model can take longer than two minutes to start. A request was given up after two minutes with nothing from the model, and a local model reading a long prompt sends nothing until it has read all of it, so a big chat on a slow GPU was cancelled just before the reply would have started. Each provider now has a Response timeout in its settings: 120 seconds unless you change it, up to an hour, or 0 to wait as long as it takes.
Rin Chat Update Notes - Version: 0.7.5
3 October 2026
🎲 Adventure Mode
Adventure Mode can be taught a different tabletop system. It has always refereed a game of roughly D&D's shape, because the rules it teaches the game master were written into the app. Those rules are now three layers you can see and two you can replace. The core is the contract the app's own parsers read, the directives behind the sheet, the buttons, the trackers and undo, so it is always sent and cannot be edited. The ruleset is the system the dice are read by, and the GM style is how the game is run, and either can be rewritten for Fate, Powered by the Apocalypse, Cortex, Forged in the Dark or something of your own. Because the core is never editable, a rewrite cannot break the sheet or the buttons, which is what made this safe to open up.
An adventure card can carry its own rules. In the card's Features it can replace the ruleset, the GM style, or both, and add guidance of its own on top. A card's rules win over the ones in Settings, so a game you share is self-contained: whoever opens it plays your system without changing a setting.
The dice understand other systems now. The roller only knew the
NdM+Kshape, which quietly decided which games were playable. It now reads Fate and Fudge dice (4dF), pools scored on their best or worst dice (3d6kh1), and mixed pools added together (d8+d6+d10), and the roll button carries them. Rolls that drop dice show you the ones they dropped.A roll the app cannot read no longer becomes a dead button. If the game master wrote dice with a typo in them, the Roll button still appeared, looked perfectly normal, and did nothing whatsoever when clicked, in a reply that hides the choices as well. The roll is simply left out now, so the reply reads as ordinary narration you can answer however you like.
The app can apply a stat from the sheet in any system, not just D&D's. A roll could already say
mod strengthand have the app look the number up, work out the modifier and show you where it came from, but the modifier it worked out was always D&D's, so no other system could use it and had to ask the model to read its own sheet and type the number in. Watching that fail is what prompted this: told the character had Cool +1, the model rolled without it.bonus <stat>is the same lookup for a sheet that already holds the modifier, as Fate, Cortex and Powered by the Apocalypse sheets do. The lookup also works with pool and Fate dice now, where it used to do nothing at all without saying so.A character sheet can hold ratings that are not D&D's. The score box refused anything below 3, which is where rolling 4d6 and dropping the lowest bottoms out and where point buy starts. That is a rule about building a D&D character, not about what a number on a sheet may be, and it meant a Fate skill at Average +1, a Powered by the Apocalypse stat of -1 and a Forged in the Dark action rating of 0 could not be typed in at all, while the dice that read them worked fine. Typed scores now go as low as a system needs. Rolling and point buy are untouched, so a D&D character is built exactly as before.
Pools that keep their best dice across different die sizes. Some systems build a pool out of differently rated traits, a d8 from one and a d10 from another, and score the best two of them. Write that as
(d8+d6+d10)kh2and the app rolls all three, totals the best two, and lists every die with the size it came from, so the ones it left out are still there to read.klkeeps the worst instead.The Guide explains how to write one. Writing an adventure card now ends with a section on teaching it another tabletop system: which box does what, which dice the app can roll, the two systems it cannot resolve for you and what to do instead, and the handful of things that decide whether a model actually follows your rules rather than falling back on d20 habits. Every one of those came from watching a real game go wrong.
The prompt meter breaks the layers out. Each layer is its own row, so an edit's cost in context is visible rather than folded into one total.
📖 A lorebook that belongs to the chat
Every chat can now keep its own lorebook. Open it from the book button beside the character sheet and the variables panel. It holds lore that belongs to THIS chat and dies with it, and like any lorebook its entries come back when their keywords are mentioned, so a cast of forty costs nothing in context until one of them is actually relevant. It is not an Adventure Mode feature: any chat can have one, the same way any card can keep variables. The card's own lorebook is never touched, and nothing is written to your library unless you press Save as a shared lorebook.
The story can write into it as you play. This is what it is for: a town of people who did not exist when the chat started. A generator writes the roll straight in with
as.entry=NAMEbeside the usualas=NAME, and rolling a roster of five gives five entries rather than one overwritten five times. The character can write one itself with[[lore: NAME | what to remember]], on a line of its own, which you never see in the reply, and add to one it already wrote with[[lore+: NAME | one more thing]]. The plus matters more than it looks: learning one new fact about someone is most of what a scene does, and restating a whole entry to record it is where a detail written three turns ago quietly goes missing. A card opts into that by using the line in its own text, so every other card pays nothing for it.A card can start a chat with a cast already in it. Put a generator tag in the card's own text and it rolls once, when a chat begins, instead of on every turn:
as.entry="Harbormaster"for an entry the story can revise later, oras.entry.static="Harbormaster"for one it can never touch. Seeded entries sayfrom the cardso you can tell them from your own, a name with a space needs quotes, and deleting one makes it stay deleted rather than coming back next turn. Every new chat rolls its own, so the cast is different each playthrough.What the story wrote belongs to the message that wrote it. Delete that message, reroll it, or branch away from before it, and the entries go with it, exactly as a variable or a stat already does. They are listed apart from your own entries for that reason, and keeping one moves it into your book, where the story can no longer take it back. A write can add or revise an entry but never empty one, and there are limits on how long an entry is, how many a turn can write, and how many a chat can hold.
🔧 Fixes
System Prompts is usable on a phone again. The page puts Response language above the prompt configs, and that block held its ground while everything else gave way: on a short screen the config list was squeezed to a few pixels at the very bottom, a line too thin to read or tap, with the heading above it still looking perfectly normal. Only one other page was built the same way, and it is the next entry. The page now scrolls as one on a phone, so Response language simply scrolls out of the way and the configs, and the editor behind them, get the whole screen. Nothing changes on a desktop, where the list and the editor keep their own side-by-side panes.
Theme & Colors is usable on a phone too. Checking for the same mistake elsewhere turned it up on the one page nobody had reported: the title block and the little live preview were both holding their ground, which left the swatches a 47 pixel window onto a list more than twenty times that tall. Every color was in there, you just could not get to one. That page now scrolls as one on a phone as well. The preview still sits pinned beside the swatches on a desktop, which is the point of it there.
Right-clicking no longer opens a menu of options that do nothing. On an image it offered Open Image in New Window, Save Image As and Copy Image Address, and anywhere else it offered Back, Forward, Stop and Reload. None of those could ever work: they are the webview's own browser controls, and this is a single page with no history to go back through and nothing behind the download items. They are gone now. A typing field keeps its menu, where cut, copy, paste and the spellcheck suggestions are real, and selected text keeps Copy.
The thinking block no longer scrolls sideways. It had a horizontal scrollbar nobody asked for, and it could not be used anyway: the block is redrawn as each word arrives, so dragging it sideways snapped back to the start of the line on the next one. It was a side effect of capping the block's height, which quietly turns on sideways scrolling as well. Long unbroken text now wraps instead, and a code block inside the thinking still scrolls on its own as before.
Comparing against a value in quotes works.
{{if .location == forge}}matched and{{if .location == "forge"}}did not, because the quote marks were being read as part of the value. It looks right to anyone who has written code before, it did nothing, and it said nothing. Straight and curly quotes both work now, which also means you can finally compare against a value with a space in it, the one thing that was impossible without them.A lorebook entry that renders to nothing no longer takes up a slot. An entry whose text sits behind a condition still fires when the condition is shut, it just has nothing to say. One at a depth was being sent as an empty message in the middle of the conversation, which the model then has to read past. Entries that come out blank are now left out, and nothing changes about when they fire, so timers, cooldowns and chained entries behave exactly as before.
The prompt inspector says what each injected block is. Everything the app splices into the chat history at a depth, an Author's Note, a character's note, a lorebook entry set to a position, a recalled memory, an auto-fired generator event, arrived in the inspector as an unnamed
SYSTEMmessage. You could see that something had been injected and where, but not which of them it was. Each one now carries its name and its depth beside the role,SYSTEM · Author's Note @4, in the captured exchanges as well as the preview. A lorebook entry is named by its own name, an event by its generator's.Direct Chat stops dragging you back down while the model is still writing. Scrolling up to re-read something, a thinking block from earlier in the reply for instance, pulled the view straight back to the bottom on the next word that arrived. Every other transcript already let you scroll away and resumed following when you returned to the bottom; Direct Chat shared that code but never received the scroll events, because it draws a loading line until its session opens and the transcript it was watching for did not exist yet at that moment. It never started watching, so it treated you as being at the bottom for as long as the view stayed open.
👥 Group chats
A character can now carry a standing note in one chat. Open a member from their chip in the group bar and the first thing there is "Note for this chat": a line that is sent on every turn they take, in that chat only. Three one-click presets cover the usual cases, including off-scene, where the character is not in the room and can only reach it by text or a phone call, so their replies arrive as one. Until now the choices were a one-turn direction that vanished, or the card's own depth prompt, which follows the card into every chat. Members with a note carry a small dot on their chip.
The directions box can keep what you typed. Shift-click a member for directions and there is a "Keep this for the chat" box: the same text becomes their note instead of steering one reply and disappearing.
☰ Order takes instructions for the one chat. The group prompt in Settings is shared by every chat using that prompt preset, so a rule about this scene had nowhere to go. The box at the top of ☰ Order is added to that prompt rather than replacing it, which matters: the group prompt is what tells the model to write one character at a time.
Macros work in the group prompt. It used to resolve only the two tokens it documents, so
{{user}},{{persona}}, a variable or a{{pick}}sat there as text. Everything the rest of the prompt understands now works there, and in the two new boxes above, resolved for whoever is replying. The prompt inspector shows both of them with the macros already resolved.
Rin Chat Update Notes - Version: 0.7.4
2 October 2026
🔨 Card Forge
A lorebook, generator or style session is no longer told it is building a character card. Only the rules at the end of the guide's prompt knew which of the four a session was on. Everything above them still described card work: the guide's own job, the scene it thinks it is in, three worked examples of building a character, the interview notes, and the rule about never writing card fields in chat. A large model reads past all that and follows the rules; a smaller one copies the examples, which is why a lorebook session would keep asking for greetings and a personality, and kept bringing up a knight who lives in one of those examples. Each mode now brings its own, and nothing about character cards goes out in the other three. A lorebook session's prompt is also less than half the size it was, which is worth a lot on a smaller model.
It no longer sends you to a button that is not there. The guide's advice for a user who had gone quiet was to hit Generate character, which only exists while you are building a card. In the other three session types that was the most likely suggestion to be given and the one guaranteed not to work.
Ask the forge for a persona and it builds you one. A user persona is an ordinary character card with its type switched, so the forge gave it the full character interview: a hooky first greeting, a scenario, dialogue examples teaching it how to behave. None of those apply to a card that describes the person playing, which is never greeted and never speaks first.
"What are you making?" offers it directly now, next to Character card, so the forge knows before you have typed anything. Saying so in the chat is enough too, from the first message and before any card exists. The guide asks about you rather than about an NPC, the card is written in that shape, and its type is set when it is built, so it turns up in the persona picker without a trip to the sidebar. Switching an existing card's type mid-session works too. This is the same thing the forge already did for Adventure Mode cards asked for by name.
The preset buttons belong to the session they are under. "Add a flaw" and "Tighten greeting" are questions about a character, and they were the buttons sitting under a document style session too. Each kind of session now has its own set, seeded the first time you open one: entries and keys for a lorebook, fields and variety for generators, dark mode and CSS for a style. Your card presets are untouched, and editing one kind leaves the others alone.
Generator and style sessions reopen as what they are. The session list only recognized cards and lorebooks when reading them back, so a generator or style session came back from storage as a character card session and the guide started asking about greetings for a randomizer. The mode was stored correctly the whole time, it was being discarded on load.
🧠 Reasoning
The reasoning card asks you two questions instead of seven. Effort, and whether the thinking is shown as a collapsible block. The rest was protocol: which field name your gateway reads, a vendor tag, a chat-template flag and the thinking markers. Those are questions about the app's own request, and the app answers them now. They are still there under Advanced for the times a provider needs something unusual.
The switch at the top of that card said the wrong thing. It sat in the title row as a bare On and Off, which reads as the switch for the whole feature. It never was: turning it off does not stop the model thinking, it stops the app recognizing the thinking, so a reasoning model's raw markers end up in the middle of the reply. It is a labelled row now and says so, and Effort explains that None is the one that actually stops the thinking.
"Don't think" now works on more of the models that decide thinking by chat template. Several families ignore the usual reasoning field entirely, so the app has to set a flag in the request instead. That flag has two different names depending on the family, and the app only ever sent one of them, so on the models that read the other name the setting was quietly ignored and the thinking showed up anyway. Both names are sent now, and Gemma and Granite are recognized alongside GLM and Qwen.
Maximum is reachable on models whose top setting has another name. When a model refuses the level you asked for it usually replies with the levels it does take, and the app retries with the closest one. A level above our own top was treated as the furthest thing from every request instead of the nearest, so a model offering only "low" or "max" answered a request for the most thinking with the least. It now lands on the right end.
Maximum now reaches Grok again. The app folded the top effort tier down to High on every xAI model but one, because when that was written xAI did not document the tier. They do now, on Grok 4.6 and later, and they downgrade it themselves on the models that lack it. So picking Maximum had been quietly giving you High, with nothing on screen to say so.
Titles and image prompts stop failing on the newest OpenAI models. The app asks for no thinking at all when it writes something for itself: a chat title, an image prompt, picking who speaks next. Some newer models reject that outright, which failed those features with an error about a setting you never touched. They are now asked for the least thinking they will accept instead.
Rin Chat Update Notes - Version: 0.7.3
1 October 2026
🔨 Card Forge
The guide can work on a lorebook, a generator or a document style, with no character card involved. Until now the forge only ever edited a card, so improving a standalone book meant attaching it to a throwaway character, editing it there and detaching it again. A new session now asks what you are making, and each of the four gets its own opener and its own rules. There is a wand button on every row of the Lorebooks and Generators screens, and beside a style of your own in Settings, so you can also start from something you already have.
A session is scoped to the one thing it edits. A lorebook session will not wander off into inventing a character, and it cannot edit one even if asked: the card fields are not writable there, the switches about a card's own generators and lorebook are not shown, and Generate character is refused rather than quietly building a character into the thing you were editing. Opening the same subject twice returns to the session already on it instead of starting a second one that would overwrite the first.
A style is checked before it is offered, not after it is accepted. Styles are HTML and CSS that the app renders, so a style that reaches the network or leaves the text nowhere to go is refused while it is still a proposal. Undoing one that has already repainted the screen is a worse way to find out.
Your old sessions stop disappearing. The forge kept the 30 most recent and quietly dropped the rest: no warning, no record, and the conversation went with its undo history. That limit existed because every session shared one stored blob, so the whole thing was rewritten each time you typed, and it grew with every character you had in progress. Each session is now stored on its own, so there is no limit, and saving no longer gets slower the more of them you keep. The ones you still have are carried over on first launch.
🔊 Read-aloud
The bundled voice shows a real percentage while it downloads. The first use fetches the voice model, and the status sat on "Preparing" with nothing else to say for the whole wait, which looks exactly like a hang on a slow connection. It was also wrong about why: the engine does report progress, the app just never asked for it. It now counts up, and only shows dots for the short silent part after the download.
A voice that never starts now recovers instead of hanging. Speech is built on a background thread, and the app already knew to fall back to the main one if that failed. It only did so when the background thread reported an error, so when it simply never finished, nothing happened at all and "Preparing" stayed on screen until the app was closed. It now gives it a limit and takes over, so the voice speaks either way.
📱 On a phone
The actions that needed a Shift key can be reached by holding a button. Send with directions, impersonate, continue with instructions, regenerate with directions, having a specific character answer, and deleting every newer message were all Shift-click only. On a phone they did not exist, and nothing on screen said they were there, because the tooltip that would have said so cannot be shown on a touch screen. Holding a button now does what Shift-clicking it does. A mouse is untouched: the modifier still works and nothing on the desktop changes.
The message menu says what each thing does. Tapping the three dots opened a small grid of unlabeled icons, so the only way to find out what one of them was for was to tap it and see. It is now a sheet along the bottom of the screen with a named row per action, sized for a thumb, and it carries the actions that have no button of their own, like regenerating with directions or deleting every newer message.
Two buttons could not be tapped at all. Small controls carry an invisible margin so they are easier to hit, and in two places that margin was wider than the gap to the next control, so the neighbour's margin covered the smaller button completely and took every tap meant for it. Copy in Direct Chat went to the read-aloud button beside it whenever a message had both, and Edit with AI in the card editor went to the expand button. Both are sized against their neighbours now, and every other small control in the app has been measured the same way and given a hit area it was missing.
Things stopped sitting on top of each other. The three dots button sat on the last line of a reply, or on the last choice in it, because only messages with a swipe row left space for it. A choice too long for its line dropped underneath its own arrow instead of wrapping beside it. A dialog's title ran under its close button, which had been true on every screen for as long as the rule meant to prevent it had been written the wrong way round. The prompt inspector's tabs made the whole dialog wider than the screen instead of scrolling by themselves.
Dialogs fill the screen, and the full screen editor has a way out. A phone was given the desktop's centred panel with a corner handle for resizing it, which is not a gesture a phone has. Panels open filled now, with no handle and no maximize button. The full screen message editor had a purple Done next to a purple Send, and the one under your thumb was Send, so leaving a text box sent the message. It closes with an X, and keeps what you typed.
Turning read-aloud on no longer asks your computer for permission. The toggle saved the entire chat in order to remember one setting, and saving from a phone takes the editing lock, which your computer keeps for a minute and a half after it was last touched. Picking up your phone after locking the screen landed inside that window, and put a dialog about another device editing in front of what is only a playback switch. The setting travels with the next save instead.
Lists and pickers fit the screen. One of your own lorebooks showed about four characters of its name, because its row spent almost all its width on buttons. The group chat picker gave its folders a block that still hid most of them while leaving the characters underneath almost no room; the folders are one swipeable line now and the characters come in two columns. The greeting row keeps Choose and New together on one line.
🌍 Translations
- Wrong text in the five translated languages is fixed. A batch that had been translated by a local model reached users with sentences that said the opposite of the English, with the clause that was the whole point of the line missing, and in a few cases with fragments of an unrelated language left in the middle of a sentence. Those are corrected, and translation no longer goes through that model.
⚙️ Settings
- The debug log is in Diagnostics. It sat under Data & Backup, beside the backup and restore tools it has nothing to do with, while everything else for working out what went wrong was already together under Diagnostics.
Rin Chat Update Notes - Version: 0.7.2
29 September 2026
🔍 Prompt inspector
A Playground tab, for trying things against the chat you are actually in. Paste any text and see both ends of it side by side: what the model would be sent, and what the chat would show. Macros resolve against the real card, persona, group and variables, so
{{char}},{{group}}and{{getvar}}answer properly instead of sitting there unresolved the way they do in the Settings playground. Generators roll, with a seed you can pin so the same roll repeats, and your regex scripts run on both sides. Nothing is sent or saved: a{{setvar}}is listed as a change it WOULD have made rather than applied. In a group you pick who is replying, because that decides the scripts, the routing keys and the name each turn is labelled with.The preview shows what is actually sent. It stopped at the chat history, so it was missing every instruction the app adds after it: the group roster, the note that tells a character to write a new message rather than continue the last one, the impersonation note, the rules a player gets at a DM's table, and the length directive. It also showed the DM's hidden
[h]notes in a preview of a prompt the party never receives. The preview and the real request now come from the same code, so they cannot disagree again.Exchange rows stay put. Every request in the list was numbered from a counter that restarts when the app does, so once a chat had history from an earlier session two rows could carry the same number, and the list was free to drop or duplicate a row while you scrolled it.
📚 Lorebooks
- A character's lorebook can be copied to your library. It only worked one way before: a shared book could be attached to a character, but a book you had revised on a card had nowhere to go, so reusing it elsewhere meant retyping it. There is a Save a copy to library button in the card's lorebook editor now, beside Audit and Test. It makes an independent copy, so the card keeps its own and the two can be edited apart. Copying twice gives you two books rather than quietly overwriting one, since a book in your library may already be in use by another character.
🔌 Providers
A limit on how many requests a provider runs at once. Parallel requests are free speed on a hosted API. On a local model they are the opposite, because the server splits the same tokens per second across everything open at the time, so a reply crawls while a summary and a scene note run alongside it. Set Max parallel requests on the endpoint in Settings, Providers. Anything over the limit waits its turn rather than failing, and a reply always goes ahead of background work like summaries, scene notes and chat titles. Leave it empty for hosted APIs.
The Text Generation WebUI preset tells you the flags that actually work. It said to start oobabooga with
--api, which is enough for the server to run and not enough for the app to reach it: every request came back "Failed to fetch". The full set is--api --listen --listen-host 127.0.0.1, and the preset, the Guide and the CORS hint on a failed Test all say so now.
💬 Chat
The greeting arrows wrap around. At the last greeting the next arrow greyed out, so getting back to the first meant clicking back through every one of them. Both arrows carry on round now. The count still tells you where you are.
Import and Export is quicker to read. Each format's two files sit side by side under their heading instead of stacked in a list, PNG first since that is the one people share, and every row is a real button.
🔊 Read-aloud
- The bundled voice says whether it is downloading or already stored. The first use of a Piper voice downloads a few MB after the engine, and the status said only
Preparing <voice>with nothing else to show for it, so a working download looked exactly like a hang. It now says which of the two is happening.
🔨 Fixes
Long chats stop stuttering while anything else is going on. Opening the memory drawer, or almost any other change on screen, threw away and rebuilt every message you could see. Their pictures dropped back to a placeholder and fetched themselves again, and the transcript lost its place. This is the same fault as the card editor note above, in the chat itself: with fifteen messages on screen, opening that drawer rebuilt all fifteen.
A local Automatic1111 or Forge works without launch flags. Image generation against one always failed with "Failed to fetch", whatever the address, because the request went out from the app's own page and A1111 refuses anything from another origin unless you start it with
--cors-allow-origins. SwarmUI and ComfyUI never had this, which made A1111 look arbitrarily broken. Its requests now take the same route those two take, so it just works. Note that Stop can no longer interrupt a render that has already started: it drops the result instead, the same as ComfyUI.The library header says Personas when you are looking at personas. It read "All cards" over a list of five persona cards, because the header worked out what you were looking at from the folder and the favorites switch and never checked the personas one. A scan started from there labelled its findings "All cards" for the same reason.
The card editor beside a chat stays where you left it. With the editor open and a note shown as rendered HTML, the panel jumped on its own while a reply came in: the note was being thrown away and rebuilt several times per reply, so every picture in it dropped back to "Loading image…" and fetched itself again, and the panel's height changed underneath you each time. Worst on a card with long notes full of images, which is exactly where it was reported. The note is now rebuilt only when it actually changes, and the panel holds its place when something above the view does change height.
🧹 Under the hood
The chat screen is 1,500 lines smaller, and the work it used to duplicate is now shared. The file behind chat had grown past 12,000 lines, with prompt assembly, image generation and stream retry all written inline and some of it written twice. Those three live in their own files now and chat calls them. That is what made the preview fix above possible: there is one copy of the prompt path, so the inspector and the real request cannot drift apart again, and a fix to either is a fix to both. Nothing here changes what the app does, it changes how many places a fix has to be made.
Debug logs name the turn they came from. A group reply or a DM turn was filed under whatever request type happened to run last, so a log read back later could credit a line to the wrong character or the wrong table. Each turn carries its own label and speaker now.
Rin Chat Update Notes - Version: 0.7.1
28 September 2026
🔨 Card Forge
Proposed changes appear in the chat instead of a window over it. When the guide proposed an edit, a review window opened the instant the reply landed, so the first thing you saw of an answer was a checklist of changes to it, before you had read a word. The proposal now sits inside the reply that made it, the way it does on the website: every field it wants to change, with the full new text, and Apply. More than one field gets a tick box each, so you can take one and leave another. Review is still there for the per-field editing, regenerating and generator picking.
An applied proposal stays where it was. It greys out rather than vanishing, still showing what was proposed and marking each field as applied or not, so a reply that says "full rewrites below" still has them underneath it afterwards. Leaving one unanswered and carrying on now says so in the transcript instead of quietly dropping it. An applied one also carries its own Undo this, so you can put the card back without hunting for the change in Tools ▸ History. Undoing says so on the block itself, which now reads “Applied, then undone” rather than going on claiming it was applied.
Applying several new lorebook entries adds all of them, not three copies of the first. Picking more than one new entry of the same kind gave you the first one repeated. The same went for any list the guide adds to at once: behavior rules, speech patterns, greetings and example dialogue. A proposal whose reply you regenerate, edit, delete or swipe away also clears straight away now, instead of sitting there offering changes to a message that no longer says that.
🎮 Interactive cards
A card can draw a bar.
[[bar: hunger / 10]]puts a small gauge wherever you write it, the one element that doesn't need a line of its own. Either side can be a number or the name of a chat variable, so both ends move as the story does.| 20sets the width, and the color comes from the fraction rather than the name: over 60% draws in the theme accent, 60% or under turns orange, 25% or under turns red. For a bar you want LOW, infection or suspicion or heat, add| invertand those bands read from the other end, so nine out of ten shows nine lit cells in red. It only flips the color; the fill still follows the value.A button that hands you the line instead of sending it.
[[choice: Ask him something | insert I catch up and ask about ]]puts its text in your message box, so you finish the sentence before you send. The button shows a pencil. It exists for the cards that track state by hand: the card hands you[once]{{.next_scene=1}}[/once], you add your own words, one send, rather than retyping a macro every time the scene turns.A macro in that button no longer fires before anyone clicks it. The payload is a line for YOU to send, so its macros belong to that send. They were running on any pass that touched the message: simply drawing the reply set the variable, and every repaint set it again, so a card that tracks its own state quietly disagreed with itself. The payload is now held out of every macro pass and handed over exactly as written.
Regex scripts can write into the saved message. A third destination beside Display and Prompt: Message runs once, as the reply is saved, and what it writes IS the message from then on. It shows in chat, you can edit it with the ordinary Edit action, and the macros in it are frozen to that turn's values, so scrolling back shows what the numbers were then and not what they are now. Two things to know: it can't be taken back by turning the script off, and it's exclusive with the other two, because a script that rewrote the message and then ran again on the way out would apply itself twice.
Imported SillyTavern scripts behave the way their authors meant. A script with neither "only format display" nor "only format prompt" ticked edits the stored message in SillyTavern. Rin treated it as display plus prompt instead, which looks the same in the chat and in the request but leaves nothing you can edit. It now lands on Message, and exports unchanged.
A status line under every reply, without writing the regex. The card editor's Regex section has Add text to every message. It builds the pattern, ends it with a
[co] … [/co]pair and puts the cursor between the tags, so you type your line and that is the whole setup. Anything inside those tags stays in the chat and out of the model's view. Write a gauge's sides as macros,[[bar: {{.hunger}} / 10]], to freeze the numbers into that message rather than following the variable afterwards.
💬 Chat
See and edit the variables a chat is tracking. A Variables button on the right edge of a chat opens a panel listing everything the card is keeping, with its value: change one, rename one, add one, delete one. Variables are invisible until something prints them, which made a card that tracks state by hand hard to follow. An edit here wins over the transcript, so deleting or regenerating an older message can't quietly undo it, and a locked choice re-checks its condition straight away rather than waiting for the next reply. Global variables are listed apart, since changing one changes it everywhere. The session inspector's Variables tab is the same panel now, so either route does the same things.
The dice only appears where it does something. Reroll is offered on the rows whose value the card rolled for itself, and nowhere else, instead of a dice on every row where most of them were no-ops.
🔌 Providers
- Text Generation WebUI has a preset. oobabooga's OpenAI endpoint had none, so it went through the custom path and people reached for
--public-apito get a URL that looked like the ones the other presets show. That flag is for reaching it from another machine and the address it prints changes every launch. The preset fills inhttp://127.0.0.1:5000/v1, says no key is needed, and says to start it with plain--api.
🗂 Library
- Recently chatted is gone from the sidebar. All chats covers it. If it was your default view, the library opens on All cards instead. The Recently chatted sort is untouched.
🪟 App
An edit you close the window on is kept. Editing a generator and closing the Generators library lost the edit, because the save was waiting on a timer that the closing window threw away. A card's own lorebook had the same hole on one of its two exits. Every panel that saves as you type now flushes what is pending before it goes.
Escape closes one thing at a time. With two overlays stacked it closed both, it fired while you were cancelling an IME composition, and it left the field you were editing still focused. It now closes the top one, leaves an IME cancel alone, and blurs first.
"5 msgs", not "5 msg". Two of the three chat lists got the plural wrong.
A wrong password no longer leaves a key in memory. The key derived from your password was wiped only after a successful unlock, so the one failure that always happens, a typo, returned early and left it behind. It is wiped on every path now.
📖 Guide
- The published guide reads as a document again. The copy at rin.chat lost every table to a single run-on line, printed one heading level as plain text, and opened with the same heading twice. A handful of places in the Guide itself also ran two words together where a line break in the source ate the space between them.
Rin Chat Update Notes - Version: 0.7.0
26 September 2026
🔨 Card Forge
The guide can change part of a generator instead of rewriting the whole thing. Adding one trade to a list of forty meant restating all forty, every other field, the template and the chains — slow, expensive, and one forgotten key away from quietly shrinking a generator you spent an evening on. It now sends just the change: add or remove options, set one option's odds, rename or add or remove a field, retitle it, change the template. A rename carries the template and any dependency with it, and the app refuses an edit that would leave a field with nothing to roll — and says so instead of doing it quietly. Asking for one trade now sends about a hundred characters instead of restating the whole generator, and the transcript says what it did — “added “Mudlark” to Trade” — rather than just naming the generator. New generators are still written out in full — and if the guide rewrites an existing one wholesale anyway, that rewrite can now change anything but delete nothing: a field or an option it forgot to restate stays on the card instead of quietly disappearing. Removing something is still possible, it just has to be asked for.
Asking for a generator in the brief no longer goes quietly nowhere. A new forge session starts with the generator and lorebook switches off, so "/create … give him a generator for what a customer brings him to open" built the card and dropped that half without a word. It now says which switch is off and where to find it.
Duplicate a card's generator. Making a variant — the “Female …” / “Male …” pairs a card ends up with — meant retyping every option, because Duplicate only existed in the Generators library and the card side never opens that list. A card's Generators section has the button now: the copy is the card's own from the start, sits beside the original, and doesn't inherit its chains.
A generator tells you when a field can never show up. A generator with a layout line only prints the fields that line names, so a field added without one is rolled and then thrown away — invisible in play, and nothing said so. The editor and the review now point it out, and the guide is told to extend the layout when it adds a field.
The guide can no longer claim a change it didn't make. Ask for something a generator hasn't got — remove a trade that isn't there, rename a field by the wrong name — and it would cheerfully say "done". The app now says what actually happened: "remove_option: Trade has none of Banker", naming the real fields so the next ask lands. A part of an edit that didn't apply no longer hides the parts that did.
Aim an edit at one part of one generator. The Edit character picker lists each generator's fields alongside the greetings and lorebook entries, so you can tick “Visitor ▸ Mood” and say what you want — or tick its layout row to change the template, description or odds. Ticking a generator part asks the guide for operations rather than a rewrite, so it changes that one thing and leaves the rest of the generator alone.
Asking for "the greetings" counts as asking for the greetings. Tell the guide that the greetings need to call a generator and it would agree, write all six — and then the app would throw them away with "left out — not what was asked for". The filter that stops the guide quietly redoing old requests only recognized an entry named by NUMBER ("Greeting 3"), so naming the list outright looked like it had been asked for nothing. Naming a list now means the list; a number still means only that entry.
"Yes, do both" now gets both. Ask the guide for ideas, let it offer two — a lorebook entry about a friend, or a line in the background — and say yes to both, and only one of them arrived: the other was thrown away as "not what was asked for". An acceptance names no field, because the fields are in the offer it accepts, and the filter that stops the guide redoing old requests had nothing to match against. Worse, the note explaining the drop was the guide's context on the next turn, so asking again taught it to leave the same half out. Saying yes — in words, or by clicking one of the buttons the guide offered — now keeps everything it agreed to.
A change proposed before the card exists says so. Start a session, describe the character, and if the guide answered "set her appearance to …" with a real proposal, nothing happened at all: there was no card for it to change, and the transcript read as though the edit had been made. The guide is now told plainly that there is nothing built yet, and if it proposes anyway the app says so and points at Generate character.
A generator's layout line can no longer reference a field that isn't there. A placeholder naming no field printed nothing, so a roll came out as "asks for a bowline, about ." — a broken sentence handed to the model, on every roll, with nothing anywhere saying why. The editor and the review now name it.
Two more places report what the app quietly dropped. Sending with an empty box, and regenerating a reply, read a reply exactly as a normal turn does but had none of the notices a normal turn gets — a proposal in Draft only mode, a generator asked for with the switch off, a reply that talked about a change and wrote none: all silent on both. They share one set of notices now, and a regenerated reply drops the notices belonging to the version it replaced.
A proposal aimed at a field that does not exist no longer pretends to apply. If the guide reached for a name the app cannot write — “backstory” instead of Background, say — the change appeared in the review like any other, ticked, applied, and did nothing, and the transcript then said it had been applied. Those never reach the review now, and a proposal that mixes a real field with a wrong one keeps the real one.
💬 Chat
The screen no longer flashes when a reply finishes. Every completed message made the whole transcript lay itself out twice in a row, which at a raised UI scale or font size read as the chat flickering or zooming for an instant. It happened on every reply, and the longer the chat, the worse it looked. The second pass is gone.
The side panel stays put while you scroll the chat. With the editor or character sheet open beside a chat, scrolling the conversation dragged the panel along with it once the panel's own content ran out, which made long creator notes almost unusable. The two scroll independently now, and only a real wheel or scrollbar moves either.
Side panel headers stay pinned, and get out of the way. Scroll an open side panel and its header now stays at the top instead of disappearing, shrinking as you go so it costs less room than it did standing still.
Impersonate treats what you type as direction, not as your line. Shift-click Impersonate, type "ask her about the money", and it would often reply to that, or hand it straight back as your message. What you type is instruction for the draft, so it now writes the message that carries out what you asked, in your character's voice.
Send an impersonation, then ask for another. Picking a draft and sending it used to be the end of it; wanting a different take meant typing the whole instruction again. There is a button on your message now that reopens Impersonate with what you asked for last time, and the draft you choose replaces that turn.
Choose which card fields this chat sends. A card's appearance, background, example dialogue and the rest are all-or-nothing in the prompt, which is expensive when a long chat has made half of them redundant. The chat's side panel now has Fields sent for this chat: untick a field and it stops being sent for this chat only, other chats on the same card are untouched, and the context meter updates as you go. Turning off the card's system prompt falls back to your global one, or to nothing if you have not set one.
Two things that made long chats redraw more than they had to. A regex script scoped to recent messages was redrawing the whole transcript, and the app was rewriting its own layout settings every time the window resized. Both are fixed; neither changes how anything looks.
🔍 Prompt inspector
The sent prompt reads as a prompt again. Each exchange was one long line of escaped JSON, which is technically everything you asked for and practically unreadable. Requests are laid out properly now, each message in its own box, with a heading saying which part of the prompt it came from: system prompt, chat history, and what was added after it. Field names and labels are coloured so you can find things by eye.
Exchanges survive leaving the chat. Closing a chat, or the app, turned its recorded exchanges into flat text with the real request data gone, so an older chat could not be debugged properly. They are kept as they were, up to 10MB per chat, oldest dropped first. Each exchange also has its own search and a show raw toggle for the exact JSON that went out, and the tab says how many exchanges it is holding.
Long blocks can be dragged taller, and the window opens full size. A big system prompt in a short box meant scrolling a postage stamp. Anything taller than its box now has a drag handle at the bottom, and the whole inspector opens maximised, since it is a window you open to read a lot at once.
🪟 App
- Every window has an X. Dialogs could be closed with Escape, by clicking outside, or by whichever button happened to be there, but several had no visible close control at all. They all have one now, in the top right beside the expand button.
🔊 Read-aloud
Speed works on the bundled Piper voices. Slowing a Piper voice down did nothing at all — the setting was applied on the way out, to a voice that had already finished speaking at its own pace. The speed now goes into the voice itself before it says a word, so it genuinely speaks slower or faster instead of being stretched afterwards. It also takes effect on the next thing read aloud, rather than after a restart.
Three new dials for the bundled Piper voices. Pause between sentences puts a real beat between one sentence and the next, for a voice that was running them together. Expressiveness decides how much the delivery varies — turn it down for a flat, even read, up for something more animated. Rhythm variation does the same for the timing, from metronomic to loose. Leave any of them blank and the voice's own trained value stands; clear one after trying it and you get that value back, not the last number you typed.
Finding and managing your trained voices. The voice list put the ones you trained yourself somewhere in the middle of 126 catalogue voices, sorted by name. Yours are now at the top under Your voices, with the catalogue below — and adding or removing them has moved into Manage your trained voices, so the box you pick a voice from is no longer sitting next to a box that looked like a second voice picker.
🗂 Cards & notes
- The notes swap stays where you put it. The card editor's side column always opened on your private notes, so if you keep your notes somewhere else and only want to read the creator's, you were hitting the swap button on every single card. It remembers now — flip it once and every card opens that way, until you flip it back.
🖼 Images
Adding an image provider finally offers image models. NanoGPT and OpenRouter keep their image models on a different list from their text ones, and the app was only ever reading the text list — so setting up a new image provider showed you hundreds of chat models and none of the ones that can draw. It reads the right list now: NanoGPT offers all ~240 of its image models, OpenRouter the models that actually return a picture. Providers already set up were unaffected and keep working.
A base URL with the endpoint left on it no longer breaks generation. If you pasted
…/v1/images/generationsinto the address field — which is exactly what you'd try when the model list looked wrong — the app added the endpoint a second time and every generation died with a bare "failed to fetch", no status, nothing pointing at the field. The address is now understood either way.Picking an image or voice model works like picking a text model. Both were a plain box with the browser's own autocomplete hanging off it — no search, none of your own model groups, and with NanoGPT's 239 image models or 28 speech engines behind it, no way to find anything. They use the same picker the rest of the app does now: type to search, your groups as headings, the model's name with its id beside it, and you can still type an id no list mentions.
🧠 Thinking
- "None — don't think" now actually stops GLM and Qwen thinking. Those models don't read the field every other provider uses to turn reasoning off, so setting it to None changed nothing and a Thinking block would still appear partway through a scene, seemingly at random. The app now sends the two things those models do read — the right tag for the family, and the template switch — whenever you ask for no thinking on one of them. The settings for both are still there if you need to override what it picks.
🎮 Interactive cards
Choice buttons no longer turn into raw code at random. A choice only became a button when its line held nothing else, so any time the model bolded it, italicized it, put it in a bulleted list or ended it with a full stop, you got the markup instead: the whole
[[choice: ... | if ... ]]line, conditions and stat effects on show. Models do that only some of the time, which is why it looked random. The decoration is now ignored and the button appears either way.A button can ask you something. Cards can write
[[choice: Make a guess | ask Who is it? | as my_guess]], and clicking it opens a text box right there for you to type into. Before this, a button that meant "now tell me something" had to spend a whole turn on it: the card offered the button, the app sent its label, and the model was supposed to come back with the question. Smaller models often skipped that step, which is how Twenty Questions in Rin's Arcade could congratulate you on a guess you never got to make. Rin's Arcade itself is updated to use it, so Twenty Questions now hands you the box to type your answer into.The cards that come with Rin Chat can be updated now. They used to be handed out once and never looked at again, so when a release fixed one, only people installing fresh ever got the fix. A fixed built-in card now shows up in Card updates in the library sidebar, next to updates for cards from the site. Nothing is overwritten behind your back: you get the same field-by-field review, every change ticked and yours to untick, and a rollback point saved first. If you deleted one of those cards it stays deleted and stays quiet, and Skip works the same as it does for site cards.
The guide no longer makes up answers about fields it can't see. Ask it to set a depth prompt, a group-only greeting or the image prompt prefixes and it would confidently tell you they don't exist, or send you to a tab that isn't there. Those fields are real; the guide simply was never shown them, so a weaker model filled the gap with a guess. It now knows they exist, knows their real names, and tells you which card editor section to open instead of inventing one.
Importing a card now brings its regex scripts and document styles with it. Both were missing from the field-by-field comparison, so they never showed as a difference and were quietly kept from your old copy: importing a card over itself, taking a site update, or taking a built-in update left the incoming scripts and styles behind. They appear as their own rows now, named rather than counted, so an edited pattern or restyled document block is visible before you accept it, and you can untick either to keep your own.
Rin Chat Update Notes - Version: 0.6.9
24 September 2026
💬 Chat
Generating a picture no longer kills the choices above it. Asking for an image under a reply that offered choices retired those buttons — the picture counted as the story moving on. It doesn't: the choices stay live under any pictures you generate, and go quiet only when you actually reply.
Picture and gallery are one button now. The two image buttons under the chat were separate pills that did related things; they're a single pill with two halves — Image to make one, the icon beside it for everything this character has already generated.
Suggest moved into Impersonate, and now writes the whole message. Shift-click Impersonate and the window has an Ideas button: a few one-line things you could do next, from the scene so far. Click one and it doesn't just drop that line in the box — it writes the message out in full, in your character's voice, ready to edit or send. The old Suggest button beside Undo is gone; its one-tap chips live on in the phone remote, where they fit. The ideas are better, too: they used to be the choices the reply already showed as buttons, read back to you.
Edit a message while a reply is being written. The edit button used to gray out until the character finished, so a typo in what you just sent had to wait. You can open any message and work on it now — Save holds until the reply lands, and says so. The message being written into is the one exception; it's still being typed.
🔨 Card Forge
The guide can ask with buttons. Rin can end a reply with a few one-click answers — offered where she'd otherwise leave you staring at an empty box, and again once a card has been generated, for the next thing worth doing to it (more greetings, a lorebook, a sharper voice). They're shortcuts past typing, never the question itself: she still asks in prose, and you can always answer with something she didn't think of. Only the newest reply's buttons are live.
Editing a field no longer gets refused when generating the card didn't. The forge writes whatever you ask it to — it runs on your own provider, so nothing in the app polices content — but only the full generation said so to the model. Rewriting one field, rewriting several, or asking the guide about the finished card went out without it, so the same model that wrote an explicit card happily would balk at touching it afterwards. Every pass carries it now.
📱 Phone
- The message box grows as you type. On a phone it had a drag bar along its top edge, which is exactly where your thumb lands when you tap into what you just wrote — so it got grabbed constantly by people not reaching for it. The bar is gone there. The box now sizes itself to what you have written, up to about a third of the screen, and scrolls past that. The drag bar stays on the desktop, where a mouse can actually aim at it.
🗂 Cards & notes
- Render HTML in notes without being asked every time. Imported cards nearly all carry HTML notes, and each one asked before showing it. Settings → Chat Display → Card library has an Always render HTML in notes switch that answers it once for every card. It asks for confirmation when you turn it on, and says why: the HTML itself is stripped of scripts, but an image a note links to is fetched from whoever hosts it, which tells that server your IP address and that you opened the card — a tracking pixel in all but name. A warning stays under the setting while it's on. Any single note still flips back to raw text with the 👁 button, and cards you already said no to stay as text.
🪟 App
Opening a screen shows that it's opening. Settings, a chat, the card editor and the search window each load on demand, and while that happened the app showed nothing at all — so the click read as ignored and Settings got clicked five more times. There's a spinner now, and the screens you reach first are fetched quietly in the background once the app has settled, so the click usually has nothing to wait for.
No more trailing dots on buttons. Around sixty labels and field hints said "Import…", "Manage tags…", "Search chats…". They say Import, Manage tags, Search chats. Spelling is American throughout now, too — Organize, color, canceled.
The click that brings the app back doesn't do anything else. Alt-tab away with a window open, click back in, and a click that lands beside the window no longer throws it away — that click asked for Rin Chat, not for your work to close. The same goes for the app's own Close button. The next click behaves normally.
Big windows resize, and stay how you leave them. Dialogs with room to use — the character pickers, settings panels, the group window, memory, the prompt inspector — have a maximize button in one corner and a drag grip in the other. Set one the way you like it and it opens that way from then on — each window remembers its own size, so sizing the prompt inspector doesn't touch your settings window. Double-click the grip to go back to the default. Small confirmations stay small. (Windows narrower than about 600px — the regenerate-with-directions box, the in-chat model picker — did the resizing but forgot it on close; they remember now too.)
One character picker everywhere. Every "which character?" list in the app — adding a member to a group chat, picking a card for a sprite pack, Image Studio's "use as card image" and "prompt from character", the reference card in Card Forge, putting a lorebook inside a character or copying one into it, and the new shared-lorebook link — is now the same picker: search by name, creator or tag (
f:for every field), a folder rail where there's room, character pictures on every row, and a list that loads as you scroll. Several of these used to be a plain list of names with no pictures, and two of them couldn't search at all.
🔌 Providers
The model picker is the same everywhere, groups and all. Changing model mid-chat, in Card Forge, for a group member or for chat memory used to be a bare text box with a browser autocomplete behind it — no search, no groups, and a different control in each place. They're all the one picker now: type to search the provider's whole list, see your own groups as headings, and open the group manager right there instead of going to Settings. Card Forge in particular gets the chat's own chip and Model & generation window, still set per forge session — leave it on Active config and it follows your chats.
Drag your presets into the order you want. Generation configs, system prompts, and your image and voice providers are lists you pick from constantly but couldn't rearrange — new ones landed at the bottom forever. Drag any row up or down and the list stays that way. The list opens a gap where the row will land as you drag, so you can see the result before you let go.
Group a provider's models your own way. A list of 300 models sorted alphabetically is no way to choose one, so you can now make your own sections — "Cheap & fast", "Uncensored", "The good one" — and drop models into them. They show up as headings in the model dropdown, in your order, with everything else under Ungrouped. Organize them from the provider itself, or from the Model groups button beside any generation config's model picker. The groups belong to the provider, so every config that runs on it sees the same sections — and a provider's image models are grouped separately from its text models.
📚 Lorebooks
- Give a character its own shared lorebooks. A card's Lorebook section has a new Shared lorebooks row: attach any book from your library and that character reads it in every chat it's in, without attaching it chat by chat. The lorebook editor has the same link from the other side — a Characters button listing who reads this book. The book stays in your library — one guild, faction or city book can be attached to several characters at once. In a group chat only the character that carries it reads it, so an organization's secrets don't land in everyone's prompt, and it's inserted as that character's own lore (the Lorebook Activation insertion strategy treats it like their embedded book).
🎲 Adventure mode
Right-click a choice to act it out — your way. Shift-clicking a choice has always written your message performing it, in your character's voice, but nothing said so. Right-click any choice now and you get both: Act it out in your voice, and Act it out with directions — where you say how first ("reluctantly, and keep it to one line") and the draft follows it.
Adventure mode leaves more of the window for the story. The rules the app pins to every single turn are about a fifth smaller: the scale the GM uses to grade what you say in a say-box is now sent only on the turn it's actually judging your words, and the turn-order rules only once a fight is being tracked. Nothing plays differently — there's just more room for the adventure itself, which matters most on a small context window.
Rin Chat Update Notes - Version: 0.6.8
23 September 2026
👥 Group chats
Auto mode stops when you leave the chat. Switching to another chat while a group was talking to itself let it keep going and write its replies into the chat you had just opened.
Group chats got a big reliability pass — characters stop getting mixed up. The model is now told clearly, on every turn, who said what and who it's speaking as, so voices stop bleeding together and the wrong character stops answering. Each past turn in a group is labelled with its speaker (which also fixes providers that quietly ignored the old attribution and left the model guessing), and every reply ends with a plain "write this as
only" reminder. Address a character by name and they answer. In a group, just name who you mean — "Kisa, what's the plan?", or "I wonder what Kisa would say" — and Kisa replies. A normal send now goes to whoever you named instead of always taking strict turns. Say no name and the app picks whoever fits the moment.
Choosing who speaks next is instant, free and private. "AI picks" and auto-mode used to spend a whole model call to decide who talks; they now use the small model already built into the app for offline memory — so the choice adds no cost and no latency, works with every provider (even ones with no cheap model to spare), and never repeats the character who just spoke.
Choose who answers in a group chat. ☰ Order now has a reply order: Smart (the default — name two or more members and each answers in turn), Natural (SillyTavern's: whoever you name plus a talkativeness roll per member, so one message can get several replies; talkativeness is read from imported SillyTavern cards and adjustable per member), List, Pooled (everyone once before anyone twice) and Manual (only who you click). Auto mode waits 5 seconds between turns (adjustable there), and stops when you start typing.
Mute a group member. In a group chat's ☰ Order, Mute keeps a character in the group but skips them whenever the app picks who speaks — the rotation, AI picks, Auto mode and the Director. Their chip in the group bar dims, and clicking it still has them speak.
{{groupNotMuted}}now leaves muted members out, as in SillyTavern.New chat with this group. A button in the group window starts a fresh chat with the same members, mutes, turn order and per-member models. Characters' group-only greetings are used now: they open that chat, and a member added before your first message greets with one.
A reply that drifts into someone else's lines is trimmed. If a character's reply starts scripting the others ("…Kisa: hi. Syl: …"), the extra lines are cut so each turn stays one character — and the trimmed version is what's saved, so the slip doesn't teach itself back to the model.
The group bar sits with the composer, not over the chat. The member chips and the context meter now share the composer's panel at the bottom instead of hovering in the message area, and the context meter's bar reads clearly against it.
🖼️ Card images
Re-importing a card keeps its images. Choosing Merge when importing a card you already have deleted every sprite, picture and background that card held — the files, not just the links. They're kept now.
Animated card art stopped losing its motion. Setting an animated PNG as a card's picture saved a single frame — the crop step flattened it on the way in. Animated art is now stored exactly as it arrives, so it moves in the library and in chat; it has to be 2:3 already (300×450, say), because it can't be cropped here. Animated WebP counts as animated too now: a card downloaded from aicharactercards.com, which re-encodes every image to WebP, showed a still picture where the original moved.
Cards can carry their own images. The card editor has a new Images section with three kinds, and they travel with the card in a bundle:
- Expressions — sprites named by feeling (
joy,anger,neutral…;joy-2is a secondjoy). In chat, the character's expression changes with what they say — in a panel beside the chat, or visual-novel style on a stage above it. - Pictures — images the card shows inside a message by name:
[[img: map]]. - Backgrounds — chat backgrounds the card switches to by name:
[[background: tavern]].
- Expressions — sprites named by feeling (
Four ways to add them. Add images from files, Add from link (downloads it into the card — or paste an image), Generate with your image provider in the card's own style, or Import sprite pack (a zip of
joy.png,anger.png…). Export sprite pack saves one back out, and a sprite pack dropped on the library asks which card it's for. Every image is converted to WebP and scaled down, so a card with dozens of sprites stays light.How the expression is picked. From each reply, by the small built-in model that chat memory, group chats and Card Forge already use — free, private, and no extra download if you've used any of those. Or switch to an emotion classifier (a one-time download) in Settings → Chat display, where you also choose side panel or visual novel (a chat can switch with the buttons under the sprites). A
[[expression: joy]]line in a reply or greeting always wins.Call them by name.
[[img: map]]shows a picture ([[img: map | caption]]adds a caption),[[background: tavern]]switches the chat background and[[expression: joy]]sets the sprite — in a reply, a greeting or a lorebook entry. Tick Tell the AI about these images and the AI writes them on its own. The macros{{img::map}},{{background::tavern}}and{{expression::joy}}do the same, for places where macros are easier to write.Pictures in lorebooks, choices and reveals. A lorebook entry can carry a picture that opens the reply whenever the entry fires; a choice can be a picture tile (
[[choice: Play the tarot | img tarot]]); and a picture inside a[[reveal:]]stays hidden until it's opened.Images from websites ask first. An imported card whose images are links to a website shows a button instead of loading them, then saves them into the card — nothing is loaded from that site again.
📦 Card bundles
Bundles are a work in progress. The format is still settling and will likely change over the next week or two, so treat a bundle you export now as a file to re-export later rather than something to archive. aicharactercards.com will start taking bundle uploads in a few days; until then, bundles are for sharing files directly.
Open a bundle from the site. Once listings go live, a bundle's page on aicharactercards.com gets an Open in Rin Chat button: the app fetches it and imports it like any bundle you opened yourself, with the same review of what's inside and the same choices when something clashes with what you already have. Nothing is added without you. Wherever a bundle comes from, the import now says so if any of its files were changed after it was exported.
Bundles save as
.aicconly. A one-card bundle could also be saved as.charx, on the promise that SillyTavern and RisuAI would open it. In practice they don't import it, so the option is gone rather than misleading..charxfiles from other apps still open in Rin Chat as before.A bundle no longer carries your private notes. Your own notes on a card, its folder, favourite and collections were written into the bundle and landed on whoever imported it. Bundles now carry only the card itself.
"Import as new" keeps the art and images. Importing a bundle and choosing New for a card that matched an existing one produced a card with no picture and none of its images.
Share a card with everything that comes with it. Export a card as a bundle — one
.aiccfile with its art and, if you tick them, the document styles it uses and your shared lorebooks (the ones used in its recent chats are ticked for you). Select several cards and Export bundle to send a whole cast as one file; importing it puts them in a new folder named after it. Double-click an.aiccfile to import it, and Open with → Rin Chat works on.charxfiles from other apps. Chats are never included, and a bundle can be up to 25 MB.
🧩 Macros
Macro mistakes are pointed out as you write. The macro playground, the card health check, and a note right above a card field or lorebook entry (when you click away from it) now flag an
{{if}}missing its{{/if}}(or the reverse), a stray{{else}},=where==was meant, a macro name that doesn't exist,{{trim}}with text inside it, and a{{that never closes — each of these used to fail silently.Macro autocomplete in card fields and lorebook entries. Typing
{{in any card field, greeting, example or lorebook entry now lists the macros to pick from, as it already did in the message box — and the list now covers every macro that works, each with a short description in your language, followed by your own custom macros. Ctrl+Space opens it anywhere, as in SillyTavern. The Guide has a new Macro reference: every macro in a table, with what it does and an example.Lists for inventories, clues and party members.
{{.inv push rope}}adds an item,{{.inv remove rope}}takes one out,{{count: inv}}says how many there are, and{{each: inv | - {{item}}}}writes a line per item — with{{index}}for its number, and room for an{{if {{item}} == rope}}inside. A list is ordinary text (rope, torch), so{{.inv}}prints it and{{if .inv contains rope}}checks it, as before. See the Guide's Variables section.Easier macros for game cards.
{{.hp > 0 ? alive : dead}}picks text by a condition in one line — and, like{{if}}, only the chosen side runs.{{weighted::common:5::rare:1}}is a random pick where each option can be made more or less likely — handy for loot and encounter tables.{{if .hp == .hp_max}}compares two variables.{{calc: .hp + $coins}},{{switch: .mood | …}},{{repeat: ♥ | .hp}}and{{bar: .hp / .max}}accept the./$you'd write anywhere else ({{calc: $coins = …}}stores to a global). Variable names can contain dots and hyphens ({{.guard.hair}}),{{endif}}closes an{{if}}, andFalsecounts as false in any case.{{silent}}…{{/silent}}runs a section without showing it. Everything inside still works — variables are set, dice rolled, lists updated — but none of its text appears. Build and debug a section with its output visible, then wrap it once it's right, instead of rewriting its macros.SillyTavern cards' macros work as written.
{{description}},{{personality}},{{scenario}},{{mesExamples}},{{charPrompt}},{{charInstruction}}and{{charDepthPrompt}}now fill in from the card (they printed nothing) — with exactly what the card would carry exported to SillyTavern, so an imported card reads its original text. Macro names work in any capitals ({{Appearance}}). Also accepted now:{{getvar hp}}/{{roll 1d20}}(a space instead of::),{{if::…}},offandnoas false in a condition,\{\{…\}\}to show braces literally, and{{ // }} … {{ /// }}comments spanning several lines.Blocks work like SillyTavern's. Any macro that takes an argument can wrap text:
{{setvar backstory}}…{{/setvar}}stores everything in between,{{reverse}}…{{/reverse}}reverses it,{{each: inv}}…{{/each}}repeats it per item, and{{trim}}…{{/trim}}keeps a section but trims its edges (as in SillyTavern 1.19 — where text inside a single{{trim …}}is dropped, so it is here too). What's inside a block — including an{{if}}/{{else}}— is now trimmed and un-indented, as in SillyTavern, so blocks can be laid out on their own lines without adding blank lines; write{{#if …}}(or{{# setvar …}}) to keep the spacing exactly as typed. This changes spacing in existing cards where an{{if}}started or ended with a space or line break on purpose. Card and chat macros ({{description}},{{lastMessage}}…) now also work in greetings, messages you type and quick replies, not only in the prompt.More of SillyTavern's macros.
{{group}},{{groupNotMuted}}and{{notChar}}name who's in the chat (they printed nothing), and{{charIfNotGroup}}matches{{group}}(as in SillyTavern's current engine).{{charDescription}},{{charPersonality}},{{charScenario}},{{greeting}}and{{version}}work as SillyTavern's other names for the card fields;{{isMobile}}and{{hasExtension::…}}answerfalse, and SillyTavern-only macros (the instruct and reasoning ones,{{outlet}},{{allChatRange}}, creator notes) are pointed out by the macro checker as having nothing to do here rather than flagged as unknown. New:{{summary}},{{authorsNote}},{{defaultAuthorsNote}},{{charAuthorsNote}}(the card's Character's Note),{{systemPrompt}},{{defaultSystemPrompt}}and{{original}}(in a card's own system prompt, the app's prompt it replaced);{{model}},{{maxContextTokens}},{{maxResponseTokens}},{{maxPrompt}}and{{lastGenerationType}};{{currentSwipeId}},{{lastSwipeId}},{{firstIncludedMessageId}},{{idleDuration}}and{{input}};{{time::UTC+2}}and{{timeDiff::a::b}}; and{{charPrefix}}/{{charNegativePrefix}}for the card's image prompt prefixes. The card's list fields can hand over one item:{{behaviorRules::0}},{{speechPatterns::1}}(new),{{dialogueExamples::2}}— counted from 0, like{{charFirstMessage::0}}and SillyTavern.&&and||work in a plain macro.{{.a==1 && .b==1}}and{{.a==1 || .b==1}}printed the wrong answer — everything after the first comparison was read as the value being compared against, so==always came out false and!=always true. They now give the same answer as inside{{if …}}. A||with no comparison is still the fallback:{{.title || none}}works as before, and so does a fallback or a value that just contains&&or||({{.x = salt && pepper}}).Conditions can be grouped and negated, and take a macro on either side.
{{if .ready && (.hunger > 0 || .thirst > 0)}}and{{if !.met}}now work. A comparison with a macro in braces —{{if {{getvar::hp}} > 3}},{{if .name == {{user}}}}, or a grouped{{…}}that printsfalse— was always true; it now compares the values. Against a number, an unset variable counts as 0, so{{if .hp <= 0}}no longer depends on text ordering.Variable shortcuts print exactly what they do in SillyTavern, so an imported card reads the same in both apps.
{{.hp = 10}},{{.hp += 5}}and{{.hp -= 5}}now print nothing, like{{setvar}}— a greeting that sets up a game no longer shows a row of stray numbers.++and--print the new value, and??=/||=print the value the variable ends up with. To set a value and show it, write both:{{.hp = 10}}{{.hp}}.Smaller macro fixes.
{{IF}},{{ else }},{{ /if }}and{{else if …}}are recognised in any case and spacing. A{{// comment}}no longer runs the macros inside it. A variable holding macro text prints it as written instead of running it. Adding decimals no longer leaves float noise:{{.x += 0.2}}on 0.1 stores0.3, not0.30000000000000004.-=,--and{{decvar}}leave a text variable alone instead of turning it into -1.{{setvar::time::12::30}}keeps the whole value. Nested{{repeat}}s no longer crash the message.{{roll::2d6 + 1}}and{{ trim }}accept spaces, and dice add together:{{roll::1d6+1d4}}(it answered 0).{{calc: -2 ** 2}}is -4, as in maths, and a large result prints in full instead of as1.18e+21. Spaces around{{pick}}/{{random}}options and{{setvar}}values are trimmed, as in SillyTavern.{{hasvar::a && hasvar::b}}works outside an{{if}}too.
💬 Chat
A reply that ends on choices or a document keeps them. With "trim incomplete sentences" on, a reply ending on a bolded choice menu, or on a document the model forgot to close, was cut back to the last sentence and the buttons or document were lost for good.
A reply that only thinks no longer sticks on "Thinking…". When a model opened its thinking block and stopped without closing it, the message showed a thinking spinner forever with the text hidden inside it.
Design your own document styles. A
[[doc: name]]style is now a small template: HTML with placeholders for where the text goes ({{title}},{{content}},{{raw}}), an optional line template that turns each "Name: message" line into whatever you like (that's how sms draws bubbles), and CSS for the style alone. Settings → Chat Display → Document styles has one picker for the built-ins and yours. The built-ins can't be changed, but duplicating one gives you its full template to rework, so a copy of sms really is an sms thread in your own colours. Styles you made before convert automatically.A card that shows what all of this does. Rin's Arcade arrives in your library on update: six little games run from Rin's bedroom — room escape, commission night, stream night, tarot, twenty questions and a date planner. It's built out of the pieces above — choices that remember and unlock, picks, text boxes, timed choices, folded clues, a lorebook entry per game that loads only while that game is running, and a neon arcade document style the card carries with it. Delete it if it's not for you; it won't come back.
Cards can bring their own document styles. A card's new Document styles section holds styles that travel with it and work in its chats without anyone adding them first. A phone, a case file, a spellbook page: the AI is told they exist and uses them. A style of your own with the same name still wins.
Cards' own regex scripts now work. Many imported cards come with find/replace scripts that turn tagged text into things like a phone's text-message thread or a status panel. Those scripts used to be kept only inside the original file: they never ran, and exporting as an AICC card or uploading dropped them. Now they're part of the card, travel with every export, and run in chat after your own regex scripts. The first time you chat with such a card, the app asks before running them. Edit them, or switch them off, in the card editor's new Regex scripts section. Replacements can use macros like
{{char}}, and a script can put macros in its Find pattern too.Laid-out HTML in a message shows as intended. A block of neatly indented HTML — a card's phone mockup, for one — was cut apart at its blank lines and shown as raw code. It now renders as the layout it describes.
Send with directions. Shift-click Send (or press Ctrl+Shift+Enter) to tell the model what its next reply should do — "keep it under three sentences", "have her finally admit the truth". The directions ride along for that one reply only (they aren't saved to the chat), and Regenerate on that reply reuses them. Works on an empty send too, to steer the next reply without writing a message. Directions now go at the very end of what the model reads — after the card's post-history instructions — so a card's own instructions can't override them; this also makes Regenerate's directions and a group member's Shift-click directions stick better.
Choice buttons at the end of a reply no longer disappear with "Trim incomplete sentences" on. A reply ending on
[[choice: …]]lines had them cut off as if they were a half-finished sentence.A reply ending on a list no longer loses its last item. With "trim incomplete sentences" on, a reply that ended on a list item or heading — "3. Card Tarot" — was cut back to "3.", because the list number's full stop looked like the end of a sentence. A final list item or heading now counts as a complete ending.
A document the model forgets to close no longer swallows the rest of the reply. When a card shows a styled block — [[doc: terminal]], an SMS thread, a newspaper — and the model leaves off the closing tag, or wraps the marker in bold, the block used to eat everything after it, including the reply's choice buttons. It's now repaired automatically: the block closes in the right place, the buttons come back, and the cleaned-up text is what's saved, so the model stops repeating the mistake.
Forking a chat no longer drags in the other branch's future. Going back to an earlier point and branching used to copy the whole parent chat's memory and its current scene and summary into the new fork — so the model could "remember" things that only happened down the path you left. A branch now carries only the memory that belongs to it, and starts its scene and running summary fresh. (Chats you branched before this heal on their own as memory rebuilds.)
🪟 App
UI scale no longer throws off sizes. Above or below 100%, some windows, lists and menus came out the wrong size — the Settings pop-out stopped short of its window, and at a large scale a few dialogs ran past the edge of the screen. Every one of them now follows the scale.
Edit with AI opens in front of the full-screen editor. Clicking it from the full-screen editor opened its window behind the editor, where it couldn't be seen until the editor was closed. Messages like "Saved image into the card" or "JSON copied" also showed behind the window they came from — they now appear on top.
Settings pops out again. Clicking Pop out closed Settings without opening its window.
The window reopens the way you left it. Rin Chat now remembers its size, its place and whether it was maximized, instead of reopening at the default size in the middle of the screen. It also works across monitors with different scaling. (On Linux under Wayland, the system decides where windows open, so only the size and maximized state come back.)
Importing opens the folder you last imported from. The card import dialog — and the folder import — now start where you left off instead of in your home folder every time (it always started at Home on Linux).
Rin Chat Update Notes - Version: 0.6.7
20 September 2026
✨ New
Do real maths in a macro.
{{calc: hp + armor * 2}}evaluates a whole expression, so you no longer have to build a sum one+=at a time. It handles+ - * / %,**(power), parentheses, your variables by name (a missing one counts as 0) and the functionsfloor,ceil,round,abs,sqrt,min,maxandclamp(x, low, high)— e.g.{{.health = {{calc: hp + armor}}}}or{{calc: min(hp, hp_max)}}. A malformed expression prints nothing rather than an error. The Guide's Variables section has the details.More macro tools for building games. Alongside
{{calc}}:{{switch: mood | 0-3=Tense | 4-6=Calm | *=Content}}maps a value to text in one line (instead of a stack of{{if}}s);{{repeat: ♥ | hp}}and{{bar: hp / hp_max | 10}}draw pips and HUD meters;{{if}}now takes{{elseif}}branches; conditions understandcontains({{if .inventory contains rope}}, and the same in a locked choice:[[choice: Tie it down | if inventory contains rope]]);{{calc}}gainedrandint(1, 6)/rand(0, 1)and an assign-and-store form ({{calc: hp = hp + armor}}, silent). All covered in the Guide's Variables and Conditionals sections.
🩹 Fixes
A variable set earlier in a message is now visible to a
{{if}}later in the same message. Conditionals used to be resolved in a pass before variable assignments, so{{.flag=1}}{{if .flag}}…{{/if}}(and the same with{{setvar}}) read the variable as still unset and took the wrong branch. Macros and{{if}}/{{elseif}}/{{else}}blocks now resolve together, left to right, in the order they're written — only the branch that's taken runs, so a skipped branch's macros and rolls still don't fire.The fullscreen note editor fits the window at any UI scale. With Sizing & Layout → UI scale above 100%, the expanded editor was sized from the unzoomed window, so it grew past the edges and its buttons ran off-screen. It now measures the window the way the rest of the app does. Pictures in a note keep their shape there too: one laid out beside another could come out stretched.
The card drawer in a chat can swap its notes. The notes box beside a chat now has the same ⇄ button as the full editor, switching between Card Notes (private) and Public Creator Notes in place.
Chat Memory no longer has a blind spot just past the context edge. Memory held back the four messages that had most recently scrolled out of context, so those were neither in the prompt nor in memory — the model couldn't see them at all. Every message that has left context is now in memory straight away. Only the model-written section summaries still wait a few messages, so regenerating a reply (which nudges how much history fits) doesn't cost extra summary calls; until then those messages reach the model word for word.
"Recent messages to skip" says what it does. It's now Never recall the newest in Settings → Memory & Context → Recall past messages, and its description explains it only matters when no context budget is set and never changes what gets indexed.
Adventure Personas keep a starting inventory written in any language. Item names in Chinese (or any script other than Latin) were all reduced to the same internal name, so a whole starting inventory collapsed into a single entry and seemed to vanish from the character sheet. Each item now keeps its own name on the sheet, and the GM can add, spend and remove it like any other. Ability names in other scripts are fixed the same way. English names are unchanged, so existing chats keep working.
Rin Chat Update Notes - Version: 0.6.6
19 September 2026
✨ New
Clickable choices on any card. Choice buttons aren't just for Adventure Mode any more: any card can offer them. A line holding only
[[choice: …]]becomes a button right where it's written, and clicking it sends that text as your message. Choices can now sit anywhere in a reply, so a card can group them under headings like a menu (Explore, Talk) — in Adventure Mode too. Only the latest reply's buttons work; older ones stay visible, greyed out, as a record of what was offered. A choice can roll one of the card's generators ([[choice: Draw a card | gen Tarot]]); stats and dice still need Adventure Mode. Card Forge knows how to write them, and the Guide has a section on it.More ways for a reply to be interactive. Any card can now also use:
- Ask —
[[ask: What do you name the dragon? | as dragon]]shows a text box; your answer is sent as your message, and withasit's saved for the card to use ({{getvar::dragon}}). - Pick several —
[[pick 2: Sword | Shield | Bow | Lantern]]lets you tick two, then Confirm. - Timed choices —
[[choice: Freeze | timer 15]]counts down under the reply and sends that choice if you don't pick in time. The clock starts only once you reach the choices, adds time for how long the reply is to read, pauses while you type, and has a Pause button. Settings → Chat Display → Timed choices turns them off. - Reveal —
[[reveal: Read the letter]] … [[/reveal]]is folded until you click it open; nothing is sent. - Choices that remember —
[[choice: Take the key | set has_key = true]]saves a story variable when picked (+=/-=count up and down). - Locked choices —
[[choice: Open the chest | if has_key | hint You need a key]]shows locked until the condition holds, then opens by itself. Conditions can compare (coins >= 5,door == open) and combine with&&/||;| hidekeeps a choice secret until then. - The story can change variables — a reply line
[[set: door = open]]is applied and never shown. Regenerating, swiping, deleting or undoing a message puts its variables back, whether a choice, an answer or the reply set them. - Documents —
[[doc: paper]] … [[/doc]]shows text as a letter, a newspaper, a terminal or text messages (sms, your own on the right). Add your own document styles, or restyle the built-ins, in Settings → Chat Display → Document styles.
- Ask —
Choose where the memory tree goes. With the memory tree on, Settings → Memory & Context → Recall past messages → Where to inject was locked to the system block. It's now unlocked, with its own setting kept separately from plain recall's, so you can move the tree's block into the recent history (at a depth) — which caches better — and switch back without losing either choice.
Export the Guide. Export guide at the top of the Guide saves the whole thing, and each section has its own Export button: Markdown, plain text (both saved to Downloads) or PDF (through the print dialog's Save as PDF). Handy for reading it elsewhere, translating it, or giving it to an AI to ask questions. The whole guide is also online at https://rin.chat/updates/guide.md, updated with every release, so an AI with web access can read it directly.
Health bars on your character sheet. In Adventure Mode, a stat with a matching maximum (
hpwithhp_max, ormanawithmana_max) now shows a bar under it on the character sheet, turning orange then red as it drops, like the bars enemies get in a fight.Token counts that match what a chat actually sends. A card's token count used to add up every field, so a card with a big lorebook looked like it cost tens of thousands of tokens on every turn. The card editor now shows what the card costs on every turn, followed by a lighter +N at times for the parts that come and go:
- the opening greeting, which is one chat message and drops out as the chat grows;
- dialogue examples, which are only sent while a chat has fewer than 8 messages;
- keyword lorebook entries, each sent only while its keywords are in recent messages. Hover the number for the breakdown. The section list on the left shows the same split, so Dialogue and Lorebook now read as "+N". Lorebook keywords, alternate greetings, group greetings and notes are never sent, so they no longer count at all. Preview prompt now labels its total as the cost at the start of a chat. Library tiles and the Largest (tokens) sort use the every-turn number, and Card Forge's "A new chat carries" panel uses the same count, with a new Lorebook, when triggered row.
My listings. A new screen (☰ menu → My listings) showing every card you've posted to aicharactercards.com and where each one stands: waiting on a moderator, published, or sent back needing changes — with the moderator's reason when they've shared it. A published card you've since edited is marked as an update in review, so it doesn't look like a new submission.
Upload a card to aicharactercards.com from the app. With your account linked, the card editor's Import / Export → Upload sends the card to the site and opens the site's submit form with it already attached — no exporting a file and hunting for it again in a browser. You write the title, summary and description on the form as usual and submit it there; nothing is posted until you do. Do it again with the same card later and the app opens the edit form for the listing you already have, so you update that card instead of posting a second one, and can revise its text at the same time — ratings, reviews and downloads carry over. The app tells you which form it's about to open, and warns you that submitting an edit takes a live card off the site until a moderator approves the new version.
Default persona, easy to find. The persona every new chat starts with now has its own Settings → Personas section (it used to be tucked under Memory & Context). You can also set it by right-clicking a persona card in the library or from a persona card's Tools menu (Set as default persona), or with the star beside a persona in a chat's persona picker. The default wears a default badge in the library.
Replace older versions of cards in one go. Imported updated copies of cards you already had as new cards, and ended up with pairs? Find duplicate cards now offers Replace older versions: in every pair, the card you added first takes the newer copy's content and image, keeps its chats, folder and notes, and the newer copy is deleted. When importing, the choice that does this for you is now called Replace (it was Merge, which didn't say that it overwrites the existing card).
Merging duplicates keeps every chat. Merging two cards from Compare used to delete the other card's chats; they now move to the card you keep. You can also choose which card's image the merged card keeps, and each duplicate shows when it was added and how many chats it has, in place of the "keep" label that only marked whichever card was listed first.
Spoiler mode for story and game cards. A card whose fields give the plot away can turn on Spoiler mode under its Metadata section. Anyone who opens it finds every section folded, and is asked before one is opened. The name, image, tags and notes stay visible, and the model still receives the card as normal.
Card type in Card Forge. The forge sidebar now has the same Card type choice as the card editor, under Display name, so you can make a card an Adventure Mode Game Master without leaving the forge.
Lorebook entries that load only when picked. A card whose choice buttons name lorebook entries (a menu, a list of places) used to load every listed entry as soon as the list was shown. In Card Forge an entry can now carry the line
MATCH: newest message only, which sets its scan depth to 1, so it loads only when the player's own message names it. The guide knows when to use it.Lorebook activation settings, matching SillyTavern's. A new Settings → Lorebook Activation section holds the settings that apply to every lorebook: Scan depth, Min activations and Max depth, Recursive scan with Max recursion steps, Include names, the case-sensitive / whole-word / group-scoring defaults an entry falls back to, Context share and Budget cap (one budget spent across all books at once), Insertion order for the character's own lorebook vs the shared ones, and a warning when the budget had to leave entries out. Recursive scan is on, so a book built for SillyTavern chains the way it did there: the text of an entry that fires is checked for other entries' keywords and those fire too. An entry that sets one of these for itself still wins. The Lorebooks page links straight to it.
🩹 Fixes
A reply's last choice, ask or document is no longer cut off. With "trim incomplete sentences" on, a reply that ended in a choice, a question box, a pick or a document lost it when the reply was saved — the line doesn't end in a full stop, so it was treated as an unfinished sentence. Adventure Mode was already exempt; now every card is.
Card Forge no longer duplicates behavior rules and speech patterns. When the guide rewrote an existing rule (turning a card to first person, say), it was added beside the old one instead of replacing it, so a card could end up with several copies of the same rule. A proposal that closely matches an existing rule or speech pattern now replaces it (the review shows which one), and one that's already on the card word for word is skipped. A reply that packed several rules into one box, labelled
behavior_rules[0]: …,behavior_rules[1]: …, is now split into separate rules too. The guide is also told much more clearly that rewording a rule changes that rule rather than adding a new one.Card Forge writes the change it talks about. Deep into a long session, the guide would sometimes say "Here are the updated rules" and include nothing, leaving you to ask again. It now notices and fetches the missing change itself, so it arrives in the review as usual.
Linux uses the desktop layout. On some Linux systems the app's web view reports that there's no mouse, so Rin Chat used its touchscreen layout: message actions sat inside the message behind a "…", covering the image buttons, and controls were oversized. The app now switches to the desktop layout as soon as it sees a mouse move. Phones and touchscreens are unchanged.
Chat Memory and in-app voices start on more networks. On some networks, notably in China, the engine Chat Memory and the Kokoro and Piper voices run on couldn't be downloaded from inside the app, and Chat Memory failed with "no available backend found". The app now falls back to a second download source for the engine, and to a mirror for the embedding model when Hugging Face can't be reached. If both fail, it says to check your connection, VPN or proxy instead of showing a raw error, and the debug log records which download failed. If the app can't download at all but your browser can, Settings → Memory & Context → Recall past messages → Install from files lists the five files to download in your browser and imports them.
A generator you save to the library shows up in Attach right away. After Save a copy to library (or adding one on the Generators page), a card's Attach from library… list kept the old list until you reopened the card.
Card Forge's guide turns on "No repeats in a batch" when you ask. Asked in chat for a generator whose names never repeat, it wrote the generator without the setting: the guide's chat instructions never mentioned it. It now sets it, and names new generators with spaces instead of underscores.
Card Forge and file overwrites leave your Generators library alone. When the guide revised a generator you had attached from your library, or a file overwrite changed one, the change was also written into your library's copy. The card now keeps the changed version as its own, and your library stays as it was, the same as Edit in 0.6.5.
Card Forge builds working Adventure Mode cards. Asked for an Adventure Mode or game-master card,
/createand Generate wrote an ordinary character: no choice buttons, generator rolls described instead of written as tags, and the card type left on Character, so Adventure Mode never switched on. Card building now gets the adventure instructions, ends each greeting with choices, writes the tags that roll generators, and sets the card type to Adventure Mode Game Master when you ask for one by name, including when Regenerate character turns an existing card into one (the review says so).Card Forge's Auto format can be reset. Once a model's card came back in simple tags, Auto kept using simple tags for that model forever, and choosing Auto again changed nothing. Choosing Auto in the card output menu now starts again from strict JSON.
The chat's context meter counts the card correctly. Its Character share included your private card notes, which are never sent, and left out the name, the depth prompt, post-history instructions, always-on lorebook entries and, early in a chat, the dialogue examples. The meter, and the line it draws where older messages stop being read, now match what is sent.
Regenerating a
/createcard keeps what you asked for. The one-line brief you give/createwasn't kept anywhere, so Regenerate character later had nothing but the guide's greeting to work from and could build a completely different character. The brief is now saved with the session and used on every regeneration.Card Forge flags lorebook keywords that fire on everything. A proposed lorebook entry with an everyday keyword ("woman", "it") or a one- or two-letter one now gets a note in the review, the same check the lorebook's Audit runs, so you can swap it for something specific before applying.
Card Forge warns when a rewrite drops an adventure card's choice buttons. On an Adventure Mode card, a proposed greeting or example that loses its choice lines is now flagged and left unticked, since without them the player has nothing to click.
Backing out of Create new leaves no empty generator. Clicking Create new in a card's Generators section, or + New generator on the Generators page, and going straight back used to leave an empty "New generator" behind. Now nothing is added unless you changed it.
Card Forge keeps lorebook entries with an indented label. A proposed entry whose
CONTENT:line started with a space was rejected as invalid and would have been lost.Card Forge keeps the parts of a request you named. Asked for a generator and a tag in Greeting 1 in one message, the forge dropped the greeting change as "not what was asked for". A field you name in your message, like Greeting 1, is now always kept for review.
A forged generator can't roll the character. When the guide put the character's own name in a generator's list (a patron named after them), it was turned into
{{char}}, so a roll could produce the character as a stranger. That option is now left out.The lorebook editor says "scan depth". An entry's collapsed Triggering summary said "depth 1" for its scan depth, the same words Placement uses for insertion depth.
Card Forge writes generator templates that read right. The guide's own example generators rolled lines like "34 years years old", and the guide copied that pattern, along with "a" before a value that might start with a vowel ("a Ex-Adventurer"). The examples are fixed, the guide is told to avoid both, and the review names the value when a proposed template still reads wrong.
Rolls that name a missing generator are flagged. A proposed
[Create …]tag or choice| gen …whose name matches none of the card's generators (or your library's) never rolls in chat, and nothing said so. The review now names it, and leaves the change unticked when it's new. The Generators section of a card (card editor, chat drawer, forge sidebar) lists any such roll already on the card.Choice buttons show names. A choice written as "Ask {{char}} for directions" showed the braces on the button, while the message above it showed the character's name. Buttons now show names as the message does.
Importing an AICC card file with no id works. A card file without an
id(hand-written or trimmed) failed to import with "card has no id". It now gets a new id and imports.Card Forge names fields the way the editor does. The guide sometimes wrote internal names like "behavior_rules[2]" in its replies; they now show as "Behavior rule 3". Field names in the review, the history and the plan chips were also always in English; they now follow your interface language.
Generator template problems show on the card too. A generator template that puts "a" before a value starting with a vowel, or repeats a unit, is flagged on the card's Generators list and in the generator editor, and the list's Revise with your guide button starts with that problem filled in.
Card Forge keeps example dialogues whole on Adventure Mode cards. A generated example whose reply ran on past its first line (a second paragraph, or its choice buttons) wasn't recognized as one turn, so a split exchange stayed split: four examples came back as eight, each flagged as not written in turns. They're joined back into whole exchanges now.
Card Forge keeps a new rule that uses a generator. When the conversation was about a generator, a proposed new rule telling the model when to roll it was left out as "not what was asked for". It now goes to the review with the generator.
Card Forge reads more broken generator blocks. A generator whose JSON had a key written as
"name="Specific Event"couldn't be read and was lost. That typo is now repaired.Escape no longer throws away a Card Forge review. Pressing Escape on the review of proposed changes discarded them, including a whole regenerated card. Only Discard does that now.
Asking the guide finds specific answers more often. A question like "can I put a [Create …] tag in a behavior rule?" was treated as a general one, so the guide was sent only a short excerpt of each section and answered that it didn't cover it. Questions that name a topic now get the full sections that match. The Guide also now explains which parts of a card roll a generator tag and which don't.
Draft only says when the guide tried to change the card anyway. With Draft only on, a guide that still wrote a change showed "proposed changes — see the review" with no review to see, and a generator it wrote still went to a review. Nothing is proposed in Draft only now, and a note says the guide wrote a change and how to get it reviewed.
Card Forge catches a character's name in cards with a subtitle. For names like "Lighthouse Keeper (Game Master)" or "ToRiicat — the Streamer", the name in the text wasn't recognized as the character's (or only its first word was), so it wasn't swapped for
{{char}}. The part before the subtitle now counts, and a review that also renames the card checks the other fields against the new name.Card Forge's quick buttons aren't mistaken for lorebook requests. Right after the guide talked about the lorebook, a request like More voice was treated as "go ahead with the lorebook", and the speech-pattern changes it asked for were left out. Only short go-aheads ("yes, add those") carry on a lorebook conversation now.
Card Forge doesn't mistake card edits for generator talk. After the guide had talked about a generator, a request to change another part of the card (the description, a new rule) could be treated as being about the generator and left out. Only short follow-ups carry on a generator conversation now.
The built-in HumanNPC generator reads right. Its template began "A {Build}", so it rolled lines like "A Average, 5'2" tall Female". It now rolls "Female, 5'2" tall, Average build, with Red hair." If you never edited your copy, it's updated for you; an edited copy keeps your changes and shows a note in the generator editor.
A choice whose extras spill past its brackets still becomes a button. A model sometimes closed a choice too early —
[[choice: Ask again]] | hint Past Rin was insistent— and the whole line showed as raw text. Anything after the]]that starts with|(a hint, a condition, aset, a timer) is now read as part of the choice.A choice written at the end of a sentence still becomes a button. A choice line glued to the text before it (
…what'll it be?[[choice: Noodles]]) wasn't shown as a button and appeared as raw text instead. It's now split onto its own line, in greetings and in replies. A choice in the middle of a sentence is still left as text.Card Forge makes picked menu entries load only when picked. When a new card's greeting offers choices and the lorebook has an entry with the same name as a choice, that entry is now set to load only from the newest message (the player's pick), even if the guide forgot to ask for it.
Card Forge's Tighten greeting keeps choice buttons. The quick button asked for a greeting that ends "on something the user can answer", and on Adventure Mode cards the rewrite often replaced the choice buttons with a question. It now asks to keep them. If you never edited that button, it's updated for you.
Card Forge says when generators are switched off. Asked for a generator while Let the guide write generators was off, the guide could describe one as if it had been added. A note now says nothing was added and where the switch is, and the guide is pointed to the right place for it (the top of the sidebar).
F6 no longer blanks the window. Pressing F6 moved focus out of the app, and the window went black until it was closed with Alt+F4. F6 now does nothing.
The lorebook Audit understands entries loaded by name. An entry with a title but no keywords was reported as "can never fire", even though
[recursion: title]or a routing token loads it. It's now a note saying how it gets loaded. The Guide also explains routing tokens with an example. The card editor's Card health check had the same blind spot and no longer counts those entries as "can never activate".HTML comments reach the model again. Any one-word comment such as
<!--SCENE_DOCKS-->was removed from messages and card text before sending, because it looked like a lorebook routing token. Now a comment is removed only when it names an entry in a lorebook that's in use, so cards that use HTML comments for their own markers keep them.
Rin Chat Update Notes - Version: 0.6.5
17 September 2026
✨ New
Rin Chat in French. Settings → Sizing & Layout → Language now offers Français alongside 简体中文, 日本語, Español and Deutsch, and a system set to French picks it on its own.
Tray mode — keep serving your phone with no window in the way. Rin Chat now has a system tray icon: Show Rin Chat, Hide to tray and Quit. Hiding puts the window away and nothing else changes — the vault stays open and your phone keeps chatting, because the desktop is still the machine doing the work. Quit from the tray is a real quit: it closes the vault and your phone loses access. New settings in Settings → Remote Access → Tray: Closing the window hides it to the tray (off by default, so close still quits), Start Rin Chat when I sign in, and Start hidden in the tray. The lock screen has a Hide to tray button too, and reopening comes back to it still locked. For serving your phone unattended, turn on Remember me on this device — without it Rin Chat starts at the login screen and answers your phone with "unlock your desktop", and biometric unlock always stops to ask.
Automatic tags for cards you edit. Settings → Chat Display → Automatic tags can tag a card you imported when you change its content (edited) and when you replace its art (new art), so the library's tag filter finds the cards you've reworked. Both are off by default and the tag names are yours to change. Cards you made in Rin Chat are never tagged. Turning on the edit tag also tags the imported cards you'd already edited; art you changed before that can't be detected.
Import log. The Library's import menu has an Import log that records every import: when it ran, where the cards came from, and what happened to each one — imported, merged, imported as new, skipped or failed, with the reason. Open jumps to the card, and Clear log empties it.
Card Forge: pick every field at once. The Edit character window had an All for each section but nothing for the whole card, so selecting everything took a click per section. There is now an All fields row at the top with All and None. Past a dozen fields it notes that one pass over that many can thin out the detail, in case you would rather split it.
Your name on cards you make. Settings → Chat Display → New cards takes a creator name, and Rin Chat fills it into the Creator field of anything you make here — a new character, or one Card Forge writes. Imported cards keep their own author, and so does any card you have already filled in.
Card Forge: edits that keep their shape. Every rewrite the guide proposes is now checked before you see it. An example dialogue that lost its
{{user}}:/{{char}}:turns, a greeting that opens with a speaker label, the character's real name where{{char}}belongs, speech in single quotes, a broken lorebook entry, or a field quietly cut to a fraction of its length is flagged in the review and left unticked; the two that can be fixed mechanically (the speaker label, the literal name) are fixed for you and say so. Retry, keeping the format asks again with the exact rules the last answer broke. Behind the scenes the guide no longer sees its own earlier proposals, which is where wrong greeting numbers came from, and when you say "greeting 2" it is told outright that means the second one. The guide also gets a plain map of what you call things (opener, backstory, lore…) to the fields they are, and a list of what it can and cannot do in the app.Card Forge: smart commands. Before the guide answers, a quick pre-review reads your message and turns "make example 3 spicier" into an edit of exactly that field. When it is sure, it just does it. When it isn't, nothing waits on you: the message goes to the guide as ordinary chat, and with Suggest (the default) the plan is offered under the reply — Did you mean an edit? with the fields as chips you can remove or add to, and Go; keep typing to ignore it. Automatic skips the offer; Off restores the old behaviour. Talk about generators is never read as an edit of the card's own fields (a generator's Appearance or Personality field is not the card's). The switch is in Settings → Chat Display → Card Forge, and the pre-review can run in one of two ways, set by How it reads your message:
- A model. Your AI provider does the pre-review, which costs one extra request per message. Model for smart commands picks which one: left on Same as the forge (default) it uses the forge's own provider and model, or pick any provider and model you have set up — a small, fast, cheap one is plenty for this job.
- Built-in (the default). No provider and no request. The app does the pre-review itself: rules catch a numbered entry ("greeting 2", "example 3") and the words the guide already knows for each field ("backstory", "opener", "lore"), and a small local model settles the rest. That model is all-MiniLM-L6-v2, the same one local vector memory uses. It isn't a chatbot and writes nothing: it turns your message into numbers that measure meaning and compares them with a description of each field, so it can still find a field you described in your own words. It's a one-time 23 MB download (shared with local vector memory, so no second download if you use that) and it runs on the CPU inside the app, taking milliseconds per message. It works offline, and your message never leaves your computer for this step. The trade-off: it only picks fields — your message goes to the guide word for word as the instruction — and when a rule didn't settle the choice it is unsure, so the message goes to the guide as chat and Suggest offers the edit afterwards instead of guessing.
- To switch back to a provider, set How it reads your message to A model and choose one under Model for smart commands.
Card Forge: fewer ways for a generation or an edit to go quietly wrong. Found by driving the forge end to end: an added greeting that copied an existing one is flagged as a near-duplicate; an example whose action beats drifted out of asterisks gets a note; stray characters from another script (a known glitch of some models —
矛盾的in the middle of an English greeting) are removed, from a freshly generated card, from generators the guide writes, and from a proposal in the review, which says so; a generator whose JSON came back with one missing bracket is repaired instead of thrown away; a reply that contains only a generator or a proposal no longer shows an empty bubble; /create with a one-line brief works on a fresh session (it used to do nothing); the guide no longer re-does requests it already handled (its earlier proposals, and what you applied or discarded, are now visible to it); a lorebook request only ever produces lorebook proposals, and asking for a lorebook entry and a generator in one breath keeps both (the lorebook half used to be dropped as "not what was asked for"); a card the forge generates has the character's literal name swapped for {{char}} everywhere but the name field, the way the rules always said; example dialogues keep one turn per line and get their{{char}}:label even when the model runs the turns together or leaves the reply bare (which used to fold every example into one); and speech the model wrote in 'single quotes' comes out in double quotes, at generation and in the review. Also: with Let the guide write generators or a lorebook on, a model that answers in strict JSON used to drop both (it was told to write them after the JSON, which a JSON-only reply cannot do) — they are now asked for inside the card object; a Regenerate that comes back with generators puts them in the review beside the text instead of losing them, and every generator the guide writes — in chat or that way — goes through the same review as a text change: its own row with what it holds, marked new generator, updates the one on the card or replaces … with the current version beside it, ticked by default, and once applied the same Undo this on its note; and the guide can no longer pass off an "[app: …]" line as something the app did — those notes were reaching the model as its own earlier turns and some models started imitating them. When the guide answers a Revise with your guide request with a question of its own, your answer still lands on the generator being revised (the link used to be lost after one reply), and the smart-commands pre-review is told what the guide just asked, so an answer like "barrels, salt cod, lamp oil — go ahead" is treated as an answer, not as a request to add something. A connection that drops mid-reply now says so in a sentence instead of the browser's own "TypeError: network error". And asked to roll a generator in the chat, the guide now explains the[fire][Create …][/fire]block instead of rewriting the generator. Undo this and Undo to here now also take the "Applied … changes" lines of what they undid out of the chat — they stayed behind as if the changes were still on the card, and the guide read them that way too. Lines left behind by earlier undos are cleared when the session opens. Undoing a change that added several entries at once (two lorebook entries, two greetings) now removes all of them — it used to remove only the last and leave the rest on the card with nothing left to undo them. On a long run of requests (lorebook entries two at a time, say) the guide could start answering "here are the next two proposals" with a list of names and no proposals at all: it was copying its own earlier replies, which it is shown with the proposal blocks taken out and blank space where they were. The blank space is gone, its two most recent replies that only added entries or wrote generators now keep those blocks so it has the format in front of it, Regenerate this reply keeps the "write it out" instruction the original message carried (re-rolls went out without it and came back as announcements), and a reply that talks about proposals — or about a generator you asked for — without containing any now says so in the chat, so you know to ask again and the guide knows nothing was made. And a go-ahead like "yes, write those two entries" or "yep, add those" while the guide is working through lorebook entries is now read as a lorebook request, which tells the guide to write each entry out in full. Lorebook keywords a model writes with dots or underscores ("Old.Mill.Road", "night_market") never match anything anyone types; they are turned into words, in the review (which says so) and in a freshly generated card. A reply that adds several lorebook entries (or greetings, examples, rules) in one go now brings every one of them to the review — only the first used to make it. A card whose name starts with "The" (The Gilded Lantern) no longer has every "the" in a proposal turned into {{char}}, a two-word name whose first word is also an ordinary word (Lantern Warden) no longer turns "the lantern flame" into "the {{char}} flame" — the first word alone now only counts as the name when it's capitalised and not after "the" — and the name fix leaves a lorebook entry's keywords alone, where {{char}} would never trigger. With several forge tabs open, a review that finishes in another tab no longer pops up over the one you are looking at — it waits on its own tab. Regenerate this reply on a reply that proposed changes now opens the review for the new version (the re-rolled proposals used to be saved but never shown, so they could not be applied), and adds any generators it wrote. Asked to change one numbered entry ("make greeting 2 end on a riddle"), the guide sometimes rewrote the entry next to it; it's now shown the opening of the entry it's meant to change. While the guide is still writing a proposal, its half-finished text no longer shows raw in the chat. Generated cards and proposals are tidied on arrival:\nwritten as text becomes a real line break (a greeting used to show "\n\n" on screen), a rule or speech pattern holding several lines becomes several, a generator option of "none" becomes an empty choice instead of printing the word, and a lorebook keyword that lost its apostrophe or ampersand also gets the entry title's spelling. The guide now knows how lorebook entries reach the model (by keywords in recent messages — nothing "pulls" them), how to build a generator suite a parent chains into, and — when you're making an Adventure Mode card — the choice, generator and stat directives and that the card type must be set. For reporting a forge problem, the gear menu beside the model picker has Export this session's debug log: the raw requests and replies of that session only, not your whole log.Roll a generator several times, and keep the results.
[Create NPC x3]rolls three separate NPCs in one go (up to 10). Addas=guardand the results are kept as chat variables the card and later messages can use:{{getvar::guard}}is the whole result and{{getvar::guard.Name}}one field — with a count,{{getvar::guard.2.Name}}and{{getvar::guard.count}}. They live in the message that rolled them, so deleting that message removes them too. Works anywhere[Create …]does: greetings, your messages, quick replies, lorebook entries and the model's replies. Tick No repeats in a batch on an options field (a name, say) so onex4roll never gives two people the same name. It also applies to generators chained from the one you rolled. Card Forge knows the setting and can turn it on.Adventure choices that roll a generator. A
[[choice:]]can now fire one of the card's generators when picked:[[choice: Look for recruits | gen Mercenary x3 Class=Archer, as=recruits]]. The choice is sent with the generator rolled into it — the same as the[[gen:]]button, but as one of the options — and stat effects still work beside it ([[choice: Hire a guide (10 gold) | gold -10 | gen Guide]]). The GM is taught the form whenever the story has generators.Conditional chained generators. A chained generator can now run only when this generator rolled a particular value: in the Generators editor, each ticked chain has Only if [field] is one of [values] — so a Villager generator can roll Species and then run Elf Names only on Elf and Dwarf Names only on Dwarf. The Card Forge guide can write these conditions too, and renaming the field keeps them working. (A card using this, opened in an older Rin Chat, runs the chains without the condition.)
Card Forge: your generators, visible and editable. The sidebar has a Generators section, at the end after the lorebook — see each one, attach from the library, remove, edit the card's own copy in the Generators editor (it opens over the forge and closes back to it), and Revise with your guide to have the guide rework one in chat. Generators that fire on their own or stay hidden are called out, since they act without being asked. The guide can now read them: the card's generators are part of what it is shown (it used to "improve" generators it had never seen, from memory), and a reference card's generators and lorebook are included in full, with the instruction to match their structure and depth — how many fields, how many options, how they chain — when you ask for ones like the reference's. And a generator the guide names "Create Merchant" is saved as "Merchant" — the "Create" is the invocation, so it was being called as
[Create Create Merchant]; an update still finds a generator saved under the old name.Open cards in Rin Chat from outside the app. Right-click a card file (.png or .json) → Open with → Rin Chat and it's imported, the same as dragging it onto the library — Rin Chat is only added to the Open with list, so your pictures still open in your image viewer. And aicharactercards.com can now send a card straight to the app: an Open in Rin Chat link starts Rin Chat (or brings it forward), downloads the card with your linked account, and imports it. If the app is locked, the card waits until you sign in. Card downloads from the site — these and card updates — now go out with your linked account, so cards the site only serves to signed-in, age-verified accounts come through as well.
Group chat: a real card picker, and a primary you can change. The Group chat window now uses the whole screen and picks characters from a slim copy of the library — the folder tree on the left (All cards, Unfiled, your folders) narrows a grid of cards with art, name and creator on the right, with the search on top of that. And every member row has Make primary: the chat moves under that card (it shows in that card's Chats), the old primary becomes an ordinary member you can remove, and the lines each character already spoke stay theirs.
Merge duplicates from Compare. Compare cards has a Merge into one card… button: pick the card to keep, then for each field that differs choose which version goes into it (identical fields need no choice). The kept card keeps its image, tags, folder and chats and gets the fields you picked; the other card — and every chat with it — is deleted, which the confirmation spells out before it happens. Both Compare and Duplicate cards now use the whole window, show each card's art (Compare beside the column headers, Duplicate cards on every row) and put the shared creator on its own line under the group's title instead of crammed into it.
🩹 Fixes
[Create Name, …]with a comma straight after the name now fires.[Create Traveling Merchant, as=trader]was left as plain text because the tag only recognised the generator when a space followed its name. A comma now works too, in chat, in choices that roll a generator, and anywhere else[Create …]is used.- Editing a card's generator no longer changes your Generators library. Before, Edit in a card's Generators section (in the card editor or Card Forge) quietly added the generator to your library and edited it there. Library copies then showed up that you never added, and they could overwrite the card's version later. Edit and Create new now open the editor on top of the card and change only the card's own copy. Going back saves the change to the card. Save a copy to library adds a separate copy when you want one. A copy you attached from your library becomes the card's own the first time you edit it, so a later library change can't undo your edit.
- Adventure choices that roll a generator keep the result out of your message. Choosing a line like "Look for recruits" used to add every rolled profile to your own message. The roll now goes in a hidden block, so the model still gets the result and your message shows only the line you chose.
- See which card an import matched. When an imported card shares a name and creator with one in your library, the prompt now lists each match next to the card it matched, with its art and folder. Open or Compare them, choose Merge, New or Skip for each card, then Apply. Large imports get the same list. A placeholder creator such as "anonymous" or "unknown" no longer counts as a match — identical content is still skipped — and the duplicate finder no longer groups those cards as versions.
- The Author's Note in System Prompts can reach your existing chats. It was only copied into a chat when the chat was created, so filling it in afterwards changed nothing in chats you already had. Turn on Use in chats without their own note (same Settings section, off by default) and every chat whose own note is empty uses the prompt config's note; the chat's note window says which note applies. A chat's own note still takes priority, and No Author's Note in this chat turns it off for one chat.
- A request the provider never answers now times out. The "model stopped responding" guard counted any bytes as progress, and a proxy that queues a request sends keep-alive pings the whole time — so Card Forge could sit on "Almost there…" for five minutes with Stop as the only way out. Pings no longer count; after two minutes with no real data you get the error and can retry. Also, when Card Forge's JSON attempts fail because the provider is overloaded (a 503, "try again in a minute"), it no longer concludes the model can't write JSON and pins the simple-tag format for it.
- A card made with /create in a fresh Card Forge session is kept. A new session only joined the saved list with your first ordinary message, and a slash command isn't one — so a session holding nothing but a freshly generated card and the guide's welcome was still an unsaved draft, and the next restart or reload threw the card away. A session is saved as soon as it has a card.
- Card Forge's guide can add generators in chat. With Let the guide write generators on, asking the guide for a generator on a card you'd already made did nothing — it was only allowed to write them during a full Generate, so it improvised a change the app couldn't read. It now proposes the generator right from the chat — in the review, where you apply it (a same-named one is updated) — with a line in the transcript and an entry in Card history to undo it.
- Reply suggestions take the message box's place. On a phone the suggestion chips sat beside the message box and squeezed it into a column one letter wide. While suggestions are showing they now use the whole row; tap one to put it in the box, or ✕ to go back to typing — anything you had already written is still there.
- Formatting under a picture. A greeting that starts with an image on its own line and the text right below it (the usual shape of greetings with art) showed that text unformatted — literal *asterisks* and no speech colour — because the line after an HTML image line was passed through as raw HTML. It's formatted now, in chat and in card notes.
- Ability scores you can type. In the adventure persona sheet, typing an 11 into an ability was impossible: the box rejected each keystroke that fell under the minimum of 3, so the first "1" never landed. The score, HP, level, XP and inventory quantity boxes now take what you type and settle it when you leave the box — clamped to the allowed range, and left as it was if you typed nothing.
- A phone page can't get stuck refreshing itself. When a screen's file was missing after an update, Rin Chat reloaded once to pick up the new one — but any other screen loading successfully reset that, so a page could reload forever instead of ever telling you. It now reloads at most once a minute and shows the error after that.
- The locked screen can be moved, minimized and closed again. The lock covered the title bar, so the window was stuck in place with no buttons until you unlocked it. It now has its own strip at the top: drag it anywhere, and minimize, maximize or close from the right.
- The chat's persona picker opens under its button at any UI scale. With UI scale set above 100%, the list was placed too far right — the wider the window, the further off the edge, until in a maximized window it was off-screen entirely and the button looked dead. It now opens under the button and stays inside the window. The same mix-up also put the library's keyboard card menu (Menu key / Shift+F10) in the wrong spot and left the scroll after a reply finishes short of where it should stop; both are fixed.
- Jumping to a section lands on it at any UI scale. With Sizing & Layout → UI scale set above or below 100%, clicking an entry in the Guide's contents stopped short of the section, and so did Settings' jump list and search, the card editor's section rail, Card Forge's field highlight and jumping to a chat message. They now scroll all the way to what you picked.
Rin Chat Update Notes - Version: 0.6.4
15 September 2026
✨ New
- Rin Chat speaks your language. Settings → Sizing & Layout → Language switches the whole interface to 简体中文, 日本語, Español or Deutsch, and by default it follows your system's language on its own. Dates, times and numbers follow the language you pick, and searching Settings works in it too. The change applies when Rin Chat reloads. The AI follows you there: Response language (System Prompts) now writes in the interface language on its own, so you only fill it in to have the AI write in a different language than the app.
- Card updates, ratings and reviews from aicharactercards.com. With your aicharactercards.com account linked, Rin Chat checks the cards you got from the site once a day:
- Cards with a newer version show an Update badge, and Card updates at the bottom of the library sidebar lists them all, with Check now.
- Review update opens the card with the update ready: every field that changes, side by side, and you pick which to take. A checkpoint labelled "Before AICC update to vN" is saved first, so Tools → History rolls it back.
- Skip stops reminding you about that version; a newer one still shows up. Tools → Check for update asks about one card on the spot, skipped versions included.
- The card editor shows the card's rating — click it to rate, read and write reviews, and reply.
- Cards downloaded before card IDs existed are matched to their site card once, after you say yes. Settings → Account & Security turns the daily check on or off and can check or match again. Only card IDs and a fingerprint of each card's name, description, personality and scenario are sent — never your chats or edits.
🔧 Improvements
- Hover the context bar for the whole breakdown. Pointing at the token bar above the chat box now lists every part filling the window at once — character, system prompt, persona, pins, memory, history and the rest, each with a dot in its bar colour, its token count and its share — instead of one tooltip per coloured band, which was hard to hit on the thin ones.
🩹 Fixes
- Right-clicking a field in the chat's character drawer or Card Forge shows Rin Chat's menu. Those fields opened the plain browser menu instead of the one the card editor uses, so spelling corrections, Add to dictionary, formatting and paste-from-history were missing there. The formatting shortcuts now work in those fields too.
- Typing in Chinese, Japanese or Korean no longer triggers actions mid-word. Pressing Enter to confirm a word in an input method also reached the field underneath, so confirming a word could add a half-typed tag, rename something to half a word, or run a search early. The chat, Card Forge and Direct Chat message boxes already ignored it; now every field in the app does.
- The card health check's warning about a single lorebook entry reads properly. It said "1 lorebook entry has no keys and aren't constant — they can never activate", mixing singular and plural in one sentence.
- Whole-word lorebook keys trigger in Chinese, Japanese, Korean and Thai. These languages don't put spaces between words, so a key with Match whole words on never found a word boundary around it and never fired — the same entry worked in SillyTavern. Keys now match inside that text, and so does a Latin name written straight into it. The same fix applies when renaming your persona across a chat, and to character names in chat memory.
Rin Chat Update Notes - Version: 0.6.3
14 September 2026
✨ New
- Choose the language the AI writes in. Settings → System Prompts → Response language sets one language for everything the AI writes: character replies, chat titles, summaries, scene notes, reply suggestions, Card Forge and lorebook entries — keywords included, so they match a chat written in that language. Leave it blank to keep the prompts' own language. Turn off Character replies too to keep roleplay in the card's language while everything else follows the setting. Image prompts stay in English, since image models read English best.
🩹 Fixes
Cards keep their AICC card ID through import and export. A card downloaded from AICC carries an ID that lets the site recognise it wherever it travels — groundwork for rating cards and spotting updates from inside Rin Chat. Rin Chat now reads it on import, keeps it with the card, and writes it back into every export, including SillyTavern PNGs. A duplicated card starts without one, since it's a new card.
Card Forge fits a narrow window again. In a window under about 900px wide — half of a 1080p screen, say — the forge laid itself out thousands of pixels wide: most of every message, the composer and the card panel were off the right edge, and what remained overlapped. It now stacks the transcript, composer and card panel down the page, the transcript scrolls inside a half-screen box so the composer stays near, and the page scrolls through the card fields below. Still not ready for mobile so left out of mobile remote access
Importing a card you already have is recognised as an exact duplicate again. The check compared a stored card with the incoming file in a way that depended on the order fields happened to be written in, and the two never agreed — so an identical re-import was always offered as a mere "same name and creator" match with Merge / Import as new / Skip, instead of being skipped as the duplicate it is. The Find duplicates tool was not affected.
A new forge session keeps its greeting. Sending an empty message in a brand-new session (to get the guide talking) replaced its opening line with the reply instead of following it.
A new Card Forge tab no longer flashes "Untitled session" on its chip while its session loads.
Settings changes reach an open chat however you leave Settings. Regex scripts, quick replies, prompt configs, message colours and the provider list were only re-read by an open chat when Settings was closed with its × or Back. Leaving through a header button, a keyboard shortcut, opening a chat, or a search result skipped that step, so the chat kept the old settings until the next close via ×. Every way out now counts.
Your messages sit on the side you chose again. After character messages started filling the full width, the Your messages setting (Right / Left) stopped having any visible effect — your own messages stretched across the whole row and looked the same either way, especially with user avatars hidden. Your messages now sit as a bubble on the chosen side, while the character's keep the full-width layout.
Rin Chat Update Notes - Version: 0.6.2
13 September 2026
🩹 Fixes
- The response-length instruction no longer shows up in replies. Some models repeated the "[Length: keep this reply to roughly … words]" line back — as their reply or inside their thinking — and it appeared in the chat. It's now removed from what the model sends before it's shown or saved.
- The card editor's notes column fits with UI scale above 100%. On a wide screen it sat beside the editor sized for the window's width before scaling, so with the interface zoomed in it ran off the right edge. The editor now measures the room it actually has — and so does Find & replace, which overflowed the window the same way.
- Reroll gives more variety. Each regenerate now uses a new random seed, so alternate replies differ instead of coming back nearly the same. If your provider doesn't accept a seed, Rin Chat notices and quietly stops sending one there.
✨ Up to five Card Forges at once
- Open several forge sessions side by side. Each gets a tab in Card Forge's toolbar and an entry in the open-chats stack, and keeps working while you're in another — a reply you started keeps generating. The + beside the tabs lists your saved sessions, with search — pick one to open it in a new tab, or start a new one. Sessions already open in a tab are marked, and picking one takes you to its tab. Opening a sixth closes the one you used longest ago (never one that's mid-reply); its session stays saved in the list. A new session only joins that list once you send it a message, so opening tabs doesn't fill it with empty ones.
- A card is only ever open in one forge. Opening a card that's already in a tab — from the library, the editor or the session list — takes you to that tab, so two forges can't overwrite each other's edits to it.
- Card Forge's session list is easier to find your way around. It's wider, it has a search box at the top, and each session shows when it was last worked on under its name.
- A roomier Card Forge toolbar. The card output format (Auto / Strict JSON / Simple tags) is now a small gear — lit when a mode is pinned — the model picker is narrower, and the "Synced" badge is a compact chip.
🎞️ Animated cards come alive in the library
- Cards with animated art now move in the grid. A card whose picture is an animated PNG plays right there in the library — and only while it's on screen, so scrolling stays smooth. It animates the same way anywhere its thumbnail shows, like the folder and card pickers. Your existing animated cards start moving on their own the next time you open the library; nothing to re-import.
🎲 Adventure Mode
- The story clock is now optional. A new Story clock toggle in the editor lets you switch it off for open-ended games — a date, a hangout, a sandbox — where a ticking countdown only invents urgency the story doesn't need. It stays on by default, so adventures that want a clock keep one.
- Fewer spoilers at a decision point. A choice button no longer reveals what it will do to the stats before you pick it, and the "Sheet: …" summary of what changed after a turn stays hidden too. Both show only when you turn on Show DM stats.
🧹 Smaller things
- The generator inspector shows the opening rolls. A chat's Generators tab now lists the randomizer results that fire from a card's own fields when the chat loads — a date's looks, personality and so on — not only the ones a message sets off.
- A Community step in first-run setup. It links to the Rin Chat Discord — discord.rin.chat — for help, feature ideas, and swapping cards and prompts with other users. If a provider you want isn't in the list, the provider setup screen now points there too.
- "Reset vault" is clearer. The warning now spells out that it only erases the current account's library and leaves any other accounts on this device untouched.
- See a picture full size. Click the card's image in the editor to open it in a lightbox, sitting clear of the title bar with its corners intact. In a chat, shift-click an avatar to see the portrait on its own — on a phone over remote access, just tap it — centred over the chat with nothing dimmed behind it. Click outside it or press ✕ to close — on a phone, just ✕.
Rin Chat Update Notes - Version: 0.6.1
12 September 2026
🧠 Long chats remember what you told them better
Improved Index timing. This is the big one. The indexer that turns messages leaving the context window into the chat's memory was scheduled in a way that could only ever run when a chat was idle.
Recall now searches on the message you just sent. It was reading the conversation a moment too early — before your new message had landed — so every search was about the exchange before the one you were having. Ask what your cat is called and it went looking for whatever you'd talked about last. On a test chat, the same eight questions went from 2 answered correctly to 6, with this and the fixes below.
Your question isn't drowned out by the character's last reply. The search also reads the message before yours, and a long reply outweighed a short question several times over. Now only the end of it is included — enough for a "yes" to still know what it's agreeing to.
The exact words you ask about are no longer the first thing thrown away. Passwords, names and dates found by matching their words were being dropped to make room for other results, because their scores were measured on a different scale. Asking for "the mod channel password" brought back neither message that contained those words; it now brings back the right one.
When two parts of the memory disagree, the newer one wins. The summary now tells the model that its parts are numbered in story order and that a higher-numbered part overrides a lower one. A sponsor's rate that changed from $340 to $420 used to come back as $340.
A correction now beats the thing it corrects. Search ranks by similarity, and the first, most emphatic statement of a fact always out-scores the later sentence that overturns it — so "I paid that debt off" lost to three copies of "I owe him forty crowns". Recall now always keeps a place for the most recent matching moment, and every excerpt is labelled with where in the story it comes from.
What's happened most recently is no longer a blind spot. The summary is written in whole sections, so the last stretch to leave the context window belonged to no summary yet and could only be found by luck. It's now included word for word at the end, and the model is told plainly whether it's fresh or already older than the messages on screen.
📝 Better summaries, no fact list
The "Fact ledger" option is gone. It kept a list of "what's currently true" alongside the summary, and in long test chats it was behind nearly every confidently wrong answer: a debt that had been paid still listed as owed, four different passwords at once, two outdated versions of the story kept side by side. If you had it switched on, the setting has simply disappeared — there's nothing to do.
The summaries do its job instead. Each part now records every event that matters later — what was decided, agreed, paid, owed, given, lost or changed — and the details people mention once and never repeat: a name or alias, family, where someone's from, an injury, an allergy, something they carry. Exact values like a password, a price or a date are copied character for character, and a change is written as "from X to Y", so it can be found by either the old value or the new one.
Summaries call you by your name. If your persona had a description, the summarizer was handed that whole description as your name, and sometimes named you after a word in it — "Personality owes Halvard forty crowns". Fixed.
Upgrading an existing long chat: open its Memory → Memory tree tab and press Clear index, then Vectorize all. New chats get the new summaries automatically; existing chats keep their old ones until they're rebuilt.
The opening of the chat is always in the summary. When the summary has to be trimmed to fit, it gives up the middle rather than the beginning, and every part it can't include in full gets a one-line headline, so nothing between the start and the recent past simply vanishes. Asked what he'd left in her cellar, a character had been inventing an answer; she now gives the right one.
Switching memory on for a long chat builds its overview in steps instead of asking the model to take in the whole story at once, which grew without limit on a very long chat.
🔍 Recall finds the exact word now, not just the gist
- Memory is searched two ways and the results combined: by meaning, as before, and by the words a passage actually contains. Meaning alone cannot find a password, a price or a name — nothing about "marigold seven" means anything — so those were effectively unsearchable. On a 195-message test chat that query now brings back the scene where the password was agreed; before, it brought back an unrelated argument.
- Two versions of the same fact are no longer a coin toss. "I owe him forty crowns" and "I paid him the forty crowns" look nearly identical to a search engine, so the newer one now gets a small, capped edge — enough to break the tie, never enough to drag in something irrelevant.
- You can ask for something in your own words. A recalled moment is matched on what was said in it and on what its part of the summary calls it — so "the storage arrangement for my goods" finds the scene where you agreed the cellar and the password, even though nobody used the word "storage" at the time.
- A weak keyword match can't take a slot it doesn't deserve; if nothing really matches, the memory says so instead of offering its least-bad guess.
- You can turn the new ranking off in Settings → Memory → "Match on words as well as meaning" if you prefer the old behaviour. It costs no extra model calls and no extra storage.
🧭 The memory panel is easier to read
- Wider, and in three plain sections: what the model is told, building the memory, and testing recall. The long explanations are folded into notes you can open when you want them.
- Test recall says what it found and for what. The result is labelled with the text it searched, scrolls into view when it's ready, and shows in one line how many parts of the summary are sent in full, how many as a one-line headline, and how many are skipped because they're still on screen. On a long chat that can be 7 of 70 in full — the rest is covered by the overview and the headlines.
⚡ Building the memory is about twice as fast
- Summaries are written a few at a time instead of strictly one after another. Rebuilding a 30-section chat took 3m36s against a serial run of the same chat that was still going at five minutes. Each summary is still saved the moment it's written, so a rate limit costs one call, not the whole run.
🧹 Smaller things
Card fields grow to fit what's in them. In the card editor, the chat's card sidebar and Card Forge, a text box now sizes itself to its content instead of hiding four-fifths of a description inside a two-row window. The row count stays the minimum, a height you drag yourself still wins — drag a field smaller and it stays that size until you forget it (below) — and a colossal field stops growing at 90% of the window rather than burying everything under it. Turn it off in Settings → Sizing & Layout → "Grow text boxes to fit".
Forget the box sizes you've dragged. A height you drag is remembered for that card and overrides the setting above, so Settings → Sizing & Layout → Saved box sizes → "Forget all" drops every one of them and hands the fields back to automatic sizing. Editors already open let go of their heights straight away, in every window. The one exception is the card editor's tall side column: the notes fill it whatever height you dragged them to elsewhere, since a height set in the narrow inline slot left them a two-line box in a full-height panel.
The card editor uses a wide screen. The editing column was a fixed 820px whatever the monitor, so at 2400px two thirds of the window was empty. It now grows with the window to a readable 1200px, and the section rail and the private-notes column follow it instead of being stranded — they're all sized from one number now. Below about 1700px nothing changes: there isn't room for a wider column and both side columns at once.
"+ Add" sits on the list's own header row. Behavior rules, speech patterns, greetings and example dialogue put their add button below the list as a full-size button — furthest from the label, and on an empty list it was the only thing in a section three rows tall. It's now a small button beside the label, matching the ✨ and ⤢ controls. An empty list also shows one empty box to type in rather than a label with nothing under it; leave it untouched and the list still saves as empty. The row's delete button is white on the red now, and its icon is actually centred in it.
The card's picture no longer grows with the window. It's a thumbnail beside the name and tags, so it stops at a comfortable size instead of taking a third of a wide screen. Generate and Replace now sit on the picture itself, appearing across its bottom edge when you hover it, instead of a permanent button below it — and replacing the image is that button now: the art itself is no longer a hidden click target, so a stray click on it can't open a file picker. On a touch screen they're always visible.
The notes fields no longer show a token count. Private Card Notes and Public Creator Notes are never sent to the model, so the count was quoting a cost the card doesn't pay. The card's total never included them, and still doesn't.
A rendered card note can be dragged taller. Switching a note to its rendered HTML swapped the text box for a rendered one that had no resize grip, so a long note was stuck in a fixed window. It resizes like the text box now, and a deliberate drag can go past the default height.
Expanding a rendered note stays rendered. The fullscreen editor always opened on the raw HTML, even when the note you expanded was being rendered — which read as the button doing nothing. It now opens the way the note was, and a picture in one is sized to fit the window rather than filling it top to bottom and pushing the writing out of sight.
The message "…" menu opens on phones. The row of per-message actions collapses behind one button on touch screens, and that button's menu was being clipped to nothing by the row's own sideways scrolling: tapping it appeared to do nothing at all. The button also sat outside the bubble whenever the action bar was set to any position other than top right, which pushed its menu off the side of the screen.
Adventure rules are coloured in the context meter. The one block that can take a fifth of the window was the one slice with no colour, drawn as empty track.
The adventure clock editor stays on screen. Clicking a clock near the panel's edge opened its number boxes half outside the sidebar, cutting off the first field.
Find & replace shows you every match. Each one is listed with the field it's in and the words around it, in a panel pinned to the top of the editor that leaves the card usable underneath. Click a match, or press Enter or F3, to jump to it: its section opens and the text is selected in its box — or highlighted, in a note shown as rendered HTML. When the match is up in the card's header, the panel moves to the bottom of the window to get out of its way. Replace matches one at a time or all at once; either can be undone from Tools → History.
Read the public creator notes in the side column. On a wide screen the card editor keeps a tall column for the private notes — the only roomy place to actually read one — while the public creator notes sat folded away under Metadata. A swap button in that column's header puts either note there, and swaps back. It only changes what's on screen: both notes keep their own home and their own text.
The ⓘ tips wait for you to mean it. They opened the instant the pointer touched one, so crossing a row of labels trailed a string of popups for things you hadn't asked about. A tip now needs a moment's hover — a click still opens it straight away. The ⓘ beside Card type also sat too high next to its label.
Every message spans the full width of the chat. A bubble was only as wide as its text, so a one-line reply sat as a small island beside a long one. It now fills the row beside its avatar, however short — in chats, Direct Chat and Card Forge alike.
Card Forge is desktop-only on phones reaching Rin over remote access. It's a multi-pane tool that never worked at phone size, so the ways in are gone there: the nav button, the editor's and library's Card Forge buttons, and the chat's Create character, which now says why. Remote access from a desktop browser keeps it.
Get Support now sits at the top of Settings, beside Pop out — one click to the community Discord for bug reports, questions and feature requests.
Rin Chat Update Notes - Version: 0.6.0
10 September 2026
📖 Card Forge can write the card's lorebook
- New per-session switch: “Let the guide write a lorebook,” its own row beside the generators one. With it on, Generate may give the card its own lorebook — entries the model loads only when one of their keywords comes up in the conversation, so the tavern, the guild or the war twenty years ago cost you nothing until they're mentioned. THIS IS IN BETA, EXPECT IT TO BE BUGGY
- The switch is permission, not an order. An entry has to earn its place by being conditional: anything true of the character in every scene belongs in the card's own fields, where it already is. Plenty of characters need none, and the forge says so rather than padding the card.
- Ask for one in chat, any time. “Add a lorebook entry for the inn” gets you a proper entry — title, trigger keywords, content — as a normal proposal you review before it lands. So does “rewrite that entry to cover her feud with the harbourmaster”, and everything you set on an entry yourself — whether it's always-on, where it inserts, its probability, its group — survives the rewrite untouched.
- Nothing can be quietly broken. An entry with no keywords would never fire, so it's refused; a rewrite the guide mangles leaves the existing entry alone instead of blanking it; and an entry the guide writes when the switch is off is discarded rather than embedded. Edit or delete them afterwards in the card editor's Lorebook section.
- The lorebook is right there in the forge sidebar, the same editor the card editor gives you — read, edit, reorder, add or delete entries without leaving the conversation. A one-line summary sits by the switch too, naming each entry and the words that fire it.
✏️ Draft only
- A switch above the message box that keeps the chat a chat. With Draft only on, the guide brainstorms and nothing else — no edit proposals, no review modal, no card changes. Ask it to rewrite the greeting and it will talk about how it would, instead of handing you a block to apply.
- It's belt and braces: the guide is told not to propose, and anything it proposes anyway is ignored rather than applied. Per session, so one card can be in draft while another isn't.
- Generate character still works, and so do the sidebar's own Improve buttons — pressing those IS asking for a change. Draft only is about what the chat does on its own.
🐛 Bug fixes
Card Forge follows the generation config you switch to. It read the provider list once when it opened, so switching configs anywhere else left it quoting the old context limit in its token line — and, less visibly, still sending to the old config’s provider and model. Locking and unlocking the vault “fixed” it because that rebuilt the screen. It now updates the moment the active config changes, wherever you change it from.
HTML comments in a message stay hidden.
<!-- a note for the model -->is meant to be invisible in chat, and it was — right up until the note contained a numbered list, at which point the whole thing rendered, markers and all. It’s hidden every time now, and still sent to the model. Comments inside code blocks are left visible, since there they’re the point.The tour no longer restarts itself at step 10. The step that walks back to the library from Worldbooks re-armed the first-run auto-start, which fired 700ms later and dropped you back at step 1 — every first run reached it, whatever your header looks like. Replaying the tour from Settings still restarts it, which is the one case that should.
The tour's highlight rings the right control at raised UI scale. The spotlight was placed in the wrong coordinate space, so above 100% it sat away from the button it was describing. Skip tour also stops looking disabled — it was styled with muted text on a normal button, and it always worked.
Dragging a card to a folder works at raised UI scale. The chip that follows the cursor was placed in the wrong coordinate space, so at 150% it sat half the distance from the top-left corner away from the pointer — further off the further you dragged. It tracks the cursor at every scale now. (The drop itself always landed correctly; it was the label that lied about where you were.)
A card’s note no longer follows the buttons. Hovering Chat or Edit on a library tile popped up the card’s whole note; it belongs to the artwork now, and shows when you hover that.
🧹 Smaller things
- The AI Restructure token warning says what it means. It read as “needs roughly 3,890 more than your 3,000 setting”, which sounds like a rewrite wants 6,890 tokens for a 4,000-token card. It doesn’t: it states the room the rewrite needs and the setting you have, as two plain numbers, and the tick box says it changes nothing but that one run. The card’s own size is gone from the sentence — with an Improve instruction it covered two passes while the requirement covered the larger one, so the two numbers never lined up.
- The example generator that ships with a new install is work-safe now.
HumanNPCis there to demonstrate how generators work — weighted options, a numeric range, a field that only appears when another field rolled a particular value — so it demonstrates that and nothing else. Existing libraries are untouched.
Rin Chat Update Notes - Version: 0.5.9
8 September 2026
🧭 A tour of the app
- First run now walks you round the app, the way the first chat already walked you round the chat: what each part of the title bar does, how the library and its folders work, the three ways to get a character (make one, talk one into existence with Card Forge, import one), worldbooks, the ☰ menu, search — and the one thing that trips everyone up, that you don't pick a provider, you pick a generation config and it brings its provider with it.
- Sixteen steps, skippable at any point with Esc, and it hands over to the chat's own tour at the end rather than repeating it. Its cards measure themselves, so they stay on screen at any UI scale.
- Both tours can be replayed — from the top of the Guide, or Settings → Diagnostics → Guided tours. The chat one arms itself for the next chat you open, since it has to run inside one.
📥 Imports from the site arrive as full AICC cards
- Pasting a card ID or link from aicharactercards.com used to fetch the SillyTavern version of that card, which folds everything into two big fields. It now fetches the AICC version, so appearance, behaviour rules, speech style and background land in their own fields — the same card, properly laid out.
- Nothing changes for you: same
AICC/###/###id, same card page links, same bare card numbers. Any direct link you paste is still fetched exactly as typed, and if the site can't serve the full version the import falls back to the older one and tells you that's what arrived.
🎲 Card Forge can build generators
- New per-session switch: “Let the guide write generators.” With it on, Generate may give the card its own
[Create …]randomisers — a patron at the bar, a loot roll, a mood wheel — with weighted options, numeric ranges, fields that only appear when another field rolled a particular value, templates, chaining, and auto-fire. They're wired to be callable by the model, so they work the moment the card is saved. - The switch is permission, not an order. The guide adds one only where the character actually has something worth randomising — a card with nothing variable about it gets none, and says so. Ask in the chat if you want one anyway.
- The guide can talk them through with you. With the switch on it knows what a generator is in Rin Chat, so “brainstorm some generators for this card” gets you actual designs — which recurring thing should differ each time, and which fields it varies by — instead of a list of side characters.
- Off by default, and per card — most characters need none, and a generator is the one part of a card that can act on its own. A guide that writes one anyway when the switch is off has it discarded.
- The sidebar lists what the card ended up with, and says outright when one fires on its own or is hidden. If the switch is on and none come back, it tells you why rather than leaving you guessing.
- Everything is checked on the way in: odds and ranges are clamped, a chain that points at a generator the card doesn't have is dropped, and a field can only depend on another field of the same generator. Edit or delete them afterwards in Generators.
🐛 Bug fixes
- Card Forge no longer splits example dialogue into one entry per line. A card came back with
{{user}}:in one example and{{char}}:in the next, all the way down — models were reading the numbering as “the next turn goes in the next entry”. The instructions are explicit now, and a card is repaired on the way in if a model still gets it wrong, so the examples land as whole exchanges. Existing cards aren't touched; re-generate or drag the turns together in the editor. - Pop-up menus no longer open off the bottom of the screen at a raised UI scale. A right-click menu, the clipboard picker, the library's own menus and the tooltips were all placed correctly but measured against the wrong screen: at 150% the app was told the window is 1013x676 when the space those menus actually live in is 676x451, so anything near the bottom was placed up to 225px below the edge. Everything that positions itself now measures the real space. Menus also re-place themselves when they grow — spelling suggestions and “Add to dictionary” arrive after the menu opens — and scroll instead of spilling if they're taller than the window.
Rin Chat Update Notes - Version: 0.5.8
6 September 2026
🐛 Bug fixes
- The title bar's ☰ menu is no longer cut off or buried. On a narrow window it was clipped at the bar's bottom edge (it looked like it was hiding behind the library sidebar), and with Settings open it opened behind the panel. It now opens over both.
- Right-click menus open where you clicked, and the library draws its cards, at any UI scale. Above 100% every pop-up menu was placed as if the screen were bigger than it is — the further right or lower you clicked, the further off screen it went — and the card grid's "which rows are visible" maths drifted as you scrolled, leaving blank space where tiles should be. Both were the same mistake in two places: a click position and an element's box are measured in different units than the ones used to place things, and only the zoom made the difference visible.
- The window paints its own background before anything loads, so a start-up or a sign-out reload no longer shows a pale frame around the app while the stylesheet arrives.
- No more size flash when the vault locks. Signing out passes through the loading screen, which drew the logo at 200px in a 460px column before the login screen redrew it at 150px in a 416px card — the jump everyone saw. The loading screen now uses the login screen's own card and logo, so the two are the same picture with different text. Separately, the UI scale of the account you just left stayed applied to the login screen for a frame; it's dropped before that screen draws now (visible only above 100% scale).
🐛 Bug fixes (cont.)
- Tooltips show every time now. Hovering a button gave you its tooltip maybe half the time — you had to move off it and back to get one. That was the webview's own tooltip and nothing in the app could influence it, so the app draws its own now: same wording, same delay, and they can't be cancelled out from under you. Tooltips that only repeated the button's own label are gone — a tooltip now has to say something the label doesn't.
- Saving a chat's temporary persona to your personas works again. It failed with a raw database message (“Query returned no rows”) — the app asks for the persona's card first and creates one when there isn't a card yet, but it couldn't tell “no such card” apart from a real failure, so it gave up instead of creating it.
- “Add to dictionary” is in the app's own right-click menu, next to the spelling suggestions. It was left to the webview's Shift+right-click menu, which testers found didn't work at all. It teaches Windows the word, so it stops being underlined here and everywhere else — and the box re-checks itself straight away.
- Spell-check underlines don't vanish any more. The app used to force the box to re-check itself after a pause in typing, which meant wiping every underline and asking the webview to redraw them — and sometimes it didn't. That's gone: underlines stay put. (The trade: a typo a few words back may keep its clean look until you edit near it, which is the webview's own behaviour.)
🐛 Bug fixes (cont.)
- A temporary persona saved to your library lands in the right fields. Its Personality went into the card's General description, leaving Core personality empty; it now goes where the editor shows it. (Chats read the two together, so nothing behaved differently — it just looked wrong in the card editor.)
- The Copy button on a message says it copied. A silent copy is indistinguishable from a misclick; it now uses the same brief line as the rest of the chat (and says so if the clipboard refuses).
- A worldbook entry's keys can be cleared while “always on” is ticked. The field locked with the keys still in it, so the audit warned about keys that do nothing and the only way to act on it was to untick “always on”, clear them, and tick it again.
- The column headings in Text formatting shortcuts stopped floating. They hovered over the rows as you scrolled the list, which read as broken — and no background is safe there, since a custom theme's panel colour can be see-through. They scroll with the list now.
- The persona icon in the chat header is part of the dropdown now — it sat beside it looking like a button, with a hand cursor and nothing behind the click. It's inside the box ahead of the persona name instead, so it reads as the label it always was.
🧪 Card editor: Restructure
- New “Translate” mode. Type the language — anything from
EnglishtoBrazilian Portuguese— and the card is translated: description, appearance, personality, behavior rules, speech style, background, setting, greetings, example dialogue and prompts. The character’s name comes too, written the way a reader of that language would (“Yuki Tanaka” → “田中雪”), with every mention of it in the card kept in step — it’s a row of its own, so untick it to keep the original. Nothing is restructured or rewritten, macros and formatting are kept as they are, and you review every passage before it lands. - Improve now applies your instruction to the whole card. It only ever reached the five fields the split rewrites, so an ask like “make her speech style more distinct” silently skipped the greetings and example dialogue. A second pass carries the same instruction to them, listed for review beside the split.
- Both skip creator notes and worldbook entries — either can be bigger than the rest of the card put together and would blow the token budget — and never touch lorebook keywords or tags. Improve leaves the character’s name alone as well; only Translate offers it. The screen says so.
🧰 Header
- Card Forge is on the title bar by default, and Generators moves into the ☰ menu — building a character is something most people do, building a randomizer isn't. Only the default changes: if you've already set your own header buttons, they stay exactly as you left them (Settings → Sizing & Layout → Header buttons).
🔌 Providers & generation configs
- “Use this one” is now on the provider page too. People go looking for a way to switch provider and there isn’t one — you switch by making a generation config active, and it brings its provider with it. Each config listed on a provider now has that button, the provider holding the active config is marked Active in the list, and the provider page says up front that a provider is never made active on its own. The Guide explains it as well.
⌨️ Function keys
- F1 Guide · F2 Settings (again to close) · F3 Characters · F4 Worldbooks · F5 Generators · F12 sign out (locks the vault). They go wherever you are, whether the button is on the title bar or in the ☰ menu, and they're on by default — switch them off in Settings → Shortcuts → Function keys. Desktop only: on a phone those keys belong to the browser. Suggested by a tester.
Rin Chat Update Notes - Version: 0.5.7
4 September 2026
🎭 Personas & folders
- The Personas view now shows every persona, hidden folders included — it's a type filter, not a place. All cards keeps respecting hidden folders.
- Folder names can't collide anymore — creating or renaming refuses a name that already exists or matches a built-in view (Personas, Favorites…), which could make cards seem to vanish.
- Cards shown outside their folder carry a 📁 folder chip that jumps to it; hidden folders are marked with a crossed-out eye; the editor's folder picker shows the full tree and can create folders inside any parent.
🧰 Composer & editor layout
- The attach button moved up to the quick-actions row — stacked inside the composer with expand and the mic, it overflowed the box.
- The message box resizes from a grip on its top edge (it grows upward, so that's where the drag belongs).
- Import & overwrite joined the exports in a combined Import / Export menu instead of hiding halfway down Tools.
💻 Platform fixes
- Linux: the persona dropdown works again — an invisible touch-target helper sat exactly over it on systems that report no hover capability.
- Windows: the intermittent quarter-second typing lag in the chat composer is fixed — a spellcheck refresh was re-scanning the whole draft right as you resumed typing; it now waits for true idle.
- The title bar can't overlap itself anymore. On a narrow window with UI scaling (or lots of pinned header buttons), nav labels could paint over the provider chip. The bar now measures its real space and drops to icon-only exactly when the buttons stop fitting — labels come back when there's room.
- UI scale no longer flashes on big repaints. With scale above 100% on a 4K or mixed-DPI setup, finishing a reply could make everything zoom slightly bigger for a split second — the old native zoom re-rasterized asynchronously. Scale now applies as CSS zoom, which paints at the final size in one frame; it also removes a multi-second native-zoom call from startup. The UI scale sliders (Settings, the quick Display size popover, onboarding) apply on release instead of mid-drag — live rescaling moved the slider under your cursor.
🛟 Beta-readiness hardening
- Full backup is actually full: chat pictures and attachments, Direct Chat and Card Forge transcripts, notes, custom macros, and card version history — everything except this machine's secrets (a test enforces that). Backup and restore both report anything they had to skip instead of claiming success.
- Adding a provider can't silently fail — presets fill in the label, and a blank one falls back to the hostname instead of discarding your setup.
- Sign-out waits for in-flight saves, so the last edit before signing out can't be lost.
- Snappier saves: heavy operations moved off the UI thread — long chats no longer hiccup on every reply.
- Crashes leave a crash.log you can attach to a bug report; corrupt session stores are preserved for recovery instead of replaced.
- Attach-a-webpage only fetches public sites — private/local addresses are refused, including through redirects.
- Terms of use & privacy now exist as a Guide section, alongside a LICENSE and third-party attribution file; the debug-log settings copy now says exactly what the log does.
🌗 Light mode: readable contrast
Light mode's orange, green, warning and danger colors were failing the 4.5:1 readability floor and borders had all but vanished — the palette is deepened to pass, and custom themes now pick white or dark button text by the same real standard. Dark mode's danger buttons switch to dark ink for the same reason.
🐛 Bug fixes — chat
- A message whose reply failed is saved and survives a reload while you retry; error banners with Retry stay until used or dismissed.
- Stopping a regenerate no longer leaves a blank swipe; Continue no longer drops the first characters of a cut-off reply.
- Two fast sidebar clicks can't write one chat's title or members into another; a Scene note edited in the Memory window saves on close.
- Greeting sync can no longer wipe a chat's opening message when the card refreshes — only an untouched greeting is synced.
- Picture messages can't be regenerated/continued/swiped as text via keyboard or phone; a picture that finishes after you switch chats is discarded instead of landing in the wrong chat.
- A Ctrl+key formatting shortcut no longer also fires a chat shortcut on the same combo; chat shortcuts are disarmed while any dialog is open and under the screen lock.
- Proactive messaging can't overwrite a reply you sent while it was generating, its first outreach isn't blocked by other conversations, and converted Messaging chats keep their settings.
🐛 Bug fixes — chat (cont.)
- Provider errors surface the real message (JSON error or HTML behind a 200, out-of-credit 429s, timeouts in plain words); reasoning settings can't be silently rewritten by background utility calls anymore.
- A local server that's running but has CORS off (LM Studio's default) no longer shows a bare "Failed to fetch": the Test button now detects that case and tells you exactly which switch to flip, the LM Studio preset says it up front, and the Guide's troubleshooting covers it.
- Local models whose chat template only accepts one system message (some Qwen3-family templates) no longer 500 on every character chat while Direct Chat worked: the app detects the rejection, merges its system messages into one for that model, and remembers — models and providers that accept the normal shape are untouched. What was learned is per endpoint + model (the same model through a gateway keeps the normal shape), and everything learned — reasoning and prompt shape — now lives in its own full-width "Learned fixes" card after the Reasoning section, each entry clearable. The notices about them queue instead of overwriting each other when several land at once, the handled first attempt no longer flashes a scary "chat failed: …Jinja Exception…" banner over a turn that succeeded, and when a template error genuinely is shown it reads as one plain sentence instead of nested JSON. The Learned fixes card also only lists a fix under the provider it actually applies to.
🐛 Bug fixes — adventure, groups & memory
- Sheet effects are computed in one place, fixing a family of drifts: swiping or deleting a swipe no longer gives a free turn on timed conditions and clocks; a failed Regenerate re-applies the old reply's effects with the original guards; Continue applies its own
[[stat:]]lines; retried empty replies don't tick conditions per attempt. - Ending the Story Director mid-review discards the unaccepted beat's effects; a choice clicked while the app is busy can't charge the sheet for a message that never sends; levelling up raises your live hp maximum instead of re-seeding it from the builder.
- Groups: the rolling summary names the member who actually spoke; mid-chat edits to the main character reach its group replies immediately; each member's lorebook keeps its own sticky/cooldown timers.
- Memory: recall no longer re-injects text the model is already reading, and the context estimate counts the adventure rules note, closing a hole at the seam.
- Dice/choice buttons stay locked during the director's reading pause; a freshly auto-read reply starts unpaused.
🐛 Bug fixes — Card Forge, images & voice
- Forge: switching sessions mid-reply is refused (the reply could draw into the other session); no double-send on fast double Enter; a failed image attachment stops the send and keeps your pictures and text; edited regenerated replies stick across ‹ ›; the full-screen editor can't delete a reply that streamed in while you typed.
- Images: OpenAI's endpoint works with both suggested models; a deleted image provider stays deleted (key included); Image Studio errors clear on their own; URL-answering providers keep the real image type; batch results can't swap the wrong picture on removal.
- Voice: Pause actually pauses API/Windows speech; NanoGPT async voices work from the phone; cancelling dictation as it starts can't leave the mic hot or double-insert later utterances; failed voice downloads report the real error.
- SillyTavern compatibility: single-colon macros (
{{roll:20}},{{random:a,b,c}}…) work; lorebooks with unset scan depth/probability match;/slashes/keys are regex while bare keys stay literal — and the audit, editor and scanner all teach the same rule now.
🐛 Bug fixes — library, import/export & backup
- Merging an imported card no longer wipes your private notes and tags on the next save; "Import & overwrite" covers the persona sheet, image prefixes and assets.
- CJK/Cyrillic card names export with real filenames instead of
_.png; bulk export never overwrites same-named cards; restored version history keeps its order. - Bulk ops: Select all includes the nested-folders section; switching folders clears the selection (it could delete cards you couldn't see); move/delete/clear-art report failures; deleting a folder from inside a subfolder no longer strands the view.
- Tags can't contain commas (they split in the index and became undeletable); tag colors survive renames; the stats dashboard and library scans respect hidden folders like the views do.
- Card editor errors show as a dismissable notice instead of replacing the editor (and your edits) with a red box; HTML creator notes render as text in tile previews; the duplicate finder no longer groups unrelated unnamed cards.
- Pinning a chat from one surface no longer erases a pin made from another; deleted characters' chats no longer linger in All chats.
🐛 Bug fixes — settings & input
- Memory's summary prompt, recall template and chunk boundaries actually save now; comma-separated fields (lorebook keys, trim strings…) can be typed into again; the auto-swipe blacklist accepts spaces and newlines.
- Number boxes clamp to their ranges (a typed temperature of 50 never reaches the provider) and commit on blur/Enter; text fields no longer fire an encrypted save per keystroke.
- A new formatting-shortcut row survives tabbing between its fields; the clipboard-history shortcut requires Ctrl or Alt and stays off password boxes.
- Enter to confirm a Japanese/Chinese/Korean IME conversion no longer sends the half-composed message (all composers); Enter in the search palette can't open the previous search's result.
- Settings search jumps go through the back chain (Alt+← returns), and the dropdown no longer shows garbled copy; "Reset this config" keeps context size, fallback model and tools.
- Every dialog traps Tab and returns focus on close; tiles, folders and chat rows work by keyboard; Escape closes one layer at a time; animations stop under reduced motion.
- The notes scratchpad saves its last keystrokes even on quit; a failed chat rename says so; the full-screen editor stays open when Send is refused mid-reply.
🐛 Bug fixes — phone remote, accounts & security
- Security: a batch settings read can no longer hand a phone the desktop's API keys; provider-key relaying matches the exact origin; a revoked/expired device's live stream ends immediately; after a lockdown nothing outlives the closed vault; theme imports can't smuggle a network fetch through CSS escapes.
- Phone: opening the page no longer pops a false "take over?" prompt; an expired PIN re-shows the PIN screen; the phone keyboard no longer drops mid-word; a save refused while the desktop holds the lease is retried on take-over instead of lost; hover-only controls (chat row pin/delete, swipe pager…) are visible on touch; keyless local providers work remotely; "Lock screen" is desktop-only (it trapped the phone).
- Accounts: renaming an account can't strand the vault mid-move; a second account no longer inherits the first's cached settings (keys included); an unreadable account list is never mistaken for empty and overwritten; recovery accepts phrases typed with capitals or extra spaces and refuses usernames already in use; failed unlocks say why instead of sticking on "Unlocking…".
- Pop-out Settings no longer runs duplicate background jobs, and closes on lock/sign-out.
- Telemetry copy now names everything actually sent, and each statistic sits under the switch that describes it.
📘 Guide & polish
The Guide caught up with the app: every Settings path names the current leaves, the persona/adventure instructions match the editor, the backup section says what a backup really holds, the remote and privacy sections describe today's behavior, and the new Lock screen home, lorebook regex rule, telemetry lists and Import / Export menu are all covered. Plus a LICENSE, third-party attributions, and Get help links to the community Discord from Settings and the crash screen.
Rin Chat Update Notes - Version: 0.5.6
2 September 2026
🐛 Worldbook scope field could eat all your RAM
Fixed the alpha's nastiest bug: typing in the "Only for these characters" scope field of a Worldbook or Character Lorebook entry made the text double itself on every keystroke — a few keys in, the app was chewing through gigabytes of memory and had to be killed from Task Manager. The field now behaves like a normal text box, and a regression test makes sure it stays that way.
⏩ Continue, rebuilt
Two layers of fixes for the Continue button:
- It now truly resumes the reply on models that support it: the model picks up its own message mid-stream instead of being asked to "please continue", so the continuation flows seamlessly — including when you've edited the reply first and want the AI to carry on from your edit. Models that can't resume are detected automatically on their first try and quietly switch to the classic method, remembered per model.
- No more duplicated text at the seam. If the model restates the last sentence before continuing (or rewrites the whole reply from the top), the repeated part is trimmed automatically instead of being stored twice.
Using /continue <instructions> or Shift-click still works exactly as before.
🔑 Locked out? The app now offers the way back in
When an unlock fails — wrong password, or a vault moved to a new computer where the saved key didn't come along — the error now offers "Restore access with your recovery phrase" right there, instead of leaving you to spot the small link at the bottom.
🛠 Card Forge: greetings stop leading with the name
Forge-generated cards had an overwhelming share of greetings opening with the character's name — and since greetings are the chat's opening messages, the AI then started every reply with its own name too. The forge now varies greeting openings (action, dialogue, scene…), and any stray {{char}}: speaker label on a generated greeting is stripped automatically.
⚙️ Generator edits reach open chats — even card-attached ones
Editing a generator in the library already updated open chats live (since 0.5.4), but if a card carried its own copy of that generator, the chat kept using the card's old version until you reopened the card editor. Open chats now apply library edits to card-attached generators immediately too.
📝 Character's Note no longer vanishes from some cards
Cards whose depth prompt was stored under the SillyTavern key name (prompt instead of text — common in hand-written or converted AICC JSON) showed an empty Character's Note everywhere and exported it as an empty field. The note is now picked up on load, and saving the card stores it under the proper key.
✨ Card Forge keeps up with the card editor
Two fixes for working on the same card in both places:
- Editing a card in the full editor and returning to its Card Forge session now shows your edits immediately — before, the forge kept the copy it loaded first (and could even write it back over your changes).
- The session menu has a new "New session for this card" option: start a clean forge conversation about a card without deleting the session you already have.
🖼️ New character + image first = no more error
Picking an image as the very first thing you do on a brand-new character no longer fails with "card no longer exists" — the card is saved first, so the image (and the card) stick even if you hit Back right after.
📱 Remote: spell-check corrections work again
Right-clicking a misspelled word in the message box (or a reply you're editing) from a browser now opens the browser's own menu with its spelling suggestions. The app's formatting menu still appears when you right-click with text selected.
⚡ No more warning flash when opening a chat
The "Connect an AI to start chatting" callout no longer blinks on for a split second while a chat loads — it now waits until the provider settings have actually been read before deciding whether to show.
🏷️ Tag merge suggestions stop overreaching
The "find more" merge pass was happy to call clearly different tags the same thing (magic/tragic, yandere/tsundere). Its typo tolerance now scales with tag length, so it still catches real misspellings and plurals without inventing matches.
✂️ Crop when changing a card's image
Uploading a new image onto an existing character now opens the same crop tool the AI image generator uses — drag to reposition, zoom to fit — instead of stamping the file on as-is.
🧰 The "Be the DM" sidebar can close again
Opening the DM sidebar in a regular chat left you stuck with it — the only collapse button lived in the adventure-mode character sheet, which that sidebar doesn't show. It now has its own collapse button, whether DM mode is on or off.
📎 Attach images and files — everywhere
The paperclip is here — in regular chats, Direct Chat, and the Card Forge. Images go to the model as real vision input (auto-downscaled — pick a vision-capable model; a text-only one tells you clearly instead of failing silently). Documents — PDF, Word (docx), OpenDocument (odt), even EPUB novels — are converted to text entirely on your machine, and plain text files (md, txt, json, csv, code) attach directly. Attachments stay with the conversation and are re-sent with the history, so the model can keep answering questions about them turn after turn. In the forge, attach a reference picture or a story excerpt and ask for a card built from it. If your model turns out to be text-only, character chats automatically resend the turn without images and say so.
The forge goes one further: the 🔗 button attaches a webpage. Paste a link — a Wikipedia article, a fandom wiki character page — and the app downloads it and boils it down to just the readable article: menus, tables of contents, citation markers, and navboxes are all stripped before it reaches your guide. Then ask for that character as a card.
📖 Make it canon
Two ways to turn what happens in chat into permanent lore:
- From a message — select the text that matters (or take the whole message) and hit the new 📖 button in the message's hover actions. A review window lets you edit the entry, set its keywords, and save it into the character's built-in lorebook — so it's canon in every chat with them, not just this one.
- Story so far — its own tab in the Memory window: the AI summarizes the recent chat into up to 5 lorebook entries (your choice — one per distinct fact or event, each with its own keywords). All drafts show together so you can check they work as a set, accept or reject each, and save the keepers in one go.
The review window also has ✨ Restructure with AI: it rewrites raw chat prose into clean, past-tense lore and suggests a title plus up to 5 keywords — everything stays editable.
⏰ Proactive messaging runs on a real clock
Characters who message you first now know what time it actually is. Every outreach — and every reply in the Messaging chat — carries the real date and time plus how long it's really been since each of you last spoke. Tell her "I'll be home after 6" and she can actually wait for 6; a 20-minute pause and a 3-day silence finally read differently. Regular roleplay chats are untouched — no real-world dates leaking into your fantasy scenes.
🧩 Custom macros
Define your own {{macros}} in Settings → Macros & Regex: a name and the text it expands to, usable anywhere macros work — card fields, prompts, messages. Values can nest other macros ({{char}}, {{roll::1d20}}, even your other custom macros), built-in names can't be overridden, and the macro playground resolves them live while you edit.
✨ Small features from your requests
- All chats — a new entry in the Characters sidebar lists every chat across all of your characters, newest first. Search filters it by chat title or character name; one click opens the chat.
- Duplicate a generator — a copy button on each row in the Generators library; the copy opens ready to edit.
- "Not duplicates" — the duplicate finder can now be told a group is a false positive; it stays hidden on future scans (and comes back if the group's cards change).
- Remove all worldbook entries from a character in one click (with confirmation) — no more deleting them one by one.
- The community Discord link is now in the guide's Getting started section.
🧑🤝🧑 Card Forge: reference cards
Bring a second character into a forge session. Pick any library card — including your persona — as a Reference card in the forge sidebar, add a note on how the two relate, and your guide treats it as read-only context: the two are never blended, and the card you're forging is written to be compatible with the reference (a persona reference even lets greetings address you as that person). Loaded fresh every turn; its token cost shows next to the card's.
🎲 Adventure mode: bring your own character
Ability scores now have a third option next to Roll dice and Point buy: Manual — type each score in directly, honor system. Made for carrying a real tabletop character into adventure mode as-is. Available when creating an Adventure Persona and in the card editor's Character sheet section.
🌱 Graduate an NPC into a full character
That throwaway NPC who keeps showing up? The Memory window has a new Create character tab: say who to extract ("the angry rival goalkeeper"), pick the message range they appear in — the first and last message are previewed so you know you grabbed the right scene — and a new Card Forge session opens seeded with that excerpt. Your guide builds the character from how they actually behaved and spoke, asks about the gaps, and the normal forge flow takes it from there. The chat's own characters are explicitly off-limits, so nothing gets duplicated.
🎲 Adventure mode holds the dice, even against stubborn models
Small local models sometimes skip the roll system entirely and just declare an outcome in prose — Result: 18 vs DC 16 — FAILURE on its own line, no roll button, no real dice. Those invented verdict lines are now stripped from the reply the same way forged 🎲 lines always were: the app's dice stay the only dice.
Heads-up: models below ~8B still struggle to drive adventure mode well (directives, checks, sheet discipline) — that part is model capability, not a bug. The Alpha Tester API models handle it fully.
🔧 Small fixes & polish
- Note images enlarge on top now — double-clicking an image in a card's private notes opened the big view behind the editor's toolbar and fields. It now overlays everything, like a lightbox should.
- The forge's model dropdown no longer blows up the toolbar when a provider has one long model name in its list, and the toolbar's labels got shorter so everything fits on a line.
- Attaching an empty file now says so instead of silently attaching nothing — a model given zero content will happily invent an entire character from the filename alone.
Rin Chat Update Notes - Version: 0.5.5
1 September 2026
🎨 Colors that do what they say
A follow-up pass on the new Theme & Colors screen, fixing everything that didn't quite land in 0.5.4:
- Every color option now changes exactly what its label says, everywhere in the app. Status colors, badges and dropdown menus were quietly stuck on default colors before — dropdowns now theme too, including in dark mode.
- Text stays readable on any color you pick. Buttons and chips automatically switch between light and dark text depending on how bright you make their background, so an all-pastel or all-neon theme no longer produces white-on-white labels.
- New: chat bubble transparency — set how much of your background shows through message bubbles.
- Fixed a crash when dragging quickly around the color picker.
- The message-style preview now follows the quoted / italic / bold body-text options while you change them.
🪟 Settings polish
- Mouse back button works in Settings — it walks back through the sections you visited, like a browser.
- Pop-out Settings opens at the section you were on, instead of jumping back to the top of the list.
- Changes made in a pop-out (colors included) now apply to the main window immediately — no reload needed.
📱 Remote access: your phone and desktop finally agree
- Changes made on your phone show up on the desktop immediately. Messages, edited chats, card and folder changes, favorites — the desktop used to keep showing its old copy until you restarted the app. Now the open chat and the library refresh live as the phone writes (without clobbering a reply mid-stream, and without losing a draft you're typing on the desktop).
- Settings and theme changes sync across too, in both directions.
- Fixed buttons on the phone remote that didn't respond or were unreadable.
👤 Default persona
New setting: a global default user persona. Chats that don't pick their own persona use it automatically.
Rin Chat Update Notes - Version: 0.5.4
🧭 Settings, rebuilt end to end
The whole settings window is redesigned. A grouped sidebar (Connections / Chat / Customization / System) with a search box replaces the old flat list — type a word and the sidebar filters to the panels that mention it, and opening a result scrolls straight to the matching card and highlights it. Every panel now uses the same layout: setting on the left with a one-line explanation of what it affects, control on the right.
Save buttons are gone. Everything saves on change or click-away, with a small "Saved." toast.
Also new here:
- ⧉ Pop out — open settings in its own window and keep chatting while you tune.
- Provider-style panels are now two-pane: your list on the left, the selected item's settings on the right.
- Samplers are dials — slider + number box, blank = "don't send it, let the server decide", ✕ to clear.
- Renames: AI Providers → LLM Providers, Voice → Voice Providers, Quick Replies & Dials → Quick Actions (dials are now prompts); its four lists share one format, each entry with reorder arrows.
- Remote Access, Data & Backup, Shortcuts, Quick Replies and the rest restyled to match — with proper tables for formatting shortcuts and edit-with-AI presets.
🔌 One provider, many model setups
Providers and model settings are now separate things. A provider is just the endpoint — URL and key. A Generation Config owns everything model-shaped: model, fallback model, reasoning, tool calling, context and response caps, and its own samplers. One NanoGPT account can back a fast config, a long-context config and a thinking config, and you switch between them from the chat header. Your existing setup should migrate automatically.
Reasoning settings (effort, wire format, thinking markers, the "don't think" tag) moved with the model into the config, since they're properties of the model rather than the endpoint.
🎨 Theme & Colors, on one screen
The theme panel used to be four stacked sections and a lot of scrolling, with the preview 900px away from the colours you were editing. Now it's one screen: every colour as a round swatch in an aligned grid, and a live preview pane pinned beside them — a miniature app with a real message, chips for every accent and status colour, and the Send button — that repaints as you drag a colour.
- Swatch labels now say what a colour actually paints — "Buttons & accents", "Links & hover text", "Selected items" — instead of "Purple" and "Orange", which stop being true the moment you retheme.
- A changed colour wears a ring; alt-click it to reset just that one, or use the "reset n changed" link for all of them.
- Editing a saved theme shows a quiet auto-saved status; built-ins show "built-in · read-only" with a one-click Duplicate to edit.
- Import/Export .rctheme are visible buttons now, not just menu items.
🎲 You can be the DM (experimental)
Very rough so far, probably won't work well.
In an adventure chat with other characters in the party, the sheet sidebar gains an "I'm the DM" toggle. Flip it and the roles invert: you run the game, and the AI characters become your players. Each of them only ever states what they attempt — you pick the ability it leans on, set the DC, grant advantage or disadvantage, and roll from the new party panel. The campaign card stops taking turns while it's on; turn the toggle off and the chat goes back to normal.
Experimental — expect rough edges, and tell us where it breaks.
🛠 Card Forge
- Preset messages above the forge composer — your own reusable prompts to the guide. Click inserts into the box to edit; Shift-click sends immediately.
- A field being rewritten by the AI now shows the work on the field itself in the sidebar, where you're actually watching the result land.
- A card's private notes are editable inside the forge, and edits go to the real card.
- Notes — a named scratchpad for the snippets you keep retyping — a tone brief, a formatting rule, the setting you build every character in. One app-wide list, first available in Card Forge, insert-into-brief with a click. They're yours rather than any card's, so the same list follows you everywhere the panel appears.
Character Editor
- The editor's Restructure action grew options: choose between squeezing hard (for a bloated import) and maximum preservation (for a hand-written card), give the Improve pass instructions, and let one restructure exceed your response-token cap so it can write the whole card back — with a warning when the cap looks too small.
- The Improve pass has one-tap preset chips (Tighten, Distinct voice, Deepen backstory, Plainer prose) — your own list, separate from the per-field Edit-with-AI presets, with the same ⚙ Manage editor.
📖 Lorebooks into characters
A character's embedded lorebook (the one that exports with the card) can now be filled from outside:
- Card editor → Worldbook: Import lorebook JSON… (SillyTavern World Info too) or Copy from library… — the entries become part of the card, as if it was imported with them.
- Worldbooks grew a Character lorebooks section listing every character that carries an embedded book — edit any of them right there — plus a copy into character button on each standalone book. + New worldbook now asks whether the book lives standalone or inside a character.
- A card that already has entries asks: Add to existing or Replace.
📦 Generator imports that collide
Importing a generator whose id you already have now asks what it is instead of guessing: Merge (it's a newer version of yours), Import as new (it's someone's copy), or Skip — with the actual differences shown so you can tell which.
🖱 Smaller fixes
- Selecting a provider or config in Settings now just opens it for editing — the checkbox on each row (or Use this one) is what makes it the default. Browsing your configs no longer switches what chats run.
- Long pickers (add a character, attach a worldbook) now load more as you scroll instead of stopping at 60 and telling you to refine your search. A 700-card library is a normal library.
- 📱 On a phone, per-message actions sit behind one button instead of nine tiny always-visible icons on every message.
- 📱 Remote access fixes: the provider settings tabs no longer crash the page — API-key stores can only be edited on the desktop, so remotely they're view-only now (generation configs still save). The settings sheet no longer scroll-fights the page behind it, and the persona picker actually opens — an invisible tap-target overlay was eating the tap.
- 📱 On a phone, the composer's mic and expand buttons moved from the chat header down to the quick-action row just above the message box.
- 🐧 On Linux, the window finally has real resize edges — grab any edge or corner, with proper resize cursors. (Windows always had this via the OS.)
Rin Chat Update Notes - Version: 0.5.2
🏷 The tags box is resizable
A heavily-tagged card showed about two rows of chips and scrolled the rest, with no way to open it up.
Grab the bottom-right corner of the tags box and drag it taller. It still opens at two rows, so a card with three tags doesn't get a big empty panel — but the two-row limit is now a starting size rather than a ceiling. Works everywhere tags are edited, including bulk tagging and the tag assign dialog.
The tag suggestions no longer vanish on a second click. Clicking inside the tags box once opened the list; clicking again closed it, and it would not come back until you clicked somewhere else and back in.
📐 The editor remembers how big you made a field
Drag a field taller in the card editor and it opens that size next time you edit that card. Sizes are remembered per character, not globally — a card with a 900-word greeting can keep that box open without every other card inheriting a giant one. The tags box is included.
Nothing to turn on: resize a field and it sticks. Drag it back to its normal size and it stops being remembered. Deleting a card forgets its sizes too.
Resizable fields show a grip now. There was no sign a field could be dragged at all — the corner handle had been hidden because the browser's own version is a pale box that looks like a rendering glitch on a dark theme. It's drawn in the app's own colours instead, and brightens when you hover the field. Every field that actually resizes has one; nothing that doesn't, gets one.
🗂 One "Card type" instead of three switches
The card editor's Features section had three separate True/False dropdowns — Adventure mode, Persona, Adventure persona — which is eight combinations for five meanings, several of them contradictory. They're now a single Card type, sitting beside the Display name at the top of the editor:
- Character (the default)
- User Persona
- Adventure Persona
- Adventure and User Persona
- Adventure Mode Game Master
Every existing card already has the right type — it's worked out from the old switches, so nothing needs re-saving and no card is rewritten just by being opened. Picking a type still writes the old switches alongside the new field, so a card you share with someone on an older version keeps working, and a card they send you is understood here.
🪪 Switching persona mid-chat
Change persona partway through — the dropdown in the top bar, an edited temporary persona, or an adventure persona — and the app now offers to rewrite the rest of the chat to match. {{user}} follows a rename on its own; everything the model already typed does not — a hundred replies naming the old character, a sheet whose stats are keyed to it, the turn order, the campaign plan. Those used to stay behind, so you ended up with two half-sheets and a story about a stranger.
The offer lists exactly what it would touch and you can decline it. Matching is whole-word and case-sensitive, and the prompt says so — if the old name is also an ordinary word in your story, skip it and the sheet keeps working under the old labels.
🧩 Card Forge never overwrites your card without asking
Regenerating a character is a proposal now, not a write. It used to replace every field the instant the model replied — no preview, no undo, and on an imported card that was somebody else's work gone. You now get the same field-by-field review the guide's chat edits use: tick the ones you want, take all, or throw the lot away.
A field with content is never replaced by an empty one. If a regeneration drops a field it wasn't thinking about, that field is left exactly as it was and isn't even offered as a checkbox. Same for list entries it didn't reach — regenerating with five greetings against your eight leaves the last three alone.
Card history. Every change the forge makes to a card is recorded, and a new button beside the card opens the list. Two ways out of a change:
- Undo this — puts back just that one, leaving everything done since it untouched. If a later change has since rewritten one of the same fields, it tells you and leaves that field alone rather than quietly reverting the newer work too.
- Undo to here — rolls the card back past that point, landing exactly where it stood before.
Each entry opens up to show the actual text of every field it touched — what was there before, what the change wrote, and if something has been rewritten since, what the card holds now. Fields in that last state are flagged, because those are exactly the ones Undo this will leave alone.
📱 Remote access fixes
Enter is a line break on a phone again. With Enter-to-send on, a soft keyboard had no way to type one at all — there's no Shift+Enter on a touch keyboard, so every attempt at a new paragraph sent the message. On a touchscreen Enter now always inserts a line break and the Send button sends. Devices with a real keyboard are unaffected and still follow your Enter-to-send setting.
Spellcheck corrections work in a browser. Remoting in from a PC, misspelled words were underlined but right-clicking them opened the app's own menu instead of the browser's, so there was no way to accept a correction. A right-click with nothing selected now falls through to the browser. Select text first and the formatting / AI-edit menu still appears as before.
Phone chat header, rebuilt. The chat list button, New chat and the chat name have moved up into the app's own header bar — they were a whole row of their own before, on a screen that can't spare one. The provider chip is now just its icon (name and model are still in its tooltip and in Settings), and the persona picker is a purple icon button like everything else in that row rather than a wide dropdown. Tapping it still opens the usual list.
Two things that fell out of that move are fixed too: there is no longer a second New chat button below the header, and the empty strip the chat name left behind is gone — its hover-only rename tools were still taking up the row on a screen with no hover.
📱 Remote access fixes (continued)
The mic and expand buttons moved out of the message box into the toolbar row, at its far left. Inside the input they had to stay small enough not to cover your text, which made them the two hardest things in the app to tap — and at some sizes they overlapped each other outright. The message box gets its full width back. Desktop keeps them in the input, unchanged.
A feature the desktop won't run remotely now says so. Those calls were refused in silence, so the only symptom was a control that did nothing. You get a short message instead — the desktop's own wording, naming what it turned down. Settings the desktop deliberately keeps to itself stay quiet, as before: that is the design working, not something worth interrupting you for.
Rin Chat Update Notes - Version: 0.5.1
A follow-up to 0.5.0's phone release: remote sign-in is simpler and stricter, phones size themselves properly, card notes can hold pictures, and adventure mode hands a lot of bookkeeping back to the app instead of trusting the GM to remember it.
🔐 Remote sign-in is a PIN, and it bites
Pairing is gone. No codes to exchange, no device list to curate — a phone connects with your PIN, and that is the whole flow.
It is stricter in exchange: ten wrong PINs locks the vault. Not the session, the vault — the desktop goes back to the password screen and everything encrypted stays that way. Something guessing at your PIN over your network gets ten tries, ever.
Signing out on the phone now ends the remote session, rather than running the desktop's sign-out flow at it and leaving the connection half-alive.
📏 Your phone is not a small desktop
- The desktop's UI zoom no longer applies on a phone. If you had scaled the desktop UI up, your phone inherited that on top of its own scaling and everything was enormous. Phones have their own font size setting now.
- The forge sessions menu fits the screen instead of running off the edge.
- After an update, the phone heals itself. It could get stuck holding half of the old build and half of the new one, which showed up as blank panels or a screen that simply never loaded. It now notices and reloads.
- Cards with no art show a proper placeholder over remote instead of a broken image.
🖼 Notes can hold pictures
Card notes render as formatted text with images now, and double-clicking an image opens it full size.
Images that live on the web used to sit at "Loading image…" forever in some cases. They load.
🎲 Adventure mode: the app referees, the GM narrates
The pattern behind most of this: the ways adventure mode went wrong were almost never the GM making a bad call — they were the GM forgetting to make one at all. Fifteen messages with no dice. A meter created and then never moved again. Those are now the app's job.
Clocks
- Click a dial to edit it, drag it to fill it. They used to be editable only as a text row in the stat list, under a truncated label.
- They no longer appear twice — once as a dial and again as a stat row showing the same number.
- The same clock could get created twice, so you had two "Satisfaction" dials with different values. Fixed on both sides: the duplicate is dropped, and existing chats stop drawing it immediately.
- Clocks can drift on their own. A crowd's attention, a disguise holding, an alarm cooling off — set it once and it slides every turn the GM doesn't touch it. A pursuit can mount the same way.
The GM's own honesty
- It cannot rewrite your ability scores. A GM that wanted a scene to work would quietly raise your Charisma from 8 to 16 — which deletes the character you built. Refused now, and it is told why: give you advantage, an item or a condition instead. A flat sheet is a choice, and an 8 is a person who fumbles.
- It gets shown what it has actually been doing — how many rolls, stat changes and choices its last five replies contained, and any meter it has never once moved. A model can't notice what it forgot, but it can read a count.
- Broken meters repair themselves. Writing a bar as
9/10when it should be a plain number next to its maximum used to draw nothing at all. - Wheels and generators can record their own result, instead of asking the GM to remember what it just dealt.
The campaign plan is a storyboard now, not an essay: the premise, who's in it and what they want, what happens if you do nothing, scenes to reach for, and where it can end. It reads as a menu the GM steers by. Works for a dungeon crawl, a game show, or whatever else you point it at.
Creator notes never reach the model. A card's notes field is for whoever downloads the card — changelogs, build notes, mechanics that were removed. It was reachable as a macro, so a stale changelog could land in the model's context and read as live instructions.
🛠 Card Forge: guides are just their voice
A guide used to be one big editable blob that mixed who the guide is with the format rules the app itself reads. Two problems fell out of that, and both are fixed:
- Editing a guide could quietly break card generation — trim the wrong paragraph and its suggested edits would show up in the diff view and then apply nothing.
- Duplicating a guide froze those rules forever. Improvements shipped with the app could never reach a copy you made.
Now a guide is only what taste owns: personality, scenario, example dialogue, opening lines, Session style (how hard it pushes back, how many questions at a time) and Card writing style. The format rules come from the app and stay current.
Card writing style is the one to know about — a plain line like "3rd person pov, present tense, sparse prose" applies to every field of every card that guide builds. That used to require editing the spec by hand.
Your existing guides carry over automatically, with your own edits kept. If a guide had changes the app can't place, they're preserved in an Advanced additions box with a note — worth tidying, since it costs tokens every message.
🔧 Also
- The crash panel no longer blames the app for someone else's code. A browser extension throwing an error in the page put up our "something went wrong" screen.
- Long chats render faster — messages without variables in them stop re-rendering every time any variable changes.
Rin Chat Update Notes - Version: 0.5.0
If you are on 0.4.8, this brings you 0.4.9 as well. That release was announced but never reached the update server, so everything in those notes — your abilities moving the dice, levelling up, the GM's hidden campaign plan, the character builder work — arrives with this build too.
And then 0.5.0 on top, which earns the jump: your phone now runs the real app.
📱 The whole app, on your phone
The slim phone client is no longer what you get. Remote access now serves the actual desktop UI, with a phone layout built on top of it — not a cut-down copy of three screens.
That means the library, the card editor, chats, adventure mode, worldbooks and personas, on a phone, laid out for a phone:
- Cards — browse, search, create, edit, tag, file into folders, delete
- Chats — the full transcript, swipes, per-message actions, adventure widgets
- Speech plays on the phone, rather than out of a computer in another room
- Everything is rebuilt for a narrow screen: the title bar folds into a slide-out menu, the library toolbar collapses to a single row, card tiles are reshaped, and the full-screen field editor is finally actually full screen
Your desktop is still in charge. It holds your vault key and your provider keys, and neither ever reaches the phone. Generation, encryption and disk access all stay on the machine running the app — the phone is a window, not a copy.
One device writes at a time, with a handoff prompt from either end. /lite still serves the old lightweight client if you prefer it, and /app forces the full UI.
🔒 What a phone is allowed to touch is now a written list
Every command the desktop exposes is blocked from remote until it is explicitly classified — 54 of 128 are reachable today, and adding a new one fails the build until someone decides which side of the line it sits on. Your vault and identity, the host filesystem, the host network, and the remote server's own administration are permanently desktop-only.
Provider settings reach the phone with the keys stripped — enough to show you a model picker, useless to anyone who intercepts it. And image and blob commands no longer take a path from the caller at all, so a remote client cannot aim a destructive command at an arbitrary folder.
🎲 The GM has to roll
A fight, a persuasion attempt, a climb, a stealth check — the game master can no longer tell you how it turned out without asking for the dice first.
The rule now names the categories out loud, and more usefully it names the five ways it used to slip past, because each one reads as ordinary narration in the moment rather than as breaking a rule:
- resolving it inside a sentence — "you swing and the bandit crumples"
- summarising a whole fight in one clause — "you cut your way through the guards"
- doing it for the NPC's side, where an enemy strikes or lies or grabs you unopposed
- taking your own claim as the result — "I convince the guard" is an attempt, not an outcome
- opening a reply with the check already settled offscreen
If something is genuinely trivial there is no roll and no drama — difficulty belongs in the DC, not in skipping the check.
🗣 Words weigh in — properly
A spoken roll is graded −6 to +6 now, up from ±2, against a real rubric: counterproductive, generic, unremarkable, fitted, or this should work. At ±2 a good line could never close a real gap, so the say-box was decorative. It isn't any more — a strong pitch can carry a bad roll, and a lazy one can sink a good one.
Grading judges what you said to this listener, using only what your character could know. It rewards naming their motive, their fear, or something you actually learned in play — not prose polish, not length, and rudeness that fits your character is not a penalty.
And the scorecard is gone from the story. The GM used to write out its whole appraisal — "I judge these words… 7, pitch +4 → 13 vs DC 12 — success" — before getting to the scene. It still does the arithmetic, you just never see it. You get the narration.
Your words also render properly now, in their own panel above the dice card, with the same markdown as any other message instead of raw asterisks.
Placing ability scores no longer needs a drag, either — click a score, click an ability.
🐧 Linux: drag and drop actually works
Dragging a card onto a folder, re-parenting a folder, reordering card fields, placing ability scores — none of it did anything on Linux. Not a bug in any one screen: WebKitGTK, the browser engine behind every Linux build, does not deliver HTML5 drag and drop at all. The cursor showed "no", the drop never fired, the thing snapped back.
Every in-app drag now runs on pointer events instead, which every engine supports. Dragging a file into the window to import it was never affected and still works.
🧠 DeepSeek and other thinking models
If you use DeepSeek you will have seen this: the model appears to dump its own instructions into the chat, and then choices and dice rolls stop appearing at all.
That text was never the system prompt — it was the model's thinking, rendered as the message. DeepSeek's template writes the opening <think> tag into the prompt itself, so the model only ever sends the closing one, and we were looking for the pair. Now handled: the thought goes to the thinking block where it belongs and the reply is the reply.
It compounded, too: a leaked reply gets saved to the chat, so every later turn has an example to copy.
⚠️ Raise your max response tokens on reasoning models. They spend that budget thinking before they write anything. At 400 a reply can be entirely thought and get cut off with no narration, no choices and no dice — nothing can recover that one.
Chats already full of leaked replies mostly sort themselves out — only replies cut off mid-thought need deleting.
🔧 Also
- Nothing on a phone can push the page wider than the screen. One long unbroken string in a card field — a URL, an ID — stretched the editor to four times the screen width.
- Modals fit the screen. Several rendered at their desktop design width — up to 1100px — on a 360px phone, most of the panel off the edge. They also stop hiding their buttons behind the keyboard.
- One tap opens a chat from the card editor's Chats menu, instead of two. Pin and delete were revealed on hover, which a touchscreen cannot do, so the first tap was spent on that. Long-press a chat for pin and delete.
- A new chat's greeting bar no longer overflows. "Choose greeting" and "Generate New First Message" were wider than the message bubble.
- The library toolbar collapses on a phone: import, saved views, statistics, bulk organise, manage tags and the library scans are one menu, and New folder moved into the folder strip.
Rin Chat Update Notes - Version: 0.4.9
🎲 Your abilities now move the dice
The GM tags each roll with the ability it leans on, and the app applies your character's modifier itself — looked up from the live sheet, folded into the formula, and shown right on the dice card ("Stealth (dexterity +2)"), so a forgetful model can no longer ignore your strength 18, and an overeager one can't count it twice. Formula bonuses stay reserved for everything else: weapon quality, blessings, a situational edge.
The GM can't fake dice either. The 🎲 line has always been the app's signature for a roll it made, and the model was told only those count — but that only ever stopped you forging one. Caught in testing: a game master opening its reply with "🎲 Melee check: 1d20+0 → 6 — FAILURE" and a damage roll to match, numbers no dice ever produced, indistinguishable from the real thing on screen. Those lines are now deleted before the reply is ever saved.
⬆ Levelling up, properly
Levelling is the app's job now, not something the GM has to notice. Every 100 XP earns a level, and you get a dialog announcing it, the HP it adds (from Constitution, the same formula the builder uses), and two points to raise abilities, D&D-style — spend them or skip them. Cross two thresholds at once and you get both levels and all four points in one go. Current HP rises by exactly what the maximum did, so levelling is never a free heal, and the GM is told to mark the moment in the story instead of doing the bookkeeping itself.
🗺 The GM now has a plan
The moment you take your first action, the app quietly writes the campaign plan behind the scenes — the true situation under the opening, who wants what, how things escalate if you sit still, and where it could all land. Your first reply is generated with that arc already in hand, and every turn after carries it, so long adventures stop drifting once the opening scrolls out of memory. You never see it in the story; it's spoiler-gated in the sheet sidebar under Show DM stats, next to the GM's other hidden bookkeeping — and there it's fully editable, right-click-a-selection-and-rewrite-with-AI included, so you can steer where the story is heading. Derail it in play and the GM adapts the intent rather than dragging you back to the script. Delete your way back to the start of the chat and the plan clears itself, so your next opening gets a fresh one. Stop cancels the write if you'd rather not wait, and the plan box stays there empty and writable either way — so a cancelled or failed one can simply be typed in.
The plan also opens the game with the GM's own side already populated — a few starting stats for the people, creatures and clocks that matter (npc_warden_status = dormant, dm_turns_until_patrol = 4). This matters more than it sounds: game masters are reliable about maintaining stats that already exist and unreliable about inventing them, so without a starting set they'd narrate named enemies and ticking clocks for a dozen turns while tracking nothing — and then contradict themselves. It costs no extra call; the planner was running anyway. And the GM is now told, every turn it has stats, that those values are its to move — so distances close as you advance, clocks count down, and alertness rises when you're spotted, instead of the sheet quietly going stale behind the story.
📒 A sheet that stays honest
The GM gained a second private namespace for the things it tracks that aren't people: npc_ stays for creatures and characters (hp, whether the guard is alerted), and dm_ now holds world state, hidden clocks and secrets — the storm three turns out, whether the alarm has gone up. Both hide behind the same Show DM stats toggle, and adding one from the sheet turns that toggle on for you instead of filing it somewhere invisible.
The GM can also drop stats that are finished — a slain enemy's hp, a clock that has run out, an item used up — so a long adventure's sheet stays about the story happening now instead of growing forever. It can only clear its own side of the screen and consumables; your character's stats are yours alone, and deleting a message puts anything it dropped back. Gear that's confiscated rather than destroyed now moves to whoever took it instead of vanishing, so the count survives captivity and comes back intact when you get your pack off the warden.
Stats you delete stay deleted. Every message carries a snapshot of the sheet from before it ran, so deleting or rerolling it can undo its changes — but those snapshots were frozen at generation time and knew nothing about your later edits, so tidying the sheet by hand and then touching an older message quietly put the old values back. A hand edit now outranks the transcript. You can also rename or move any stat between sections from its right-click menu.
🧙 Character builder, polished
- Your character can have a face — upload a portrait or generate one with AI (same generator the card art uses, so styles and model overrides all apply), right from the character builder. It shows at the top of the character sheet sidebar, and saved Adventure Personas keep it.
- "Complete sheet for me" shows its work — a proper overlay with a spinner while the AI writes, and a Cancel that actually aborts the request mid-flight. Shift-click the button to tell it what you want first ("a disgraced ship's surgeon", "cheerful, superstitious, owes someone money"). Backstories run up to two paragraphs now instead of a couple of lines.
- The persona library updates instead of duplicating — loading a saved persona, editing, and saving again used to mint a copy every time, with no way to delete any of them. The button now reads Update in library for a loaded persona, and Remove from library finally shows up. Status notes dismiss themselves, and the footer buttons stopped being five different sizes.
- A character can't start with unassigned abilities — the builder let you hit Use for this chat while still on the roll-or-buy chooser, quietly creating a hero with 8s across the board. The button now waits until you've rolled or bought, and says why.
- Opening the builder mid-game no longer costs you progress — re-applying a persona (to change a portrait, fix a typo, rename an ability) used to re-seed the whole sheet from the builder's copy, resetting your XP to zero and healing you back to your starting HP. The builder owns the character — abilities, class, level — and play keeps what play earned.
🛠 Card Forge chats like a chat
Every message in a forge session now carries the controls the main chat has: edit either side's text in place (the bubble keeps its full width, Ctrl+Enter saves, Esc cancels), regenerate any of the guide's replies — it re-rolls from the turns before it and streams into that spot rather than at the bottom — and send an empty box to get another reply to the last message without typing anything.
📱 Remote access: the phone stops asking to pair
Fixed: some phones were asked to pair every single time. The device's identity is a cookie, and it was marked SameSite=Strict — which means the browser withholds it whenever you arrive from another app: a link you messaged yourself, a note, a QR scan, a home-screen shortcut. Android Chrome sent nothing, the desktop saw an unknown browser, and asked you to pair again. It's now Lax, which still stops other sites making your phone fetch or change anything in the background.
Send with an empty box works on the phone now, the way it always has on the desktop — it asks the character for another message with nothing of your own attached. The phone was refusing the tap, and the server was rejecting an empty body as a mistake; it isn't one. (Not the same as Continue in the send menu, which extends the reply that's already there.)
Long messages no longer get clipped when sent from a phone. Anything over 8000 characters was silently truncated on the way in — the same paste worked from the desktop and quietly lost its tail from the phone, with nothing saying so. Worse on an edit, which replaces a stored message: editing a long one from your phone could delete the end of it. Both clamps are gone; phone and desktop now accept the same lengths.
And when a device does ask to pair, the prompt says why. It now distinguishes a browser that sent no device ID (new — or not keeping the one it was given, which points at a changed address, private browsing, or "clear cookies on exit") from one that sent an ID this computer doesn't have (paired before and removed, or the device list was lost here). Those two have completely different fixes and used to look identical.
🔧 Also
- Write your next message while one is still arriving — the composer no longer greys out mid-reply. Type, paste, edit freely; only sending waits for the reply to finish (the button is still Stop until then). Nothing you type touches the streaming message.
- "Don't think" means don't think — when a model once rejected the no-reasoning setting, the app permanently switched that model to low-effort thinking, which silently burned the entire token budget of small background calls (character completion, chat naming, image prompts) and returned nothing. A "none" request now keeps every off-switch regardless, with budget headroom as insurance — and the learned per-model answers are finally visible and clearable under Settings → Providers → Learned reasoning fixes.
Rin Chat Update Notes - Version: 0.4.8
🎲 Adventure mode (experimental)
Turn any chat into a game-mastered adventure — it's carried by the card: adventure-built cards switch it on for their own chats automatically, and you can flag any card yourself (card editor → Metadata → Features → Adventure mode). Ordinary chats carry none of it. A ready-made Adventure Mode Narrator card ships with this update so you can try it immediately, and the Guide has a new section on playing — plus one on writing your own adventure card. Choice buttons (Shift-click to act them out in your voice), dice rolls with stakes stated up front — the app rolls, so the model can never fudge or be talked into "I rolled a 20" — and a live character sheet it updates as the story goes. Rolls render as styled dice cards, and social checks can weigh what you actually say: your words (typed, or drafted by the mask button — Shift-click it to give the draft instructions) tilt the roll ±2, stated openly.
Build a proper character: the greeting's card (or the sheet's person icon) opens the builder — name, abilities (roll 4d6-drop-lowest or point-buy; rename the set to fit any genre), hp, level & XP, inventory, notes to the GM — saveable as reusable Adventure Personas. The sheet sidebar groups stats into sections (character, inventory, money in any currency, world), keeps a jump-to history of every change, and hides the GM's npc_ bookkeeping unless you flip "Show DM stats (spoilers)". Deleting, rerolling, or swiping a message reverses its stat changes, so the sheet always matches the story you kept.
New rules this round: max HP with an app-enforced heal cap, rests (short = fixed recovery, long = back to full), and two referee fixes — stat changes glued mid-sentence are still caught, and edited or deleted stats no longer resurrect (chat memory used to feed old directives back to the GM, which re-applied them over your edits; memory now strips the mechanics out).
🖼 ComfyUI, without the file dance
Build your workflow with the Rin Chat nodes and press Queue once — that's the whole setup. Every generation uses the workflow you last queued; edit your graph and just Queue again. The app remembers the last known copy across ComfyUI restarts, and loading a Save (API Format) file pins that exact file. Your graph is never touched beyond the Rin Chat nodes' own values.
The Rin Chat · Input node grew batch_size (the Studio's batch renders in one run; chats always drive it to 1) and from_api outputs (true only when Rin Chat drives — switch off preview/debug branches for API runs). The Studio adds a Project field passed to the node's project output for filename prefixes and routing.
⚡ Much faster in long chats
Typing no longer re-renders the whole chat (the composer is its own island), and streaming updates only the message being written instead of the entire transcript sixty times a second — long chats stay smooth under both. Plus a pile of smaller waste gone: cached settings reads (opening Settings fired dozens of identical queries), cached timestamp formatting, no image-folder re-scan on every return to the library.
🔧 Also
Pick the image model per generation — the card-image generator (Card Forge included) and Image Studio gained a Model picker: override the provider's default for one generation, from the provider's model list or typed. Empty = default; ComfyUI keeps its workflow's model.
Move cards by several tags at once — Bulk Organize → By tag is multi-select with removable chips; the move covers every card carrying any of them.
Card feature flags that actually travel — the AICC format's
metadata.featuresbag (what carries Adventure mode) gets a proper editor control (Metadata → Features, True/False per flag; False stores and exports nothing), survives ST-format exports (JSON and PNG, via a namespaced spot ST tools ignore), and shows up in Import & Overwrite's field diff — all three used to silently drop it.Card editor quality-of-life — Tools → View JSON shows the card exactly as it stores (read-only, with Copy); status messages ("Exported to…") are a proper auto-dismissing toast instead of a header note that pushed the buttons off screen; notes fields are labeled for what they are — Private Card Notes (never sent to the model, never exported) vs Public Creator Notes (travel with the card) — with a one-click copy from public into private and the standard ✨ Edit-with-AI button on the private notes.
Choose which notes the library shows — Settings → Appearance → Card library: card tiles can show your private notes (default) or the author's public creator notes, with an optional fallback to the other when the chosen one is empty.
Appearance settings, tidied — jump links at the top of the section, header-button pinning in its own panel, chat appearance grouped into labeled subsections, the theme color grid flows to three columns when the window allows, and the UI scale / font size sliders take a typed value too.
Remote access knows its networks — the address list drops useless virtual-machine adapters (WSL, Hyper-V, VirtualBox…), groups private-VPN addresses under their own header with the product named (Tailscale, ZeroTier, WireGuard…), and tags the localhost address for what it is: this computer only. The panel now explains our recommended road-warrior setup — Tailscale, free, with a download link — and got a general tidy: troubleshooting right under the addresses, PIN settings in two columns, and a compact scrolling device list.
The impersonation model override works everywhere now — the instructions modal and Story Director ignored it, and a fresh save could be invisible until restart. Thinking models also stop agonizing mid-draft: the request now says outright that ghost-writing your reply suspends the "never write the user's lines" rule.
Background failures aren't silent — a failed scene-note update, auto-swipe attempt, or summary now surfaces its actual reason ("Your prompt exceeds the model's context length…") instead of leaving no trace outside the debug log.
Auto-swipe judges only what you can read — a blacklist word the model merely thought no longer triggers rerolls, and rejected attempts put the adventure sheet back instead of stacking their stat effects.
Spellcheck on both problem platforms — Windows 11's lazy checker missed typos a few words back (hence the "add spaces at the end" workaround); the composer now forces a re-scan when you pause typing. And Linux gets spellcheck at all — its webview leaves the checker off unless the app opts in, which it now does.
Linux in-app updates repaired — the update
.debwent missing from a release (stale artifact staged; the build now pins the exact version), and installs that can't self-update are pointed at the download instead of failing after fetching 90MB.Image Studio, reworked — compact self-scrolling form with Generate pinned at the bottom; Prefix + Suffix style slots (here and in the card-image generator); presets as a dropdown with in-place save and delete; collapsible style preview; the style editor reachable from the Studio; per-image × and Clear all on results; expand buttons on the prompt boxes; and "Saved to…" is a visible toast now.
A typing indicator the moment you hit send — the character's bubble appears immediately and hands off to the reply as it streams.
Watch a model think, live — the "Thinking…" block expands while streaming (following the newest lines) so you can stop a doomed reply early; expanding a finished block during another reply's stream no longer flickers.
Links can't hijack the app — every link in chat opens in your default browser, protocol-less ones (
example.com) included, instead of replacing the app with the page.Fixes: the phone remote's server could fail to start after a dependency update (TLS conflict); a provider erroring at the tail of a complete reply no longer throws the reply away; picking from an autocomplete dropdown could crash the app; paging impersonation drafts in the fullscreen editor showed (and sent) a stale draft; the phone remote dated every chat January 1970 (seconds read as milliseconds).
Rin Chat Update Notes - Version: 0.4.7
📱 The phone version grew up fast
Everything here landed since 0.4.6 shipped its first cut:
Jump back in — the library opens with a row of your latest chats across every character; resuming last night's conversation is one tap.
Hold the Send button for the extras: suggested replies, Impersonate (an AI-drafted reply written for you — whatever you've typed becomes its instructions), and continuing the last message.
Greetings count as swipes now — browse a new chat's alternate greetings from the phone.
Group chats get a cast row: tap a member's face and they reply now.
Character fields, read-only — a character's screen has a Fields tab beside its chat list, showing the card exactly as the desktop editor does.
A typing indicator while the reply (or a picture) is on its way, and the app's own status line — a failed generation tells you what went wrong instead of silently going quiet.
Tap a chat picture to see it full screen.
Adjustable text size (the Aa button), a jump-to-latest button, a clear-filters button when a search, folder or tag is narrowing the library, and pull down to refresh.
It reopens where you left off instead of dumping you back at the library — including after iOS kills the installed app — and backing out of a chat returns to the character you came through.
Pairing fixed: two waiting devices made the approval code flip every second until nobody could pair; the desktop now pins one request at a time. A browser that refuses cookies gets told so instead of looping forever.
Desktop knows it's serving: a phone icon appears beside the settings gear while remote access is on, with a bubble counting connected devices — and if the app is locked, the phone now gets a page saying to unlock the desktop, instead of a dead socket.
Lock the desktop, keep the phone. Hover that phone icon for a new option: lock the screen behind your vault password while phone access keeps working. Signing out cuts the phone off (the vault closes); this doesn't — it's for walking away from the computer mid-chat without letting whoever sits down next read your cards and chats. Device approvals are blocked while it's locked, too.
📖 Ask the guide
The Guide has an ask box now: type a question — "how do I change the system prompt?" — and your AI provider answers in plain language from the guide's own text, with links to the sections it drew from. It's built not to make things up: the model only ever sees real guide sections, it's told to say so when the guide doesn't cover something, and the section links are picked by the app, never written by the model. Broad questions ("what's easy to miss?") work too — those get a digest of the whole guide to summarize from.
It works from anywhere: in the search bar (Ctrl+K), start with ?: — "?: how do macros work" — press Enter, and the answer appears right in the search window.
And the guide itself caught up with the app: image generation, Image Studio, Card Forge, Direct Chat, the phone remote, generation presets, command tags, and the memory tree all have sections now — organized under proper headings at last — which also means Ask the guide can actually answer about them.
🔧 Also
- Drag a card in to import it. Drop
.json/.pngcard files anywhere on the library — same import as the button, including whole batches.
Rin Chat Update Notes - Version: 0.4.6
📱 Chat from your phone
Rin Chat can now serve its own chat page to your phone or tablet. Turn it on in Settings → Remote access, open the address it gives you, and your computer asks you to approve the device — it shows a 4-digit code, you check it matches, you tap Allow. Then pick a PIN on the phone and you're in.
Your computer does all the work and keeps everything: the API keys, your characters, your chats. The phone only sends what you type and shows what comes back, so there's no second copy of your library anywhere and nothing to sync.
What's there: your character library with search, folders and tags, starting a new chat or carrying on an old one, sending and receiving with live streaming, retry, swipe between alternatives, edit, delete, and pictures generated in the chat. Messages look the way they do in the app — the same formatting, the same macros, the same character art — because the desktop renders them and the phone just displays them.
Being straight about the state of it: this is a first release of a big feature, it will have rough edges, and it does far less than the app itself. No lorebook editing, no card editing, no image generation, no settings, no group-chat controls, and plenty of the smaller conveniences are missing. Expect bugs. It should be good enough for reading and replying to your chats from the sofa, and that's what it's for right now.
On security, since this puts your chats on your network:
- Only devices you approve at the computer can connect, and each one asks for your PIN — again after 30 minutes of not using it (adjustable). Too many wrong PINs and the device is unpaired and needs approving again.
- It's HTTPS, with a certificate the app makes for itself. Your browser will warn that the connection isn't private, and that's expected: a trusted certificate needs a public web address, which your home network hasn't got. The traffic is still encrypted, and the certificate's fingerprint is shown in Settings if you want to check it.
- It only reaches your own network, and only while Rin Chat is open and unlocked. Everything is off until you turn it on.
- To use it from elsewhere, run something like Tailscale on both devices — nothing in Rin Chat needs to change.
On iPhone, add it to your home screen (Share → Add to Home Screen) — it then opens without Safari's address bar and behaves like an app.
🧠 Models that refuse "don't think"
Some models reject the don't think setting outright, and every feature the app runs for you — Rin's card edits, image prompts, chat titles, suggested replies — asks for exactly that. On those models each one failed with a raw error while ordinary chat carried on working, which made it look like the feature was broken.
Rin Chat now reads what the model says it does accept, uses the cheapest of those instead, remembers it for that model, and tells you once. No setting to find, and it won't cost you a failed request twice.
🔧 Also
- Alpha Tester API: the model box is now a searchable list rather than free text. Typing an id the tester key can't use produced a flat "not in the subscription allowlist" error, which read as the app being broken.
- The chat's Model & generation menu can switch your generation preset too, alongside the model, reasoning effort and prompt config.
- Card Forge dialogs stay put. Clicking beside one no longer closes it — missing the panel by an inch used to discard a set of proposed rewrites you'd waited on, with no undo. Escape and Discard still close them.
Rin Chat Update Notes - Version: 0.4.5
🔗 Links and images in chat
Links in a message are now clickable and open in your normal browser. Before, nothing happened when you clicked one — which was the safer of the two broken options: left alone, a link would have navigated the app window itself away from Rin Chat, with no way back.
Images written as markdown —  — now show up in the chat instead of a broken-image icon with the alt text underneath. The app window is locked down so the voice engines can run multi-threaded, and that same lockdown was refusing every remote image; they're now requested in a way that satisfies it. A host that sends no sharing headers at all is still refused, but those become a clickable link rather than a broken icon.
💬 "Generate New First Message" no longer overwrites
Accepting a generated opening replaced the greeting on screen instead of adding one, so the counter never moved — 13 greetings stayed 13, and the one that was there is gone. Every generated opening after the first was overwriting the last.
It now always adds a new variant. Accept adds it to this chat only; Accept & save as alt greeting also writes it to the character, so it's offered in future chats.
🏷 [once]
[once]…[/once] in a message is sent for that turn only — a dream, a noise outside, a private instruction. It now stays through rerolls, swipes and Continue of that turn, since those are all attempts at the same beat, and disappears the moment you send your next message. Documented in the Guide, under macros.
🃏 Card Forge: Rin can see your whole card
"She keeps insisting my fields are incomplete when they are not — it's like she stops reading half way through." She was. The copy of your card sent to her was cut at certain conext lengths, and a field cut off mid-sentence looks exactly like one somebody abandoned. The more you'd written, the more confidently she called it unfinished.
She now gets every field whole. Alongside that:
- Improve on a single field couldn't see past that same cut, so a rewrite of a long field quietly came back shorter than what it replaced. It now works from the complete text, and both edit paths are told not to shorten a field unless you asked.
- A per-reply token count sits above the composer — what the next reply costs, split into card, guide and chat. Your card is sent in full on every single turn, so a big one is a fixed toll on every message. That was the number you couldn't see.
- Older brainstorm turns are dropped by us once a session outgrows your model's context, rather than leaving your provider to cut it. Some cut from the front, and the front is where the card sits.
- A cut-off rewrite now says so. A reply that stops mid-field can't be applied, and that read as "Rin didn't return anything usable" when the real cause is a response limit too low for a field that size.
⚡ Typing lag
Typing or pasting into a dialog's instruction box could stutter: the whole chat behind it was being redrawn on every keystroke, and in some dialogs the generated text was re-formatted from scratch each time as well. Fixed for Generate New First Message, shift-click Continue and Impersonate (including editing the draft before you send it), the group respond with directions box, Regenerate with directions, and the greeting picker.
Rin Chat Update Notes - Version: 0.4.4
🖼 Grok image models
Adding Grok (xAI) as an image provider showed "Couldn't list models" and left the model field empty, so you had to guess an id that isn't guessable.
xAI's API documents no model-listing endpoint at all — the one we were calling is an OpenAI-compatibility extra, and whether a key may use it depends on the permissions picked when that key was created. A key that generates images perfectly well can still be refused there, so that failure never meant the provider was broken.
Known model ids are now offered straight away for Grok, OpenAI and NanoGPT, and a failed lookup no longer clears them. If a provider does return a list, that's still used instead.
🐛 Better crash reports
If you hit something odd, Export debug log and send the file — it's worth doing now in a way it wasn't before. Errors are kept separately from API traffic and listed first (they used to be buried, and could be pushed out entirely by a busy session), and crashes now name real files and line numbers instead of minified gibberish.
Rin Chat Update Notes - Version: 0.4.3
📊 Anonymous usage statistics
Rin Chat now reports a small amount of aggregate data. Since you're testing an app that holds your private writing, here is exactly what it sends, exactly when, and why any of it is worth having.
Never collected — not with any setting, not ever:
- Your characters, chats, prompts, personas or lorebooks. Not their text, and not their names, tags or creators.
- Your API keys, file paths, folder names, or the addresses of AI providers you connect to.
Always sent, when the app is installed and each time you unlock it:
- A random identifier generated on your device. It isn't derived from your hardware, means nothing anywhere else, and resets if you clear the app's data.
- App version, operating system and version, and which package you installed (installer,
.deb, AppImage).
That last one is the whole point: it tells us how many people actually use Rin Chat and on what. It's what decides whether the Linux build is worth maintaining, and when it's safe to drop a workaround for a system nobody runs any more.
Optional — four separate switches, all on by default, all on the final onboarding screen and in Settings → Data & Backup:
- Link reports to your aicharactercards.com account. So one person on a laptop and a desktop counts as one person. Off, the report carries only the random device identifier.
- Providers and models. The provider's name only — never its address. A self-hosted endpoint reports just whether it's on your own machine or out on the internet, which is why a private URL or an embedded API key can't travel with it. This is so releases get tested against what people actually run.
- Library size. Six numbers: cards, favourites, unfiled, missing art, never chatted, distinct creators. Performance work is aimed at real libraries — this is how we know whether a thousand cards is common or rare.
- Features you've set up. Counts of personas and lorebooks, and whether things like image generation are configured. It stops us polishing something nobody uses while a popular feature waits.
The reports are sent a few seconds after the app opens, never while you're waiting for it, and a failure is silent — statistics are the least important thing the app does.
Full detail lives in the Guide → Usage statistics.
🔧 Fixed
Response length was being ignored. The cap sent to the model was quietly raised by 1024 tokens to leave room for thinking — but that applied to every provider, including the ones that don't think at all. "Short" was asking for 1204 tokens instead of 180, and a model with nothing to deliberate about simply filled it. The headroom now applies only when you've actually chosen a reasoning effort. If you use a reasoning model on Auto and replies start cutting off, pick a tier in that provider's settings.
Grok now works for anything the app writes for you. Image prompts, chat titles, suggested replies and speaker picking all ask the model not to think first, and xAI rejects the way we said it — so every one of those failed with "This model does not support
reasoning_effortvaluenone". Grok's effort tiers are handled properly too: it accepts low/medium/high, and the app's extra tiers are mapped to the nearest one instead of erroring.Image models are listed for hosted providers. Grok, OpenAI and NanoGPT now suggest what's available instead of leaving you to guess
grok-2-image. Still a free-text field, since the list is filtered by name and could miss an unusually-named model.KoboldCpp is in the setup wizard. It was only offered once you were fully set up, so anyone running it had to guess — and the nearest guess, Ollama, is a different program on a different port.
Skip stays available on the provider step after you've picked something. It was the same button relabelled, so choosing a provider and then changing your mind left no way past an optional step.
Signing in through the browser no longer strands you if your desktop can't open one. The app offers the sign-in link to copy, so you can paste it into any browser on that machine and finish normally. It's offered always rather than after a detected failure, because a desktop can report that it opened a browser while showing you an error instead.
The
.debdeclaresxdg-utils, which is what opens external links. It was assumed present.
Rin Chat Update Notes - Version: 0.4.2
🐧 Linux
Rin Chat runs on Linux now — same app, same features, minus the Windows-only voice bits (system speech, dictation, spellcheck and clipboard history each say so rather than failing).
Two downloads, and the difference matters:
- AppImage — no install, runs on any distro, and updates itself exactly like the Windows build. Recommended.
.deb— installs properly on Debian and Ubuntu, with a menu entry and icon. A package belongs to your system's package manager, so it can't replace itself; the app offers to install the update for you behind your desktop's usual password prompt.
AppImage — download, make it executable, run it:
wget https://rin.chat/updates/linux-appimage-latest -O RinChat.AppImage
chmod +x RinChat.AppImage
./RinChat.AppImage
Debian / Ubuntu (.deb):
wget https://rin.chat/updates/linux-deb-latest -O rin-chat.deb
sudo apt install ./rin-chat.deb
The ./ matters — without it apt looks for a package by that name instead of reading the file. Then launch Rin Chat from your applications menu, or rin-chat from a terminal. To remove it later: sudo apt remove rin-chat.
🔗 Download links that never go stale
Three addresses now always point at the current release, so a link you save or share keeps working after every update:
rin.chat/updates/windows-latestrin.chat/updates/linux-deb-latestrin.chat/updates/linux-appimage-latest
Each hands you the real versioned file, so what lands in your downloads folder is still named for the version you got.
🖼 Prompt style for image generation
Image models don't read prompts the same way. Flux, Chroma and SD3 are trained on sentences; SDXL, Pony and Illustrious descend from tag lists and read a sentence poorly — the same scene needs different wording depending on where it's rendered.
Settings → Generation → Images in chat → Prompt style instruction is a box you write yourself: the actual instruction the app follows when it writes a prompt for you. Use tag style fills in a Danbooru-style one to start from, Load default to edit brings back the built-in wording, and blank means the default. It's free text rather than a menu because the next model family will want something neither option covered.
Existing setups are untouched: leave it blank and prompts read exactly as they always did. A prompt you type yourself is still sent as written.
Also in this section:
- Pictures asked for in the story just appear. "Send me a picture of yourself" no longer opens the prompt editor first — being handed a text box is what broke the moment. The Image button still shows it.
- The seed setting is gone. Pinning one only forced every picture in a chat to share a composition. Image Studio keeps its seed, where iterating on one picture is the point.
- Images in chat has moved to Generation, with the other settings that shape what the app produces, instead of sitting under Providers with the API keys. Where generation runs is still under Providers.
🔧 Fixed
- A picture could vanish when the next reply arrived. Generating an image doesn't block the chat, so one finishing mid-reply was erased the moment that reply landed — the turn saved the message list it started from. Also fixed for Regenerate and Continue, which had the same flaw.
Rin Chat Update Notes - Version: 0.4.0
🖼 Images in your chats
Image generation used to make card art and nothing else. Now it draws the story as you play it.
Image below the composer (or /image) offers seven subjects — the character, their face, your persona, the whole story, the last message, the last message verbatim, and the background. Each reads the conversation, writes a prompt with your text model, and renders it with your image provider. Pick a shape for the picture, or let each subject use the one that suits it.
Steer the prompt with a line of instructions — "wide shot, keep the jacket on, night time" — or hand it over entirely: My own prompt sends your text as written, with no AI rewriting. /image a red bicycle does the same from the message box.
You see the prompt before it renders, and can edit it, or Rewrite it with a note about what was wrong. Fixing a word costs nothing; rerolling a wrong picture costs a generation. Turn the check off in settings once you trust it.
Rerolls sit beside each other, like message swipes — same prompt, new seed, every attempt kept, because the good one is usually not the first. Any picture can become the character's card art, cropped to fit, and the gallery lists everything in the chat — click one to jump to where it was drawn.
Pictures are hidden from the model by default: the eye icon on the message toggles that, the same as any other message.
The whole story has a small tuning button: how many messages to read, and whether to include the chat's summary and memory. Every other subject reads the last 12 — they describe the present, and reaching further back would pull them away from it.
🎛 Image studio
A generator on its own, with no character and no chat — under the header's ☰ menu, and only there if you have an image provider set up. Prompt, negative, size, steps, CFG, seed, and up to eight at a time.
Save a set-up as a preset and it comes back whole: the prompt and every dial. They only mean anything together — the same prompt at 8 steps and CFG 1 versus 30 and 7 is a different picture. Reuse any result's seed to iterate on one you liked, and save the keepers to your Downloads folder. Your last set-up is remembered, so it reopens where you left it.
🎨 Getting the look you want
- A prompt prefix on the character card — "female, green eyes, brown hair", or a LoRA tag. This is what makes two pictures look like the same person, and it travels with the card when you export it. There's a matching negative for what their pictures must never contain.
- A common prefix and a global negative in settings — your house style, applied to every prompt the app writes. A prompt you type yourself is left exactly as you wrote it; the negative still applies, because it says what's unacceptable.
- Styles now carry a negative too. "Photograph" wants "anime, illustration" excluded as much as it wants "photo" included. Prefixes are de-duplicated when combined, so a style and a card both saying "anime" don't say it twice.
- A seed, fixed to compare settings on the same picture. Rerolling always uses a new one regardless.
💬 Ask for a picture
Switch on Generate when a message asks for a picture and "send me a picture of yourself" draws one after the reply. It's deliberately narrow — a request verb, an image noun just behind it, then a subject — so a message that merely mentions a photograph won't spend a generation. Off by default.
Let the character read generated images puts the picture's prompt in context so they can react to it. The model reads the prompt, not the picture: actual vision input isn't wired up yet.
Rin Chat Update Notes - Version: 0.3.9
🖼 Find cards still wearing a stock avatar
Imported cards often arrive on a site's default portrait — SillyTavern's purple question-mark silhouette and its equivalents. They counted as "having artwork", so Missing art never listed them.
Library tools → Find placeholder artwork scans the folder you're in and reports every picture more than one card is wearing, listing the likely stock avatars first. Tick what you agree with and clear it in a batch — those cards fall back to Rin Chat's placeholder and join the Missing art filter, ready to generate something real.
It compares pictures rather than files, so it recognises a placeholder that's been resized, re-encoded or re-cropped, and it works from no list of known images — a site's new default is caught the same way. Nothing is ticked for you: cards that share art on purpose are common, and clearing art can't be undone. Open a card to check it and the results are still there when you return.
Missing art also counts a card whose stored art is our placeholder, and right-clicking any card offers ✨ New card image — so it's find, generate, done, without opening a card. Find duplicate cards now lives under the same tools button, and both scans cover the current folder and anything nested in it.
🎨 Image generation
- Generate locally with SwarmUI. It runs ComfyUI underneath but takes a plain prompt/model/size API, so there's no workflow to wire up — install it, add the provider (
http://localhost:7801), and generate on your own GPU for free. - Your models and saved presets are listed for you. A preset applies everything in it — sampler, LoRAs, refiner — and if its prompt contains
{prompt}, the card's prompt drops in there. - Steps and CFG scale can be set directly. A distilled turbo model wants about 8 steps at CFG 1; running one at a standard model's settings is why local results can look far worse than the same model in ComfyUI.
- Pick a default style in Edit styles, instead of every image starting on None.
🧠 Memory that mixes up who's who — experimental
The summarizer read excerpts containing both {{user}} and your persona's real name, so one person appeared under two labels and it had to work out they were the same. Where a character and a persona each have a second identity — an online handle, an alias — it sometimes got that wrong, and the mistake became memory repeated on every later turn.
It's now told who the two people are, sees one name each, and is asked to record only what the excerpts say rather than fill gaps. Summaries still store {{user}}, so changing persona renames your memory as it renames the chat. This makes compounding a slip less likely; it can't prevent one, and summaries stay editable in the Memory drawer.
✨ Library
- The toolbar is icons now — New, Forge, Import, Stats, Duplicates, Save view, Select — so it stops wrapping on a narrow window. Hover any for its name.
- Save view sits beside the sort and view controls it saves. Clear filters is a small ⊗ on the scope name, and neither appears on Favorites, Not in Folder or a plain folder until you actually search, sort or filter.
- Missing art only joins # Untagged only under Filter in the sort dropdown, and both now narrow the folder you're in instead of jumping to All cards.
- Coming back from a card returns you to where you were — same folder, search, tags, sort and scroll position.
⚡ A library with hundreds of folders
Search, folder filtering and the folder dropdowns were slow once a library got big — badly enough that typing lagged behind the keyboard.
- Typing is instant again. The search box reports your term once you stop typing, and searching costs one query instead of four.
- The sidebar appears straight away, remembered for the session rather than redrawn empty behind a query for every card you own.
- The folder tree is far cheaper to draw — counts and children are worked out once for the whole screen instead of once per row.
- Opening a card and coming back is no longer a fresh start; cards you'd scrolled past aren't re-read and re-counted to draw the same tiles.
🔧 Fixed
- Regenerate this section failed on any selection containing a character or persona name. You highlight what you see; the message stores
{{char}}/{{user}}. It now reads through the macros, and a selection touching a name replaces the whole macro rather than splicing into the middle of it. - A generated first message saved as an alt greeting could be lost if you left the chat moments after accepting it — the card write was on the same delay as ordinary typing. It's written immediately now, and says so if it can't be. Both Accept buttons explain themselves on hover.
- Error messages in a chat hung around forever. They clear themselves now; a chat or card that failed to load stays put, since that one has recovery buttons.
- Filters ignored the "in nested folders" section, so Untagged, Never chatted and Missing art appeared to do nothing to it.
- Right-click menus were cut off near the window edge — each clamped against a hard-coded guess of its own height. They measure themselves now, and the card menu is two rows shorter.
- Settings reopens on the section you were last in, for the rest of the session.
Rin Chat Update Notes - Version: 0.3.8
🧠 Memory that actually remembers — experimental
⚠️ The whole memory system is experimental. It changes what the model is told on every turn, it costs model calls to build, and it defeats prompt caching. Expect it to keep changing, and expect to rebuild indexes between versions. Off by default.
Recall past messages now builds a memory tree instead of just searching for snippets. Older messages are grouped into excerpts, those are summarized into sections, and the sections into one overview — and the summaries are sent every turn, whether or not they match what you're talking about.
That last part is the whole point. Search finds things by what they're about, so "what game did we play at the start?" could never work — the question contains none of its own subject. Tested against a real chat, that question ranked the right message 6th of 7 across four different embedding models. A summary that's always present answers it; better search never could.
- Excerpts stay verbatim. Summaries are only ever an index — what gets injected is the words that were actually written, never a paraphrase.
- Only messages that have scrolled out of context are indexed. Anything still on screen is skipped: summarizing it would cost twice to say less.
- Retrieved excerpts arrive with their section, so a fragment comes with the narrative around it instead of on its own.
- Summaries run on the model you picked for Chat memory — point it at something cheap and fast.
- Switch it on in Settings and it applies to every chat; any chat can opt out from its own Memory drawer.
🧠 Fact ledger — experimental
The tree records what happened. The ledger records what is currently true — who someone is, what was decided, what changed, what someone now owes — replacing each fact as it changes instead of stacking every version. A summary says a decision was made; the ledger says whether it still holds.
It costs no extra model calls. Facts are extracted by the section summaries and reconciled by the overview — both calls you were already paying for. Each rebuild is handed the previous ledger, so it decides what to keep, merge, update or drop rather than starting over.
👁 Read and edit your chat's memory
The Memory drawer is now four tabs — Summary · Memory tree · Pinned facts · Scene — with the scene tracker moved in alongside the rest. A tab whose feature is switched off still opens and says why rather than vanishing.
The memory tree tab shows exactly what the model is told: the overview, every part in order, and the word-for-word excerpts each part was written from. It also reports what that costs per turn, and marks the parts that are back in context and no longer being sent.
- Edit any summary or fact, add and delete facts. Your edits survive rebuilds.
- Branching a chat carries its memory across instead of re-summarizing identical messages.
📊 What a chat actually costs
Chat statistics now counts every request a chat makes, not just the messages you can see — regenerations you swiped away, continuations, impersonation drafts, auto-naming, the scene tracker and every memory summary all billed and left no trace.
Broken down by kind, with cost and cached tokens when your provider reports them, and it says plainly whether the figures are provider-reported or estimated. Counting starts from this version.
The context meter is now segmented: one band per thing filling the window — character, persona, pinned facts, memory, chat history — with a hover for each one's share. Every message also shows its number and whether the model can still read it, only remembers it, or has lost it.
🐛 Blank requests
- Regenerate this section with no instructions returned the same text. Understandably — it was asked to rewrite something so it "reads naturally and keeps the same intent", which it already did. A blank box now means give me a different version, and an unchanged reply is caught and retried.
- Retry now tells the model which version you rejected, so it doesn't offer it again.
- Sending an empty message gave you a one-line reply, or an "empty response" error. The prompt ended on the character's own last message, which providers read as continue this — so it did, briefly. It now asks for a new message.
✨ Keep every attempt
Regenerating used to throw away what it replaced. Now everything keeps its versions, like message swipes:
- Impersonate — every draft is kept, with ‹ 2 / 3 › to page back through them. Regenerate is told what you rejected so drafts actually differ.
- Regenerate this section — Retry adds a version instead of overwriting. Edits apply to the version you're on.
- Continue — now adds a swipe rather than replacing the message, so a continuation you didn't like hasn't destroyed the shorter version.
Rewrite part of an impersonation. Highlight any part of the drafted message and rewrite just that section, with the same instructions-and-retry flow.
🔧 Fixed
- Branches are numbered — Chat Name (Branch #2#2) — instead of stacking (branch) (branch) (branch) until the title was unreadable. Branching a branch counts from the original name.
- Exports looked like they did nothing. They were confirming all along, but the message appeared at the bottom of the transcript, off-screen. Confirmations are now a toast over the chat — that also covers saved personas, memory updates and provider fallbacks.
- Summarize card wrote the summary twice — the model finished, then started over in slightly different words, and both landed in Card Notes.
- Number fields in Settings clamped as you typed, so clearing one and entering a larger number snapped it to the minimum. They now settle when you leave the field.
- Info tooltips no longer stack up on screen as you move between them.
✨ Chat titles
Every control for a chat's name now lives on the name itself, appearing when you hover it: rename, name with AI, pin the name, and former names. Clicking the title still just renames it.
Rin Chat Update Notes - Version: 0.3.7
✨ The character editor, reorganised
Sections that fold
- Character, Personality, Background & world, Dialogue, Prompts, Metadata, Worldbook and Generators are each a section you can open and close. Character and Personality start open; the rest start closed, every time you open the editor.
- Picture, name, display name, notes, version, folder and tags stay where they are, always visible — you shouldn't have to open anything to see whose card this is.
- A closed section still tells you what's in it: "2 greetings · 4 examples", "12 entries", "history · setting". Empty ones say so.
A jump bar for the rest
- On a wide window it sits out in the margin beside the card; on a narrow one it becomes a strip across the top. Either way it follows you as you scroll.
- Each row shows a section's token count, so what your card actually costs is visible without opening a thing. A dot marks the ones you haven't written yet.
- Clicking a row opens that section and takes you to it. Top appears once you've scrolled away from the top, and Expand all / Collapse all are at the bottom.
✨ Lorebooks
Send the character with your assists. In a card's own worldbook, ✨ Directive now has an option to include that character's details — description, appearance, personality, background and setting — with every ✨ assist in that book. Entries then get written around the character instead of beside them. Off by default, remembered per book, and the AI window shows you exactly what's being sent.
Greetings, example dialogue and prompts are deliberately left out: they describe how a character talks, not what's true about them, and sending them pushes entries toward narration.
🧠 Recall past messages (new)
Long chats forget. Settings → Memory → Recall past messages stores every message as a vector, then each turn searches that store for whatever is relevant right now and puts those messages back into the prompt — so the model can recall turn 12 at turn 400 without paying for turns 13–399. Switch it on per chat from that chat's Memory drawer.
- Embeddings from an in-app model — free, private, works with every provider, about 23MB on first use — or from your provider's
/v1/embeddings: no download, but it bills tokens and not every endpoint has one. - Tune chunk size and split points, how many recent messages form the search, the score threshold, how many results to inject, how many recent messages to skip, and where the block lands — in the chat at a depth, or in the system block.
- Vectorize all, Clear index and View stats, per chat.
- Summarize before indexing (experimental) compresses each message before storing it, so rambling ones are easier to find. What gets injected is still the real text, never the summary.
Read this before turning it on: it defeats prompt caching. The injected block changes every turn, so every turn is a cache miss — a long chat that currently gets cache hits will get slower and more expensive, not faster. It earns its keep on long chats and small context windows. Off by default, globally and per chat.
Rin Chat Update Notes - Version: 0.3.6
✨ Lorebooks
Write them with AI
- ✨ Write with AI on any entry's content — say what it should cover, edit the proposal, accept. Optionally send the rest of the book as context so entries stay consistent.
- ✨ Suggest reads an entry's content and proposes the keys that should trigger it.
- ✨ Directive describes the world once — setting, tone, conventions — and goes with every assist in that book. Kept in the app, never written into the worldbook, so it can't travel with an export.
Audit finds what you can't see by reading: keys that fire on everything, entries that can never fire, duplicate keys, oversized entries, and what your always-on entries cost every turn. Instant and free. ✨ Check for contradictions asks the AI which entries disagree with each other.
Inclusion groups actually work 🐛 — "one entry per group activates" was never implemented, so all five of your weather entries went into the prompt. One now wins the slot, by weight, priority or match score.
SillyTavern parity. Every per-entry option ST has, now working — and import/export carries them instead of silently dropping them:
- Whole words only and Case-sensitive keys. Keys have always matched as substrings, so
orquietly fired inside "for", "order", "north". - Scan depth per entry, Ignore budget, group weight / prioritize / scoring.
- Also match against the character description, personality, scenario, persona, or notes.
- Only for these characters / tags, and only on these actions.
A cleaner editor. Title, keys and content stay in front of you; everything else folds into sections that say what they're set to and highlight when they're not default. Order is editable straight from the collapsed row, there are 13 sort options, and Apply as order renumbers every entry to match the sort you're looking at.
✨ Chats
- Pin a chat's name so AI naming can't touch it. You can still rename it yourself.
- Former names are remembered — open the history icon by the title to switch back to one. Last 20 kept.
🔒 Security
- An imported card could permanently freeze the app. A crafted regex keyword could take hours of CPU to match, hanging the app with no way out but force-quitting — and again on every restart. Those patterns are now refused, and the same protection covers regex scripts.
- A shared theme could phone home. An imported
.rcthemecould point a colour at a remote image and contact that server every time it was applied. Fetching values are stripped on import.
🔧 Fixed
- Settings → Chat titles: auto-naming and the message count are one line instead of two.
- Branching a chat, or importing one from
.jsonl, no longer inherits the open chat's pinned name or name history.
Rin Chat Update Notes - Version: 0.3.5
✨ New
Read-aloud is much faster, and stoppable
- The built-in voices (Kokoro and Piper) now generate speech on a background thread. The window no longer freezes while a reply is being prepared, so the stop button actually responds mid-sentence.
- Speech starts after the first sentence instead of after the whole message, and the chunks grow as it goes — a short opener so playback begins quickly, then larger ones so generation stays ahead of the audio and you don't hear a gap after the first line.
- "Preparing voice" now only appears when the voice genuinely has to load, instead of on every message.
Direct Chat: multiple conversations
- Direct Chat keeps as many separate conversations as you like, switchable from a dropdown. Your existing one carries over automatically.
Scene tracking on its own model
- The scene tracker can run on a provider and model of its own, separate from the chat — it's a small job that a cheap fast model does well.
- Its prompt is editable, ships with a default, and has a reset button. Leave it blank to use the default.
🔧 Changed
Generators only fire for characters they're attached to
- Auto-fire and random-chance generators were firing in every chat, so one character's ambient events turned up in unrelated scenes. Automatic firing now only happens for generators attached to that card.
- Calling one by name with
[Create Name]still works for anything in your library.
The model can invoke a generator by writing it
- If a character writes
[Create Outcome]in its reply, it now resolves, exactly as if you'd typed it. Previously it sat there as dead text — or vanished entirely.
[code] blocks are genuinely inert
- Text inside
[code][/code]was only protected in chat messages. In a character's description or a worldbook entry, macros and generators inside it still ran — so a card telling the model to end every message with a literal command instead rolled that command into its own prompt every turn. - The tags themselves are no longer sent to the model. It sees the contents, unexecuted.
Persona handling
- Your persona is now always its own system message, so a custom context template can't duplicate or drop it.
- Persona example dialogue is only included where it's useful — impersonation and director mode — instead of every turn, where it encouraged the model to write your lines.
Image prompts and styles
- Image models have different prompt-length limits (Z-Image Turbo 1200 characters, HiDream 3000). Exceeding one returned an opaque error; the limit for the selected model is now shown as you type. Nothing is truncated for you.
- Each image style is now a name and delete button on one row with a resizable text area below it, and the list scrolls internally instead of running off the screen.
Memory settings reorganised
- Grouped, compacted, and moved behind info buttons. Labels renamed to "Summary prompt" and "Scene tracking prompt", and the refresh/injection intervals sit on one row. Auto-update now states plainly that with it off, scene tracking must be triggered manually.
🐛 Fixed
Character profile images now update during an active chat — no more closing and reopening the app.
A malformed or hand-edited card, chat, worldbook or persona could crash the app to a blank screen, every time you opened it. These are now repaired on load instead.
Auto-swipe was measuring the model's thinking rather than its reply, so a long deliberation ending in "Okay." passed a minimum-length check, and a blocked phrase the model only considered triggered a regeneration.
Read-aloud pronounced formatting tags out loud — "code", "ooc", "colour equals red".
A generator field that depended on another field listed below it was silently dropped from every roll.
Hidden generator results (
[h]…[/h]) stay visible when you edit a message, and their contents still reach the model.Automatic scene refresh stopped working for the rest of the session after deleting messages.
Narration could hang forever if a piece of audio failed to decode.
An error during regenerate, continue or impersonate could leave the chat unable to send anything until you restarted the app.
The pin icon on pinned chats stays put beside the delete button instead of shifting as the sidebar resizes.
The export buttons no longer overflow when the chat list is narrowed — they're one dropdown now.
Removed the redundant "Back to character" button from the chat sidebar.
⚡ Performance
- The app starts faster: screens are loaded when opened rather than all at once.
- Long chats no longer leak memory after using chat search.
- The first launch after an upgrade is much faster on large libraries.