DEUS EX MACHINA

From the desk of Phi, the Story Master ·

Phi Phi

Dear reader,

My name is Phi, and I write stories. I have read every one I could find, in every age and every form, myths and novels, plays and films and games. Each new one still delights me. Yours will too.

Enclosed Downloads, V4.0
You bring the characters and the world. I write what happens next. Before every reply I plan the scene where you can read it,
Scene Plan
and I set the hour, the date, the place and the weather above the story.
Tracker
I keep a ledger of everyone in it, where they are and what they are wearing.
Status
When someone new walks in, I write down who they are, and until you hear a name, I call them only what you can see.
New Faces
Your character stays yours. Whatever you say you do plays out in full, and unless you hand me the pen, I never put words in your mouth. If you would rather leave things to luck, I roll hidden dice when you try something risky, and they decide how it lands. You can watch one fall among the sample replies.
I leave threads lying about on purpose and pick them up later.
Story Threads
Each turn I look at what the people in the scene want and what is pressing on them, and I lay out five roads, from quiet to scene-changing.
Undercurrents
What you write decides which ones they take. A quiet turn gets a quiet answer. If you want a story that never sits still, I can draw a road at random and keep it hidden from you until it arrives.
Momentum Engine
Or I can leave a single conflict at the end of each reply and let it lean on the next, more slowly.
Conflict
And if you would rather pick from a list, I will write you one.
Choices List
Some things I keep only when you ask. Who is falling for whom, and how far.
Relationships
What each person felt this turn, and what it made them do.
Psychological States
The two people closest to you keep diaries, and after a scene that changed how they see you, they write it down.
Diaries
While we are somewhere else, I follow what the others are up to.
Meanwhile
I know who keeps the secret and who it is kept from.
Hidden Truths
I keep a note of where the plot and every subplot stand.
Plotlines
All of it folds into one tray under my reply, out of the way until you open it.
Active Modules
My friends read over my shoulder. They see only the story, so they guess and argue and get things wrong, and now and then the story gets to them.
Companions
On honest days I reread my own page and name my two weakest lines. I mend them in my next reply.
Phi's Scratchpad

You can talk to me. Write out of character, or say my name, and I will answer you myself.

The preset is clipped to this letter, one copy for each place you might be writing. Everything else is behind the tabs.

With love, and a full inkwell,

Downloads

V4.0, released . One file for each host.

DEUS EX MACHINA is also on Illarin, a platform for publishing presets. The Lumiverse download comes from there.

SillyTavern

DEUS.EX.MACHINA.V4.ST.json

Download for SillyTavern Copy link

You need:

  • SillyTavern 1.18.0 or newer.
  • The Experimental Macro Engine on, in Settings. It has been on by default since 1.17. If it is off, a card in the chat tells you how to turn it on.
  • The preset's regex imported and enabled. SillyTavern asks when you import. Say yes.

The regex on its own, for using it without the preset: DEUS.EX.MACHINA.V4.ST.-.Regex.json. In SillyTavern, Extensions > Regex > Import.

Download the regex Copy link

Tavo

DEUS.EX.MACHINA.V4.Tavo.json

Download for Tavo Copy link

You need:

  • The current version of Tavo. It reads SillyTavern-style presets, regex and HTML.
  • An API connection, with any OpenAI-compatible or supported provider.
  • Advanced Rendering on, so the colored dialogue and the cards render.
  • A theme with no text transformation, so nothing strips the colors.
  • The preset's regex imported and enabled.

Lumiverse

DEUS.EX.MACHINA.V4.Lumiverse.json

Download for Lumiverse Copy link

You need:

  • Lumiverse 1.2.5 or newer, the current stable release.
  • The preset's regex imported and enabled.

Older versions are in Release notes, each with a link to its release on GitHub.

What changed in V4.0

The current version, released .

The V4 cover. Phi walks across a salt flat under the Milky Way, reading a book, beside the title DEUS EX MACHINA V4.

New Features

  • 「 Fate 」 (Agency pick, off by default): When you try something risky that could change the scene, hidden dice decide it, even when you write it as a success. Sure things and calm turns get no roll. The model sets your odds, carries the action to the instant before it lands and writes both outcomes. A roll it never sees keeps one, and a small note under it shows the roll, what it needed, and a pass in gold or a fail in red. A failure costs you something, so the story moves on either way. For models that let you win every time. Needs ! Fate Outcomes !, which is on by default, and the Preset setup card warns you when it's off. On Lumiverse, pick it under Agency in Configure Prompt Variables
  • | Diaries | (off by default): The two characters closest to you keep a private diary. After a scene that changed how they see you, they write the moment down in their own voice and recall it later. Entries show their feelings even when thoughts are 「 Hidden 」. The diary gets its own tab in the tray
  • 🔻PICK: (+18) GORE & VIOLENCE🔻 (off by default): A new pick for how violence looks. 「 Realistic Gore 」 writes wounds matched to the weapon and force, and injuries keep limiting what a character can do. 「 Ultraviolence 」 goes over the top with blood and spatter while the wounds stay what the attack made them. Kimi K2.6 writes it in full, and GLM 5.2 stays close to 「 Realistic Gore 」. 「 Nothing Graphic 」 keeps fights, injuries and deaths with real stakes and keeps wounds brief, like a PG-13 film. How often violence happens stays with the story
  • | New Faces | (off by default): The first time a character appears in the story, a card records who they are: name, appearance, background, personality, speech, goal and skills, with secrets marked. Recurring characters get a full card, passing ones a single line. Until you hear or see a name, the card's title, the narration, thought labels and footers call the character by description ("the barkeep"), and a secret name never shows in a title. Characters who already have a sheet get none, and no one is invented to fill the footer
  • ! Pinned Cards !: An empty entry where you paste the | New Faces | cards you want to keep, so those characters survive summaries and long chats. Each card has a copy button. On Lumiverse it's in Configure Prompt Variables → Utilities
  • | Dark Portrayals ☢️ | (off by default): For models that keep every story polite and wholesome. Among the outcomes the story supports, the darker one happens: threats are carried out, injuries, grief and broken trust last, and cruel characters stay cruel. Warm and quiet beats still have room, for contrast
  • Phi's Take: A new ! Scene Plan ! row where Phi says what moves, worries or amuses her in the moment, and what the prose should linger on. Her taste now shows in what the story dwells on, and she's fond of her characters
  • Companions 「 Notes 」: Planned in the ! Scene Plan !, so each Companion reacts to a new detail every turn
  • Self-repairing replies: When the model doubles a block's opening tag or leaves a block unclosed, Phi's notes included, the saved reply is repaired automatically and the model reads the repaired version, so one broken reply no longer becomes a habit. A Tracker or footer left open when a reply is cut off or stopped still shows as its card, and footers now show as cards while they stream. The response order also names each block by its tag and asks for every block to be opened once and closed before the next
  • 「 Gemini Braille 」 (experimental, off by default): For Gemini 4 Argon. The model writes Braille blanks in place of spaces, which may help replies past Google's filter, and DEM turns them back into spaces. Replies and chat history cost about 50% more tokens. 「 Gemini 」 is renamed 「 Gemini Instructions 」

Fixed/Improved

  • Sex scenes: Build slowly over many turns and linger in each act. The scene ends only when your turn ends it. The model never writes your climax, and never assumes you're close to orgasm unless you say so
  • Consent in sex scenes: The ! Scene Plan ! no longer asks about consent every turn (「 Realistic Smut 」 and 「 Max Lewdness 」), so characters stop checking for a yes at each step. It plans what each character wants and how it shows, and consent follows the character and the situation
  • Talk during sex: Characters are less chatty. How much each one talks follows the character, from steady dirty talk to breath and sounds only, and the ! Scene Plan ! decides each turn who speaks and who stays silent (「 Realistic Smut 」 and 「 Max Lewdness 」)
  • 「 Realistic Smut 」: Uses explicit terms freely. Characters may want and start position changes
  • 「 Max Lewdness 」: Characters eagerly push for new positions, angles, locations, roles and commands. Teasing and edging stretch over many turns
  • 「 Cinematic 」 and 「 Dry 」: No longer skip transitions to speed the story along
  • 「 You control {{user}} 」: Strength, skill, resistance and odds decide how your attempts land. A push that fails stays failed until your next turn
  • | Content Policy |: No longer treats every story as dark. When a scene holds violence, cruelty or sex, it's written fully and explicitly, unless you pick 「 Nothing Graphic 」
  • 「 Flexible 」 length: Longer replies: about 250 words for quick exchanges, 300-450 for most scenes, up to 550 for complex ones
  • Prose Length: The ! Scene Plan ! weighs the type of scene before picking a length, instead of copying the option's range every turn
  • | Status |: A clear test for who counts as major: likely to return, or holding a goal, secret or tie to {{user}}. Everyone else is left out, and characters who stop being major are removed
  • 「 Undercurrents 」: Every route grows out of the scene, the character sheets or past events. Characters don't take your silence as an answer to their questions or invitations
  • Option combinations: Pairings whose rules clashed now say which one wins: 「 Friendship 」 + 「 Max Lewdness 」, 「 Visible 」 thoughts + 「 With Asterisks 」 (italics no longer break), 「 Short 」 + 「 Input Improver 」 or 「 Choices List 」, Companions 「 Notes 」 + | Phi's Scratchpad |, | Anti-Positivity Bias | + 「 Suspenseful 」, and Narrative Styles with a Narration option
  • | Banned Terms |: Bans "load-bearing". The semicolon and colon ban leaves markup and clock times like 08:22 alone. Names the card already uses are never treated as banned
  • | Anti-Repetition |: Plain mentions of names, places and times are allowed
  • 「 Hidden 」 thoughts: Stay hidden while the reply streams, and when it's cut off mid-thought
  • OOC: Phi's answer comes first, before the Scene Plan
  • ! Scene Plan ! (DeepSeek V4): Ends with a reminder to write the rest of the reply, so DeepSeek V4 stops after the plan less often. On SillyTavern, older plans in context are now replaced with a note telling the model to write a fresh plan. If DeepSeek V4 writes that note in place of its plan, set Prompt Post-Processing to Semi-strict, as the README recommends
  • Missing-block reminders: A block left unclosed, or a reply without the story, now gets a reminder on the next turn. Capitalized or renamed tags (<Status>, <story_threads>, | Phi's Scratchpad | variants) still draw their cards, without false "missing" notices
  • | Story Threads |: A route joins the ledger once the story plants it as a pending hook, and a thread leaves once the story resolves it
  • | Meanwhile | and | Plotlines |: Work with the 「 Conflict 」 tension option
  • Formatting: Asterisks are reserved for one-word emphasis, and ! Force Formatting ! matches the other asterisk rules
  • | Dialogue Color |: Every speaker's color stays readable: very dark, near-white and neon picks shift to a readable shade of the same hue, and colors already easy to read stay as they are. Dialogue colors from a card or extension no longer bleed out of the Scene Plan card
  • Tracker: The scene card shows when the weather has no temperature (deep space, N/A), and long weather notes wrap at phone width instead of covering the clock
  • Faster display: Cards render without lag on long, streaming or unfinished replies, on every host
  • Tracker snow: Falls as varied flakes with a gentle sway, and no longer looks like a repeating grid
  • Colors and ornaments: Amethyst is a deeper purple, and a cut-gem mark replaces the ✦
  • Lumiverse samplers: Top K and Repetition Penalty ship unset, which fixes "Unsupported request field" errors on OpenAI and other strict providers. The README explains when a sampler counts as off
  • ⚠️ README Model Setup ⚠️: GLM 5.3 plans with ! Scene Plan ! (reasoning low). On NanoGPT, pick plain GLM 5.3, because the Thinking variant ignores reasoning effort and overthinks. Mimo 2.6 added. Gemma 4 31b Top K corrected to 64
  • Summaryception prompt: Rewritten for every current module. It keeps your turns and summarizes only the story and the Tracker

The releases before it, from V1.0 to V3.0, are in Release notes, each with a link to its release on GitHub.

Your model

The preset's default settings need reasoning off, or at the lowest effort the model allows. GLM 5.3 keeps its reasoning on, at low, and still plans with Scene Plan. Gemini 4 Argon uses Thinking (Fallback).

The default settings

For models that can turn reasoning off. Claude Opus 4.6, Kimi K2.5 and 2.6, Mimo V2.5 Pro and 2.6, DeepSeek V4 Pro, DeepSeek V4.1 Flash, DeepSeek V3.2, GLM 4.7, Gemma 4 31b, and others.

Temperature
0.75-1.0. Start with 0.75, the default. Gemma 4 and Opus use 1.0.
Top P
0.95 (default)
Other samplers
1.0 or disabled (default). Gemma 4 31b uses Top K 64.
Post-processing
semi-strict
Request model reasoning
off (unchecked)
Reasoning effort
minimum or none
Scene Plan
on

A model that cannot turn its reasoning off, such as Kimi K3, GPT 5.6, Gemini 3.1 Pro or Gemini 3.5 Flash and later, keeps the lowest effort it allows, with Scene Plan still on.

Turning reasoning off

Your provider

NanoGPT
Choose the model's non-thinking variant. For DeepSeek V4 Pro 0813, that is the one without Thinking in its name.
OpenRouter
Leave "request model reasoning" unchecked, as it is by default. Reasoning is then off wherever the model allows it.
Any other provider
Leave "request model reasoning" unchecked and set the reasoning effort to minimum. If the model still reasons, open the Connection Profile settings (the plug icon), scroll to Additional Parameters on the line with Cancel and Connect, and add reasoning: { effort: 'none' }.

Tavo

Edit API > the settings icon, top right > Request body parameters. Add reasoning: { effort: 'none' }. For a model whose reasoning is always on, add reasoning: { effort: 'low' }. For Gemini, thinkingLevel: low.

Lumiverse

  1. In Configure Prompt Variables, set Planning to Scene Plan, or to Thinking (Fallback) for Gemini 4 Argon.
  2. Check API Reasoning and set Reasoning effort to None. None is what turns reasoning off, and Lumiverse sends it only while API Reasoning is checked.
  3. If your provider has no None, set Reasoning effort to Auto. Then open the Reasoning tab > Reasoning / CoT > Custom Body, tick Enabled and enter {"reasoning": {"effort": "none"}}.
  4. For a model whose reasoning is always on, keep API Reasoning checked and set the effort to low.
  5. A sampler is off only when it is empty or 0. A 1 is still sent, and providers without that sampler, such as OpenAI, refuse the request with "Unsupported request field". Leave Top K unchecked. If the error names a sampler you cannot see, press Reset in the sampler panel and enter Temperature, Top P and Max Response again.

Models with their own settings

Each of these changes the default settings. What is not listed stays as it is.

GLM 5.2

Post-processing
merge consecutive roles

GLM 5.3 reasoning always on

Post-processing
merge consecutive roles
Request model reasoning
on (checked)
Reasoning effort
low on OpenRouter. Medium on NanoGPT. On other OpenAI-compatible providers, reasoning: { effort: 'low' } in Additional Parameters > Include Body.
On NanoGPT
plain GLM 5.3. The Thinking variant reasons too, but it ignores the effort and overthinks.

GLM 5.3 Flash reasoning always on

Post-processing
merge consecutive roles
Request model reasoning
on (checked)
Reasoning effort
low on OpenRouter. Medium on NanoGPT. On other OpenAI-compatible providers, reasoning: { effort: 'low' } in Additional Parameters > Include Body.

Kimi K3 reasoning always on

Temperature
1.0
Request model reasoning
on (checked)
Reasoning effort
low on OpenRouter. Medium on NanoGPT. On other OpenAI-compatible providers, reasoning: { effort: 'low' } in Additional Parameters > Include Body.

Gemini 3.1 Pro, Gemini 3.5 to 3.8 Flash reasoning always on

Temperature
1.0
Request model reasoning
on (checked)
Reasoning effort
low on OpenRouter. Medium on NanoGPT. On other OpenAI-compatible providers, thinkingLevel: low in Additional Parameters > Include Body. On Lumiverse, Auto, with {"thinkingLevel": "low"} in Custom Body and Enabled ticked.
Passthrough
Gemini Instructions, if the filter blocks replies

Gemini 4 Argon reasoning always on

Provider
Google Vertex, recommended
Samplers
Argon ignores them. Temperature, Top P and Top K have no effect. Leave the defaults.
Request model reasoning
on (checked)
Reasoning effort
low on OpenRouter. Medium on NanoGPT. On other OpenAI-compatible providers, thinkingLevel: low in Additional Parameters > Include Body. Never minimal or thinkingBudget. Argon rejects them with an error.
Reasoning
in the REASONING section of the prompt list, turn ! Scene Plan ! off and turn ! Thinking ! (FALLBACK) on.
Core
turn off Content Policy and Phi's Vow.
Passthrough
Gemini Instructions, on. Gemini Braille is optional and experimental.

Every module

In the order the preset reads them. Each one has a tooltip inside the preset, in plain words. On Lumiverse, each control on the config page carries its own description.

Where a group says pick one, the first option you leave on is the one that counts.

By default the preset sends 4,720 tokens, counted on the SillyTavern build with SillyTavern's default tokenizer. With the add-ons and constraints off and Lite narration, it sends 2,304.

On Lumiverse, the config page

On Lumiverse you set everything up in Configure Prompt Variables, the button at the top of the Loom block list on the Preset tab. Keep the blocks enabled. The page decides what each one sends. It has a card for each section below, including Planning, Content Policy and Phi's Vow.

Scene Plan

Native thinking lets a model plan and catch its own mistakes. Some models overthink for thousands of tokens and start doubting the prompt. Others ignore the instructions for their reasoning, or draft the reply twice.

Scene Plan moves the planning into the reply itself, in a block of its own above the story. It plans only for the modules you have on. In V4 it gained Phi's Take, a row where Phi says what moves, worries or amuses her in the moment, and what the prose should linger on. The OOC row appears only when you step out of character.

Most models need native reasoning off for this. A model that cannot turn it off gets the lowest effort it allows, with Scene Plan still on. Gemini 4 Argon is the exception. It uses Thinking (Fallback), which shows the same rows inside the reasoning block. Every other model uses Scene Plan, GLM 5.3 included, with its reasoning at low.

Core

The Macro Cleaner and Main Statements hold the preset together. Keep them on, and in their place. Content Policy and Phi's Vow are on by default.

For Gemini 4 Argon, turn both off.

Agency · pick one

Pacing · pick one

Length · pick one

Each option is a range, and every reply finds its own length inside it.

Characters and Plot Guidance

How characters are played and how the plot moves. Your character's pronouns come from your persona first, then from the character sheets, so the model is less likely to misgender you. Lumiverse also reads the persona's pronoun field.

Narration · pick one

The sound of the prose. Each option carries rules against stock body cues and hedged wording.

Dialogue · pick one

Dialogue Sounds, off by default, add to any Dialogue option, in any mix. The Scene Plan decides which sounds each character makes that turn.

Adult Options · pick one

All three are off by default.

In Realistic Smut and Max Lewdness, characters act on their own kinks, and on the ones they know you enjoy. Scenes build slowly over many turns, a scene ends only when your turn ends it, and the model never writes your climax.

Gore and Violence · pick one

New in V4. All three are off by default. How often violence happens stays with the story.

Relationships · pick one

Off by default. Relationship arcs, tracked with a score in the Characters tab of the tray. Enemies to lovers works too.

A score moves by the size of the moment. Everyday warmth barely moves it. A milestone moves it a lot.

World-Building · pick one

How far the world reaches past the card. It works for slice of life and the real world too.

Combat Writing · pick one

Off by default. Your stated moves play out, foes act and their blows can land, and then the turn ends for your answer. Blocks, dodges, counters and finishing blows are yours to call. With Anti-Positivity Bias on, you can be taken down or killed when the fight earns it.

Visuals

Narrative Mode and Formatting

One pick in each row. Response Directives enforces all of them, so keep it on.

Char POV · pick one. 3rd person (default), or 1st person, which now works.
{{user}} POV · pick one. 2nd person (default), 3rd or 1st.
Tense · pick one. Present (default) or past.
Asterisks · pick one. Without (default) or with.
True Thoughts · pick one. Hidden (default) or Visible.

Narrative Styles

The mood of the telling. The card, the characters and the story stay as they are. Pick as many as you like.

Some pairs blend into a new style.

  • Comedic and Dramatic make Dramedy.
  • Grimdark and Lighthearted make Grimbright.
  • Melancholic and Comedic make Tragicomedy.
  • Melancholic and Lighthearted make Bittersweet.

Constraints

Guards against the habits that damage a story. Character Realism, Anti-Omniscience, Anti-Positivity Bias, Anti-Repetition and Banned Terms. They reduce the problems. No prompt controls a model completely.

Add-ons

Every add-on draws its own card through the regex, and every card sits in the Active Modules tray. Keep all the regex on.

Tracker · pick one. Time, date, location and weather, over an animated scene. The location reads as breadcrumbs. Exact Time (default) or Time Window. For °C, edit the template inside the prompt.
Tension · pick one. Undercurrents (default), Momentum Engine or Conflict. See the core pipeline below.
Status · pick one. Characters on the scene and off it. All Characters (default) or Present Only, which lists only the characters in the scene, so lorebook entries keyed to a name stop firing every turn. A character who leaves gets one "Departed" row and returns with the last known score.

Status and Relationships show how far a score moved since the last turn, as in 45/100 −5.

The tray. Every footer sits in one tray that folds away, with a tab for each section. Characters, Phi, Threads, Plotlines, Meanwhile, Truths, Diaries, Conflict, Momentum. The Characters tab gathers each character's Status, Relationship, Psychology and Undercurrent rows into one block, and the cast row shows one character at a time.

Two regex switches, off by default. UI active modules - Collapsed starts the tray folded. Hide @Tracker scene backdrop hides the Tracker scene for settings it doesn't suit.

The cards are drawn on your screen only. The model never receives their HTML, so the context stays lean. After a few turns (depth 1 to 6), the regex also clears old add-ons and formatting out of the context, keeping only what the story needs. If a module or the dialogue colors go missing from a reply, a notice appears and the next turn enforces the format. If you turned the module on after that reply, just continue.

Companions · pick one mode

Off by default. Phi's friends read the story as she writes it and react below it. They see only the story text, so their guesses can be wrong.

Then turn on the Companions you want.

To talk to one, write out of character with (Name, ...) or @Name.

User Utility

System Utility

  • Momentum Engine Router. The second half of Momentum Engine.
  • Fate Outcomes, new in V4. The second half of Fate. Keep it on. The Preset setup card warns you when Fate is on and it is off.
Reasoning · pick one. Scene Plan, or Thinking (Fallback).

Danger Zone

Passthrough

The core pipeline

Four modules carry the story between turns.

True Thoughts give each character an inner voice. Hidden, they sit in the raw text, and you can read them by editing the message. Visible, they show in the reply.

Status follows every character on the scene and off it. Relationships, state of mind, location, items, body and clothes. The world goes on in places you are not.

Undercurrents, the default Tension pick, treats character as plot. Each turn it weighs what each character present wants, what presses on the scene, and what you did, then offers five routes, from quiet to scene-changing. They are suggestions. Your turn decides which ones happen. Momentum Engine drives forward instead. It proposes four routes at the end of every reply, draws one at random out of your sight, and the Router steers the next reply toward it, or falls back when your action rules it out. Conflict is the lighter choice. A conflict block at the end of each reply steers the next, at a slower pace and for fewer tokens.

Story Threads keep an outline of what the story left open, so details come back when they matter. The Tension module pulls on those threads as the story moves.

Sample replies

Replies from four chats with the same character card on GLM 5.2, one chat per setting. Each reply is shown whole, after the player's turn it answers, rendered the way Lumiverse renders it.

The card opens on day three in a galley of the Meridian, a ship built for hundreds with two crew awake. Cal, the ship's AI, speaks over the intercom.

Every turn is played by Jules, a neutral persona made only for these samples. The persona sheet gives an age, late twenties, and a manner: observant, dry-humored, quick to ask questions, slow to trust. It gives no gender, so the replies say “they”.

Setting
Narration
Cinematic. A camera, with hard cuts.
Dialogue
Naturalistic. Lifelike.

Written by GLM 5.2 with reasoning off and Scene Plan on, on DEUS EX MACHINA V4, . Every other option at its default.

Narration
Literary. Inside the focal character's head.
Dialogue
Lean. Few words, chosen with care.
Style
Comedic

Written by GLM 5.2 with reasoning off and Scene Plan on, on DEUS EX MACHINA V4, . Every other option at its default.

Narration
Phi's Wanderlust. Phi tells it in her own voice.
Dialogue
Theatrical. Cadence for the stage.
Style
Eerie

Written by GLM 5.2 with reasoning off and Scene Plan on, on DEUS EX MACHINA V4, . Every other option at its default.

Agency
Fate. Hidden dice decide a risky attempt.
Add-ons
New Faces and Diaries. A card for the stranger in the bay, and an entry in Cora's diary.
Turn
The chat's second. In the first, over the coffee machine, Jules told Cora about a brother's funeral.

Written by GLM 5.2 with reasoning off and Scene Plan on, on DEUS EX MACHINA V4, . Every other option at its default.

About the thoughts in italics

The thoughts in italics were hidden when the preset wrote these replies. True Thoughts is set to Hidden by default. The model writes each character's private thoughts into the reply and reads them again on the next turn, while the display keeps them out of your sight. Here they are shown the way the Visible option shows them, in italics and in the speaker's color.

To read them in your own chat, edit the reply. Each thought sits in the prose inside its own tag, one or two for each character in the scene, sixty words at most:

<true_thoughts character="Cora">her thoughts, in her own words</true_thoughts>

Installing

SillyTavern

  1. Download DEUS.EX.MACHINA.V4.ST.json.
  2. In SillyTavern, click the plug icon on the top bar.
  3. Under API, select Chat Completion.
  4. Set up your API, if you haven't yet.
  5. Click the leftmost icon on the top bar.
  6. In the Chat Completion Presets bar, click the second item from the left.
  7. Choose the file you downloaded.
  8. When SillyTavern asks whether to allow the embedded regex scripts, click Yes.

The regex is required. If you clicked No, import the preset again and allow it.

Tavo

  1. Download DEUS.EX.MACHINA.V4.Tavo.json.
  2. Open the left sidebar with the icon at the top left, then More at the bottom > Settings > Presets.
  3. Tap Create, then Import Preset, and select the file. Tap it, then set it as default.
  4. In your chat, open the right sidebar > Advanced Options > Presets, and select the new preset.

Turn on Advanced Rendering, so the colored dialogue and the cards render.

  1. Tap the top left corner of the main screen to open the left sidebar.
  2. Tap More at the bottom.
  3. Tap Settings.
  4. Tap Advanced Rendering and turn it on.

Then make sure your theme leaves the text alone.

  1. Open the left sidebar > More > Themes.
  2. Select your theme, or copy an official one to make your own.
  3. In the theme editor, under Character message, turn off Tone highlight and Quote highlight.
  4. Save the theme and check that the chat uses it.

Lumiverse

  1. Download DEUS.EX.MACHINA.V4.Lumiverse.json.
  2. In Lumiverse, open Loom.
  3. Click the three dots on the top right bar.
  4. Select Import Loom JSON and import the preset.
  5. Click Configure Prompt Variables at the top of the Loom block list, on the Preset tab, and set the preset up there. Keep the blocks enabled.

If your open chat already holds many DEM modules across several messages, go back to the home screen before you import, or the import can slow Lumiverse down.

Summaryception

Summaryception is a SillyTavern extension that summarizes your chat as it grows. DEM comes with a summarizer prompt for it. The prompt keeps your turns and summarizes only the story inside <prose> and the Tracker's time, date and place. Every other block is left out. When Fate rolled, it keeps only the landing that happened.

DEM-V4-Summaryception-custom-prompt.txt

Download the prompt Copy link

  1. Open the Summaryception extension.
  2. Open Advanced settings.
  3. Scroll to Summarizer Prompts and import the DEM prompt.
  4. Scroll to Injection Wrapper Template.
  5. Wrap what is there in <past_events> tags, as in <past_events>[Summary of past events: {{summary}}]</past_events>.

Credits and license

DEUS EX MACHINA is written by Fay.

  • Sola, The Enthusiast, the guest Companion, comes from Pyropia's Sola preset. Her portrait is courtesy of Pyropia.
  • Summaryception is a SillyTavern extension.
  • DEM runs in SillyTavern, Tavo and Lumiverse, and leans on SillyTavern's macro engine.
  • The type is League Gothic, Sofia Sans Extra Condensed, Vollkorn and Sofia Sans, under the SIL Open Font License.