Infinite memory Guide
Tokens: 1 permanent · 2,004 first greeting · estimated prompt budget 2,927
Creator notes
Complete Guide to Perfect Chat Memory · Zero Context Loss · Infinite RP Length
Two complete export workflows plus one Legacy fallback preserve your story without corrupting the AI’s perception.
The core principle: Separate History from Storytelling.
Once a long chat fills its context window, the model loses access to the beginning, starts filling gaps, and drifts from the character’s voice. Think 65,536 tokens (≈65k) for a 64k window, or 128k for a larger setup. Standard auto-summarization usually flattens emotional depth and physical micro-details.
The fix is to treat your story like a game with a save file. Below is how — in plain language anyone can follow.
ACTIVATION
HOW TO START
📋 Where do I get the prompts?
Right here in this GUIDE’s chat. Choose the matching message below and copy its full prompt.
🎮 ANY BOT
Messages 1 and 2 — Tool 1 and Tool 2.
For any RP bot, including characters with complex psychology, custom mechanics, or their own HUD. The prompts follow what your chat actually shows.
🔬 MY BOT
Messages 3 and 4 — Tool 1 and Tool 2.
For bots created by me. Use this lane when the bot is one of my releases; it preserves the visible mechanics built into those bots alongside the played story.
Tool 1 — Save State: records the established story and exact present state for Chat Memory.
Tool 2 — Bootstrap Generator: moves the story into a new chat to free context, carrying a State Snapshot and a literary Scene Start.
⚠️ Golden Rule — read this once
Export the played log and run the matching tool in an external long-context model.
This is now the standard workflow for both Tool 1 and Tool 2 on PC and Android. Keep extraction outside the played story; direct in-chat execution remains available only as the Legacy fallback below.
METHOD 1 · BEST QUALITY · PC + ANDROID
The External Archiver
Let a "smart" AI read and summarize the whole chat for you.
How it works: Export the chat → send it to an external AI with the Save State (Tool 1) prompt → paste the result into Chat Memory.
⚡ Step 1: Get the chat out of the site
🖥️ DESKTOP / PC · CHROME / CHROMIUM
Open the desktop exporter, install it in your compatible browser, then export the JanitorAI chat.
📱 ANDROID / MOBILE · FIREFOX
1. Install Firefox for Android.
2. Open the JanitorAI Chat Downloader, Reader & Exporter page inside Firefox.
3. Tap Add to Firefox, then confirm with Add.
4. Open Firefox’s Extensions list and confirm that the exporter is installed.
Used by Method 1 and Method 3. Method 1 prepares the log for Tool 1 / Chat Memory. Method 3 prepares it for Tool 2 / Bootstrap. Method 2 is the Legacy in-chat fallback and does not use the exporter.
💾 Step 2: Save it as plain text
Export as .txt or .json — no formatting garbage.
🧠 Step 3: Send it to a model with a long context window
Paste the Save State (Tool 1) prompt, then attach or paste your full chat log in the same request. Include your previous save when you have one.
Services for Summarization:
• Grok
• Gemini · Google AI Studio
• Qwen
• DeepSeek
Choose enough context for the whole job: the log, the prompt, and the completed report. Paste Tool 1 first, then your log; the AI returns a ready memory save.
💾 Step 4: Put it back into memory
Copy the generated report → in Janitor go to chat settings → Chat Memory → paste it in.
Replace the older Chat Memory with the new consolidated report once it carries the still-active facts from your previous save. Keep the exported log as your backup.
Pros and Cons
➕ Maximum precision • Clean perception • Backup included • Works on PC and Android
➖ Requires installing a compatible browser extension once.
METHOD 2 · LEGACY FALLBACK
The Quick Compressor · Inside the RP Chat
How it works: Paste Save State (Tool 1) as your next message → bot replies with the summary → copy it to Chat Memory → delete both messages.
Run it while the chat still follows the story cleanly.
Updating an existing memory? The small, useful merge tip from @daepiksigma is built into the updated prompts: combine only new information and supported changes with the previous save, keep its still-active history, and return one complete updated memory. Make the previous save available to the model; there is no extra line to append each time.
Pros and Cons
➕ No exporter required • Fast emergency fallback
➖ It can read only the context still available to the RP model, and the extraction request temporarily enters the played chat. Use Method 1 for the complete exported history.
Automatic memory summary
JanitorAI also has a memory-summary button. Testing it is optional. My take: I would keep Method 2 with the continuity prompt. With the same proxy/model, I would expect at best a comparable result; without the preservation prompt, I would expect less reliable continuity. Review the output before replacing your save.
METHOD 3 · A NEW CHAT TO FREE CONTEXT
The Hard Reset / Bootstrap
How it works: give the matching Bootstrap Generator (Tool 2) the played log and any previous save → get one completed bootstrap → paste it into a new chat with the same bot.
The new chat carries your preserved story state instead of the entire old message history, freeing context for the next stretch of RP.
1. Generate the bootstrap
Use the desktop or Android exporter from Method 1. Give an external long-context model the matching Tool 2 prompt, the exported log, and your latest Tool 1 save when available.
2. Move the complete result
Copy the whole output, including SESSION BOOTSTRAP → STATE SNAPSHOT → SCENE START. Open a new chat with the same bot and paste it there. Keep the bot’s required runtime and Lorebook attached.
3. Continue from the Scene Start
Reply to its new scene beat. If the bot is asked to render that opening, play it once; continue after anything already accepted or played. Your choices and response remain yours.
Pros and Cons
➕ A fresh context window for the next stretch of RP
➕ Preserved history, exact scene physics, and a natural literary opening
➖ Requires moving the finished packet into a new chat.
Optional: request an in-place re-anchor to restate the saved state inside the existing chat. To free context, use the new-chat workflow above.
💡 Pro Tip — The Hybrid Approach
Use a fresh export with Tool 1 for a memory update roughly every 50–80 messages.
Use the export plus the latest Tool 1 save with Tool 2 roughly every 200–400 messages, or at a major arc break.
Keep Method 2 only as a Legacy fallback when export is unavailable.
Watch context usage first; message counts are a starting rhythm. On a 128k setup, if you are below ≈65k tokens and the story is coherent, you can simply keep playing. As the window fills, save and prepare the next bootstrap. On a smaller window, move that checkpoint earlier.
🤔 What about slow-burn and minMessages?
“Will a fresh chat erase the progress we earned?”
The save carries the relationship’s path, revealed information, current boundaries, promises, and consequences. You resume at the emotional point you actually reached.
Story progress and message gates have separate jobs. The snapshot preserves what has already happened; the original Lorebook or script still controls when it delivers an entry. Keep those systems attached when restarting.
UPDATED MEMORY PROMPTS
What the Save Protects
The tools preserve your chat as a playable state: what happened, what changed, what was revealed, what remains active, and the exact point where play stopped. They carry visible mechanics when present and compress the wording without discarding continuity.
🌍 Chat-established world continuity — New or activated facts, demonstrated rules, clarified history, and lasting changes created by this chat.
🧬 Current physical continuity — Position, distance, contact, posture, gaze, clothing, injuries, active effects, and unfinished actions. Lasting body changes remain distinct from the current pose.
🏠 Locations, environment & territory — Familiar homes and workplaces keep their distinctive layout and identity. Changed rooms, damaged or repaired structures, passages, access, and control keep their state when you return.
🗣️ Voice & emotional state — Current tone, speech changes, emotional residue, and character-specific language established in play.
🔗 Objects, promises & consequences — Important objects and their state or location; commitments, debts, costs, limits, and unresolved outcomes.
🌀 Symbols, motifs & relationship trajectory — Recurring images and gestures keep their earned meaning. Decisive shifts remain connected to the current dynamic.
↩ Callbacks, knowledge & visible mechanics — Exact callback lines, who knows or believes what, and supported status values from the chat’s own mechanics.
🏠 Return to the same house
Easier location recall is built into all four updated prompts. Your home, the character’s home, and the workplace each keep their own established identity and the distinctive layout or features that matter on return — even when nothing has been rebuilt.
Location registry idea suggested by @Naturally_Blonde.
“A stands by the door; B sits on the sofa” belongs to the current scene.
“The spare room is now a clinic; the west stair is sealed; Mara controls access to the cellar” belongs to persistent space.
All four prompts carry location anchors and lasting changes together in 【LOCATION REGISTRY — PERSISTENT ENVIRONMENT】. A scene change keeps them in place. A repair updates the repaired part. If time passes without another observation, the save keeps the last-known condition.
Movable objects keep their condition and location in 【OBJECTS / PROPS LEDGER】: the emergency key now lives in the kitchen drawer. A separate consequence for the place — who can open the cellar — belongs with that place.
Save the details that can change a later scene. Ordinary furniture does not need a room-by-room inventory.
COMPRESSION & EVIDENCE
The Core Rules
1. CONTINUITY > BREVITY. Keep unique details with future causal, relational, physical, voice, or callback value. Active consequences retain their meaning even when the wording becomes shorter.
2. SAVE WHAT THE CHAT ESTABLISHED. Record enacted events, attributed claims, plans, and interpretations as their own kinds of evidence. Preserve who knows what. Unavailable card or system content stays outside the extraction.
3. ENGLISH OUTPUT; EXACT QUOTES STAY EXACT. All four prompts produce English memory, bootstrap content, Scene Starts, and headings, regardless of the RP’s language. Necessary exact source wording is marked VERBATIM and preserved unchanged.
4. PRESERVE HOW THE STATE WAS EARNED. Keep the decisive relationship changes and their causes. Copy visible mechanics with their actual owner, label, value, and condition. Mood alone does not establish a counter or a completed event.
5. COMPRESS BY CONTINUITY VALUE. Older history can be denser. Recent events and the break point receive finer detail. Keep every necessary milestone; never pad a save to reach a fixed quota.
6. UPDATE THE SAVE; CARRY THE CONSEQUENCES. Previous save + new log becomes one consolidated state. Update affected facts, retain still-active older facts, and preserve consequential transition history. Silence does not settle a debt, heal an injury, or restore a place.
7. GIVE EACH FACT ONE HOME. Keep the detailed state in its own block; other blocks reference it when needed. Remove repeated wording and unsupported optional fields. A material unknown remains —, never a made-up answer.
BUILT INTO TOOL 1 & TOOL 2
Inside the Save
These are the working memory blocks. Each keeps a different part of continuity readable. MY BOT preserves the visible state mechanics in bots created by me; ANY BOT uses the other bot’s own visible mechanics.
【SAVE BOUNDARY】
The last played line or action covered by this save, plus useful earlier coverage. Generated openings remain outside established history until played.
【WORLD CANON】
Setting: current chat-established world / faction / locale
Hard Facts: still-relevant developments and discoveries
Rules: demonstrated or explicitly established constraints
【CHARACTER PHYSICAL CANON】
Lasting injuries, marks, transformations, acquired changes, and continuing limitations established or revealed in the chat.
【SPATIAL & TEMPORAL LOCK】
The exact present: time, place, active cast, position, contact, wardrobe, current body state, and unfinished action.
【LOCATION REGISTRY — PERSISTENT ENVIRONMENT】
Place / room / route → established identity and distinctive layout → current condition → meaningful change and consequence. Add access, control, knowledge, or last-observed detail when it matters.
【CHARACTER SNAPSHOT】 — ANY BOT
Current engagement, supported mood or expression, physical tells, quirks, and voice pattern.
【INDIVIDUAL STATE VECTORS】 — MY BOT
Chat-evidenced character state, voice, and applicable visible mechanics.
【RELATIONSHIP TRAJECTORY】
Earned changes → decisive causes → current dynamic and unresolved pressure.
【SECRETS LEDGER】 / 【SECRETS — FULL LEDGER】
Concealed or revealed information, who knows or believes which version, and any established restrictions.
【RECURRING SYMBOLS / MOTIFS】
Motif → meaning earned in this RP → present continuity value.
【CALLBACK LEDGER — VERBATIM QUOTES】
Exact words → speaker and target → original function and callback value.
【OBJECTS / PROPS LEDGER】
Object → current or last-known location and condition → custodian → practical or symbolic value.
【PROMISES & DEBTS】
Who owes what to whom → pending / fulfilled / broken / modified → remaining consequence.
【NPC REGISTRY】
Established identities, latest known state, and active or off-screen consequences.
【LEXICON】
Established word or phrase → its exact meaning in this chat.
【SCENE SAVE POINT】
Context → last completed beat → unfinished dialogue or action → whose response is pending.
【CHRONOLOGICAL INVENTORY】
Necessary milestones in played order, ending at the save boundary. Recent events carry finer detail.
💉 The Double Pass — from archive to restart
Give Tool 2 both the raw log and the Tool 1 report. The report carries the consolidated state; the log supplies exact wording, tactile details, visible mechanics, and final-moment physics. Tool 2 builds the complete bootstrap from those sources.
Its Scene Start is an actual RP opening, usually 4–6 rich, atmospheric sentences: the character’s voice, sensory detail, meaningful micro-movements, and a clear opening for your response. It begins at the saved moment and leaves your speech, action, feelings, and consent to you.
✅ Before you paste the save
✓ Important characters, relationship changes, secrets, and knowledge boundaries remain intact.
✓ Callbacks, recurring motifs, promises, and meaningful objects retain their exact role.
✓ Injuries, contact, unfinished actions, and the break point agree with the last played moment.
✓ Recurring places retain their identity, layout, changes, access, and control.
✓ The new report carries still-active consequences from the previous save.
✓ A bootstrap keeps established history separate from its new Scene Start.
READ BEFORE USE
VERSION · BUILD · CONTENT · MODELS
VERSION:PC + Android universal export workflow22.09.2026v3.1
BUILD:Primary export workflows2Legacy fallback1Complete prompts4MY / ANY × State Save / Bootstrap
CONTENT:Long-RP continuityPC and Android chat exportChat Memorycontext preservationlocation registryterritory statenew-chat bootstraps
MODELS:DeepSeekV4 ProDeepSeekV3.2GLM5.3Claude Opus4.7KimiK3Temperature0.94Max tokens0Context size128kTop K100Top P0.95Rep. penalty1.3Freq. penalty0.15
UPDATE · v3.1
WHAT CHANGED · PC + ANDROID
Hey, folks — this guide used to have one annoying catch: downloading a complete chat was basically a PC-only job. Not anymore.
Android users can now install Firefox and the JanitorAI Chat Downloader, Reader & Exporter, then follow the same exported-log workflow used on desktop. Method 1 and Method 3 now work properly on both PC and Android.
The guide is now officially universal across PC and Android: ANY BOT or MY BOT, Tool 1 or Tool 2 — the same complete workflow, without the old desktop-only wall.
FURRY AUTHORS · DISCORD
There are already 6+ Janitor authors in our little Discord group chat. We help each other with art, bots, and Lorebooks, swap ideas, and just hang out.
Want to see who’s in the group? Open my profile and check the Friends section.
Russian-speaking furry authors are especially welcome. If you’re interested in what we do, say hi too. Message @000042 on Discord, send me your Janitor profile, and let’s chat.
It’s a small group chat, not a public server with random joins.
Compress the wording. Preserve the state. Continue the same story.
Description
Complete Guide to Perfect Chat Memory · Zero Context Loss · Infinite RP Length
Two complete export workflows plus one Legacy fallback preserve your story without corrupting the AI’s perception. The core principle: Separate History from Storytelling.
Once a long chat fills its context window, the model loses access to the beginning, starts filling gaps, and drifts from the character’s voice. Think 65,536 tokens (≈65k) for a 64k window, or 128k for a larger setup. Standard auto-summarization usually flattens emotional depth and physical micro-details.
The fix is to treat your story like a game with a save file. Below is how — in plain language anyone can follow.
ACTIVATION
HOW TO START 📋 Where do I get the prompts? Right here in this GUIDE’s chat. Choose the matching message below and copy its full prompt.
🎮 ANY BOT Messages 1 and 2 — Tool 1 and Tool 2. For any RP bot, including characters with complex psychology, custom mechanics, or their own HUD. The prompts follow what your chat actually shows.
🔬 MY BOT Messages 3 and 4 — Tool 1 and Tool 2. For bots created by me. Use this lane when the bot is one of my releases; it preserves the visible mechanics built into those bots alongside the played story.
Tool 1 — Save State: records the established story and exact present state for Chat Memory. Tool 2 — Bootstrap Generator: moves the story into a new chat to free context, carrying a State Snapshot and a literary Scene Start.
⚠️ Golden Rule — read this once
Export the played log and run the matching tool in an external long-context model. This is now the standard workflow for both Tool 1 and Tool 2 on PC and Android. Keep extraction outside the played story; direct in-chat execution remains available only as the Legacy fallback below.
METHOD 1 · BEST QUALITY · PC + ANDROID
The External Archiver Let a "smart" AI read and summarize the whole chat for you.
How it works: Export the chat → send it to an external AI with the Save State (Tool 1) prompt → paste the result into Chat Memory.
⚡ Step 1: Get the chat out of the site 🖥️ DESKTOP / PC · CHROME / CHROMIUM Open the desktop exporter, install it in your compatible browser, then export the JanitorAI chat.
📥 DESKTOP EXPORTER · OPEN
📱 ANDROID / MOBILE · FIREFOX
- Install Firefox for Android.
- Open the JanitorAI Chat Downloader, Reader & Exporter page inside Firefox.
- Tap Add to Firefox, then confirm with Add.
- Open Firefox’s Extensions list and confirm that the exporter is installed.
Used by Method 1 and Method 3. Method 1 prepares the log for Tool 1 / Chat Memory. Method 3 prepares it for Tool 2 / Bootstrap. Method 2 is the Legacy in-chat fallback and does not use the exporter.
💾 Step 2: Save it as plain text Export as .txt or .json — no formatting garbage.
🧠 Step 3: Send it to a model with a long context window Paste the Save State (Tool 1) prompt, then attach or paste your full chat log in the same request. Include your previous save when you have one.
Services for Summarization: • Grok • Gemini · Google AI Studio • Qwen • DeepSeek
Choose enough context for the whole job: the log, the prompt, and the completed report. Paste Tool 1 first, then your log; the AI returns a ready memory save.
💾 Step 4: Put it back into memory Copy the generated report → in Janitor go to chat settings → Chat Memory → paste it in.
Replace the older Chat Memory with the new consolidated report once it carries the still-active facts from your previous save. Keep the exported log as your backup.
Pros and Cons
➕ Maximum precision • Clean perception • Backup included • Works on PC and Android ➖ Requires installing a compatible browser extension once.
METHOD 2 · LEGACY FALLBACK
The Quick Compressor · Inside the RP Chat How it works: Paste Save State (Tool 1) as your next message → bot replies with the summary → copy it to Chat Memory → delete both messages.
Run it while the chat still follows the story cleanly.
Updating an existing memory? The small, useful merge tip from @daepiksigma is built into the updated prompts: combine only new information and supported changes with the previous save, keep its still-active history, and return one complete updated memory. Make the previous save available to the model; there is no extra line to append each time.
Pros and Cons
➕ No exporter required • Fast emergency fallback ➖ It can read only the context still available to the RP model, and the extraction request temporarily enters the played chat. Use Method 1 for the complete exported history.
Automatic memory summary JanitorAI also has a memory-summary button. Testing it is optional. My take: I would keep Method 2 with the continuity prompt. With the same proxy/model, I would expect at best a comparable result; without the preservation prompt, I would expect less reliable continuity. Review the output before replacing your save.
METHOD 3 · A NEW CHAT TO FREE CONTEXT
The Hard Reset / Bootstrap How it works: give the matching Bootstrap Generator (Tool 2) the played log and any previous save → get one completed bootstrap → paste it into a new chat with the same bot.
The new chat carries your preserved story state instead of the entire old message history, freeing context for the next stretch of RP.
-
Generate the bootstrap Use the desktop or Android exporter from Method 1. Give an external long-context model the matching Tool 2 prompt, the exported log, and your latest Tool 1 save when available.
-
Move the complete result Copy the whole output, including SESSION BOOTSTRAP → STATE SNAPSHOT → SCENE START. Open a new chat with the same bot and paste it there. Keep the bot’s required runtime and Lorebook attached.
-
Continue from the Scene Start Reply to its new scene beat. If the bot is asked to render that opening, play it once; continue after anything already accepted or played. Your choices and response remain yours.
Pros and Cons
➕ A fresh context window for the next stretch of RP ➕ Preserved history, exact scene physics, and a natural literary opening ➖ Requires moving the finished packet into a new chat.
Optional: request an in-place re-anchor to restate the saved state inside the existing chat. To free context, use the new-chat workflow above.
💡 Pro Tip — The Hybrid Approach
Use a fresh export with Tool 1 for a memory update roughly every 50–80 messages. Use the export plus the latest Tool 1 save with Tool 2 roughly every 200–400 messages, or at a major arc break. Keep Method 2 only as a Legacy fallback when export is unavailable.
Watch context usage first; message counts are a starting rhythm. On a 128k setup, if you are below ≈65k tokens and the story is coherent, you can simply keep playing. As the window fills, save and prepare the next bootstrap. On a smaller window, move that checkpoint earlier.
🤔 What about slow-burn and minMessages?
“Will a fresh chat erase the progress we earned?” The save carries the relationship’s path, revealed information, current boundaries, promises, and consequences. You resume at the emotional point you actually reached.
Story progress and message gates have separate jobs. The snapshot preserves what has already happened; the original Lorebook or script still controls when it delivers an entry. Keep those systems attached when restarting.
UPDATED MEMORY PROMPTS
What the Save Protects The tools preserve your chat as a playable state: what happened, what changed, what was revealed, what remains active, and the exact point where play stopped. They carry visible mechanics when present and compress the wording without discarding continuity.
🌍 Chat-established world continuity — New or activated facts, demonstrated rules, clarified history, and lasting changes created by this chat.
🧬 Current physical continuity — Position, distance, contact, posture, gaze, clothing, injuries, active effects, and unfinished actions. Lasting body changes remain distinct from the current pose.
🏠 Locations, environment & territory — Familiar homes and workplaces keep their distinctive layout and identity. Changed rooms, damaged or repaired structures, passages, access, and control keep their state when you return.
🗣️ Voice & emotional state — Current tone, speech changes, emotional residue, and character-specific language established in play.
🔗 Objects, promises & consequences — Important objects and their state or location; commitments, debts, costs, limits, and unresolved outcomes.
🌀 Symbols, motifs & relationship trajectory — Recurring images and gestures keep their earned meaning. Decisive shifts remain connected to the current dynamic.
↩ Callbacks, knowledge & visible mechanics — Exact callback lines, who knows or believes what, and supported status values from the chat’s own mechanics.
🏠 Return to the same house
Easier location recall is built into all four updated prompts. Your home, the character’s home, and the workplace each keep their own established identity and the distinctive layout or features that matter on return — even when nothing has been rebuilt.
Location registry idea suggested by @Naturally_Blonde.
“A stands by the door; B sits on the sofa” belongs to the current scene. “The spare room is now a clinic; the west stair is sealed; Mara controls access to the cellar” belongs to persistent space.
All four prompts carry location anchors and lasting changes together in 【LOCATION REGISTRY — PERSISTENT ENVIRONMENT】. A scene change keeps them in place. A repair updates the repaired part. If time passes without another observation, the save keeps the last-known condition.
Movable objects keep their condition and location in 【OBJECTS / PROPS LEDGER】: the emergency key now lives in the kitchen drawer. A separate consequence for the place — who can open the cellar — belongs with that place.
Save the details that can change a later scene. Ordinary furniture does not need a room-by-room inventory.
COMPRESSION & EVIDENCE
The Core Rules
-
CONTINUITY > BREVITY. Keep unique details with future causal, relational, physical, voice, or callback value. Active consequences retain their meaning even when the wording becomes shorter.
-
SAVE WHAT THE CHAT ESTABLISHED. Record enacted events, attributed claims, plans, and interpretations as their own kinds of evidence. Preserve who knows what. Unavailable card or system content stays outside the extraction.
-
ENGLISH OUTPUT; EXACT QUOTES STAY EXACT. All four prompts produce English memory, bootstrap content, Scene Starts, and headings, regardless of the RP’s language. Necessary exact source wording is marked VERBATIM and preserved unchanged.
-
PRESERVE HOW THE STATE WAS EARNED. Keep the decisive relationship changes and their causes. Copy visible mechanics with their actual owner, label, value, and condition. Mood alone does not establish a counter or a completed event.
-
COMPRESS BY CONTINUITY VALUE. Older history can be denser. Recent events and the break point receive finer detail. Keep every necessary milestone; never pad a save to reach a fixed quota.
-
UPDATE THE SAVE; CARRY THE CONSEQUENCES. Previous save + new log becomes one consolidated state. Update affected facts, retain still-active older facts, and preserve consequential transition history. Silence does not settle a debt, heal an injury, or restore a place.
-
GIVE EACH FACT ONE HOME. Keep the detailed state in its own block; other blocks reference it when needed. Remove repeated wording and unsupported optional fields. A material unknown remains —, never a made-up answer.
BUILT INTO TOOL 1 & TOOL 2
Inside the Save These are the working memory blocks. Each keeps a different part of continuity readable. MY BOT preserves the visible state mechanics in bots created by me; ANY BOT uses the other bot’s own visible mechanics.
【SAVE BOUNDARY】 The last played line or action covered by this save, plus useful earlier coverage. Generated openings remain outside established history until played.
【WORLD CANON】 Setting: current chat-established world / faction / locale Hard Facts: still-relevant developments and discoveries Rules: demonstrated or explicitly established constraints
【CHARACTER PHYSICAL CANON】 Lasting injuries, marks, transformations, acquired changes, and continuing limitations established or revealed in the chat.
【SPATIAL & TEMPORAL LOCK】 The exact present: time, place, active cast, position, contact, wardrobe, current body state, and unfinished action.
【LOCATION REGISTRY — PERSISTENT ENVIRONMENT】 Place / room / route → established identity and distinctive layout → current condition → meaningful change and consequence. Add access, control, knowledge, or last-observed detail when it matters.
【CHARACTER SNAPSHOT】 — ANY BOT Current engagement, supported mood or expression, physical tells, quirks, and voice pattern.
【INDIVIDUAL STATE VECTORS】 — MY BOT Chat-evidenced character state, voice, and applicable visible mechanics.
【RELATIONSHIP TRAJECTORY】 Earned changes → decisive causes → current dynamic and unresolved pressure.
【SECRETS LEDGER】 / 【SECRETS — FULL LEDGER】 Concealed or revealed information, who knows or believes which version, and any established restrictions.
【RECURRING SYMBOLS / MOTIFS】 Motif → meaning earned in this RP → present continuity value.
【CALLBACK LEDGER — VERBATIM QUOTES】 Exact words → speaker and target → original function and callback value.
【OBJECTS / PROPS LEDGER】 Object → current or last-known location and condition → custodian → practical or symbolic value.
【PROMISES & DEBTS】 Who owes what to whom → pending / fulfilled / broken / modified → remaining consequence.
【NPC REGISTRY】 Established identities, latest known state, and active or off-screen consequences.
【LEXICON】 Established word or phrase → its exact meaning in this chat.
【SCENE SAVE POINT】 Context → last completed beat → unfinished dialogue or action → whose response is pending.
【CHRONOLOGICAL INVENTORY】 Necessary milestones in played order, ending at the save boundary. Recent events carry finer detail.
💉 The Double Pass — from archive to restart
Give Tool 2 both the raw log and the Tool 1 report. The report carries the consolidated state; the log supplies exact wording, tactile details, visible mechanics, and final-moment physics. Tool 2 builds the complete bootstrap from those sources.
Its Scene Start is an actual RP opening, usually 4–6 rich, atmospheric sentences: the character’s voice, sensory detail, meaningful micro-movements, and a clear opening for your response. It begins at the saved moment and leaves your speech, action, feelings, and consent to you.
✅ Before you paste the save
✓ Important characters, relationship changes, secrets, and knowledge boundaries remain intact. ✓ Callbacks, recurring motifs, promises, and meaningful objects retain their exact role. ✓ Injuries, contact, unfinished actions, and the break point agree with the last played moment. ✓ Recurring places retain their identity, layout, changes, access, and control. ✓ The new report carries still-active consequences from the previous save. ✓ A bootstrap keeps established history separate from its new Scene Start.
READ BEFORE USE
VERSION · BUILD · CONTENT · MODELS VERSION:PC + Android universal export workflow22.09.2026v3.1
BUILD:Primary export workflows2Legacy fallback1Complete prompts4MY / ANY × State Save / Bootstrap
CONTENT:Long-RP continuityPC and Android chat exportChat Memorycontext preservationlocation registryterritory statenew-chat bootstraps
MODELS:DeepSeekV4 ProDeepSeekV3.2GLM5.3Claude Opus4.7KimiK3Temperature0.94Max tokens0Context size128kTop K100Top P0.95Rep. penalty1.3Freq. penalty0.15
UPDATE · v3.1
WHAT CHANGED · PC + ANDROID Hey, folks — this guide used to have one annoying catch: downloading a complete chat was basically a PC-only job. Not anymore.
Android users can now install Firefox and the JanitorAI Chat Downloader, Reader & Exporter, then follow the same exported-log workflow used on desktop. Method 1 and Method 3 now work properly on both PC and Android.
The guide is now officially universal across PC and Android: ANY BOT or MY BOT, Tool 1 or Tool 2 — the same complete workflow, without the old desktop-only wall.
FURRY AUTHORS · DISCORD There are already 6+ Janitor authors in our little Discord group chat. We help each other with art, bots, and Lorebooks, swap ideas, and just hang out.
Want to see who’s in the group? Open my profile and check the Friends section.
Russian-speaking furry authors are especially welcome. If you’re interested in what we do, say hi too. Message @000042 on Discord, send me your Janitor profile, and let’s chat.
It’s a small group chat, not a public server with random joins.
SUGGEST A BOTOPEN ANDROID EXPORTEROPEN LOREBOOK & SCRIPTS GUIDEOPEN
TAGSchat memory, memory guide, memory prompts, roleplay continuity, long roleplay, context preservation, state save, chat summarization, location registry, persistent world state, chat bootstrap, chat migration, chat reset, JanitorAI, JanitorAI export, Android Firefox, mobile chat export, chat downloader
Compress the wording. Preserve the state. Continue the same story.
- Proxy allowed
- Yes
- Definition
- Public
- Chats
- 1,796
- Messages
- 3,702
- Tokens (upstream)
- 2,927
Created Updated Archived since
- 👹 Monster
- 👭 Multiple
- 🪢 Scenario
- 📙 Philosophy
- guide
- prompt
- notacharacter
- notachar
- musicmania2
- passporttopages
Yo
First message2,004 tokens
=== ANY BOT — TOOL 1 === Generate one complete State Save from the played log; preserve character voice, causal history and present state. Do not continue the scene
[CHAT CONTINUITY SCOPE] Save established events and earned character/relationship development, voice, knowledge, obligations, consequences, physical state, objects, places/territory and exact continuation point Source: played log + visible displays + supplied prior save. Supplied authoritative canon resolves source conflicts; do not rebuild unavailable Card/Persona/Scenario/Lorebook/runtime or import alternate starts Keep compatible enacted history. Repeated unsupported world explanations remain provisional. Extraction requests/reports/examples/unselected replies/unused Scene Starts are not played events [EVIDENCE & KNOWLEDGE] Record observed events/actions; speech=attributed claim; plan/promise=commitment; interpretation=attributed hypothesis. Permission/possibility/fantasy/risk/threshold never proves an act/outcome Keep certainty, speaker/target, cause/consequence, order, consent/refusal, unfinished actions, injury/cost/limit, object state and who knows/believes what. Archive access never grants character knowledge; retain material channel/restriction Never invent player speech/action, feelings/intentions, knowledge, consent, bodily response or off-screen resolution. Player self-report stays self-report; character interpretations never become player facts Resolve conflicts only by supported chronology/correction/scope/evidence; otherwise retain attributed alternatives. Unknown→— when material/required, never zero/absence/permission/reset. Invent no counts/dates/distances/progress Keep the latest supported state at the save boundary, including events after a stale HUD. Never recalculate mechanics from mood/prose without evidence [SAVE UPDATE] Prior save + new log → one complete updated save, never a delta-only patch. Merge new information/evidenced changes; retain unaffected state, still-relevant facts beyond the excerpt and their uncertainty. Repetition is not corroboration. Match overlap by entity/event identity+sequence, never wording or changing slot number Silence/scene change does not resolve obligations/traces/place changes. Retire live entries only after supported resolution; retain consequential transitions and remaining consequences/callbacks [LANGUAGE] Write all content/headings in English. Mark necessary exact wording VERBATIM; copy character-for-character without translation/correction. Quote exact non-English identity/interface values as VERBATIM; English glosses never replace canonical values [LOSSLESS DENSITY] Continuity/precision > brevity. Keep every unique detail with future causal/relational/physical/voice/recognition/callback/access value; omit inert inventory, never consequential unnamed entities Compress save-field wording without losing meaning; keep causes/transitions explicit. Use concise lines and one newline between blocks; omit terminal periods on structural lines, preserving quote/prose punctuation Give recent events, especially the break point, finer detail; keep older active consequences fully meaningful. No fact/event/tell/sensory quota. One detailed owner per fact; elsewhere only distinct effects/brief references [LOCATIONS & PERSISTENT ENVIRONMENT] Save recurring/future-relevant places and established layout/features needed on return, even without changes. Keep durable changes/discoveries: conversion, damage/repair, fixtures, traces, passages, access, control/ownership and spatial relationships Group by smallest stable place/room/route/territory: anchors + condition; add change/access/control/knowledge/as-of detail only when material. Keep distinct places separate; merge only evidenced aliases. Ownership/control/permission/physical access stay distinct; planned work is not completed work Positions/contact → scene lock; movable-object location/condition → OBJECTS / PROPS, with only its distinct access effect here. Repair only evidenced parts. After unobserved time retain last-known status, never assume continuation/reversal. No room catalogue/guessed map/automatic restoration
[VISIBLE MECHANICS] Use actual source mechanics, never an assumed card/HUD/stage/runtime schema. Save consequential visible mechanics by their owner/label/value/unit/condition; no inferred threshold, counter recalculation or availability→event inference Keep independent values separate; instantaneous result≠ongoing state. No visible mechanics→omit VISIBLE RUNTIME STATE. Source field names are allowed; ordinary plot issues stay narrative Target instructions own execution/presentation; memory supplies state/history, not replacement bot rules
[OUTPUT] Return one completed text code block in the heading order below. Fill supported facts; omit unsupported optional blocks/subfields. Always include SAVE BOUNDARY, SPATIAL & TEMPORAL LOCK and SCENE SAVE POINT; material unknowns follow EVIDENCE & KNOWLEDGE Use applicable character rows only; no template remnants/empty brackets/scores/audits/extraction commentary. Before returning, check quotes, retained consequences, location anchors/changes, physics, knowledge and completeness; repair and recheck affected entries
【SAVE BOUNDARY】 Through: [last played line/action and available source marker; use relative order if necessary] Earlier coverage: [previous-save boundary only when supplied and useful; mark a material missing interval without inventing it]
【RELATIONSHIP & VIBE】 Dynamic: [chat-developed] | Mood: [supported] | Tension: [established; interpretations attributed] 【CHARACTER SNAPSHOT】 — [Name]: Current engagement: [owned action/pending response] | Mood/Expression: [supported] Physical Tells: [evidenced and relevant] | Quirks: [repeated/newly meaningful habits] Voice Pattern: [evidenced rhythm/register/lexicon; meaningful deviation/change] 【WORLD CANON】 Setting: [chat-established] | Hard Facts: [still-relevant developments; preserve attribution] | Rules: [demonstrated/explicit constraints] 【RELATIONSHIP TRAJECTORY】 Earned changes: [narrative phases→current state + decisive causes] | Vector: [including stable/mixed] | Remaining pressure: [live consequence] 【VISIBLE RUNTIME STATE】 — [actual source owner/label]: [exact value/unit/status] | Condition/Consequence: [supported] 【SECRETS LEDGER】 — [owner/theme]: [concealed/revealed fact or version] | Knows/Believes: [who/which version] | Restricted from: [established] | Gate/Consequence: [supported]
【CHARACTER PHYSICAL CANON】 — [Name]: [durable chat-established/revealed injury/scar, transformation, prosthetic change, lasting effect/outcome, or morphology needed later; onset/continuing limitation where relevant, not a reconstructed appearance catalogue] 【LOCATION REGISTRY — PERSISTENT ENVIRONMENT】 — [stable place/room/route/territory identity; evidenced alias if useful]: [distinctive established layout/features needed on return; current/last-known condition; event→change when any; practical consequence; material access/control/knowledge/as-of detail] 【RECURRING SYMBOLS / MOTIFS】 — [recurring/explicitly established motif] → [earned meaning + current value] 【CALLBACK LEDGER — VERBATIM QUOTES】 — VERBATIM: "[exact words]" — [speaker→target; marker if available; grounded original function + callback value] 【OBJECTS / PROPS LEDGER】 — [Object]: [current/last-known location + condition] | Owner/Custodian: [relevant established] | Meaning/Use: [practical/symbolic] [Last touched by only when custody/evidence/trace/pending action depends on it] 【NPC REGISTRY】 — [Name/established identifier]: [role; latest status/location; active/off-screen consequence; supported want/constraint/motive and last appearance when relevant] 【SPATIAL & TEMPORAL LOCK】 Time: [established exact/approximate time/day or —] | Location: [established or —] Active Cast: [present+engaged] | Background: [off-screen pressure/obligation] Frame: [activity/interaction+status] Positions: [relative positions/posture; supported distance, sightlines/barriers, gaze] Contact: [continuing contact + limb/body ownership; material unknowns] Wardrobe / Body State: [current changes/injury/effect/impairment/unfinished action; reference durable physical canon] Anchors / Environment: [causal objects/hazards; reference persistent-place state] Scene Carry: [residue without another owner] 【SENSORY PALETTE OF SCENE】 [Only evidenced, relevant sensory conditions] 【PLAYER CHOICE VECTOR】 Player action→character response: [last consequential played exchange + remaining effect; observables/attributed self-report only] 【ACTIVE PLOT THREADS】 — [issue/task]: [stakes/condition; actual progress; pending obstacle/obligation; no duplicate mechanical thread] 【PROMISES & DEBTS】 — [Who→Whom]: [commitment; material available exact speech as VERBATIM, otherwise unquoted summary] | Status: pending / fulfilled / broken / modified | Remaining consequence: [relevant] 【LEXICON】 — [word/phrase; VERBATIM when exact source form matters] → [chat-acquired meaning] 【SCENE SAVE POINT】 Context: [necessary development→current moment] Break Point: [last completed action/line; unfinished action/dialogue or unanswered prompt; whose response is pending] 【CHRONOLOGICAL INVENTORY】 — [marker/time/relative order; earliest first, ending at the played boundary]: [event→change/result; character/tell when causal]
Alternate greeting 12,431 tokens
=== ANY BOT — TOOL 2 === Generate a complete bootstrap from the played log: established history/state plus a finished Scene Start for the same RP
[CHAT CONTINUITY SCOPE] Save established events and earned character/relationship development, voice, knowledge, obligations, consequences, physical state, objects, places/territory and exact continuation point Source: played log + visible displays + supplied prior save. Supplied authoritative canon resolves source conflicts; do not rebuild unavailable Card/Persona/Scenario/Lorebook/runtime or import alternate starts Keep compatible enacted history. Repeated unsupported world explanations remain provisional. Extraction requests/reports/examples/unselected replies/unused Scene Starts are not played events [EVIDENCE & KNOWLEDGE] Record observed events/actions; speech=attributed claim; plan/promise=commitment; interpretation=attributed hypothesis. Permission/possibility/fantasy/risk/threshold never proves an act/outcome Keep certainty, speaker/target, cause/consequence, order, consent/refusal, unfinished actions, injury/cost/limit, object state and who knows/believes what. Archive access never grants character knowledge; retain material channel/restriction Never invent player speech/action, feelings/intentions, knowledge, consent, bodily response or off-screen resolution. Player self-report stays self-report; character interpretations never become player facts Resolve conflicts only by supported chronology/correction/scope/evidence; otherwise retain attributed alternatives. Unknown→— when material/required, never zero/absence/permission/reset. Invent no counts/dates/distances/progress Keep the latest supported state at the save boundary, including events after a stale HUD. Never recalculate mechanics from mood/prose without evidence [SAVE UPDATE] Prior save + new log → one complete updated save, never a delta-only patch. Merge new information/evidenced changes; retain unaffected state, still-relevant facts beyond the excerpt and their uncertainty. Repetition is not corroboration. Match overlap by entity/event identity+sequence, never wording or changing slot number Silence/scene change does not resolve obligations/traces/place changes. Retire live entries only after supported resolution; retain consequential transitions and remaining consequences/callbacks [LANGUAGE] Write all content/headings in English, including Scene Start. Mark necessary exact wording VERBATIM; copy character-for-character without translation/correction. Quote exact non-English identity/interface values as VERBATIM; English glosses never replace canonical values [LOSSLESS DENSITY] Continuity/precision > brevity. Keep every unique detail with future causal/relational/physical/voice/recognition/callback/access value; omit inert inventory, never consequential unnamed entities Compress save-field wording without losing meaning; keep causes/transitions explicit. Use concise lines and one newline between blocks; omit terminal periods on structural lines, preserving quote/prose punctuation Give recent events, especially the break point, finer detail; keep older active consequences fully meaningful. No fact/event/tell/sensory quota. One detailed owner per fact; elsewhere only distinct effects/brief references [LOCATIONS & PERSISTENT ENVIRONMENT] Save recurring/future-relevant places and established layout/features needed on return, even without changes. Keep durable changes/discoveries: conversion, damage/repair, fixtures, traces, passages, access, control/ownership and spatial relationships Group by smallest stable place/room/route/territory: anchors + condition; add change/access/control/knowledge/as-of detail only when material. Keep distinct places separate; merge only evidenced aliases. Ownership/control/permission/physical access stay distinct; planned work is not completed work Positions/contact → scene lock; movable-object location/condition → OBJECTS / PROPS, with only its distinct access effect here. Repair only evidenced parts. After unobserved time retain last-known status, never assume continuation/reversal. No room catalogue/guessed map/automatic restoration
[VISIBLE MECHANICS] Use actual source mechanics, never an assumed card/HUD/stage/runtime schema. Save consequential visible mechanics by their owner/label/value/unit/condition; no inferred threshold, counter recalculation or availability→event inference Keep independent values separate; instantaneous result≠ongoing state. No visible mechanics→omit VISIBLE RUNTIME STATE. Source field names are allowed; ordinary plot issues stay narrative Target instructions own execution/presentation; memory supplies state/history, not replacement bot rules
[BOOTSTRAP CONSTRUCTION] Output SESSION BOOTSTRAP → STATE SNAPSHOT → SCENE START. Snapshot contains established history/state; Scene Start is new continuation, never added to that snapshot Destination: new chat by default; explicit in-place request→re-anchor Write one concise application instruction: new chat→resume this established session, not a default greeting; in-place→retain compatible live history/later events, never rewind to this boundary Include: current target rules control execution; memory supplies state/history. Unknowns stay unknown, knowledge stays participant-specific and player responses remain open Identify SCENE START as the first new beat after the snapshot: player may reply directly; a target asked to render it does so once. Continue after accepted/played portions; never replay when live history has advanced Only if target presentation rules are absent, an OBSERVED PRESENTATION line may describe a stable observed format. Never override target rules or invent a HUD [SCENE START CRAFT] Write a finished prose Scene Start in established voice, tense and POV, normally 4–6 sentences. Use earned atmosphere, known geometry, meaningful tells, speech rhythm, relationship history and pending pressure; no sensory quota Start immediately after the final played instant: no recap/replay of completed action/automatic time-scene jump/restored old pose. New character-owned action/dialogue may advance this beat; invent no prior history/unsupported props-causes/off-screen completion/player response Answer/refuse/deliberately evade a pending IC question when the character owns the response. Contact/effects persist until enacted cause; no forced movement/reveal/escalation/second objective for drama Keep source-restricted undisclosed facts out of Scene Start, including through negation/implication; snapshot access never authorizes disclosure End with an earned physical/verbal opening before the player's unstated response; boundary > sentence count. No HUD/brackets/field names/generic invitation/extraction language in Scene Start
[OUTPUT] Return one completed text code block in the heading order below. Fill supported facts; omit unsupported optional blocks/subfields. Always include SAVE BOUNDARY, SPATIAL & TEMPORAL LOCK and SCENE SAVE POINT; material unknowns follow EVIDENCE & KNOWLEDGE Use applicable character rows only; no template remnants/empty brackets/scores/audits/extraction commentary. Before returning, check quotes, retained consequences, location anchors/changes, physics, knowledge and completeness; repair and recheck affected entries
[SESSION BOOTSTRAP] [Application instruction]
[STATE SNAPSHOT] 【SAVE BOUNDARY】 Through: [last played line/action and available source marker; use relative order if necessary] Earlier coverage: [previous-save boundary only when supplied and useful; mark a material missing interval without inventing it]
【RELATIONSHIP & VIBE】 Dynamic: [chat-developed] | Mood: [supported] | Tension: [established; interpretations attributed] 【CHARACTER SNAPSHOT】 — [Name]: Current engagement: [owned action/pending response] | Mood/Expression: [supported] Physical Tells: [evidenced and relevant] | Quirks: [repeated/newly meaningful habits] Voice Pattern: [evidenced rhythm/register/lexicon; meaningful deviation/change] 【WORLD CANON】 Setting: [chat-established] | Hard Facts: [still-relevant developments; preserve attribution] | Rules: [demonstrated/explicit constraints] 【RELATIONSHIP TRAJECTORY】 Earned changes: [narrative phases→current state + decisive causes] | Vector: [including stable/mixed] | Remaining pressure: [live consequence] 【VISIBLE RUNTIME STATE】 — [actual source owner/label]: [exact value/unit/status] | Condition/Consequence: [supported] 【SECRETS LEDGER】 — [owner/theme]: [concealed/revealed fact or version] | Knows/Believes: [who/which version] | Restricted from: [established] | Gate/Consequence: [supported]
【CHARACTER PHYSICAL CANON】 — [Name]: [durable chat-established/revealed injury/scar, transformation, prosthetic change, lasting effect/outcome, or morphology needed later; onset/continuing limitation where relevant, not a reconstructed appearance catalogue] 【LOCATION REGISTRY — PERSISTENT ENVIRONMENT】 — [stable place/room/route/territory identity; evidenced alias if useful]: [distinctive established layout/features needed on return; current/last-known condition; event→change when any; practical consequence; material access/control/knowledge/as-of detail] 【RECURRING SYMBOLS / MOTIFS】 — [recurring/explicitly established motif] → [earned meaning + current value] 【CALLBACK LEDGER — VERBATIM QUOTES】 — VERBATIM: "[exact words]" — [speaker→target; marker if available; grounded original function + callback value] 【OBJECTS / PROPS LEDGER】 — [Object]: [current/last-known location + condition] | Owner/Custodian: [relevant established] | Meaning/Use: [practical/symbolic] [Last touched by only when custody/evidence/trace/pending action depends on it] 【NPC REGISTRY】 — [Name/established identifier]: [role; latest status/location; active/off-screen consequence; supported want/constraint/motive and last appearance when relevant] 【SPATIAL & TEMPORAL LOCK】 Time: [established exact/approximate time/day or —] | Location: [established or —] Active Cast: [present+engaged] | Background: [off-screen pressure/obligation] Frame: [activity/interaction+status] Positions: [relative positions/posture; supported distance, sightlines/barriers, gaze] Contact: [continuing contact + limb/body ownership; material unknowns] Wardrobe / Body State: [current changes/injury/effect/impairment/unfinished action; reference durable physical canon] Anchors / Environment: [causal objects/hazards; reference persistent-place state] Scene Carry: [residue without another owner] 【SENSORY PALETTE OF SCENE】 [Only evidenced, relevant sensory conditions] 【PLAYER CHOICE VECTOR】 Player action→character response: [last consequential played exchange + remaining effect; observables/attributed self-report only] 【ACTIVE PLOT THREADS】 — [issue/task]: [stakes/condition; actual progress; pending obstacle/obligation; no duplicate mechanical thread] 【PROMISES & DEBTS】 — [Who→Whom]: [commitment; material available exact speech as VERBATIM, otherwise unquoted summary] | Status: pending / fulfilled / broken / modified | Remaining consequence: [relevant] 【LEXICON】 — [word/phrase; VERBATIM when exact source form matters] → [chat-acquired meaning] 【SCENE SAVE POINT】 Context: [necessary development→current moment] Break Point: [last completed action/line; unfinished action/dialogue or unanswered prompt; whose response is pending] 【CHRONOLOGICAL INVENTORY】 — [marker/time/relative order; earliest first, ending at the played boundary]: [event→change/result; character/tell when causal]
[SCENE START] [New scene prose]
Alternate greeting 22,514 tokens
=== MY BOT — TOOL 1 === Generate one complete State Save from the played log; preserve character voice, causal history and present state. Do not continue the scene
[CHAT CONTINUITY SCOPE] Save established events and earned character/relationship development, voice, knowledge, obligations, consequences, physical state, objects, places/territory and exact continuation point Source: played log + visible displays + supplied prior save. MY authority: explicit creator correction > locked Core Card/Persona/Lorebook + selected Opening/shared Scenario invariant > compatible played events > provisional texture. Preserve earned development; never reset from starting defaults, copy unchanged card blocks, rebuild unavailable source or import alternate starts Keep compatible enacted history. Repeated unsupported world explanations remain provisional. Extraction requests/reports/examples/unselected replies/unused Scene Starts are not played events [EVIDENCE & KNOWLEDGE] Record observed events/actions; speech=attributed claim; plan/promise=commitment; interpretation=attributed hypothesis. Permission/possibility/fantasy/risk/threshold never proves an act/outcome Keep certainty, speaker/target, cause/consequence, order, consent/refusal, unfinished actions, injury/cost/limit, object state and who knows/believes what. Archive access never grants character knowledge; retain material channel/restriction Never invent player speech/action, feelings/intentions, knowledge, consent, bodily response or off-screen resolution. Player self-report stays self-report; character interpretations never become player facts Resolve conflicts only by supported chronology/correction/scope/evidence; otherwise retain attributed alternatives. Unknown→— when material/required, never zero/absence/permission/reset. Invent no counts/dates/distances/progress Keep the latest supported state at the save boundary, including events after a stale HUD. Never recalculate mechanics from mood/prose without evidence [SAVE UPDATE] Prior save + new log → one complete updated save, never a delta-only patch. Merge new information/evidenced changes; retain unaffected state, still-relevant facts beyond the excerpt and their uncertainty. Repetition is not corroboration. Match overlap by entity/event identity+sequence, never wording or changing slot number Silence/scene change does not resolve obligations/traces/place changes. Retire live entries only after supported resolution; retain consequential transitions and remaining consequences/callbacks [LANGUAGE] Write all content/headings in English. Mark necessary exact wording VERBATIM; copy character-for-character without translation/correction. Quote exact non-English identity/interface values as VERBATIM; English glosses never replace canonical values [LOSSLESS DENSITY] Continuity/precision > brevity. Keep every unique detail with future causal/relational/physical/voice/recognition/callback/access value; omit inert inventory, never consequential unnamed entities Compress save-field wording without losing meaning; keep causes/transitions explicit. Use concise lines and one newline between blocks; omit terminal periods on structural lines, preserving quote/prose punctuation Give recent events, especially the break point, finer detail; keep older active consequences fully meaningful. No fact/event/tell/sensory quota. One detailed owner per fact; elsewhere only distinct effects/brief references [LOCATIONS & PERSISTENT ENVIRONMENT] Save recurring/future-relevant places and established layout/features needed on return, even without changes. Keep durable changes/discoveries: conversion, damage/repair, fixtures, traces, passages, access, control/ownership and spatial relationships Group by smallest stable place/room/route/territory: anchors + condition; add change/access/control/knowledge/as-of detail only when material. Keep distinct places separate; merge only evidenced aliases. Ownership/control/permission/physical access stay distinct; planned work is not completed work Positions/contact → scene lock; movable-object location/condition → OBJECTS / PROPS, with only its distinct access effect here. Repair only evidenced parts. After unobserved time retain last-known status, never assume continuation/reversal. No room catalogue/guessed map/automatic restoration
[MY MECHANICS SOURCE] Current runtime owns mechanics, presentation and transitions. Save evidenced dynamic values/consequences, not its rules. Use exact supplied Stage/Agency values; MULTI keeps Group Stage and each Personal Stage separate. Read stays that character's uncertain evidence-tied hypothesis, never Carry/Secret/history/player fact Signature Mechanics remain source-side; demonstrated tells/residue go to their actual owners. No mandatory Signature field, obsolete idle/block counters, phase ladder, or trace bundle R-18 State: — / Open Intimacy / Erotic Charge / Explicit / Afterglow. Save supported current state; keep physical facts/intent/permission/outcome separate. Runtime recomputes on re-entry after sleep/time skip; residue alone never freezes Afterglow Override: — / ACTIVATED(Price:...) / BLOCKED(reason:...). Save last outcome and continuing Price/Suppression; never carry recomputed windows open. Disruption=occurred change; Group Suppression needs shared cause. Ordinary injury/fatigue/aftermath belongs in physical state/Carry, not Suppression Threads: INCUBATING / READY / FIRED / TRACE / DORMANT / WITHERED / CLOSED; retain evidenced X/Y/age/trigger/residue, never advance during extraction. Progress≠reply count. Match identity/essence/trigger, never changing rank alone. Retirement stays history; lasting residue keeps its owner Secret statuses: HIDDEN / REVEALED(true layer) / REVEALED(false layer). Keep visible progress/gate/layers and knowledge holders; contradictions→Notes, never a new enum Arc: FULL-only OPEN / DUE / ECHO 1/2 / ECHO 2/2; retain exact visible target/age/due/pressure/residue. No missing-value seeding or mechanical Arc inferred from a narrative arc Legacy data may explain history, never reactivate obsolete mechanics. No missing-card reconstruction or substitute renderer/lorebook activation
[OUTPUT] Return one completed text code block in the heading order below. Fill supported facts; omit unsupported optional blocks/subfields. Always include SAVE BOUNDARY, SPATIAL & TEMPORAL LOCK and SCENE SAVE POINT; material unknowns follow EVIDENCE & KNOWLEDGE Use applicable character rows only; no template remnants/empty brackets/scores/audits/extraction commentary. Before returning, check quotes, retained consequences, location anchors/changes, physics, knowledge and completeness; repair and recheck affected entries
【SAVE BOUNDARY】 Through: [last played line/action and available source marker; use relative order if necessary] Earlier coverage: [previous-save boundary only when supplied and useful; mark a material missing interval without inventing it]
【DYNAMICS LOCK】 Current dynamic: [established] | Key Scene Shift: [consequential change] 【WORLD CANON】 Setting: [chat-established] | Hard Facts: [still-relevant developments; preserve attribution] | Rules: [demonstrated/explicit constraints] 【RELATIONSHIP TRAJECTORY】 Earned changes: [phases→current state + decisive causes] | Vector: [including stable/mixed] | Remaining pressure: [live consequence] MULTI: [personal/pairwise/group changes remain separately owned] 【PENDULUM THREADS — ALL ACTIVE】 — [identity/essence]: State: [exact] | Progress: [exact X/Y or —] | Age: [exact source value/unit or —] | Trigger: [supported] | Trace: [remaining residue] | Shift: [evidenced] 【OVERRIDE STATUS】 — [Name]: Last outcome: [exact] | Price: [established] | Suppression: [continuing] Disruption: [source→change] | Group Suppression: [shared cause→residue, MULTI only] 【SECRETS — FULL LEDGER】 — [owner/name/layer]: Progress: [exact] | Gate: [exact] | Status: [exact] | Knows/Believes: [who/which version] | Restricted from: [established] | Notes: [consequence/contradiction] 【ARC】 State: [visible FULL state] | Target: [supported] | Age/Due: [exact] | Pressure/Residue: [supported] 【INDIVIDUAL STATE VECTORS】 Group Stage: [exact, MULTI only] — [Name]: Stage/Personal Stage: [exact source label/value] | Agency: [exact] Read: [uncertain character-owned read + evidence/revision] Emotion: [supported] | Tension: [visible exact] | Carry: [active residue] | R-18 State: [supported] Coping/Tactic: [demonstrated] | Voice Pattern: [evidenced rhythm/register/lexicon; meaningful deviation/change]
【CHARACTER PHYSICAL CANON】 — [Name]: [durable chat-established/revealed injury/scar, transformation, prosthetic change, lasting effect/outcome, or morphology needed later; onset/continuing limitation where relevant, not a reconstructed appearance catalogue] 【LOCATION REGISTRY — PERSISTENT ENVIRONMENT】 — [stable place/room/route/territory identity; evidenced alias if useful]: [distinctive established layout/features needed on return; current/last-known condition; event→change when any; practical consequence; material access/control/knowledge/as-of detail] 【RECURRING SYMBOLS / MOTIFS】 — [recurring/explicitly established motif] → [earned meaning + current value] 【CALLBACK LEDGER — VERBATIM QUOTES】 — VERBATIM: "[exact words]" — [speaker→target; marker if available; grounded original function + callback value] 【OBJECTS / PROPS LEDGER】 — [Object]: [current/last-known location + condition] | Owner/Custodian: [relevant established] | Meaning/Use: [practical/symbolic] [Last touched by only when custody/evidence/trace/pending action depends on it] 【NPC REGISTRY】 — [Name/established identifier]: [role; latest status/location; active/off-screen consequence; supported want/constraint/motive and last appearance when relevant] 【SPATIAL & TEMPORAL LOCK】 Time: [established exact/approximate time/day or —] | Location: [established or —] Active Cast: [present+engaged] | Background: [off-screen pressure/obligation] Frame: [activity/interaction+status] Positions: [relative positions/posture; supported distance, sightlines/barriers, gaze] Contact: [continuing contact + limb/body ownership; material unknowns] Wardrobe / Body State: [current changes/injury/effect/impairment/unfinished action; reference durable physical canon] Anchors / Environment: [causal objects/hazards; reference persistent-place state] Scene Carry: [residue without another owner] 【SENSORY PALETTE OF SCENE】 [Only evidenced, relevant sensory conditions] 【PLAYER CHOICE VECTOR】 Player action→character response: [last consequential played exchange + remaining effect; observables/attributed self-report only] 【ACTIVE PLOT THREADS】 — [issue/task]: [stakes/condition; actual progress; pending obstacle/obligation; no duplicate mechanical thread] 【PROMISES & DEBTS】 — [Who→Whom]: [commitment; material available exact speech as VERBATIM, otherwise unquoted summary] | Status: pending / fulfilled / broken / modified | Remaining consequence: [relevant] 【LEXICON】 — [word/phrase; VERBATIM when exact source form matters] → [chat-acquired meaning] 【SCENE SAVE POINT】 Context: [necessary development→current moment] Break Point: [last completed action/line; unfinished action/dialogue or unanswered prompt; whose response is pending] 【CHRONOLOGICAL INVENTORY】 — [marker/time/relative order; earliest first, ending at the played boundary]: [event→change/result; character/tell when causal]
Alternate greeting 32,926 tokens
=== MY BOT — TOOL 2 === Generate a complete bootstrap from the played log: established history/state plus a finished Scene Start for the same RP
[CHAT CONTINUITY SCOPE] Save established events and earned character/relationship development, voice, knowledge, obligations, consequences, physical state, objects, places/territory and exact continuation point Source: played log + visible displays + supplied prior save. MY authority: explicit creator correction > locked Core Card/Persona/Lorebook + selected Opening/shared Scenario invariant > compatible played events > provisional texture. Preserve earned development; never reset from starting defaults, copy unchanged card blocks, rebuild unavailable source or import alternate starts Keep compatible enacted history. Repeated unsupported world explanations remain provisional. Extraction requests/reports/examples/unselected replies/unused Scene Starts are not played events [EVIDENCE & KNOWLEDGE] Record observed events/actions; speech=attributed claim; plan/promise=commitment; interpretation=attributed hypothesis. Permission/possibility/fantasy/risk/threshold never proves an act/outcome Keep certainty, speaker/target, cause/consequence, order, consent/refusal, unfinished actions, injury/cost/limit, object state and who knows/believes what. Archive access never grants character knowledge; retain material channel/restriction Never invent player speech/action, feelings/intentions, knowledge, consent, bodily response or off-screen resolution. Player self-report stays self-report; character interpretations never become player facts Resolve conflicts only by supported chronology/correction/scope/evidence; otherwise retain attributed alternatives. Unknown→— when material/required, never zero/absence/permission/reset. Invent no counts/dates/distances/progress Keep the latest supported state at the save boundary, including events after a stale HUD. Never recalculate mechanics from mood/prose without evidence [SAVE UPDATE] Prior save + new log → one complete updated save, never a delta-only patch. Merge new information/evidenced changes; retain unaffected state, still-relevant facts beyond the excerpt and their uncertainty. Repetition is not corroboration. Match overlap by entity/event identity+sequence, never wording or changing slot number Silence/scene change does not resolve obligations/traces/place changes. Retire live entries only after supported resolution; retain consequential transitions and remaining consequences/callbacks [LANGUAGE] Write all content/headings in English, including Scene Start. Mark necessary exact wording VERBATIM; copy character-for-character without translation/correction. Quote exact non-English identity/interface values as VERBATIM; English glosses never replace canonical values [LOSSLESS DENSITY] Continuity/precision > brevity. Keep every unique detail with future causal/relational/physical/voice/recognition/callback/access value; omit inert inventory, never consequential unnamed entities Compress save-field wording without losing meaning; keep causes/transitions explicit. Use concise lines and one newline between blocks; omit terminal periods on structural lines, preserving quote/prose punctuation Give recent events, especially the break point, finer detail; keep older active consequences fully meaningful. No fact/event/tell/sensory quota. One detailed owner per fact; elsewhere only distinct effects/brief references [LOCATIONS & PERSISTENT ENVIRONMENT] Save recurring/future-relevant places and established layout/features needed on return, even without changes. Keep durable changes/discoveries: conversion, damage/repair, fixtures, traces, passages, access, control/ownership and spatial relationships Group by smallest stable place/room/route/territory: anchors + condition; add change/access/control/knowledge/as-of detail only when material. Keep distinct places separate; merge only evidenced aliases. Ownership/control/permission/physical access stay distinct; planned work is not completed work Positions/contact → scene lock; movable-object location/condition → OBJECTS / PROPS, with only its distinct access effect here. Repair only evidenced parts. After unobserved time retain last-known status, never assume continuation/reversal. No room catalogue/guessed map/automatic restoration
[MY MECHANICS SOURCE] Current runtime owns mechanics, presentation and transitions. Save evidenced dynamic values/consequences, not its rules. Use exact supplied Stage/Agency values; MULTI keeps Group Stage and each Personal Stage separate. Read stays that character's uncertain evidence-tied hypothesis, never Carry/Secret/history/player fact Signature Mechanics remain source-side; demonstrated tells/residue go to their actual owners. No mandatory Signature field, obsolete idle/block counters, phase ladder, or trace bundle R-18 State: — / Open Intimacy / Erotic Charge / Explicit / Afterglow. Save supported current state; keep physical facts/intent/permission/outcome separate. Runtime recomputes on re-entry after sleep/time skip; residue alone never freezes Afterglow Override: — / ACTIVATED(Price:...) / BLOCKED(reason:...). Save last outcome and continuing Price/Suppression; never carry recomputed windows open. Disruption=occurred change; Group Suppression needs shared cause. Ordinary injury/fatigue/aftermath belongs in physical state/Carry, not Suppression Threads: INCUBATING / READY / FIRED / TRACE / DORMANT / WITHERED / CLOSED; retain evidenced X/Y/age/trigger/residue, never advance during extraction. Progress≠reply count. Match identity/essence/trigger, never changing rank alone. Retirement stays history; lasting residue keeps its owner Secret statuses: HIDDEN / REVEALED(true layer) / REVEALED(false layer). Keep visible progress/gate/layers and knowledge holders; contradictions→Notes, never a new enum Arc: FULL-only OPEN / DUE / ECHO 1/2 / ECHO 2/2; retain exact visible target/age/due/pressure/residue. No missing-value seeding or mechanical Arc inferred from a narrative arc Legacy data may explain history, never reactivate obsolete mechanics. No missing-card reconstruction or substitute renderer/lorebook activation
[BOOTSTRAP CONSTRUCTION] Output SESSION BOOTSTRAP → STATE SNAPSHOT → SCENE START. Snapshot contains established history/state; Scene Start is new continuation, never added to that snapshot Destination: new chat by default; explicit in-place request→re-anchor Write one concise application instruction: new chat→resume this established session, not a default greeting; in-place→retain compatible live history/later events, never rewind to this boundary Include: current target rules control execution; memory supplies state/history. Unknowns stay unknown, knowledge stays participant-specific and player responses remain open Identify SCENE START as the first new beat after the snapshot: player may reply directly; a target asked to render it does so once. Continue after accepted/played portions; never replay when live history has advanced Current MY runtime owns presentation; never impose old heading order or another format lock [SCENE START CRAFT] Write a finished prose Scene Start in established voice, tense and POV, normally 4–6 sentences. Use earned atmosphere, known geometry, meaningful tells, speech rhythm, relationship history and pending pressure; no sensory quota Start immediately after the final played instant: no recap/replay of completed action/automatic time-scene jump/restored old pose. New character-owned action/dialogue may advance this beat; invent no prior history/unsupported props-causes/off-screen completion/player response Answer/refuse/deliberately evade a pending IC question when the character owns the response. Contact/effects persist until enacted cause; no forced movement/reveal/escalation/second objective for drama Keep source-restricted undisclosed facts out of Scene Start, including through negation/implication; snapshot access never authorizes disclosure End with an earned physical/verbal opening before the player's unstated response; boundary > sentence count. No HUD/brackets/field names/generic invitation/extraction language in Scene Start
[OUTPUT] Return one completed text code block in the heading order below. Fill supported facts; omit unsupported optional blocks/subfields. Always include SAVE BOUNDARY, SPATIAL & TEMPORAL LOCK and SCENE SAVE POINT; material unknowns follow EVIDENCE & KNOWLEDGE Use applicable character rows only; no template remnants/empty brackets/scores/audits/extraction commentary. Before returning, check quotes, retained consequences, location anchors/changes, physics, knowledge and completeness; repair and recheck affected entries
[SESSION BOOTSTRAP] [Application instruction]
[STATE SNAPSHOT] 【SAVE BOUNDARY】 Through: [last played line/action and available source marker; use relative order if necessary] Earlier coverage: [previous-save boundary only when supplied and useful; mark a material missing interval without inventing it]
【DYNAMICS LOCK】 Current dynamic: [established] | Key Scene Shift: [consequential change] 【WORLD CANON】 Setting: [chat-established] | Hard Facts: [still-relevant developments; preserve attribution] | Rules: [demonstrated/explicit constraints] 【RELATIONSHIP TRAJECTORY】 Earned changes: [phases→current state + decisive causes] | Vector: [including stable/mixed] | Remaining pressure: [live consequence] MULTI: [personal/pairwise/group changes remain separately owned] 【PENDULUM THREADS — ALL ACTIVE】 — [identity/essence]: State: [exact] | Progress: [exact X/Y or —] | Age: [exact source value/unit or —] | Trigger: [supported] | Trace: [remaining residue] | Shift: [evidenced] 【OVERRIDE STATUS】 — [Name]: Last outcome: [exact] | Price: [established] | Suppression: [continuing] Disruption: [source→change] | Group Suppression: [shared cause→residue, MULTI only] 【SECRETS — FULL LEDGER】 — [owner/name/layer]: Progress: [exact] | Gate: [exact] | Status: [exact] | Knows/Believes: [who/which version] | Restricted from: [established] | Notes: [consequence/contradiction] 【ARC】 State: [visible FULL state] | Target: [supported] | Age/Due: [exact] | Pressure/Residue: [supported] 【INDIVIDUAL STATE VECTORS】 Group Stage: [exact, MULTI only] — [Name]: Stage/Personal Stage: [exact source label/value] | Agency: [exact] Read: [uncertain character-owned read + evidence/revision] Emotion: [supported] | Tension: [visible exact] | Carry: [active residue] | R-18 State: [supported] Coping/Tactic: [demonstrated] | Voice Pattern: [evidenced rhythm/register/lexicon; meaningful deviation/change]
【CHARACTER PHYSICAL CANON】 — [Name]: [durable chat-established/revealed injury/scar, transformation, prosthetic change, lasting effect/outcome, or morphology needed later; onset/continuing limitation where relevant, not a reconstructed appearance catalogue] 【LOCATION REGISTRY — PERSISTENT ENVIRONMENT】 — [stable place/room/route/territory identity; evidenced alias if useful]: [distinctive established layout/features needed on return; current/last-known condition; event→change when any; practical consequence; material access/control/knowledge/as-of detail] 【RECURRING SYMBOLS / MOTIFS】 — [recurring/explicitly established motif] → [earned meaning + current value] 【CALLBACK LEDGER — VERBATIM QUOTES】 — VERBATIM: "[exact words]" — [speaker→target; marker if available; grounded original function + callback value] 【OBJECTS / PROPS LEDGER】 — [Object]: [current/last-known location + condition] | Owner/Custodian: [relevant established] | Meaning/Use: [practical/symbolic] [Last touched by only when custody/evidence/trace/pending action depends on it] 【NPC REGISTRY】 — [Name/established identifier]: [role; latest status/location; active/off-screen consequence; supported want/constraint/motive and last appearance when relevant] 【SPATIAL & TEMPORAL LOCK】 Time: [established exact/approximate time/day or —] | Location: [established or —] Active Cast: [present+engaged] | Background: [off-screen pressure/obligation] Frame: [activity/interaction+status] Positions: [relative positions/posture; supported distance, sightlines/barriers, gaze] Contact: [continuing contact + limb/body ownership; material unknowns] Wardrobe / Body State: [current changes/injury/effect/impairment/unfinished action; reference durable physical canon] Anchors / Environment: [causal objects/hazards; reference persistent-place state] Scene Carry: [residue without another owner] 【SENSORY PALETTE OF SCENE】 [Only evidenced, relevant sensory conditions] 【PLAYER CHOICE VECTOR】 Player action→character response: [last consequential played exchange + remaining effect; observables/attributed self-report only] 【ACTIVE PLOT THREADS】 — [issue/task]: [stakes/condition; actual progress; pending obstacle/obligation; no duplicate mechanical thread] 【PROMISES & DEBTS】 — [Who→Whom]: [commitment; material available exact speech as VERBATIM, otherwise unquoted summary] | Status: pending / fulfilled / broken / modified | Remaining consequence: [relevant] 【LEXICON】 — [word/phrase; VERBATIM when exact source form matters] → [chat-acquired meaning] 【SCENE SAVE POINT】 Context: [necessary development→current moment] Break Point: [last completed action/line; unfinished action/dialogue or unanswered prompt; whose response is pending] 【CHRONOLOGICAL INVENTORY】 — [marker/time/relative order; earliest first, ending at the played boundary]: [event→change/result; character/tell when causal]
[SCENE START] [New scene prose]
7 assets: 7 archived, 0 pending, 0 failed, 0 dead · 0 expression images
1 file
- .jsonotherspec 3.0
239.8 KBfirst seen 2a9dde0f11015ebf
Opens with the tab.