| Session | Turns | Tokens | Cost |
|---|
| Session | Status | Turns | Actions |
|---|
The Narrator and Character models produce the story text you read. The Session provider/model handles background work (summarization, action resolution) and is the fallback if either role model is blank.
Quantified trait vectors, dynamic psychological state, and action taxonomy for character AI.
Global defaults for engine controls. Per-session overrides inherit from these values when not explicitly set.
| Name | Size | |
|---|---|---|
| No models | ||
| On | Provider | Model | Context | In $/M | Out $/M | Stream | |
|---|---|---|---|---|---|---|---|
| Click "Refresh from AWS" to discover models | |||||||
Full backup: database, character images, config files. Saved to home directory.
/portal.html.
| Label | Status | Uses | Expires | Created | Actions |
|---|
| ID | Status | Created | Completed | Turns | Actions |
|---|
| Name | Description | Roles | Enabled | Actions |
|---|
| Model | Calls | Tokens | Cost |
|---|
Description
Guided workflow for human-likeness evaluation of AI actor behavior
Generate structured behavioral intelligence summaries from quantified character data
Describe what characters you want generated for this session. The AI will use the session description and location as context.
| Attribute | Description |
|---|
| Key Event | What | Who | When |
|---|
No character templates available.
Create character templates first using the "Characters" tab.
| # | Gender | Rough Age | Role | Profession |
|---|
Choose what happens to each character when this scenario is used.
Configure each side independently. Pick a session, source mode, model, and engine for left and right columns.
The Behavioral System replaces freeform prose-only character prompts with a structured, quantified approach. Characters gain numerical trait vectors, dynamic psychological state, and classified action intent — enabling more consistent, psychologically grounded behavior across turns.
Each character is scored 0–10 on: Warmth, Assertiveness, Composure, Honesty, Curiosity, Empathy, Impulsivity, Confidence, Deference, Resilience, Manipulativeness, Protectiveness.
Traits are derived automatically by the Character Sheet Digestor when characters are generated. Warmth is anchored to Disposition and Honesty to Moral Alignment for consistency.
Valence, Arousal, Anxiety, Defensiveness, Trust, Fatigue, Focus, Cognitive Bandwidth, Motivation — all 0–10, updated after every turn.
Updates are bounded: LLM-proposed deltas are clamped to ±2.0 per turn. The engine applies deterministic action-class effects, drains cognitive bandwidth under stress, and decays 10% toward baseline each turn to prevent runaway drift.
Every character response is classified into a strategic intent: disclose, conceal, appease, confront, deflect, withdraw, comply, resist, seek reassurance, moralize, intellectualize. This classification drives deterministic state effects and enables the two-call strategy to constrain prose generation.
| Mode | LLM Calls | Description |
|---|---|---|
| 1-Call | 1 | Action + action class + state delta in one JSON response. Fastest. |
| Hybrid | 1–2 | Starts as 1-Call; auto-escalates to 2-Call when anxiety > 7.5, defensiveness > 7.0, or cognitive bandwidth < 3.0. |
| 2-Call | 2 | Call 1 selects action class + state delta. Call 2 generates prose constrained by the selected class. Maximum control. |
Prompts are assembled in three layers optimized for LLM prefix caching:
Relationships between characters are scored on Trust, Affection, Respect, Fear, and Dependence (0–10) with a stance classification (neutral, ally, rival, etc.). The Relationship Resolver scores and selects the top-N most relevant relationships per turn based on character presence, narrative mentions, and extreme values.
The system is gated behind Enable Behavioral System (default off). When disabled, the existing monolithic prompt path is used unchanged. Enabling it activates trait vectors, dynamic state tracking, action taxonomy, and the layered prompt builder for all new sessions.
Override specific character traits for this session only. Leave fields empty to use the base value.