NPC actions
Two questions per exchange, both asked to TypeSafe's Jev (a typed-judgment model: it returns one choice from
a fixed set, with a probability, in ~0.1 s; key TYPESAFE_API_KEY, https://docs.typesafe.ai):
- Before the reply (in parallel with the LLM): is the player giving an order? "Take your shirt off", "get on your knees", "give me a hug", "run". If Jev picks an action with ≥ 0.6 probability, it's an order: the NPC does it, and the LLM writes the line again knowing "you're right now", so they grumble or joke while they comply instead of refusing. Costs ~0.1 s more, only then.
- After the reply (in parallel with the voice): what does their mood call for? From the player's words and the NPC's reply, pick the action, or none.
The catalog (examples/gta-v/mod/ActionCatalog.cs)
Each action has a name, a description Jev reads, and the probability Jev must reach before it happens:
| Action | Min. probability | Notes |
|---|---|---|
| none | - | just talk: most exchanges |
| slap, punch, facepalm, square_up, threaten_gun, hug, kiss | 0.45 | |
| headbutt, shirt_off (men), pants_off (to underwear), bend_over, kneel_beg | 0.5 | |
| shoot, run_away | 0.6 | need real certainty: they end the conversation |
| middle_finger | 0.7 | Jev picks it a lot, so it needs more |
- Thresholds per action, not one global cut-off: tune the ones that fire too often upward.
- Cooldown: the same NPC doesn't repeat an action within 60 s unless ordered to.
- Descriptions are the prompt. Write when it applies ("only when the reply clearly means killing them right now"), not just what it is.
- Gender rules (men only) and content rules (underwear stays on) live in code, not in the prompt.
Mapping to the game (NpcActions.cs)
- Each name maps to candidates: animation dictionary + clip, a task (flee, fight), or a clothing swap. Check
every candidate exists when the mod loads and log what was found (
action anims:); fall back to the next. - Play the action while the line is spoken, aimed at the player (or at whoever the scene says).
- A director or scripted scene can pin an action (
do: kneel_beg) to skip the picker.
Test it
npcvoice-check actions (GTA example) runs 25 exchanges through Jev, 10 of them orders, and checks each pick
(25/25 expected). In game, dev mode's PgUp/PgDn pick an action and End makes the target do it, to check the
animation without a conversation.
Without Jev
A second LLM call with a JSON schema works, but it's slower (0.3-1 s) and its "confidence" isn't calibrated, so thresholds are guesswork. Whatever picks, keep the shape: a fixed set, a probability, per-action thresholds, orders checked first.
