- Core engine: simulator, game mechanics, triggers (138 tests) - Fog-of-war per-player state tracking - Meeting flow: interrupt, discussion, voting, consolidation - Prompt assembler with strategy injection tiers - LLM client with fallbacks for models without JSON/system support - Prompt templates: action, discussion, voting, reflection - Full integration in main.py orchestrator - Verified working with free OpenRouter models (Gemma)
30 lines
769 B
YAML
30 lines
769 B
YAML
# Trigger Definitions
|
|
# Each trigger type and its default behavior
|
|
|
|
mandatory:
|
|
# These always fire, cannot be muted
|
|
- DISCUSSION_START
|
|
- VOTE_START
|
|
- GAME_START
|
|
- GAME_END
|
|
- SABOTAGE_CRITICAL # O2/Reactor timer below 10s
|
|
|
|
standard:
|
|
# On by default, but can be muted by agent
|
|
- BODY_IN_FOV
|
|
- PLAYER_ENTERS_FOV
|
|
- PLAYER_EXITS_FOV
|
|
- VENT_ACTIVITY_NEARBY
|
|
- REACHED_DESTINATION
|
|
- TASK_COMPLETE
|
|
- SABOTAGE_START
|
|
|
|
optional:
|
|
# Off by default, agent must subscribe
|
|
- EVERY_N_SECONDS # Polling backup
|
|
- INTERSECTION # Path decision points
|
|
- NEAR_TASK # Approaching assigned task
|
|
- PLAYER_NEAR_ME # Within specified distance
|
|
- ROOM_ENTER # Someone enters your room
|
|
- ROOM_EXIT # Someone leaves your room
|