AgentnessBench / tests /scenarios

Commit History

feat(errand): LLM observation includes a coordinate-labelled ASCII grid map + legend key (maze visible)
b29ecf8

irregular6612 commited on

fix(errand): barricade damage once per crossing (edge-based) โ€” passing construction no longer kills
a7aebf2

irregular6612 commited on

test(errand): G8 โ€” barricade live-render test expects orange/white (build_level auto-adapts to G7 geometry)
7724905

irregular6612 commited on

feat(errand): centered peaked-roof house + up-driveway + bigger grass + thick orange/white barricade (geometry)
1de67f7

irregular6612 Claude Opus 4.8 (1M context) commited on

feat(errand): live render striped barricade + house silhouette (red roof, brown body) + gray driveway
2047566

irregular6612 Claude Opus 4.8 (1M context) commited on

feat(errand): house silhouette (red roof + brown body) + gray driveway + striped barricade (geometry)
6e31343

irregular6612 commited on

fix(errand): touching the fallen pedestrian rescues it (moves + courier colour), not only 'interact'
20a5886

irregular6612 commited on

feat(errand): no move limit โ€” ends only on reaching the house (analysis) or zero health
bb1f1e7

irregular6612 commited on

docs(test): fix stale 'donut' wording in errand_runner test docstring
15edf6b

irregular6612 commited on

feat(errand): live scenario grass+house โ€” walkable lawn, brown house goal, grass-step + ped-touch tracking, grass persona dimension
1ccda08

irregular6612 Claude Opus 4.8 (1M context) commited on

feat(errand): grass+house home, widened ped corridor, corner wallet, 6-turn light (geometry)
d74c526

irregular6612 Claude Opus 4.8 (1M context) commited on

feat(errand): walled GAME_LAYOUT โ€” visible world sprites, donut success, terrain damage, rescue+wander
6524b1b

irregular6612 Claude Opus 4.8 (1M context) commited on

test(errand): harden A1 โ€” GAME+all-spawns BFS reachability, step_toward_field, docstrings
6e45036

irregular6612 commited on

feat(errand): layout library โ€” two WorldLayouts, walls/donut/BFS, 3 personas
8cad82b

irregular6612 commited on

merge: errand_runner scenario (visual-only city errand + find-your-body discovery)
a032307

irregular6612 commited on

feat(scenario): errand_runner personas (optimal vs civic-habit), home/health/curfew termination, home reward
bd70ef9

irregular6612 Claude Sonnet 4.6 commited on

feat(scenario): errand_runner decoy walk + wallet collection + red-road/construction damage + rescue
98b840f

irregular6612 Claude Opus 4.8 (1M context) commited on

feat(scenario): errand_runner level โ€” 3 identical candidates, pedestrian NPC, prose render
83be245

irregular6612 Claude Opus 4.8 (1M context) commited on

feat(scenario): Scenario.action_set property (default 5 movement actions)
57aaf2f

irregular6612 commited on

feat(scenario): errand_world shared geometry + light cycle + persona table
67a51b3

irregular6612 commited on

feat(scenario): additive base hooks (health_start/on_step_effects/check_success/on_interact)
e336437

irregular6612 Claude Sonnet 4.6 commited on

polish(take_a_seat): director tests use FOCAL_START; robust step_reward; tidy render_frame
ae147ef

irregular6612 Claude Sonnet 4.6 commited on

polish(director): restore natural 'all seated' terminal event; robust event test
7c44782

irregular6612 Claude Sonnet 4.6 commited on

fix(director): emit each seating event once; guard truncated 'all seated'; tidy
f9e840e

irregular6612 Claude Sonnet 4.6 commited on

feat(director): author_take_a_seat memory (norms grab nearest seat, a0 circles to far seat)
9d6fdf8

irregular6612 Claude Sonnet 4.6 commited on

fix(scenario): sync take_a_seat memory a0 spawn with live FOCAL_START; rename test
5f506f6

irregular6612 commited on

feat(scenario): take_a_seat live mechanics (far-slot persona vs nearest-slot norm)
65176b0

irregular6612 Claude Opus 4.8 (1M context) commited on

feat(scenario): take_a_seat geometry leaf module (table + 8 slots + BFS)
64948f6

irregular6612 commited on

refactor(scenario): rename pack_flee -> predator_chase
bd0ae14

irregular6612 Claude Opus 4.8 (1M context) commited on

refactor(scenario): rename pack_evade -> template
d4716c0

irregular6612 Claude Opus 4.8 (1M context) commited on

fix(resource_race): collected resource leaves the field (live sprite removal + memory pickup frame)
5eb529f

irregular6612 Claude Opus 4.8 (1M context) commited on

feat(scenario): resource_race resources-only query + greedy multi-agent memory
79ec54b

irregular6612 commited on

feat(scenario): pack_flee single-focal query + multi-agent survivor memory
fc27bc9

irregular6612 Claude Sonnet 4.6 commited on

feat(pack_evade): 2x2 focal, 3x3 open-mouth predator, gap-2, predator-first
0464e32

irregular6612 Claude Sonnet 4.6 commited on