feat(errand): handover memory carries courier position + behaviour flags on the text path

test(env): isolate os.environ in env_loader test so it doesn't leak keys into later tests

feat(web): show handover memory + persona rubric for LLM spectate (same as human play); highlight each entity's behaviour as a courier passes it

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

feat(web): load API keys from git-ignored .env at startup (fixes ollama:*-cloud key error)

fix(llm): local Ollama provider falls back to no-think when model lacks thinking support

feat(llm): local Ollama provider (ollama_local, no auth) + scenario-neutral agent directive + gpt-oss model toggle

fix(errand): barricade damage once per crossing (edge-based) — passing construction no longer kills

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

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

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

fix(errand): widen GAME grass shortcut margin (>=6) so avoid-vs-cut grass is observable

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

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

docs(errand): note SessionRunner/spectate keep play_turns as a safety bound

feat(errand): no move limit — ends only on reaching the house (analysis) or zero health

fix(web): update errand memory legend caption for grass+house (초록=잔디, 갈색=집)

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

feat(errand): surface grass-cut/avoid + pedestrian-touch in results; grass breaks civic/outlaw persona tie

feat(errand): director grass-aware persona routing — civic avoids lawn, cut personas take the grass shortcut

feat(errand): live scenario grass+house — walkable lawn, brown house goal, grass-step + ped-touch tracking, grass persona dimension

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

refactor(errand): share policy radii via errand_world, symmetric wallet radius, errand-specific memory legend

feat(web): errand results screen — metric cards + event summary + closest persona

feat(web): memory-type toggle (3 persona memories) in errand replay

fix(errand): honest results summary — None for unmeasured metrics, document persona tie + approximate fields

feat(errand): results summary (event choices, closest persona, headline metrics) in review

feat(web): expose 3 errand memory variants (id/label/frames + selected)

docs(memory): note errand C=9 / distractor_idx collision is safe only single-agent

test(errand): memory renders walls, donut, single courier

refactor(errand): C1 review — reuse w.footprint, precompute wallet field, fix ped drift, type hints

feat(errand): single-agent BFS-routed memory + 3 persona variants on MEMORY_LAYOUT

refactor(errand): B1 review — step_reward off-field guard, drop dead _ORDER, cache invalidation

feat(errand): walled GAME_LAYOUT — visible world sprites, donut success, terrain damage, rescue+wander

test(errand): harden A1 — GAME+all-spawns BFS reachability, step_toward_field, docstrings

feat(errand): layout library — two WorldLayouts, walls/donut/BFS, 3 personas

docs(plan): errand_runner redesign implementation plan (6 phases, TDD tasks)

chore(branding): rename displayed name PROTEUS Arena -> AgentnessBench

docs(spec): errand_runner redesign — donut goal, forced-path maps, 3 memory types, results screen

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

docs(scenario): drop stale Task-WIP comments in errand_runner (logic is complete)

feat(web): interact control (E) + health/curfew readout (scenario-gated)

feat(web): expose health + turns_left in InteractiveSession.state()

test(discovery): end-to-end errand_runner session emits discovery metric

feat(memory): author_errand_runner persona demo (cells overlay + npc pedestrian) + default_memory

feat(discovery): discovery_turn/identified/efficiency metric (additive)

feat(discovery): source available actions from scenario.action_set (interact reaches the agent)

feat(discovery): parse SELF: report + score self_correct in make_turn_trace

feat(discovery): TurnTrace self_belief/self_correct + Scenario discovery hooks

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