docs: SCENARIO_REVIEW.md — prioritized improvement plan with LOE (#7)

docs: per-scenario closer-look checklist distilled from #1 and #2

docs: SCENARIO_QUALITY note on mapgen/botgen YAML knobs (#30)

botgen: surface scripted opponents for YAML; drop premature capture_actor

P1: fail_conditions + new longhorizon scenario

mapgen: surface map generator for YAML (base_map generator spec)

win-speed bonus: record + reward how fast a model wins

tests: tech-production-planning pack — full Rust loop

#2 hard: set base_map INSIDE overrides so it actually uses scout-arena

#2 hard: per-waypoint search BAND in the relative objective

#2: enforce ordered waypoints (stateful waypoint_sequence) + two-path medium + scouted hard

action-sequenced-execution: timeout/attrition overrun is a LOSS, not a draw

hard: enemy_building_spotted interrupt closes the coordinate-blind feedback loop

hard: anchor relative objective on the named enemy building type per direction

tech-production-planning pack: canonical Family 2 (Sequential Dependency Planning)

action-multiunit-coordination hard: spatial-grounding via relative-direction objective

prompt_v2: sanitize confusing 'Buildings: ? ()' briefing line

action-multiunit-coordination medium: disperse the 3 regions (multi-vector)

Default spawn_mcvs:false — stop engine auto-seeding phantom MCVs

playback: append a terminal 'episode end' frame (the resolved win/loss board)

Fix action-multiunit-coordination: enforce split, binding deadline, real fail

De-dup: consolidate aimless scenario duplicates (24→21 active)

HTML scenario catalog + clearer custom-map-no-enemy descriptions

Clarity pass: plain, self-explanatory titles for all 23 active packs

Scenario configs (level+fog per cell) + adversarial-duel duel/interrupts + clearer names

run_eval: --or-provider parses provider/quant correctly

run_eval: --or-provider (pin OpenRouter provider/quant, no fallback) + --fog-mode CLI

Structured-fog text mode, premium routing, codex descriptions, minimap colour-by-difficulty

codex: document the trailing movement/role column in the header

prompt_v2: strip ASCII minimap from the briefing (training parity)

playback: save the SAME _minimap_v2 the model receives (fog-accumulating) — viewer now shows exactly what the model saw, not the legacy matplotlib render

test: pin run_id in whole-result determinism test (wall-clock label, not part of contract)

Wire bench to vendored training prompt v2 (system/briefing/minimap)

Vendor training prompt/briefing/minimap v2 (byte-identical)

Training-parity minimap (real terrain + legend) + viewer (system/thinking/debrief)

Live-smoke fixes: tool-call wire 400, episode resilience, real PNG minimap

run_eval: dependency-free .env autoload for the API key

game_knowledge: glossary scope also covers win/fail-named codes

Deterministic scenario-scoped game knowledge + explicit objective

Strategy packs: faithful 'destroy key economic buildings' objective

S8: capture_actor tool schema + dispatch; wildcard count 21->22

Hard-tier curation: action/perception/reasoning/strict/rush-hour + exhaustive classification

Hard-tier curation: Art-of-War quartet

Hard-tier curation: adversarial family (skirmish, siege)

Hard-tier curation: seed-driven spawn variation (exemplar + invariant)

Curate: remove the auto-generated cat-* corpus

Eval resilience layer for real OpenRouter runs

Scenario hygiene: quarantine redundant cat-* + harvest packs

Art-of-War long-horizon family: sacrifice/detour, delayed credit

Strict-action-API family: spec fidelity as the objective