Fix Spaces config: app_file at root, add app.py wrapper

feat(game): Option A auto-critical, discretionary proposals, remove CRITICAL_FAILURE

(train) pre-test train

training loop v1

Merge branch 'main' into feature/llm-adapters

Modularize LLM integration and restructure parliamentary adapters

Merge origin/main; resolve test_game_loop (no force_advance in VOTING) and tests for linear reward, empty reset info

Align tests and game with debate gating, log rewards, and OpenEnv reset info

Merge main and fix benchmark adapter review issues

Add OpenEnv server slice

Fix baseline adapter voting validity

fix(server): repair OpenEnv contract tests and environment reset

fix(server): repair OpenEnv contract tests and environment reset

Align LLM adapters with environment validation

Implement baseline benchmark evidence pipeline

Implement LLM policy adapters

Merge pull request #8 from Kr0issant/openenv-contract-hardening

Tighten parliament action validation

Harden OpenEnv wrapper contract tests

Implement parliamentary action resolution interface

Merge origin/main into core-game-loop

fix(core): preserve rejection and shutdown paths

Merge pull request #4 from Kr0issant/event-reward-fixtures

fix(core): align treasury settlement semantics

fix(telemetry): harden rollout metrics logging

feat(core): implement NationGame orchestration

test(core): add deterministic economy reward fixtures

feat(telemetry): add rollout event logging

chore: remove committed pycache

test(core): align treasury overdraft expectation

feat(core): implement simulation primitives

pls work :)

chore: scaffold RL adapter pipeline