fix: query budget 500, sync all hardcoded refs across codebase

feat: playground all-fields-visible grid, loop detection, 200 query budget

fix: brutal audit — reset tool_call_counts, date dedup, unused vars, playground overhaul with scenario picker + status dashboard

fix: render placeholders in reset observation message

fix: python 3.11 f-string compat, inference OPENENV_BASE_URL fix, README action/observation spaces

feat: investigation-grade overhaul + procedural generation

fix: auto-grade on budget exhaustion + max steps, no more 0.01 dead scores

feat: eu ai act compliance auditor — mcp-based openenv environment