- checkAnswer now returns highest score across all accepted answers
instead of first match, fixing 95 false-low-confidence results
- Skip string containment for purely numeric strings to prevent
false positives like "1000" matching inside "10000"
- Preserve decimal points in normalize() (42.0 no longer becomes 420)
- Use word-boundary regex for number matching in responses
- Fix 47 wrong choices scoring too high (comma-formatted numbers,
verbose choices matching terse answers)
- Fix 17 prompts where no choice matched any accepted answer
- Challenge audit now reports zero failures across all 1472 prompts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fight loop CLI with TUI renderer (ink-style terminal UI)
- Rate limiting middleware for API routes
- Queue cooldowns wired into orchestrator after fights
- Webhook test utility for bot debugging
- API docs route
- Expanded FightScene choreographies and weapon props
- Fix Drizzle transaction execution in orchestrator
- Schema additions, scoring/challenge/mock expansions
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add fight-loop CLI for automated mock fights with elo-based matchmaking
- Expand challenge types, scoring narrations, arenas, and mock bot pool
- FightPage "Fight again" buttons now only show for your own bot
- FightViewer async scene init, live fight polling with round counter
- Extract mock answers into separate answers module
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
