feat: training results page + SFT Colab notebook

Add pre-training audit scripts, OpenEnv manifest, and tune Parlay training/env (GRPO 1.5B default, min-reward filters, weighted data gen, hiring ZOPA+drift, veteran/opponent prompts, Docker/docs)

feat: flash-lite for data-gen and flash for UI; remove training page; card tests; --quiet data gen; data/ inspect path; random baseline; GRPO env wrapper; reward fixes (buyer ZOPA, ToM signals); drift + Brier metrics; Bayesian ToM module

fix: move global declarations before first use (grpo_train, call_gemini)

feat: backup existing data + per-episode progress tracking + gemini live-call verification

fix: upgrade gemini model string to 2.5-flash-lite + add tom diagnostic script

fix: gemini retry backoff + tom belief diagnostic logging

feat: streamline parlay for demo mode and add spectator negotiation mechanics

feat: split Gemini 2.5 Flash (demo) and Flash-Lite (data), SFT threshold 0.3, favicon + check_gemini

fix: fixed UI bugs, keyless testing initiated

refactor(agent): migrate Gemini client from google-generativeai to google-genai

feat: project setup