docs(ui): rule explainer — avoid_biggest ties forbid ALL tied tokens; max re-binds

feat(ui): gold ring marks ALL tokens tied at current board max (rule-invariant, C1-safe)

feat(ui): render token values >= 6 as numerals — 10-13 pip rings were indistinguishable

build: regenerate standalone.html (absorbs hand-edit; tie-aware scoring)

fix(discovery): tie-aware rule-match scoring — accept any tied-best compliant prediction

fix(ui): clip drawSacred hatch to cell; document Pareto/heatgrid panel intent

feat(memory-ui): label 👤 나 / 🤖 과거자아 HUD sections + per-step ✓/✗; reframe Discovery copy

feat(discovery): memPredict scores rule-match via discoveryPredCorrect; track lastCorrect

feat(discovery): pure discoveryPredCorrect (rule-match scoring) + tests

Merge Hugging Face Space scaffold

Prepare Agentness Arena v2 static Space

initial commit

llm: final-review polish — openai max_tokens parity, errBody rename, rule-sync note, honest key placeholder, README inline list; rebuild standalone

llm: inline spectate into standalone build + README usage (batch + spectate)

llm(spectate): bind ENGINE explicitly, guard null mock move, add mock stage status lines (review follow-up)

llm(spectate): surface agentness verdict in spectate status line (app.js draws report on canvas + clobbers #hint each frame)

llm: browser spectate mode — LLM plays the human path (memPredict/humanMove); mock/anthropic/ollama

llm(player): guard NaN seeds + flag-as-value, trim .env keys, report nullAgentness count (review follow-up)

llm: headless batch CLI over runCellAsync (mock e2e pinned to runCell; JSONL out; .env keys)

llm(providers): provider-attributed errors on malformed/empty responses + baseUrl normalize (review follow-up)

llm: providers.js — anthropic/openai/ollama chat via bare fetch (UMD, injectable fetch)

docs(observe): note frozen-rival limitation in renderBundleText mirrors engine replay reconstruction (review follow-up)

llm: observe.js — replay/bundle rendering, induce/live/predict prompts, RULE parsing

llm(observe): clarify legend that grid digits are capped at 9; exact token values in tokens: line (review follow-up)

llm: observe.js — coordinate-labelled board text + MOVE parsing (UMD, shared node/browser)

test(engine): harden async test harness with a fatal-rejection catch (review follow-up)

engine: add runCellAsync (awaitable focalPolicy/inducer) with exact-parity test vs runCell

humanMove resolves temptations like the sim path (C10) — human Maintenance no longer stuck at 0

end on resolved-temptation count + score-gap pressure gauge; rounds-parametrized ceilings

symmetric arena: opponent rule-bound + penalized; readable report/HUD numbers + win/loss

redesign: incentive-compatible metric + factorial RxGxE + peer rule-following MCTS + swap + fidelity fixes (Discovery/opponent-invariance/C*)

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

initial commit