rewrite readme

fix: add score= to END output, clamp to (0.01, 0.99)

fix: use HF_TOKEN as api_key per hackathon spec, fix END format

fix: use os.environ for API_KEY and API_BASE_URL, remove dummy fallback

fix: use GenericAction(**kwargs) instead of positional dict arg

fix: emit structured START/END output even when env connection fails

fix: run all 7 tasks with per-task START/END logging, match reference format

fix: add has_grader: true to all tasks for evaluator grader check

fix: test LLM proxy call before env connection to ensure proxy usage

fix: prioritize API_KEY over HF_TOKEN for LLM proxy, fail loudly on first call

fix graders

fix inference final

fix get model_messages

fix: api key as first priority

fix graders

fix: inference format

fix: inference

fix inference format

chore: trigger cache refresh

fix: add YAML frontmatter to README

minor changes

minor changes

Minor fixes

fix: track uv.lock for openenv validate compliance

inference format fix

minor changes

Major fixes

task 6 and 7 made hard

chore: remove AI planning artifacts and junk files from repo

fix: remove parametric fallback from simulation.py, clean baseline table

fix: clean repo for hackathon submission

HF deploy

Made improvments

feat: harden Task 5 grader + fix inference.py for hackathon submission

fix: root to dashboard

fix: add demo and inference.py

update readme

update readme

improved huristic

fix: dashboard, debug logs

updates docs

docker size reduced

LLM scores added

Real training curves added

Task 7 added

Major fixes + gap fixes

Remaining task added + full openenv compliance

Version 1