Commit History

  1. feat: reward verifier alignment, notebook hardening, model name fix⁠

    CreativeEngineer +1: Claude Opus 4.6
    cdc237b
  2. refactor: replace unsloth with plain transformers+peft for GRPO training⁠

    CreativeEngineer +1: Claude Opus 4.6
    3313e24
  3. feat: add verifier-native reward v1

    2fccde8
  4. feat: upgrade notebook to Qwen3.5-4B with H100 hyperparams⁠

    CreativeEngineer +1: Claude Opus 4.6
    2cb6617
  5. docs: align training workflow and plan ssot

    e8e5af5
  6. refactor: align colab notebook with shared llm helpers

    ddcb837
  7. feat: make llm training workflow low-fidelity only

    9c3599b
  8. fix: align notebook evaluation with grpo rewards

    8254ade
  9. fix: robust JSON array extraction and notebook GRPO fixes⁠

    CreativeEngineer +1: Claude Opus 4.6
    e826e11
  10. docs: clarify notebook surfaces and OpenEnv guidance

    2348d3e
  11. feat: polish notebook and README for hackathon submission⁠

    CreativeEngineer +1: Claude Opus 4.6
    c647aa0
  12. feat: add HF Space deployment + GRPO training notebook⁠

    CreativeEngineer +1: Claude Opus 4.6
    3bfd80a
  13. docs: codify multifidelity training policy

    513a2e2
  14. feat: add replay playtest and tighten fail-fast validation

    8bf0155
  15. docs: require trained policy evidence

    27d58b3
  16. docs: clarify notebook artifact requirement

    d22b376
  17. docs: fix p1 parameterization blocker fallout

    acb992c
  18. docs: mark northflank smoke pass

    3f7be89
  19. feat: add northflank smoke workflow

    78463b7
  20. docs: sync status trackers to verifier state

    ba716cf
  21. docs: lock p1 plan and hackathon runtime setup

    5354ca9