SOCEnv / inference.py

Commit History

  1. Final Hardening: Add 'score=' to [END] log and implement stderr reward auditing

    557040d
  2. Harden reward boundaries: Shift from [0.01, 0.99] to safer [0.05, 0.95] to avoid potential validator threshold issues

    d66a82a
  3. Fix stdout formatter rounding rewards to 1.00 in Edge Cases

    8697558
  4. Refactor error sanitization

    2df97ec
  5. Add heuristic fallback agent to inference.py to handle LLM API failures gracefully

    a34321e

  1. Fix edge-case explicitly emitting 0.00 rewards on LLM failure in inference.py

    035ee09
  2. Add app.py and YAML configuration

    6edd399

  1. Initial commit for AI SOC Gym Hackathon submission

    cf8e53a