Apr 25

1. 16:06

   Update Red/Blue showdown behavior and refresh Qwen benchmark artifacts.⁠

   Viraj
   f4ce885
2. 15:26

   refactor: enhance type safety in inference and evaluation scripts; update pyright config to exclude specific directories

   Viraj
   2780361
3. 15:14

   refactor: enhance type safety in inference and evaluation scripts; update pyright config to exclude specific directories

   Viraj
   e40ec5e
4. 13:47

   feat: improve blue showdown runtime context⁠

   Viraj
   c4730ff
5. 11:27

   feat: add red reasoning metadata⁠

   Viraj
   6947df8
6. 11:14

   feat: harden environment integration⁠

   Viraj
   ef2c8af
7. 11:03

   feat: add dense red reward scoring⁠

   Viraj
   027331e
8. 10:50

   feat: add blue defender curriculum⁠

   Viraj
   a0cce81
9. 10:29

   feat: add raw bash red agent access⁠

   Viraj
   5d7586e
10. 10:19

    feat: port WarGames phase 0 environment⁠

    Viraj
    20eb0ca