Spaces:
Sleeping
Sleeping
Commit History
-
fix: rename rewards= to score= and add task= to END block in stdout for proper validator parsing
Abhishek Tiwaric11d056 -
fix: strictly output [START], [STEP], [END] to stdout for phase 2 validator parsing
Abhishek Tiwariebcd8b6 -
fix: restore UI, add /tasks /grade, clamp scores to (0.05, 0.95)
Abhishek Tiwari6d2ec98 -
Massive Rewrite: Rebuilt Phase 2 standalone validation constraints perfectly mapped to 0.05-0.95
Abhishek Tiwarie0a6d43 -
Fix inference.py output format to strictly match Step/End validation criteria per task
Abhishek Tiwari755655b
-
hf done
root9496a0e -
hf
root38819be
-
good to go
root14de67e -
feat: implement SQL agent environment with OpenEnv integration, SQLite management, and automated task grading
root9b9c562