Fetching metadata from the HF Docker repository...
-
feat: run easy/medium/hard sequentially with START/END logs
TanujInsane
-
fix: use task difficulty ID in [END] line for task validation
TanujInsane
-
fix: LLM budget + keyword fallback + num_episodes=1 + closure bug fix
TanujInsane
-
fix: use AgentGrader directly instead of HTTP calls
TanujInsane
-
fix: clip score to (0.05, 0.95) to avoid exact 0.0 or 1.0
TanujInsane
-
fix: track actual steps for accurate score calculation
TanujInsane
-
fix: run 3 difficulties with 10 steps each for task validation
TanujInsane
-
fix: add LLM classification via API_BASE_URL and API_KEY
TanujInsane
-
fix: add wait_for_server and remove sys.exit(1)
TanujInsane
-
fix: use HF Space URL in inference.py, not localhost
TanujInsane
-
fix: add required [START]/[STEP]/[END] structured output to inference.py
TanujInsane
-
fix: add wait_for_server retry loop for phase 2
TanujInsane
-
Update inference.py retry loop for server connection
TanujInsane
-
fix: update inference.py with API_BASE_URL and HTTP client format
TanujInsane