Fetching metadata from the HF Docker repository...
-
feat: run easy/medium/hard sequentially with START/END logs
TanujInsane
-
feat: richer grader output object
TanujInsane
-
fix: add grader field to all 3 tasks in openenv.yaml
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: remove gradio to resolve websockets conflict with openenv-core
TanujInsane
-
fix: upgrade gradio to 4.44.1 and remove conflicting websockets/httpx pins
TanujInsane
-
fix: pin dependencies to stop pip backtracking during Docker build
TanujInsane
-
fix: use openenv-core 0.2.3 (0.3.0 does not exist on PyPI)
TanujInsane
-
Fix 500 error on /reset and manually implement FastAPI endpoints for grader compatibility
TanujInsane
-
fix: add gradio to requirements
TanujInsane
-
Revert "Fix missing dependencies and app.py consistency"
TanujInsane
This reverts commit 62c1df2b2df0ca96d7522123e4c7500178c53f7d. -
Fix server/app.py entrypoint for Phase 1 compatibility
TanujInsane
-
Fix missing dependencies and app.py consistency
TanujInsane
-
fix: add wait_for_server retry loop for phase 2
TanujInsane
-
Update inference.py retry loop for server connection
TanujInsane
-
fix: update server/app.py imports and Dockerfile CMD
TanujInsane
-
fix: add proper server/app.py with main() and __name__ guard
TanujInsane
-
fix: add uv.lock and server/app.py for openenv validate
TanujInsane
-
Change Dockerfile CMD to uvicorn
TanujInsane
-
Add recursive JSON sanitizer and wrap JSONResponse payloads
TanujInsane
-
Restore env instantiation and add robust try-except error handling
TanujInsane
-
Completely secure /reset logic avoiding any external env calls
TanujInsane
-
Fix POST /reset internal server error by using Pydantic BaseModel and handling empty body safely
TanujInsane
-
Allow /reset endpoint to accept GET requests to prevent 404
TanujInsane
-
Add fastapi and uvicorn to requirements
TanujInsane
-
Fix server module dependency with a simple, native FastAPI app
TanujInsane
-
Remove Gradio UI and transition to pure FastAPI server for HF Space
TanujInsane
-
Fix LogisticRegression multi_class error
TanujInsane
-
fix: remove train_rl import to fix HuggingFace runtime error
TanujInsane
-
chore: update dependencies in requirements.txt
TanujInsane
-
fix: restore completely original constants.py and clean agent.py imports
TanujInsane
-
fix: resolve broken imports and add CATEGORY_KWORDS
TanujInsane
-
fix: update constants.py with new CATEGORIES definition
TanujInsane
-
fix: change Dockerfile CMD to run app.py
TanujInsane
-
chore: add hugingface spaces frontmatter to README
TanujInsane
-
fix: update inference.py with API_BASE_URL and HTTP client format
TanujInsane
-
fix: deploy updates, add inference.py and /reset /step endpoints
TanujInsane
-
fix: pin starlette<0.37.0 to fix gradio 4.44.0 incompatibility with jinja2 template rendering
TanujInsane
-
fix: downgrade jinja2 to 3.1.3 to fix runtime error parsing gradio routes in starlette
TanujInsane
-
fix: pin jinja2 to 3.1.4 for gradio 4.44 compatibility
TanujInsane
-
fix: pin scikit-learn<1.6.0 because of multi_class argument removal
TanujInsane