Commit History

  1. feat: run easy/medium/hard sequentially with START/END logs

    TanujInsane
    6e39a51
  2. feat: richer grader output object

    TanujInsane
    9260b23
  3. fix: add grader field to all 3 tasks in openenv.yaml

    TanujInsane
    a2d30b7

  1. fix: use task difficulty ID in [END] line for task validation

    TanujInsane
    cfd8bf6
  2. fix: LLM budget + keyword fallback + num_episodes=1 + closure bug fix

    TanujInsane
    6cfc309
  3. fix: use AgentGrader directly instead of HTTP calls

    TanujInsane
    e7e59dd
  4. fix: clip score to (0.05, 0.95) to avoid exact 0.0 or 1.0

    TanujInsane
    b06dcfb
  5. fix: track actual steps for accurate score calculation

    TanujInsane
    581ad49
  6. fix: run 3 difficulties with 10 steps each for task validation

    TanujInsane
    19d3a15
  7. fix: add LLM classification via API_BASE_URL and API_KEY

    TanujInsane
    e263f9c

  1. fix: add wait_for_server and remove sys.exit(1)

    TanujInsane
    676fd8d

  1. fix: use HF Space URL in inference.py, not localhost

    TanujInsane
    3a86e09
  2. fix: add required [START]/[STEP]/[END] structured output to inference.py

    TanujInsane
    860a4b8
  3. fix: remove gradio to resolve websockets conflict with openenv-core

    TanujInsane
    d558bd3
  4. fix: upgrade gradio to 4.44.1 and remove conflicting websockets/httpx pins

    TanujInsane
    4e9573d
  5. fix: pin dependencies to stop pip backtracking during Docker build

    TanujInsane
    0a77131
  6. fix: use openenv-core 0.2.3 (0.3.0 does not exist on PyPI)

    TanujInsane
    7aed237
  7. Fix 500 error on /reset and manually implement FastAPI endpoints for grader compatibility

    TanujInsane
    25a7357
  8. fix: add gradio to requirements

    TanujInsane
    2e051b6
  9. Revert "Fix missing dependencies and app.py consistency"⁠

    TanujInsane
    b8c1416
  10. Fix server/app.py entrypoint for Phase 1 compatibility

    TanujInsane
    4d10011
  11. Fix missing dependencies and app.py consistency

    TanujInsane
    62c1df2
  12. fix: add wait_for_server retry loop for phase 2

    TanujInsane
    53c6dcf
  13. Update inference.py retry loop for server connection

    TanujInsane
    1b64cdd

  1. fix: update server/app.py imports and Dockerfile CMD

    TanujInsane
    847096d
  2. fix: add proper server/app.py with main() and __name__ guard

    TanujInsane
    3687a02
  3. fix: add uv.lock and server/app.py for openenv validate

    TanujInsane
    b1dec00
  4. Change Dockerfile CMD to uvicorn

    TanujInsane
    1c58b85
  5. Add recursive JSON sanitizer and wrap JSONResponse payloads

    TanujInsane
    46d7b20
  6. Restore env instantiation and add robust try-except error handling

    TanujInsane
    83330fe
  7. Completely secure /reset logic avoiding any external env calls

    TanujInsane
    9ba83b5
  8. Fix POST /reset internal server error by using Pydantic BaseModel and handling empty body safely

    TanujInsane
    8380751
  9. Allow /reset endpoint to accept GET requests to prevent 404

    TanujInsane
    44c118c
  10. Add fastapi and uvicorn to requirements

    TanujInsane
    f5d5fe3
  11. Fix server module dependency with a simple, native FastAPI app

    TanujInsane
    d399a8c
  12. Remove Gradio UI and transition to pure FastAPI server for HF Space

    TanujInsane
    e6d5b30
  13. Fix LogisticRegression multi_class error

    TanujInsane
    cdd19a1
  14. fix: remove train_rl import to fix HuggingFace runtime error

    TanujInsane
    d13f865
  15. chore: update dependencies in requirements.txt

    TanujInsane
    de62d8b
  16. fix: restore completely original constants.py and clean agent.py imports

    TanujInsane
    7ff371f
  17. fix: resolve broken imports and add CATEGORY_KWORDS

    TanujInsane
    c11cb65
  18. fix: update constants.py with new CATEGORIES definition

    TanujInsane
    4054ee7
  19. fix: change Dockerfile CMD to run app.py

    TanujInsane
    1e5d94c
  20. chore: add hugingface spaces frontmatter to README

    TanujInsane
    f5d5ab8
  21. fix: update inference.py with API_BASE_URL and HTTP client format

    TanujInsane
    99d66ea
  22. fix: deploy updates, add inference.py and /reset /step endpoints

    TanujInsane
    49234f8

  1. fix: pin starlette<0.37.0 to fix gradio 4.44.0 incompatibility with jinja2 template rendering

    TanujInsane
    7bc80a8
  2. fix: downgrade jinja2 to 3.1.3 to fix runtime error parsing gradio routes in starlette

    TanujInsane
    9aecb16
  3. fix: pin jinja2 to 3.1.4 for gradio 4.44 compatibility

    TanujInsane
    ca6e3ff
  4. fix: pin scikit-learn<1.6.0 because of multi_class argument removal

    TanujInsane
    c4b8016