Hugging Face's logo

Spaces:
DeepikaChintamreddy
/
config-debug-env
Sleeping

App Files Community
config-debug-env

Commit History

  1. fix: eliminate all 0.0 reward values across all files

    Deepikachintamreddy
    bc98e17

  2. fix: progress_ratio default 0.01

    Deepikachintamreddy
    b1c5449

  3. fix: total_reward init 0.01

    Deepikachintamreddy
    3ca9f73

  4. fix: remove function aliases from grader_api, classes only, NaN protection

    Deepikachintamreddy
    d500ed3

  5. fix: grader classes with grade() method per Meta feedback

    Deepikachintamreddy
    b5751d2

  6. fix: model defaults 0.01 not 0.0

    Deepikachintamreddy
    c8197e5

  7. fix: initial previous_reward 0.01 not 0.0

    Deepikachintamreddy
    991b3a8

  8. fix: reset reward 0.01 not 0.0

    Deepikachintamreddy
    f198438

  9. fix: grader handles all call patterns, reset reward 0.01

    Deepikachintamreddy
    b17299b

  10. fix: class-based graders with grade() method per Meta instructions

    Deepikachintamreddy
    b5fc338

  11. fix: bulletproof graders - never throw, always return float in range

    Deepikachintamreddy
    5b5379b

  12. fix: grader_api returns float only, not tuple

    Deepikachintamreddy
    e421a0a

  13. fix: correct step format, per-task output, tuple grader returns

    Deepikachintamreddy
    c7b11e5

  14. FINAL: emit per-task START/END blocks for validator task counting

    Deepikachintamreddy
    529657f

  15. fix: clamp inference.py scores to (0.001, 0.999) strictly

    Deepikachintamreddy
    8401a46

  16. add POST /grader endpoint for validator

    Deepikachintamreddy
    5e04bd7

  17. trigger rebuild

    Deepikachintamreddy
    fba04fa

  18. fix: resolve merge conflict in grader_api.py

    Deepikachintamreddy
    b53b055

  19. Fix formatting in openenv.yaml

    Chintamreddy Deepika
    Unverified signature
    4662d81

  20. Refactor graders to use clamping wrapper

    Chintamreddy Deepika
    Unverified signature
    16b042a

  21. Update grader_api.py

    Chintamreddy Deepika
    Unverified signature
    7289a7e

  22. Update app.py

    Chintamreddy Deepika
    Unverified signature
    99b0783

  23. Update env.py

    Chintamreddy Deepika
    Unverified signature
    495f412

  24. Update openenv.yaml

    Chintamreddy Deepika
    Unverified signature
    1bb2ce7

  25. CRITICAL FIX: Add missing grader_api.py

    Deepikachintamreddy
    8ad450c

  1. SIMPLIFY: Override /reset to create fresh environment directly, avoiding original endpoint call

    Nanda Kumar Kondreddy
    cf3a550

  2. FIX: Properly type request parameter in /reset endpoint as fastapi.Request

    Nanda Kumar Kondreddy
    a91aa82

  3. CRITICAL FIX: Replace /reset middleware with direct endpoint override - ensure base fields included

    Nanda Kumar Kondreddy
    f2a42f5

  4. ENHANCE: Update reset middleware to include base Observation fields (done, reward, metadata) at top level

    Nanda Kumar Kondreddy
    270a32f

  5. FIX: Add middleware to correct /reset response schema - add 'info' field, remove reward/done

    Nanda Kumar Kondreddy
    5bc98e9

  6. FIX: Remove incorrect action wrapper in HTTPEnvClient.step() - POST body must be direct ConfigDebugAction, not nested

    Nanda Kumar Kondreddy
    9f8c7b6

  7. Add comprehensive instrumentation to all graders for validator diagnostic

    Nanda Kumar Kondreddy
    4891046

  8. Fix OpenEnv API step payload format - wrap action in action key

    Nanda Kumar Kondreddy
    73a9696

  9. Add detailed instrumentation to grade_task1 and normalize_reward for validator debugging

    Nanda Kumar Kondreddy
    31647f3

  10. CRITICAL RUNTIME FIX: Remove tuple unpacking from environment handlers - graders now return FLOAT only, not tuples

    Nanda Kumar Kondreddy
    b8c69e2

  11. CRITICAL FIX: Graders now return FLOAT ONLY (not tuples) for validator contract compliance - extracted float from raw grader tuples

    Nanda Kumar Kondreddy
    c256e38

  12. CRITICAL FIX: Wrappers now return full tuples (reward, error, bugs) instead of just floats - fixes env.py unpacking

    Nanda Kumar Kondreddy
    cf1808d

  13. Add comprehensive runtime grader validation endpoint (/validate-graders) to audit actual grader outputs under validator-style conditions

    Nanda Kumar Kondreddy
    5e5a089

  14. CRITICAL WIRING FIX: Import wrapped graders from grader_api, not raw graders - ensures normalization is used

    Nanda Kumar Kondreddy
    1566ba9

  15. FINAL FIX: Centralized universal reward normalization - GUARANTEES all scores in (0.01, 0.99)

    Nanda Kumar Kondreddy
    6d73738

  16. CRITICAL BUG FIX: Clamp reward on ALL early return paths - prevents returning 0.0

    Nanda Kumar Kondreddy
    6138889

  17. Enhanced /diagnostics: validate manifest import paths with importlib (mirrors validator behavior)

    Nanda Kumar Kondreddy
    c87f77e

  18. Add startup and diagnostics logging to debug task loading

    Nanda Kumar Kondreddy
    9331aaf

  19. Simplify metadata task schema to minimal fields (id, has_grader) for validator compatibility

    Nanda Kumar Kondreddy
    491de7d

  20. PROPER FIX: Remove default /metadata route before registering custom override with tasks

    Nanda Kumar Kondreddy
    3a48cf2

  21. CRITICAL FIX: Add /metadata endpoint with task enumeration for validator discovery

    Nanda Kumar Kondreddy
    a2f8fcd

  22. Add validator invocation logging to all grader wrappers

    Nanda Kumar Kondreddy
    e924908

  23. Add debug endpoint to verify deployed grader fix

    Nanda Kumar Kondreddy
    afad682

  24. Fix: Enforce strict open interval (0.01, 0.99) for all grader rewards - validator compliance

    Nanda Kumar Kondreddy
    8e7ae76

  25. Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure

    Nanda Kumar Kondreddy
    b43aff5