Commit History

  1. fix: reset reward 0.01 not 0.0

    Deepikachintamreddy
    f198438
  2. add POST /grader endpoint for validator

    Deepikachintamreddy
    5e04bd7
  3. trigger rebuild

    Deepikachintamreddy
    fba04fa
  4. Update app.py

    Chintamreddy Deepika
    Unverified signature
    99b0783

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

    Nanda Kumar Kondreddy
    c256e38
  7. Add comprehensive runtime grader validation endpoint (/validate-graders) to audit actual grader outputs under validator-style conditions

    Nanda Kumar Kondreddy
    5e5a089
  8. Enhanced /diagnostics: validate manifest import paths with importlib (mirrors validator behavior)

    Nanda Kumar Kondreddy
    c87f77e
  9. Add startup and diagnostics logging to debug task loading

    Nanda Kumar Kondreddy
    9331aaf
  10. Simplify metadata task schema to minimal fields (id, has_grader) for validator compatibility

    Nanda Kumar Kondreddy
    491de7d
  11. PROPER FIX: Remove default /metadata route before registering custom override with tasks

    Nanda Kumar Kondreddy
    3a48cf2
  12. CRITICAL FIX: Add /metadata endpoint with task enumeration for validator discovery

    Nanda Kumar Kondreddy
    a2f8fcd
  13. Add debug endpoint to verify deployed grader fix

    Nanda Kumar Kondreddy
    afad682
  14. Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure

    Nanda Kumar Kondreddy
    b43aff5