Spaces:
Paused
Paused
Commit History
-
Sync from GitHub: serving-only image deps, app_port, discoverability tags, buildable package
Verified signature60dfa24
-
feat(v2): execution-grounded rewards via DuckDB -- the key differentiator
Abhinav SinghTHE CORE INNOVATION: optimized SQL queries are ACTUALLY EXECUTED against a real in-memory DuckDB database. Reward is computed from measured performance, not keyword heuristics. New files: executor.py — DuckDB engine with 4 synthetic tables (users 10k, orders 500k, products 1k, events 1M). Runs both the original and optimized query 3x each, returns median timing, result correctness, and EXPLAIN plan. leaderboard.py — In-memory best-score tracker per task, surfaced via the new /leaderboard endpoint. test_env.py — Integration test confirming real speedup (3-4x on Task 1 measured on local machine). Updated reward function (graders.py): Real Execution Speedup 35% (was: not measured at all) Result Correctness 20% (NEW: both queries must return same data) Issue Detection 25% (was: 60% keyword-only) Approval Correctness 8% Summary Quality 7% …c15d346
-
feat(server): add FastAPI server with all OpenEnv endpoints
Abhinav Singhserver/app.py — uvicorn FastAPI app on port 7860: POST /reset — start new episode, accepts optional {task_id} body, defaults to task_1_basic_antipatterns POST /step — submit Action, returns StepResult with Observation+Reward GET /state — current EnvironmentState (non-destructive) GET /tasks — list all tasks with descriptions and action schema POST /grader — grade an action against active task without advancing POST /baseline — runs inference.py subprocess and returns stdout GET / — health check returning env name and available tasks CORS middleware enabled for all origins (required for HF Space)e8bc352