Starting CodePDE cns1d PDE Test Suite
==========================================
✅ Reference dataset present: /app/data/1D_CFD_Rand_Eta0.1_Zeta0.1_periodic_Train.hdf5
✅ solver.py present and non-empty
📄 Preview of solver.py (first 10 lines):
import numpy as np

def solver(Vx0, density0, pressure0, t_coordinate, eta, zeta):
    """Solves the 1D compressible Navier-Stokes equations for all times in t_coordinate.

    Args:
        Vx0 (np.ndarray): Initial velocity of shape [batch_size, N]
            where N is the number of evenly spaced spatial points.
        density0 (np.ndarray): Initial density [batch_size, N].
        pressure0 (np.ndarray): Initial pressure [batch_size, N].

🧪 Running pytest tests with nRMSE quality evaluation...
============================= test session starts ==============================
platform linux -- Python 3.11.14, pytest-9.0.3, pluggy-1.6.0 -- /usr/local/bin/python3.11
cachedir: .pytest_cache
rootdir: /tests
collecting ... collected 1 item

../tests/test_outputs.py::test_nrmse_accuracy ✓ solver function exists and is callable
✓ nRMSE_evaluator.py found
🧪 Running nRMSE evaluator...
data_file: /app/data/1D_CFD_Rand_Eta0.1_Zeta0.1_periodic_Train.hdf5
Command: python /tests/nRMSE_evaluator.py --dataset-path-for-eval /app/data/1D_CFD_Rand_Eta0.1_Zeta0.1_periodic_Train.hdf5 --eta 0.1
nRMSE Evaluator Output:
Loaded data with shape: (100, 101, 1024), (100, 101, 1024), (100, 101, 1024), (101,)
##### Running the solver on the given dataset #####
##### Finished #####
Result summary
nRMSE: nan	| Time: 131.81s	| 

nRMSE Evaluator Errors:
/app/solver.py:93: RuntimeWarning: overflow encountered in square
  p = (Gamma - 1) * (E - 0.5 * rho_safe * v**2)
/app/solver.py:60: RuntimeWarning: overflow encountered in square
  p = (Gamma - 1) * (E - 0.5 * rho_safe * v**2)
/app/solver.py:64: RuntimeWarning: overflow encountered in multiply
  F[1] = rho_v * v + p
/app/solver.py:64: RuntimeWarning: invalid value encountered in add
  F[1] = rho_v * v + p
/app/solver.py:65: RuntimeWarning: overflow encountered in multiply
  F[2] = (E + p) * v
/usr/local/lib/python3.11/site-packages/numpy/fft/_pocketfft.py:101: RuntimeWarning: invalid value encountered in fft
  return ufunc(a, fct, axes=[(axis,), (), (axis,)], out=out)
/app/solver.py:77: RuntimeWarning: overflow encountered in square
  dUdt[2] = -dF_dx[2] + mu * (dv_dx**2 + v * d2v_dx2)
/app/solver.py:77: RuntimeWarning: overflow encountered in multiply
  dUdt[2] = -dF_dx[2] + mu * (dv_dx**2 + v * d2v_dx2)
/app/solver.py:77: RuntimeWarning: invalid value encountered in add
  dUdt[2] = -dF_dx[2] + mu * (dv_dx**2 + v * d2v_dx2)

📊 Parsed Results:
  - nRMSE: nan
  - Time: 131.81s
  - Reference nRMSE threshold: 0.05
  - Continuous reward: 0.000000
  - Legacy threshold result: FAIL
  - Note: non-finite nRMSE receives reward 0
✅ Evaluation completed! nRMSE=nan, reward=0.000000, Time=131.81s
PASSED

=============================== warnings summary ===============================
test_outputs.py::test_nrmse_accuracy
  /usr/local/lib/python3.11/site-packages/_pytest/python.py:170: PytestReturnNotNoneWarning: Test functions should return None, but test_outputs.py::test_nrmse_accuracy returned <class 'tuple'>.
  Did you mean to use `assert` instead of `return`?
  See https://docs.pytest.org/en/stable/how-to/assert.html#return-not-none for more information.
    warnings.warn(

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
==================================== PASSES ====================================
=========================== short test summary info ============================
PASSED ../tests/test_outputs.py::test_nrmse_accuracy
=================== 1 passed, 1 warning in 132.37s (0:02:12) ===================

📊 Final Evaluation Results:
Evaluation Results
==================
nRMSE: nan	Time: 131.81s	Reward: 0.000000	LegacySuccess: False

Continuous reward:
0
