🐛 [TestRemoval/TestRepair] - 211, 215- include status code in mock response

[dmelcer9]

trafficstars

EvalPlus version

v0_1_0_hf

Output of running ls ~/.cache/bigcodebench

BigCodeBench-v0.1.0_hf.jsonl

Task ID of the programming task

BigCodeBench/211, BigCodeBench/215, probably some others as well

The original test

(All tests)
mock_response = MagicMock() 
mock_response.content = MOCK_CONTENT 
mock_requests_get.return_value = mock_response

Your proposed new test

mock_response = MagicMock() 
mock_response.content = MOCK_CONTENT 
mock_response.status_code = 200
mock_requests_get.return_value = mock_response

Description

The LLM sometimes (reasonably!) generates code like:

    if r.status_code != 200:
        print("Error: Failed to download file from URL.")
        return None

   (Rest of code solves task correctly)

But fails the test

Other context

No response

[terryyz]

Thanks @dmelcer9! It makes sense :) We didn't think about this when developing the initial tasks. We will incorporate this change in the next dataset release.

[hvaara]

@dmelcer9 which model did you use? I'd like to verify resolution in #49.

[dmelcer9]

Not 100% sure but I believe this was with Starcoder2-15b, temperature was somewhere between 0.7 and 1.