aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2025-12-18 14:34:23 +01:00
Code Issues Packages Projects Releases Wiki Activity

Make agbenchmark a proxy of the evaluated agent (#5279)

Browse Source 
Make agbenchmark a Proxy of the evaluated agent

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
This commit is contained in:
merwanehamadi
2023-09-20 16:06:00 -07:00
committed by GitHub
parent 1a471b73cd
commit ff4c76ba00
71 changed files with 2459 additions and 1297 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
benchmark/agbenchmark/conftest.py
View File

@@ -255,7 +255,13 @@ def pytest_runtest_makereport(item: Any, call: Any) -> None:
if call.when == "call":
answers = getattr(item, "answers", None)
generate_single_call_report(item, call, challenge_data, answers)
challenge_location: str = getattr(item.cls, "CHALLENGE_LOCATION", "")
test_name = item.nodeid.split("::")[1]
item.test_name = test_name
generate_single_call_report(
item, call, challenge_data, answers, challenge_location, test_name
)
if call.when == "teardown":
finalize_reports(item, challenge_data)