Albert Örwall
4ef912d734
fix(benchmark/challenges): Improve spec and eval of TicTacToe challenge
...
* In challenge specification, specify `subprocess.PIPE` for `stdin` and `stderr` for completeness
* Additional tweak: let Pytest load only the current file when running the test file as a script
Co-authored-by: Reinier van der Leer <pwuts@agpt.co>
2024-02-20 11:52:59 +01:00
merwanehamadi
0e804e27dd
Add more data challenges ( #5390 )
...
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-28 19:30:08 -07:00
merwanehamadi
37fbb52d19
Add more challenges + cleanup ( #5368 )
...
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-27 17:58:58 -07:00
merwanehamadi
18e576cb53
Structure challenges ( #5296 )
2023-09-21 20:06:37 -07:00
merwanehamadi
f67a352937
Add categories skill tree ( #5295 )
...
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-21 17:39:16 -07:00
merwanehamadi
f4d319cee4
Refactor benchmark ( #5247 )
...
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-17 06:55:20 -07:00
merwanehamadi
295702867a
Ability to run by categories ( #5229 )
...
* Ability to run by categories
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
* always use Path.cwd()
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
---------
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-15 20:04:12 -07:00
Merwane Hamadi
1b14d304d4
Benchmark changes
...
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-12 12:13:39 -07:00
SwiftyOS
c73e90c4e6
Fixing benchmarks
2023-09-11 17:41:27 -07:00
Auto-GPT-Bot
45c15e370f
Auto-GPT-20230905085638
...
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-05 10:10:03 -07:00