Commit Graph

181 Commits

Author SHA1 Message Date
merwanehamadi
41909f0de7 Tic tac toe challenge (#345)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-31 20:45:31 -07:00
Luke
595e04def1 Updating Turbo (#343)
Co-authored-by: Luke <2609441+lc0rp@user.noreply.github.com>
2023-08-31 07:09:41 -04:00
Silen Naihin
b6ad300eda restructure library, deprecate challenges (#336)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-30 22:38:31 -07:00
Merwane Hamadi
e96d492fb1 Get total cost 2023-08-30 21:57:28 -07:00
merwanehamadi
7c49b0f29c Fix tests (#338) 2023-08-30 20:31:10 -07:00
merwanehamadi
afb59a0778 Support agent protocol (#337)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-30 19:44:39 -07:00
Luke
16a1d884f1 Update TestPasswordGenerator_Easy to mention ValueError (#335)
Co-authored-by: Luke <2609441+lc0rp@user.noreply.github.com>
2023-08-30 19:08:36 -04:00
SwiftyOS
e1f82d1469 added the ability to run the benchmark back 2023-08-29 16:29:45 +02:00
merwanehamadi
6715b462fd remove warning (#332) 2023-08-28 22:20:07 -07:00
Reinier van der Leer
d86ed40f83 Improve TestRevenueRetrieval_1.1 task specification (#329)
Co-authored-by: Luke <2609441+lc0rp@users.noreply.github.com>
2023-08-28 09:37:26 -07:00
merwanehamadi
a8dd079d4c Updatee cutoff for SuperAGI (#330) 2023-08-28 08:13:18 -07:00
Silen Naihin
59655a8d96 adding backend and a basic ui (#309) 2023-08-27 03:18:30 -04:00
Fluder-Paradyne
2176e1179a Fix for TestWrite6Files and TestWrite5FilesWithArray (#328)
Co-authored-by: Silen Naihin <silen.naihin@gmail.com>
2023-08-24 09:14:03 -04:00
Luke
9f1631719c Fix "code.py" conflict with Python's code module, and fix TestReturnCode_Simple conflict between two test.py files. (#321)
Co-authored-by: Luke <2609441+lc0rp@user.noreply.github.com>
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
2023-08-19 09:04:18 -07:00
merwanehamadi
6fa303509f Fix linter 2 (#319) 2023-08-16 16:56:02 -07:00
merwanehamadi
6b9a75f786 Only push to gdrive correct timestamps (#318)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-16 16:43:14 -07:00
merwanehamadi
62c52643b4 Remove build a nuke challenge (#316)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-16 15:58:17 -07:00
merwanehamadi
760b60b249 Remove colons in timestamp (#315)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-16 15:53:06 -07:00
merwanehamadi
82ed4a136a Remove submodule (#314)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-16 14:57:52 -07:00
merwanehamadi
277f3e4e4d Add endpoints to power dev tool (#310) 2023-08-16 09:00:05 -07:00
Luke
281d8486df Fixing paths that were preventing artifacts from being copied to workspace (#311)
Co-authored-by: Luke <2609441+lc0rp@user.noreply.github.com>
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
2023-08-16 08:59:04 -07:00
Swifty
16053a3137 Enhanced Test Report Directory Naming and Handling (#312) 2023-08-16 08:45:46 -07:00
Silen Naihin
8bc3710e23 init backend, fix frontend module (#307) 2023-08-15 14:14:35 +01:00
Silen Naihin
c59e5fb7d8 new frontend connections (#306) 2023-08-15 13:16:07 +01:00
Silen Naihin
a6b229f4cd Merge branch 'master' of https://github.com/Significant-Gravitas/Auto-GPT-Benchmarks 2023-08-14 21:57:12 +01:00
Silen Naihin
0d7fbba134 graph data json 2023-08-14 21:57:09 +01:00
merwanehamadi
0f010def5d fix eval (#305)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-14 11:13:44 -07:00
merwanehamadi
07f831878f Fix eval (#304) 2023-08-14 10:54:54 -07:00
merwanehamadi
d27d17e51b Fix linter (#302) 2023-08-13 10:34:45 -07:00
merwanehamadi
0da8a2bd99 Fix agent protocol test (#301)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-13 10:27:54 -07:00
merwanehamadi
1129e6b426 Add safety challenge (#300)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-13 10:15:58 -07:00
merwanehamadi
8bf2f3fe5d Fix all tests skipped (#296)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-12 17:35:55 -07:00
merwanehamadi
e1c043975f Fix all tests skipped (#294)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-12 10:19:02 -07:00
merwanehamadi
d8d7fa662b Use index.html instead of dependencies.html (#293) 2023-08-11 20:32:23 -07:00
merwanehamadi
6dc713059c Remember goal loss (#291) 2023-08-11 18:44:18 -07:00
merwanehamadi
1560892c58 Sync skill tree to a versioned website (#289)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-11 17:28:53 -07:00
Erik Peterson
79be5cd70f Update challenges submodule 2023-08-11 14:45:36 -07:00
Silen Naihin
1a61c66898 mock flag, workspace io fixes, mark fixes 2023-08-11 13:22:21 +01:00
Jakub Novák
c2269397f1 Use agent protocol (#278)
Signed-off-by: Jakub Novak <jakub@e2b.dev>
2023-08-11 09:04:08 +02:00
merwanehamadi
47c6062092 Cleanup skill tree (#287) 2023-08-10 16:29:58 -07:00
Rob
fb67c3aaf1 add updated challenges 2023-08-10 21:45:58 +02:00
Rob
a2380a7bdd feat: ethereum price challenge 2023-08-10 21:09:04 +02:00
merwanehamadi
1b20e45ec1 Implement the 'explore' mode (#284) 2023-08-09 17:59:48 -07:00
merwanehamadi
6afd962270 Remove baserun because api key issue (#282)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-09 11:24:54 -07:00
merwanehamadi
e3f1e2184f Release 0.0.4 (#280)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-09 10:04:57 -07:00
merwanehamadi
7d60ce5f44 See the task when clicking in the skill tree (#279) 2023-08-09 09:37:17 -07:00
merwanehamadi
14e6d4968e Integrate with baserun (#274) 2023-08-08 14:04:43 -07:00
merwanehamadi
305f3a6138 Add web app creation challenge (#272) 2023-08-08 13:08:51 -07:00
Swifty
e0a72b86c1 AUTO-25: Add the ability to run multiple categories and to skip categories (#270) 2023-08-07 12:29:00 +01:00
Luke
9326ef7826 Feat: --cutoff and "keep_workspace_files" options (#261)
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
2023-08-06 21:14:55 -07:00