Commit Graph

132 Commits (9326ef78265269578887d35da661a7ad94331407)

Author SHA1 Message Date
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
Erik Peterson fa8f010e80
Kill all subprocesses (#265)
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
2023-08-06 21:12:10 -07:00
merwanehamadi db48e7849b
Add product advisor tests (#267) 2023-08-06 20:59:53 -07:00
merwanehamadi f157f46a07
Fix test write file (#266) 2023-08-06 18:44:42 -07:00
Silen Naihin 3c20191156 updating challenges commit sha 2023-08-06 23:02:35 +01:00
Silen Naihin 710ad448fe making sure show_graph is optional 2023-08-06 22:43:42 +01:00
Silen Naihin 19848f362d
remove pytest-depends, rerouting functions (#250) 2023-08-06 22:35:22 +01:00
merwanehamadi aa37109707
Remove graphql logs (#264)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-06 12:22:49 -07:00
merwanehamadi e32713be68
Helicone Lock Manager fix (#263)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-06 11:30:03 -07:00
merwanehamadi 5232522e47
Remove space challenges (#262) 2023-08-06 10:10:58 -07:00
merwanehamadi 53ec3337f3
Add all agent protocol tests (#260)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-06 09:52:46 -07:00
merwanehamadi 530eb61f25
Add agent protocol interface test (#259)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-05 18:00:05 -07:00
merwanehamadi fb13a83d15
Add more coding challenge (#254)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-05 09:51:53 -07:00
merwanehamadi ec262f0667
Fix more attempted metrics not working (#252)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-04 15:07:15 -07:00
merwanehamadi 34814d837a
Fix "attempted" metric being incorrect (#251)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-04 11:28:45 -07:00
merwanehamadi 20c87fbc26
Fix typing (#247) 2023-08-02 15:08:07 -07:00
merwanehamadi 59f015ab93
fix-linter (#246) 2023-08-02 14:49:03 -07:00
merwanehamadi 8fa67ea466
Correct agent and benchmark commit sha (#245)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-02 14:44:14 -07:00
merwanehamadi e3562a4b66
Add attempted metrics (#244)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-02 13:27:57 -07:00
merwanehamadi f41533ce62
Fix reports and add commit sha (#233)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-08-01 17:54:23 -07:00
merwanehamadi eeb68858d7
Only run mini-agi on tests (#232) 2023-08-01 16:50:41 -07:00
Silen Naihin 3992f0865b comitting changes 2023-08-01 20:49:20 +01:00
Silen Naihin f4225f63bf linter and handling errs 2023-08-01 17:55:00 +01:00
Silen Naihin f8a01ef70a fixing combined charts issue 2023-08-01 17:15:15 +01:00
Silen Naihin f195840d35 fixing combined_graph 2023-08-01 14:35:14 +01:00
Silen Naihin 6f3fd2a578 fix graphs, processing, workflow 2023-08-01 13:44:32 +01:00
merwanehamadi ce24857a74
Return none as fallback Helicone (#228)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-31 20:18:15 -07:00
merwanehamadi 46dce97c4e
Fix reports (#227)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-31 19:39:49 -07:00
merwanehamadi a2dc4693a3
Fix costs helicone (#226)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-31 16:13:06 -07:00
Silen Naihin f9fea473f5
Refactoring for TDD (#222) 2023-07-31 21:59:47 +01:00
merwanehamadi 719f894520
Fix send to gdrive and tracking the wrong challenge name (#225)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-31 12:35:37 -07:00
Justin Torre 3a32adbce5
Fix f-string get_data_from_helicone.py (#223) 2023-07-31 09:06:04 -07:00
Silen Naihin 9d75712bae ci ofr auth 2023-07-31 14:02:46 +01:00
Silen Naihin f8de706a15 removing data that didnt work 2023-07-31 13:41:45 +01:00
Silen Naihin 2ec306e850 linter fixes 2023-07-31 13:28:01 +01:00
Silen Naihin db49e8de15 helicone push 2 2023-07-31 13:26:49 +01:00
Silen Naihin 14c49fa7ea handling helicone errors 2023-07-31 12:54:27 +01:00
Silen Naihin 4011cb228f
working bar and radar charts (#221) 2023-07-31 12:22:38 +01:00
merwanehamadi ad00a0634e
Get helicone costs (#220)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-30 21:33:09 -07:00
merwanehamadi 6309bc9c3d
Update submodule (#219) 2023-07-30 20:03:53 -07:00
merwanehamadi d93950e6d9
Fix timeout not working (#218) 2023-07-30 19:05:09 -07:00
Silen Naihin 19db3151dd
Feature: Visualize Test Results (#211) 2023-07-30 23:51:17 +01:00
merwanehamadi a6c3730ac8
Add timeout that allows teardown (#216)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-29 20:02:41 -07:00
merwanehamadi c4554225bd
Update submodules (#212)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-29 10:18:35 -07:00
Silen Naihin ecc386ec7b
returning scores (#210)
Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>
2023-07-29 11:43:22 +01:00
Silen Naihin f07e7b60d4
Advanced LLM Evaluation Implementation (#205)
Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>
2023-07-29 10:26:19 +01:00
merwanehamadi 80bd0c4260
Fix tests not being run (#207)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-27 20:50:53 -07:00
merwanehamadi 6098b70408
Use beebot autopackai (#203)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-27 12:21:43 -07:00
merwanehamadi 31897e7892
Delete reports (#201) 2023-07-27 11:42:24 -07:00
Silen Naihin 71e0c598d6 forcing AGENT_NAME to be defined from repo 2023-07-27 14:28:11 +01:00