Code

AssistantBench#186

Code

Merged

gasse merged 21 commits intoServiceNow:mainServiceNow/BrowserGym:mainfrom oriyor:ori/add-aboriyor/BrowserGym:ori/add-abCopy head branch name to clipboardOct 22, 2024

+1,164-3

Commits

Commits on Oct 22, 2024

• add AssistantBench

  Show description for 59c501d
  

  oriyor

  authored and

  gasse

  committed
  59c501d

  Copy full SHA for 59c501d

• add AssistantBench

  Show description for 31d92d0
  

  oriyor

  authored and

  gasse

  committed
  31d92d0

  Copy full SHA for 31d92d0

• black formatting

  

  oriyor

  authored and

  gasse

  committed
  e74c6c6

  Copy full SHA for e74c6c6

• Update .gitignore

  

  oriyor

  authored and

  gasse

  committed
  fa0d74b

  Copy full SHA for fa0d74b

• packaging + fixes

  gasse

  committed
  a9816bb

  Copy full SHA for a9816bb

• ci tests

  gasse

  committed
  ff2313b

  Copy full SHA for ff2313b

• fix tests and rename

  

  oriyor

  authored and

  gasse

  committed
  54087bd

  Copy full SHA for 54087bd

• Update requirements.txt

  

  oriyor

  authored and

  gasse

  committed
  b88e7ef

  Copy full SHA for b88e7ef

• add assistantbench csv

  

  oriyor

  authored and

  gasse

  committed
  4d61da5

  Copy full SHA for 4d61da5

• Update assistantbench.csv

  

  oriyor

  authored and

  gasse

  committed
  7316515

  Copy full SHA for 7316515

• cleanup

  gasse

  committed
  902c932

  Copy full SHA for 902c932

• typo

  gasse

  committed
  45c00c2

  Copy full SHA for 45c00c2

• explicit ValueError for send_message_to_user and report_infeasible_instructions

  gasse

  committed
  2ce7788

  Copy full SHA for 2ce7788

• fix

  gasse

  committed
  8e90178

  Copy full SHA for 8e90178

• dev -> valid renaming

  gasse

  committed
  0fd7849

  Copy full SHA for 0fd7849

• more tests

  gasse

  committed
  b1ee044

  Copy full SHA for b1ee044

• tests fix

  gasse

  committed
  2baa2c9

  Copy full SHA for 2baa2c9

• assistantbench benchmark

  gasse

  committed
  b9de995

  Copy full SHA for b9de995

• minor refactor

  gasse

  committed
  2bcce2c

  Copy full SHA for 2bcce2c

• remove implementation task from benchmark

  gasse

  committed
  f23cd1f

  Copy full SHA for f23cd1f

• assistantbench packaging

  gasse

  committed
  6f3ac9d

  Copy full SHA for 6f3ac9d