browsergym-workarena 0.4.1__tar.gz → 0.4.3__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (167) hide show
  1. browsergym_workarena-0.4.3/.github/ISSUE_TEMPLATE/bug_report.yml +125 -0
  2. browsergym_workarena-0.4.3/CODE_OF_CONDUCT.md +46 -0
  3. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/PKG-INFO +37 -46
  4. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/README.md +35 -44
  5. browsergym_workarena-0.4.3/SECURITY.md +22 -0
  6. browsergym_workarena-0.4.3/assets/WorkArena_banner.png +0 -0
  7. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/__init__.py +1 -1
  8. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/config.py +1 -1
  9. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/report_retrieval_minmax_task.json +1 -1
  10. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/report_retrieval_value_task.json +1 -1
  11. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/install.py +15 -0
  12. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/instance.py +1 -1
  13. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/dashboard.py +4 -0
  14. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/list.py +78 -8
  15. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/service_catalog.py +0 -10
  16. browsergym_workarena-0.4.3/tests/test_filter_list_task.py +81 -0
  17. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/.github/workflows/pypi.yml +0 -0
  18. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/.github/workflows/unit_tests.yml +0 -0
  19. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/.gitignore +0 -0
  20. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/LICENSE +0 -0
  21. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/dcat-metadata.jsonld +0 -0
  22. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/dev/environment.yaml +0 -0
  23. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/dev/requirements.txt +0 -0
  24. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/generate_knowledge_base.ipynb +0 -0
  25. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/make_human_eval_curriculum.py +0 -0
  26. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/pyproject.toml +0 -0
  27. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/requirements.txt +0 -0
  28. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/scripts/extract_finetuning_traces.py +0 -0
  29. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/scripts/generate_knowledge_base.ipynb +0 -0
  30. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/scripts/make_human_eval_curriculum.py +0 -0
  31. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/__init__.py +0 -0
  32. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/category.py +0 -0
  33. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/change_request.py +0 -0
  34. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/computer_asset.py +0 -0
  35. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/cost_center.py +0 -0
  36. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/expense_line.py +0 -0
  37. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/incident.py +0 -0
  38. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/knowledge.py +0 -0
  39. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/problem.py +0 -0
  40. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/report.py +0 -0
  41. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/requested_items.py +0 -0
  42. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/requests.py +0 -0
  43. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/ui_themes.py +0 -0
  44. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/user.py +0 -0
  45. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/api/utils.py +0 -0
  46. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/forms/expected_change_request_form_fields.json +0 -0
  47. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/forms/expected_hardware_form_fields.json +0 -0
  48. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/forms/expected_incident_form_fields.json +0 -0
  49. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/forms/expected_problem_form_fields.json +0 -0
  50. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/forms/expected_request_item_form_fields.json +0 -0
  51. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/forms/expected_user_form_fields.json +0 -0
  52. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/knowledge/kb_autopublish_workflow.xml +0 -0
  53. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/knowledge/knowledge_base.json +0 -0
  54. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/knowledge/protocols.json +0 -0
  55. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/knowledge/test.html +0 -0
  56. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/lists/expected_asset_list_columns.json +0 -0
  57. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/lists/expected_change_request_list_columns.json +0 -0
  58. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/lists/expected_expense_line_list_columns.json +0 -0
  59. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/lists/expected_hardware_list_columns.json +0 -0
  60. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/lists/expected_incident_list_columns.json +0 -0
  61. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/lists/expected_problem_list_columns.json +0 -0
  62. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/lists/expected_requested_items_list_columns.json +0 -0
  63. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/lists/expected_service_catalog_list_columns.json +0 -0
  64. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/lists/expected_user_list_columns.json +0 -0
  65. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/setup_files/ui_themes/workarena_themes.xml +0 -0
  66. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/all_menu.json +0 -0
  67. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/create_change_request_task.json +0 -0
  68. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/create_hardware_asset_task.json +0 -0
  69. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/create_incident_task.json +0 -0
  70. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/create_problem_task.json +0 -0
  71. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/create_user_task.json +0 -0
  72. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/dashboard_retrieval_minmax_task.json +0 -0
  73. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/dashboard_retrieval_value_task.json +0 -0
  74. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/filter_asset_list_task.json +0 -0
  75. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/filter_change_request_list_task.json +0 -0
  76. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/filter_hardware_list_task.json +0 -0
  77. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/filter_incident_list_task.json +0 -0
  78. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/filter_service_catalog_item_list_task.json +0 -0
  79. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/filter_user_list_task.json +0 -0
  80. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/impersonation_users.json +0 -0
  81. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/knowledge_base_configs.json +0 -0
  82. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/order_apple_mac_book_pro15_task.json +0 -0
  83. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/order_apple_watch_task.json +0 -0
  84. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/order_developer_laptop_task.json +0 -0
  85. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/order_development_laptop_pc_task.json +0 -0
  86. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/order_ipad_mini_task.json +0 -0
  87. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/order_ipad_pro_task.json +0 -0
  88. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/order_loaner_laptop_task.json +0 -0
  89. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/order_sales_laptop_task.json +0 -0
  90. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/order_standard_laptop_task.json +0 -0
  91. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/sort_asset_list_task.json +0 -0
  92. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/sort_change_request_list_task.json +0 -0
  93. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/sort_hardware_list_task.json +0 -0
  94. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/sort_incident_list_task.json +0 -0
  95. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/sort_service_catalog_item_list_task.json +0 -0
  96. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/data_files/task_configs/sort_user_list_task.json +0 -0
  97. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/human_eval/console.js +0 -0
  98. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/human_eval/tool.py +0 -0
  99. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/__init__.py +0 -0
  100. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/base.py +0 -0
  101. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/comp_building_block.py +0 -0
  102. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/__init__.py +0 -0
  103. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/base.py +0 -0
  104. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/dash_do_base.py +0 -0
  105. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/dash_do_catalog.py +0 -0
  106. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/dash_do_catalog_infeasible.py +0 -0
  107. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/dash_do_create_incident.py +0 -0
  108. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/dash_do_create_incident_infeasible.py +0 -0
  109. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/dash_do_create_problem.py +0 -0
  110. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/dash_do_create_problem_infeasible.py +0 -0
  111. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/dash_do_filter.py +0 -0
  112. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/dash_do_request_item.py +0 -0
  113. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/dash_do_request_item_infeasible.py +0 -0
  114. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/delete_record.py +0 -0
  115. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/edit_knowledge_base.py +0 -0
  116. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/expense_management.py +0 -0
  117. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/filter_and_do.py +0 -0
  118. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/find_and_order_item.py +0 -0
  119. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/manage_change_request_schedule.py +0 -0
  120. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/mark_duplicate_problems.py +0 -0
  121. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/maximize_investment_return.py +0 -0
  122. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/navigate_and_do.py +0 -0
  123. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/navigate_and_do_infeasible.py +0 -0
  124. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/offboard_user.py +0 -0
  125. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/onboard_user.py +0 -0
  126. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/update_task.py +0 -0
  127. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/utils/curriculum.py +0 -0
  128. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/utils/infeasible_configs.py +0 -0
  129. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/utils/knapsack.py +0 -0
  130. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/warranty_check.py +0 -0
  131. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/work_assignment.py +0 -0
  132. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/compositional/workload_balancing.py +0 -0
  133. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/form.py +0 -0
  134. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/knowledge.py +0 -0
  135. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/mark_duplicate_problem.py +0 -0
  136. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/navigation.py +0 -0
  137. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/scripts/README.md +0 -0
  138. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/scripts/extract_all_menu_items.py +0 -0
  139. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/scripts/generate_dashboard_configs.py +0 -0
  140. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/scripts/generate_forms.py +0 -0
  141. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/scripts/knowledge.py +0 -0
  142. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/scripts/list.py +0 -0
  143. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/scripts/navigation.py +0 -0
  144. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/scripts/service_catalog.py +0 -0
  145. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/scripts/validate.py +0 -0
  146. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/send_chat_message.py +0 -0
  147. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/utils/__init__.py +0 -0
  148. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/utils/debug.py +0 -0
  149. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/utils/form.py +0 -0
  150. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/utils/js_utils.js +0 -0
  151. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/utils/private_tasks.py +0 -0
  152. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/utils/string.py +0 -0
  153. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/tasks/utils/utils.py +0 -0
  154. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/browsergym/workarena/utils.py +0 -0
  155. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/wa_action_traces.py +0 -0
  156. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/src/workarena_test.py +0 -0
  157. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/tests/test_api.py +0 -0
  158. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/tests/test_compositional.py +0 -0
  159. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/tests/test_compositional_utils.py +0 -0
  160. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/tests/test_random_config_generation.py +0 -0
  161. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/tests/test_snow_instance.py +0 -0
  162. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/tests/test_task_from_config.py +0 -0
  163. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/tests/test_task_general.py +0 -0
  164. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/tests/test_task_setup.py +0 -0
  165. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/tests/test_utils.py +0 -0
  166. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/tests/test_validate.py +0 -0
  167. {browsergym_workarena-0.4.1 → browsergym_workarena-0.4.3}/tests/utils.py +0 -0
@@ -0,0 +1,125 @@
1
+ name: Bug Report
2
+ description: Report an issue with browsergym/Playwright setup
3
+ title: "[Bug]: "
4
+ labels: ["bug"]
5
+ body:
6
+ - type: markdown
7
+ attributes:
8
+ value: |
9
+ Thanks for reporting an issue! Please fill out the information below to help us diagnose the problem.
10
+
11
+ - type: input
12
+ id: browsergym-version
13
+ attributes:
14
+ label: Browsergym Version
15
+ description: What version of browsergym are you using?
16
+ placeholder: "e.g., 1.2.0"
17
+ validations:
18
+ required: true
19
+
20
+ - type: input
21
+ id: playwright-version
22
+ attributes:
23
+ label: Playwright Version
24
+ description: What version of Playwright are you using?
25
+ placeholder: "e.g., 1.41.0"
26
+ validations:
27
+ required: true
28
+
29
+ - type: dropdown
30
+ id: os-type
31
+ attributes:
32
+ label: Operating System Type
33
+ description: What type of operating system are you using?
34
+ options:
35
+ - Ubuntu
36
+ - Debian
37
+ - macOS
38
+ - Windows
39
+ - Other Linux (specify version below)
40
+ validations:
41
+ required: true
42
+
43
+ - type: dropdown
44
+ id: os-version
45
+ attributes:
46
+ label: Operating System Version
47
+ description: Select your OS version
48
+ options:
49
+ # Ubuntu LTS versions
50
+ - Ubuntu 24.04 LTS (Noble Numbat)
51
+ - Ubuntu 22.04 LTS (Jammy Jellyfish)
52
+ - Ubuntu 20.04 LTS (Focal Fossa)
53
+ # macOS versions
54
+ - macOS 14 (Sonoma)
55
+ - macOS 13 (Ventura)
56
+ - macOS 12 (Monterey)
57
+ - macOS 11 (Big Sur)
58
+ # Windows versions
59
+ - Windows 11 23H2 (Build 22631)
60
+ - Windows 11 22H2 (Build 22621)
61
+ - Windows 10 22H2 (Build 19045)
62
+ - Windows 10 21H2 (Build 19044)
63
+ # Other
64
+ - Other (specify in Additional Context)
65
+ validations:
66
+ required: true
67
+
68
+ - type: dropdown
69
+ id: browsers
70
+ attributes:
71
+ label: Affected Browsers
72
+ description: Which browsers are you seeing this issue with?
73
+ multiple: true
74
+ options:
75
+ - Chromium
76
+ - Firefox
77
+ - WebKit
78
+ validations:
79
+ required: true
80
+
81
+ - type: textarea
82
+ id: what-happened
83
+ attributes:
84
+ label: What happened?
85
+ description: Please describe what happened and what you expected to happen
86
+ placeholder: |
87
+ 1. What did you do?
88
+ 2. What happened?
89
+ 3. What did you expect to happen?
90
+ validations:
91
+ required: true
92
+
93
+ - type: textarea
94
+ id: reproduction
95
+ attributes:
96
+ label: Reproduction Steps
97
+ description: Please provide minimal steps to reproduce the issue
98
+ placeholder: |
99
+ 1. Install dependencies...
100
+ 2. Run command...
101
+ 3. See error...
102
+ validations:
103
+ required: true
104
+
105
+ - type: textarea
106
+ id: logs
107
+ attributes:
108
+ label: Relevant Logs
109
+ description: Please copy and paste any relevant logs. This will be automatically formatted into code.
110
+ render: shell
111
+
112
+ - type: textarea
113
+ id: additional-context
114
+ attributes:
115
+ label: Additional Context
116
+ description: For "Other" OS versions, please specify here. Also add any other context about the problem.
117
+
118
+ - type: checkboxes
119
+ id: terms
120
+ attributes:
121
+ label: Code of Conduct
122
+ description: By submitting this issue, you agree to follow our project's Code of Conduct
123
+ options:
124
+ - label: I agree to follow this project's Code of Conduct
125
+ required: true
@@ -0,0 +1,46 @@
1
+ ### ServiceNow Open Source Code-of-Conduct
2
+
3
+ This code of conduct provides guidelines for participation in ServiceNow-managed open-source communities and projects.
4
+
5
+ **Discussion forum guidelines**
6
+
7
+ Communities thrive when members support each other and provide useful feedback.
8
+
9
+ - Be polite and courteous. Respect and treat others as you would expect to be treated yourself.
10
+ - Respect your audience. Posts should not upset, annoy, threaten, harass, abuse or embarrass other members.
11
+ - User Contributions must not include material that is defamatory, obscene, indecent, abusive, offensive, harassing, violent, hateful, inflammatory or otherwise objectionable.
12
+ - Lively and collegial discussions are always encouraged in a healthy community. It is okay to argue facts but not okay to argue personalities or personal beliefs.
13
+ - Do not use text formats such as all caps or bold that may be read as annoying, rude or send a strong message.
14
+ - Do not publish anyone’s private personal information without their explicit consent.
15
+ - Avoid using abbreviations or terminology that others may not understand. An abbreviation may mean something to you but in another context or country, it may have another meaning.
16
+ - Be accountable for your actions by correcting your mistakes and indicating where you have changed a previous post of yours.
17
+ - Mark content as correct and helpful, and provide feedback. If you read a discussion post that you find helpful, we encourage you to leave a positive vote and comment in the replies. If you find a post that is unhelpful, please provide more information in the issue comments.
18
+
19
+ **Issue board guidelines**
20
+
21
+ Many open-source projects provide an Issues board, with similar functionality to a Discussions forum. The same rules from the discussion forum guidelines apply to the Issues board.
22
+
23
+ ServiceNow suggests the following technical support pathways for open-source projects:
24
+
25
+ 1. Clearly identify and document the issue or question you have.
26
+ 2. View the Documentation.
27
+ 3. Search the Discussions.
28
+ 4. Search the project knowledge base or Wiki for known errors, useful solutions, and troubleshooting tips.
29
+ 5. Check the project guidelines in the [`CONTRIBUTING.md`](CONTRIBUTING.md) file if you would like details on how you can submit a change. Community contributions are valued and appreciated!
30
+ 6. Log an Issue if it hasn’t already been logged. If the issue has already been logged by another user, vote it up, and add a comment with additional or missing information. Do your best to choose the correct category when logging a new issue. This will make it easier to differentiate bugs from new feature requests or ideas. If after logging an issue you find the solution, please close your issue and provide a comment with the solution. This will help the project owners and other users.
31
+ 7. Contact the project team contributors of the project to see if they can help as a last resort only.
32
+
33
+ **Repositories**
34
+
35
+ - Read and follow the license instructions
36
+ - Remember to include citations if you use someone else’s work in your own project. Use the [`CITATION.cff`](CITATION.cff) to find the correct project citation reference.
37
+ - ‘Star’ project repos to save for future reference.
38
+ - ‘Watch’ project repos to get notifications of changes – this can get noisy for some projects, so only watch the ones you really need to track closely.
39
+
40
+ **Enforcement and reporting**
41
+
42
+ We encourage community members and users to help each other and to resolve issues amongst themselves as much as possible. If a matter cannot be resolved in good faith within the means available, please reach out to a team member or email servicenow-research@servicenow.com.
43
+
44
+ **ServiceNow Disclaimer.**
45
+
46
+ We may, but are under no obligation to, monitor or censor comments made by users or content provided by contributors and we are not responsible for the accuracy, completeness, appropriateness or legality of anything posted, depicted or otherwise provided by third‑party users and we disclaim any and all liability relating thereto.
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.3
1
+ Metadata-Version: 2.4
2
2
  Name: browsergym-workarena
3
- Version: 0.4.1
3
+ Version: 0.4.3
4
4
  Summary: WorkArena benchmark for BrowserGym
5
5
  Project-URL: homepage, https://github.com/ServiceNow/WorkArena
6
6
  Author: Léo Boisvert, Alex Drouin, Maxime Gasse, Alex Lacoste, Manuel Del Verme, Megh Thakkar
@@ -22,20 +22,44 @@ Requires-Dist: tenacity>=8.2.3
22
22
  Requires-Dist: tqdm>=4.66.2
23
23
  Description-Content-Type: text/markdown
24
24
 
25
+ <a href="./assets/WorkArena_banner.png">
26
+ <img src="./assets/WorkArena_banner.png" width="1000" />
27
+ </a>
28
+
25
29
  # WorkArena: A Benchmark for Evaluating Agents on Knowledge Work Tasks
26
- [[Benchmark Contents]](#benchmark-contents) ♦ [[Getting Started]](#getting-started) ♦ [[Live Demo]](#live-demo) ♦ [[BrowserGym]](https://github.com/ServiceNow/BrowserGym) ♦ [[Citing This Work]](#citing-this-work)
30
+ [[Benchmark Contents]](#benchmark-contents) ♦ [[Getting Started]](#getting-started) ♦ [[Live Demo]](#live-demo) ♦ [[BrowserGym]](https://github.com/ServiceNow/BrowserGym) ♦ [[Citing This Work]](#citing-this-work) ♦ [Join us on Discord!](https://discord.gg/rDkP69X7)
31
+
32
+ ## Join Our Discord Community
33
+
34
+ Want to brainstorm ideas, troubleshoot issues, or just geek out with fellow agent builders? Our official Discord server is the perfect place to connect and collaborate. Come hang out with us to:
35
+
36
+ - Exchange tips, tricks, and success stories
37
+ - Get real-time support and feedback
38
+ - Stay updated on the latest features and announcements
39
+
40
+ [Join us on Discord!](https://discord.gg/rDkP69X7)
41
+
42
+ ---
43
+
44
+ ### Explore the BrowserGym Ecosystem
45
+
46
+ Looking for more tools and resources? Check out these open-source projects:
47
+
48
+ - **[AgentLab](https://github.com/ServiceNow/AgentLab)**
49
+ - **[BrowserGym](https://github.com/ServiceNow/BrowserGym)**
50
+
51
+ Both are part of the broader [BrowserGym ecosystem](https://arxiv.org/abs/2412.05467)
27
52
 
28
53
  ### Papers
29
54
  * [ICML 2024] WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks? [[Paper]](https://arxiv.org/abs/2403.07718)
30
55
 
31
- * WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks [[Paper]](https://arxiv.org/abs/2407.05291)
56
+ * [NeurIPS 2024] WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks [[Paper]](https://arxiv.org/abs/2407.05291)
32
57
 
33
58
 
34
59
  `WorkArena` is a suite of browser-based tasks tailored to gauge web agents' effectiveness in supporting routine tasks for knowledge workers.
35
60
  By harnessing the ubiquitous [ServiceNow](https://www.servicenow.com/what-is-servicenow.html) platform, this benchmark will be instrumental in assessing the widespread state of such automations in modern knowledge work environments.
36
61
 
37
- WorkArena is included in [BrowserGym](https://github.com/ServiceNow/BrowserGym), a conversational gym environment for the evaluation of web agents.
38
-
62
+ The preferred way to evaluate on WorkArena is with [AgentLab](https://github.com/ServiceNow/AgentLab/) which will conduct parallel experiments through [BrowserGym](https://github.com/ServiceNow/BrowserGym) and report on a [unified leaderboard](https://huggingface.co/spaces/ServiceNow/browsergym-leaderboard).
39
63
 
40
64
  https://github.com/ServiceNow/WorkArena/assets/2374980/68640f09-7d6f-4eb1-b556-c294a6afef70
41
65
 
@@ -48,7 +72,9 @@ To setup WorkArena, you will need to get your own ServiceNow instance, install o
48
72
  1. Go to https://developer.servicenow.com/ and create an account.
49
73
  2. Click on `Request an instance` and select the `Washington` release (initializing the instance will take a few minutes)
50
74
  3. Once the instance is ready, you should see your instance URL and credentials. If not, click _Return to the Developer Portal_, then navigate to _Manage instance password_ and click _Reset instance password_.
51
- 4. You should now see your URL and credentials. Based on this information, set the following environment variables:
75
+ 4. Change the role of the user to admin in yoyr instance parameters ![image](https://github.com/user-attachments/assets/6f0fbf8e-f40f-411a-84cb-fead93d85f60)
76
+
77
+ 5. You should now see your URL and credentials. Based on this information, set the following environment variables:
52
78
  * `SNOW_INSTANCE_URL`: The URL of your ServiceNow developer instance
53
79
  * `SNOW_INSTANCE_UNAME`: The username, should be "admin"
54
80
  * `SNOW_INSTANCE_PWD`: The password, make sure you place the value in quotes "" and be mindful of [escaping special shell characters](https://onlinelinuxtools.com/escape-shell-characters). Running `echo $SNOW_INSTANCE_PWD` should print the correct password.
@@ -123,41 +149,6 @@ https://github.com/ServiceNow/WorkArena/assets/1726818/ca26dfaf-2358-4418-855f-8
123
149
 
124
150
  https://github.com/ServiceNow/WorkArena/assets/1726818/0023232c-081f-4be4-99bd-f60c766e6c3f
125
151
 
126
- ## Getting Started
127
-
128
- To setup WorkArena, you will need to get your own ServiceNow instance, install our Python package, and upload some data to your instance. Follow the steps below to achieve this.
129
-
130
- ### a) Create a ServiceNow Developer Instance
131
-
132
- 1. Go to https://developer.servicenow.com/ and create an account.
133
- 2. Click on `Request an instance` and select the `Washington` release (initializing the instance will take a few minutes)
134
- 3. Once the instance is ready, you should see your instance URL and credentials. If not, click _Return to the Developer Portal_, then navigate to _Manage instance password_ and click _Reset instance password_.
135
- 4. You should now see your URL and credentials. Based on this information, set the following environment variables:
136
- * `SNOW_INSTANCE_URL`: The URL of your ServiceNow developer instance
137
- * `SNOW_INSTANCE_UNAME`: The username, should be "admin"
138
- * `SNOW_INSTANCE_PWD`: The password, make sure you place the value in single quotes '' and be mindful of [escaping special shell characters](https://onlinelinuxtools.com/escape-shell-characters). Running `echo $SNOW_INSTANCE_PWD` should print the correct password.
139
- 6. Log into your instance via a browser using the admin credentials. Close any popup that appears on the main screen (e.g., agreeing to analytics).
140
-
141
- **Warning:** Feel free to look around the platform, but please make sure you revert any changes (e.g., changes to list views, pinning some menus, etc.) as these changes will be persistent and affect the benchmarking process.
142
-
143
- ### b) Install WorkArena and Initialize your Instance
144
-
145
- Run the following command to install WorkArena in the [BrowswerGym](https://github.com/servicenow/browsergym) environment:
146
- ```
147
- pip install browsergym-workarena
148
- ```
149
-
150
- Then, install [Playwright](https://github.com/microsoft/playwright):
151
- ```
152
- playwright install
153
- ```
154
-
155
- Finally, run this command in a terminal to upload the benchmark data to your ServiceNow instance:
156
- ```
157
- workarena-install
158
- ```
159
- Your installation is now complete! 🎉
160
-
161
152
  ## Live Demo
162
153
 
163
154
  Run this code to see WorkArena in action.
@@ -169,12 +160,12 @@ Note: the following example executes WorkArena's oracle (cheat) function to solv
169
160
  import random
170
161
 
171
162
  from browsergym.core.env import BrowserEnv
172
- from browsergym.workarena import ALL_WORKARENA_TASKS
163
+ from browsergym.workarena import ATOMIC_TASKS
173
164
  from time import sleep
174
165
 
175
166
 
176
- random.shuffle(ALL_WORKARENA_TASKS)
177
- for task in ALL_WORKARENA_TASKS:
167
+ random.shuffle(ATOMIC_TASKS)
168
+ for task in ATOMIC_TASKS:
178
169
  print("Task:", task)
179
170
 
180
171
  # Instantiate a new environment
@@ -276,4 +267,4 @@ Please use the following BibTeX to cite our work:
276
267
  primaryClass={cs.AI},
277
268
  url={https://arxiv.org/abs/2407.05291},
278
269
  }
279
- ```
270
+ ```
@@ -1,17 +1,41 @@
1
+ <a href="./assets/WorkArena_banner.png">
2
+ <img src="./assets/WorkArena_banner.png" width="1000" />
3
+ </a>
4
+
1
5
  # WorkArena: A Benchmark for Evaluating Agents on Knowledge Work Tasks
2
- [[Benchmark Contents]](#benchmark-contents) ♦ [[Getting Started]](#getting-started) ♦ [[Live Demo]](#live-demo) ♦ [[BrowserGym]](https://github.com/ServiceNow/BrowserGym) ♦ [[Citing This Work]](#citing-this-work)
6
+ [[Benchmark Contents]](#benchmark-contents) ♦ [[Getting Started]](#getting-started) ♦ [[Live Demo]](#live-demo) ♦ [[BrowserGym]](https://github.com/ServiceNow/BrowserGym) ♦ [[Citing This Work]](#citing-this-work) ♦ [Join us on Discord!](https://discord.gg/rDkP69X7)
7
+
8
+ ## Join Our Discord Community
9
+
10
+ Want to brainstorm ideas, troubleshoot issues, or just geek out with fellow agent builders? Our official Discord server is the perfect place to connect and collaborate. Come hang out with us to:
11
+
12
+ - Exchange tips, tricks, and success stories
13
+ - Get real-time support and feedback
14
+ - Stay updated on the latest features and announcements
15
+
16
+ [Join us on Discord!](https://discord.gg/rDkP69X7)
17
+
18
+ ---
19
+
20
+ ### Explore the BrowserGym Ecosystem
21
+
22
+ Looking for more tools and resources? Check out these open-source projects:
23
+
24
+ - **[AgentLab](https://github.com/ServiceNow/AgentLab)**
25
+ - **[BrowserGym](https://github.com/ServiceNow/BrowserGym)**
26
+
27
+ Both are part of the broader [BrowserGym ecosystem](https://arxiv.org/abs/2412.05467)
3
28
 
4
29
  ### Papers
5
30
  * [ICML 2024] WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks? [[Paper]](https://arxiv.org/abs/2403.07718)
6
31
 
7
- * WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks [[Paper]](https://arxiv.org/abs/2407.05291)
32
+ * [NeurIPS 2024] WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks [[Paper]](https://arxiv.org/abs/2407.05291)
8
33
 
9
34
 
10
35
  `WorkArena` is a suite of browser-based tasks tailored to gauge web agents' effectiveness in supporting routine tasks for knowledge workers.
11
36
  By harnessing the ubiquitous [ServiceNow](https://www.servicenow.com/what-is-servicenow.html) platform, this benchmark will be instrumental in assessing the widespread state of such automations in modern knowledge work environments.
12
37
 
13
- WorkArena is included in [BrowserGym](https://github.com/ServiceNow/BrowserGym), a conversational gym environment for the evaluation of web agents.
14
-
38
+ The preferred way to evaluate on WorkArena is with [AgentLab](https://github.com/ServiceNow/AgentLab/) which will conduct parallel experiments through [BrowserGym](https://github.com/ServiceNow/BrowserGym) and report on a [unified leaderboard](https://huggingface.co/spaces/ServiceNow/browsergym-leaderboard).
15
39
 
16
40
  https://github.com/ServiceNow/WorkArena/assets/2374980/68640f09-7d6f-4eb1-b556-c294a6afef70
17
41
 
@@ -24,7 +48,9 @@ To setup WorkArena, you will need to get your own ServiceNow instance, install o
24
48
  1. Go to https://developer.servicenow.com/ and create an account.
25
49
  2. Click on `Request an instance` and select the `Washington` release (initializing the instance will take a few minutes)
26
50
  3. Once the instance is ready, you should see your instance URL and credentials. If not, click _Return to the Developer Portal_, then navigate to _Manage instance password_ and click _Reset instance password_.
27
- 4. You should now see your URL and credentials. Based on this information, set the following environment variables:
51
+ 4. Change the role of the user to admin in yoyr instance parameters ![image](https://github.com/user-attachments/assets/6f0fbf8e-f40f-411a-84cb-fead93d85f60)
52
+
53
+ 5. You should now see your URL and credentials. Based on this information, set the following environment variables:
28
54
  * `SNOW_INSTANCE_URL`: The URL of your ServiceNow developer instance
29
55
  * `SNOW_INSTANCE_UNAME`: The username, should be "admin"
30
56
  * `SNOW_INSTANCE_PWD`: The password, make sure you place the value in quotes "" and be mindful of [escaping special shell characters](https://onlinelinuxtools.com/escape-shell-characters). Running `echo $SNOW_INSTANCE_PWD` should print the correct password.
@@ -99,41 +125,6 @@ https://github.com/ServiceNow/WorkArena/assets/1726818/ca26dfaf-2358-4418-855f-8
99
125
 
100
126
  https://github.com/ServiceNow/WorkArena/assets/1726818/0023232c-081f-4be4-99bd-f60c766e6c3f
101
127
 
102
- ## Getting Started
103
-
104
- To setup WorkArena, you will need to get your own ServiceNow instance, install our Python package, and upload some data to your instance. Follow the steps below to achieve this.
105
-
106
- ### a) Create a ServiceNow Developer Instance
107
-
108
- 1. Go to https://developer.servicenow.com/ and create an account.
109
- 2. Click on `Request an instance` and select the `Washington` release (initializing the instance will take a few minutes)
110
- 3. Once the instance is ready, you should see your instance URL and credentials. If not, click _Return to the Developer Portal_, then navigate to _Manage instance password_ and click _Reset instance password_.
111
- 4. You should now see your URL and credentials. Based on this information, set the following environment variables:
112
- * `SNOW_INSTANCE_URL`: The URL of your ServiceNow developer instance
113
- * `SNOW_INSTANCE_UNAME`: The username, should be "admin"
114
- * `SNOW_INSTANCE_PWD`: The password, make sure you place the value in single quotes '' and be mindful of [escaping special shell characters](https://onlinelinuxtools.com/escape-shell-characters). Running `echo $SNOW_INSTANCE_PWD` should print the correct password.
115
- 6. Log into your instance via a browser using the admin credentials. Close any popup that appears on the main screen (e.g., agreeing to analytics).
116
-
117
- **Warning:** Feel free to look around the platform, but please make sure you revert any changes (e.g., changes to list views, pinning some menus, etc.) as these changes will be persistent and affect the benchmarking process.
118
-
119
- ### b) Install WorkArena and Initialize your Instance
120
-
121
- Run the following command to install WorkArena in the [BrowswerGym](https://github.com/servicenow/browsergym) environment:
122
- ```
123
- pip install browsergym-workarena
124
- ```
125
-
126
- Then, install [Playwright](https://github.com/microsoft/playwright):
127
- ```
128
- playwright install
129
- ```
130
-
131
- Finally, run this command in a terminal to upload the benchmark data to your ServiceNow instance:
132
- ```
133
- workarena-install
134
- ```
135
- Your installation is now complete! 🎉
136
-
137
128
  ## Live Demo
138
129
 
139
130
  Run this code to see WorkArena in action.
@@ -145,12 +136,12 @@ Note: the following example executes WorkArena's oracle (cheat) function to solv
145
136
  import random
146
137
 
147
138
  from browsergym.core.env import BrowserEnv
148
- from browsergym.workarena import ALL_WORKARENA_TASKS
139
+ from browsergym.workarena import ATOMIC_TASKS
149
140
  from time import sleep
150
141
 
151
142
 
152
- random.shuffle(ALL_WORKARENA_TASKS)
153
- for task in ALL_WORKARENA_TASKS:
143
+ random.shuffle(ATOMIC_TASKS)
144
+ for task in ATOMIC_TASKS:
154
145
  print("Task:", task)
155
146
 
156
147
  # Instantiate a new environment
@@ -252,4 +243,4 @@ Please use the following BibTeX to cite our work:
252
243
  primaryClass={cs.AI},
253
244
  url={https://arxiv.org/abs/2407.05291},
254
245
  }
255
- ```
246
+ ```
@@ -0,0 +1,22 @@
1
+ # Security Policy
2
+
3
+ ## Reporting a Vulnerability
4
+
5
+ If you find a vulnerability in ServiceNow systems, products, or network infrastructure, our [Responsible Disclosure Program](https://www.servicenow.com/company/trust/privacy/responsible-disclosure.html#our+Commitment) is the place to make a report.
6
+
7
+ If you find a vulnerability in this open-source project published by the ServiceNow Research team, please email [servicenow-research@servicenow.com](servicenow-research@servicenow.com) to report your findings.
8
+
9
+ We will process your report as soon as possible, depending on the severity of your report. We appreciate everyone’s help in disclosing vulnerabilities in a responsible manner.
10
+
11
+ ## Guidelines
12
+
13
+ Please follow the guidelines below when disclosing vulnerabilities:
14
+
15
+ - Report any potential security issue as soon as possible. We will make every effort to quickly resolve the issue.
16
+ - Provide sufficient detail to reproduce the vulnerability, including proof of concept.
17
+ - Please do not disclose an issue to the public or a third party until ServiceNow has resolved it.
18
+ - Make a good faith effort to avoid privacy violations, destruction of data, and interruption or degradation of our service. Only interact with accounts you own or accounts for which you have the explicit permission of the account holder.
19
+ - Redact any language or images that may identify the program or ServiceNow customers from information about a fixed vulnerability.
20
+ - Do not engage in disruptive testing (such as DoS) or any action that could impact the confidentiality, integrity, or availability of information and systems.
21
+ - Do not engage in social engineering or phishing of customers or employees.
22
+ - Please do not request compensation for time and materials or discovered vulnerabilities.
@@ -1,4 +1,4 @@
1
- __version__ = "0.4.1"
1
+ __version__ = "0.4.3"
2
2
 
3
3
  import inspect
4
4
  from logging import warning
@@ -224,4 +224,4 @@ EXPECTED_REQUEST_ITEM_FORM_FIELDS_PATH = str(
224
224
 
225
225
  # Report date filter patch flag
226
226
  REPORT_PATCH_FLAG = "WORKARENA_DATE_FILTER_PATCH"
227
- REPORT_DATE_FILTER = "2024-04-01"
227
+ REPORT_DATE_FILTER = "2025-07-15"