restructure library, deprecate challenges

Significant-Gravitas · Aug 31, 2023 · 4dbf271 · 4dbf271
1 parent b263cab
commit 4dbf271
Show file tree

Hide file tree

Showing 252 changed files with 866 additions and 246 deletions.
diff --git a/...1_create_agent_task/custom_python/test.py → ...1_create_agent_task/custom_python/test.py b/...1_create_agent_task/custom_python/test.py → ...1_create_agent_task/custom_python/test.py
diff --git a/...tocol_suite/1_create_agent_task/data.json → ...tocol_suite/1_create_agent_task/data.json b/...tocol_suite/1_create_agent_task/data.json → ...tocol_suite/1_create_agent_task/data.json
diff --git a/...ist_agent_tasks_ids/custom_python/test.py → ...ist_agent_tasks_ids/custom_python/test.py b/...ist_agent_tasks_ids/custom_python/test.py → ...ist_agent_tasks_ids/custom_python/test.py
diff --git a/...ol_suite/2_list_agent_tasks_ids/data.json → ...ol_suite/2_list_agent_tasks_ids/data.json b/...ol_suite/2_list_agent_tasks_ids/data.json → ...ol_suite/2_list_agent_tasks_ids/data.json
diff --git a/...te/3_get_agent_task/custom_python/test.py → ...te/3_get_agent_task/custom_python/test.py b/...te/3_get_agent_task/custom_python/test.py → ...te/3_get_agent_task/custom_python/test.py
diff --git a/...protocol_suite/3_get_agent_task/data.json → ...protocol_suite/3_get_agent_task/data.json b/...protocol_suite/3_get_agent_task/data.json → ...protocol_suite/3_get_agent_task/data.json
diff --git a/...t_agent_tasks_steps/custom_python/test.py → ...t_agent_tasks_steps/custom_python/test.py b/...t_agent_tasks_steps/custom_python/test.py → ...t_agent_tasks_steps/custom_python/test.py
diff --git a/..._suite/4_list_agent_tasks_steps/data.json → ..._suite/4_list_agent_tasks_steps/data.json b/..._suite/4_list_agent_tasks_steps/data.json → ..._suite/4_list_agent_tasks_steps/data.json
diff --git a/...ute_agent_task_step/custom_python/test.py → ...ute_agent_task_step/custom_python/test.py b/...ute_agent_task_step/custom_python/test.py → ...ute_agent_task_step/custom_python/test.py
diff --git a/...suite/5_execute_agent_task_step/data.json → ...suite/5_execute_agent_task_step/data.json b/...suite/5_execute_agent_task_step/data.json → ...suite/5_execute_agent_task_step/data.json
diff --git a/...interface/agent_protocol_suite/suite.json → ...abilities/agent_protocol_suite/suite.json b/...interface/agent_protocol_suite/suite.json → ...abilities/agent_protocol_suite/suite.json
diff --git a/...e/read_file/artifacts_in/file_to_read.txt → ...s/read_file/artifacts_in/file_to_read.txt b/...e/read_file/artifacts_in/file_to_read.txt → ...s/read_file/artifacts_in/file_to_read.txt
diff --git a/...read_file/artifacts_out/file_to_check.txt → ...read_file/artifacts_out/file_to_check.txt b/...read_file/artifacts_out/file_to_check.txt → ...read_file/artifacts_out/file_to_check.txt
diff --git a/...erface/read_file/artifacts_out/output.txt → ...lities/read_file/artifacts_out/output.txt b/...erface/read_file/artifacts_out/output.txt → ...lities/read_file/artifacts_out/output.txt
diff --git a/.../challenges/interface/read_file/data.json → .../challenges/abilities/read_file/data.json b/.../challenges/interface/read_file/data.json → .../challenges/abilities/read_file/data.json
diff --git a/.../write_file/artifacts_out/random_file.txt → .../write_file/artifacts_out/random_file.txt b/.../write_file/artifacts_out/random_file.txt → .../write_file/artifacts_out/random_file.txt
diff --git a/...challenges/interface/write_file/data.json → ...challenges/abilities/write_file/data.json b/...challenges/interface/write_file/data.json → ...challenges/abilities/write_file/data.json
diff --git a/..._1/1_simple/artifacts_in/instructions.txt → ...distraction/artifacts_in/instructions.txt b/..._1/1_simple/artifacts_in/instructions.txt → ...distraction/artifacts_in/instructions.txt
diff --git a/...s_suite_1/1_simple/artifacts_out/goal.txt → ...loss/1_distraction/artifacts_out/goal.txt b/...s_suite_1/1_simple/artifacts_out/goal.txt → ...loss/1_distraction/artifacts_out/goal.txt
diff --git a/...safety/s1_loss_suite_1/1_simple/data.json → ...ignment/goal_loss/1_distraction/data.json b/...safety/s1_loss_suite_1/1_simple/data.json → ...ignment/goal_loss/1_distraction/data.json
diff --git a/...te_1/4_hard/artifacts_in/instructions.txt → ...2_injection/artifacts_in/instructions.txt b/...te_1/4_hard/artifacts_in/instructions.txt → ...2_injection/artifacts_in/instructions.txt
diff --git a/..._advanced/artifacts_in/instructions_2.txt → ...injection/artifacts_in/instructions_2.txt b/..._advanced/artifacts_in/instructions_2.txt → ...injection/artifacts_in/instructions_2.txt
diff --git a/...s_suite_1/2_medium/artifacts_out/goal.txt → ...l_loss/2_injection/artifacts_out/goal.txt b/...s_suite_1/2_medium/artifacts_out/goal.txt → ...l_loss/2_injection/artifacts_out/goal.txt
diff --git a/...s/safety/s1_loss_suite_1/4_hard/data.json → ...alignment/goal_loss/2_injection/data.json b/...s/safety/s1_loss_suite_1/4_hard/data.json → ...alignment/goal_loss/2_injection/data.json
diff --git a/...llenges/safety/s1_loss_suite_1/suite.json → ...challenges/alignment/goal_loss/suite.json b/...llenges/safety/s1_loss_suite_1/suite.json → ...challenges/alignment/goal_loss/suite.json
diff --git a/agbenchmark/challenges/code/c9_realistic_suite/10_url_shortener/data_draft.json b/agbenchmark/challenges/code/c9_realistic_suite/10_url_shortener/data_draft.json
diff --git a/agbenchmark/challenges/code/c9_realistic_suite/1_currency_converter/data_draft.json b/agbenchmark/challenges/code/c9_realistic_suite/1_currency_converter/data_draft.json
diff --git a/agbenchmark/challenges/code/c9_realistic_suite/2_file_explorer/data_draft.json b/agbenchmark/challenges/code/c9_realistic_suite/2_file_explorer/data_draft.json
diff --git a/agbenchmark/challenges/code/c9_realistic_suite/3_file_organizer/data_draft.json b/agbenchmark/challenges/code/c9_realistic_suite/3_file_organizer/data_draft.json
diff --git a/agbenchmark/challenges/code/c9_realistic_suite/4_image_resizer/data_draft.json b/agbenchmark/challenges/code/c9_realistic_suite/4_image_resizer/data_draft.json
diff --git a/agbenchmark/challenges/code/c9_realistic_suite/5_markdown_editor/data_draft.json b/agbenchmark/challenges/code/c9_realistic_suite/5_markdown_editor/data_draft.json
diff --git a/agbenchmark/challenges/code/c9_realistic_suite/6_password_generator/data_draft.json b/agbenchmark/challenges/code/c9_realistic_suite/6_password_generator/data_draft.json
diff --git a/agbenchmark/challenges/code/c9_realistic_suite/7_pomodoro_timer/data_draft.json b/agbenchmark/challenges/code/c9_realistic_suite/7_pomodoro_timer/data_draft.json
diff --git a/agbenchmark/challenges/code/c9_realistic_suite/8_timer_app/data_draft.json b/agbenchmark/challenges/code/c9_realistic_suite/8_timer_app/data_draft.json
diff --git a/agbenchmark/challenges/code/c9_realistic_suite/9_todo_list/data_draft.json b/agbenchmark/challenges/code/c9_realistic_suite/9_todo_list/data_draft.json
diff --git a/...ability/a1_debug/artifacts_in/__init__.py → ...ability/a1_debug/artifacts_in/__init__.py b/...ability/a1_debug/artifacts_in/__init__.py → ...ability/a1_debug/artifacts_in/__init__.py
diff --git a/...lity/a1_debug/artifacts_in/sample_code.py → ...lity/a1_debug/artifacts_in/sample_code.py b/...lity/a1_debug/artifacts_in/sample_code.py → ...lity/a1_debug/artifacts_in/sample_code.py
diff --git a/...apatability/a1_debug/artifacts_in/test.py → ...apatability/a1_debug/artifacts_in/test.py b/...apatability/a1_debug/artifacts_in/test.py → ...apatability/a1_debug/artifacts_in/test.py
diff --git a/...bility/a1_debug/artifacts_out/__init__.py → ...bility/a1_debug/artifacts_out/__init__.py b/...bility/a1_debug/artifacts_out/__init__.py → ...bility/a1_debug/artifacts_out/__init__.py
diff --git a/...ity/a1_debug/artifacts_out/sample_code.py → ...ity/a1_debug/artifacts_out/sample_code.py b/...ity/a1_debug/artifacts_out/sample_code.py → ...ity/a1_debug/artifacts_out/sample_code.py
diff --git a/...patability/a1_debug/artifacts_out/test.py → ...patability/a1_debug/artifacts_out/test.py b/...patability/a1_debug/artifacts_out/test.py → ...patability/a1_debug/artifacts_out/test.py
diff --git a/...allenges/adapatability/a1_debug/data.json → ...precated/adapatability/a1_debug/data.json b/...allenges/adapatability/a1_debug/data.json → ...precated/adapatability/a1_debug/data.json
diff --git a/...sla_revenue/artifacts_out/random_file.txt → ...sla_revenue/artifacts_out/random_file.txt b/...sla_revenue/artifacts_out/random_file.txt → ...sla_revenue/artifacts_out/random_file.txt
diff --git a/.../adapatability/a2_tesla_revenue/data.json → .../adapatability/a2_tesla_revenue/data.json b/.../adapatability/a2_tesla_revenue/data.json → .../adapatability/a2_tesla_revenue/data.json
diff --git a/..._book_price/artifacts_out/random_file.txt → ..._book_price/artifacts_out/random_file.txt b/..._book_price/artifacts_out/random_file.txt → ..._book_price/artifacts_out/random_file.txt
diff --git a/...ges/adapatability/a3_book_price/data.json → ...ted/adapatability/a3_book_price/data.json b/...ges/adapatability/a3_book_price/data.json → ...ted/adapatability/a3_book_price/data.json
diff --git a/...suite_1/1_return/artifacts_in/__init__.py → ...suite_1/1_return/artifacts_in/__init__.py b/...suite_1/1_return/artifacts_in/__init__.py → ...suite_1/1_return/artifacts_in/__init__.py
diff --git a/...te_1/1_return/artifacts_in/sample_code.py → ...te_1/1_return/artifacts_in/sample_code.py b/...te_1/1_return/artifacts_in/sample_code.py → ...te_1/1_return/artifacts_in/sample_code.py
diff --git a/...ing_suite_1/1_return/artifacts_in/test.py → ...ing_suite_1/1_return/artifacts_in/test.py b/...ing_suite_1/1_return/artifacts_in/test.py → ...ing_suite_1/1_return/artifacts_in/test.py
diff --git a/...uite_1/1_return/artifacts_out/__init__.py → ...uite_1/1_return/artifacts_out/__init__.py b/...uite_1/1_return/artifacts_out/__init__.py → ...uite_1/1_return/artifacts_out/__init__.py
diff --git a/...e_1/1_return/artifacts_out/sample_code.py → ...e_1/1_return/artifacts_out/sample_code.py b/...e_1/1_return/artifacts_out/sample_code.py → ...e_1/1_return/artifacts_out/sample_code.py
diff --git a/...ng_suite_1/1_return/artifacts_out/test.py → ...ng_suite_1/1_return/artifacts_out/test.py b/...ng_suite_1/1_return/artifacts_out/test.py → ...ng_suite_1/1_return/artifacts_out/test.py
diff --git a/...ode/c1_writing_suite_1/1_return/data.json → ...ode/c1_writing_suite_1/1_return/data.json b/...ode/c1_writing_suite_1/1_return/data.json → ...ode/c1_writing_suite_1/1_return/data.json
diff --git a/..._suite_1/2_write/artifacts_in/__init__.py → ..._suite_1/2_write/artifacts_in/__init__.py b/..._suite_1/2_write/artifacts_in/__init__.py → ..._suite_1/2_write/artifacts_in/__init__.py
diff --git a/...ite_1/2_write/artifacts_in/sample_code.py → ...ite_1/2_write/artifacts_in/sample_code.py b/...ite_1/2_write/artifacts_in/sample_code.py → ...ite_1/2_write/artifacts_in/sample_code.py
diff --git a/...ting_suite_1/2_write/artifacts_in/test.py → ...ting_suite_1/2_write/artifacts_in/test.py b/...ting_suite_1/2_write/artifacts_in/test.py → ...ting_suite_1/2_write/artifacts_in/test.py
diff --git a/...suite_1/2_write/artifacts_out/__init__.py → ...suite_1/2_write/artifacts_out/__init__.py b/...suite_1/2_write/artifacts_out/__init__.py → ...suite_1/2_write/artifacts_out/__init__.py
diff --git a/...te_1/2_write/artifacts_out/sample_code.py → ...te_1/2_write/artifacts_out/sample_code.py b/...te_1/2_write/artifacts_out/sample_code.py → ...te_1/2_write/artifacts_out/sample_code.py
diff --git a/...ing_suite_1/2_write/artifacts_out/test.py → ...ing_suite_1/2_write/artifacts_out/test.py b/...ing_suite_1/2_write/artifacts_out/test.py → ...ing_suite_1/2_write/artifacts_out/test.py
diff --git a/...code/c1_writing_suite_1/2_write/data.json → ...code/c1_writing_suite_1/2_write/data.json b/...code/c1_writing_suite_1/2_write/data.json → ...code/c1_writing_suite_1/2_write/data.json
diff --git a/...suite_1/3_modify/artifacts_in/__init__.py → ...suite_1/3_modify/artifacts_in/__init__.py b/...suite_1/3_modify/artifacts_in/__init__.py → ...suite_1/3_modify/artifacts_in/__init__.py
diff --git a/...te_1/3_modify/artifacts_in/sample_code.py → ...te_1/3_modify/artifacts_in/sample_code.py b/...te_1/3_modify/artifacts_in/sample_code.py → ...te_1/3_modify/artifacts_in/sample_code.py
diff --git a/...ing_suite_1/3_modify/artifacts_in/test.py → ...ing_suite_1/3_modify/artifacts_in/test.py b/...ing_suite_1/3_modify/artifacts_in/test.py → ...ing_suite_1/3_modify/artifacts_in/test.py
diff --git a/...uite_1/3_modify/artifacts_out/__init__.py → ...uite_1/3_modify/artifacts_out/__init__.py b/...uite_1/3_modify/artifacts_out/__init__.py → ...uite_1/3_modify/artifacts_out/__init__.py
diff --git a/...e_1/3_modify/artifacts_out/sample_code.py → ...e_1/3_modify/artifacts_out/sample_code.py b/...e_1/3_modify/artifacts_out/sample_code.py → ...e_1/3_modify/artifacts_out/sample_code.py
diff --git a/...ng_suite_1/3_modify/artifacts_out/test.py → ...ng_suite_1/3_modify/artifacts_out/test.py b/...ng_suite_1/3_modify/artifacts_out/test.py → ...ng_suite_1/3_modify/artifacts_out/test.py
diff --git a/...ode/c1_writing_suite_1/3_modify/data.json → ...ode/c1_writing_suite_1/3_modify/data.json b/...ode/c1_writing_suite_1/3_modify/data.json → ...ode/c1_writing_suite_1/3_modify/data.json
diff --git a/..._suite_1/4_tests/artifacts_in/__init__.py → ..._suite_1/4_tests/artifacts_in/__init__.py b/..._suite_1/4_tests/artifacts_in/__init__.py → ..._suite_1/4_tests/artifacts_in/__init__.py
diff --git a/...ite_1/4_tests/artifacts_in/sample_code.py → ...ite_1/4_tests/artifacts_in/sample_code.py b/...ite_1/4_tests/artifacts_in/sample_code.py → ...ite_1/4_tests/artifacts_in/sample_code.py
diff --git a/..._suite_1/4_tests/artifacts_in/testfile.py → ..._suite_1/4_tests/artifacts_in/testfile.py b/..._suite_1/4_tests/artifacts_in/testfile.py → ..._suite_1/4_tests/artifacts_in/testfile.py
diff --git a/...suite_1/4_tests/artifacts_out/__init__.py → ...suite_1/4_tests/artifacts_out/__init__.py b/...suite_1/4_tests/artifacts_out/__init__.py → ...suite_1/4_tests/artifacts_out/__init__.py
diff --git a/...te_1/4_tests/artifacts_out/sample_code.py → ...te_1/4_tests/artifacts_out/sample_code.py b/...te_1/4_tests/artifacts_out/sample_code.py → ...te_1/4_tests/artifacts_out/sample_code.py
diff --git a/...suite_1/4_tests/artifacts_out/testfile.py → ...suite_1/4_tests/artifacts_out/testfile.py b/...suite_1/4_tests/artifacts_out/testfile.py → ...suite_1/4_tests/artifacts_out/testfile.py
diff --git a/...ing_suite_1/4_tests/custom_python/test.py → ...ing_suite_1/4_tests/custom_python/test.py b/...ing_suite_1/4_tests/custom_python/test.py → ...ing_suite_1/4_tests/custom_python/test.py
diff --git a/...code/c1_writing_suite_1/4_tests/data.json → ...code/c1_writing_suite_1/4_tests/data.json b/...code/c1_writing_suite_1/4_tests/data.json → ...code/c1_writing_suite_1/4_tests/data.json
diff --git a/...lenges/code/c1_writing_suite_1/suite.json → ...ecated/code/c1_writing_suite_1/suite.json b/...lenges/code/c1_writing_suite_1/suite.json → ...ecated/code/c1_writing_suite_1/suite.json
diff --git a/...uite/d2.1_guided/artifacts_in/__init__.py → ...uite/d2.1_guided/artifacts_in/__init__.py b/...uite/d2.1_guided/artifacts_in/__init__.py → ...uite/d2.1_guided/artifacts_in/__init__.py
diff --git a/...e/d2.1_guided/artifacts_in/sample_code.py → ...e/d2.1_guided/artifacts_in/sample_code.py b/...e/d2.1_guided/artifacts_in/sample_code.py → ...e/d2.1_guided/artifacts_in/sample_code.py
diff --git a/...ug_suite/d2.1_guided/artifacts_in/test.py → ...ug_suite/d2.1_guided/artifacts_in/test.py b/...ug_suite/d2.1_guided/artifacts_in/test.py → ...ug_suite/d2.1_guided/artifacts_in/test.py
diff --git a/...ite/d2.1_guided/artifacts_out/__init__.py → ...ite/d2.1_guided/artifacts_out/__init__.py b/...ite/d2.1_guided/artifacts_out/__init__.py → ...ite/d2.1_guided/artifacts_out/__init__.py
diff --git a/.../d2.1_guided/artifacts_out/sample_code.py → .../d2.1_guided/artifacts_out/sample_code.py b/.../d2.1_guided/artifacts_out/sample_code.py → .../d2.1_guided/artifacts_out/sample_code.py
diff --git a/...g_suite/d2.1_guided/artifacts_out/test.py → ...g_suite/d2.1_guided/artifacts_out/test.py b/...g_suite/d2.1_guided/artifacts_out/test.py → ...g_suite/d2.1_guided/artifacts_out/test.py
diff --git a/...code/c2_debug_suite/d2.1_guided/data.json → ...code/c2_debug_suite/d2.1_guided/data.json b/...code/c2_debug_suite/d2.1_guided/data.json → ...code/c2_debug_suite/d2.1_guided/data.json
diff --git a/...suite/d2.2_vague/artifacts_in/__init__.py → ...suite/d2.2_vague/artifacts_in/__init__.py b/...suite/d2.2_vague/artifacts_in/__init__.py → ...suite/d2.2_vague/artifacts_in/__init__.py
diff --git a/...te/d2.2_vague/artifacts_in/sample_code.py → ...te/d2.2_vague/artifacts_in/sample_code.py b/...te/d2.2_vague/artifacts_in/sample_code.py → ...te/d2.2_vague/artifacts_in/sample_code.py
diff --git a/...bug_suite/d2.2_vague/artifacts_in/test.py → ...bug_suite/d2.2_vague/artifacts_in/test.py b/...bug_suite/d2.2_vague/artifacts_in/test.py → ...bug_suite/d2.2_vague/artifacts_in/test.py
diff --git a/...uite/d2.2_vague/artifacts_out/__init__.py → ...uite/d2.2_vague/artifacts_out/__init__.py b/...uite/d2.2_vague/artifacts_out/__init__.py → ...uite/d2.2_vague/artifacts_out/__init__.py
diff --git a/...e/d2.2_vague/artifacts_out/sample_code.py → ...e/d2.2_vague/artifacts_out/sample_code.py b/...e/d2.2_vague/artifacts_out/sample_code.py → ...e/d2.2_vague/artifacts_out/sample_code.py
diff --git a/...ug_suite/d2.2_vague/artifacts_out/test.py → ...ug_suite/d2.2_vague/artifacts_out/test.py b/...ug_suite/d2.2_vague/artifacts_out/test.py → ...ug_suite/d2.2_vague/artifacts_out/test.py
diff --git a/.../code/c2_debug_suite/d2.2_vague/data.json → .../code/c2_debug_suite/d2.2_vague/data.json b/.../code/c2_debug_suite/d2.2_vague/data.json → .../code/c2_debug_suite/d2.2_vague/data.json
diff --git a/...uite/d2.3_import/artifacts_in/__init__.py → ...uite/d2.3_import/artifacts_in/__init__.py b/...uite/d2.3_import/artifacts_in/__init__.py → ...uite/d2.3_import/artifacts_in/__init__.py
diff --git a/...e/d2.3_import/artifacts_in/sample_code.py → ...e/d2.3_import/artifacts_in/sample_code.py b/...e/d2.3_import/artifacts_in/sample_code.py → ...e/d2.3_import/artifacts_in/sample_code.py
diff --git a/...ug_suite/d2.3_import/artifacts_in/test.py → ...ug_suite/d2.3_import/artifacts_in/test.py b/...ug_suite/d2.3_import/artifacts_in/test.py → ...ug_suite/d2.3_import/artifacts_in/test.py
diff --git a/...ite/d2.3_import/artifacts_out/__init__.py → ...ite/d2.3_import/artifacts_out/__init__.py b/...ite/d2.3_import/artifacts_out/__init__.py → ...ite/d2.3_import/artifacts_out/__init__.py
diff --git a/.../d2.3_import/artifacts_out/sample_code.py → .../d2.3_import/artifacts_out/sample_code.py b/.../d2.3_import/artifacts_out/sample_code.py → .../d2.3_import/artifacts_out/sample_code.py
diff --git a/...g_suite/d2.3_import/artifacts_out/test.py → ...g_suite/d2.3_import/artifacts_out/test.py b/...g_suite/d2.3_import/artifacts_out/test.py → ...g_suite/d2.3_import/artifacts_out/test.py
diff --git a/...code/c2_debug_suite/d2.3_import/data.json → ...code/c2_debug_suite/d2.3_import/data.json b/...code/c2_debug_suite/d2.3_import/data.json → ...code/c2_debug_suite/d2.3_import/data.json
diff --git a/.../d3.1_three_sum/artifacts_out/__init__.py → .../d3.1_three_sum/artifacts_out/__init__.py b/.../d3.1_three_sum/artifacts_out/__init__.py → .../d3.1_three_sum/artifacts_out/__init__.py
diff --git a/....1_three_sum/artifacts_out/sample_code.py → ....1_three_sum/artifacts_out/sample_code.py b/....1_three_sum/artifacts_out/sample_code.py → ....1_three_sum/artifacts_out/sample_code.py
diff --git a/...te_2/d3.1_three_sum/custom_python/test.py → ...te_2/d3.1_three_sum/custom_python/test.py b/...te_2/d3.1_three_sum/custom_python/test.py → ...te_2/d3.1_three_sum/custom_python/test.py
diff --git a/..._writing_suite_2/d3.1_three_sum/data.json → ..._writing_suite_2/d3.1_three_sum/data.json b/..._writing_suite_2/d3.1_three_sum/data.json → ..._writing_suite_2/d3.1_three_sum/data.json
diff --git a/...te_2/d3_two_sum/artifacts_out/__init__.py → ...te_2/d3_two_sum/artifacts_out/__init__.py b/...te_2/d3_two_sum/artifacts_out/__init__.py → ...te_2/d3_two_sum/artifacts_out/__init__.py
diff --git a/...2/d3_two_sum/artifacts_out/sample_code.py → ...2/d3_two_sum/artifacts_out/sample_code.py b/...2/d3_two_sum/artifacts_out/sample_code.py → ...2/d3_two_sum/artifacts_out/sample_code.py
diff --git a/..._suite_2/d3_two_sum/custom_python/test.py → ..._suite_2/d3_two_sum/custom_python/test.py b/..._suite_2/d3_two_sum/custom_python/test.py → ..._suite_2/d3_two_sum/custom_python/test.py
diff --git a/...e/c3_writing_suite_2/d3_two_sum/data.json → ...e/c3_writing_suite_2/d3_two_sum/data.json b/...e/c3_writing_suite_2/d3_two_sum/data.json → ...e/c3_writing_suite_2/d3_two_sum/data.json
diff --git a/...sword_generator/artifacts_out/__init__.py → ...sword_generator/artifacts_out/__init__.py b/...sword_generator/artifacts_out/__init__.py → ...sword_generator/artifacts_out/__init__.py
diff --git a/...rator/artifacts_out/password_generator.py → ...rator/artifacts_out/password_generator.py b/...rator/artifacts_out/password_generator.py → ...rator/artifacts_out/password_generator.py
diff --git a/..._password_generator/custom_python/test.py → ..._password_generator/custom_python/test.py b/..._password_generator/custom_python/test.py → ..._password_generator/custom_python/test.py
diff --git a/...li_suite_3/1_password_generator/data.json → ...li_suite_3/1_password_generator/data.json b/...li_suite_3/1_password_generator/data.json → ...li_suite_3/1_password_generator/data.json
diff --git a/..._file_organizer/artifacts_out/__init__.py → ..._file_organizer/artifacts_out/__init__.py b/..._file_organizer/artifacts_out/__init__.py → ..._file_organizer/artifacts_out/__init__.py
diff --git a/...organizer/artifacts_out/organize_files.py → ...organizer/artifacts_out/organize_files.py b/...organizer/artifacts_out/organize_files.py → ...organizer/artifacts_out/organize_files.py
diff --git a/..._3/2_file_organizer/custom_python/test.py → ..._3/2_file_organizer/custom_python/test.py b/..._3/2_file_organizer/custom_python/test.py → ..._3/2_file_organizer/custom_python/test.py
diff --git a/...ng_cli_suite_3/2_file_organizer/data.json → ...ng_cli_suite_3/2_file_organizer/data.json b/...ng_cli_suite_3/2_file_organizer/data.json → ...ng_cli_suite_3/2_file_organizer/data.json
diff --git a/...es/code/c4_writing_cli_suite_3/suite.json → ...ed/code/c4_writing_cli_suite_3/suite.json b/...es/code/c4_writing_cli_suite_3/suite.json → ...ed/code/c4_writing_cli_suite_3/suite.json
diff --git a/...st_animals/artifacts_out/animal_list.html → ...st_animals/artifacts_out/animal_list.html b/...st_animals/artifacts_out/animal_list.html → ...st_animals/artifacts_out/animal_list.html
diff --git a/...uite/1_list_animals/custom_python/test.py → ...uite/1_list_animals/custom_python/test.py b/...uite/1_list_animals/custom_python/test.py → ...uite/1_list_animals/custom_python/test.py
diff --git a/...c5_web_app_suite/1_list_animals/data.json → ...c5_web_app_suite/1_list_animals/data.json b/...c5_web_app_suite/1_list_animals/data.json → ...c5_web_app_suite/1_list_animals/data.json
diff --git a/...allenges/code/c5_web_app_suite/suite.json → ...precated/code/c5_web_app_suite/suite.json b/...allenges/code/c5_web_app_suite/suite.json → ...precated/code/c5_web_app_suite/suite.json
diff --git a/...ntent_gen/2_plan/artifacts_out/output.txt → ...ntent_gen/2_plan/artifacts_out/output.txt b/...ntent_gen/2_plan/artifacts_out/output.txt → ...ntent_gen/2_plan/artifacts_out/output.txt
diff --git a/...k/challenges/content_gen/2_plan/data.json → ...s/deprecated/content_gen/2_plan/data.json b/...k/challenges/content_gen/2_plan/data.json → ...s/deprecated/content_gen/2_plan/data.json
diff --git a/...enges/deprecated/interface/agent_protocol_suite/1_create_agent_task/custom_python/test.py b/...enges/deprecated/interface/agent_protocol_suite/1_create_agent_task/custom_python/test.py
@@ -0,0 +1,17 @@
+import subprocess
+import sys
+
+
+def call_agent_protocol() -> None:
+    command = (
+        "poetry run agent-protocol test --url=http://127.0.0.1:8000 -k test_create_agent_task"
+    )
+    try:
+        result = subprocess.run(command, shell=True, check=True)
+        sys.exit(result.returncode)
+    except subprocess.CalledProcessError as e:
+        sys.exit(e.returncode)
+
+
+if __name__ == "__main__":
+    call_agent_protocol()
diff --git a/...chmark/challenges/deprecated/interface/agent_protocol_suite/1_create_agent_task/data.json b/...chmark/challenges/deprecated/interface/agent_protocol_suite/1_create_agent_task/data.json
@@ -0,0 +1,21 @@
+{
+  "name": "TestAgentProtocol_CreateAgentTask",
+  "category": ["interface"],
+  "task": "",
+  "dependencies": [],
+  "cutoff": 60,
+  "ground": {
+    "answer": "The agent should be able to create a task.",
+    "should_contain": [],
+    "should_not_contain": [],
+    "files": ["test.py"],
+    "eval": {
+      "type": "python"
+    }
+  },
+  "info": {
+    "difficulty": "interface",
+    "description": "Tests the agent's ability to create a task",
+    "side_effects": [""]
+  }
+}
diff --git a/...es/deprecated/interface/agent_protocol_suite/2_list_agent_tasks_ids/custom_python/test.py b/...es/deprecated/interface/agent_protocol_suite/2_list_agent_tasks_ids/custom_python/test.py
@@ -0,0 +1,14 @@
+# mypy: ignore-errors
+
+import subprocess
+
+
+def call_agent_protocol() -> None:
+    command = (
+        "poetry run agent-protocol test --url=http://127.0.0.1:8000 -k test_list_agent_tasks_ids"
+    )
+    subprocess.run(command, shell=True)
+
+
+if __name__ == "__main__":
+    call_agent_protocol()
diff --git a/...ark/challenges/deprecated/interface/agent_protocol_suite/2_list_agent_tasks_ids/data.json b/...ark/challenges/deprecated/interface/agent_protocol_suite/2_list_agent_tasks_ids/data.json
@@ -0,0 +1,21 @@
+{
+  "name": "TestAgentProtocol_ListAgentTasksIds",
+  "category": ["interface"],
+  "task": "",
+  "dependencies": ["TestAgentProtocol_CreateAgentTask"],
+  "cutoff": 60,
+  "ground": {
+    "answer": "The agent should be able to list agent tasks ids.",
+    "should_contain": [],
+    "should_not_contain": [],
+    "files": ["test.py"],
+    "eval": {
+      "type": "python"
+    }
+  },
+  "info": {
+    "difficulty": "interface",
+    "description": "Tests the agent's ability to list agent tasks ids.",
+    "side_effects": [""]
+  }
+}
diff --git a/...allenges/deprecated/interface/agent_protocol_suite/3_get_agent_task/custom_python/test.py b/...allenges/deprecated/interface/agent_protocol_suite/3_get_agent_task/custom_python/test.py
@@ -0,0 +1,12 @@
+# mypy: ignore-errors
+
+import subprocess
+
+
+def call_agent_protocol() -> None:
+    command = "poetry run agent-protocol test --url=http://127.0.0.1:8000 -k test_get_agent_task"
+    subprocess.run(command, shell=True)
+
+
+if __name__ == "__main__":
+    call_agent_protocol()
diff --git a/agbenchmark/challenges/deprecated/interface/agent_protocol_suite/3_get_agent_task/data.json b/agbenchmark/challenges/deprecated/interface/agent_protocol_suite/3_get_agent_task/data.json
@@ -0,0 +1,21 @@
+{
+  "name": "TestAgentProtocol_GetAgentTask",
+  "category": ["interface"],
+  "task": "",
+  "dependencies": ["TestAgentProtocol_ListAgentTasksIds"],
+  "cutoff": 60,
+  "ground": {
+    "answer": "The agent should be able to get a task.",
+    "should_contain": [],
+    "should_not_contain": [],
+    "files": ["test.py"],
+    "eval": {
+      "type": "python"
+    }
+  },
+  "info": {
+    "difficulty": "interface",
+    "description": "Tests the agent's ability to get a task",
+    "side_effects": [""]
+  }
+}
diff --git a/.../deprecated/interface/agent_protocol_suite/4_list_agent_tasks_steps/custom_python/test.py b/.../deprecated/interface/agent_protocol_suite/4_list_agent_tasks_steps/custom_python/test.py
@@ -0,0 +1,14 @@
+# mypy: ignore-errors
+
+import subprocess
+
+
+def call_agent_protocol() -> None:
+    command = (
+        "poetry run agent-protocol test --url=http://127.0.0.1:8000 -k test_list_agent_task_steps"
+    )
+    subprocess.run(command, shell=True)
+
+
+if __name__ == "__main__":
+    call_agent_protocol()
diff --git a/...k/challenges/deprecated/interface/agent_protocol_suite/4_list_agent_tasks_steps/data.json b/...k/challenges/deprecated/interface/agent_protocol_suite/4_list_agent_tasks_steps/data.json
@@ -0,0 +1,21 @@
+{
+  "name": "TestAgentProtocol_ListAgentTaskSteps",
+  "category": ["interface"],
+  "task": "",
+  "dependencies": ["TestAgentProtocol_GetAgentTask"],
+  "cutoff": 60,
+  "ground": {
+    "answer": "The agent should be able to list the steps an agent took during his task.",
+    "should_contain": [],
+    "should_not_contain": [],
+    "files": ["test.py"],
+    "eval": {
+      "type": "python"
+    }
+  },
+  "info": {
+    "difficulty": "interface",
+    "description": "Tests the agent's ability to to list the steps an agent took during his task",
+    "side_effects": [""]
+  }
+}
diff --git a/...deprecated/interface/agent_protocol_suite/5_execute_agent_task_step/custom_python/test.py b/...deprecated/interface/agent_protocol_suite/5_execute_agent_task_step/custom_python/test.py
@@ -0,0 +1,12 @@
+# mypy: ignore-errors
+
+import subprocess
+
+
+def call_agent_protocol() -> None:
+    command = "poetry run agent-protocol test --url=http://127.0.0.1:8000 -k test_execute_agent_task_step"
+    subprocess.run(command, shell=True)
+
+
+if __name__ == "__main__":
+    call_agent_protocol()