halo-engine 0.1.1__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 (630) hide show
  1. halo_engine-0.1.1/.githooks/pre-commit +11 -0
  2. halo_engine-0.1.1/.githooks/pre-push +22 -0
  3. halo_engine-0.1.1/.github/workflows/engine--e2e-tests.yml +88 -0
  4. halo_engine-0.1.1/.github/workflows/engine--integration-tests-live.yml +92 -0
  5. halo_engine-0.1.1/.github/workflows/engine--integration-tests.yml +89 -0
  6. halo_engine-0.1.1/.github/workflows/engine--lint-format-typecheck.yml +76 -0
  7. halo_engine-0.1.1/.github/workflows/engine--release.yml +269 -0
  8. halo_engine-0.1.1/.github/workflows/engine--unit-tests.yml +79 -0
  9. halo_engine-0.1.1/.gitignore +20 -0
  10. halo_engine-0.1.1/.infisical.json +5 -0
  11. halo_engine-0.1.1/PKG-INFO +150 -0
  12. halo_engine-0.1.1/README.md +134 -0
  13. halo_engine-0.1.1/Taskfile.yml +237 -0
  14. halo_engine-0.1.1/assets/halo-app-world-sgc.png +0 -0
  15. halo_engine-0.1.1/assets/halo-rlm.png +0 -0
  16. halo_engine-0.1.1/demo/appworld/.env.example +12 -0
  17. halo_engine-0.1.1/demo/appworld/.gitattributes +2 -0
  18. halo_engine-0.1.1/demo/appworld/.gitignore +139 -0
  19. halo_engine-0.1.1/demo/appworld/HALO_PATCH.md +192 -0
  20. halo_engine-0.1.1/demo/appworld/LICENSE +201 -0
  21. halo_engine-0.1.1/demo/appworld/README.md +254 -0
  22. halo_engine-0.1.1/demo/appworld/README.pypi.md +5 -0
  23. halo_engine-0.1.1/demo/appworld/Taskfile.yml +231 -0
  24. halo_engine-0.1.1/demo/appworld/experiments/.env.template +12 -0
  25. halo_engine-0.1.1/demo/appworld/experiments/MANIFEST.in +12 -0
  26. halo_engine-0.1.1/demo/appworld/experiments/README.md +5 -0
  27. halo_engine-0.1.1/demo/appworld/experiments/__init__.py +20 -0
  28. halo_engine-0.1.1/demo/appworld/experiments/code/__init__.py +12 -0
  29. halo_engine-0.1.1/demo/appworld/experiments/code/common/__init__.py +0 -0
  30. halo_engine-0.1.1/demo/appworld/experiments/code/common/api_predictor.py +140 -0
  31. halo_engine-0.1.1/demo/appworld/experiments/code/common/logger.py +203 -0
  32. halo_engine-0.1.1/demo/appworld/experiments/code/common/tool_parsers.py +115 -0
  33. halo_engine-0.1.1/demo/appworld/experiments/code/common/usage_tracker.py +328 -0
  34. halo_engine-0.1.1/demo/appworld/experiments/code/common/utils.py +32 -0
  35. halo_engine-0.1.1/demo/appworld/experiments/code/common/vllm_plugins/__init__.py +16 -0
  36. halo_engine-0.1.1/demo/appworld/experiments/code/common/vllm_plugins/nemotron_toolcall_parser.py +106 -0
  37. halo_engine-0.1.1/demo/appworld/experiments/code/common/vllm_plugins/xlam_tool_call_parser.py +203 -0
  38. halo_engine-0.1.1/demo/appworld/experiments/code/hal/main.py +32 -0
  39. halo_engine-0.1.1/demo/appworld/experiments/code/hal/requirements.txt +2 -0
  40. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/__init__.py +0 -0
  41. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/plain/__init__.py +0 -0
  42. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/plain/agents/__init__.py +8 -0
  43. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/plain/agents/agent.py +149 -0
  44. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/plain/agents/full_code_reflexion_agent.py +349 -0
  45. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/plain/agents/function_calling_agent.py +294 -0
  46. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/plain/agents/lm_agent.py +132 -0
  47. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/plain/language_models/__init__.py +7 -0
  48. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/plain/language_models/language_model.py +11 -0
  49. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/plain/language_models/openai_language_model.py +547 -0
  50. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/plain/run.py +93 -0
  51. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/recoma/__init__.py +11 -0
  52. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/recoma/appworld_env_models.py +63 -0
  53. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/recoma/appworld_prompted_lm.py +71 -0
  54. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/recoma/appworld_reader.py +65 -0
  55. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/recoma/plan_and_execute.py +111 -0
  56. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/recoma/react_controller.py +195 -0
  57. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/recoma/run.py +113 -0
  58. halo_engine-0.1.1/demo/appworld/experiments/code/legacy/recoma/singleton_appworld.py +19 -0
  59. halo_engine-0.1.1/demo/appworld/experiments/code/openai_agents/__init__.py +0 -0
  60. halo_engine-0.1.1/demo/appworld/experiments/code/openai_agents/api_predictor.py +40 -0
  61. halo_engine-0.1.1/demo/appworld/experiments/code/openai_agents/language_model.py +60 -0
  62. halo_engine-0.1.1/demo/appworld/experiments/code/openai_agents/mcp.py +110 -0
  63. halo_engine-0.1.1/demo/appworld/experiments/code/openai_agents/run.py +335 -0
  64. halo_engine-0.1.1/demo/appworld/experiments/code/openai_agents/tracing.py +522 -0
  65. halo_engine-0.1.1/demo/appworld/experiments/code/simplified/__init__.py +7 -0
  66. halo_engine-0.1.1/demo/appworld/experiments/code/simplified/agent.py +157 -0
  67. halo_engine-0.1.1/demo/appworld/experiments/code/simplified/api_predictor.py +43 -0
  68. halo_engine-0.1.1/demo/appworld/experiments/code/simplified/full_code_agent.py +211 -0
  69. halo_engine-0.1.1/demo/appworld/experiments/code/simplified/function_calling_agent.py +200 -0
  70. halo_engine-0.1.1/demo/appworld/experiments/code/simplified/language_model.py +844 -0
  71. halo_engine-0.1.1/demo/appworld/experiments/code/simplified/react_code_agent.py +208 -0
  72. halo_engine-0.1.1/demo/appworld/experiments/code/simplified/run.py +37 -0
  73. halo_engine-0.1.1/demo/appworld/experiments/code/smolagents/__init__.py +3 -0
  74. halo_engine-0.1.1/demo/appworld/experiments/code/smolagents/agents.py +31 -0
  75. halo_engine-0.1.1/demo/appworld/experiments/code/smolagents/api_predictor.py +65 -0
  76. halo_engine-0.1.1/demo/appworld/experiments/code/smolagents/models.py +101 -0
  77. halo_engine-0.1.1/demo/appworld/experiments/code/smolagents/run.py +321 -0
  78. halo_engine-0.1.1/demo/appworld/experiments/code/smolagents/task_completer.py +57 -0
  79. halo_engine-0.1.1/demo/appworld/experiments/configs/__init__.py +0 -0
  80. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/__init__.py +0 -0
  81. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/agents/__init__.py +76 -0
  82. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/__init__.py +242 -0
  83. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/alibaba.py +279 -0
  84. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/anthropic.py +577 -0
  85. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/baidu.py +43 -0
  86. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/cohere.py +28 -0
  87. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/deepseek.py +132 -0
  88. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/google.py +485 -0
  89. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/longcat.py +55 -0
  90. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/meta.py +52 -0
  91. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/minimax.py +53 -0
  92. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/misc.py +84 -0
  93. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/moonshot.py +53 -0
  94. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/nous_research.py +43 -0
  95. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/nvidia.py +55 -0
  96. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/openai.py +693 -0
  97. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/salesforce.py +90 -0
  98. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/xai.py +99 -0
  99. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/models/zai.py +78 -0
  100. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/run.py +234 -0
  101. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/templates/__init__.py +0 -0
  102. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/templates/openai_agents_mcp_agent.jsonnet.j2 +122 -0
  103. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/templates/simplified_full_code_agent.jsonnet.j2 +116 -0
  104. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/templates/simplified_function_calling_agent.jsonnet.j2 +127 -0
  105. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/templates/simplified_react_code_agent.jsonnet.j2 +105 -0
  106. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/templates/smolagents_code_agent.jsonnet.j2 +96 -0
  107. halo_engine-0.1.1/demo/appworld/experiments/configs/_generator/templates/smolagents_tool_calling_agent.jsonnet.j2 +102 -0
  108. halo_engine-0.1.1/demo/appworld/experiments/configs/ci/full_code_agent.jsonnet +51 -0
  109. halo_engine-0.1.1/demo/appworld/experiments/configs/ci/function_calling_agent.jsonnet +46 -0
  110. halo_engine-0.1.1/demo/appworld/experiments/configs/ci/react_code_agent.jsonnet +36 -0
  111. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_full_code_agent/deepseek/deepseek-coder-33b-instruct_together/test_challenge.jsonnet +49 -0
  112. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_full_code_agent/deepseek/deepseek-coder-33b-instruct_together/test_normal.jsonnet +49 -0
  113. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_full_code_agent/meta/llama-3-70b-chat-hf_together/test_challenge.jsonnet +50 -0
  114. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_full_code_agent/meta/llama-3-70b-chat-hf_together/test_normal.jsonnet +50 -0
  115. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_full_code_agent/openai/gpt-4-turbo-2024-04-09/test_challenge.jsonnet +48 -0
  116. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_full_code_agent/openai/gpt-4-turbo-2024-04-09/test_normal.jsonnet +48 -0
  117. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_full_code_agent/openai/gpt-4o-2024-05-13/test_challenge.jsonnet +48 -0
  118. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_full_code_agent/openai/gpt-4o-2024-05-13/test_normal.jsonnet +48 -0
  119. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_full_code_agent/openai/gpt-4o-mini-2024-07-18/test_challenge.jsonnet +48 -0
  120. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_full_code_agent/openai/gpt-4o-mini-2024-07-18/test_normal.jsonnet +48 -0
  121. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_function_calling_agent/openai/gpt-4-turbo-2024-04-09/test_challenge.jsonnet +42 -0
  122. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_function_calling_agent/openai/gpt-4-turbo-2024-04-09/test_normal.jsonnet +42 -0
  123. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_function_calling_agent/openai/gpt-4o-2024-05-13/test_challenge.jsonnet +42 -0
  124. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_function_calling_agent/openai/gpt-4o-2024-05-13/test_normal.jsonnet +42 -0
  125. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_function_calling_agent/openai/gpt-4o-mini-2024-07-18/test_challenge.jsonnet +42 -0
  126. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_function_calling_agent/openai/gpt-4o-mini-2024-07-18/test_normal.jsonnet +42 -0
  127. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_plan_execute_code_agent/deepseek/deepseek-coder-33b-instruct_together/test_challenge.jsonnet +74 -0
  128. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_plan_execute_code_agent/deepseek/deepseek-coder-33b-instruct_together/test_normal.jsonnet +74 -0
  129. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_plan_execute_code_agent/meta/llama-3-70b-chat-hf_together/test_challenge.jsonnet +74 -0
  130. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_plan_execute_code_agent/meta/llama-3-70b-chat-hf_together/test_normal.jsonnet +74 -0
  131. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_plan_execute_code_agent/openai/gpt-4-turbo-2024-04-09/test_challenge.jsonnet +74 -0
  132. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_plan_execute_code_agent/openai/gpt-4-turbo-2024-04-09/test_normal.jsonnet +74 -0
  133. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_plan_execute_code_agent/openai/gpt-4o-2024-05-13/test_challenge.jsonnet +74 -0
  134. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_plan_execute_code_agent/openai/gpt-4o-2024-05-13/test_normal.jsonnet +74 -0
  135. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_plan_execute_code_agent/openai/gpt-4o-mini-2024-07-18/test_challenge.jsonnet +74 -0
  136. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_plan_execute_code_agent/openai/gpt-4o-mini-2024-07-18/test_normal.jsonnet +74 -0
  137. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/deepseek/deepseek-coder-33b-instruct_together/test_challenge.jsonnet +55 -0
  138. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/deepseek/deepseek-coder-33b-instruct_together/test_normal.jsonnet +55 -0
  139. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/meta/llama-3-70b-chat-hf_together/test_challenge.jsonnet +55 -0
  140. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/meta/llama-3-70b-chat-hf_together/test_normal.jsonnet +55 -0
  141. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/openai/gpt-4-turbo-2024-04-09/test_challenge.jsonnet +55 -0
  142. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/openai/gpt-4-turbo-2024-04-09/test_normal.jsonnet +55 -0
  143. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/openai/gpt-4o-2024-05-13/dev.jsonnet +55 -0
  144. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/openai/gpt-4o-2024-05-13/test_challenge.jsonnet +55 -0
  145. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/openai/gpt-4o-2024-05-13/test_normal.jsonnet +55 -0
  146. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/openai/gpt-4o-2024-05-13/train.jsonnet +55 -0
  147. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/openai/gpt-4o-mini-2024-07-18/test_challenge.jsonnet +55 -0
  148. halo_engine-0.1.1/demo/appworld/experiments/configs/legacy_react_code_agent/openai/gpt-4o-mini-2024-07-18/test_normal.jsonnet +55 -0
  149. halo_engine-0.1.1/demo/appworld/experiments/configs/openai_agents_mcp_agent/openai/gpt-4o-2024-05-13/test_challenge.jsonnet +74 -0
  150. halo_engine-0.1.1/demo/appworld/experiments/configs/openai_agents_mcp_agent/openai/gpt-4o-2024-05-13/test_normal.jsonnet +74 -0
  151. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_full_code_agent/deepseek/deepseek-coder-33b-instruct_together/test_challenge.jsonnet +69 -0
  152. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_full_code_agent/deepseek/deepseek-coder-33b-instruct_together/test_normal.jsonnet +69 -0
  153. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_full_code_agent/meta/llama-3-70b-chat-hf_together/test_challenge.jsonnet +69 -0
  154. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_full_code_agent/meta/llama-3-70b-chat-hf_together/test_normal.jsonnet +69 -0
  155. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_full_code_agent/openai/gpt-4-turbo-2024-04-09/test_challenge.jsonnet +68 -0
  156. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_full_code_agent/openai/gpt-4-turbo-2024-04-09/test_normal.jsonnet +68 -0
  157. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_full_code_agent/openai/gpt-4o-2024-05-13/test_challenge.jsonnet +68 -0
  158. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_full_code_agent/openai/gpt-4o-2024-05-13/test_normal.jsonnet +68 -0
  159. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_full_code_agent/openai/gpt-4o-mini-2024-07-18/test_challenge.jsonnet +68 -0
  160. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_full_code_agent/openai/gpt-4o-mini-2024-07-18/test_normal.jsonnet +68 -0
  161. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/alibaba/qwen3-235b-a22b-thinking-2507/test_challenge.jsonnet +70 -0
  162. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/alibaba/qwen3-235b-a22b-thinking-2507/test_normal.jsonnet +70 -0
  163. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/alibaba/qwen3-coder-480b-a35b-instruct/test_challenge.jsonnet +70 -0
  164. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/alibaba/qwen3-coder-480b-a35b-instruct/test_normal.jsonnet +70 -0
  165. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/alibaba/qwen3-max-2025-09-23/test_challenge.jsonnet +70 -0
  166. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/alibaba/qwen3-max-2025-09-23/test_normal.jsonnet +70 -0
  167. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-3-5-haiku-20241022/test_challenge.jsonnet +67 -0
  168. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-3-5-haiku-20241022/test_normal.jsonnet +67 -0
  169. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-3-7-sonnet-20250219-high-reasoning/test_challenge.jsonnet +68 -0
  170. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-3-7-sonnet-20250219-high-reasoning/test_normal.jsonnet +68 -0
  171. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-3-7-sonnet-20250219-no-reasoning/test_challenge.jsonnet +67 -0
  172. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-3-7-sonnet-20250219-no-reasoning/test_normal.jsonnet +67 -0
  173. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-haiku-4-5-20251001-medium-reasoning/test_challenge.jsonnet +68 -0
  174. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-haiku-4-5-20251001-medium-reasoning/test_normal.jsonnet +68 -0
  175. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-opus-4-1-20250805-high-reasoning/test_challenge.jsonnet +68 -0
  176. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-opus-4-1-20250805-high-reasoning/test_normal.jsonnet +68 -0
  177. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-opus-4-1-20250805-medium-reasoning/test_challenge.jsonnet +68 -0
  178. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-opus-4-1-20250805-medium-reasoning/test_normal.jsonnet +68 -0
  179. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-opus-4-1-20250805-no-reasoning/test_challenge.jsonnet +67 -0
  180. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-opus-4-1-20250805-no-reasoning/test_normal.jsonnet +67 -0
  181. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-20250514-high-reasoning/test_challenge.jsonnet +68 -0
  182. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-20250514-high-reasoning/test_normal.jsonnet +68 -0
  183. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-20250514-no-reasoning/test_challenge.jsonnet +67 -0
  184. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-20250514-no-reasoning/test_normal.jsonnet +67 -0
  185. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-5-20250929-high-reasoning/test_challenge.jsonnet +68 -0
  186. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-5-20250929-high-reasoning/test_normal.jsonnet +68 -0
  187. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-5-20250929-low-reasoning/test_challenge.jsonnet +68 -0
  188. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-5-20250929-low-reasoning/test_normal.jsonnet +68 -0
  189. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-5-20250929-medium-reasoning/test_challenge.jsonnet +68 -0
  190. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-5-20250929-medium-reasoning/test_normal.jsonnet +68 -0
  191. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-5-20250929-no-reasoning/test_challenge.jsonnet +67 -0
  192. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/anthropic/claude-sonnet-4-5-20250929-no-reasoning/test_normal.jsonnet +67 -0
  193. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/cohere/command-a-03-2025/test_challenge.jsonnet +69 -0
  194. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/cohere/command-a-03-2025/test_normal.jsonnet +69 -0
  195. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/deepseek/deepseek-r1-0528_openrouter/test_challenge.jsonnet +68 -0
  196. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/deepseek/deepseek-r1-0528_openrouter/test_normal.jsonnet +68 -0
  197. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/deepseek/deepseek-v3-0324_together/test_challenge.jsonnet +68 -0
  198. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/deepseek/deepseek-v3-0324_together/test_normal.jsonnet +68 -0
  199. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/deepseek/deepseek-v3.2-terminus-exp-with-reasoning/test_challenge.jsonnet +71 -0
  200. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/deepseek/deepseek-v3.2-terminus-exp-with-reasoning/test_normal.jsonnet +71 -0
  201. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/deepseek/deepseek-v3.2-terminus-exp-without-reasoning/test_challenge.jsonnet +70 -0
  202. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/deepseek/deepseek-v3.2-terminus-exp-without-reasoning/test_normal.jsonnet +70 -0
  203. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/google/gemini-2.0-flash/test_challenge.jsonnet +67 -0
  204. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/google/gemini-2.0-flash/test_normal.jsonnet +67 -0
  205. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/google/gemini-2.5-flash-medium-reasoning/test_challenge.jsonnet +68 -0
  206. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/google/gemini-2.5-flash-medium-reasoning/test_normal.jsonnet +68 -0
  207. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/google/gemini-2.5-pro-high-reasoning/test_challenge.jsonnet +68 -0
  208. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/google/gemini-2.5-pro-high-reasoning/test_normal.jsonnet +68 -0
  209. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/google/gemini-2.5-pro-low-reasoning/test_challenge.jsonnet +68 -0
  210. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/google/gemini-2.5-pro-low-reasoning/test_normal.jsonnet +68 -0
  211. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/google/gemini-2.5-pro-medium-reasoning/test_challenge.jsonnet +68 -0
  212. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/google/gemini-2.5-pro-medium-reasoning/test_normal.jsonnet +68 -0
  213. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/meta/llama-3.1-70b-instruct_openrouter/test_challenge.jsonnet +68 -0
  214. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/meta/llama-3.1-70b-instruct_openrouter/test_normal.jsonnet +68 -0
  215. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/moonshot/kimi-k2-0905-preview/test_challenge.jsonnet +70 -0
  216. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/moonshot/kimi-k2-0905-preview/test_normal.jsonnet +70 -0
  217. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-4-turbo-2024-04-09/test_challenge.jsonnet +68 -0
  218. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-4-turbo-2024-04-09/test_normal.jsonnet +68 -0
  219. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-4.1-2025-04-14/test_challenge.jsonnet +68 -0
  220. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-4.1-2025-04-14/test_normal.jsonnet +68 -0
  221. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-4.1-mini-2025-04-14/test_challenge.jsonnet +68 -0
  222. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-4.1-mini-2025-04-14/test_normal.jsonnet +68 -0
  223. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-4o-2024-05-13/test_challenge.jsonnet +68 -0
  224. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-4o-2024-05-13/test_normal.jsonnet +68 -0
  225. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-4o-mini-2024-07-18/test_challenge.jsonnet +68 -0
  226. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-4o-mini-2024-07-18/test_normal.jsonnet +68 -0
  227. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-2025-08-07-high-reasoning/test_challenge.jsonnet +68 -0
  228. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-2025-08-07-high-reasoning/test_normal.jsonnet +68 -0
  229. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-2025-08-07-low-reasoning/test_challenge.jsonnet +68 -0
  230. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-2025-08-07-low-reasoning/test_normal.jsonnet +68 -0
  231. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-2025-08-07-medium-reasoning/test_challenge.jsonnet +68 -0
  232. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-2025-08-07-medium-reasoning/test_normal.jsonnet +68 -0
  233. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-2025-08-07-minimal-reasoning/test_challenge.jsonnet +68 -0
  234. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-2025-08-07-minimal-reasoning/test_normal.jsonnet +68 -0
  235. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-mini-2025-08-07-medium-reasoning/test_challenge.jsonnet +68 -0
  236. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-mini-2025-08-07-medium-reasoning/test_normal.jsonnet +68 -0
  237. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-nano-2025-08-07-medium-reasoning/test_challenge.jsonnet +68 -0
  238. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-5-nano-2025-08-07-medium-reasoning/test_normal.jsonnet +68 -0
  239. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-oss-120b-medium-reasoning_openrouter/test_challenge.jsonnet +68 -0
  240. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-oss-120b-medium-reasoning_openrouter/test_normal.jsonnet +68 -0
  241. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-oss-20b-medium-reasoning_openrouter/test_challenge.jsonnet +68 -0
  242. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/gpt-oss-20b-medium-reasoning_openrouter/test_normal.jsonnet +68 -0
  243. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/o3-2025-04-16-medium-reasoning/test_challenge.jsonnet +68 -0
  244. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/o3-2025-04-16-medium-reasoning/test_normal.jsonnet +68 -0
  245. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/o4-mini-2025-04-16-high-reasoning/test_challenge.jsonnet +68 -0
  246. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/o4-mini-2025-04-16-high-reasoning/test_normal.jsonnet +68 -0
  247. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/o4-mini-2025-04-16-low-reasoning/test_challenge.jsonnet +68 -0
  248. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/openai/o4-mini-2025-04-16-low-reasoning/test_normal.jsonnet +68 -0
  249. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/xai/grok-4-0709/test_challenge.jsonnet +69 -0
  250. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/xai/grok-4-0709/test_normal.jsonnet +69 -0
  251. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/xai/grok-4-fast-non-reasoning/test_challenge.jsonnet +69 -0
  252. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/xai/grok-4-fast-non-reasoning/test_normal.jsonnet +69 -0
  253. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/xai/grok-4-fast-reasoning/test_challenge.jsonnet +69 -0
  254. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/xai/grok-4-fast-reasoning/test_normal.jsonnet +69 -0
  255. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/xai/grok-code-fast-1-0825/test_challenge.jsonnet +69 -0
  256. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/xai/grok-code-fast-1-0825/test_normal.jsonnet +69 -0
  257. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/zai/glm-4.5/test_challenge.jsonnet +70 -0
  258. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/zai/glm-4.5/test_normal.jsonnet +70 -0
  259. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/zai/glm-4.5-air/test_challenge.jsonnet +70 -0
  260. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/zai/glm-4.5-air/test_normal.jsonnet +70 -0
  261. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/zai/glm-4.6/test_challenge.jsonnet +70 -0
  262. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_function_calling_agent/zai/glm-4.6/test_normal.jsonnet +70 -0
  263. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/alibaba/qwen3-235b-a22b-thinking-2507/test_challenge.jsonnet +59 -0
  264. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/alibaba/qwen3-235b-a22b-thinking-2507/test_normal.jsonnet +59 -0
  265. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/alibaba/qwen3-coder-480b-a35b-instruct/test_challenge.jsonnet +59 -0
  266. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/alibaba/qwen3-coder-480b-a35b-instruct/test_normal.jsonnet +59 -0
  267. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/alibaba/qwen3-max-2025-09-23/test_challenge.jsonnet +59 -0
  268. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/alibaba/qwen3-max-2025-09-23/test_normal.jsonnet +59 -0
  269. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-3-5-haiku-20241022/test_challenge.jsonnet +56 -0
  270. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-3-5-haiku-20241022/test_normal.jsonnet +56 -0
  271. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-3-7-sonnet-20250219-high-reasoning/test_challenge.jsonnet +57 -0
  272. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-3-7-sonnet-20250219-high-reasoning/test_normal.jsonnet +57 -0
  273. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-3-7-sonnet-20250219-no-reasoning/test_challenge.jsonnet +56 -0
  274. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-3-7-sonnet-20250219-no-reasoning/test_normal.jsonnet +56 -0
  275. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-haiku-4-5-20251001-medium-reasoning/test_challenge.jsonnet +57 -0
  276. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-haiku-4-5-20251001-medium-reasoning/test_normal.jsonnet +57 -0
  277. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-opus-4-1-20250805-high-reasoning/test_challenge.jsonnet +57 -0
  278. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-opus-4-1-20250805-high-reasoning/test_normal.jsonnet +57 -0
  279. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-opus-4-1-20250805-medium-reasoning/test_challenge.jsonnet +57 -0
  280. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-opus-4-1-20250805-medium-reasoning/test_normal.jsonnet +57 -0
  281. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-opus-4-1-20250805-no-reasoning/test_challenge.jsonnet +56 -0
  282. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-opus-4-1-20250805-no-reasoning/test_normal.jsonnet +56 -0
  283. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-20250514-high-reasoning/test_challenge.jsonnet +57 -0
  284. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-20250514-high-reasoning/test_normal.jsonnet +57 -0
  285. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-20250514-no-reasoning/test_challenge.jsonnet +56 -0
  286. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-20250514-no-reasoning/test_normal.jsonnet +56 -0
  287. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-5-20250929-high-reasoning/test_challenge.jsonnet +57 -0
  288. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-5-20250929-high-reasoning/test_normal.jsonnet +57 -0
  289. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-5-20250929-low-reasoning/test_challenge.jsonnet +57 -0
  290. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-5-20250929-low-reasoning/test_normal.jsonnet +57 -0
  291. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-5-20250929-medium-reasoning/test_challenge.jsonnet +57 -0
  292. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-5-20250929-medium-reasoning/test_normal.jsonnet +57 -0
  293. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-5-20250929-no-reasoning/test_challenge.jsonnet +56 -0
  294. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/anthropic/claude-sonnet-4-5-20250929-no-reasoning/test_normal.jsonnet +56 -0
  295. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/cohere/command-a-03-2025/test_challenge.jsonnet +59 -0
  296. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/cohere/command-a-03-2025/test_normal.jsonnet +59 -0
  297. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/deepseek/deepseek-coder-33b-instruct_together/test_challenge.jsonnet +58 -0
  298. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/deepseek/deepseek-coder-33b-instruct_together/test_normal.jsonnet +58 -0
  299. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/deepseek/deepseek-r1-0528_openrouter/test_challenge.jsonnet +57 -0
  300. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/deepseek/deepseek-r1-0528_openrouter/test_normal.jsonnet +57 -0
  301. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/deepseek/deepseek-v3-0324_together/test_challenge.jsonnet +57 -0
  302. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/deepseek/deepseek-v3-0324_together/test_normal.jsonnet +57 -0
  303. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/deepseek/deepseek-v3.2-terminus-exp-with-reasoning/test_challenge.jsonnet +60 -0
  304. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/deepseek/deepseek-v3.2-terminus-exp-with-reasoning/test_normal.jsonnet +60 -0
  305. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/deepseek/deepseek-v3.2-terminus-exp-without-reasoning/test_challenge.jsonnet +59 -0
  306. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/deepseek/deepseek-v3.2-terminus-exp-without-reasoning/test_normal.jsonnet +59 -0
  307. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/google/gemini-2.0-flash/test_challenge.jsonnet +56 -0
  308. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/google/gemini-2.0-flash/test_normal.jsonnet +56 -0
  309. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/google/gemini-2.5-flash-medium-reasoning/test_challenge.jsonnet +57 -0
  310. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/google/gemini-2.5-flash-medium-reasoning/test_normal.jsonnet +57 -0
  311. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/google/gemini-2.5-pro-high-reasoning/test_challenge.jsonnet +57 -0
  312. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/google/gemini-2.5-pro-high-reasoning/test_normal.jsonnet +57 -0
  313. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/google/gemini-2.5-pro-low-reasoning/test_challenge.jsonnet +57 -0
  314. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/google/gemini-2.5-pro-low-reasoning/test_normal.jsonnet +57 -0
  315. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/google/gemini-2.5-pro-medium-reasoning/test_challenge.jsonnet +57 -0
  316. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/google/gemini-2.5-pro-medium-reasoning/test_normal.jsonnet +57 -0
  317. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/meta/llama-3-70b-chat-hf_together/test_challenge.jsonnet +58 -0
  318. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/meta/llama-3-70b-chat-hf_together/test_normal.jsonnet +58 -0
  319. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/meta/llama-3.1-70b-instruct_openrouter/test_challenge.jsonnet +57 -0
  320. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/meta/llama-3.1-70b-instruct_openrouter/test_normal.jsonnet +57 -0
  321. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/moonshot/kimi-k2-0905-preview/test_challenge.jsonnet +59 -0
  322. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/moonshot/kimi-k2-0905-preview/test_normal.jsonnet +59 -0
  323. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4-turbo-2024-04-09/test_challenge.jsonnet +57 -0
  324. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4-turbo-2024-04-09/test_normal.jsonnet +57 -0
  325. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4.1-2025-04-14/test_challenge.jsonnet +57 -0
  326. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4.1-2025-04-14/test_normal.jsonnet +57 -0
  327. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4.1-mini-2025-04-14/test_challenge.jsonnet +57 -0
  328. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4.1-mini-2025-04-14/test_normal.jsonnet +57 -0
  329. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4o-2024-05-13/dev.jsonnet +57 -0
  330. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4o-2024-05-13/test_challenge.jsonnet +57 -0
  331. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4o-2024-05-13/test_normal.jsonnet +57 -0
  332. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4o-2024-05-13/train.jsonnet +57 -0
  333. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4o-mini-2024-07-18/test_challenge.jsonnet +57 -0
  334. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-4o-mini-2024-07-18/test_normal.jsonnet +57 -0
  335. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-2025-08-07-high-reasoning/test_challenge.jsonnet +57 -0
  336. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-2025-08-07-high-reasoning/test_normal.jsonnet +57 -0
  337. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-2025-08-07-low-reasoning/test_challenge.jsonnet +57 -0
  338. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-2025-08-07-low-reasoning/test_normal.jsonnet +57 -0
  339. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-2025-08-07-medium-reasoning/test_challenge.jsonnet +57 -0
  340. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-2025-08-07-medium-reasoning/test_normal.jsonnet +57 -0
  341. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-2025-08-07-minimal-reasoning/test_challenge.jsonnet +57 -0
  342. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-2025-08-07-minimal-reasoning/test_normal.jsonnet +57 -0
  343. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-mini-2025-08-07-medium-reasoning/test_challenge.jsonnet +57 -0
  344. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-mini-2025-08-07-medium-reasoning/test_normal.jsonnet +57 -0
  345. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-nano-2025-08-07-medium-reasoning/test_challenge.jsonnet +57 -0
  346. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-5-nano-2025-08-07-medium-reasoning/test_normal.jsonnet +57 -0
  347. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-oss-120b-medium-reasoning_openrouter/test_challenge.jsonnet +57 -0
  348. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-oss-120b-medium-reasoning_openrouter/test_normal.jsonnet +57 -0
  349. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-oss-20b-medium-reasoning_openrouter/test_challenge.jsonnet +57 -0
  350. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/gpt-oss-20b-medium-reasoning_openrouter/test_normal.jsonnet +57 -0
  351. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/o3-2025-04-16-medium-reasoning/test_challenge.jsonnet +57 -0
  352. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/o3-2025-04-16-medium-reasoning/test_normal.jsonnet +57 -0
  353. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/o4-mini-2025-04-16-high-reasoning/test_challenge.jsonnet +57 -0
  354. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/o4-mini-2025-04-16-high-reasoning/test_normal.jsonnet +57 -0
  355. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/o4-mini-2025-04-16-low-reasoning/test_challenge.jsonnet +57 -0
  356. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/openai/o4-mini-2025-04-16-low-reasoning/test_normal.jsonnet +57 -0
  357. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/xai/grok-4-0709/test_challenge.jsonnet +58 -0
  358. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/xai/grok-4-0709/test_normal.jsonnet +58 -0
  359. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/xai/grok-4-fast-non-reasoning/test_challenge.jsonnet +58 -0
  360. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/xai/grok-4-fast-non-reasoning/test_normal.jsonnet +58 -0
  361. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/xai/grok-4-fast-reasoning/test_challenge.jsonnet +58 -0
  362. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/xai/grok-4-fast-reasoning/test_normal.jsonnet +58 -0
  363. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/xai/grok-code-fast-1-0825/test_challenge.jsonnet +58 -0
  364. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/xai/grok-code-fast-1-0825/test_normal.jsonnet +58 -0
  365. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/zai/glm-4.5/test_challenge.jsonnet +59 -0
  366. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/zai/glm-4.5/test_normal.jsonnet +59 -0
  367. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/zai/glm-4.5-air/test_challenge.jsonnet +59 -0
  368. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/zai/glm-4.5-air/test_normal.jsonnet +59 -0
  369. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/zai/glm-4.6/test_challenge.jsonnet +59 -0
  370. halo_engine-0.1.1/demo/appworld/experiments/configs/simplified_react_code_agent/zai/glm-4.6/test_normal.jsonnet +59 -0
  371. halo_engine-0.1.1/demo/appworld/experiments/configs/smolagents_code_agent/openai/gpt-4o-2024-05-13/test_normal.jsonnet +56 -0
  372. halo_engine-0.1.1/demo/appworld/experiments/configs/smolagents_tool_calling_agent/openai/gpt-4o-2024-05-13/test_normal.jsonnet +59 -0
  373. halo_engine-0.1.1/demo/appworld/experiments/prompts/__init__.py +0 -0
  374. halo_engine-0.1.1/demo/appworld/experiments/prompts/api_predictor.txt +21 -0
  375. halo_engine-0.1.1/demo/appworld/experiments/prompts/full_code_agent/_legacy_full_code_instructions.txt +63 -0
  376. halo_engine-0.1.1/demo/appworld/experiments/prompts/full_code_agent/full_code_instructions.txt +94 -0
  377. halo_engine-0.1.1/demo/appworld/experiments/prompts/full_code_agent/reflexion_instructions.txt +1 -0
  378. halo_engine-0.1.1/demo/appworld/experiments/prompts/function_calling_agent/_legacy_instructions.txt +22 -0
  379. halo_engine-0.1.1/demo/appworld/experiments/prompts/function_calling_agent/demos.json +301 -0
  380. halo_engine-0.1.1/demo/appworld/experiments/prompts/function_calling_agent/instructions.txt +56 -0
  381. halo_engine-0.1.1/demo/appworld/experiments/prompts/plan_execute_code_agent/execute_instructions.txt +591 -0
  382. halo_engine-0.1.1/demo/appworld/experiments/prompts/plan_execute_code_agent/plan_instructions.txt +57 -0
  383. halo_engine-0.1.1/demo/appworld/experiments/prompts/react_code_agent/_legacy_instructions.txt +343 -0
  384. halo_engine-0.1.1/demo/appworld/experiments/prompts/react_code_agent/instructions.txt +371 -0
  385. halo_engine-0.1.1/demo/appworld/experiments/prompts/smolagents/code_instructions.yaml +208 -0
  386. halo_engine-0.1.1/demo/appworld/experiments/prompts/smolagents/task_completer_instructions.txt +59 -0
  387. halo_engine-0.1.1/demo/appworld/experiments/prompts/smolagents/tool_calling_instructions.yaml +186 -0
  388. halo_engine-0.1.1/demo/appworld/experiments/pyproject.toml +111 -0
  389. halo_engine-0.1.1/demo/appworld/generate/.source/data.bundle +3 -0
  390. halo_engine-0.1.1/demo/appworld/generate/.source/tasks.bundle +3 -0
  391. halo_engine-0.1.1/demo/appworld/generate/__init__.py +0 -0
  392. halo_engine-0.1.1/demo/appworld/pyproject.toml +289 -0
  393. halo_engine-0.1.1/demo/appworld/src/appworld/.source/apps.bundle +3 -0
  394. halo_engine-0.1.1/demo/appworld/src/appworld/.source/tests.bundle +3 -0
  395. halo_engine-0.1.1/demo/appworld/src/appworld/__init__.py +66 -0
  396. halo_engine-0.1.1/demo/appworld/src/appworld/api_docs.py +737 -0
  397. halo_engine-0.1.1/demo/appworld/src/appworld/apps/__init__.py +569 -0
  398. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/__init__.py +0 -0
  399. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/apis/__init__.py +0 -0
  400. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/apis/authentication.py +631 -0
  401. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/apis/callers.py +408 -0
  402. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/apis/datetime.py +65 -0
  403. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/apis/local_remote.py +295 -0
  404. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/apis/pagination.py +69 -0
  405. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/factories/__init__.py +64 -0
  406. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/models/__init__.py +0 -0
  407. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/models/db.py +536 -0
  408. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/models/filter_sort.py +306 -0
  409. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/models/orm.py +1976 -0
  410. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/models/users.py +41 -0
  411. halo_engine-0.1.1/demo/appworld/src/appworld/apps/lib/responses/__init__.py +77 -0
  412. halo_engine-0.1.1/demo/appworld/src/appworld/cli.py +2367 -0
  413. halo_engine-0.1.1/demo/appworld/src/appworld/collections/__init__.py +0 -0
  414. halo_engine-0.1.1/demo/appworld/src/appworld/collections/api_docs.py +368 -0
  415. halo_engine-0.1.1/demo/appworld/src/appworld/collections/api_docs.pyi +1000 -0
  416. halo_engine-0.1.1/demo/appworld/src/appworld/collections/apis.py +211 -0
  417. halo_engine-0.1.1/demo/appworld/src/appworld/collections/apis.pyi +3049 -0
  418. halo_engine-0.1.1/demo/appworld/src/appworld/collections/models.py +571 -0
  419. halo_engine-0.1.1/demo/appworld/src/appworld/collections/models.pyi +204 -0
  420. halo_engine-0.1.1/demo/appworld/src/appworld/common/__init__.py +0 -0
  421. halo_engine-0.1.1/demo/appworld/src/appworld/common/background_server.py +295 -0
  422. halo_engine-0.1.1/demo/appworld/src/appworld/common/code_parsing.py +753 -0
  423. halo_engine-0.1.1/demo/appworld/src/appworld/common/code_tools.py +160 -0
  424. halo_engine-0.1.1/demo/appworld/src/appworld/common/collections.py +632 -0
  425. halo_engine-0.1.1/demo/appworld/src/appworld/common/constants.py +54 -0
  426. halo_engine-0.1.1/demo/appworld/src/appworld/common/copy.py +11 -0
  427. halo_engine-0.1.1/demo/appworld/src/appworld/common/crypto.py +318 -0
  428. halo_engine-0.1.1/demo/appworld/src/appworld/common/database.py +58 -0
  429. halo_engine-0.1.1/demo/appworld/src/appworld/common/datetime.py +793 -0
  430. halo_engine-0.1.1/demo/appworld/src/appworld/common/errors.py +143 -0
  431. halo_engine-0.1.1/demo/appworld/src/appworld/common/evaluation.py +370 -0
  432. halo_engine-0.1.1/demo/appworld/src/appworld/common/finders.py +1166 -0
  433. halo_engine-0.1.1/demo/appworld/src/appworld/common/hashing.py +48 -0
  434. halo_engine-0.1.1/demo/appworld/src/appworld/common/imports.py +92 -0
  435. halo_engine-0.1.1/demo/appworld/src/appworld/common/inspect.py +218 -0
  436. halo_engine-0.1.1/demo/appworld/src/appworld/common/io.py +442 -0
  437. halo_engine-0.1.1/demo/appworld/src/appworld/common/math.py +202 -0
  438. halo_engine-0.1.1/demo/appworld/src/appworld/common/misc.py +133 -0
  439. halo_engine-0.1.1/demo/appworld/src/appworld/common/naming.py +36 -0
  440. halo_engine-0.1.1/demo/appworld/src/appworld/common/path_store.py +95 -0
  441. halo_engine-0.1.1/demo/appworld/src/appworld/common/plotting.py +337 -0
  442. halo_engine-0.1.1/demo/appworld/src/appworld/common/printer.py +116 -0
  443. halo_engine-0.1.1/demo/appworld/src/appworld/common/prompts.py +163 -0
  444. halo_engine-0.1.1/demo/appworld/src/appworld/common/random.py +248 -0
  445. halo_engine-0.1.1/demo/appworld/src/appworld/common/registrable.py +208 -0
  446. halo_engine-0.1.1/demo/appworld/src/appworld/common/safety_guard.py +402 -0
  447. halo_engine-0.1.1/demo/appworld/src/appworld/common/system.py +194 -0
  448. halo_engine-0.1.1/demo/appworld/src/appworld/common/temp.py +37 -0
  449. halo_engine-0.1.1/demo/appworld/src/appworld/common/text.py +122 -0
  450. halo_engine-0.1.1/demo/appworld/src/appworld/common/time.py +175 -0
  451. halo_engine-0.1.1/demo/appworld/src/appworld/common/types.py +130 -0
  452. halo_engine-0.1.1/demo/appworld/src/appworld/common/unique_caller.py +23 -0
  453. halo_engine-0.1.1/demo/appworld/src/appworld/common/utils.py +34 -0
  454. halo_engine-0.1.1/demo/appworld/src/appworld/download.py +136 -0
  455. halo_engine-0.1.1/demo/appworld/src/appworld/environment.py +1413 -0
  456. halo_engine-0.1.1/demo/appworld/src/appworld/evaluator.py +645 -0
  457. halo_engine-0.1.1/demo/appworld/src/appworld/ground_truth.py +502 -0
  458. halo_engine-0.1.1/demo/appworld/src/appworld/install.py +107 -0
  459. halo_engine-0.1.1/demo/appworld/src/appworld/leaderboard.py +311 -0
  460. halo_engine-0.1.1/demo/appworld/src/appworld/py.typed +1 -0
  461. halo_engine-0.1.1/demo/appworld/src/appworld/requester.py +954 -0
  462. halo_engine-0.1.1/demo/appworld/src/appworld/serve/__init__.py +0 -0
  463. halo_engine-0.1.1/demo/appworld/src/appworld/serve/_apis.py +33 -0
  464. halo_engine-0.1.1/demo/appworld/src/appworld/serve/_mcp.py +465 -0
  465. halo_engine-0.1.1/demo/appworld/src/appworld/serve/apis.py +73 -0
  466. halo_engine-0.1.1/demo/appworld/src/appworld/serve/environment.py +310 -0
  467. halo_engine-0.1.1/demo/appworld/src/appworld/serve/playground.html +761 -0
  468. halo_engine-0.1.1/demo/appworld/src/appworld/serve/static/icon.png +0 -0
  469. halo_engine-0.1.1/demo/appworld/src/appworld/serve/uis.py +66 -0
  470. halo_engine-0.1.1/demo/appworld/src/appworld/task.py +335 -0
  471. halo_engine-0.1.1/demo/appworld/src/appworld/verify.py +218 -0
  472. halo_engine-0.1.1/demo/appworld/tests/__init__.py +0 -0
  473. halo_engine-0.1.1/demo/appworld/tests/lib.py +1437 -0
  474. halo_engine-0.1.1/demo/appworld/tests/package/common/test_background_server.py +357 -0
  475. halo_engine-0.1.1/demo/appworld/tests/package/common/test_code_parsing.py +529 -0
  476. halo_engine-0.1.1/demo/appworld/tests/package/common/test_code_tools.py +81 -0
  477. halo_engine-0.1.1/demo/appworld/tests/package/common/test_collections.py +252 -0
  478. halo_engine-0.1.1/demo/appworld/tests/package/common/test_crypto.py +148 -0
  479. halo_engine-0.1.1/demo/appworld/tests/package/common/test_database.py +9 -0
  480. halo_engine-0.1.1/demo/appworld/tests/package/common/test_datetime.py +60 -0
  481. halo_engine-0.1.1/demo/appworld/tests/package/common/test_errors.py +30 -0
  482. halo_engine-0.1.1/demo/appworld/tests/package/common/test_evaluation.py +154 -0
  483. halo_engine-0.1.1/demo/appworld/tests/package/common/test_finders.py +20 -0
  484. halo_engine-0.1.1/demo/appworld/tests/package/common/test_io.py +33 -0
  485. halo_engine-0.1.1/demo/appworld/tests/package/common/test_math.py +11 -0
  486. halo_engine-0.1.1/demo/appworld/tests/package/common/test_misc.py +60 -0
  487. halo_engine-0.1.1/demo/appworld/tests/package/common/test_prompts.py +148 -0
  488. halo_engine-0.1.1/demo/appworld/tests/package/common/test_random.py +177 -0
  489. halo_engine-0.1.1/demo/appworld/tests/package/common/test_system.py +30 -0
  490. halo_engine-0.1.1/demo/appworld/tests/package/common/test_time.py +39 -0
  491. halo_engine-0.1.1/demo/openai-agents-sdk-demo/.env.example +6 -0
  492. halo_engine-0.1.1/demo/openai-agents-sdk-demo/.python-version +1 -0
  493. halo_engine-0.1.1/demo/openai-agents-sdk-demo/README.md +18 -0
  494. halo_engine-0.1.1/demo/openai-agents-sdk-demo/agent.py +109 -0
  495. halo_engine-0.1.1/demo/openai-agents-sdk-demo/main.py +30 -0
  496. halo_engine-0.1.1/demo/openai-agents-sdk-demo/pyproject.toml +11 -0
  497. halo_engine-0.1.1/demo/openai-agents-sdk-demo/sample-traces/README.md +37 -0
  498. halo_engine-0.1.1/demo/openai-agents-sdk-demo/sample-traces/traces.jsonl +7 -0
  499. halo_engine-0.1.1/demo/openai-agents-sdk-demo/tracing.py +522 -0
  500. halo_engine-0.1.1/demo/openai-agents-sdk-demo/uv.lock +981 -0
  501. halo_engine-0.1.1/demo/openai-agents-sdk-demo/verify_traces.py +34 -0
  502. halo_engine-0.1.1/docs/integrations/openai-agents-sdk.md +148 -0
  503. halo_engine-0.1.1/engine/__init__.py +3 -0
  504. halo_engine-0.1.1/engine/agents/__init__.py +0 -0
  505. halo_engine-0.1.1/engine/agents/agent_config.py +22 -0
  506. halo_engine-0.1.1/engine/agents/agent_context.py +217 -0
  507. halo_engine-0.1.1/engine/agents/agent_context_items.py +30 -0
  508. halo_engine-0.1.1/engine/agents/agent_execution.py +32 -0
  509. halo_engine-0.1.1/engine/agents/compactor.py +72 -0
  510. halo_engine-0.1.1/engine/agents/engine_output_bus.py +57 -0
  511. halo_engine-0.1.1/engine/agents/engine_run_state.py +42 -0
  512. halo_engine-0.1.1/engine/agents/openai_agent_runner.py +164 -0
  513. halo_engine-0.1.1/engine/agents/openai_event_mapper.py +231 -0
  514. halo_engine-0.1.1/engine/agents/prompt_templates.py +127 -0
  515. halo_engine-0.1.1/engine/agents/runner_protocol.py +32 -0
  516. halo_engine-0.1.1/engine/engine_config.py +29 -0
  517. halo_engine-0.1.1/engine/errors.py +21 -0
  518. halo_engine-0.1.1/engine/main.py +184 -0
  519. halo_engine-0.1.1/engine/model_config.py +20 -0
  520. halo_engine-0.1.1/engine/model_provider_config.py +23 -0
  521. halo_engine-0.1.1/engine/models/__init__.py +0 -0
  522. halo_engine-0.1.1/engine/models/engine_output.py +46 -0
  523. halo_engine-0.1.1/engine/models/messages.py +45 -0
  524. halo_engine-0.1.1/engine/sandbox/README.md +263 -0
  525. halo_engine-0.1.1/engine/sandbox/__init__.py +15 -0
  526. halo_engine-0.1.1/engine/sandbox/models.py +22 -0
  527. halo_engine-0.1.1/engine/sandbox/pyodide_runtime.py +137 -0
  528. halo_engine-0.1.1/engine/sandbox/runner.js +255 -0
  529. halo_engine-0.1.1/engine/sandbox/sandbox.py +923 -0
  530. halo_engine-0.1.1/engine/tools/__init__.py +0 -0
  531. halo_engine-0.1.1/engine/tools/agent_context_tools.py +43 -0
  532. halo_engine-0.1.1/engine/tools/run_code_tool.py +39 -0
  533. halo_engine-0.1.1/engine/tools/subagent_result.py +23 -0
  534. halo_engine-0.1.1/engine/tools/subagent_tool_factory.py +325 -0
  535. halo_engine-0.1.1/engine/tools/synthesis_tool.py +78 -0
  536. halo_engine-0.1.1/engine/tools/tool_protocol.py +105 -0
  537. halo_engine-0.1.1/engine/tools/trace_tools.py +163 -0
  538. halo_engine-0.1.1/engine/traces/__init__.py +0 -0
  539. halo_engine-0.1.1/engine/traces/models/__init__.py +0 -0
  540. halo_engine-0.1.1/engine/traces/models/canonical_span.py +55 -0
  541. halo_engine-0.1.1/engine/traces/models/trace_index_config.py +14 -0
  542. halo_engine-0.1.1/engine/traces/models/trace_index_models.py +46 -0
  543. halo_engine-0.1.1/engine/traces/models/trace_query_models.py +211 -0
  544. halo_engine-0.1.1/engine/traces/trace_index_builder.py +371 -0
  545. halo_engine-0.1.1/engine/traces/trace_store.py +412 -0
  546. halo_engine-0.1.1/halo_cli/README.md +71 -0
  547. halo_engine-0.1.1/halo_cli/__init__.py +0 -0
  548. halo_engine-0.1.1/halo_cli/main.py +93 -0
  549. halo_engine-0.1.1/pyproject.toml +78 -0
  550. halo_engine-0.1.1/pyrightconfig.json +25 -0
  551. halo_engine-0.1.1/scripts/git-hooks/pre-commit +24 -0
  552. halo_engine-0.1.1/scripts/git-hooks/pre-push +53 -0
  553. halo_engine-0.1.1/scripts/setup-git-hooks.sh +14 -0
  554. halo_engine-0.1.1/scripts/validate_pinned_versions.py +89 -0
  555. halo_engine-0.1.1/skills/claude/SKILL.md +253 -0
  556. halo_engine-0.1.1/tests/__init__.py +0 -0
  557. halo_engine-0.1.1/tests/_sdk_events.py +107 -0
  558. halo_engine-0.1.1/tests/conftest.py +12 -0
  559. halo_engine-0.1.1/tests/e2e/__init__.py +0 -0
  560. halo_engine-0.1.1/tests/e2e/test_engine_e2e.py +227 -0
  561. halo_engine-0.1.1/tests/fixtures/_generate_medium_traces.py +104 -0
  562. halo_engine-0.1.1/tests/fixtures/medium_traces.jsonl +2000 -0
  563. halo_engine-0.1.1/tests/fixtures/realistic_traces.jsonl +58 -0
  564. halo_engine-0.1.1/tests/fixtures/tiny_traces.jsonl +6 -0
  565. halo_engine-0.1.1/tests/integration/__init__.py +0 -0
  566. halo_engine-0.1.1/tests/integration/test_engine_compaction.py +91 -0
  567. halo_engine-0.1.1/tests/integration/test_engine_subagent.py +140 -0
  568. halo_engine-0.1.1/tests/integration/test_sandbox_availability.py +26 -0
  569. halo_engine-0.1.1/tests/integration/test_sandbox_policy_denials.py +447 -0
  570. halo_engine-0.1.1/tests/integration/test_sandbox_runner.py +174 -0
  571. halo_engine-0.1.1/tests/integration/test_tool_call_subagent.py +67 -0
  572. halo_engine-0.1.1/tests/integration/test_tool_count_traces.py +41 -0
  573. halo_engine-0.1.1/tests/integration/test_tool_get_context_item.py +58 -0
  574. halo_engine-0.1.1/tests/integration/test_tool_get_dataset_overview.py +53 -0
  575. halo_engine-0.1.1/tests/integration/test_tool_inventory.py +49 -0
  576. halo_engine-0.1.1/tests/integration/test_tool_query_traces.py +50 -0
  577. halo_engine-0.1.1/tests/integration/test_tool_run_code.py +59 -0
  578. halo_engine-0.1.1/tests/integration/test_tool_search_trace.py +43 -0
  579. halo_engine-0.1.1/tests/integration/test_tool_synthesize_traces.py +54 -0
  580. halo_engine-0.1.1/tests/integration/test_tool_view_trace.py +46 -0
  581. halo_engine-0.1.1/tests/integration/tool_isolation_kit.py +128 -0
  582. halo_engine-0.1.1/tests/probes/README.md +429 -0
  583. halo_engine-0.1.1/tests/probes/__init__.py +0 -0
  584. halo_engine-0.1.1/tests/probes/example_agent_context_input.py +203 -0
  585. halo_engine-0.1.1/tests/probes/example_circuit_breaker.py +166 -0
  586. halo_engine-0.1.1/tests/probes/example_compaction.py +257 -0
  587. halo_engine-0.1.1/tests/probes/example_depth_enforcement.py +245 -0
  588. halo_engine-0.1.1/tests/probes/example_final_sentinel.py +196 -0
  589. halo_engine-0.1.1/tests/probes/example_streaming_contract.py +158 -0
  590. halo_engine-0.1.1/tests/probes/example_subagent_lifecycle.py +306 -0
  591. halo_engine-0.1.1/tests/probes/probe_kit.py +494 -0
  592. halo_engine-0.1.1/tests/unit/__init__.py +0 -0
  593. halo_engine-0.1.1/tests/unit/agents/__init__.py +0 -0
  594. halo_engine-0.1.1/tests/unit/agents/test_agent_config.py +16 -0
  595. halo_engine-0.1.1/tests/unit/agents/test_agent_context.py +232 -0
  596. halo_engine-0.1.1/tests/unit/agents/test_agent_context_items.py +34 -0
  597. halo_engine-0.1.1/tests/unit/agents/test_agent_execution.py +31 -0
  598. halo_engine-0.1.1/tests/unit/agents/test_engine_output_bus.py +70 -0
  599. halo_engine-0.1.1/tests/unit/agents/test_engine_run_state.py +67 -0
  600. halo_engine-0.1.1/tests/unit/agents/test_openai_agent_runner.py +387 -0
  601. halo_engine-0.1.1/tests/unit/agents/test_openai_event_mapper.py +167 -0
  602. halo_engine-0.1.1/tests/unit/agents/test_prompt_templates.py +64 -0
  603. halo_engine-0.1.1/tests/unit/models/__init__.py +0 -0
  604. halo_engine-0.1.1/tests/unit/models/test_engine_output.py +54 -0
  605. halo_engine-0.1.1/tests/unit/models/test_messages.py +50 -0
  606. halo_engine-0.1.1/tests/unit/sandbox/__init__.py +0 -0
  607. halo_engine-0.1.1/tests/unit/sandbox/test_models.py +14 -0
  608. halo_engine-0.1.1/tests/unit/sandbox/test_sandbox.py +977 -0
  609. halo_engine-0.1.1/tests/unit/test_engine_config.py +46 -0
  610. halo_engine-0.1.1/tests/unit/test_errors.py +27 -0
  611. halo_engine-0.1.1/tests/unit/test_main.py +18 -0
  612. halo_engine-0.1.1/tests/unit/test_model_config.py +16 -0
  613. halo_engine-0.1.1/tests/unit/tools/__init__.py +0 -0
  614. halo_engine-0.1.1/tests/unit/tools/test_agent_context_tools.py +38 -0
  615. halo_engine-0.1.1/tests/unit/tools/test_run_code_tool.py +68 -0
  616. halo_engine-0.1.1/tests/unit/tools/test_run_code_tool_gating.py +118 -0
  617. halo_engine-0.1.1/tests/unit/tools/test_sdk_adapter.py +34 -0
  618. halo_engine-0.1.1/tests/unit/tools/test_subagent_tool_factory.py +430 -0
  619. halo_engine-0.1.1/tests/unit/tools/test_synthesis_tool.py +52 -0
  620. halo_engine-0.1.1/tests/unit/tools/test_tool_protocol.py +31 -0
  621. halo_engine-0.1.1/tests/unit/tools/test_trace_tools.py +72 -0
  622. halo_engine-0.1.1/tests/unit/traces/__init__.py +0 -0
  623. halo_engine-0.1.1/tests/unit/traces/models/__init__.py +0 -0
  624. halo_engine-0.1.1/tests/unit/traces/models/test_canonical_span.py +36 -0
  625. halo_engine-0.1.1/tests/unit/traces/models/test_trace_index_config.py +16 -0
  626. halo_engine-0.1.1/tests/unit/traces/models/test_trace_index_models.py +37 -0
  627. halo_engine-0.1.1/tests/unit/traces/models/test_trace_query_models.py +110 -0
  628. halo_engine-0.1.1/tests/unit/traces/test_trace_index_builder.py +571 -0
  629. halo_engine-0.1.1/tests/unit/traces/test_trace_store.py +116 -0
  630. halo_engine-0.1.1/uv.lock +965 -0
@@ -0,0 +1,11 @@
1
+ #!/usr/bin/env bash
2
+ set -euo pipefail
3
+
4
+ REPO_ROOT="$(git rev-parse --show-toplevel)"
5
+ export GIT_WORK_TREE="$REPO_ROOT"
6
+
7
+ HOOK="$REPO_ROOT/scripts/git-hooks/pre-commit"
8
+
9
+ if [[ -x "$HOOK" ]]; then
10
+ "$HOOK"
11
+ fi
@@ -0,0 +1,22 @@
1
+ #!/usr/bin/env bash
2
+ set -euo pipefail
3
+
4
+ REPO_ROOT="$(git rev-parse --show-toplevel)"
5
+ export GIT_WORK_TREE="$REPO_ROOT"
6
+
7
+ REFS_FILE="$(mktemp)"
8
+
9
+ cleanup() {
10
+ rm -f "$REFS_FILE"
11
+ }
12
+
13
+ trap cleanup EXIT
14
+ cat > "$REFS_FILE"
15
+
16
+ REMOTE="${1:-}"
17
+ URL="${2:-}"
18
+ HOOK="$REPO_ROOT/scripts/git-hooks/pre-push"
19
+
20
+ if [[ -x "$HOOK" ]]; then
21
+ "$HOOK" "$REMOTE" "$URL" < "$REFS_FILE"
22
+ fi
@@ -0,0 +1,88 @@
1
+ name: "[Engine] E2E Tests"
2
+
3
+ on:
4
+ workflow_dispatch:
5
+ workflow_call:
6
+ secrets:
7
+ INFISICAL_CLIENT_ID:
8
+ required: true
9
+ INFISICAL_CLIENT_SECRET:
10
+ required: true
11
+
12
+ env:
13
+ PYTHON_VERSION: "3.12"
14
+ INFISICAL_CLI_VERSION: "0.41.2"
15
+ INFISICAL_PROJECT_ID: "822ab0ec-ad72-4b7d-9f49-93b43be4eda0"
16
+
17
+ permissions:
18
+ checks: write
19
+ contents: read
20
+
21
+ jobs:
22
+ e2e-tests:
23
+ name: E2E Tests
24
+ runs-on: depot-ubuntu-latest
25
+ timeout-minutes: 45
26
+
27
+ steps:
28
+ - name: Checkout code
29
+ uses: actions/checkout@v4
30
+
31
+ - name: Set up Python
32
+ uses: actions/setup-python@v5
33
+ with:
34
+ python-version: ${{ env.PYTHON_VERSION }}
35
+
36
+ - name: Install uv
37
+ uses: astral-sh/setup-uv@v4
38
+ with:
39
+ enable-cache: true
40
+ cache-dependency-glob: "uv.lock"
41
+
42
+ - name: Install go-task
43
+ uses: arduino/setup-task@v2
44
+ with:
45
+ version: 3.x
46
+
47
+ - name: Install Infisical CLI
48
+ run: |
49
+ curl -fsSL "https://github.com/Infisical/infisical/releases/download/infisical-cli%2Fv${INFISICAL_CLI_VERSION}/infisical_${INFISICAL_CLI_VERSION}_linux_amd64.deb" -o /tmp/infisical.deb
50
+ sudo dpkg -i /tmp/infisical.deb
51
+ rm /tmp/infisical.deb
52
+
53
+ - name: Install engine dependencies
54
+ run: task ci:setup
55
+
56
+ - name: Authenticate Infisical
57
+ env:
58
+ INFISICAL_CLIENT_ID: ${{ secrets.INFISICAL_CLIENT_ID }}
59
+ INFISICAL_CLIENT_SECRET: ${{ secrets.INFISICAL_CLIENT_SECRET }}
60
+ run: |
61
+ TOKEN=$(infisical login --method=universal-auth \
62
+ --client-id="$INFISICAL_CLIENT_ID" \
63
+ --client-secret="$INFISICAL_CLIENT_SECRET" \
64
+ --silent --plain)
65
+ echo "::add-mask::$TOKEN"
66
+ echo "INFISICAL_TOKEN=$TOKEN" >> "$GITHUB_ENV"
67
+
68
+ - name: Run E2E tests
69
+ run: task test:e2e
70
+
71
+ - name: Publish Test Report
72
+ uses: mikepenz/action-junit-report@v5
73
+ if: always()
74
+ with:
75
+ report_paths: "test-results/e2e/junit.xml"
76
+ update_check: true
77
+ detailed_summary: true
78
+ include_passed: true
79
+ include_time_in_summary: true
80
+ fail_on_failure: true
81
+
82
+ - name: Upload artifacts
83
+ uses: actions/upload-artifact@v4
84
+ if: always()
85
+ with:
86
+ name: engine-e2e-test-results
87
+ path: test-results/e2e/
88
+ retention-days: 14
@@ -0,0 +1,92 @@
1
+ name: "[Engine] Integration Tests (Live)"
2
+
3
+ # Live integration tests hit a real LLM provider, so this workflow is gated
4
+ # behind Infisical credentials and never auto-triggers on PR or push. It runs
5
+ # on demand via ``workflow_dispatch`` and is invoked from
6
+ # ``engine--release.yml`` via ``workflow_call``.
7
+ on:
8
+ workflow_dispatch:
9
+ workflow_call:
10
+ secrets:
11
+ INFISICAL_CLIENT_ID:
12
+ required: true
13
+ INFISICAL_CLIENT_SECRET:
14
+ required: true
15
+
16
+ env:
17
+ PYTHON_VERSION: "3.12"
18
+ INFISICAL_CLI_VERSION: "0.41.2"
19
+ INFISICAL_PROJECT_ID: "822ab0ec-ad72-4b7d-9f49-93b43be4eda0"
20
+
21
+ permissions:
22
+ checks: write
23
+ contents: read
24
+
25
+ jobs:
26
+ live-integration-tests:
27
+ name: Live Integration Tests
28
+ runs-on: depot-ubuntu-latest
29
+ timeout-minutes: 30
30
+
31
+ steps:
32
+ - name: Checkout code
33
+ uses: actions/checkout@v4
34
+
35
+ - name: Set up Python
36
+ uses: actions/setup-python@v5
37
+ with:
38
+ python-version: ${{ env.PYTHON_VERSION }}
39
+
40
+ - name: Install uv
41
+ uses: astral-sh/setup-uv@v4
42
+ with:
43
+ enable-cache: true
44
+ cache-dependency-glob: "uv.lock"
45
+
46
+ - name: Install go-task
47
+ uses: arduino/setup-task@v2
48
+ with:
49
+ version: 3.x
50
+
51
+ - name: Install Infisical CLI
52
+ run: |
53
+ curl -fsSL "https://github.com/Infisical/infisical/releases/download/infisical-cli%2Fv${INFISICAL_CLI_VERSION}/infisical_${INFISICAL_CLI_VERSION}_linux_amd64.deb" -o /tmp/infisical.deb
54
+ sudo dpkg -i /tmp/infisical.deb
55
+ rm /tmp/infisical.deb
56
+
57
+ - name: Install engine dependencies
58
+ run: task ci:setup
59
+
60
+ - name: Authenticate Infisical
61
+ env:
62
+ INFISICAL_CLIENT_ID: ${{ secrets.INFISICAL_CLIENT_ID }}
63
+ INFISICAL_CLIENT_SECRET: ${{ secrets.INFISICAL_CLIENT_SECRET }}
64
+ run: |
65
+ TOKEN=$(infisical login --method=universal-auth \
66
+ --client-id="$INFISICAL_CLIENT_ID" \
67
+ --client-secret="$INFISICAL_CLIENT_SECRET" \
68
+ --silent --plain)
69
+ echo "::add-mask::$TOKEN"
70
+ echo "INFISICAL_TOKEN=$TOKEN" >> "$GITHUB_ENV"
71
+
72
+ - name: Run live integration tests
73
+ run: task test:integration:live
74
+
75
+ - name: Publish Test Report
76
+ uses: mikepenz/action-junit-report@v5
77
+ if: always()
78
+ with:
79
+ report_paths: "test-results/integration-live.xml"
80
+ update_check: true
81
+ detailed_summary: true
82
+ include_passed: true
83
+ include_time_in_summary: true
84
+ fail_on_failure: true
85
+
86
+ - name: Upload artifacts
87
+ uses: actions/upload-artifact@v4
88
+ if: always()
89
+ with:
90
+ name: engine-live-integration-test-results
91
+ path: test-results/
92
+ retention-days: 14
@@ -0,0 +1,89 @@
1
+ name: "[Engine] Integration Tests"
2
+
3
+ on:
4
+ pull_request:
5
+ branches: [main]
6
+ paths:
7
+ - "engine/**"
8
+ - "tests/**"
9
+ - "scripts/**"
10
+ - "pyproject.toml"
11
+ - "uv.lock"
12
+ - "Taskfile.yml"
13
+ - "pyrightconfig.json"
14
+ - ".github/workflows/engine--integration-tests.yml"
15
+ push:
16
+ branches: [main]
17
+ paths:
18
+ - "engine/**"
19
+ - "tests/**"
20
+ - "scripts/**"
21
+ - "pyproject.toml"
22
+ - "uv.lock"
23
+ - "Taskfile.yml"
24
+ - "pyrightconfig.json"
25
+ - ".github/workflows/engine--integration-tests.yml"
26
+ workflow_dispatch:
27
+ workflow_call:
28
+
29
+ concurrency:
30
+ group: ${{ github.workflow }}-${{ github.ref }}
31
+ cancel-in-progress: false
32
+
33
+ env:
34
+ PYTHON_VERSION: "3.12"
35
+
36
+ permissions:
37
+ checks: write
38
+ contents: read
39
+
40
+ jobs:
41
+ integration-tests:
42
+ name: Integration Tests
43
+ runs-on: depot-ubuntu-latest
44
+ timeout-minutes: 15
45
+
46
+ steps:
47
+ - name: Checkout code
48
+ uses: actions/checkout@v4
49
+
50
+ - name: Set up Python
51
+ uses: actions/setup-python@v5
52
+ with:
53
+ python-version: ${{ env.PYTHON_VERSION }}
54
+
55
+ - name: Install uv
56
+ uses: astral-sh/setup-uv@v4
57
+ with:
58
+ enable-cache: true
59
+ cache-dependency-glob: "uv.lock"
60
+
61
+ - name: Install go-task
62
+ uses: arduino/setup-task@v2
63
+ with:
64
+ version: 3.x
65
+
66
+ - name: Install engine dependencies
67
+ run: task ci:setup
68
+
69
+ - name: Run integration tests (excludes ``-m live``)
70
+ run: task test:integration
71
+
72
+ - name: Publish Test Report
73
+ uses: mikepenz/action-junit-report@v5
74
+ if: always()
75
+ with:
76
+ report_paths: "test-results/integration.xml"
77
+ update_check: true
78
+ detailed_summary: true
79
+ include_passed: true
80
+ include_time_in_summary: true
81
+ fail_on_failure: true
82
+
83
+ - name: Upload artifacts
84
+ uses: actions/upload-artifact@v4
85
+ if: always()
86
+ with:
87
+ name: engine-integration-test-results
88
+ path: test-results/
89
+ retention-days: 14
@@ -0,0 +1,76 @@
1
+ name: "[Engine] Lint, Format & Typecheck"
2
+
3
+ on:
4
+ pull_request:
5
+ branches: [main]
6
+ paths:
7
+ - "engine/**"
8
+ - "tests/**"
9
+ - "scripts/**"
10
+ - "pyproject.toml"
11
+ - "uv.lock"
12
+ - "Taskfile.yml"
13
+ - "pyrightconfig.json"
14
+ - ".github/workflows/engine--lint-format-typecheck.yml"
15
+ push:
16
+ branches: [main]
17
+ paths:
18
+ - "engine/**"
19
+ - "tests/**"
20
+ - "scripts/**"
21
+ - "pyproject.toml"
22
+ - "uv.lock"
23
+ - "Taskfile.yml"
24
+ - "pyrightconfig.json"
25
+ - ".github/workflows/engine--lint-format-typecheck.yml"
26
+ workflow_call:
27
+
28
+ concurrency:
29
+ group: ${{ github.workflow }}-${{ github.ref }}
30
+ cancel-in-progress: false
31
+
32
+ env:
33
+ PYTHON_VERSION: "3.12"
34
+
35
+ permissions:
36
+ contents: read
37
+
38
+ jobs:
39
+ lint-format-typecheck:
40
+ name: Lint, Format & Typecheck
41
+ runs-on: depot-ubuntu-latest
42
+
43
+ steps:
44
+ - name: Checkout code
45
+ uses: actions/checkout@v4
46
+
47
+ - name: Set up Python
48
+ uses: actions/setup-python@v5
49
+ with:
50
+ python-version: ${{ env.PYTHON_VERSION }}
51
+
52
+ - name: Install uv
53
+ uses: astral-sh/setup-uv@v4
54
+ with:
55
+ enable-cache: true
56
+ cache-dependency-glob: "uv.lock"
57
+
58
+ - name: Install go-task
59
+ uses: arduino/setup-task@v2
60
+ with:
61
+ version: 3.x
62
+
63
+ - name: Install engine dependencies
64
+ run: task ci:setup
65
+
66
+ - name: Validate pinned versions
67
+ run: task pinned-versions
68
+
69
+ - name: Lint (ruff)
70
+ run: task lint
71
+
72
+ - name: Format check (ruff)
73
+ run: task format
74
+
75
+ - name: Type check (basedpyright)
76
+ run: task typecheck
@@ -0,0 +1,269 @@
1
+ name: "[Engine] Release"
2
+
3
+ on:
4
+ workflow_dispatch:
5
+ inputs:
6
+ semver_action:
7
+ description: "Semantic version bump"
8
+ required: true
9
+ default: patch
10
+ type: choice
11
+ options:
12
+ - patch
13
+ - minor
14
+ - major
15
+ dry_run:
16
+ description: "Dry run (build only; skip commit, push, and PyPI publish)"
17
+ required: true
18
+ default: true
19
+ type: boolean
20
+
21
+ concurrency:
22
+ group: engine-release-${{ github.ref_name }}
23
+ cancel-in-progress: false
24
+
25
+ env:
26
+ PYTHON_VERSION: "3.12"
27
+ CI_BOT_GITHUB_APP_ID: "1281730"
28
+
29
+ INFISICAL_IDENTITY_ID: "dc1d9282-7640-471d-bc3e-926297a5ef85" # halo-github-ci
30
+
31
+ permissions:
32
+ contents: write # tag-and-push pushes the version commit + tag
33
+ checks: write # called workflows publish JUnit reports via checks API
34
+ id-token: write # Required for OIDC-based Infisical auth and PyPI trusted publishing
35
+
36
+ jobs:
37
+ lint-format-typecheck:
38
+ name: Lint, Format & Typecheck
39
+ uses: ./.github/workflows/engine--lint-format-typecheck.yml
40
+ secrets: inherit
41
+
42
+ unit-tests:
43
+ name: Unit Tests
44
+ uses: ./.github/workflows/engine--unit-tests.yml
45
+ secrets: inherit
46
+
47
+ integration-tests:
48
+ name: Integration Tests
49
+ needs: [lint-format-typecheck, unit-tests]
50
+ uses: ./.github/workflows/engine--integration-tests.yml
51
+ secrets: inherit
52
+
53
+ integration-tests-live:
54
+ name: Integration Tests (Live)
55
+ needs: [lint-format-typecheck, unit-tests]
56
+ uses: ./.github/workflows/engine--integration-tests-live.yml
57
+ secrets: inherit
58
+
59
+ e2e-tests:
60
+ name: E2E Tests
61
+ needs: [integration-tests, integration-tests-live]
62
+ uses: ./.github/workflows/engine--e2e-tests.yml
63
+ secrets: inherit
64
+
65
+ bump-version:
66
+ name: Bump Version
67
+ needs: [e2e-tests]
68
+ runs-on: depot-ubuntu-latest
69
+ outputs:
70
+ new_version: ${{ steps.bump.outputs.new_version }}
71
+ steps:
72
+ - uses: actions/checkout@v4
73
+
74
+ - name: Set up Python
75
+ uses: actions/setup-python@v5
76
+ with:
77
+ python-version: ${{ env.PYTHON_VERSION }}
78
+
79
+ - name: Install uv
80
+ uses: astral-sh/setup-uv@v4
81
+ with:
82
+ enable-cache: true
83
+ cache-dependency-glob: "uv.lock"
84
+
85
+ - name: Bump engine version
86
+ id: bump
87
+ run: |
88
+ NEW_VERSION=$(uv version --bump "${{ inputs.semver_action }}" --short --no-sync)
89
+ echo "Bumped engine version to ${NEW_VERSION}"
90
+ echo "new_version=${NEW_VERSION}" >> "$GITHUB_OUTPUT"
91
+ # Refresh uv.lock so the version inside it matches the bumped
92
+ # pyproject.toml. ``--no-sync`` above skips reinstall but also
93
+ # skips the lock refresh — without this, the release commit
94
+ # would push a uv.lock that lags pyproject.toml.
95
+ uv lock
96
+
97
+ - name: Upload bumped manifests
98
+ uses: actions/upload-artifact@v4
99
+ with:
100
+ name: engine-release-manifests
101
+ path: |
102
+ pyproject.toml
103
+ uv.lock
104
+ retention-days: 1
105
+
106
+ build:
107
+ name: Build
108
+ needs: [bump-version]
109
+ runs-on: depot-ubuntu-latest
110
+ steps:
111
+ - uses: actions/checkout@v4
112
+
113
+ - name: Download bumped manifests
114
+ uses: actions/download-artifact@v4
115
+ with:
116
+ name: engine-release-manifests
117
+ path: .
118
+
119
+ - name: Set up Python
120
+ uses: actions/setup-python@v5
121
+ with:
122
+ python-version: ${{ env.PYTHON_VERSION }}
123
+
124
+ - name: Install uv
125
+ uses: astral-sh/setup-uv@v4
126
+ with:
127
+ enable-cache: true
128
+ cache-dependency-glob: "uv.lock"
129
+
130
+ - name: Build distributions
131
+ run: uv build
132
+
133
+ - name: Upload distribution artifact
134
+ uses: actions/upload-artifact@v4
135
+ with:
136
+ name: halo-engine-dist
137
+ path: dist/*
138
+ retention-days: 14
139
+
140
+ publish:
141
+ name: Publish to PyPI
142
+ needs: [bump-version, build]
143
+ if: ${{ inputs.dry_run == false }}
144
+ runs-on: depot-ubuntu-latest
145
+ permissions:
146
+ contents: read
147
+ id-token: write
148
+ environment:
149
+ name: pypi
150
+ url: https://pypi.org/project/halo-engine/${{ needs.bump-version.outputs.new_version }}/
151
+ steps:
152
+ - uses: actions/checkout@v4
153
+
154
+ - name: Set up Python
155
+ uses: actions/setup-python@v5
156
+ with:
157
+ python-version: ${{ env.PYTHON_VERSION }}
158
+
159
+ - name: Install uv
160
+ uses: astral-sh/setup-uv@v4
161
+ with:
162
+ enable-cache: true
163
+ cache-dependency-glob: "uv.lock"
164
+
165
+ - name: Download distribution artifact
166
+ uses: actions/download-artifact@v4
167
+ with:
168
+ name: halo-engine-dist
169
+ path: dist
170
+
171
+ - name: Publish to PyPI
172
+ run: uv publish --trusted-publishing always
173
+
174
+ tag-and-push:
175
+ name: Tag & Push Version Bump
176
+ needs: [bump-version, publish]
177
+ if: ${{ inputs.dry_run == false }}
178
+ runs-on: depot-ubuntu-latest
179
+ permissions:
180
+ contents: write
181
+ id-token: write # Required for OIDC-based Infisical auth
182
+ steps:
183
+ - name: Load Infisical secrets
184
+ uses: Infisical/secrets-action@v1.0.15
185
+ with:
186
+ method: "oidc"
187
+ identity-id: ${{ env.INFISICAL_IDENTITY_ID }}
188
+ project-slug: "halo-0ys-z"
189
+ env-slug: "dev"
190
+ secret-path: "/ci"
191
+ include-imports: true
192
+
193
+ - name: Mint CI Bot token
194
+ uses: actions/create-github-app-token@v1
195
+ id: app-token
196
+ with:
197
+ app-id: ${{ env.CI_BOT_GITHUB_APP_ID }}
198
+ private-key: ${{ env.CI_BOT_GITHUB_APP_PRIVATE_KEY }}
199
+
200
+ - uses: actions/checkout@v4
201
+ with:
202
+ fetch-depth: 0
203
+ token: ${{ steps.app-token.outputs.token }}
204
+
205
+ - name: Download bumped manifests
206
+ uses: actions/download-artifact@v4
207
+ with:
208
+ name: engine-release-manifests
209
+ path: .
210
+
211
+ - name: Commit, tag, and push version bump
212
+ env:
213
+ NEW_VERSION: ${{ needs.bump-version.outputs.new_version }}
214
+ run: |
215
+ git config user.email "github-actions[bot]@users.noreply.github.com"
216
+ git config user.name "github-actions[bot]"
217
+ git add pyproject.toml uv.lock
218
+ git commit -m "Release engine v${NEW_VERSION}"
219
+ git tag "engine-v${NEW_VERSION}"
220
+ git push origin "HEAD:${GITHUB_REF_NAME}"
221
+ git push origin "engine-v${NEW_VERSION}"
222
+
223
+ summary:
224
+ name: Release Summary
225
+ needs:
226
+ - lint-format-typecheck
227
+ - unit-tests
228
+ - integration-tests
229
+ - integration-tests-live
230
+ - e2e-tests
231
+ - bump-version
232
+ - build
233
+ - publish
234
+ - tag-and-push
235
+ if: always()
236
+ runs-on: depot-ubuntu-latest
237
+ steps:
238
+ - name: Generate summary
239
+ env:
240
+ DRY_RUN: ${{ inputs.dry_run }}
241
+ SEMVER_ACTION: ${{ inputs.semver_action }}
242
+ NEW_VERSION: ${{ needs.bump-version.outputs.new_version }}
243
+ LINT_RESULT: ${{ needs.lint-format-typecheck.result }}
244
+ UNIT_RESULT: ${{ needs.unit-tests.result }}
245
+ INTEGRATION_RESULT: ${{ needs.integration-tests.result }}
246
+ INTEGRATION_LIVE_RESULT: ${{ needs.integration-tests-live.result }}
247
+ E2E_RESULT: ${{ needs.e2e-tests.result }}
248
+ BUMP_RESULT: ${{ needs.bump-version.result }}
249
+ BUILD_RESULT: ${{ needs.build.result }}
250
+ PUBLISH_RESULT: ${{ needs.publish.result }}
251
+ TAG_PUSH_RESULT: ${{ needs.tag-and-push.result }}
252
+ run: |
253
+ {
254
+ echo "## Engine Release Summary"
255
+ echo ""
256
+ echo "**Semver action:** ${SEMVER_ACTION}"
257
+ echo "**New version:** ${NEW_VERSION:-unknown}"
258
+ echo "**Dry run:** ${DRY_RUN}"
259
+ echo ""
260
+ echo "**Lint/Format/Typecheck:** ${LINT_RESULT}"
261
+ echo "**Unit Tests:** ${UNIT_RESULT}"
262
+ echo "**Integration:** ${INTEGRATION_RESULT}"
263
+ echo "**Integration (Live):** ${INTEGRATION_LIVE_RESULT}"
264
+ echo "**E2E:** ${E2E_RESULT}"
265
+ echo "**Version Bump:** ${BUMP_RESULT}"
266
+ echo "**Build:** ${BUILD_RESULT}"
267
+ echo "**Publish:** ${PUBLISH_RESULT}"
268
+ echo "**Tag & Push:** ${TAG_PUSH_RESULT}"
269
+ } >> "$GITHUB_STEP_SUMMARY"