agentcompass 1.0.0__py3-none-any.whl

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 (440) hide show
  1. agentcompass/__init__.py +53 -0
  2. agentcompass/analyzers/__init__.py +24 -0
  3. agentcompass/analyzers/basic/__init__.py +19 -0
  4. agentcompass/analyzers/basic/basic_metric_analyzer.py +88 -0
  5. agentcompass/analyzers/basic/command_running_analyzer.py +256 -0
  6. agentcompass/analyzers/basic/completion_length_analyzer.py +92 -0
  7. agentcompass/analyzers/basic/empty_content_analyzer.py +80 -0
  8. agentcompass/analyzers/basic/exception_analyzer.py +167 -0
  9. agentcompass/analyzers/basic/json_error_analyzer.py +177 -0
  10. agentcompass/analyzers/basic/keyword_analyzer.py +156 -0
  11. agentcompass/analyzers/basic/latency_analyzer.py +265 -0
  12. agentcompass/analyzers/basic/mixed_lang_analyzer.py +175 -0
  13. agentcompass/analyzers/basic/network_op_analyzer.py +192 -0
  14. agentcompass/analyzers/basic/repetition_analyzer.py +340 -0
  15. agentcompass/analyzers/basic/tool_repetition_analyzer.py +409 -0
  16. agentcompass/analyzers/basic/truncation_analyzer.py +62 -0
  17. agentcompass/analyzers/hack_detection/__init__.py +14 -0
  18. agentcompass/analyzers/hack_detection/analyzer.py +419 -0
  19. agentcompass/analyzers/hack_detection/llm_verification.py +395 -0
  20. agentcompass/analyzers/hack_detection/rules.py +322 -0
  21. agentcompass/analyzers/qualitative/__init__.py +4 -0
  22. agentcompass/analyzers/qualitative/assets/codebook.md +342 -0
  23. agentcompass/analyzers/qualitative/assets/prompt.md +195 -0
  24. agentcompass/analyzers/qualitative/multi_qualitative_analyzer.py +640 -0
  25. agentcompass/analyzers/qualitative/qualitative_analyzer.py +1178 -0
  26. agentcompass/analyzers/qualitative/trajectory_parser.py +198 -0
  27. agentcompass/analyzers/trajectory_graph/__init__.py +40 -0
  28. agentcompass/analyzers/trajectory_graph/graph.py +484 -0
  29. agentcompass/analyzers/trajectory_graph/io.py +302 -0
  30. agentcompass/analyzers/trajectory_graph/render_html.py +1108 -0
  31. agentcompass/benchmarks/__init__.py +35 -0
  32. agentcompass/benchmarks/brainarena/__init__.py +5 -0
  33. agentcompass/benchmarks/brainarena/brainarena.py +326 -0
  34. agentcompass/benchmarks/brainarena/data/queries/genkin_2025/Fig_2B.md +1 -0
  35. agentcompass/benchmarks/brainarena/data/queries/genkin_2025/Fig_3A.md +1 -0
  36. agentcompass/benchmarks/brainarena/data/queries/genkin_2025/Fig_3C.md +1 -0
  37. agentcompass/benchmarks/brainarena/data/queries/genkin_2025/Fig_4B.md +1 -0
  38. agentcompass/benchmarks/brainarena/data/queries/legare_2025/Fig_2B.md +1 -0
  39. agentcompass/benchmarks/brainarena/data/queries/legare_2025/Fig_3A.md +1 -0
  40. agentcompass/benchmarks/brainarena/data/queries/tanaka_2026/Fig_3E.md +1 -0
  41. agentcompass/benchmarks/brainarena/data/queries/tanaka_2026/Fig_4A.md +1 -0
  42. agentcompass/benchmarks/brainarena/data/queries/tanaka_2026/Fig_4G.md +1 -0
  43. agentcompass/benchmarks/brainarena/data/queries/yu_2025/Fig_5C.md +1 -0
  44. agentcompass/benchmarks/brainarena/data/queries/yu_2025/Fig_5M.md +1 -0
  45. agentcompass/benchmarks/brainarena/data/references/genkin_2025/Fig_2B.png +0 -0
  46. agentcompass/benchmarks/brainarena/data/references/genkin_2025/Fig_3A.png +0 -0
  47. agentcompass/benchmarks/brainarena/data/references/genkin_2025/Fig_3C.png +0 -0
  48. agentcompass/benchmarks/brainarena/data/references/genkin_2025/Fig_4B.png +0 -0
  49. agentcompass/benchmarks/brainarena/data/references/legare_2025/Fig_2B.png +0 -0
  50. agentcompass/benchmarks/brainarena/data/references/legare_2025/Fig_3A.png +0 -0
  51. agentcompass/benchmarks/brainarena/data/references/legare_2025/README.md +7 -0
  52. agentcompass/benchmarks/brainarena/data/references/tanaka_2026/Fig_3E.png +0 -0
  53. agentcompass/benchmarks/brainarena/data/references/tanaka_2026/Fig_4A.png +0 -0
  54. agentcompass/benchmarks/brainarena/data/references/tanaka_2026/Fig_4G.png +0 -0
  55. agentcompass/benchmarks/brainarena/data/references/yu_2025/Fig_5C.png +0 -0
  56. agentcompass/benchmarks/brainarena/data/references/yu_2025/Fig_5M.png +0 -0
  57. agentcompass/benchmarks/brainarena/data/rubrics/genkin_2025/Fig_2B.json +44 -0
  58. agentcompass/benchmarks/brainarena/data/rubrics/genkin_2025/Fig_3A.json +53 -0
  59. agentcompass/benchmarks/brainarena/data/rubrics/genkin_2025/Fig_3C.json +41 -0
  60. agentcompass/benchmarks/brainarena/data/rubrics/genkin_2025/Fig_4B.json +40 -0
  61. agentcompass/benchmarks/brainarena/data/rubrics/legare_2025/Fig_2B.json +41 -0
  62. agentcompass/benchmarks/brainarena/data/rubrics/legare_2025/Fig_3A.json +43 -0
  63. agentcompass/benchmarks/brainarena/data/rubrics/tanaka_2026/Fig_3E.json +51 -0
  64. agentcompass/benchmarks/brainarena/data/rubrics/tanaka_2026/Fig_4A.json +44 -0
  65. agentcompass/benchmarks/brainarena/data/rubrics/tanaka_2026/Fig_4G.json +45 -0
  66. agentcompass/benchmarks/brainarena/data/rubrics/yu_2025/Fig_5C.json +39 -0
  67. agentcompass/benchmarks/brainarena/data/rubrics/yu_2025/Fig_5M.json +43 -0
  68. agentcompass/benchmarks/brainarena/data/tasks.json +13 -0
  69. agentcompass/benchmarks/brainarena/datasets.py +197 -0
  70. agentcompass/benchmarks/brainarena/scorer.py +202 -0
  71. agentcompass/benchmarks/browsecomp.py +127 -0
  72. agentcompass/benchmarks/browsecomp_zh.py +127 -0
  73. agentcompass/benchmarks/config.py +118 -0
  74. agentcompass/benchmarks/deepresearch_bench/__init__.py +5 -0
  75. agentcompass/benchmarks/deepresearch_bench/dataset.py +142 -0
  76. agentcompass/benchmarks/deepresearch_bench/deepresearch_bench.py +528 -0
  77. agentcompass/benchmarks/deepresearch_bench/fact.py +472 -0
  78. agentcompass/benchmarks/deepresearch_bench/parsing.py +178 -0
  79. agentcompass/benchmarks/deepresearch_bench/prompts.py +353 -0
  80. agentcompass/benchmarks/deepresearch_bench/race.py +429 -0
  81. agentcompass/benchmarks/deepresearch_bench/weighting.py +180 -0
  82. agentcompass/benchmarks/deepsearchqa.py +142 -0
  83. agentcompass/benchmarks/deepswe.py +532 -0
  84. agentcompass/benchmarks/frontier_engineering/__init__.py +5 -0
  85. agentcompass/benchmarks/frontier_engineering/data/medal_podium.csv +48 -0
  86. agentcompass/benchmarks/frontier_engineering/data/rank_baseline.csv +441 -0
  87. agentcompass/benchmarks/frontier_engineering/data/v1.yaml +264 -0
  88. agentcompass/benchmarks/frontier_engineering/data/v1_lite.yaml +83 -0
  89. agentcompass/benchmarks/frontier_engineering/evaluator.py +663 -0
  90. agentcompass/benchmarks/frontier_engineering/frontier_engineering.py +1995 -0
  91. agentcompass/benchmarks/frontier_engineering/openevolve_evaluator.py +38 -0
  92. agentcompass/benchmarks/frontier_swe.py +485 -0
  93. agentcompass/benchmarks/frontierscience.py +147 -0
  94. agentcompass/benchmarks/gaia.py +141 -0
  95. agentcompass/benchmarks/gdpval_ac/__init__.py +5 -0
  96. agentcompass/benchmarks/gdpval_ac/dataset.py +285 -0
  97. agentcompass/benchmarks/gdpval_ac/gdpval_ac.py +1211 -0
  98. agentcompass/benchmarks/gdpval_ac/pairwise_core.py +3111 -0
  99. agentcompass/benchmarks/gdpval_ac/stage_baseline.py +165 -0
  100. agentcompass/benchmarks/hle.py +320 -0
  101. agentcompass/benchmarks/osworld/__init__.py +10 -0
  102. agentcompass/benchmarks/osworld/agent_loop.py +118 -0
  103. agentcompass/benchmarks/osworld/agents/__init__.py +12 -0
  104. agentcompass/benchmarks/osworld/agents/base.py +30 -0
  105. agentcompass/benchmarks/osworld/agents/claude.py +639 -0
  106. agentcompass/benchmarks/osworld/agents/qwen35.py +420 -0
  107. agentcompass/benchmarks/osworld/osworld.py +435 -0
  108. agentcompass/benchmarks/osworld/runtime/__init__.py +23 -0
  109. agentcompass/benchmarks/osworld/runtime/controllers/__init__.py +0 -0
  110. agentcompass/benchmarks/osworld/runtime/controllers/python.py +496 -0
  111. agentcompass/benchmarks/osworld/runtime/controllers/setup.py +1068 -0
  112. agentcompass/benchmarks/osworld/runtime/docker_adapter.py +124 -0
  113. agentcompass/benchmarks/osworld/runtime/evaluator.py +161 -0
  114. agentcompass/benchmarks/osworld/runtime/evaluators/__init__.py +5 -0
  115. agentcompass/benchmarks/osworld/runtime/evaluators/getters/__init__.py +21 -0
  116. agentcompass/benchmarks/osworld/runtime/evaluators/getters/calc.py +15 -0
  117. agentcompass/benchmarks/osworld/runtime/evaluators/getters/chrome.py +2714 -0
  118. agentcompass/benchmarks/osworld/runtime/evaluators/getters/file.py +156 -0
  119. agentcompass/benchmarks/osworld/runtime/evaluators/getters/general.py +44 -0
  120. agentcompass/benchmarks/osworld/runtime/evaluators/getters/gimp.py +38 -0
  121. agentcompass/benchmarks/osworld/runtime/evaluators/getters/impress.py +129 -0
  122. agentcompass/benchmarks/osworld/runtime/evaluators/getters/info.py +50 -0
  123. agentcompass/benchmarks/osworld/runtime/evaluators/getters/misc.py +495 -0
  124. agentcompass/benchmarks/osworld/runtime/evaluators/getters/replay.py +20 -0
  125. agentcompass/benchmarks/osworld/runtime/evaluators/getters/vlc.py +98 -0
  126. agentcompass/benchmarks/osworld/runtime/evaluators/getters/vscode.py +43 -0
  127. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/__init__.py +45 -0
  128. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/basic_os.py +68 -0
  129. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/chrome.py +582 -0
  130. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/docs.py +1195 -0
  131. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/general.py +676 -0
  132. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/gimp.py +951 -0
  133. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/libreoffice.py +24 -0
  134. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/others.py +102 -0
  135. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/pdf.py +30 -0
  136. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/slides.py +1147 -0
  137. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/table.py +693 -0
  138. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/thunderbird.py +179 -0
  139. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/utils.py +820 -0
  140. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/vlc.py +556 -0
  141. agentcompass/benchmarks/osworld/runtime/evaluators/metrics/vscode.py +469 -0
  142. agentcompass/benchmarks/osworld/runtime/task_environment.py +154 -0
  143. agentcompass/benchmarks/osworld/runtime/types.py +49 -0
  144. agentcompass/benchmarks/pinchbench/__init__.py +3 -0
  145. agentcompass/benchmarks/pinchbench/grading_runner.py +118 -0
  146. agentcompass/benchmarks/pinchbench/pinchbench.py +908 -0
  147. agentcompass/benchmarks/pinchbench/pinchbench_grading_runtime.py +656 -0
  148. agentcompass/benchmarks/researchclawbench.py +545 -0
  149. agentcompass/benchmarks/scicode/__init__.py +8 -0
  150. agentcompass/benchmarks/scicode/data/13.6.txt +49 -0
  151. agentcompass/benchmarks/scicode/data/62.1.txt +29 -0
  152. agentcompass/benchmarks/scicode/data/76.3.txt +27 -0
  153. agentcompass/benchmarks/scicode/data/background_comment_template.txt +28 -0
  154. agentcompass/benchmarks/scicode/data/multistep_template.txt +23 -0
  155. agentcompass/benchmarks/scicode/data/problems_dev.jsonl +15 -0
  156. agentcompass/benchmarks/scicode/data/problems_test.jsonl +65 -0
  157. agentcompass/benchmarks/scicode/scicode.py +962 -0
  158. agentcompass/benchmarks/screenspot.py +213 -0
  159. agentcompass/benchmarks/sealqa.py +286 -0
  160. agentcompass/benchmarks/sgi_deep_research.py +124 -0
  161. agentcompass/benchmarks/skillsbench/__init__.py +10 -0
  162. agentcompass/benchmarks/skillsbench/benchmark.py +378 -0
  163. agentcompass/benchmarks/skillsbench/parser/__init__.py +12 -0
  164. agentcompass/benchmarks/skillsbench/parser/parsers.py +60 -0
  165. agentcompass/benchmarks/skillsbench/parser/v10.py +51 -0
  166. agentcompass/benchmarks/skillsbench/parser/v11.py +57 -0
  167. agentcompass/benchmarks/special_pattern.py +256 -0
  168. agentcompass/benchmarks/swe_marathon/__init__.py +9 -0
  169. agentcompass/benchmarks/swe_marathon/swe_marathon.py +632 -0
  170. agentcompass/benchmarks/swe_marathon/verifier.py +189 -0
  171. agentcompass/benchmarks/swe_marathon/workdir.py +48 -0
  172. agentcompass/benchmarks/swebench_multilingual.py +539 -0
  173. agentcompass/benchmarks/swebench_pro.py +641 -0
  174. agentcompass/benchmarks/swebench_pro_verified/__init__.py +13 -0
  175. agentcompass/benchmarks/swebench_pro_verified/network_policy.py +41 -0
  176. agentcompass/benchmarks/swebench_pro_verified/swebench_pro_verified.py +756 -0
  177. agentcompass/benchmarks/swebench_verified.py +579 -0
  178. agentcompass/benchmarks/taubench/__init__.py +5 -0
  179. agentcompass/benchmarks/taubench/_taubench_patch.py +536 -0
  180. agentcompass/benchmarks/taubench/agent_runner.py +261 -0
  181. agentcompass/benchmarks/taubench/remote_runner.py +443 -0
  182. agentcompass/benchmarks/taubench/taubench.py +786 -0
  183. agentcompass/benchmarks/taubench/utils/__init__.py +19 -0
  184. agentcompass/benchmarks/taubench/utils/embedding_cache.py +174 -0
  185. agentcompass/benchmarks/taubench/utils/model_backend.py +518 -0
  186. agentcompass/benchmarks/taubench/utils/utils.py +198 -0
  187. agentcompass/benchmarks/terminalbench2/__init__.py +0 -0
  188. agentcompass/benchmarks/terminalbench2/terminalbench2.py +344 -0
  189. agentcompass/benchmarks/terminalbench2/terminalbench2_1.py +369 -0
  190. agentcompass/benchmarks/terminalbench2/terminalbench2_verified.py +404 -0
  191. agentcompass/benchmarks/terminalbench2/verifier.py +185 -0
  192. agentcompass/benchmarks/terminalbench2/verifier_health.py +68 -0
  193. agentcompass/benchmarks/terminalbench2/workdir.py +53 -0
  194. agentcompass/benchmarks/utils/__init__.py +6 -0
  195. agentcompass/benchmarks/utils/data.py +118 -0
  196. agentcompass/benchmarks/utils/harbor.py +355 -0
  197. agentcompass/benchmarks/utils/scorers/__init__.py +25 -0
  198. agentcompass/benchmarks/utils/scorers/base.py +101 -0
  199. agentcompass/benchmarks/utils/scorers/deepsearchqa.py +239 -0
  200. agentcompass/benchmarks/utils/scorers/frontier_swe.py +257 -0
  201. agentcompass/benchmarks/utils/scorers/frontierscience.py +523 -0
  202. agentcompass/benchmarks/utils/scorers/llm.py +258 -0
  203. agentcompass/benchmarks/utils/scorers/researchclawbench.py +367 -0
  204. agentcompass/benchmarks/utils/scorers/sealqa.py +156 -0
  205. agentcompass/benchmarks/utils/scorers/xbench_deepsearch.py +94 -0
  206. agentcompass/benchmarks/widesearch/__init__.py +28 -0
  207. agentcompass/benchmarks/widesearch/benchmark.py +240 -0
  208. agentcompass/benchmarks/widesearch/dataset.py +90 -0
  209. agentcompass/benchmarks/widesearch/evaluator.py +724 -0
  210. agentcompass/benchmarks/widesearch/metrics.py +20 -0
  211. agentcompass/benchmarks/wildclawbench.py +998 -0
  212. agentcompass/benchmarks/wildclawbench_grading_runner.py +60 -0
  213. agentcompass/benchmarks/xbench_deepsearch.py +168 -0
  214. agentcompass/cli/__init__.py +7 -0
  215. agentcompass/cli/__main__.py +7 -0
  216. agentcompass/cli/main.py +1230 -0
  217. agentcompass/environments/__init__.py +10 -0
  218. agentcompass/environments/brainpp.py +531 -0
  219. agentcompass/environments/daytona.py +576 -0
  220. agentcompass/environments/docker.py +845 -0
  221. agentcompass/environments/docker_egress_proxy.py +398 -0
  222. agentcompass/environments/env_gateway.py +761 -0
  223. agentcompass/environments/host_process.py +202 -0
  224. agentcompass/environments/hsandbox.py +536 -0
  225. agentcompass/environments/modal.py +606 -0
  226. agentcompass/environments/opensandbox.py +384 -0
  227. agentcompass/environments/utils/__init__.py +1 -0
  228. agentcompass/environments/utils/exec.py +60 -0
  229. agentcompass/environments/utils/files.py +54 -0
  230. agentcompass/environments/utils/pvisor.py +208 -0
  231. agentcompass/environments/utils/shared_storage.py +181 -0
  232. agentcompass/errors.py +55 -0
  233. agentcompass/harnesses/__init__.py +14 -0
  234. agentcompass/harnesses/claude_code.py +576 -0
  235. agentcompass/harnesses/codex.py +639 -0
  236. agentcompass/harnesses/gui_agents/__init__.py +1 -0
  237. agentcompass/harnesses/gui_agents/qwen3vl.py +286 -0
  238. agentcompass/harnesses/mini_swe_agent/__init__.py +6 -0
  239. agentcompass/harnesses/mini_swe_agent/harness.py +503 -0
  240. agentcompass/harnesses/mini_swe_agent/interleaved_model.py +31 -0
  241. agentcompass/harnesses/mini_swe_agent/local_runner.py +684 -0
  242. agentcompass/harnesses/mini_swe_agent/plan.py +60 -0
  243. agentcompass/harnesses/mini_swe_agent/remote_runner.py +143 -0
  244. agentcompass/harnesses/mini_swe_agent/trajectory.py +160 -0
  245. agentcompass/harnesses/naive_search_agent/__init__.py +6 -0
  246. agentcompass/harnesses/naive_search_agent/engine/__init__.py +1 -0
  247. agentcompass/harnesses/naive_search_agent/engine/coordinator.py +148 -0
  248. agentcompass/harnesses/naive_search_agent/engine/fc_inferencer.py +711 -0
  249. agentcompass/harnesses/naive_search_agent/engine/runner.py +338 -0
  250. agentcompass/harnesses/naive_search_agent/engine/sub_agents.py +289 -0
  251. agentcompass/harnesses/naive_search_agent/engine/tools/__init__.py +1 -0
  252. agentcompass/harnesses/naive_search_agent/engine/tools/browse.py +577 -0
  253. agentcompass/harnesses/naive_search_agent/engine/tools/registry.py +198 -0
  254. agentcompass/harnesses/naive_search_agent/engine/tools/search.py +647 -0
  255. agentcompass/harnesses/naive_search_agent/engine/tools/web_visitor.py +491 -0
  256. agentcompass/harnesses/naive_search_agent/harness.py +204 -0
  257. agentcompass/harnesses/naive_search_agent/local_runner.py +115 -0
  258. agentcompass/harnesses/naive_search_agent/plan.py +80 -0
  259. agentcompass/harnesses/naive_search_agent/trajectory.py +211 -0
  260. agentcompass/harnesses/openai_chat.py +267 -0
  261. agentcompass/harnesses/openclaw.py +1413 -0
  262. agentcompass/harnesses/openevolve/__init__.py +13 -0
  263. agentcompass/harnesses/openevolve/harness.py +793 -0
  264. agentcompass/harnesses/openevolve/runner.py +557 -0
  265. agentcompass/harnesses/openhands/__init__.py +6 -0
  266. agentcompass/harnesses/openhands/harness.py +258 -0
  267. agentcompass/harnesses/openhands/plan.py +27 -0
  268. agentcompass/harnesses/openhands/prompt.py +34 -0
  269. agentcompass/harnesses/openhands/remote_entry.py +818 -0
  270. agentcompass/harnesses/openhands/remote_runner.py +432 -0
  271. agentcompass/harnesses/openhands/trajectory.py +453 -0
  272. agentcompass/harnesses/qwen3vl_gui.py +119 -0
  273. agentcompass/harnesses/researchharness.py +856 -0
  274. agentcompass/harnesses/scicode_tool_use.py +1038 -0
  275. agentcompass/harnesses/terminus2/__init__.py +0 -0
  276. agentcompass/harnesses/terminus2/llms/__init__.py +0 -0
  277. agentcompass/harnesses/terminus2/llms/chat.py +179 -0
  278. agentcompass/harnesses/terminus2/llms/llm.py +796 -0
  279. agentcompass/harnesses/terminus2/templates/terminus-json-plain.txt +54 -0
  280. agentcompass/harnesses/terminus2/templates/terminus-toolcall.txt +30 -0
  281. agentcompass/harnesses/terminus2/templates/terminus-xml-plain.txt +60 -0
  282. agentcompass/harnesses/terminus2/templates/timeout.txt +10 -0
  283. agentcompass/harnesses/terminus2/terminus_2.py +2496 -0
  284. agentcompass/harnesses/terminus2/tmux_session.py +801 -0
  285. agentcompass/harnesses/utils/__init__.py +23 -0
  286. agentcompass/harnesses/utils/glibc.py +139 -0
  287. agentcompass/harnesses/utils/model.py +24 -0
  288. agentcompass/harnesses/utils/result.py +24 -0
  289. agentcompass/harnesses/utils/sync.py +231 -0
  290. agentcompass/launcher.py +1394 -0
  291. agentcompass/recipes/__init__.py +37 -0
  292. agentcompass/recipes/brainarena/__init__.py +5 -0
  293. agentcompass/recipes/brainarena/docker.py +36 -0
  294. agentcompass/recipes/deepswe/__init__.py +5 -0
  295. agentcompass/recipes/deepswe/common.py +25 -0
  296. agentcompass/recipes/deepswe/daytona.py +24 -0
  297. agentcompass/recipes/deepswe/docker.py +24 -0
  298. agentcompass/recipes/deepswe/modal.py +24 -0
  299. agentcompass/recipes/frontier_engineering/__init__.py +3 -0
  300. agentcompass/recipes/frontier_engineering/docker.py +90 -0
  301. agentcompass/recipes/frontier_swe/__init__.py +5 -0
  302. agentcompass/recipes/frontier_swe/common.py +25 -0
  303. agentcompass/recipes/frontier_swe/daytona.py +21 -0
  304. agentcompass/recipes/frontier_swe/docker.py +23 -0
  305. agentcompass/recipes/frontier_swe/modal.py +26 -0
  306. agentcompass/recipes/gdpval_ac/__init__.py +5 -0
  307. agentcompass/recipes/gdpval_ac/common.py +19 -0
  308. agentcompass/recipes/gdpval_ac/daytona.py +25 -0
  309. agentcompass/recipes/gdpval_ac/docker.py +31 -0
  310. agentcompass/recipes/gdpval_ac/modal.py +25 -0
  311. agentcompass/recipes/osworld/__init__.py +3 -0
  312. agentcompass/recipes/osworld/docker.py +139 -0
  313. agentcompass/recipes/pinchbench/__init__.py +5 -0
  314. agentcompass/recipes/pinchbench/common.py +47 -0
  315. agentcompass/recipes/pinchbench/daytona.py +33 -0
  316. agentcompass/recipes/pinchbench/docker.py +34 -0
  317. agentcompass/recipes/pinchbench/modal.py +33 -0
  318. agentcompass/recipes/researchclawbench/__init__.py +11 -0
  319. agentcompass/recipes/researchclawbench/daytona.py +28 -0
  320. agentcompass/recipes/researchclawbench/docker.py +29 -0
  321. agentcompass/recipes/researchclawbench/modal.py +28 -0
  322. agentcompass/recipes/skillsbench/__init__.py +3 -0
  323. agentcompass/recipes/skillsbench/docker.py +54 -0
  324. agentcompass/recipes/swe_marathon/docker.py +30 -0
  325. agentcompass/recipes/swebench_multilingual/__init__.py +5 -0
  326. agentcompass/recipes/swebench_multilingual/daytona.py +47 -0
  327. agentcompass/recipes/swebench_multilingual/docker.py +45 -0
  328. agentcompass/recipes/swebench_multilingual/modal.py +47 -0
  329. agentcompass/recipes/swebench_pro/__init__.py +5 -0
  330. agentcompass/recipes/swebench_pro/daytona.py +42 -0
  331. agentcompass/recipes/swebench_pro/docker.py +50 -0
  332. agentcompass/recipes/swebench_pro/modal.py +42 -0
  333. agentcompass/recipes/swebench_pro_verified/__init__.py +3 -0
  334. agentcompass/recipes/swebench_pro_verified/docker.py +50 -0
  335. agentcompass/recipes/swebench_verified/__init__.py +6 -0
  336. agentcompass/recipes/swebench_verified/common.py +55 -0
  337. agentcompass/recipes/swebench_verified/daytona.py +58 -0
  338. agentcompass/recipes/swebench_verified/docker.py +44 -0
  339. agentcompass/recipes/swebench_verified/host_process.py +28 -0
  340. agentcompass/recipes/swebench_verified/modal.py +56 -0
  341. agentcompass/recipes/taubench/__init__.py +5 -0
  342. agentcompass/recipes/taubench/docker.py +34 -0
  343. agentcompass/recipes/terminalbench2/daytona.py +31 -0
  344. agentcompass/recipes/terminalbench2/docker.py +28 -0
  345. agentcompass/recipes/terminalbench2/docker_ac.py +62 -0
  346. agentcompass/recipes/terminalbench2/modal.py +29 -0
  347. agentcompass/recipes/terminalbench2_1/daytona.py +31 -0
  348. agentcompass/recipes/terminalbench2_1/docker.py +28 -0
  349. agentcompass/recipes/terminalbench2_1/docker_ac.py +62 -0
  350. agentcompass/recipes/terminalbench2_1/modal.py +29 -0
  351. agentcompass/recipes/terminalbench2_verified/daytona.py +34 -0
  352. agentcompass/recipes/terminalbench2_verified/docker.py +33 -0
  353. agentcompass/recipes/terminalbench2_verified/docker_ac.py +67 -0
  354. agentcompass/recipes/terminalbench2_verified/modal.py +32 -0
  355. agentcompass/recipes/wildclawbench/__init__.py +3 -0
  356. agentcompass/recipes/wildclawbench/common.py +55 -0
  357. agentcompass/recipes/wildclawbench/docker.py +34 -0
  358. agentcompass/runtime/__init__.py +147 -0
  359. agentcompass/runtime/analysis.py +161 -0
  360. agentcompass/runtime/artifacts.py +812 -0
  361. agentcompass/runtime/attempts/__init__.py +29 -0
  362. agentcompass/runtime/attempts/repository.py +374 -0
  363. agentcompass/runtime/attempts/scheduler.py +192 -0
  364. agentcompass/runtime/base.py +1034 -0
  365. agentcompass/runtime/capsule.py +507 -0
  366. agentcompass/runtime/checkpoint.py +256 -0
  367. agentcompass/runtime/config/__init__.py +73 -0
  368. agentcompass/runtime/config/component.py +203 -0
  369. agentcompass/runtime/config/environment.py +72 -0
  370. agentcompass/runtime/config/loader.py +418 -0
  371. agentcompass/runtime/config/settings.py +139 -0
  372. agentcompass/runtime/context.py +37 -0
  373. agentcompass/runtime/dependencies.py +218 -0
  374. agentcompass/runtime/issues.py +123 -0
  375. agentcompass/runtime/limits.py +309 -0
  376. agentcompass/runtime/llm/__init__.py +66 -0
  377. agentcompass/runtime/llm/anthropic.py +52 -0
  378. agentcompass/runtime/llm/errors.py +22 -0
  379. agentcompass/runtime/llm/generate.py +238 -0
  380. agentcompass/runtime/llm/openai.py +402 -0
  381. agentcompass/runtime/llm/protocol.py +123 -0
  382. agentcompass/runtime/logging.py +488 -0
  383. agentcompass/runtime/metrics/__init__.py +103 -0
  384. agentcompass/runtime/metrics/benchmark_aggregation.py +423 -0
  385. agentcompass/runtime/metrics/contract.py +250 -0
  386. agentcompass/runtime/metrics/mode.py +12 -0
  387. agentcompass/runtime/metrics/reducer.py +377 -0
  388. agentcompass/runtime/metrics/reducers.py +238 -0
  389. agentcompass/runtime/metrics/report.py +455 -0
  390. agentcompass/runtime/metrics/report_aggregation.py +418 -0
  391. agentcompass/runtime/metrics/strategies.py +214 -0
  392. agentcompass/runtime/metrics/types.py +26 -0
  393. agentcompass/runtime/models/__init__.py +104 -0
  394. agentcompass/runtime/models/analysis.py +28 -0
  395. agentcompass/runtime/models/model.py +75 -0
  396. agentcompass/runtime/models/orchestration.py +243 -0
  397. agentcompass/runtime/models/plan.py +97 -0
  398. agentcompass/runtime/models/request.py +658 -0
  399. agentcompass/runtime/models/result.py +117 -0
  400. agentcompass/runtime/models/task.py +320 -0
  401. agentcompass/runtime/models/trajectory.py +84 -0
  402. agentcompass/runtime/network.py +462 -0
  403. agentcompass/runtime/orchestration.py +1150 -0
  404. agentcompass/runtime/planner.py +384 -0
  405. agentcompass/runtime/progress.py +1002 -0
  406. agentcompass/runtime/recipes.py +128 -0
  407. agentcompass/runtime/recovery.py +108 -0
  408. agentcompass/runtime/registry.py +106 -0
  409. agentcompass/runtime/resources.py +203 -0
  410. agentcompass/runtime/results/__init__.py +15 -0
  411. agentcompass/runtime/results/detail.py +474 -0
  412. agentcompass/runtime/results/layout.py +308 -0
  413. agentcompass/runtime/results/legacy.py +44 -0
  414. agentcompass/runtime/results/render.py +185 -0
  415. agentcompass/runtime/results/store.py +1706 -0
  416. agentcompass/runtime/results/summary.py +101 -0
  417. agentcompass/runtime/runner.py +2385 -0
  418. agentcompass/runtime/setup.py +71 -0
  419. agentcompass/runtime/tasks.py +137 -0
  420. agentcompass/runtime/timeouts.py +59 -0
  421. agentcompass/utils/__init__.py +5 -0
  422. agentcompass/utils/api_key.py +40 -0
  423. agentcompass/utils/call.py +90 -0
  424. agentcompass/utils/command.py +108 -0
  425. agentcompass/utils/env.py +89 -0
  426. agentcompass/utils/exceptions.py +25 -0
  427. agentcompass/utils/redaction.py +29 -0
  428. agentcompass/utils/workspace.py +39 -0
  429. agentcompass/viewer/__init__.py +0 -0
  430. agentcompass/viewer/reader.py +838 -0
  431. agentcompass/viewer/server.py +160 -0
  432. agentcompass/viewer/static/assets/index-BywoR7aU.js +170 -0
  433. agentcompass/viewer/static/assets/index-CqGkz9_L.css +1 -0
  434. agentcompass/viewer/static/index.html +17 -0
  435. agentcompass-1.0.0.dist-info/METADATA +275 -0
  436. agentcompass-1.0.0.dist-info/RECORD +440 -0
  437. agentcompass-1.0.0.dist-info/WHEEL +5 -0
  438. agentcompass-1.0.0.dist-info/entry_points.txt +2 -0
  439. agentcompass-1.0.0.dist-info/licenses/LICENSE +203 -0
  440. agentcompass-1.0.0.dist-info/top_level.txt +1 -0
@@ -0,0 +1,13 @@
1
+ """OpenEvolve harness package."""
2
+
3
+ from .harness import (
4
+ OpenEvolveConfig,
5
+ OpenEvolveHarness,
6
+ OpenEvolvePlan,
7
+ )
8
+
9
+ __all__ = [
10
+ "OpenEvolveConfig",
11
+ "OpenEvolveHarness",
12
+ "OpenEvolvePlan",
13
+ ]