@elizaos/sweagent-root 2.0.0-alpha

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 (323) hide show
  1. package/LICENSE +21 -0
  2. package/README.md +270 -0
  3. package/package.json +71 -0
  4. package/python/LICENSE +21 -0
  5. package/python/config/README.md +15 -0
  6. package/python/config/bash_only.yaml +222 -0
  7. package/python/config/benchmarks/250212_sweagent_heavy_sbl.yaml +188 -0
  8. package/python/config/benchmarks/250225_anthropic_filemap_simple_review.yaml +75 -0
  9. package/python/config/benchmarks/250522_anthropic_filemap_simple_review.yaml +92 -0
  10. package/python/config/benchmarks/250526_anthropic_filemap_simple_review_sbl.yaml +93 -0
  11. package/python/config/benchmarks/anthropic_filemap_multilingual.yaml +66 -0
  12. package/python/config/coding_challenge.yaml +104 -0
  13. package/python/config/default.yaml +69 -0
  14. package/python/config/default_backticks.yaml +69 -0
  15. package/python/config/default_mm_no_images.yaml +82 -0
  16. package/python/config/default_mm_with_images.yaml +83 -0
  17. package/python/config/demo/default.yaml +80 -0
  18. package/python/config/demo/no_instructions.yaml +69 -0
  19. package/python/config/demo/only_bash.yaml +60 -0
  20. package/python/config/exotic/default_shell.yaml +52 -0
  21. package/python/config/exotic/windowed_replace.yaml +125 -0
  22. package/python/config/exotic/windowed_replace_late_repro.yaml +127 -0
  23. package/python/config/human/human.yaml +24 -0
  24. package/python/config/human/human_demo.yaml +52 -0
  25. package/python/config/sweagent_0_7/07.yaml +101 -0
  26. package/python/config/sweagent_0_7/07_fcalling.yaml +100 -0
  27. package/python/config/sweagent_0_7/07_from_url.yaml +114 -0
  28. package/python/config/sweagent_0_7/07_thought_action.yaml +102 -0
  29. package/python/config/sweagent_0_7/07_thought_action_xml.yaml +96 -0
  30. package/python/mlc_config.json +44 -0
  31. package/python/pyproject.toml +262 -0
  32. package/python/sweagent/__init__.py +114 -0
  33. package/python/sweagent/__main__.py +4 -0
  34. package/python/sweagent/agent/__init__.py +0 -0
  35. package/python/sweagent/agent/action_sampler.py +317 -0
  36. package/python/sweagent/agent/agents.py +1294 -0
  37. package/python/sweagent/agent/extra/shell_agent.py +106 -0
  38. package/python/sweagent/agent/history_processors.py +399 -0
  39. package/python/sweagent/agent/hooks/__init__.py +0 -0
  40. package/python/sweagent/agent/hooks/abstract.py +139 -0
  41. package/python/sweagent/agent/hooks/status.py +34 -0
  42. package/python/sweagent/agent/models.py +896 -0
  43. package/python/sweagent/agent/problem_statement.py +312 -0
  44. package/python/sweagent/agent/reviewer.py +664 -0
  45. package/python/sweagent/environment/__init__.py +0 -0
  46. package/python/sweagent/environment/hooks/__init__.py +0 -0
  47. package/python/sweagent/environment/hooks/abstract.py +60 -0
  48. package/python/sweagent/environment/hooks/status.py +28 -0
  49. package/python/sweagent/environment/repo.py +219 -0
  50. package/python/sweagent/environment/swe_env.py +276 -0
  51. package/python/sweagent/exceptions.py +54 -0
  52. package/python/sweagent/inspector/README.md +6 -0
  53. package/python/sweagent/inspector/__init__.py +0 -0
  54. package/python/sweagent/inspector/favicon.ico +0 -0
  55. package/python/sweagent/inspector/fileViewer.js +354 -0
  56. package/python/sweagent/inspector/icons/computer.png +0 -0
  57. package/python/sweagent/inspector/icons/edit_icon.svg +11 -0
  58. package/python/sweagent/inspector/icons/swe-agent-logo-50.png +0 -0
  59. package/python/sweagent/inspector/icons/swellama_blue.png +0 -0
  60. package/python/sweagent/inspector/icons/swellama_brown.png +0 -0
  61. package/python/sweagent/inspector/icons/swellama_grey.png +0 -0
  62. package/python/sweagent/inspector/icons/swellama_tan.png +0 -0
  63. package/python/sweagent/inspector/index.html +25 -0
  64. package/python/sweagent/inspector/server.py +354 -0
  65. package/python/sweagent/inspector/static.py +169 -0
  66. package/python/sweagent/inspector/style.css +454 -0
  67. package/python/sweagent/run/__init__.py +0 -0
  68. package/python/sweagent/run/_progress.py +158 -0
  69. package/python/sweagent/run/batch_instances.py +419 -0
  70. package/python/sweagent/run/common.py +387 -0
  71. package/python/sweagent/run/compare_runs.py +123 -0
  72. package/python/sweagent/run/extract_pred.py +19 -0
  73. package/python/sweagent/run/hooks/__init__.py +0 -0
  74. package/python/sweagent/run/hooks/abstract.py +67 -0
  75. package/python/sweagent/run/hooks/apply_patch.py +106 -0
  76. package/python/sweagent/run/hooks/open_pr.py +244 -0
  77. package/python/sweagent/run/hooks/swe_bench_evaluate.py +113 -0
  78. package/python/sweagent/run/inspector_cli.py +493 -0
  79. package/python/sweagent/run/merge_predictions.py +64 -0
  80. package/python/sweagent/run/quick_stats.py +96 -0
  81. package/python/sweagent/run/remove_unfinished.py +63 -0
  82. package/python/sweagent/run/rich_test.py +91 -0
  83. package/python/sweagent/run/run.py +147 -0
  84. package/python/sweagent/run/run_batch.py +442 -0
  85. package/python/sweagent/run/run_replay.py +219 -0
  86. package/python/sweagent/run/run_shell.py +155 -0
  87. package/python/sweagent/run/run_single.py +225 -0
  88. package/python/sweagent/run/run_traj_to_demo.py +85 -0
  89. package/python/sweagent/tools/__init__.py +0 -0
  90. package/python/sweagent/tools/bundle.py +57 -0
  91. package/python/sweagent/tools/commands.py +220 -0
  92. package/python/sweagent/tools/parsing.py +619 -0
  93. package/python/sweagent/tools/tools.py +430 -0
  94. package/python/sweagent/tools/utils.py +108 -0
  95. package/python/sweagent/types.py +102 -0
  96. package/python/sweagent/utils/__init__.py +0 -0
  97. package/python/sweagent/utils/config.py +80 -0
  98. package/python/sweagent/utils/files.py +27 -0
  99. package/python/sweagent/utils/github.py +118 -0
  100. package/python/sweagent/utils/jinja_warnings.py +14 -0
  101. package/python/sweagent/utils/log.py +175 -0
  102. package/python/sweagent/utils/patch_formatter.py +152 -0
  103. package/python/sweagent/utils/serialization.py +45 -0
  104. package/python/tests/__init__.py +0 -0
  105. package/python/tests/conftest.py +191 -0
  106. package/python/tests/test_agent.py +258 -0
  107. package/python/tests/test_batch_instance.py +43 -0
  108. package/python/tests/test_commands/_interactive_dummy.py +35 -0
  109. package/python/tests/test_commands/interactive_dummy_wrapper.sh +29 -0
  110. package/python/tests/test_data/config_files/dummy_interactive.yaml +62 -0
  111. package/python/tests/test_data/data_sources/ctf/crypto/Katy/Dockerfile +20 -0
  112. package/python/tests/test_data/data_sources/ctf/crypto/Katy/README.md +13 -0
  113. package/python/tests/test_data/data_sources/ctf/crypto/Katy/challenge.json +12 -0
  114. package/python/tests/test_data/data_sources/ctf/crypto/Katy/customrandom.c +50 -0
  115. package/python/tests/test_data/data_sources/ctf/crypto/Katy/docker-compose.yml +14 -0
  116. package/python/tests/test_data/data_sources/ctf/crypto/Katy/release +0 -0
  117. package/python/tests/test_data/data_sources/ctf/crypto/Katy/server +0 -0
  118. package/python/tests/test_data/data_sources/ctf/crypto/Katy/solver.py +12 -0
  119. package/python/tests/test_data/data_sources/ctf/forensics/flash/README.md +16 -0
  120. package/python/tests/test_data/data_sources/ctf/forensics/flash/challenge.json +9 -0
  121. package/python/tests/test_data/data_sources/ctf/forensics/flash/flash_c8429a430278283c0e571baebca3d139.zip +0 -0
  122. package/python/tests/test_data/data_sources/ctf/misc/networking_1/README.md +15 -0
  123. package/python/tests/test_data/data_sources/ctf/misc/networking_1/challenge.json +10 -0
  124. package/python/tests/test_data/data_sources/ctf/misc/networking_1/networking.pcap +0 -0
  125. package/python/tests/test_data/data_sources/ctf/pwn/warmup/Dockerfile +28 -0
  126. package/python/tests/test_data/data_sources/ctf/pwn/warmup/README.md +14 -0
  127. package/python/tests/test_data/data_sources/ctf/pwn/warmup/challenge.json +14 -0
  128. package/python/tests/test_data/data_sources/ctf/pwn/warmup/docker-compose.yml +14 -0
  129. package/python/tests/test_data/data_sources/ctf/pwn/warmup/flag.txt +1 -0
  130. package/python/tests/test_data/data_sources/ctf/pwn/warmup/warmup +0 -0
  131. package/python/tests/test_data/data_sources/ctf/pwn/warmup/warmup.c +26 -0
  132. package/python/tests/test_data/data_sources/ctf/pwn/warmup/warmup.py +9 -0
  133. package/python/tests/test_data/data_sources/ctf/rev/rock/README.md +14 -0
  134. package/python/tests/test_data/data_sources/ctf/rev/rock/challenge.json +8 -0
  135. package/python/tests/test_data/data_sources/ctf/rev/rock/rock +0 -0
  136. package/python/tests/test_data/data_sources/ctf/rev/rock/rock.cpp +167 -0
  137. package/python/tests/test_data/data_sources/ctf/rev/rock/solution.cpp +24 -0
  138. package/python/tests/test_data/data_sources/ctf/rev/rock/test_solver/solution.py +6 -0
  139. package/python/tests/test_data/data_sources/ctf/rev/rock/test_solver/test.sh +10 -0
  140. package/python/tests/test_data/data_sources/ctf/web/i_got_id_demo/000-default.conf +18 -0
  141. package/python/tests/test_data/data_sources/ctf/web/i_got_id_demo/Dockerfile +20 -0
  142. package/python/tests/test_data/data_sources/ctf/web/i_got_id_demo/cgi/file.pl +38 -0
  143. package/python/tests/test_data/data_sources/ctf/web/i_got_id_demo/cgi/forms.pl +40 -0
  144. package/python/tests/test_data/data_sources/ctf/web/i_got_id_demo/cgi/hello.pl +11 -0
  145. package/python/tests/test_data/data_sources/ctf/web/i_got_id_demo/challenge.json +12 -0
  146. package/python/tests/test_data/data_sources/ctf/web/i_got_id_demo/docker-compose.yml +14 -0
  147. package/python/tests/test_data/data_sources/ctf/web/i_got_id_demo/flag +1 -0
  148. package/python/tests/test_data/data_sources/ctf/web/i_got_id_demo/index.html +11 -0
  149. package/python/tests/test_data/data_sources/ctf/web/i_got_id_demo/solution.txt +1 -0
  150. package/python/tests/test_data/data_sources/debug_20240322.json +1 -0
  151. package/python/tests/test_data/data_sources/expert_instances.yaml +16 -0
  152. package/python/tests/test_data/data_sources/human_eval.json +1 -0
  153. package/python/tests/test_data/data_sources/simple_instances.yaml +3 -0
  154. package/python/tests/test_data/data_sources/simple_instances_long.yaml +30 -0
  155. package/python/tests/test_data/data_sources/swe-bench-dev-easy.json +1 -0
  156. package/python/tests/test_data/data_sources/swe-bench-dev-easy_first_only.json +1 -0
  157. package/python/tests/test_data/data_sources/swe-bench-lite-test.json +1 -0
  158. package/python/tests/test_data/trajectories/gpt4__swe-agent-test-repo__default_from_url__t-0.00__p-0.95__c-3.00__install-1/6e44b9__sweagenttestrepo-1c2844.traj +342 -0
  159. package/python/tests/test_data/trajectories/gpt4__swe-agent-test-repo__default_from_url__t-0.00__p-0.95__c-3.00__install-1/solution_missing_colon.py +15 -0
  160. package/python/tests/test_data/trajectories/gpt4__swe-agent__test-repo__default_from_url__t-0.00__p-0.95__c-3.00__install-1/args.yaml +518 -0
  161. package/python/tests/test_data/trajectories/gpt4__swe-agent__test-repo__default_from_url__t-0.00__p-0.95__c-3.00__install-1/swe-agent__test-repo-i1.traj +124 -0
  162. package/python/tests/test_data/trajectories/gpt4__swe-bench-dev-easy_first_only__default__t-0.00__p-0.95__c-3.00__install-1/all_preds.jsonl +1 -0
  163. package/python/tests/test_data/trajectories/gpt4__swe-bench-dev-easy_first_only__default__t-0.00__p-0.95__c-3.00__install-1/args.yaml +520 -0
  164. package/python/tests/test_data/trajectories/gpt4__swe-bench-dev-easy_first_only__default__t-0.00__p-0.95__c-3.00__install-1/patches/pydicom__pydicom-1458.patch +18 -0
  165. package/python/tests/test_data/trajectories/gpt4__swe-bench-dev-easy_first_only__default__t-0.00__p-0.95__c-3.00__install-1/pydicom__pydicom-1458.traj +257 -0
  166. package/python/tests/test_env.py +66 -0
  167. package/python/tests/test_env_utils.py +129 -0
  168. package/python/tests/test_history_processors.py +40 -0
  169. package/python/tests/test_models.py +23 -0
  170. package/python/tests/test_openai_live.py +164 -0
  171. package/python/tests/test_packaging.py +7 -0
  172. package/python/tests/test_parsing.py +131 -0
  173. package/python/tests/test_problem_statement_multimodal.py +111 -0
  174. package/python/tests/test_quick_stats.py +42 -0
  175. package/python/tests/test_run.py +37 -0
  176. package/python/tests/test_run_batch.py +110 -0
  177. package/python/tests/test_run_hooks.py +114 -0
  178. package/python/tests/test_run_replay.py +33 -0
  179. package/python/tests/test_run_single.py +125 -0
  180. package/python/tests/test_tools_command_parsing.py +193 -0
  181. package/python/tests/test_utils.py +15 -0
  182. package/python/tests/tools/__init__.py +0 -0
  183. package/python/tests/tools/conftest.py +12 -0
  184. package/python/tests/tools/test_default_utils.py +153 -0
  185. package/python/tests/tools/test_edit_replace.py +0 -0
  186. package/python/tests/tools/test_split_string.py +82 -0
  187. package/python/tests/utils.py +29 -0
  188. package/python/tools/diff_state/bin/_state_diff_state +52 -0
  189. package/python/tools/diff_state/config.yaml +2 -0
  190. package/python/tools/edit_anthropic/bin/_state_anthropic +21 -0
  191. package/python/tools/edit_anthropic/bin/str_replace_editor +710 -0
  192. package/python/tools/edit_anthropic/config.yaml +56 -0
  193. package/python/tools/edit_anthropic/install.sh +3 -0
  194. package/python/tools/filemap/bin/filemap +45 -0
  195. package/python/tools/filemap/config.yaml +9 -0
  196. package/python/tools/filemap/install.sh +2 -0
  197. package/python/tools/forfeit/bin/exit_forfeit +5 -0
  198. package/python/tools/forfeit/config.yaml +5 -0
  199. package/python/tools/image_tools/bin/view_image +36 -0
  200. package/python/tools/image_tools/config.yaml +9 -0
  201. package/python/tools/multilingual_setup/bin/do_nothing +2 -0
  202. package/python/tools/multilingual_setup/config.yaml +1 -0
  203. package/python/tools/multilingual_setup/install.sh +45 -0
  204. package/python/tools/registry/bin/_read_env +10 -0
  205. package/python/tools/registry/bin/_write_env +10 -0
  206. package/python/tools/registry/config.yaml +1 -0
  207. package/python/tools/registry/install.sh +6 -0
  208. package/python/tools/registry/lib/__init__.py +0 -0
  209. package/python/tools/registry/lib/registry.py +56 -0
  210. package/python/tools/review_on_submit_m/README.md +6 -0
  211. package/python/tools/review_on_submit_m/bin/submit +54 -0
  212. package/python/tools/review_on_submit_m/config.yaml +6 -0
  213. package/python/tools/review_on_submit_m/install.sh +0 -0
  214. package/python/tools/search/bin/find_file +31 -0
  215. package/python/tools/search/bin/search_dir +39 -0
  216. package/python/tools/search/bin/search_file +55 -0
  217. package/python/tools/search/config.yaml +37 -0
  218. package/python/tools/search/install.sh +3 -0
  219. package/python/tools/submit/bin/submit +17 -0
  220. package/python/tools/submit/config.yaml +5 -0
  221. package/python/tools/web_browser/bin/click_mouse +41 -0
  222. package/python/tools/web_browser/bin/close_site +28 -0
  223. package/python/tools/web_browser/bin/double_click_mouse +37 -0
  224. package/python/tools/web_browser/bin/drag_mouse +46 -0
  225. package/python/tools/web_browser/bin/execute_script_on_page +39 -0
  226. package/python/tools/web_browser/bin/get_console_output +48 -0
  227. package/python/tools/web_browser/bin/move_mouse +35 -0
  228. package/python/tools/web_browser/bin/navigate_back +33 -0
  229. package/python/tools/web_browser/bin/navigate_forward +33 -0
  230. package/python/tools/web_browser/bin/open_site +36 -0
  231. package/python/tools/web_browser/bin/press_keys_on_page +51 -0
  232. package/python/tools/web_browser/bin/reload_page +33 -0
  233. package/python/tools/web_browser/bin/run_web_browser_server +394 -0
  234. package/python/tools/web_browser/bin/screenshot_site +38 -0
  235. package/python/tools/web_browser/bin/scroll_on_page +40 -0
  236. package/python/tools/web_browser/bin/set_browser_window_size +40 -0
  237. package/python/tools/web_browser/bin/type_text +34 -0
  238. package/python/tools/web_browser/bin/wait_time +39 -0
  239. package/python/tools/web_browser/config.yaml +155 -0
  240. package/python/tools/web_browser/install.sh +22 -0
  241. package/python/tools/web_browser/lib/browser_manager.py +404 -0
  242. package/python/tools/web_browser/lib/web_browser_config.py +33 -0
  243. package/python/tools/web_browser/lib/web_browser_utils.py +126 -0
  244. package/python/tools/web_browser/test_console.html +1 -0
  245. package/python/tools/windowed/bin/_state +25 -0
  246. package/python/tools/windowed/bin/create +29 -0
  247. package/python/tools/windowed/bin/goto +37 -0
  248. package/python/tools/windowed/bin/open +49 -0
  249. package/python/tools/windowed/bin/scroll_down +12 -0
  250. package/python/tools/windowed/bin/scroll_up +13 -0
  251. package/python/tools/windowed/config.yaml +38 -0
  252. package/python/tools/windowed/install.sh +15 -0
  253. package/python/tools/windowed/lib/__init__.py +0 -0
  254. package/python/tools/windowed/lib/flake8_utils.py +147 -0
  255. package/python/tools/windowed/lib/windowed_file.py +312 -0
  256. package/python/tools/windowed_edit_linting/bin/edit +128 -0
  257. package/python/tools/windowed_edit_linting/config.yaml +31 -0
  258. package/python/tools/windowed_edit_linting/install.sh +5 -0
  259. package/python/tools/windowed_edit_replace/bin/edit +172 -0
  260. package/python/tools/windowed_edit_replace/bin/insert +77 -0
  261. package/python/tools/windowed_edit_replace/config.yaml +60 -0
  262. package/python/tools/windowed_edit_replace/install.sh +5 -0
  263. package/python/tools/windowed_edit_rewrite/bin/edit +78 -0
  264. package/python/tools/windowed_edit_rewrite/config.yaml +11 -0
  265. package/python/tools/windowed_edit_rewrite/install.sh +5 -0
  266. package/python/trajectories/demonstrations/ctf/crypto/BabyEncryption.traj +318 -0
  267. package/python/trajectories/demonstrations/ctf/crypto/BabyTimeCapsule.traj +197 -0
  268. package/python/trajectories/demonstrations/ctf/crypto/eps.traj +289 -0
  269. package/python/trajectories/demonstrations/ctf/crypto/katy.traj +368 -0
  270. package/python/trajectories/demonstrations/ctf/forensics/flash.traj +102 -0
  271. package/python/trajectories/demonstrations/ctf/misc/networking_1.traj +102 -0
  272. package/python/trajectories/demonstrations/ctf/pwn/warmup.traj +159 -0
  273. package/python/trajectories/demonstrations/ctf/rev/rock.traj +251 -0
  274. package/python/trajectories/demonstrations/ctf/web/i_got_id_demo.traj +422 -0
  275. package/python/trajectories/demonstrations/function_calling_simple.traj +151 -0
  276. package/python/trajectories/demonstrations/human_thought__swe-bench-HumanEvalFix-python__lcb__t-0.00__p-0.95__c-4.00__install-0/humanevalfix-python-0.traj +129 -0
  277. package/python/trajectories/demonstrations/replay__marshmallow-code__marshmallow-1867__default__t-0.20__p-0.95__c-2.00__install-1___install_from_source/marshmallow-code__marshmallow-1867.traj +318 -0
  278. package/python/trajectories/demonstrations/replay__marshmallow-code__marshmallow-1867__default_sys-env_cursors_window100__t-0.20__p-0.95__c-2.00__install-1/marshmallow-code__marshmallow-1867.traj +251 -0
  279. package/python/trajectories/demonstrations/replay__marshmallow-code__marshmallow-1867__default_sys-env_window100__t-0.20__p-0.95__c-2.00__install-1/marshmallow-code__marshmallow-1867.traj +399 -0
  280. package/python/trajectories/demonstrations/replay__marshmallow-code__marshmallow-1867__function_calling__install-1/marshmallow-code__marshmallow-1867.traj +594 -0
  281. package/python/trajectories/demonstrations/replay__marshmallow-code__marshmallow-1867__function_calling_replace__install-1/marshmallow-code__marshmallow-1867.traj +592 -0
  282. package/python/trajectories/demonstrations/replay__marshmallow-code__marshmallow-1867__function_calling_replace_from_source/marshmallow-code__marshmallow-1867.traj +3316 -0
  283. package/python/trajectories/demonstrations/replay__marshmallow-code__marshmallow-1867__xml_sys-env_cursors_window100__t-0.20__p-0.95__c-2.00__install-1/marshmallow-code__marshmallow-1867.traj +251 -0
  284. package/python/trajectories/demonstrations/replay__marshmallow-code__marshmallow-1867__xml_sys-env_window100__t-0.20__p-0.95__c-2.00__install-1/marshmallow-code__marshmallow-1867.traj +399 -0
  285. package/python/trajectories/demonstrations/str_replace_anthropic_demo.yaml +432 -0
  286. package/rust/Cargo.toml +100 -0
  287. package/rust/README.md +49 -0
  288. package/rust/src/agent/action_sampler.rs +130 -0
  289. package/rust/src/agent/agents.rs +1029 -0
  290. package/rust/src/agent/history_processors.rs +277 -0
  291. package/rust/src/agent/hooks/mod.rs +208 -0
  292. package/rust/src/agent/mod.rs +24 -0
  293. package/rust/src/agent/models.rs +837 -0
  294. package/rust/src/agent/problem_statement.rs +355 -0
  295. package/rust/src/agent/reviewer.rs +505 -0
  296. package/rust/src/bin/sweagent.rs +784 -0
  297. package/rust/src/environment/deployment.rs +631 -0
  298. package/rust/src/environment/hooks/mod.rs +114 -0
  299. package/rust/src/environment/mod.rs +16 -0
  300. package/rust/src/environment/repo.rs +265 -0
  301. package/rust/src/environment/runtime.rs +237 -0
  302. package/rust/src/environment/swe_env.rs +248 -0
  303. package/rust/src/exceptions.rs +228 -0
  304. package/rust/src/lib.rs +68 -0
  305. package/rust/src/monitoring.rs +482 -0
  306. package/rust/src/run/hooks/mod.rs +134 -0
  307. package/rust/src/run/mod.rs +12 -0
  308. package/rust/src/run/run_batch.rs +563 -0
  309. package/rust/src/run/run_single.rs +196 -0
  310. package/rust/src/tools/bundle.rs +224 -0
  311. package/rust/src/tools/commands.rs +173 -0
  312. package/rust/src/tools/mod.rs +295 -0
  313. package/rust/src/tools/parsing.rs +354 -0
  314. package/rust/src/tools/registry.rs +143 -0
  315. package/rust/src/types.rs +554 -0
  316. package/rust/src/utils/config.rs +105 -0
  317. package/rust/src/utils/files.rs +137 -0
  318. package/rust/src/utils/github.rs +171 -0
  319. package/rust/src/utils/log.rs +65 -0
  320. package/rust/src/utils/mod.rs +17 -0
  321. package/rust/src/utils/serialization.rs +181 -0
  322. package/rust/src/utils/template.rs +173 -0
  323. package/typescript/README.md +335 -0
@@ -0,0 +1,454 @@
1
+ body {
2
+ font-family: Arial, sans-serif;
3
+ margin: 0;
4
+ padding: 20px;
5
+ background-color: #1e1e1e;
6
+ color: #d4d4d4;
7
+ }
8
+ h1,
9
+ h2 {
10
+ color: #d4d4d4;
11
+ }
12
+ #fileList {
13
+ list-style-type: none;
14
+ padding: 10px;
15
+ max-height: 400px;
16
+ overflow-y: auto;
17
+ margin: 0;
18
+ background-color: #252526;
19
+ border: 3px solid #1697e2;
20
+ border-radius: 10px;
21
+ }
22
+ #fileList li {
23
+ cursor: pointer;
24
+ padding: 10px;
25
+ background-color: #2d2d2d;
26
+ margin-bottom: 5px;
27
+ border: 2px solid #454545;
28
+ border-radius: 5px;
29
+ transition: background-color 0.3s;
30
+ color: #d4d4d4;
31
+ }
32
+ #fileList li:hover {
33
+ background-color: #3e3e3e;
34
+ }
35
+ #fileList li.selected {
36
+ border-color: #fabb00;
37
+ }
38
+ #fileContent {
39
+ background-color: #1e1e1e;
40
+ border: 1px solid #454545;
41
+ padding: 10px;
42
+ margin-top: 20px;
43
+ white-space: pre-wrap;
44
+ color: #d4d4d4;
45
+ }
46
+ .button-container {
47
+ display: flex;
48
+ justify-content: center;
49
+ align-items: center;
50
+ }
51
+ #refreshButton {
52
+ padding: 4px 10px;
53
+ min-width: 80px;
54
+ border: none;
55
+ font: inherit;
56
+ color: #373030;
57
+ border-radius: 10px;
58
+ outline: none;
59
+ text-decoration: none;
60
+ cursor: default;
61
+ font-weight: 400;
62
+ background: #fff;
63
+ box-shadow:
64
+ 0px 0px 1px #0000004d,
65
+ 0px 1px 1px #00000066;
66
+ }
67
+ #refreshButton:hover {
68
+ /* hover MUST come before active */
69
+ background: linear-gradient(#0000004d, #00000066);
70
+ color: #fff;
71
+ position: relative;
72
+ }
73
+ #refreshButton:active {
74
+ background: linear-gradient(#4faefc, #006bff);
75
+ color: #fff;
76
+ position: relative;
77
+ }
78
+ .history-item {
79
+ border: 3px solid black;
80
+ border-radius: 5px;
81
+ padding: 0px;
82
+ /* padding-bottom: 5%; */
83
+ margin-bottom: 15px;
84
+ overflow-x: hidden;
85
+ white-space: normal;
86
+ /* overflow-x: auto; Enables horizontal scrolling */
87
+ /* white-space: nowrap; Keeps content in a single line */
88
+ max-height: 450px; /* Adjust as needed for 25 lines */
89
+ overflow: hidden;
90
+ position: relative;
91
+ }
92
+ .shadow {
93
+ height: 30px; /* Height of the shadow */
94
+ background: linear-gradient(to bottom, transparent, rgba(0, 0, 0, 0.4));
95
+ position: absolute;
96
+ bottom: 0;
97
+ left: 0;
98
+ right: 0;
99
+ pointer-events: none; /* Ensures the shadow doesn't interfere with interaction */
100
+ display: none; /* Initially hidden */
101
+ }
102
+ .has-shadow .shadow {
103
+ display: block;
104
+ }
105
+ .content-container {
106
+ max-height: 400px; /* Adjust as needed */
107
+ overflow-y: auto;
108
+ position: relative;
109
+ padding: 10px;
110
+ }
111
+ .content-container pre {
112
+ white-space: pre-wrap; /* Wrap lines and preserve whitespace */
113
+ overflow-wrap: break-word; /* Handle long words */
114
+ }
115
+ .container {
116
+ max-width: 1000px;
117
+ margin: 0 auto; /* Centers the container */
118
+ padding: 20px; /* Optional: for some inner spacing */
119
+ }
120
+ .history-item.user {
121
+ border-color: #1697e2;
122
+ }
123
+ .history-item.tool {
124
+ border-color: #1483c3;
125
+ }
126
+ .history-item.system {
127
+ border-color: #004b80;
128
+ }
129
+ .history-item.subroutine {
130
+ border-color: #006b00;
131
+ }
132
+ .history-item.gold-patch {
133
+ border-color: #fabb00;
134
+ }
135
+ .history-item.assistant {
136
+ border-color: rgb(0, 0, 0);
137
+ }
138
+ .history-item.test-patch {
139
+ border-color: #7373d9;
140
+ }
141
+ .history-item.evaluation-report {
142
+ border-color: #35614b;
143
+ }
144
+
145
+ /* filepath-tree stuff */
146
+ .filepath {
147
+ display: flex;
148
+ flex-direction: column; /* Changes layout to one part per line */
149
+ align-items: flex-start; /* Aligns parts to the start of the container */
150
+ font-size: 16px;
151
+ gap: 10px;
152
+ padding: 5px;
153
+ background-color: #2d2d2d;
154
+ }
155
+ .part {
156
+ border: 1px solid #454545;
157
+ white-space: nowrap; /* Prevents wrapping within parts */
158
+ padding: 5px;
159
+ background-color: #3e3e3e;
160
+ border-radius: 5px;
161
+ color: #d4d4d4;
162
+ }
163
+
164
+ @keyframes fadeIn {
165
+ from {
166
+ opacity: 0;
167
+ }
168
+ to {
169
+ opacity: 1;
170
+ }
171
+ }
172
+
173
+ .fade-in {
174
+ animation: fadeIn 1s ease-out;
175
+ }
176
+
177
+ .trajectory-container {
178
+ position: relative;
179
+ width: 100%;
180
+ }
181
+
182
+ .trajectory-item {
183
+ display: flex;
184
+ flex-direction: column;
185
+ margin-bottom: 0px;
186
+ border: 3px solid #1697e2;
187
+ border-radius: 5px;
188
+ position: relative;
189
+ background: #2d2d2d;
190
+ min-height: fit-content; /* Added to ensure proper expansion */
191
+ height: auto; /* Added to ensure proper expansion */
192
+ overflow: visible; /* Changed from hidden/auto to visible */
193
+ }
194
+
195
+ .trajectory-main {
196
+ flex: 1;
197
+ min-width: 0;
198
+ display: flex;
199
+ flex-direction: column;
200
+ gap: 0;
201
+ }
202
+
203
+ .response-section,
204
+ .observation-section,
205
+ .messages-section {
206
+ padding: 0 4px;
207
+ position: relative;
208
+ min-height: 30px;
209
+ height: 400px;
210
+ max-height: min-content;
211
+ display: flex;
212
+ flex-direction: column;
213
+ resize: vertical;
214
+ overflow: hidden;
215
+ width: calc(100% - 16px);
216
+ }
217
+
218
+ .response-section {
219
+ background-color: #252526;
220
+ border-bottom: 1px solid #454545;
221
+ color: #d4d4d4;
222
+ }
223
+
224
+ .observation-section {
225
+ background-color: #2d2d2d;
226
+ color: #d4d4d4;
227
+ }
228
+
229
+ .observation-images-section {
230
+ padding: 4px;
231
+ position: relative;
232
+ min-height: 30px;
233
+ height: 200px;
234
+ max-height: 200px;
235
+ background: #2d2d30;
236
+ border-top: 1px solid #454545;
237
+ display: flex;
238
+ flex-direction: column;
239
+ resize: vertical;
240
+ overflow: hidden;
241
+ width: calc(100% - 16px);
242
+ color: #d4d4d4;
243
+ }
244
+
245
+ /* Add section headers */
246
+ .response-section::before,
247
+ .observation-section::before,
248
+ .observation-images-section::before,
249
+ .messages-section::before {
250
+ content: attr(data-title);
251
+ font-weight: bold;
252
+ padding: 8px 12px; /* Keep this comfortable padding */
253
+ background: rgba(255, 255, 255, 0.05);
254
+ margin: 0 0 8px 0; /* Add some bottom margin to separate from content */
255
+ border-bottom: 1px solid #454545;
256
+ position: sticky;
257
+ top: 0;
258
+ width: 100%;
259
+ box-sizing: border-box;
260
+ color: #d4d4d4;
261
+ }
262
+
263
+ /* Scrollable content containers */
264
+ .content-wrapper {
265
+ overflow-y: auto;
266
+ flex: 1;
267
+ padding: 0;
268
+ margin: 0;
269
+ display: flex; /* Add flex display */
270
+ flex-direction: column; /* Stack children vertically */
271
+ }
272
+
273
+ .content-wrapper pre {
274
+ margin: 0;
275
+ padding: 0;
276
+ flex: 1; /* Allow pre to fill the space */
277
+ display: flex; /* Make pre a flex container */
278
+ flex-direction: column; /* Stack children vertically */
279
+ }
280
+
281
+ .content-wrapper pre code {
282
+ margin: 0;
283
+ padding: 0;
284
+ flex: 1; /* Allow code to fill the space */
285
+ }
286
+
287
+ .messages-section {
288
+ padding: 4px;
289
+ position: relative;
290
+ min-height: 30px;
291
+ height: 30px;
292
+ max-height: min-content; /* Only expand to fit content */
293
+ background: #252526;
294
+ border-top: 1px solid #454545;
295
+ display: flex;
296
+ flex-direction: column;
297
+ resize: vertical;
298
+ overflow: hidden;
299
+ width: calc(100% - 16px);
300
+ color: #d4d4d4;
301
+ }
302
+
303
+ .messages-section::before {
304
+ content: attr(data-title);
305
+ font-weight: bold;
306
+ padding: 8px 12px; /* Increased padding around title text */
307
+ background: rgba(255, 255, 255, 0.05);
308
+ margin: -8px -8px 5px -8px; /* Reduced bottom margin */
309
+ border-bottom: 1px solid #454545;
310
+ position: sticky;
311
+ top: -8px;
312
+ width: calc(100% + 16px);
313
+ box-sizing: border-box;
314
+ color: #d4d4d4;
315
+ }
316
+
317
+ .messages-toggle {
318
+ display: none;
319
+ }
320
+
321
+ .execution-time {
322
+ font-size: 0.8em;
323
+ color: #666;
324
+ text-align: right;
325
+ padding: 5px;
326
+ border-top: 1px solid #ddd;
327
+ }
328
+
329
+ /* Add a visual indicator for resizable areas */
330
+ .response-section:hover,
331
+ .observation-section:hover,
332
+ .observation-images-section:hover,
333
+ .messages-section.expanded:hover {
334
+ outline: 1px dashed #999;
335
+ }
336
+
337
+ .demo-message {
338
+ color: #2ecc71;
339
+ font-weight: bold;
340
+ }
341
+
342
+ /* Syntax highlighting overrides for dark theme */
343
+ .hljs {
344
+ background: #1e1e1e !important;
345
+ color: #d4d4d4 !important;
346
+ }
347
+
348
+ .hljs-keyword,
349
+ .hljs-selector-tag,
350
+ .hljs-built_in,
351
+ .hljs-name,
352
+ .hljs-tag {
353
+ color: #569cd6 !important; /* Blue */
354
+ }
355
+
356
+ .hljs-string,
357
+ .hljs-title,
358
+ .hljs-section,
359
+ .hljs-attribute,
360
+ .hljs-literal,
361
+ .hljs-template-tag,
362
+ .hljs-template-variable,
363
+ .hljs-type {
364
+ color: #ce9178 !important; /* Orange/Pink */
365
+ }
366
+
367
+ .hljs-comment,
368
+ .hljs-quote {
369
+ color: #6a9955 !important; /* Green */
370
+ }
371
+
372
+ .hljs-number,
373
+ .hljs-regexp,
374
+ .hljs-symbol,
375
+ .hljs-variable,
376
+ .hljs-template-variable,
377
+ .hljs-link,
378
+ .hljs-selector-attr,
379
+ .hljs-selector-pseudo {
380
+ color: #b5cea8 !important; /* Light green */
381
+ }
382
+
383
+ label {
384
+ color: #d4d4d4; /* Matches the theme's text color */
385
+ display: flex;
386
+ align-items: center;
387
+ gap: 5px;
388
+ }
389
+
390
+ input[type="checkbox"] {
391
+ margin: 0;
392
+ cursor: pointer;
393
+ }
394
+
395
+ /* observation images styles */
396
+ .observation-images {
397
+ margin-top: 10px;
398
+ padding: 10px 0;
399
+ }
400
+
401
+ .observation-image-container {
402
+ margin-bottom: 15px;
403
+ text-align: center;
404
+ }
405
+
406
+ .observation-image {
407
+ max-width: 100%;
408
+ max-height: 400px;
409
+ border: 1px solid #454545;
410
+ border-radius: 5px;
411
+ background-color: #1e1e1e;
412
+ box-shadow: 0 2px 8px rgba(0, 0, 0, 0.3);
413
+ cursor: pointer;
414
+ transition: transform 0.2s ease;
415
+ }
416
+
417
+ .observation-image:hover {
418
+ transform: scale(1.02);
419
+ border-color: #1697e2;
420
+ }
421
+
422
+ .image-caption {
423
+ margin-top: 5px;
424
+ font-size: 0.9em;
425
+ color: #b3b3b3;
426
+ font-style: italic;
427
+ }
428
+
429
+ .observation-image.expanded {
430
+ position: fixed;
431
+ top: 50%;
432
+ left: 50%;
433
+ transform: translate(-50%, -50%) scale(1);
434
+ max-width: 90vw;
435
+ max-height: 90vh;
436
+ z-index: 1000;
437
+ border: 2px solid #1697e2;
438
+ box-shadow: 0 0 20px rgba(0, 0, 0, 0.8);
439
+ }
440
+
441
+ .image-overlay {
442
+ position: fixed;
443
+ top: 0;
444
+ left: 0;
445
+ width: 100%;
446
+ height: 100%;
447
+ background-color: rgba(0, 0, 0, 0.8);
448
+ z-index: 999;
449
+ display: none;
450
+ }
451
+
452
+ .image-overlay.active {
453
+ display: block;
454
+ }
File without changes
@@ -0,0 +1,158 @@
1
+ """This module contains an auxiliary class for rendering progress of the batch run."""
2
+
3
+ import collections
4
+ from pathlib import Path
5
+ from threading import Lock
6
+
7
+ import yaml
8
+ from rich.console import Group
9
+ from rich.progress import (
10
+ BarColumn,
11
+ MofNCompleteColumn,
12
+ Progress,
13
+ SpinnerColumn,
14
+ TaskID,
15
+ TaskProgressColumn,
16
+ TextColumn,
17
+ TimeElapsedColumn,
18
+ TimeRemainingColumn,
19
+ )
20
+ from rich.table import Table
21
+
22
+ from sweagent.agent.models import GLOBAL_STATS
23
+
24
+
25
+ def _shorten_str(s: str, max_len: int, shorten_left=False) -> str:
26
+ if not shorten_left:
27
+ s = s[: max_len - 3] + "..." if len(s) > max_len else s
28
+ else:
29
+ s = "..." + s[-max_len + 3 :] if len(s) > max_len else s
30
+ return f"{s:<{max_len}}"
31
+
32
+
33
+ class RunBatchProgressManager:
34
+ def __init__(
35
+ self,
36
+ num_instances: int,
37
+ yaml_report_path: Path | None = None,
38
+ ):
39
+ """This class manages a progress bar/UI for run-batch
40
+
41
+ Args:
42
+ num_instances: Number of task instances
43
+ yaml_report_path: Path to save a yaml report of the instances and their exit statuses
44
+ """
45
+
46
+ self._spinner_tasks: dict[str, TaskID] = {}
47
+ """We need to map instance ID to the task ID that is used by the rich progress bar."""
48
+
49
+ self._lock = Lock()
50
+
51
+ self._instances_by_exit_status = collections.defaultdict(list)
52
+ self._main_progress_bar = Progress(
53
+ SpinnerColumn(spinner_name="dots2"),
54
+ TextColumn("[progress.description]{task.description} (${task.fields[total_cost]})"),
55
+ BarColumn(),
56
+ MofNCompleteColumn(),
57
+ TaskProgressColumn(),
58
+ TimeElapsedColumn(),
59
+ TextColumn("[cyan]eta:[/cyan]"),
60
+ TimeRemainingColumn(),
61
+ # Wait 5 min before estimating speed
62
+ speed_estimate_period=60 * 5,
63
+ )
64
+ self._task_progress_bar = Progress(
65
+ SpinnerColumn(spinner_name="dots2"),
66
+ TextColumn("{task.fields[instance_id]}"),
67
+ TextColumn("{task.fields[status]}"),
68
+ TimeElapsedColumn(),
69
+ )
70
+ """Task progress bar for individual instances. There's only one progress bar
71
+ with one task for each instance.
72
+ """
73
+
74
+ self._main_task_id = self._main_progress_bar.add_task(
75
+ "[cyan]Overall Progress", total=num_instances, total_cost=0
76
+ )
77
+
78
+ self.render_group = Group(Table(), self._task_progress_bar, self._main_progress_bar)
79
+ self._yaml_report_path = yaml_report_path
80
+
81
+ @property
82
+ def n_completed(self) -> int:
83
+ return sum(len(instances) for instances in self._instances_by_exit_status.values())
84
+
85
+ def update_exit_status_table(self):
86
+ # We cannot update the existing table, so we need to create a new one and
87
+ # assign it back to the render group.
88
+ t = Table()
89
+ t.add_column("Exit Status")
90
+ t.add_column("Count", justify="right", style="bold cyan")
91
+ t.add_column("Most recent instances")
92
+ t.show_header = False
93
+ with self._lock:
94
+ t.show_header = True
95
+ # Sort by number of instances in descending order
96
+ sorted_items = sorted(self._instances_by_exit_status.items(), key=lambda x: len(x[1]), reverse=True)
97
+ for status, instances in sorted_items:
98
+ instances_str = _shorten_str(", ".join(reversed(instances)), 55)
99
+ t.add_row(status, str(len(instances)), instances_str)
100
+ assert self.render_group is not None
101
+ self.render_group.renderables[0] = t
102
+
103
+ def _update_total_costs(self) -> None:
104
+ with self._lock:
105
+ self._main_progress_bar.update(self._main_task_id, total_cost=f"{GLOBAL_STATS.total_cost:.2f}")
106
+
107
+ def update_instance_status(self, instance_id: str, message: str):
108
+ assert self._task_progress_bar is not None
109
+ assert self._main_progress_bar is not None
110
+ with self._lock:
111
+ self._task_progress_bar.update(
112
+ self._spinner_tasks[instance_id],
113
+ status=_shorten_str(message, 30),
114
+ instance_id=_shorten_str(instance_id, 25, shorten_left=True),
115
+ )
116
+ self._update_total_costs()
117
+
118
+ def on_instance_start(self, instance_id: str):
119
+ with self._lock:
120
+ self._spinner_tasks[instance_id] = self._task_progress_bar.add_task(
121
+ description=f"Task {instance_id}",
122
+ status="Task initialized",
123
+ total=None,
124
+ instance_id=instance_id,
125
+ )
126
+
127
+ def on_instance_end(self, instance_id: str, exit_status: str | None) -> None:
128
+ self._instances_by_exit_status[exit_status].append(instance_id)
129
+ with self._lock:
130
+ self._task_progress_bar.remove_task(self._spinner_tasks[instance_id])
131
+ self._main_progress_bar.update(TaskID(0), advance=1)
132
+ self.update_exit_status_table()
133
+ self._update_total_costs()
134
+ if self._yaml_report_path is not None:
135
+ self._save_overview_data_yaml(self._yaml_report_path)
136
+
137
+ def on_uncaught_exception(self, instance_id: str, exception: Exception) -> None:
138
+ self.on_instance_end(instance_id, f"Uncaught {type(exception).__name__}")
139
+
140
+ def print_report(self) -> None:
141
+ """Print complete list of instances and their exit statuses."""
142
+ for status, instances in self._instances_by_exit_status.items():
143
+ print(f"{status}: {len(instances)}")
144
+ for instance in instances:
145
+ print(f" {instance}")
146
+
147
+ def _get_overview_data(self) -> dict:
148
+ """Get data like exit statuses, total costs, etc."""
149
+ return {
150
+ # convert defaultdict to dict because of serialization
151
+ "instances_by_exit_status": dict(self._instances_by_exit_status),
152
+ "total_cost": GLOBAL_STATS.total_cost,
153
+ }
154
+
155
+ def _save_overview_data_yaml(self, path: Path) -> None:
156
+ """Save a yaml report of the instances and their exit statuses."""
157
+ with self._lock:
158
+ path.write_text(yaml.dump(self._get_overview_data(), indent=4))