@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 +1,355 @@
1
+ //! Problem statement types for SWE-agent
2
+ //!
3
+ //! This module defines various ways to specify a problem for the agent to solve.
4
+
5
+ use crate::exceptions::{Result, SWEAgentError};
6
+ use crate::utils::github::{parse_github_issue_url, GithubIssueInfo};
7
+ use serde::{Deserialize, Serialize};
8
+ use std::collections::HashMap;
9
+ use std::path::Path;
10
+
11
+ /// Trait for problem statements
12
+ pub trait ProblemStatement: Send + Sync {
13
+ /// Get the problem statement text
14
+ fn get_problem_statement(&self) -> String;
15
+
16
+ /// Get the unique identifier for this problem
17
+ fn id(&self) -> &str;
18
+
19
+ /// Get any extra fields for template rendering
20
+ fn get_extra_fields(&self) -> HashMap<String, String> {
21
+ HashMap::new()
22
+ }
23
+ }
24
+
25
+ /// Empty problem statement for testing
26
+ #[derive(Debug, Clone, Default, Serialize, Deserialize)]
27
+ pub struct EmptyProblemStatement {
28
+ #[serde(default = "default_empty_id")]
29
+ pub id: String,
30
+ }
31
+
32
+ fn default_empty_id() -> String {
33
+ "empty".to_string()
34
+ }
35
+
36
+ impl EmptyProblemStatement {
37
+ pub fn new() -> Self {
38
+ Self {
39
+ id: default_empty_id(),
40
+ }
41
+ }
42
+ }
43
+
44
+ impl ProblemStatement for EmptyProblemStatement {
45
+ fn get_problem_statement(&self) -> String {
46
+ String::new()
47
+ }
48
+
49
+ fn id(&self) -> &str {
50
+ &self.id
51
+ }
52
+ }
53
+
54
+ /// Text-based problem statement
55
+ #[derive(Debug, Clone, Serialize, Deserialize)]
56
+ pub struct TextProblemStatement {
57
+ pub text: String,
58
+ pub id: String,
59
+ }
60
+
61
+ impl TextProblemStatement {
62
+ pub fn new(text: impl Into<String>, id: impl Into<String>) -> Self {
63
+ Self {
64
+ text: text.into(),
65
+ id: id.into(),
66
+ }
67
+ }
68
+ }
69
+
70
+ impl ProblemStatement for TextProblemStatement {
71
+ fn get_problem_statement(&self) -> String {
72
+ self.text.clone()
73
+ }
74
+
75
+ fn id(&self) -> &str {
76
+ &self.id
77
+ }
78
+ }
79
+
80
+ /// Problem statement loaded from a file
81
+ #[derive(Debug, Clone, Serialize, Deserialize)]
82
+ pub struct FileProblemStatement {
83
+ pub path: String,
84
+ pub id: String,
85
+ #[serde(skip)]
86
+ cached_text: Option<String>,
87
+ }
88
+
89
+ impl FileProblemStatement {
90
+ pub fn new(path: impl Into<String>, id: impl Into<String>) -> Self {
91
+ Self {
92
+ path: path.into(),
93
+ id: id.into(),
94
+ cached_text: None,
95
+ }
96
+ }
97
+
98
+ pub fn load(&mut self) -> Result<()> {
99
+ let content = std::fs::read_to_string(&self.path)?;
100
+ self.cached_text = Some(content);
101
+ Ok(())
102
+ }
103
+ }
104
+
105
+ impl ProblemStatement for FileProblemStatement {
106
+ fn get_problem_statement(&self) -> String {
107
+ if let Some(ref text) = self.cached_text {
108
+ return text.clone();
109
+ }
110
+
111
+ std::fs::read_to_string(&self.path).unwrap_or_default()
112
+ }
113
+
114
+ fn id(&self) -> &str {
115
+ &self.id
116
+ }
117
+ }
118
+
119
+ /// GitHub issue as a problem statement
120
+ #[derive(Debug, Clone, Serialize, Deserialize)]
121
+ pub struct GithubIssue {
122
+ pub github_url: String,
123
+ #[serde(skip)]
124
+ pub info: Option<GithubIssueInfo>,
125
+ #[serde(skip)]
126
+ pub title: Option<String>,
127
+ #[serde(skip)]
128
+ pub body: Option<String>,
129
+ }
130
+
131
+ impl GithubIssue {
132
+ pub fn new(github_url: impl Into<String>) -> Result<Self> {
133
+ let url = github_url.into();
134
+ let info = parse_github_issue_url(&url)?;
135
+ Ok(Self {
136
+ github_url: url,
137
+ info: Some(info),
138
+ title: None,
139
+ body: None,
140
+ })
141
+ }
142
+
143
+ /// Fetch issue data from GitHub API
144
+ pub async fn fetch(&mut self) -> Result<()> {
145
+ let info = self.info.as_ref().ok_or_else(|| {
146
+ SWEAgentError::InvalidGithubUrl("No issue info available".to_string())
147
+ })?;
148
+
149
+ let client = reqwest::Client::new();
150
+ let api_url = format!(
151
+ "https://api.github.com/repos/{}/{}/issues/{}",
152
+ info.owner, info.repo, info.issue_number
153
+ );
154
+
155
+ let response = client
156
+ .get(&api_url)
157
+ .header("User-Agent", "swe-agent-rust")
158
+ .send()
159
+ .await?;
160
+
161
+ if !response.status().is_success() {
162
+ return Err(SWEAgentError::ApiError(format!(
163
+ "Failed to fetch issue: {}",
164
+ response.status()
165
+ )));
166
+ }
167
+
168
+ let data: serde_json::Value = response.json().await?;
169
+
170
+ self.title = data["title"].as_str().map(String::from);
171
+ self.body = data["body"].as_str().map(String::from);
172
+
173
+ Ok(())
174
+ }
175
+ }
176
+
177
+ impl ProblemStatement for GithubIssue {
178
+ fn get_problem_statement(&self) -> String {
179
+ let title = self.title.as_deref().unwrap_or("(No title)");
180
+ let body = self.body.as_deref().unwrap_or("(No description)");
181
+ format!("# {}\n\n{}", title, body)
182
+ }
183
+
184
+ fn id(&self) -> &str {
185
+ self.info
186
+ .as_ref()
187
+ .map(|i| i.full_name.as_str())
188
+ .unwrap_or("unknown")
189
+ }
190
+
191
+ fn get_extra_fields(&self) -> HashMap<String, String> {
192
+ let mut fields = HashMap::new();
193
+ if let Some(ref info) = self.info {
194
+ fields.insert("github_owner".to_string(), info.owner.clone());
195
+ fields.insert("github_repo".to_string(), info.repo.clone());
196
+ fields.insert("issue_number".to_string(), info.issue_number.to_string());
197
+ }
198
+ fields
199
+ }
200
+ }
201
+
202
+ /// SWE-Bench multimodal problem statement
203
+ #[derive(Debug, Clone, Serialize, Deserialize)]
204
+ pub struct SWEBenchMultimodalProblemStatement {
205
+ pub instance_id: String,
206
+ pub problem_statement: String,
207
+ #[serde(default)]
208
+ pub image_urls: Vec<String>,
209
+ #[serde(default)]
210
+ pub hints: Vec<String>,
211
+ }
212
+
213
+ impl SWEBenchMultimodalProblemStatement {
214
+ pub fn new(instance_id: impl Into<String>, problem_statement: impl Into<String>) -> Self {
215
+ Self {
216
+ instance_id: instance_id.into(),
217
+ problem_statement: problem_statement.into(),
218
+ image_urls: Vec::new(),
219
+ hints: Vec::new(),
220
+ }
221
+ }
222
+ }
223
+
224
+ impl ProblemStatement for SWEBenchMultimodalProblemStatement {
225
+ fn get_problem_statement(&self) -> String {
226
+ self.problem_statement.clone()
227
+ }
228
+
229
+ fn id(&self) -> &str {
230
+ &self.instance_id
231
+ }
232
+
233
+ fn get_extra_fields(&self) -> HashMap<String, String> {
234
+ let mut fields = HashMap::new();
235
+ if !self.hints.is_empty() {
236
+ fields.insert("hints".to_string(), self.hints.join("\n"));
237
+ }
238
+ fields
239
+ }
240
+ }
241
+
242
+ /// Configuration for problem statements
243
+ #[derive(Debug, Clone, Default, Serialize, Deserialize)]
244
+ #[serde(tag = "type", rename_all = "snake_case")]
245
+ pub enum ProblemStatementConfig {
246
+ #[default]
247
+ Empty,
248
+ Text {
249
+ text: String,
250
+ id: String,
251
+ },
252
+ File {
253
+ path: String,
254
+ id: String,
255
+ },
256
+ GithubIssue {
257
+ github_url: String,
258
+ },
259
+ SweBenchMultimodal {
260
+ instance_id: String,
261
+ problem_statement: String,
262
+ #[serde(default)]
263
+ image_urls: Vec<String>,
264
+ },
265
+ }
266
+
267
+ /// Create a problem statement from simplified input
268
+ pub fn problem_statement_from_simplified_input(input: &str) -> Result<Box<dyn ProblemStatement>> {
269
+ // Check if it's a GitHub URL
270
+ if input.starts_with("https://github.com/") && input.contains("/issues/") {
271
+ let issue = GithubIssue::new(input)?;
272
+ return Ok(Box::new(issue));
273
+ }
274
+
275
+ // Check if it's a file path
276
+ if Path::new(input).exists() {
277
+ let id = Path::new(input)
278
+ .file_stem()
279
+ .and_then(|s| s.to_str())
280
+ .unwrap_or("file")
281
+ .to_string();
282
+ let mut statement = FileProblemStatement::new(input, id);
283
+ statement.load()?;
284
+ return Ok(Box::new(statement));
285
+ }
286
+
287
+ // Treat as plain text
288
+ let id = format!(
289
+ "text_{}",
290
+ uuid::Uuid::new_v4().to_string().split('-').next().unwrap()
291
+ );
292
+ Ok(Box::new(TextProblemStatement::new(input, id)))
293
+ }
294
+
295
+ /// Create a problem statement from configuration
296
+ pub fn create_problem_statement(
297
+ config: &ProblemStatementConfig,
298
+ ) -> Result<Box<dyn ProblemStatement>> {
299
+ match config {
300
+ ProblemStatementConfig::Empty => Ok(Box::new(EmptyProblemStatement::new())),
301
+ ProblemStatementConfig::Text { text, id } => Ok(Box::new(TextProblemStatement::new(
302
+ text.clone(),
303
+ id.clone(),
304
+ ))),
305
+ ProblemStatementConfig::File { path, id } => {
306
+ let mut statement = FileProblemStatement::new(path.clone(), id.clone());
307
+ statement.load()?;
308
+ Ok(Box::new(statement))
309
+ }
310
+ ProblemStatementConfig::GithubIssue { github_url } => {
311
+ let issue = GithubIssue::new(github_url)?;
312
+ Ok(Box::new(issue))
313
+ }
314
+ ProblemStatementConfig::SweBenchMultimodal {
315
+ instance_id,
316
+ problem_statement,
317
+ image_urls,
318
+ } => {
319
+ let mut stmt = SWEBenchMultimodalProblemStatement::new(
320
+ instance_id.clone(),
321
+ problem_statement.clone(),
322
+ );
323
+ stmt.image_urls = image_urls.clone();
324
+ Ok(Box::new(stmt))
325
+ }
326
+ }
327
+ }
328
+
329
+ #[cfg(test)]
330
+ mod tests {
331
+ use super::*;
332
+
333
+ #[test]
334
+ fn test_empty_problem_statement() {
335
+ let ps = EmptyProblemStatement::new();
336
+ assert_eq!(ps.get_problem_statement(), "");
337
+ assert_eq!(ps.id(), "empty");
338
+ }
339
+
340
+ #[test]
341
+ fn test_text_problem_statement() {
342
+ let ps = TextProblemStatement::new("Fix the bug", "bug-123");
343
+ assert_eq!(ps.get_problem_statement(), "Fix the bug");
344
+ assert_eq!(ps.id(), "bug-123");
345
+ }
346
+
347
+ #[test]
348
+ fn test_github_issue_parsing() {
349
+ let issue = GithubIssue::new("https://github.com/owner/repo/issues/42").unwrap();
350
+ let info = issue.info.unwrap();
351
+ assert_eq!(info.owner, "owner");
352
+ assert_eq!(info.repo, "repo");
353
+ assert_eq!(info.issue_number, 42);
354
+ }
355
+ }