benchflow 0.7.11.dev2422__tar.gz → 0.9.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (1298) hide show
  1. benchflow-0.9.1/.gitignore +198 -0
  2. benchflow-0.9.1/CHANGELOG.md +1809 -0
  3. benchflow-0.9.1/PKG-INFO +289 -0
  4. benchflow-0.9.1/README.md +211 -0
  5. benchflow-0.9.1/pyproject.toml +294 -0
  6. benchflow-0.9.1/src/benchflow/__init__.py +638 -0
  7. benchflow-0.9.1/src/benchflow/_bfx/__init__.py +45 -0
  8. benchflow-0.9.1/src/benchflow/_bfx/bin/bfx-aarch64 +0 -0
  9. benchflow-0.9.1/src/benchflow/_bfx/bin/bfx-x86_64 +0 -0
  10. benchflow-0.9.1/src/benchflow/_bfx/client.py +331 -0
  11. benchflow-0.9.1/src/benchflow/_bfx/delivery.py +875 -0
  12. benchflow-0.9.1/src/benchflow/_bfx/locate.py +107 -0
  13. benchflow-0.9.1/src/benchflow/_bfx/pins.py +18 -0
  14. benchflow-0.9.1/src/benchflow/_daemon.py +1404 -0
  15. benchflow-0.9.1/src/benchflow/_daemon_wire.py +150 -0
  16. benchflow-0.9.1/src/benchflow/_diagnostics.py +239 -0
  17. benchflow-0.9.1/src/benchflow/_image_python_paths.py +548 -0
  18. benchflow-0.9.1/src/benchflow/_kit_seal.py +781 -0
  19. benchflow-0.9.1/src/benchflow/_park.py +773 -0
  20. benchflow-0.9.1/src/benchflow/_proxy_zygote.py +649 -0
  21. benchflow-0.9.1/src/benchflow/_root_only.py +147 -0
  22. benchflow-0.9.1/src/benchflow/_root_python.py +134 -0
  23. benchflow-0.9.1/src/benchflow/_runtime_tree.py +1278 -0
  24. benchflow-0.9.1/src/benchflow/_types.py +106 -0
  25. benchflow-0.9.1/src/benchflow/_utils/archive_paths.py +83 -0
  26. benchflow-0.9.1/src/benchflow/_utils/artifact_names.py +46 -0
  27. benchflow-0.9.1/src/benchflow/_utils/benchmark_repos.py +1273 -0
  28. benchflow-0.9.1/src/benchflow/_utils/command_hints.py +62 -0
  29. benchflow-0.9.1/src/benchflow/_utils/config.py +98 -0
  30. benchflow-0.9.1/src/benchflow/_utils/config_keys.py +230 -0
  31. benchflow-0.9.1/src/benchflow/_utils/config_override.py +208 -0
  32. benchflow-0.9.1/src/benchflow/_utils/config_redaction.py +324 -0
  33. benchflow-0.9.1/src/benchflow/_utils/dataset_registry.json +632 -0
  34. benchflow-0.9.1/src/benchflow/_utils/dataset_registry.py +617 -0
  35. benchflow-0.9.1/src/benchflow/_utils/disk_space.py +153 -0
  36. benchflow-0.9.1/src/benchflow/_utils/env_registry.py +237 -0
  37. benchflow-0.9.1/src/benchflow/_utils/env_values.py +49 -0
  38. benchflow-0.9.1/src/benchflow/_utils/evaluation_results.py +344 -0
  39. benchflow-0.9.1/src/benchflow/_utils/hf_datasets.py +265 -0
  40. benchflow-0.9.1/src/benchflow/_utils/job_lock.py +87 -0
  41. benchflow-0.9.1/src/benchflow/_utils/kill_record.py +106 -0
  42. benchflow-0.9.1/src/benchflow/_utils/learner_memory.py +169 -0
  43. benchflow-0.9.1/src/benchflow/_utils/log_context.py +102 -0
  44. benchflow-0.9.1/src/benchflow/_utils/modal_gpu.py +59 -0
  45. benchflow-0.9.1/src/benchflow/_utils/path_lock_record.py +66 -0
  46. benchflow-0.9.1/src/benchflow/_utils/reachable_write.py +2828 -0
  47. benchflow-0.9.1/src/benchflow/_utils/reported_models.py +91 -0
  48. benchflow-0.9.1/src/benchflow/_utils/result_metadata.py +75 -0
  49. benchflow-0.9.1/src/benchflow/_utils/result_paths.py +128 -0
  50. benchflow-0.9.1/src/benchflow/_utils/sandbox_providers.py +249 -0
  51. benchflow-0.9.1/src/benchflow/_utils/scoring.py +966 -0
  52. benchflow-0.9.1/src/benchflow/_utils/session_cost.py +222 -0
  53. benchflow-0.9.1/src/benchflow/_utils/start_pacing.py +100 -0
  54. benchflow-0.9.1/src/benchflow/_utils/task_authoring/__init__.py +686 -0
  55. benchflow-0.9.1/src/benchflow/_utils/task_authoring/scaffolding.py +446 -0
  56. benchflow-0.9.1/src/benchflow/_utils/task_authoring/structural_checks.py +673 -0
  57. benchflow-0.9.1/src/benchflow/_utils/timing_spans.py +265 -0
  58. benchflow-0.9.1/src/benchflow/_utils/trial_warnings.py +36 -0
  59. benchflow-0.9.1/src/benchflow/_utils/trusted_path.py +179 -0
  60. benchflow-0.9.1/src/benchflow/_utils/yaml_loader.py +376 -0
  61. benchflow-0.9.1/src/benchflow/_uv_pin.py +364 -0
  62. benchflow-0.9.1/src/benchflow/_verifier_env.py +97 -0
  63. benchflow-0.9.1/src/benchflow/_warm_pool.py +339 -0
  64. benchflow-0.9.1/src/benchflow/acp/__init__.py +52 -0
  65. benchflow-0.9.1/src/benchflow/acp/client.py +671 -0
  66. benchflow-0.9.1/src/benchflow/acp/container_transport.py +168 -0
  67. benchflow-0.9.1/src/benchflow/acp/runtime.py +1127 -0
  68. benchflow-0.9.1/src/benchflow/acp/selection.py +30 -0
  69. benchflow-0.9.1/src/benchflow/acp/session.py +862 -0
  70. benchflow-0.9.1/src/benchflow/acp/transport.py +161 -0
  71. benchflow-0.9.1/src/benchflow/acp/types.py +479 -0
  72. benchflow-0.9.1/src/benchflow/acp/watchdog.py +367 -0
  73. benchflow-0.9.1/src/benchflow/adapters/__init__.py +56 -0
  74. benchflow-0.9.1/src/benchflow/adapters/_toolathlon.py +1222 -0
  75. benchflow-0.9.1/src/benchflow/adapters/_toolathlon_fake_mail.py +395 -0
  76. benchflow-0.9.1/src/benchflow/adapters/inbound.py +324 -0
  77. benchflow-0.9.1/src/benchflow/adapters/resources/mcp_atlas_judge.py +114 -0
  78. benchflow-0.9.1/src/benchflow/adapters/task_toml.py +146 -0
  79. benchflow-0.9.1/src/benchflow/agent_router.py +955 -0
  80. benchflow-0.9.1/src/benchflow/agent_router_scaffold.py +271 -0
  81. benchflow-0.9.1/src/benchflow/agent_start.py +158 -0
  82. benchflow-0.9.1/src/benchflow/agents/__init__.py +22 -0
  83. benchflow-0.9.1/src/benchflow/agents/_python_agent_pins.py +57 -0
  84. benchflow-0.9.1/src/benchflow/agents/antigravity_acp_shim.py +953 -0
  85. benchflow-0.9.1/src/benchflow/agents/antigravity_config.py +153 -0
  86. benchflow-0.9.1/src/benchflow/agents/codex_config.py +320 -0
  87. benchflow-0.9.1/src/benchflow/agents/codex_connector_policy.py +287 -0
  88. benchflow-0.9.1/src/benchflow/agents/credentials.py +544 -0
  89. benchflow-0.9.1/src/benchflow/agents/deepagents_acp_shim.py +613 -0
  90. benchflow-0.9.1/src/benchflow/agents/env.py +1228 -0
  91. benchflow-0.9.1/src/benchflow/agents/errors.py +254 -0
  92. benchflow-0.9.1/src/benchflow/agents/harvey_lab_acp_shim.py +810 -0
  93. benchflow-0.9.1/src/benchflow/agents/install.py +691 -0
  94. benchflow-0.9.1/src/benchflow/agents/launch_env.py +359 -0
  95. benchflow-0.9.1/src/benchflow/agents/login_dirs.py +71 -0
  96. benchflow-0.9.1/src/benchflow/agents/manifest.py +399 -0
  97. benchflow-0.9.1/src/benchflow/agents/muse_acp_shim.py +1175 -0
  98. benchflow-0.9.1/src/benchflow/agents/muse_config.py +142 -0
  99. benchflow-0.9.1/src/benchflow/agents/pi_acp_launcher.py +177 -0
  100. benchflow-0.9.1/src/benchflow/agents/providers.py +576 -0
  101. benchflow-0.9.1/src/benchflow/agents/registry.py +2501 -0
  102. benchflow-0.9.1/src/benchflow/agents/remote_manifests.py +280 -0
  103. benchflow-0.9.1/src/benchflow/agents/requirements/deepagents.txt +1633 -0
  104. benchflow-0.9.1/src/benchflow/agents/requirements/harvey-lab.txt +1109 -0
  105. benchflow-0.9.1/src/benchflow/agents/scripts.py +42 -0
  106. benchflow-0.9.1/src/benchflow/agents/usage_limits.py +336 -0
  107. benchflow-0.9.1/src/benchflow/batch.py +446 -0
  108. benchflow-0.9.1/src/benchflow/branch.py +188 -0
  109. benchflow-0.9.1/src/benchflow/branch_api.py +605 -0
  110. benchflow-0.9.1/src/benchflow/branch_artifacts.py +77 -0
  111. benchflow-0.9.1/src/benchflow/branch_lineage.py +390 -0
  112. benchflow-0.9.1/src/benchflow/branch_result.py +117 -0
  113. benchflow-0.9.1/src/benchflow/branch_run.py +909 -0
  114. benchflow-0.9.1/src/benchflow/branch_view.py +616 -0
  115. benchflow-0.9.1/src/benchflow/budget.py +721 -0
  116. benchflow-0.9.1/src/benchflow/checkpoint_retry.py +342 -0
  117. benchflow-0.9.1/src/benchflow/checkpoints.py +212 -0
  118. benchflow-0.9.1/src/benchflow/cli/_errors.py +736 -0
  119. benchflow-0.9.1/src/benchflow/cli/_failure_evidence.py +531 -0
  120. benchflow-0.9.1/src/benchflow/cli/_hosted_env.py +300 -0
  121. benchflow-0.9.1/src/benchflow/cli/_job_listing.py +187 -0
  122. benchflow-0.9.1/src/benchflow/cli/_lazy.py +242 -0
  123. benchflow-0.9.1/src/benchflow/cli/_live_progress.py +483 -0
  124. benchflow-0.9.1/src/benchflow/cli/_options.py +85 -0
  125. benchflow-0.9.1/src/benchflow/cli/_shared.py +813 -0
  126. benchflow-0.9.1/src/benchflow/cli/_termination.py +240 -0
  127. benchflow-0.9.1/src/benchflow/cli/adopt.py +191 -0
  128. benchflow-0.9.1/src/benchflow/cli/agent.py +198 -0
  129. benchflow-0.9.1/src/benchflow/cli/branch.py +638 -0
  130. benchflow-0.9.1/src/benchflow/cli/cache.py +649 -0
  131. benchflow-0.9.1/src/benchflow/cli/continue_cmd.py +285 -0
  132. benchflow-0.9.1/src/benchflow/cli/daemon.py +97 -0
  133. benchflow-0.9.1/src/benchflow/cli/doctor.py +824 -0
  134. benchflow-0.9.1/src/benchflow/cli/embodied.py +109 -0
  135. benchflow-0.9.1/src/benchflow/cli/eval_artifacts.py +804 -0
  136. benchflow-0.9.1/src/benchflow/cli/eval_lift.py +99 -0
  137. benchflow-0.9.1/src/benchflow/cli/eval_regrade.py +126 -0
  138. benchflow-0.9.1/src/benchflow/cli/explain.py +459 -0
  139. benchflow-0.9.1/src/benchflow/cli/hub.py +243 -0
  140. benchflow-0.9.1/src/benchflow/cli/main.py +3744 -0
  141. benchflow-0.9.1/src/benchflow/cli/new_verbs.py +789 -0
  142. benchflow-0.9.1/src/benchflow/cli/rescore.py +149 -0
  143. benchflow-0.9.1/src/benchflow/cli/results.py +519 -0
  144. benchflow-0.9.1/src/benchflow/cli/review.py +344 -0
  145. benchflow-0.9.1/src/benchflow/cli/reviewer_options.py +96 -0
  146. benchflow-0.9.1/src/benchflow/cli/sandbox.py +473 -0
  147. benchflow-0.9.1/src/benchflow/cli/skills.py +507 -0
  148. benchflow-0.9.1/src/benchflow/cli/tasks.py +917 -0
  149. benchflow-0.9.1/src/benchflow/cli/trace_import.py +454 -0
  150. benchflow-0.9.1/src/benchflow/cli/train.py +1095 -0
  151. benchflow-0.9.1/src/benchflow/cli/traj.py +1168 -0
  152. benchflow-0.9.1/src/benchflow/cli/verbs.py +628 -0
  153. benchflow-0.9.1/src/benchflow/cli_parity.py +406 -0
  154. benchflow-0.9.1/src/benchflow/continue_run/orchestrator.py +905 -0
  155. benchflow-0.9.1/src/benchflow/continue_run/run_folder.py +263 -0
  156. benchflow-0.9.1/src/benchflow/continue_run/sandbox_proxy.py +504 -0
  157. benchflow-0.9.1/src/benchflow/contracts/__init__.py +125 -0
  158. benchflow-0.9.1/src/benchflow/contracts/planes.py +235 -0
  159. benchflow-0.9.1/src/benchflow/contracts/user.py +298 -0
  160. benchflow-0.9.1/src/benchflow/diagnostics.py +998 -0
  161. benchflow-0.9.1/src/benchflow/doctor.py +2241 -0
  162. benchflow-0.9.1/src/benchflow/doctor_smoke.py +537 -0
  163. benchflow-0.9.1/src/benchflow/embodied/__init__.py +55 -0
  164. benchflow-0.9.1/src/benchflow/embodied/backend.py +60 -0
  165. benchflow-0.9.1/src/benchflow/embodied/cameras.py +66 -0
  166. benchflow-0.9.1/src/benchflow/embodied/export.py +175 -0
  167. benchflow-0.9.1/src/benchflow/embodied/protocol.py +65 -0
  168. benchflow-0.9.1/src/benchflow/embodied/robo.py +290 -0
  169. benchflow-0.9.1/src/benchflow/embodied/rollouts.py +318 -0
  170. benchflow-0.9.1/src/benchflow/embodied/serve.py +59 -0
  171. benchflow-0.9.1/src/benchflow/embodied/server.py +979 -0
  172. benchflow-0.9.1/src/benchflow/embodied/sidecar.py +468 -0
  173. benchflow-0.9.1/src/benchflow/embodied/skills.py +129 -0
  174. benchflow-0.9.1/src/benchflow/embodied/spec.py +712 -0
  175. benchflow-0.9.1/src/benchflow/embodied/templates/agent.Dockerfile +13 -0
  176. benchflow-0.9.1/src/benchflow/embodied/templates/docker-compose.yaml +52 -0
  177. benchflow-0.9.1/src/benchflow/embodied/templates/sim-entry.sh +22 -0
  178. benchflow-0.9.1/src/benchflow/embodied/templates/verifier/test.sh +8 -0
  179. benchflow-0.9.1/src/benchflow/embodied/templates/verifier/verifier.md +21 -0
  180. benchflow-0.9.1/src/benchflow/embodied/trials.py +68 -0
  181. benchflow-0.9.1/src/benchflow/embodied/verifier.py +112 -0
  182. benchflow-0.9.1/src/benchflow/environment/manifest_env.py +602 -0
  183. benchflow-0.9.1/src/benchflow/environment/protocol.py +79 -0
  184. benchflow-0.9.1/src/benchflow/environment/readiness.py +76 -0
  185. benchflow-0.9.1/src/benchflow/errors.py +67 -0
  186. benchflow-0.9.1/src/benchflow/eval_artifacts.py +482 -0
  187. benchflow-0.9.1/src/benchflow/eval_plan.py +866 -0
  188. benchflow-0.9.1/src/benchflow/eval_regrade.py +881 -0
  189. benchflow-0.9.1/src/benchflow/eval_sharding.py +608 -0
  190. benchflow-0.9.1/src/benchflow/eval_worker.py +195 -0
  191. benchflow-0.9.1/src/benchflow/evaluation.py +6251 -0
  192. benchflow-0.9.1/src/benchflow/experimental/mcp/hooks.py +56 -0
  193. benchflow-0.9.1/src/benchflow/experimental/mcp/reviewer_server.py +170 -0
  194. benchflow-0.9.1/src/benchflow/failures.py +652 -0
  195. benchflow-0.9.1/src/benchflow/hosted_env.py +1158 -0
  196. benchflow-0.9.1/src/benchflow/hub/__init__.py +19 -0
  197. benchflow-0.9.1/src/benchflow/hub/registry.py +306 -0
  198. benchflow-0.9.1/src/benchflow/integration_health.py +395 -0
  199. benchflow-0.9.1/src/benchflow/integrations/skillevaluator.py +796 -0
  200. benchflow-0.9.1/src/benchflow/integrations/trl/spec.py +483 -0
  201. benchflow-0.9.1/src/benchflow/integrity/__init__.py +78 -0
  202. benchflow-0.9.1/src/benchflow/integrity/access.py +611 -0
  203. benchflow-0.9.1/src/benchflow/integrity/agent_actions.py +708 -0
  204. benchflow-0.9.1/src/benchflow/integrity/authority.py +106 -0
  205. benchflow-0.9.1/src/benchflow/integrity/claim.py +406 -0
  206. benchflow-0.9.1/src/benchflow/integrity/classify.py +116 -0
  207. benchflow-0.9.1/src/benchflow/integrity/constants.py +204 -0
  208. benchflow-0.9.1/src/benchflow/integrity/contract.py +727 -0
  209. benchflow-0.9.1/src/benchflow/integrity/emit.py +1234 -0
  210. benchflow-0.9.1/src/benchflow/integrity/events.py +389 -0
  211. benchflow-0.9.1/src/benchflow/integrity/exec_decompose.py +1463 -0
  212. benchflow-0.9.1/src/benchflow/integrity/routes.py +227 -0
  213. benchflow-0.9.1/src/benchflow/integrity/selectors.py +122 -0
  214. benchflow-0.9.1/src/benchflow/integrity/trace_checker.py +871 -0
  215. benchflow-0.9.1/src/benchflow/integrity/trial.py +759 -0
  216. benchflow-0.9.1/src/benchflow/integrity/urls.py +468 -0
  217. benchflow-0.9.1/src/benchflow/integrity/verdict.py +162 -0
  218. benchflow-0.9.1/src/benchflow/job_config.py +732 -0
  219. benchflow-0.9.1/src/benchflow/job_export.py +1045 -0
  220. benchflow-0.9.1/src/benchflow/jobs.py +1912 -0
  221. benchflow-0.9.1/src/benchflow/key_check.py +177 -0
  222. benchflow-0.9.1/src/benchflow/learner_skills.py +149 -0
  223. benchflow-0.9.1/src/benchflow/metrics.py +519 -0
  224. benchflow-0.9.1/src/benchflow/models.py +450 -0
  225. benchflow-0.9.1/src/benchflow/monitor.py +209 -0
  226. benchflow-0.9.1/src/benchflow/native_harness/__init__.py +30 -0
  227. benchflow-0.9.1/src/benchflow/native_harness/_log_io.py +21 -0
  228. benchflow-0.9.1/src/benchflow/native_harness/claude_code.py +1003 -0
  229. benchflow-0.9.1/src/benchflow/native_harness/client.py +812 -0
  230. benchflow-0.9.1/src/benchflow/native_harness/codex.py +422 -0
  231. benchflow-0.9.1/src/benchflow/native_harness/harnesses.py +148 -0
  232. benchflow-0.9.1/src/benchflow/native_harness/runtime.py +210 -0
  233. benchflow-0.9.1/src/benchflow/native_harness/session.py +77 -0
  234. benchflow-0.9.1/src/benchflow/native_harness/spec.py +188 -0
  235. benchflow-0.9.1/src/benchflow/pass_at_k.py +482 -0
  236. benchflow-0.9.1/src/benchflow/providers/litellm_bedrock_patch.py +384 -0
  237. benchflow-0.9.1/src/benchflow/providers/litellm_bedrock_preflight.py +227 -0
  238. benchflow-0.9.1/src/benchflow/providers/litellm_config.py +509 -0
  239. benchflow-0.9.1/src/benchflow/providers/litellm_gemini_passthrough_patch.py +116 -0
  240. benchflow-0.9.1/src/benchflow/providers/litellm_lazy_start.py +332 -0
  241. benchflow-0.9.1/src/benchflow/providers/litellm_logging.py +960 -0
  242. benchflow-0.9.1/src/benchflow/providers/litellm_request_guard.py +1969 -0
  243. benchflow-0.9.1/src/benchflow/providers/litellm_runtime.py +3410 -0
  244. benchflow-0.9.1/src/benchflow/providers/litellm_token_capture_patch.py +145 -0
  245. benchflow-0.9.1/src/benchflow/providers/proxy_requirements/__init__.py +491 -0
  246. benchflow-0.9.1/src/benchflow/providers/proxy_requirements/litellm-proxy-vertex.txt +2369 -0
  247. benchflow-0.9.1/src/benchflow/providers/proxy_requirements/litellm-proxy.txt +2176 -0
  248. benchflow-0.9.1/src/benchflow/providers/restricted_endpoints.py +161 -0
  249. benchflow-0.9.1/src/benchflow/providers/restricted_model_allowlist.json +1706 -0
  250. benchflow-0.9.1/src/benchflow/providers/restricted_models.py +380 -0
  251. benchflow-0.9.1/src/benchflow/providers/runtime.py +167 -0
  252. benchflow-0.9.1/src/benchflow/publish/_snapshot.py +16 -0
  253. benchflow-0.9.1/src/benchflow/publish/huggingface.py +227 -0
  254. benchflow-0.9.1/src/benchflow/publish/traj_capture.py +848 -0
  255. benchflow-0.9.1/src/benchflow/review/automatic.py +236 -0
  256. benchflow-0.9.1/src/benchflow/review/config.py +387 -0
  257. benchflow-0.9.1/src/benchflow/review/evidence.py +1605 -0
  258. benchflow-0.9.1/src/benchflow/review/evidence_runtime.py +103 -0
  259. benchflow-0.9.1/src/benchflow/review/options.py +96 -0
  260. benchflow-0.9.1/src/benchflow/review/outcome.py +206 -0
  261. benchflow-0.9.1/src/benchflow/review/persistence.py +264 -0
  262. benchflow-0.9.1/src/benchflow/review/preflight.py +60 -0
  263. benchflow-0.9.1/src/benchflow/review/resume.py +353 -0
  264. benchflow-0.9.1/src/benchflow/review/runner.py +872 -0
  265. benchflow-0.9.1/src/benchflow/review/scoring.py +120 -0
  266. benchflow-0.9.1/src/benchflow/review/wrapper.py +406 -0
  267. benchflow-0.9.1/src/benchflow/rewards/README.md +125 -0
  268. benchflow-0.9.1/src/benchflow/rewards/__init__.py +103 -0
  269. benchflow-0.9.1/src/benchflow/rewards/_safe_evidence.py +384 -0
  270. benchflow-0.9.1/src/benchflow/rewards/builtins.py +542 -0
  271. benchflow-0.9.1/src/benchflow/rewards/file_readers.py +160 -0
  272. benchflow-0.9.1/src/benchflow/rewards/llm.py +325 -0
  273. benchflow-0.9.1/src/benchflow/rewards/node.py +165 -0
  274. benchflow-0.9.1/src/benchflow/rewards/protocol.py +93 -0
  275. benchflow-0.9.1/src/benchflow/rewards/rubric_config.py +285 -0
  276. benchflow-0.9.1/src/benchflow/rewards/validation.py +828 -0
  277. benchflow-0.9.1/src/benchflow/rollout/__init__.py +6341 -0
  278. benchflow-0.9.1/src/benchflow/rollout/_artifact_links.py +22 -0
  279. benchflow-0.9.1/src/benchflow/rollout/_artifacts.py +682 -0
  280. benchflow-0.9.1/src/benchflow/rollout/_config.py +662 -0
  281. benchflow-0.9.1/src/benchflow/rollout/_deadline.py +302 -0
  282. benchflow-0.9.1/src/benchflow/rollout/_recovery_submission.py +115 -0
  283. benchflow-0.9.1/src/benchflow/rollout/_results.py +752 -0
  284. benchflow-0.9.1/src/benchflow/rollout/_review.py +426 -0
  285. benchflow-0.9.1/src/benchflow/rollout/_separate_verifier.py +2806 -0
  286. benchflow-0.9.1/src/benchflow/rollout/_session_log.py +218 -0
  287. benchflow-0.9.1/src/benchflow/rollout/_setup.py +2604 -0
  288. benchflow-0.9.1/src/benchflow/rollout/_teardown_queue.py +127 -0
  289. benchflow-0.9.1/src/benchflow/rollout/_user_loop.py +560 -0
  290. benchflow-0.9.1/src/benchflow/rollout/_verifier_recovery.py +835 -0
  291. benchflow-0.9.1/src/benchflow/rollout/session_factory_runtime.py +264 -0
  292. benchflow-0.9.1/src/benchflow/rollout/task_runtime.py +337 -0
  293. benchflow-0.9.1/src/benchflow/rollout_branch.py +1259 -0
  294. benchflow-0.9.1/src/benchflow/rollout_planes.py +414 -0
  295. benchflow-0.9.1/src/benchflow/rubric_reviews.py +372 -0
  296. benchflow-0.9.1/src/benchflow/runtime.py +1082 -0
  297. benchflow-0.9.1/src/benchflow/sandbox/_base.py +2082 -0
  298. benchflow-0.9.1/src/benchflow/sandbox/_bind_targets.py +361 -0
  299. benchflow-0.9.1/src/benchflow/sandbox/_bounded_tar.py +56 -0
  300. benchflow-0.9.1/src/benchflow/sandbox/_cache_reclaim.py +103 -0
  301. benchflow-0.9.1/src/benchflow/sandbox/_compose.py +365 -0
  302. benchflow-0.9.1/src/benchflow/sandbox/_compose_build.py +283 -0
  303. benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-base.yaml +27 -0
  304. benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-kept-freezer.yaml +10 -0
  305. benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-no-net-raw.yaml +8 -0
  306. benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-no-new-privileges.yaml +9 -0
  307. benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-no-restart.yaml +12 -0
  308. benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-remote-base.yaml +26 -0
  309. benchflow-0.9.1/src/benchflow/sandbox/_compose_runtime.py +262 -0
  310. benchflow-0.9.1/src/benchflow/sandbox/_compose_teardown.py +137 -0
  311. benchflow-0.9.1/src/benchflow/sandbox/_dependency_options.py +582 -0
  312. benchflow-0.9.1/src/benchflow/sandbox/_dir_archive.py +109 -0
  313. benchflow-0.9.1/src/benchflow/sandbox/_direct_docker.py +1139 -0
  314. benchflow-0.9.1/src/benchflow/sandbox/_docker_subnets.py +1356 -0
  315. benchflow-0.9.1/src/benchflow/sandbox/_docker_sweep.py +503 -0
  316. benchflow-0.9.1/src/benchflow/sandbox/_download.py +113 -0
  317. benchflow-0.9.1/src/benchflow/sandbox/_egress_denylist_proxy.py +1626 -0
  318. benchflow-0.9.1/src/benchflow/sandbox/_engine_api.py +236 -0
  319. benchflow-0.9.1/src/benchflow/sandbox/_exec_channel.py +884 -0
  320. benchflow-0.9.1/src/benchflow/sandbox/_exec_merge.py +263 -0
  321. benchflow-0.9.1/src/benchflow/sandbox/_exec_output.py +79 -0
  322. benchflow-0.9.1/src/benchflow/sandbox/_exec_receipt.py +240 -0
  323. benchflow-0.9.1/src/benchflow/sandbox/_hardening_python.py +83 -0
  324. benchflow-0.9.1/src/benchflow/sandbox/_hook_cleanup.py +1313 -0
  325. benchflow-0.9.1/src/benchflow/sandbox/_hooks.py +18 -0
  326. benchflow-0.9.1/src/benchflow/sandbox/_host_copy.py +11 -0
  327. benchflow-0.9.1/src/benchflow/sandbox/_identities.py +307 -0
  328. benchflow-0.9.1/src/benchflow/sandbox/_in_order.py +46 -0
  329. benchflow-0.9.1/src/benchflow/sandbox/_inert_bootstrap.py +501 -0
  330. benchflow-0.9.1/src/benchflow/sandbox/_kit_cache.py +251 -0
  331. benchflow-0.9.1/src/benchflow/sandbox/_layer_lock.py +321 -0
  332. benchflow-0.9.1/src/benchflow/sandbox/_locked_path_validation.py +28 -0
  333. benchflow-0.9.1/src/benchflow/sandbox/_metadata_helper.py +707 -0
  334. benchflow-0.9.1/src/benchflow/sandbox/_mount_aliases.py +211 -0
  335. benchflow-0.9.1/src/benchflow/sandbox/_path_inspector_state.py +39 -0
  336. benchflow-0.9.1/src/benchflow/sandbox/_prepull.py +102 -0
  337. benchflow-0.9.1/src/benchflow/sandbox/_pull_provenance.py +183 -0
  338. benchflow-0.9.1/src/benchflow/sandbox/_pytest_plugin_guard.py +1810 -0
  339. benchflow-0.9.1/src/benchflow/sandbox/_recovery_baseline.py +142 -0
  340. benchflow-0.9.1/src/benchflow/sandbox/_recovery_submission.py +470 -0
  341. benchflow-0.9.1/src/benchflow/sandbox/_root_launch.py +550 -0
  342. benchflow-0.9.1/src/benchflow/sandbox/_sdk_ops.py +208 -0
  343. benchflow-0.9.1/src/benchflow/sandbox/_shell.py +8 -0
  344. benchflow-0.9.1/src/benchflow/sandbox/_snapshot_credentials.py +383 -0
  345. benchflow-0.9.1/src/benchflow/sandbox/_su.py +80 -0
  346. benchflow-0.9.1/src/benchflow/sandbox/_system_route_walk.py +238 -0
  347. benchflow-0.9.1/src/benchflow/sandbox/_task_route.py +41 -0
  348. benchflow-0.9.1/src/benchflow/sandbox/_transport.py +298 -0
  349. benchflow-0.9.1/src/benchflow/sandbox/_trial_volumes.py +203 -0
  350. benchflow-0.9.1/src/benchflow/sandbox/_verifier_runtime.py +2169 -0
  351. benchflow-0.9.1/src/benchflow/sandbox/_verifier_tool_state.py +360 -0
  352. benchflow-0.9.1/src/benchflow/sandbox/_workspace_ancestry.py +62 -0
  353. benchflow-0.9.1/src/benchflow/sandbox/_workspace_owner.py +146 -0
  354. benchflow-0.9.1/src/benchflow/sandbox/agent_exec.py +130 -0
  355. benchflow-0.9.1/src/benchflow/sandbox/agentcore.py +1350 -0
  356. benchflow-0.9.1/src/benchflow/sandbox/agentcore_builder.py +659 -0
  357. benchflow-0.9.1/src/benchflow/sandbox/agentcore_image.py +266 -0
  358. benchflow-0.9.1/src/benchflow/sandbox/agentcore_provisioning.py +497 -0
  359. benchflow-0.9.1/src/benchflow/sandbox/apple_container.py +877 -0
  360. benchflow-0.9.1/src/benchflow/sandbox/cloud_metadata.py +425 -0
  361. benchflow-0.9.1/src/benchflow/sandbox/daytona.py +2889 -0
  362. benchflow-0.9.1/src/benchflow/sandbox/daytona_content_snapshots.py +836 -0
  363. benchflow-0.9.1/src/benchflow/sandbox/daytona_delete.py +65 -0
  364. benchflow-0.9.1/src/benchflow/sandbox/daytona_dind.py +1631 -0
  365. benchflow-0.9.1/src/benchflow/sandbox/daytona_layers.py +584 -0
  366. benchflow-0.9.1/src/benchflow/sandbox/daytona_ledger.py +598 -0
  367. benchflow-0.9.1/src/benchflow/sandbox/daytona_pty.py +187 -0
  368. benchflow-0.9.1/src/benchflow/sandbox/daytona_reaper.py +611 -0
  369. benchflow-0.9.1/src/benchflow/sandbox/daytona_start.py +273 -0
  370. benchflow-0.9.1/src/benchflow/sandbox/daytona_strategies.py +1072 -0
  371. benchflow-0.9.1/src/benchflow/sandbox/docker.py +6219 -0
  372. benchflow-0.9.1/src/benchflow/sandbox/egress_denylist.py +555 -0
  373. benchflow-0.9.1/src/benchflow/sandbox/env_layers.py +2645 -0
  374. benchflow-0.9.1/src/benchflow/sandbox/firewall_power.py +1350 -0
  375. benchflow-0.9.1/src/benchflow/sandbox/image_build.py +235 -0
  376. benchflow-0.9.1/src/benchflow/sandbox/lockdown.py +13660 -0
  377. benchflow-0.9.1/src/benchflow/sandbox/metadata.py +57 -0
  378. benchflow-0.9.1/src/benchflow/sandbox/modal_impl.py +891 -0
  379. benchflow-0.9.1/src/benchflow/sandbox/native_agent_env.py +118 -0
  380. benchflow-0.9.1/src/benchflow/sandbox/native_oauth.py +260 -0
  381. benchflow-0.9.1/src/benchflow/sandbox/oracle_egress.py +411 -0
  382. benchflow-0.9.1/src/benchflow/sandbox/process/__init__.py +42 -0
  383. benchflow-0.9.1/src/benchflow/sandbox/process/_acp_lines.py +202 -0
  384. benchflow-0.9.1/src/benchflow/sandbox/process/_base.py +341 -0
  385. benchflow-0.9.1/src/benchflow/sandbox/process/agentcore.py +481 -0
  386. benchflow-0.9.1/src/benchflow/sandbox/process/apple.py +206 -0
  387. benchflow-0.9.1/src/benchflow/sandbox/process/daytona.py +1060 -0
  388. benchflow-0.9.1/src/benchflow/sandbox/process/docker.py +288 -0
  389. benchflow-0.9.1/src/benchflow/sandbox/process/modal.py +424 -0
  390. benchflow-0.9.1/src/benchflow/sandbox/protocol.py +284 -0
  391. benchflow-0.9.1/src/benchflow/sandbox/providers.py +54 -0
  392. benchflow-0.9.1/src/benchflow/sandbox/recovery_network.py +69 -0
  393. benchflow-0.9.1/src/benchflow/sandbox/remote_docker.py +1846 -0
  394. benchflow-0.9.1/src/benchflow/sandbox/services.py +126 -0
  395. benchflow-0.9.1/src/benchflow/sandbox/setup.py +1088 -0
  396. benchflow-0.9.1/src/benchflow/sandbox/snapshot.py +119 -0
  397. benchflow-0.9.1/src/benchflow/sandbox/verifier_layers.py +677 -0
  398. benchflow-0.9.1/src/benchflow/sdk.py +256 -0
  399. benchflow-0.9.1/src/benchflow/self_gen.py +206 -0
  400. benchflow-0.9.1/src/benchflow/skill_eval/_core.py +834 -0
  401. benchflow-0.9.1/src/benchflow/skill_eval/gepa_export.py +199 -0
  402. benchflow-0.9.1/src/benchflow/task/__init__.py +392 -0
  403. benchflow-0.9.1/src/benchflow/task/_document_normalize.py +216 -0
  404. benchflow-0.9.1/src/benchflow/task/_document_parse.py +636 -0
  405. benchflow-0.9.1/src/benchflow/task/_document_profiles.py +160 -0
  406. benchflow-0.9.1/src/benchflow/task/acceptance_live.py +461 -0
  407. benchflow-0.9.1/src/benchflow/task/artifacts.py +49 -0
  408. benchflow-0.9.1/src/benchflow/task/canary.py +63 -0
  409. benchflow-0.9.1/src/benchflow/task/compose_env.py +3127 -0
  410. benchflow-0.9.1/src/benchflow/task/compose_load.py +650 -0
  411. benchflow-0.9.1/src/benchflow/task/config.py +1449 -0
  412. benchflow-0.9.1/src/benchflow/task/env.py +330 -0
  413. benchflow-0.9.1/src/benchflow/task/equivalence.py +658 -0
  414. benchflow-0.9.1/src/benchflow/task/equivalence_variants.py +968 -0
  415. benchflow-0.9.1/src/benchflow/task/export.py +566 -0
  416. benchflow-0.9.1/src/benchflow/task/formats.py +191 -0
  417. benchflow-0.9.1/src/benchflow/task/identity_switch.py +117 -0
  418. benchflow-0.9.1/src/benchflow/task/imports.py +487 -0
  419. benchflow-0.9.1/src/benchflow/task/keep_services.py +764 -0
  420. benchflow-0.9.1/src/benchflow/task/package.py +174 -0
  421. benchflow-0.9.1/src/benchflow/task/paths.py +424 -0
  422. benchflow-0.9.1/src/benchflow/task/plan_validation.py +223 -0
  423. benchflow-0.9.1/src/benchflow/task/runtime_capabilities.py +1080 -0
  424. benchflow-0.9.1/src/benchflow/task/runtime_view.py +181 -0
  425. benchflow-0.9.1/src/benchflow/task/staging.py +415 -0
  426. benchflow-0.9.1/src/benchflow/task/task.py +91 -0
  427. benchflow-0.9.1/src/benchflow/task/tb2_keep_services.json +57 -0
  428. benchflow-0.9.1/src/benchflow/task/verifier.py +53 -0
  429. benchflow-0.9.1/src/benchflow/task/verifier_core.py +2356 -0
  430. benchflow-0.9.1/src/benchflow/task/verifier_criteria_runner.py +166 -0
  431. benchflow-0.9.1/src/benchflow/task/verifier_document.py +447 -0
  432. benchflow-0.9.1/src/benchflow/task/verifier_errors.py +201 -0
  433. benchflow-0.9.1/src/benchflow/task/verifier_judge_inputs.py +84 -0
  434. benchflow-0.9.1/src/benchflow/task/verifier_ors_episode.py +307 -0
  435. benchflow-0.9.1/src/benchflow/task/verifier_sandbox.py +399 -0
  436. benchflow-0.9.1/src/benchflow/task/verifier_scan.py +112 -0
  437. benchflow-0.9.1/src/benchflow/task/verifier_script_strategy.py +136 -0
  438. benchflow-0.9.1/src/benchflow/taskmd/__init__.py +49 -0
  439. benchflow-0.9.1/src/benchflow/taskmd/_util.py +15 -0
  440. benchflow-0.9.1/src/benchflow/taskmd/_vendor/VENDOR.json +19 -0
  441. benchflow-0.9.1/src/benchflow/taskmd/_vendor/__init__.py +21 -0
  442. benchflow-0.9.1/src/benchflow/taskmd/_vendor/judgeprompt.py +1617 -0
  443. benchflow-0.9.1/src/benchflow/taskmd/_vendor/taskmd.py +3472 -0
  444. benchflow-0.9.1/src/benchflow/taskmd/check.py +95 -0
  445. benchflow-0.9.1/src/benchflow/taskmd/family.py +293 -0
  446. benchflow-0.9.1/src/benchflow/taskmd/grading.py +320 -0
  447. benchflow-0.9.1/src/benchflow/taskmd/judging.py +1564 -0
  448. benchflow-0.9.1/src/benchflow/taskmd/launch.py +99 -0
  449. benchflow-0.9.1/src/benchflow/taskmd/materialize.py +701 -0
  450. benchflow-0.9.1/src/benchflow/taskmd/plan.py +1915 -0
  451. benchflow-0.9.1/src/benchflow/taskmd/reference.py +93 -0
  452. benchflow-0.9.1/src/benchflow/taskmd/trajectory.py +236 -0
  453. benchflow-0.9.1/src/benchflow/taskmd/verify.py +2423 -0
  454. benchflow-0.9.1/src/benchflow/templates/judge.py.tmpl +219 -0
  455. benchflow-0.9.1/src/benchflow/traces/huggingface.py +672 -0
  456. benchflow-0.9.1/src/benchflow/traces/parsers.py +503 -0
  457. benchflow-0.9.1/src/benchflow/trajectories/_capture.py +584 -0
  458. benchflow-0.9.1/src/benchflow/trajectories/_export_common.py +144 -0
  459. benchflow-0.9.1/src/benchflow/trajectories/_llm_capture.py +55 -0
  460. benchflow-0.9.1/src/benchflow/trajectories/_snapshot.py +57 -0
  461. benchflow-0.9.1/src/benchflow/trajectories/branch_row_schema.py +255 -0
  462. benchflow-0.9.1/src/benchflow/trajectories/export.py +295 -0
  463. benchflow-0.9.1/src/benchflow/trajectories/export_adp.py +271 -0
  464. benchflow-0.9.1/src/benchflow/trajectories/export_atif.py +471 -0
  465. benchflow-0.9.1/src/benchflow/trajectories/export_branch.py +721 -0
  466. benchflow-0.9.1/src/benchflow/trajectories/export_prime_sft.py +1620 -0
  467. benchflow-0.9.1/src/benchflow/trajectories/export_trl_sft.py +753 -0
  468. benchflow-0.9.1/src/benchflow/trajectories/results.py +925 -0
  469. benchflow-0.9.1/src/benchflow/trajectories/rollout_stream.py +962 -0
  470. benchflow-0.9.1/src/benchflow/trajectories/sft_subagents.py +586 -0
  471. benchflow-0.9.1/src/benchflow/trajectories/token_capture.py +538 -0
  472. benchflow-0.9.1/src/benchflow/trajectories/training_signal.py +631 -0
  473. benchflow-0.9.1/src/benchflow/trajectories/types.py +808 -0
  474. benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/boot.js +182 -0
  475. benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/catalog.js +400 -0
  476. benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/detail.js +1142 -0
  477. benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/template.html +51 -0
  478. benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/viewer.css +362 -0
  479. benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/viewer.js +86 -0
  480. benchflow-0.9.1/src/benchflow/trajectories/viewer/catalog.py +159 -0
  481. benchflow-0.9.1/src/benchflow/trajectories/viewer/legacy.py +780 -0
  482. benchflow-0.9.1/src/benchflow/trajectories/viewer/models.py +816 -0
  483. benchflow-0.9.1/src/benchflow/trajectories/viewer/payload.py +1293 -0
  484. benchflow-0.9.1/src/benchflow/trajectories/viewer/render.py +108 -0
  485. benchflow-0.9.1/src/benchflow/trajectories/viewer/server.py +536 -0
  486. benchflow-0.9.1/src/benchflow/trajectories/viewer/sources.py +191 -0
  487. benchflow-0.9.1/src/benchflow/trajectories/viewer/subagents.py +182 -0
  488. benchflow-0.9.1/src/benchflow/trust/__init__.py +9 -0
  489. benchflow-0.9.1/src/benchflow/trust/ingress.py +219 -0
  490. benchflow-0.9.1/src/benchflow/trust/state.py +1104 -0
  491. benchflow-0.7.11.dev2422/.gitignore +0 -190
  492. benchflow-0.7.11.dev2422/CHANGELOG.md +0 -1334
  493. benchflow-0.7.11.dev2422/PKG-INFO +0 -320
  494. benchflow-0.7.11.dev2422/README.md +0 -245
  495. benchflow-0.7.11.dev2422/pyproject.toml +0 -231
  496. benchflow-0.7.11.dev2422/src/benchflow/__init__.py +0 -283
  497. benchflow-0.7.11.dev2422/src/benchflow/_run.py +0 -34
  498. benchflow-0.7.11.dev2422/src/benchflow/_types.py +0 -106
  499. benchflow-0.7.11.dev2422/src/benchflow/_utils/benchmark_repos.py +0 -551
  500. benchflow-0.7.11.dev2422/src/benchflow/_utils/config.py +0 -82
  501. benchflow-0.7.11.dev2422/src/benchflow/_utils/config_override.py +0 -155
  502. benchflow-0.7.11.dev2422/src/benchflow/_utils/config_redaction.py +0 -55
  503. benchflow-0.7.11.dev2422/src/benchflow/_utils/dataset_registry.py +0 -250
  504. benchflow-0.7.11.dev2422/src/benchflow/_utils/env_registry.py +0 -236
  505. benchflow-0.7.11.dev2422/src/benchflow/_utils/evaluation_results.py +0 -306
  506. benchflow-0.7.11.dev2422/src/benchflow/_utils/hf_datasets.py +0 -244
  507. benchflow-0.7.11.dev2422/src/benchflow/_utils/learner_memory.py +0 -166
  508. benchflow-0.7.11.dev2422/src/benchflow/_utils/result_metadata.py +0 -75
  509. benchflow-0.7.11.dev2422/src/benchflow/_utils/result_paths.py +0 -74
  510. benchflow-0.7.11.dev2422/src/benchflow/_utils/scoring.py +0 -460
  511. benchflow-0.7.11.dev2422/src/benchflow/_utils/task_authoring/__init__.py +0 -386
  512. benchflow-0.7.11.dev2422/src/benchflow/_utils/task_authoring/scaffolding.py +0 -425
  513. benchflow-0.7.11.dev2422/src/benchflow/_utils/task_authoring/structural_checks.py +0 -367
  514. benchflow-0.7.11.dev2422/src/benchflow/_utils/yaml_loader.py +0 -175
  515. benchflow-0.7.11.dev2422/src/benchflow/acp/__init__.py +0 -22
  516. benchflow-0.7.11.dev2422/src/benchflow/acp/client.py +0 -437
  517. benchflow-0.7.11.dev2422/src/benchflow/acp/container_transport.py +0 -145
  518. benchflow-0.7.11.dev2422/src/benchflow/acp/runtime.py +0 -906
  519. benchflow-0.7.11.dev2422/src/benchflow/acp/selection.py +0 -30
  520. benchflow-0.7.11.dev2422/src/benchflow/acp/session.py +0 -570
  521. benchflow-0.7.11.dev2422/src/benchflow/acp/transport.py +0 -145
  522. benchflow-0.7.11.dev2422/src/benchflow/acp/types.py +0 -385
  523. benchflow-0.7.11.dev2422/src/benchflow/acp/watchdog.py +0 -249
  524. benchflow-0.7.11.dev2422/src/benchflow/adapters/__init__.py +0 -56
  525. benchflow-0.7.11.dev2422/src/benchflow/adapters/_toolathlon.py +0 -1121
  526. benchflow-0.7.11.dev2422/src/benchflow/adapters/_toolathlon_fake_mail.py +0 -398
  527. benchflow-0.7.11.dev2422/src/benchflow/adapters/_toolathlon_poste_users.tsv +0 -503
  528. benchflow-0.7.11.dev2422/src/benchflow/adapters/harbor.py +0 -148
  529. benchflow-0.7.11.dev2422/src/benchflow/adapters/inbound.py +0 -326
  530. benchflow-0.7.11.dev2422/src/benchflow/adapters/resources/mcp_atlas_judge.py +0 -107
  531. benchflow-0.7.11.dev2422/src/benchflow/agent_router.py +0 -953
  532. benchflow-0.7.11.dev2422/src/benchflow/agent_router_scaffold.py +0 -271
  533. benchflow-0.7.11.dev2422/src/benchflow/agents/__init__.py +0 -27
  534. benchflow-0.7.11.dev2422/src/benchflow/agents/antigravity_acp_shim.py +0 -874
  535. benchflow-0.7.11.dev2422/src/benchflow/agents/antigravity_config.py +0 -137
  536. benchflow-0.7.11.dev2422/src/benchflow/agents/codex_config.py +0 -179
  537. benchflow-0.7.11.dev2422/src/benchflow/agents/credentials.py +0 -229
  538. benchflow-0.7.11.dev2422/src/benchflow/agents/deepagents_acp_shim.py +0 -530
  539. benchflow-0.7.11.dev2422/src/benchflow/agents/env.py +0 -845
  540. benchflow-0.7.11.dev2422/src/benchflow/agents/errors.py +0 -7
  541. benchflow-0.7.11.dev2422/src/benchflow/agents/harvey_lab_acp_shim.py +0 -749
  542. benchflow-0.7.11.dev2422/src/benchflow/agents/install.py +0 -373
  543. benchflow-0.7.11.dev2422/src/benchflow/agents/manifest.py +0 -359
  544. benchflow-0.7.11.dev2422/src/benchflow/agents/openclaw_acp_shim.py +0 -973
  545. benchflow-0.7.11.dev2422/src/benchflow/agents/pi_acp_launcher.py +0 -171
  546. benchflow-0.7.11.dev2422/src/benchflow/agents/providers.py +0 -545
  547. benchflow-0.7.11.dev2422/src/benchflow/agents/registry.py +0 -1652
  548. benchflow-0.7.11.dev2422/src/benchflow/agents/remote_manifests.py +0 -171
  549. benchflow-0.7.11.dev2422/src/benchflow/branch.py +0 -74
  550. benchflow-0.7.11.dev2422/src/benchflow/cli/_failure_evidence.py +0 -302
  551. benchflow-0.7.11.dev2422/src/benchflow/cli/_hosted_env.py +0 -185
  552. benchflow-0.7.11.dev2422/src/benchflow/cli/_live_progress.py +0 -436
  553. benchflow-0.7.11.dev2422/src/benchflow/cli/_options.py +0 -33
  554. benchflow-0.7.11.dev2422/src/benchflow/cli/_shared.py +0 -254
  555. benchflow-0.7.11.dev2422/src/benchflow/cli/adopt.py +0 -190
  556. benchflow-0.7.11.dev2422/src/benchflow/cli/agent.py +0 -93
  557. benchflow-0.7.11.dev2422/src/benchflow/cli/continue_cmd.py +0 -275
  558. benchflow-0.7.11.dev2422/src/benchflow/cli/eval_artifacts.py +0 -350
  559. benchflow-0.7.11.dev2422/src/benchflow/cli/eval_lift.py +0 -95
  560. benchflow-0.7.11.dev2422/src/benchflow/cli/hub.py +0 -199
  561. benchflow-0.7.11.dev2422/src/benchflow/cli/main.py +0 -1420
  562. benchflow-0.7.11.dev2422/src/benchflow/cli/rescore.py +0 -116
  563. benchflow-0.7.11.dev2422/src/benchflow/cli/review.py +0 -278
  564. benchflow-0.7.11.dev2422/src/benchflow/cli/reviewer_options.py +0 -62
  565. benchflow-0.7.11.dev2422/src/benchflow/cli/sandbox.py +0 -243
  566. benchflow-0.7.11.dev2422/src/benchflow/cli/skills.py +0 -476
  567. benchflow-0.7.11.dev2422/src/benchflow/cli/tasks.py +0 -488
  568. benchflow-0.7.11.dev2422/src/benchflow/cli/trace_import.py +0 -426
  569. benchflow-0.7.11.dev2422/src/benchflow/cli/train.py +0 -632
  570. benchflow-0.7.11.dev2422/src/benchflow/cli/traj.py +0 -1123
  571. benchflow-0.7.11.dev2422/src/benchflow/continue_run/orchestrator.py +0 -747
  572. benchflow-0.7.11.dev2422/src/benchflow/continue_run/run_folder.py +0 -211
  573. benchflow-0.7.11.dev2422/src/benchflow/continue_run/sandbox_proxy.py +0 -472
  574. benchflow-0.7.11.dev2422/src/benchflow/contracts/__init__.py +0 -72
  575. benchflow-0.7.11.dev2422/src/benchflow/contracts/planes.py +0 -146
  576. benchflow-0.7.11.dev2422/src/benchflow/contracts/user.py +0 -294
  577. benchflow-0.7.11.dev2422/src/benchflow/diagnostics.py +0 -567
  578. benchflow-0.7.11.dev2422/src/benchflow/environment/manifest_env.py +0 -359
  579. benchflow-0.7.11.dev2422/src/benchflow/environment/protocol.py +0 -77
  580. benchflow-0.7.11.dev2422/src/benchflow/environment/readiness.py +0 -74
  581. benchflow-0.7.11.dev2422/src/benchflow/eval_artifacts.py +0 -463
  582. benchflow-0.7.11.dev2422/src/benchflow/eval_plan.py +0 -512
  583. benchflow-0.7.11.dev2422/src/benchflow/eval_sharding.py +0 -438
  584. benchflow-0.7.11.dev2422/src/benchflow/eval_worker.py +0 -137
  585. benchflow-0.7.11.dev2422/src/benchflow/evaluation.py +0 -2048
  586. benchflow-0.7.11.dev2422/src/benchflow/experimental/mcp/hooks.py +0 -52
  587. benchflow-0.7.11.dev2422/src/benchflow/experimental/mcp/reviewer_server.py +0 -141
  588. benchflow-0.7.11.dev2422/src/benchflow/hosted_env.py +0 -913
  589. benchflow-0.7.11.dev2422/src/benchflow/hub/__init__.py +0 -19
  590. benchflow-0.7.11.dev2422/src/benchflow/hub/harbor_registry.py +0 -289
  591. benchflow-0.7.11.dev2422/src/benchflow/integrations/skillevaluator.py +0 -790
  592. benchflow-0.7.11.dev2422/src/benchflow/integrations/trl/spec.py +0 -464
  593. benchflow-0.7.11.dev2422/src/benchflow/learner_skills.py +0 -142
  594. benchflow-0.7.11.dev2422/src/benchflow/metrics.py +0 -412
  595. benchflow-0.7.11.dev2422/src/benchflow/models.py +0 -245
  596. benchflow-0.7.11.dev2422/src/benchflow/monitor.py +0 -209
  597. benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_bedrock_patch.py +0 -128
  598. benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_bedrock_preflight.py +0 -185
  599. benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_config.py +0 -500
  600. benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_gemini_passthrough_patch.py +0 -116
  601. benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_logging.py +0 -655
  602. benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_runtime.py +0 -1825
  603. benchflow-0.7.11.dev2422/src/benchflow/providers/runtime.py +0 -90
  604. benchflow-0.7.11.dev2422/src/benchflow/publish/huggingface.py +0 -223
  605. benchflow-0.7.11.dev2422/src/benchflow/publish/traj_capture.py +0 -825
  606. benchflow-0.7.11.dev2422/src/benchflow/review/automatic.py +0 -226
  607. benchflow-0.7.11.dev2422/src/benchflow/review/config.py +0 -373
  608. benchflow-0.7.11.dev2422/src/benchflow/review/evidence.py +0 -757
  609. benchflow-0.7.11.dev2422/src/benchflow/review/evidence_runtime.py +0 -49
  610. benchflow-0.7.11.dev2422/src/benchflow/review/options.py +0 -83
  611. benchflow-0.7.11.dev2422/src/benchflow/review/outcome.py +0 -175
  612. benchflow-0.7.11.dev2422/src/benchflow/review/persistence.py +0 -215
  613. benchflow-0.7.11.dev2422/src/benchflow/review/preflight.py +0 -53
  614. benchflow-0.7.11.dev2422/src/benchflow/review/resume.py +0 -174
  615. benchflow-0.7.11.dev2422/src/benchflow/review/runner.py +0 -810
  616. benchflow-0.7.11.dev2422/src/benchflow/review/scoring.py +0 -119
  617. benchflow-0.7.11.dev2422/src/benchflow/review/wrapper.py +0 -415
  618. benchflow-0.7.11.dev2422/src/benchflow/rewards/README.md +0 -125
  619. benchflow-0.7.11.dev2422/src/benchflow/rewards/__init__.py +0 -49
  620. benchflow-0.7.11.dev2422/src/benchflow/rewards/builtins.py +0 -527
  621. benchflow-0.7.11.dev2422/src/benchflow/rewards/file_readers.py +0 -142
  622. benchflow-0.7.11.dev2422/src/benchflow/rewards/llm.py +0 -307
  623. benchflow-0.7.11.dev2422/src/benchflow/rewards/node.py +0 -164
  624. benchflow-0.7.11.dev2422/src/benchflow/rewards/protocol.py +0 -89
  625. benchflow-0.7.11.dev2422/src/benchflow/rewards/rubric_config.py +0 -287
  626. benchflow-0.7.11.dev2422/src/benchflow/rewards/validation.py +0 -674
  627. benchflow-0.7.11.dev2422/src/benchflow/rollout/__init__.py +0 -2885
  628. benchflow-0.7.11.dev2422/src/benchflow/rollout/_config.py +0 -451
  629. benchflow-0.7.11.dev2422/src/benchflow/rollout/_deadline.py +0 -178
  630. benchflow-0.7.11.dev2422/src/benchflow/rollout/_results.py +0 -622
  631. benchflow-0.7.11.dev2422/src/benchflow/rollout/_review.py +0 -191
  632. benchflow-0.7.11.dev2422/src/benchflow/rollout/_separate_verifier.py +0 -651
  633. benchflow-0.7.11.dev2422/src/benchflow/rollout/_setup.py +0 -589
  634. benchflow-0.7.11.dev2422/src/benchflow/rollout/_user_loop.py +0 -556
  635. benchflow-0.7.11.dev2422/src/benchflow/rollout/session_factory_runtime.py +0 -187
  636. benchflow-0.7.11.dev2422/src/benchflow/rollout/task_runtime.py +0 -293
  637. benchflow-0.7.11.dev2422/src/benchflow/rollout_branch.py +0 -222
  638. benchflow-0.7.11.dev2422/src/benchflow/rollout_planes.py +0 -257
  639. benchflow-0.7.11.dev2422/src/benchflow/runtime.py +0 -471
  640. benchflow-0.7.11.dev2422/src/benchflow/sandbox/_base.py +0 -498
  641. benchflow-0.7.11.dev2422/src/benchflow/sandbox/_cache_reclaim.py +0 -95
  642. benchflow-0.7.11.dev2422/src/benchflow/sandbox/_compose.py +0 -74
  643. benchflow-0.7.11.dev2422/src/benchflow/sandbox/_compose_files/docker-compose-base.yaml +0 -17
  644. benchflow-0.7.11.dev2422/src/benchflow/sandbox/_egress_denylist_proxy.py +0 -914
  645. benchflow-0.7.11.dev2422/src/benchflow/sandbox/_sdk_ops.py +0 -103
  646. benchflow-0.7.11.dev2422/src/benchflow/sandbox/agentcore.py +0 -1061
  647. benchflow-0.7.11.dev2422/src/benchflow/sandbox/agentcore_builder.py +0 -653
  648. benchflow-0.7.11.dev2422/src/benchflow/sandbox/agentcore_image.py +0 -199
  649. benchflow-0.7.11.dev2422/src/benchflow/sandbox/agentcore_provisioning.py +0 -362
  650. benchflow-0.7.11.dev2422/src/benchflow/sandbox/apple_container.py +0 -620
  651. benchflow-0.7.11.dev2422/src/benchflow/sandbox/daytona.py +0 -976
  652. benchflow-0.7.11.dev2422/src/benchflow/sandbox/daytona_dind.py +0 -850
  653. benchflow-0.7.11.dev2422/src/benchflow/sandbox/daytona_pty.py +0 -142
  654. benchflow-0.7.11.dev2422/src/benchflow/sandbox/daytona_reaper.py +0 -264
  655. benchflow-0.7.11.dev2422/src/benchflow/sandbox/daytona_strategies.py +0 -400
  656. benchflow-0.7.11.dev2422/src/benchflow/sandbox/docker.py +0 -958
  657. benchflow-0.7.11.dev2422/src/benchflow/sandbox/egress_denylist.py +0 -375
  658. benchflow-0.7.11.dev2422/src/benchflow/sandbox/lockdown.py +0 -1451
  659. benchflow-0.7.11.dev2422/src/benchflow/sandbox/metadata.py +0 -34
  660. benchflow-0.7.11.dev2422/src/benchflow/sandbox/modal_impl.py +0 -410
  661. benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/__init__.py +0 -39
  662. benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/_base.py +0 -282
  663. benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/agentcore.py +0 -413
  664. benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/apple.py +0 -135
  665. benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/daytona.py +0 -670
  666. benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/docker.py +0 -185
  667. benchflow-0.7.11.dev2422/src/benchflow/sandbox/protocol.py +0 -195
  668. benchflow-0.7.11.dev2422/src/benchflow/sandbox/providers.py +0 -149
  669. benchflow-0.7.11.dev2422/src/benchflow/sandbox/services.py +0 -119
  670. benchflow-0.7.11.dev2422/src/benchflow/sandbox/setup.py +0 -884
  671. benchflow-0.7.11.dev2422/src/benchflow/sandbox/snapshot.py +0 -107
  672. benchflow-0.7.11.dev2422/src/benchflow/sdk.py +0 -237
  673. benchflow-0.7.11.dev2422/src/benchflow/self_gen.py +0 -200
  674. benchflow-0.7.11.dev2422/src/benchflow/skill_eval/_core.py +0 -837
  675. benchflow-0.7.11.dev2422/src/benchflow/skill_eval/gepa_export.py +0 -195
  676. benchflow-0.7.11.dev2422/src/benchflow/task/__init__.py +0 -201
  677. benchflow-0.7.11.dev2422/src/benchflow/task/_document_normalize.py +0 -213
  678. benchflow-0.7.11.dev2422/src/benchflow/task/_document_parse.py +0 -598
  679. benchflow-0.7.11.dev2422/src/benchflow/task/_document_profiles.py +0 -156
  680. benchflow-0.7.11.dev2422/src/benchflow/task/acceptance_live.py +0 -522
  681. benchflow-0.7.11.dev2422/src/benchflow/task/config.py +0 -1142
  682. benchflow-0.7.11.dev2422/src/benchflow/task/env.py +0 -41
  683. benchflow-0.7.11.dev2422/src/benchflow/task/export.py +0 -547
  684. benchflow-0.7.11.dev2422/src/benchflow/task/imports.py +0 -238
  685. benchflow-0.7.11.dev2422/src/benchflow/task/package.py +0 -170
  686. benchflow-0.7.11.dev2422/src/benchflow/task/paths.py +0 -390
  687. benchflow-0.7.11.dev2422/src/benchflow/task/runtime_capabilities.py +0 -855
  688. benchflow-0.7.11.dev2422/src/benchflow/task/runtime_view.py +0 -170
  689. benchflow-0.7.11.dev2422/src/benchflow/task/task.py +0 -68
  690. benchflow-0.7.11.dev2422/src/benchflow/task/verifier.py +0 -167
  691. benchflow-0.7.11.dev2422/src/benchflow/task/verifier_core.py +0 -1236
  692. benchflow-0.7.11.dev2422/src/benchflow/task/verifier_document.py +0 -412
  693. benchflow-0.7.11.dev2422/src/benchflow/task/verifier_errors.py +0 -57
  694. benchflow-0.7.11.dev2422/src/benchflow/task/verifier_judge_inputs.py +0 -77
  695. benchflow-0.7.11.dev2422/src/benchflow/task/verifier_ors_episode.py +0 -300
  696. benchflow-0.7.11.dev2422/src/benchflow/task/verifier_reward_kit.py +0 -166
  697. benchflow-0.7.11.dev2422/src/benchflow/task/verifier_sandbox.py +0 -241
  698. benchflow-0.7.11.dev2422/src/benchflow/task/verifier_scan.py +0 -65
  699. benchflow-0.7.11.dev2422/src/benchflow/task/verifier_script_strategy.py +0 -87
  700. benchflow-0.7.11.dev2422/src/benchflow/templates/judge.py.tmpl +0 -213
  701. benchflow-0.7.11.dev2422/src/benchflow/traces/huggingface.py +0 -607
  702. benchflow-0.7.11.dev2422/src/benchflow/traces/parsers.py +0 -496
  703. benchflow-0.7.11.dev2422/src/benchflow/trajectories/_capture.py +0 -446
  704. benchflow-0.7.11.dev2422/src/benchflow/trajectories/_export_common.py +0 -116
  705. benchflow-0.7.11.dev2422/src/benchflow/trajectories/_llm_capture.py +0 -50
  706. benchflow-0.7.11.dev2422/src/benchflow/trajectories/_snapshot.py +0 -39
  707. benchflow-0.7.11.dev2422/src/benchflow/trajectories/export.py +0 -288
  708. benchflow-0.7.11.dev2422/src/benchflow/trajectories/export_adp.py +0 -264
  709. benchflow-0.7.11.dev2422/src/benchflow/trajectories/export_atif.py +0 -229
  710. benchflow-0.7.11.dev2422/src/benchflow/trajectories/export_prime_sft.py +0 -1335
  711. benchflow-0.7.11.dev2422/src/benchflow/trajectories/export_trl_sft.py +0 -651
  712. benchflow-0.7.11.dev2422/src/benchflow/trajectories/results.py +0 -717
  713. benchflow-0.7.11.dev2422/src/benchflow/trajectories/types.py +0 -693
  714. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/boot.js +0 -136
  715. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/catalog.js +0 -331
  716. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/detail.js +0 -784
  717. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/template.html +0 -50
  718. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/viewer.css +0 -353
  719. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/viewer.js +0 -67
  720. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/catalog.py +0 -90
  721. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/legacy.py +0 -760
  722. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/models.py +0 -449
  723. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/payload.py +0 -724
  724. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/render.py +0 -102
  725. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/server.py +0 -439
  726. benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/sources.py +0 -186
  727. benchflow-0.7.11.dev2422/tests/__init__.py +0 -1
  728. benchflow-0.7.11.dev2422/tests/acceptance_live_harness.py +0 -313
  729. benchflow-0.7.11.dev2422/tests/agents/__init__.py +0 -1
  730. benchflow-0.7.11.dev2422/tests/agents/test_codex_config.py +0 -117
  731. benchflow-0.7.11.dev2422/tests/agents/test_manifest_dirscan.py +0 -246
  732. benchflow-0.7.11.dev2422/tests/agents/test_manifest_loader.py +0 -153
  733. benchflow-0.7.11.dev2422/tests/agents/test_manifest_parity.py +0 -265
  734. benchflow-0.7.11.dev2422/tests/agents/test_manifest_wiring.py +0 -158
  735. benchflow-0.7.11.dev2422/tests/agents/test_namespace_shorthand.py +0 -82
  736. benchflow-0.7.11.dev2422/tests/agents/test_plugin_entry_points.py +0 -98
  737. benchflow-0.7.11.dev2422/tests/agents/test_protocol.py +0 -229
  738. benchflow-0.7.11.dev2422/tests/agents/test_remote_manifest_autoload.py +0 -109
  739. benchflow-0.7.11.dev2422/tests/conformance/README.md +0 -24
  740. benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/environment/Dockerfile +0 -7
  741. benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/environment/docker-compose.yaml +0 -3
  742. benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/environment/skills/conformance-writer/SKILL.md +0 -16
  743. benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/instruction.md +0 -7
  744. benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/solution/solve.sh +0 -4
  745. benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/task.md +0 -52
  746. benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/task.toml +0 -18
  747. benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/tests/test.sh +0 -13
  748. benchflow-0.7.11.dev2422/tests/conformance/conformance-results.json +0 -40
  749. benchflow-0.7.11.dev2422/tests/conformance/proof_multi_agent.py +0 -87
  750. benchflow-0.7.11.dev2422/tests/conformance/proof_snapshot.py +0 -85
  751. benchflow-0.7.11.dev2422/tests/conformance/run_conformance.py +0 -160
  752. benchflow-0.7.11.dev2422/tests/conformance/self_gen_smoke_skills/skill-creator/SKILL.md +0 -22
  753. benchflow-0.7.11.dev2422/tests/conftest.py +0 -121
  754. benchflow-0.7.11.dev2422/tests/continue_run/__init__.py +0 -0
  755. benchflow-0.7.11.dev2422/tests/continue_run/_helpers.py +0 -100
  756. benchflow-0.7.11.dev2422/tests/continue_run/test_batch.py +0 -111
  757. benchflow-0.7.11.dev2422/tests/continue_run/test_orchestrator.py +0 -303
  758. benchflow-0.7.11.dev2422/tests/continue_run/test_replay_proxy.py +0 -176
  759. benchflow-0.7.11.dev2422/tests/continue_run/test_run_folder.py +0 -97
  760. benchflow-0.7.11.dev2422/tests/environment/__init__.py +0 -0
  761. benchflow-0.7.11.dev2422/tests/environment/test_chibench_manifest.py +0 -65
  762. benchflow-0.7.11.dev2422/tests/environment/test_clawsbench_manifest.py +0 -41
  763. benchflow-0.7.11.dev2422/tests/environment/test_manifest.py +0 -171
  764. benchflow-0.7.11.dev2422/tests/environment/test_manifest_env.py +0 -479
  765. benchflow-0.7.11.dev2422/tests/environment/test_protocol.py +0 -57
  766. benchflow-0.7.11.dev2422/tests/environment/test_readiness.py +0 -76
  767. benchflow-0.7.11.dev2422/tests/examples/hello-world-task/environment/Dockerfile +0 -7
  768. benchflow-0.7.11.dev2422/tests/examples/hello-world-task/instruction.md +0 -5
  769. benchflow-0.7.11.dev2422/tests/examples/hello-world-task/solution/solve.sh +0 -2
  770. benchflow-0.7.11.dev2422/tests/examples/hello-world-task/task.md +0 -48
  771. benchflow-0.7.11.dev2422/tests/examples/hello-world-task/task.toml +0 -17
  772. benchflow-0.7.11.dev2422/tests/examples/hello-world-task/tests/test.sh +0 -13
  773. benchflow-0.7.11.dev2422/tests/examples/test_antigravity.sh +0 -69
  774. benchflow-0.7.11.dev2422/tests/examples/test_claude.sh +0 -191
  775. benchflow-0.7.11.dev2422/tests/examples/test_codex.sh +0 -238
  776. benchflow-0.7.11.dev2422/tests/examples/test_codex_custom_provider.sh +0 -145
  777. benchflow-0.7.11.dev2422/tests/examples/test_gemini.sh +0 -192
  778. benchflow-0.7.11.dev2422/tests/examples/test_openclaw.sh +0 -191
  779. benchflow-0.7.11.dev2422/tests/examples/traces/minimal-claude.jsonl +0 -3
  780. benchflow-0.7.11.dev2422/tests/examples/traces/minimal-opentraces.jsonl +0 -1
  781. benchflow-0.7.11.dev2422/tests/fixtures/digest/README.md +0 -9
  782. benchflow-0.7.11.dev2422/tests/fixtures/digest/alpha-task/environment/Dockerfile +0 -1
  783. benchflow-0.7.11.dev2422/tests/fixtures/digest/alpha-task/instruction.md +0 -3
  784. benchflow-0.7.11.dev2422/tests/fixtures/digest/alpha-task/task.toml +0 -4
  785. benchflow-0.7.11.dev2422/tests/fixtures/digest/alpha-task/tests/test.sh +0 -2
  786. benchflow-0.7.11.dev2422/tests/fixtures/digest/beta-task/data/empty.bin +0 -0
  787. benchflow-0.7.11.dev2422/tests/fixtures/digest/beta-task/data/unicode.txt +0 -1
  788. benchflow-0.7.11.dev2422/tests/fixtures/digest/beta-task/instruction.md +0 -1
  789. benchflow-0.7.11.dev2422/tests/fixtures/digest/beta-task/task.toml +0 -1
  790. benchflow-0.7.11.dev2422/tests/fixtures/digest/not-a-task/notes.txt +0 -1
  791. benchflow-0.7.11.dev2422/tests/fixtures/mock_acp_agent.py +0 -149
  792. benchflow-0.7.11.dev2422/tests/fixtures/mock_acp_agent_interleaved.py +0 -141
  793. benchflow-0.7.11.dev2422/tests/fixtures/mock_acp_agent_multi_turn.py +0 -163
  794. benchflow-0.7.11.dev2422/tests/fixtures/mock_openai_responses_server.py +0 -98
  795. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/Dockerfile +0 -18
  796. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/data/michigan_stations.txt +0 -79
  797. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/flood-detection/SKILL.md +0 -127
  798. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/nws-flood-thresholds/SKILL.md +0 -123
  799. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/usgs-data-download/SKILL.md +0 -120
  800. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/instruction.md +0 -1
  801. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/solution/solve.sh +0 -113
  802. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/task.toml +0 -28
  803. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test.sh +0 -6
  804. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test_outputs.py +0 -45
  805. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/Dockerfile +0 -17
  806. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/climate.csv +0 -17
  807. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/hydrology.csv +0 -17
  808. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/land_cover.csv +0 -17
  809. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/water_temperature.csv +0 -17
  810. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/contribution-analysis/SKILL.md +0 -93
  811. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/meteorology-driver-classification/SKILL.md +0 -78
  812. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/pca-decomposition/SKILL.md +0 -136
  813. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/trend-analysis/SKILL.md +0 -89
  814. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/instruction.md +0 -9
  815. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/solution/solve.sh +0 -82
  816. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/task.toml +0 -27
  817. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test.sh +0 -6
  818. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test_outputs.py +0 -32
  819. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/manifest.json +0 -76
  820. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/Dockerfile +0 -23
  821. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/r2r_simulator.py +0 -205
  822. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/finite-horizon-lqr/SKILL.md +0 -56
  823. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/integral-action-design/SKILL.md +0 -50
  824. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/mpc-horizon-tuning/SKILL.md +0 -48
  825. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/state-space-linearization/SKILL.md +0 -48
  826. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/system_config.json +0 -16
  827. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/instruction.md +0 -51
  828. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/solution/solve.sh +0 -237
  829. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/task.toml +0 -29
  830. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test.sh +0 -32
  831. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test_outputs.py +0 -266
  832. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/Dockerfile +0 -64
  833. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/generate_training_pcaps.py +0 -131
  834. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/local.rules +0 -2
  835. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/SKILL.md +0 -57
  836. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/scripts/summarize_http_requests.sh +0 -31
  837. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/SKILL.md +0 -57
  838. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/scripts/run_suricata_offline.sh +0 -27
  839. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-rules-basics/SKILL.md +0 -130
  840. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/suricata.yaml +0 -24
  841. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/instruction.md +0 -11
  842. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/solution/solve.sh +0 -80
  843. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/task.toml +0 -27
  844. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test.sh +0 -29
  845. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test_outputs.py +0 -324
  846. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/Dockerfile +0 -36
  847. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syz-extract-constants/SKILL.md +0 -101
  848. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzkaller-build-loop/SKILL.md +0 -78
  849. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzlang-ioctl-basics/SKILL.md +0 -97
  850. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/instruction.md +0 -25
  851. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/solution/solve.sh +0 -179
  852. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/task.toml +0 -29
  853. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test.sh +0 -6
  854. benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test_outputs.py +0 -212
  855. benchflow-0.7.11.dev2422/tests/integration/_consistency.py +0 -122
  856. benchflow-0.7.11.dev2422/tests/integration/agent_judge.py +0 -821
  857. benchflow-0.7.11.dev2422/tests/integration/check_adapter_evidence.py +0 -431
  858. benchflow-0.7.11.dev2422/tests/integration/check_hosted_env_evidence.py +0 -209
  859. benchflow-0.7.11.dev2422/tests/integration/check_results.py +0 -1336
  860. benchflow-0.7.11.dev2422/tests/integration/check_skillsbench_harbor_parity.py +0 -739
  861. benchflow-0.7.11.dev2422/tests/integration/check_trace_to_task_evidence.py +0 -353
  862. benchflow-0.7.11.dev2422/tests/integration/configs/antigravity.yaml +0 -23
  863. benchflow-0.7.11.dev2422/tests/integration/configs/claude-agent-acp.yaml +0 -23
  864. benchflow-0.7.11.dev2422/tests/integration/configs/codex-acp.yaml +0 -23
  865. benchflow-0.7.11.dev2422/tests/integration/configs/gemini.yaml +0 -23
  866. benchflow-0.7.11.dev2422/tests/integration/configs/harvey-lab-harness.yaml +0 -23
  867. benchflow-0.7.11.dev2422/tests/integration/configs/mimo.yaml +0 -32
  868. benchflow-0.7.11.dev2422/tests/integration/configs/openclaw.yaml +0 -23
  869. benchflow-0.7.11.dev2422/tests/integration/configs/opencode.yaml +0 -23
  870. benchflow-0.7.11.dev2422/tests/integration/configs/openhands.yaml +0 -23
  871. benchflow-0.7.11.dev2422/tests/integration/configs/pi-acp.yaml +0 -23
  872. benchflow-0.7.11.dev2422/tests/integration/deepagents_harness.py +0 -370
  873. benchflow-0.7.11.dev2422/tests/integration/rubric_checks.py +0 -1396
  874. benchflow-0.7.11.dev2422/tests/integration/run.sh +0 -210
  875. benchflow-0.7.11.dev2422/tests/integration/run_suite.py +0 -946
  876. benchflow-0.7.11.dev2422/tests/integration/scenarios.py +0 -364
  877. benchflow-0.7.11.dev2422/tests/integration/suites/release.yaml +0 -515
  878. benchflow-0.7.11.dev2422/tests/test_acceptance_evidence.py +0 -779
  879. benchflow-0.7.11.dev2422/tests/test_acceptance_live.py +0 -708
  880. benchflow-0.7.11.dev2422/tests/test_acceptance_live_execution.py +0 -645
  881. benchflow-0.7.11.dev2422/tests/test_acp.py +0 -2414
  882. benchflow-0.7.11.dev2422/tests/test_acp_buffered_timeout.py +0 -122
  883. benchflow-0.7.11.dev2422/tests/test_acp_capability_advertising.py +0 -184
  884. benchflow-0.7.11.dev2422/tests/test_acp_mcp_servers.py +0 -411
  885. benchflow-0.7.11.dev2422/tests/test_acp_model_config_dispatch.py +0 -271
  886. benchflow-0.7.11.dev2422/tests/test_acp_pinned_protocol_guard.py +0 -189
  887. benchflow-0.7.11.dev2422/tests/test_acp_setup_failure_propagation.py +0 -274
  888. benchflow-0.7.11.dev2422/tests/test_acp_timeout_evidence.py +0 -259
  889. benchflow-0.7.11.dev2422/tests/test_adapter_scripts.py +0 -243
  890. benchflow-0.7.11.dev2422/tests/test_adapters.py +0 -422
  891. benchflow-0.7.11.dev2422/tests/test_agent_antigravity.py +0 -552
  892. benchflow-0.7.11.dev2422/tests/test_agent_cli.py +0 -29
  893. benchflow-0.7.11.dev2422/tests/test_agent_egress_firewall.py +0 -80
  894. benchflow-0.7.11.dev2422/tests/test_agent_env_resolution.py +0 -132
  895. benchflow-0.7.11.dev2422/tests/test_agent_gemini_defaults.py +0 -91
  896. benchflow-0.7.11.dev2422/tests/test_agent_idle_timeout_cli.py +0 -188
  897. benchflow-0.7.11.dev2422/tests/test_agent_model_decouple.py +0 -113
  898. benchflow-0.7.11.dev2422/tests/test_agent_registry.py +0 -452
  899. benchflow-0.7.11.dev2422/tests/test_agent_router.py +0 -914
  900. benchflow-0.7.11.dev2422/tests/test_agent_router_cli_e2e.py +0 -425
  901. benchflow-0.7.11.dev2422/tests/test_agent_router_scaffold.py +0 -89
  902. benchflow-0.7.11.dev2422/tests/test_agent_setup.py +0 -882
  903. benchflow-0.7.11.dev2422/tests/test_agent_spec.py +0 -226
  904. benchflow-0.7.11.dev2422/tests/test_agentcore_builder.py +0 -818
  905. benchflow-0.7.11.dev2422/tests/test_agentcore_parallel.py +0 -1111
  906. benchflow-0.7.11.dev2422/tests/test_agentcore_reaper.py +0 -297
  907. benchflow-0.7.11.dev2422/tests/test_agentcore_sandbox.py +0 -679
  908. benchflow-0.7.11.dev2422/tests/test_agentcore_transport.py +0 -484
  909. benchflow-0.7.11.dev2422/tests/test_api_error_capture.py +0 -302
  910. benchflow-0.7.11.dev2422/tests/test_apple_container_sandbox.py +0 -578
  911. benchflow-0.7.11.dev2422/tests/test_automatic_review_scoring.py +0 -299
  912. benchflow-0.7.11.dev2422/tests/test_bare_model_provider.py +0 -437
  913. benchflow-0.7.11.dev2422/tests/test_base_install_imports.py +0 -108
  914. benchflow-0.7.11.dev2422/tests/test_bedrock_thinking.py +0 -243
  915. benchflow-0.7.11.dev2422/tests/test_benchflow_experiment_review_validator.py +0 -588
  916. benchflow-0.7.11.dev2422/tests/test_benchmark_repos_resolve_repo_path.py +0 -58
  917. benchflow-0.7.11.dev2422/tests/test_branch.py +0 -89
  918. benchflow-0.7.11.dev2422/tests/test_build_context_stage.py +0 -73
  919. benchflow-0.7.11.dev2422/tests/test_build_review_pack.py +0 -757
  920. benchflow-0.7.11.dev2422/tests/test_capture_trajectory.py +0 -899
  921. benchflow-0.7.11.dev2422/tests/test_check_skillsbench_harbor_parity.py +0 -429
  922. benchflow-0.7.11.dev2422/tests/test_clawsbench_slice.py +0 -52
  923. benchflow-0.7.11.dev2422/tests/test_cli_adopt_aliases.py +0 -324
  924. benchflow-0.7.11.dev2422/tests/test_cli_arg_validation.py +0 -463
  925. benchflow-0.7.11.dev2422/tests/test_cli_daytona.py +0 -147
  926. benchflow-0.7.11.dev2422/tests/test_cli_docs_drift.py +0 -282
  927. benchflow-0.7.11.dev2422/tests/test_cli_edge_case_hardening.py +0 -929
  928. benchflow-0.7.11.dev2422/tests/test_cli_hub_env.py +0 -177
  929. benchflow-0.7.11.dev2422/tests/test_cli_live_progress.py +0 -1253
  930. benchflow-0.7.11.dev2422/tests/test_cli_misc.py +0 -178
  931. benchflow-0.7.11.dev2422/tests/test_codex_bare_model_id.py +0 -113
  932. benchflow-0.7.11.dev2422/tests/test_codex_review.py +0 -475
  933. benchflow-0.7.11.dev2422/tests/test_codex_self_write_auth.py +0 -59
  934. benchflow-0.7.11.dev2422/tests/test_config_override.py +0 -250
  935. benchflow-0.7.11.dev2422/tests/test_config_redaction.py +0 -164
  936. benchflow-0.7.11.dev2422/tests/test_connect_as_env.py +0 -196
  937. benchflow-0.7.11.dev2422/tests/test_console_error_truncation.py +0 -84
  938. benchflow-0.7.11.dev2422/tests/test_console_progress.py +0 -164
  939. benchflow-0.7.11.dev2422/tests/test_continuallearningbench_adapter.py +0 -90
  940. benchflow-0.7.11.dev2422/tests/test_dataset_registry.py +0 -596
  941. benchflow-0.7.11.dev2422/tests/test_daytona_command_polling.py +0 -96
  942. benchflow-0.7.11.dev2422/tests/test_daytona_dind_compose_up.py +0 -232
  943. benchflow-0.7.11.dev2422/tests/test_daytona_download.py +0 -254
  944. benchflow-0.7.11.dev2422/tests/test_daytona_litellm_runtime.py +0 -121
  945. benchflow-0.7.11.dev2422/tests/test_daytona_poll_deadline.py +0 -222
  946. benchflow-0.7.11.dev2422/tests/test_daytona_reap.py +0 -573
  947. benchflow-0.7.11.dev2422/tests/test_deepagents_agent.py +0 -274
  948. benchflow-0.7.11.dev2422/tests/test_diagnostics.py +0 -151
  949. benchflow-0.7.11.dev2422/tests/test_docker_prune_scoping.py +0 -153
  950. benchflow-0.7.11.dev2422/tests/test_docker_uploads.py +0 -63
  951. benchflow-0.7.11.dev2422/tests/test_docs_examples.py +0 -121
  952. benchflow-0.7.11.dev2422/tests/test_egress_connect_authority.py +0 -417
  953. benchflow-0.7.11.dev2422/tests/test_egress_denylist.py +0 -580
  954. benchflow-0.7.11.dev2422/tests/test_egress_denylist_integration.py +0 -316
  955. benchflow-0.7.11.dev2422/tests/test_egress_dynamic_certs.py +0 -115
  956. benchflow-0.7.11.dev2422/tests/test_egress_model_gateway.py +0 -146
  957. benchflow-0.7.11.dev2422/tests/test_eng50_capabilities.py +0 -164
  958. benchflow-0.7.11.dev2422/tests/test_env_registry.py +0 -297
  959. benchflow-0.7.11.dev2422/tests/test_env_setup.py +0 -550
  960. benchflow-0.7.11.dev2422/tests/test_environment_manifest_controls.py +0 -299
  961. benchflow-0.7.11.dev2422/tests/test_eval_artifact_cli.py +0 -535
  962. benchflow-0.7.11.dev2422/tests/test_eval_filters_applied.py +0 -158
  963. benchflow-0.7.11.dev2422/tests/test_eval_lift.py +0 -292
  964. benchflow-0.7.11.dev2422/tests/test_eval_sharding.py +0 -211
  965. benchflow-0.7.11.dev2422/tests/test_eval_single_task_summary.py +0 -160
  966. benchflow-0.7.11.dev2422/tests/test_eval_source_provenance.py +0 -776
  967. benchflow-0.7.11.dev2422/tests/test_eval_worker_retry.py +0 -76
  968. benchflow-0.7.11.dev2422/tests/test_eval_zero_task_guard.py +0 -116
  969. benchflow-0.7.11.dev2422/tests/test_evaluation_environment_manifest.py +0 -205
  970. benchflow-0.7.11.dev2422/tests/test_exclude_tasks.py +0 -43
  971. benchflow-0.7.11.dev2422/tests/test_filter_credentialed_cells.py +0 -262
  972. benchflow-0.7.11.dev2422/tests/test_harvey_lab_shim.py +0 -93
  973. benchflow-0.7.11.dev2422/tests/test_hilbench_adapter.py +0 -104
  974. benchflow-0.7.11.dev2422/tests/test_hosted_env.py +0 -334
  975. benchflow-0.7.11.dev2422/tests/test_hosted_env_rollout_contract.py +0 -399
  976. benchflow-0.7.11.dev2422/tests/test_hosted_search_policy.py +0 -858
  977. benchflow-0.7.11.dev2422/tests/test_hub_harbor_registry.py +0 -328
  978. benchflow-0.7.11.dev2422/tests/test_inbound_adapter_manifest.py +0 -213
  979. benchflow-0.7.11.dev2422/tests/test_inbound_adapters.py +0 -307
  980. benchflow-0.7.11.dev2422/tests/test_integration_agent_judge.py +0 -525
  981. benchflow-0.7.11.dev2422/tests/test_integration_check_results.py +0 -2694
  982. benchflow-0.7.11.dev2422/tests/test_integration_consistency.py +0 -142
  983. benchflow-0.7.11.dev2422/tests/test_integration_matrix.py +0 -722
  984. benchflow-0.7.11.dev2422/tests/test_integration_provider_selection.py +0 -57
  985. benchflow-0.7.11.dev2422/tests/test_integration_run_suite.py +0 -884
  986. benchflow-0.7.11.dev2422/tests/test_integration_suite.py +0 -494
  987. benchflow-0.7.11.dev2422/tests/test_internet_policy.py +0 -435
  988. benchflow-0.7.11.dev2422/tests/test_job.py +0 -930
  989. benchflow-0.7.11.dev2422/tests/test_job_sequential_shared.py +0 -597
  990. benchflow-0.7.11.dev2422/tests/test_job_sequential_shared_resume.py +0 -314
  991. benchflow-0.7.11.dev2422/tests/test_judge_robustness.py +0 -691
  992. benchflow-0.7.11.dev2422/tests/test_judge_symlink_ingestion.py +0 -64
  993. benchflow-0.7.11.dev2422/tests/test_learner_skills.py +0 -131
  994. benchflow-0.7.11.dev2422/tests/test_learner_skills_traversal.py +0 -91
  995. benchflow-0.7.11.dev2422/tests/test_learner_store.py +0 -257
  996. benchflow-0.7.11.dev2422/tests/test_learner_store_persistence.py +0 -138
  997. benchflow-0.7.11.dev2422/tests/test_litellm_config.py +0 -358
  998. benchflow-0.7.11.dev2422/tests/test_litellm_gemini_passthrough_patch.py +0 -63
  999. benchflow-0.7.11.dev2422/tests/test_litellm_hardening.py +0 -1125
  1000. benchflow-0.7.11.dev2422/tests/test_litellm_logging.py +0 -704
  1001. benchflow-0.7.11.dev2422/tests/test_litellm_model_via_env_generic.py +0 -87
  1002. benchflow-0.7.11.dev2422/tests/test_litellm_reasoning_passthrough.py +0 -60
  1003. benchflow-0.7.11.dev2422/tests/test_litellm_runtime.py +0 -853
  1004. benchflow-0.7.11.dev2422/tests/test_litellm_smoke.py +0 -160
  1005. benchflow-0.7.11.dev2422/tests/test_live_llm_trajectory.py +0 -661
  1006. benchflow-0.7.11.dev2422/tests/test_llm_judge.py +0 -943
  1007. benchflow-0.7.11.dev2422/tests/test_llm_judge_event_tags.py +0 -211
  1008. benchflow-0.7.11.dev2422/tests/test_llm_judge_verifier.py +0 -734
  1009. benchflow-0.7.11.dev2422/tests/test_loop_strategies.py +0 -576
  1010. benchflow-0.7.11.dev2422/tests/test_loop_summary.py +0 -153
  1011. benchflow-0.7.11.dev2422/tests/test_loop_sweep.py +0 -512
  1012. benchflow-0.7.11.dev2422/tests/test_memory_scorer.py +0 -386
  1013. benchflow-0.7.11.dev2422/tests/test_metrics.py +0 -454
  1014. benchflow-0.7.11.dev2422/tests/test_mle_bench_adapter.py +0 -519
  1015. benchflow-0.7.11.dev2422/tests/test_mock_openai_responses_server.py +0 -73
  1016. benchflow-0.7.11.dev2422/tests/test_monitor_scaffold.py +0 -133
  1017. benchflow-0.7.11.dev2422/tests/test_native_acp_usage.py +0 -276
  1018. benchflow-0.7.11.dev2422/tests/test_network_denylist_config.py +0 -305
  1019. benchflow-0.7.11.dev2422/tests/test_no_cross_provider_fallback.py +0 -84
  1020. benchflow-0.7.11.dev2422/tests/test_notification_order_real.py +0 -126
  1021. benchflow-0.7.11.dev2422/tests/test_opencode_family_proxy_tracking.py +0 -152
  1022. benchflow-0.7.11.dev2422/tests/test_oracle.py +0 -162
  1023. benchflow-0.7.11.dev2422/tests/test_oracle_chokepoint.py +0 -1194
  1024. benchflow-0.7.11.dev2422/tests/test_paths_safe.py +0 -102
  1025. benchflow-0.7.11.dev2422/tests/test_paths_symlink_helpers.py +0 -94
  1026. benchflow-0.7.11.dev2422/tests/test_pi_acp_launcher.py +0 -405
  1027. benchflow-0.7.11.dev2422/tests/test_pi_acp_proxy_routing.py +0 -46
  1028. benchflow-0.7.11.dev2422/tests/test_process.py +0 -1096
  1029. benchflow-0.7.11.dev2422/tests/test_project_skills_layout.py +0 -20
  1030. benchflow-0.7.11.dev2422/tests/test_provider_auth_detection.py +0 -412
  1031. benchflow-0.7.11.dev2422/tests/test_providers.py +0 -554
  1032. benchflow-0.7.11.dev2422/tests/test_publish_azure_blob.py +0 -777
  1033. benchflow-0.7.11.dev2422/tests/test_publish_huggingface.py +0 -147
  1034. benchflow-0.7.11.dev2422/tests/test_redacted_snapshot.py +0 -222
  1035. benchflow-0.7.11.dev2422/tests/test_reexport.py +0 -101
  1036. benchflow-0.7.11.dev2422/tests/test_registry_invariants.py +0 -551
  1037. benchflow-0.7.11.dev2422/tests/test_release_hardening_r5.py +0 -103
  1038. benchflow-0.7.11.dev2422/tests/test_release_version.py +0 -132
  1039. benchflow-0.7.11.dev2422/tests/test_release_workflow_wiring.py +0 -423
  1040. benchflow-0.7.11.dev2422/tests/test_resolve_env_helpers.py +0 -1210
  1041. benchflow-0.7.11.dev2422/tests/test_review_automatic.py +0 -380
  1042. benchflow-0.7.11.dev2422/tests/test_review_boundaries.py +0 -607
  1043. benchflow-0.7.11.dev2422/tests/test_review_evidence.py +0 -640
  1044. benchflow-0.7.11.dev2422/tests/test_review_evidence_runtime.py +0 -107
  1045. benchflow-0.7.11.dev2422/tests/test_review_lifecycle.py +0 -126
  1046. benchflow-0.7.11.dev2422/tests/test_review_resume.py +0 -393
  1047. benchflow-0.7.11.dev2422/tests/test_review_rubric.py +0 -850
  1048. benchflow-0.7.11.dev2422/tests/test_review_runtime.py +0 -892
  1049. benchflow-0.7.11.dev2422/tests/test_review_runtime_automatic.py +0 -300
  1050. benchflow-0.7.11.dev2422/tests/test_review_snapshot.py +0 -102
  1051. benchflow-0.7.11.dev2422/tests/test_reviewer_options.py +0 -425
  1052. benchflow-0.7.11.dev2422/tests/test_reward_lenient.py +0 -151
  1053. benchflow-0.7.11.dev2422/tests/test_reward_node.py +0 -145
  1054. benchflow-0.7.11.dev2422/tests/test_reward_range.py +0 -284
  1055. benchflow-0.7.11.dev2422/tests/test_reward_unified_contract.py +0 -171
  1056. benchflow-0.7.11.dev2422/tests/test_rewards.py +0 -442
  1057. benchflow-0.7.11.dev2422/tests/test_rewards_jsonl.py +0 -174
  1058. benchflow-0.7.11.dev2422/tests/test_rollout_architecture.py +0 -58
  1059. benchflow-0.7.11.dev2422/tests/test_rollout_branch.py +0 -451
  1060. benchflow-0.7.11.dev2422/tests/test_rollout_config_path_coercion.py +0 -96
  1061. benchflow-0.7.11.dev2422/tests/test_rollout_environment.py +0 -50
  1062. benchflow-0.7.11.dev2422/tests/test_rollout_hard_deadline.py +0 -200
  1063. benchflow-0.7.11.dev2422/tests/test_rollout_import_no_side_effects.py +0 -194
  1064. benchflow-0.7.11.dev2422/tests/test_rollout_on_ask_user_wiring.py +0 -299
  1065. benchflow-0.7.11.dev2422/tests/test_rollout_planes_contract.py +0 -121
  1066. benchflow-0.7.11.dev2422/tests/test_rollout_probe_sandbox_health.py +0 -101
  1067. benchflow-0.7.11.dev2422/tests/test_rollout_session_factory_dispatch.py +0 -301
  1068. benchflow-0.7.11.dev2422/tests/test_rollout_setup_commands.py +0 -145
  1069. benchflow-0.7.11.dev2422/tests/test_rollout_upload.py +0 -1038
  1070. benchflow-0.7.11.dev2422/tests/test_root_helpers_isolated.py +0 -175
  1071. benchflow-0.7.11.dev2422/tests/test_rubric_checks.py +0 -415
  1072. benchflow-0.7.11.dev2422/tests/test_rubric_config.py +0 -371
  1073. benchflow-0.7.11.dev2422/tests/test_runtime.py +0 -170
  1074. benchflow-0.7.11.dev2422/tests/test_runtime_capabilities.py +0 -1129
  1075. benchflow-0.7.11.dev2422/tests/test_runtime_config_wired.py +0 -210
  1076. benchflow-0.7.11.dev2422/tests/test_runtime_live_sandbox.py +0 -257
  1077. benchflow-0.7.11.dev2422/tests/test_sandbox.py +0 -602
  1078. benchflow-0.7.11.dev2422/tests/test_sandbox_exec_secret_handling.py +0 -316
  1079. benchflow-0.7.11.dev2422/tests/test_sandbox_hardening.py +0 -1830
  1080. benchflow-0.7.11.dev2422/tests/test_sandbox_isolation_copy_traversal.py +0 -102
  1081. benchflow-0.7.11.dev2422/tests/test_sandbox_live_process.py +0 -224
  1082. benchflow-0.7.11.dev2422/tests/test_sandbox_multi_service.py +0 -800
  1083. benchflow-0.7.11.dev2422/tests/test_sandbox_prebuilt_validation.py +0 -157
  1084. benchflow-0.7.11.dev2422/tests/test_sandbox_protocol.py +0 -222
  1085. benchflow-0.7.11.dev2422/tests/test_sandbox_provider_registry_drift.py +0 -119
  1086. benchflow-0.7.11.dev2422/tests/test_sandbox_setup.py +0 -250
  1087. benchflow-0.7.11.dev2422/tests/test_sandbox_snapshot_contract.py +0 -251
  1088. benchflow-0.7.11.dev2422/tests/test_sandbox_upload_symlink.py +0 -221
  1089. benchflow-0.7.11.dev2422/tests/test_sandbox_verifier_workspace.py +0 -179
  1090. benchflow-0.7.11.dev2422/tests/test_scene.py +0 -102
  1091. benchflow-0.7.11.dev2422/tests/test_scene_outbox_trial.py +0 -432
  1092. benchflow-0.7.11.dev2422/tests/test_scene_parallel_group.py +0 -51
  1093. benchflow-0.7.11.dev2422/tests/test_scene_result_aggregation.py +0 -189
  1094. benchflow-0.7.11.dev2422/tests/test_scoring.py +0 -317
  1095. benchflow-0.7.11.dev2422/tests/test_sdk_internals.py +0 -926
  1096. benchflow-0.7.11.dev2422/tests/test_sdk_lockdown.py +0 -1012
  1097. benchflow-0.7.11.dev2422/tests/test_sdk_run_alias.py +0 -81
  1098. benchflow-0.7.11.dev2422/tests/test_sealed_channel_container.py +0 -264
  1099. benchflow-0.7.11.dev2422/tests/test_self_gen_cli.py +0 -59
  1100. benchflow-0.7.11.dev2422/tests/test_self_gen_export_error_channel.py +0 -202
  1101. benchflow-0.7.11.dev2422/tests/test_self_gen_export_failures.py +0 -195
  1102. benchflow-0.7.11.dev2422/tests/test_self_gen_orchestration.py +0 -408
  1103. benchflow-0.7.11.dev2422/tests/test_separate_verifier.py +0 -1121
  1104. benchflow-0.7.11.dev2422/tests/test_session_factory_runtime.py +0 -380
  1105. benchflow-0.7.11.dev2422/tests/test_session_request_permission_dispatch.py +0 -294
  1106. benchflow-0.7.11.dev2422/tests/test_skill_eval.py +0 -647
  1107. benchflow-0.7.11.dev2422/tests/test_skill_eval_dryrun.py +0 -399
  1108. benchflow-0.7.11.dev2422/tests/test_skill_eval_integration.py +0 -356
  1109. benchflow-0.7.11.dev2422/tests/test_skill_eval_sweep.py +0 -461
  1110. benchflow-0.7.11.dev2422/tests/test_skill_eval_traversal.py +0 -135
  1111. benchflow-0.7.11.dev2422/tests/test_skill_invocation_artifacts.py +0 -397
  1112. benchflow-0.7.11.dev2422/tests/test_skill_policy.py +0 -234
  1113. benchflow-0.7.11.dev2422/tests/test_skillevaluator_integration.py +0 -960
  1114. benchflow-0.7.11.dev2422/tests/test_skills.py +0 -138
  1115. benchflow-0.7.11.dev2422/tests/test_skills_dir_agent_home_link.py +0 -146
  1116. benchflow-0.7.11.dev2422/tests/test_skillsbench_conversion_conformance.py +0 -116
  1117. benchflow-0.7.11.dev2422/tests/test_skillsbench_harbor_run_suite.py +0 -103
  1118. benchflow-0.7.11.dev2422/tests/test_smoke.py +0 -245
  1119. benchflow-0.7.11.dev2422/tests/test_smoke_wiring.py +0 -208
  1120. benchflow-0.7.11.dev2422/tests/test_source_adapters.py +0 -1190
  1121. benchflow-0.7.11.dev2422/tests/test_subscription_auth.py +0 -562
  1122. benchflow-0.7.11.dev2422/tests/test_task_check_eval_consistency.py +0 -500
  1123. benchflow-0.7.11.dev2422/tests/test_task_config.py +0 -483
  1124. benchflow-0.7.11.dev2422/tests/test_task_digest.py +0 -185
  1125. benchflow-0.7.11.dev2422/tests/test_task_document.py +0 -1389
  1126. benchflow-0.7.11.dev2422/tests/test_task_download.py +0 -898
  1127. benchflow-0.7.11.dev2422/tests/test_task_export.py +0 -586
  1128. benchflow-0.7.11.dev2422/tests/test_task_output_format.py +0 -67
  1129. benchflow-0.7.11.dev2422/tests/test_task_package.py +0 -452
  1130. benchflow-0.7.11.dev2422/tests/test_task_runtime_primitive.py +0 -379
  1131. benchflow-0.7.11.dev2422/tests/test_tasks.py +0 -463
  1132. benchflow-0.7.11.dev2422/tests/test_token_usage_normalization.py +0 -158
  1133. benchflow-0.7.11.dev2422/tests/test_tool_call_raw_io.py +0 -344
  1134. benchflow-0.7.11.dev2422/tests/test_trace_import_cli.py +0 -112
  1135. benchflow-0.7.11.dev2422/tests/test_trace_task_gen_traversal.py +0 -123
  1136. benchflow-0.7.11.dev2422/tests/test_trace_to_task_evidence.py +0 -165
  1137. benchflow-0.7.11.dev2422/tests/test_traces_huggingface.py +0 -130
  1138. benchflow-0.7.11.dev2422/tests/test_traces_parsers.py +0 -470
  1139. benchflow-0.7.11.dev2422/tests/test_traces_task_gen.py +0 -732
  1140. benchflow-0.7.11.dev2422/tests/test_train_cli.py +0 -2260
  1141. benchflow-0.7.11.dev2422/tests/test_train_mode_artifact_emission.py +0 -1412
  1142. benchflow-0.7.11.dev2422/tests/test_train_trl_cli.py +0 -586
  1143. benchflow-0.7.11.dev2422/tests/test_traj_report.py +0 -526
  1144. benchflow-0.7.11.dev2422/tests/test_traj_staging_phases.py +0 -242
  1145. benchflow-0.7.11.dev2422/tests/test_traj_tui.py +0 -185
  1146. benchflow-0.7.11.dev2422/tests/test_traj_upload_cli.py +0 -1407
  1147. benchflow-0.7.11.dev2422/tests/test_traj_upload_skill.py +0 -105
  1148. benchflow-0.7.11.dev2422/tests/test_traj_workspace.py +0 -418
  1149. benchflow-0.7.11.dev2422/tests/test_trajectory_integration.py +0 -261
  1150. benchflow-0.7.11.dev2422/tests/test_trajectory_streaming.py +0 -552
  1151. benchflow-0.7.11.dev2422/tests/test_trajectory_upload_layout.py +0 -77
  1152. benchflow-0.7.11.dev2422/tests/test_trajectory_upload_service.py +0 -1934
  1153. benchflow-0.7.11.dev2422/tests/test_trial_agent_timeout_verify.py +0 -92
  1154. benchflow-0.7.11.dev2422/tests/test_trial_install_agent_timeout.py +0 -361
  1155. benchflow-0.7.11.dev2422/tests/test_trial_litellm_runtime.py +0 -119
  1156. benchflow-0.7.11.dev2422/tests/test_trl_integration.py +0 -374
  1157. benchflow-0.7.11.dev2422/tests/test_usage_litellm.py +0 -315
  1158. benchflow-0.7.11.dev2422/tests/test_usage_required.py +0 -70
  1159. benchflow-0.7.11.dev2422/tests/test_usage_tracking.py +0 -229
  1160. benchflow-0.7.11.dev2422/tests/test_user.py +0 -1216
  1161. benchflow-0.7.11.dev2422/tests/test_v06_guard_ports.py +0 -160
  1162. benchflow-0.7.11.dev2422/tests/test_verifier_document.py +0 -342
  1163. benchflow-0.7.11.dev2422/tests/test_verifier_multi_container.py +0 -331
  1164. benchflow-0.7.11.dev2422/tests/test_verifier_output.py +0 -355
  1165. benchflow-0.7.11.dev2422/tests/test_verifier_output_freshness.py +0 -114
  1166. benchflow-0.7.11.dev2422/tests/test_verifier_strategies.py +0 -505
  1167. benchflow-0.7.11.dev2422/tests/test_verifier_user_config.py +0 -94
  1168. benchflow-0.7.11.dev2422/tests/test_verifier_wedge_retry.py +0 -114
  1169. benchflow-0.7.11.dev2422/tests/test_verify.py +0 -1226
  1170. benchflow-0.7.11.dev2422/tests/test_viewer_confirm.py +0 -679
  1171. benchflow-0.7.11.dev2422/tests/test_workflow_action_pinning.py +0 -121
  1172. benchflow-0.7.11.dev2422/tests/test_yaml_config.py +0 -678
  1173. benchflow-0.7.11.dev2422/tests/trajectories/__init__.py +0 -0
  1174. benchflow-0.7.11.dev2422/tests/trajectories/test_export.py +0 -157
  1175. benchflow-0.7.11.dev2422/tests/trajectories/test_export_adp.py +0 -371
  1176. benchflow-0.7.11.dev2422/tests/trajectories/test_export_atif.py +0 -275
  1177. benchflow-0.7.11.dev2422/tests/trajectories/test_export_common.py +0 -91
  1178. benchflow-0.7.11.dev2422/tests/trajectories/test_export_nan_handling.py +0 -101
  1179. benchflow-0.7.11.dev2422/tests/trajectories/test_export_prime_sft.py +0 -1221
  1180. benchflow-0.7.11.dev2422/tests/trajectories/test_redaction.py +0 -1134
  1181. benchflow-0.7.11.dev2422/tests/trajectories/test_step_granularity.py +0 -201
  1182. benchflow-0.7.11.dev2422/tests/trajectories/test_tree.py +0 -159
  1183. benchflow-0.7.11.dev2422/tests/trajectories/test_viewer_acp_renderer.py +0 -922
  1184. benchflow-0.7.11.dev2422/tests/trajectories/test_viewer_browser.py +0 -847
  1185. benchflow-0.7.11.dev2422/tests/trajectories/test_viewer_rubric.py +0 -227
  1186. benchflow-0.7.11.dev2422/tests/trajectories/test_viewer_theme.py +0 -59
  1187. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/LICENSE +0 -0
  1188. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_dotenv.py +0 -0
  1189. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_paths.py +0 -0
  1190. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/__init__.py +0 -0
  1191. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/build_context_stage.py +0 -0
  1192. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/content_address.py +0 -0
  1193. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/json_safe.py +0 -0
  1194. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/live_activity.py +0 -0
  1195. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/reward_events.py +0 -0
  1196. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/source_provenance.py +0 -0
  1197. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/task_authoring/_evidence_paths.py +0 -0
  1198. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/task_authoring/acceptance_evidence.py +0 -0
  1199. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/text.py +0 -0
  1200. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/acp/timeout_cleanup.py +0 -0
  1201. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/_toolathlon_container.py +0 -0
  1202. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/_toolathlon_services.py +0 -0
  1203. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/inspect_ai.py +0 -0
  1204. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/ors.py +0 -0
  1205. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/resources/__init__.py +0 -0
  1206. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/resources/mcp_atlas_bridge.py +0 -0
  1207. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/source.py +0 -0
  1208. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/agent_router_guide.py +0 -0
  1209. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/agent_router_parity.py +0 -0
  1210. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/agents/protocol.py +0 -0
  1211. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/cli/__init__.py +0 -0
  1212. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/cli/_traj_tui.py +0 -0
  1213. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/cli/_traj_upload_ui.py +0 -0
  1214. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/cli/environment.py +0 -0
  1215. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/cli/monitor.py +0 -0
  1216. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/continue_run/__init__.py +0 -0
  1217. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/continue_run/batch.py +0 -0
  1218. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/continue_run/replay_proxy.py +0 -0
  1219. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/demo_task/environment/Dockerfile +0 -0
  1220. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/demo_task/instruction.md +0 -0
  1221. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/demo_task/task.md +0 -0
  1222. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/demo_task/task.toml +0 -0
  1223. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/demo_task/tests/test.sh +0 -0
  1224. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/environment/__init__.py +0 -0
  1225. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/environment/_registry/env0@outage.toml +0 -0
  1226. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/environment/_registry/env0@prod.toml +0 -0
  1227. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/environment/manifest.py +0 -0
  1228. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/eval_lift.py +0 -0
  1229. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/experimental/__init__.py +0 -0
  1230. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/experimental/mcp/__init__.py +0 -0
  1231. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/integrations/__init__.py +0 -0
  1232. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/integrations/trl/__init__.py +0 -0
  1233. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/learner_store.py +0 -0
  1234. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/loop_strategies.py +0 -0
  1235. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/loop_sweep.py +0 -0
  1236. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/providers/__init__.py +0 -0
  1237. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/__init__.py +0 -0
  1238. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/_progress.py +0 -0
  1239. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/azure_blob.py +0 -0
  1240. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/broker.py +0 -0
  1241. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/redact.py +0 -0
  1242. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/traj_report.py +0 -0
  1243. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/py.typed +0 -0
  1244. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/review/__init__.py +0 -0
  1245. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/review/default-rubric.json +0 -0
  1246. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/review/prompts.py +0 -0
  1247. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/rewards/events.py +0 -0
  1248. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/rewards/memory_scorer.py +0 -0
  1249. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/rewards/rubric.py +0 -0
  1250. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/rollout/_skills.py +0 -0
  1251. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/rollout/_usage.py +0 -0
  1252. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/__init__.py +0 -0
  1253. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/_compose_files/docker-compose-build.yaml +0 -0
  1254. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/_compose_files/docker-compose-net-admin.yaml +0 -0
  1255. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/_compose_files/docker-compose-no-network.yaml +0 -0
  1256. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/_compose_files/docker-compose-prebuilt.yaml +0 -0
  1257. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/agentcore_reaper.py +0 -0
  1258. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/agentcore_sealed.py +0 -0
  1259. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/user.py +0 -0
  1260. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/scenes.py +0 -0
  1261. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/skill_eval/__init__.py +0 -0
  1262. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/skill_eval/schema.py +0 -0
  1263. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/skill_policy.py +0 -0
  1264. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/skills.py +0 -0
  1265. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/_document_evidence.py +0 -0
  1266. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/acceptance_live_model.py +0 -0
  1267. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/acceptance_live_report.py +0 -0
  1268. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/acceptance_live_validation.py +0 -0
  1269. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/discovery.py +0 -0
  1270. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/document.py +0 -0
  1271. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/output_format.py +0 -0
  1272. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/prompts.py +0 -0
  1273. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/templates/__init__.py +0 -0
  1274. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/templates/test.sh.tmpl +0 -0
  1275. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/traces/__init__.py +0 -0
  1276. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/traces/local.py +0 -0
  1277. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/traces/models.py +0 -0
  1278. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/traces/task_gen.py +0 -0
  1279. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/training/__init__.py +0 -0
  1280. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/training/backends/__init__.py +0 -0
  1281. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/training/backends/prime_rl.py +0 -0
  1282. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/training/run_manifest.py +0 -0
  1283. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/__init__.py +0 -0
  1284. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/call_purpose.py +0 -0
  1285. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/metrics.py +0 -0
  1286. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/sessions.py +0 -0
  1287. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/tree.py +0 -0
  1288. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/trl_sft_tokenization.py +0 -0
  1289. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/__init__.py +0 -0
  1290. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/__main__.py +0 -0
  1291. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/fonts/OFL-google-sans-code.txt +0 -0
  1292. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/fonts/google-sans-code-400-latin.woff2 +0 -0
  1293. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/fonts/google-sans-code-600-latin.woff2 +0 -0
  1294. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/theme.css +0 -0
  1295. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/theme.js +0 -0
  1296. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/vendor/LICENSE.highlight.js +0 -0
  1297. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/vendor/highlight.min.js +0 -0
  1298. {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/usage_tracking.py +0 -0
@@ -0,0 +1,198 @@
1
+ # Byte-compiled / optimized / DLL files
2
+ __pycache__/
3
+ *.py[cod]
4
+ *$py.class
5
+
6
+ # C extensions
7
+ *.so
8
+
9
+ # Distribution / packaging
10
+ .Python
11
+ build/
12
+ develop-eggs/
13
+ dist/
14
+ downloads/
15
+ eggs/
16
+ .eggs/
17
+ lib/
18
+ lib64/
19
+ parts/
20
+ sdist/
21
+ var/
22
+ wheels/
23
+ share/python-wheels/
24
+ *.egg-info/
25
+ .installed.cfg
26
+ *.egg
27
+ MANIFEST
28
+
29
+ # PyInstaller
30
+ # Usually these files are written by a python script from a template
31
+ # before PyInstaller builds the exe, so as to inject date/other infos into it.
32
+ *.manifest
33
+ *.spec
34
+
35
+ # Installer logs
36
+ pip-log.txt
37
+ pip-delete-this-directory.txt
38
+
39
+ # Unit test / coverage reports
40
+ htmlcov/
41
+ .tox/
42
+ .nox/
43
+ .coverage
44
+ .coverage.*
45
+ .cache
46
+ nosetests.xml
47
+ coverage.xml
48
+ *.cover
49
+ *.py,cover
50
+ .hypothesis/
51
+ .pytest_cache/
52
+ cover/
53
+
54
+ # Translations
55
+ *.mo
56
+ *.pot
57
+
58
+ # Django stuff:
59
+ *.log
60
+ local_settings.py
61
+ db.sqlite3
62
+ db.sqlite3-journal
63
+
64
+ # Flask stuff:
65
+ instance/
66
+ .webassets-cache
67
+
68
+ # Scrapy stuff:
69
+ .scrapy
70
+
71
+ # Sphinx documentation
72
+ docs/_build/
73
+
74
+ # PyBuilder
75
+ .pybuilder/
76
+ target/
77
+
78
+ # Jupyter Notebook
79
+ .ipynb_checkpoints
80
+
81
+ # IPython
82
+ profile_default/
83
+ ipython_config.py
84
+
85
+ # pyenv
86
+ # For a library or package, you might want to ignore these files since the code is
87
+ # intended to run in multiple environments; otherwise, check them in:
88
+ # .python-version
89
+
90
+ # pipenv
91
+ # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
92
+ # However, in case of collaboration, if having platform-specific dependencies or dependencies
93
+ # having no cross-platform support, pipenv may install dependencies that don't work, or not
94
+ # install all needed dependencies.
95
+ #Pipfile.lock
96
+
97
+ # UV
98
+ # Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
99
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
100
+ # commonly ignored for libraries.
101
+ #uv.lock
102
+
103
+ # poetry
104
+ # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
105
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
106
+ # commonly ignored for libraries.
107
+ # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
108
+ #poetry.lock
109
+
110
+ # pdm
111
+ # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
112
+ #pdm.lock
113
+ # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
114
+ # in version control.
115
+ # https://pdm.fming.dev/latest/usage/project/#working-with-version-control
116
+ .pdm.toml
117
+ .pdm-python
118
+ .pdm-build/
119
+
120
+ # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
121
+ __pypackages__/
122
+
123
+ # Celery stuff
124
+ celerybeat-schedule
125
+ celerybeat.pid
126
+
127
+ # SageMath parsed files
128
+ *.sage.py
129
+
130
+ # Environments
131
+ .env
132
+ .venv
133
+ .venvs/
134
+ env/
135
+ venv/
136
+ ENV/
137
+ env.bak/
138
+ venv.bak/
139
+
140
+ # Spyder project settings
141
+ .spyderproject
142
+ .spyproject
143
+
144
+ # Rope project settings
145
+ .ropeproject
146
+
147
+ # mkdocs documentation
148
+ /site
149
+
150
+ # mypy
151
+ .mypy_cache/
152
+ .dmypy.json
153
+ dmypy.json
154
+
155
+ # Pyre type checker
156
+ .pyre/
157
+
158
+ # pytype static type analyzer
159
+ .pytype/
160
+
161
+ # Cython debug symbols
162
+ cython_debug/
163
+
164
+ # PyCharm
165
+ # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
166
+ # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
167
+ # and can be added to the global gitignore or merged into this file. For a more nuclear
168
+ # option (not recommended) you can uncomment the following to ignore the entire idea folder.
169
+ #.idea/
170
+
171
+ # PyPI configuration file
172
+ .pypirc
173
+
174
+ .DS_Store
175
+ # benchflow
176
+ .cache/
177
+
178
+ trials/
179
+ jobs/
180
+ # The docs' Jobs chapter is not run output.
181
+ !docs/jobs/
182
+ .jobs/
183
+ dogfood/
184
+ tmp/
185
+ .local/
186
+ src/benchflow/adapters/_toolathlon_canvas_tokens.json
187
+ .claude/settings.local.json
188
+ tests/.smoke-jobs/
189
+ context/
190
+ tutorials/
191
+ .playwright-mcp/
192
+ /.claude/handoffs
193
+
194
+ # task.md draft 2 fixtures are verbatim copies; their logs are evidence, not output.
195
+ !tests/fixtures/taskmd/**/*.log
196
+
197
+ # bfx binaries are built (make bfx) or come with the wheel; never committed.
198
+ src/benchflow/_bfx/bin/