benchflow 0.7.8.dev2321__tar.gz → 0.7.8.dev2329__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 (767) hide show
  1. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/PKG-INFO +1 -1
  2. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/pyproject.toml +1 -1
  3. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/acp/session.py +26 -0
  4. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/_capture.py +15 -10
  5. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/assets/boot.js +1 -0
  6. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/assets/detail.js +78 -4
  7. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/assets/template.html +14 -0
  8. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/assets/theme.css +30 -0
  9. benchflow-0.7.8.dev2329/src/benchflow/trajectories/viewer/assets/theme.js +103 -0
  10. benchflow-0.7.8.dev2329/src/benchflow/trajectories/viewer/assets/vendor/LICENSE.highlight.js +29 -0
  11. benchflow-0.7.8.dev2329/src/benchflow/trajectories/viewer/assets/vendor/highlight.min.js +1213 -0
  12. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/assets/viewer.css +22 -0
  13. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/models.py +48 -0
  14. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/payload.py +127 -1
  15. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/render.py +10 -1
  16. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/sources.py +9 -0
  17. benchflow-0.7.8.dev2329/tests/test_tool_call_raw_io.py +175 -0
  18. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/test_viewer_acp_renderer.py +5 -1
  19. benchflow-0.7.8.dev2329/tests/trajectories/test_viewer_rubric.py +227 -0
  20. benchflow-0.7.8.dev2329/tests/trajectories/test_viewer_theme.py +59 -0
  21. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/.gitignore +0 -0
  22. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/CHANGELOG.md +0 -0
  23. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/LICENSE +0 -0
  24. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/README.md +0 -0
  25. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/__init__.py +0 -0
  26. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_dotenv.py +0 -0
  27. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_paths.py +0 -0
  28. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_run.py +0 -0
  29. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_types.py +0 -0
  30. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/__init__.py +0 -0
  31. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/benchmark_repos.py +0 -0
  32. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/build_context_stage.py +0 -0
  33. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/config.py +0 -0
  34. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/config_override.py +0 -0
  35. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/content_address.py +0 -0
  36. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/dataset_registry.py +0 -0
  37. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/env_registry.py +0 -0
  38. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/evaluation_results.py +0 -0
  39. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/hf_datasets.py +0 -0
  40. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/json_safe.py +0 -0
  41. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/learner_memory.py +0 -0
  42. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/live_activity.py +0 -0
  43. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/result_metadata.py +0 -0
  44. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/reward_events.py +0 -0
  45. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/scoring.py +0 -0
  46. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/source_provenance.py +0 -0
  47. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/task_authoring/__init__.py +0 -0
  48. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/task_authoring/_evidence_paths.py +0 -0
  49. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/task_authoring/acceptance_evidence.py +0 -0
  50. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/task_authoring/scaffolding.py +0 -0
  51. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/task_authoring/structural_checks.py +0 -0
  52. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/text.py +0 -0
  53. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/_utils/yaml_loader.py +0 -0
  54. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/acp/__init__.py +0 -0
  55. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/acp/client.py +0 -0
  56. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/acp/container_transport.py +0 -0
  57. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/acp/runtime.py +0 -0
  58. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/acp/selection.py +0 -0
  59. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/acp/timeout_cleanup.py +0 -0
  60. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/acp/transport.py +0 -0
  61. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/acp/types.py +0 -0
  62. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/acp/watchdog.py +0 -0
  63. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/__init__.py +0 -0
  64. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/_toolathlon.py +0 -0
  65. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/_toolathlon_container.py +0 -0
  66. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/_toolathlon_fake_mail.py +0 -0
  67. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/_toolathlon_poste_users.tsv +0 -0
  68. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/_toolathlon_services.py +0 -0
  69. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/harbor.py +0 -0
  70. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/inbound.py +0 -0
  71. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/inspect_ai.py +0 -0
  72. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/ors.py +0 -0
  73. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/resources/__init__.py +0 -0
  74. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/resources/mcp_atlas_bridge.py +0 -0
  75. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/resources/mcp_atlas_judge.py +0 -0
  76. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/adapters/source.py +0 -0
  77. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agent_router.py +0 -0
  78. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agent_router_guide.py +0 -0
  79. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agent_router_parity.py +0 -0
  80. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agent_router_scaffold.py +0 -0
  81. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/__init__.py +0 -0
  82. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/codex_config.py +0 -0
  83. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/credentials.py +0 -0
  84. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/deepagents_acp_shim.py +0 -0
  85. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/env.py +0 -0
  86. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/errors.py +0 -0
  87. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/harvey_lab_acp_shim.py +0 -0
  88. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/install.py +0 -0
  89. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/manifest.py +0 -0
  90. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/openclaw_acp_shim.py +0 -0
  91. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/pi_acp_launcher.py +0 -0
  92. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/protocol.py +0 -0
  93. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/providers.py +0 -0
  94. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/registry.py +0 -0
  95. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/agents/remote_manifests.py +0 -0
  96. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/branch.py +0 -0
  97. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/__init__.py +0 -0
  98. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/_failure_evidence.py +0 -0
  99. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/_hosted_env.py +0 -0
  100. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/_live_progress.py +0 -0
  101. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/_options.py +0 -0
  102. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/_shared.py +0 -0
  103. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/_traj_tui.py +0 -0
  104. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/_traj_upload_ui.py +0 -0
  105. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/adopt.py +0 -0
  106. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/agent.py +0 -0
  107. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/continue_cmd.py +0 -0
  108. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/environment.py +0 -0
  109. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/eval_artifacts.py +0 -0
  110. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/eval_lift.py +0 -0
  111. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/hub.py +0 -0
  112. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/main.py +0 -0
  113. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/monitor.py +0 -0
  114. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/review.py +0 -0
  115. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/sandbox.py +0 -0
  116. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/skills.py +0 -0
  117. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/tasks.py +0 -0
  118. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/trace_import.py +0 -0
  119. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/train.py +0 -0
  120. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/cli/traj.py +0 -0
  121. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/continue_run/__init__.py +0 -0
  122. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/continue_run/batch.py +0 -0
  123. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/continue_run/orchestrator.py +0 -0
  124. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/continue_run/replay_proxy.py +0 -0
  125. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/continue_run/run_folder.py +0 -0
  126. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/continue_run/sandbox_proxy.py +0 -0
  127. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/contracts/__init__.py +0 -0
  128. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/contracts/planes.py +0 -0
  129. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/contracts/user.py +0 -0
  130. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/demo_task/environment/Dockerfile +0 -0
  131. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/demo_task/instruction.md +0 -0
  132. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/demo_task/task.md +0 -0
  133. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/demo_task/task.toml +0 -0
  134. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/demo_task/tests/test.sh +0 -0
  135. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/diagnostics.py +0 -0
  136. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/environment/__init__.py +0 -0
  137. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/environment/_registry/env0@outage.toml +0 -0
  138. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/environment/_registry/env0@prod.toml +0 -0
  139. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/environment/manifest.py +0 -0
  140. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/environment/manifest_env.py +0 -0
  141. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/environment/protocol.py +0 -0
  142. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/environment/readiness.py +0 -0
  143. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/eval_artifacts.py +0 -0
  144. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/eval_lift.py +0 -0
  145. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/eval_plan.py +0 -0
  146. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/eval_sharding.py +0 -0
  147. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/eval_worker.py +0 -0
  148. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/evaluation.py +0 -0
  149. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/experimental/__init__.py +0 -0
  150. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/experimental/mcp/__init__.py +0 -0
  151. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/experimental/mcp/hooks.py +0 -0
  152. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/experimental/mcp/reviewer_server.py +0 -0
  153. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/hosted_env.py +0 -0
  154. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/hub/__init__.py +0 -0
  155. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/hub/harbor_registry.py +0 -0
  156. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/integrations/__init__.py +0 -0
  157. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/integrations/trl/__init__.py +0 -0
  158. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/integrations/trl/spec.py +0 -0
  159. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/learner_skills.py +0 -0
  160. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/learner_store.py +0 -0
  161. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/loop_strategies.py +0 -0
  162. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/loop_sweep.py +0 -0
  163. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/metrics.py +0 -0
  164. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/models.py +0 -0
  165. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/monitor.py +0 -0
  166. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/providers/__init__.py +0 -0
  167. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/providers/litellm_bedrock_patch.py +0 -0
  168. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/providers/litellm_bedrock_preflight.py +0 -0
  169. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/providers/litellm_config.py +0 -0
  170. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/providers/litellm_gemini_passthrough_patch.py +0 -0
  171. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/providers/litellm_logging.py +0 -0
  172. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/providers/litellm_runtime.py +0 -0
  173. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/providers/runtime.py +0 -0
  174. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/publish/__init__.py +0 -0
  175. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/publish/_progress.py +0 -0
  176. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/publish/azure_blob.py +0 -0
  177. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/publish/broker.py +0 -0
  178. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/publish/huggingface.py +0 -0
  179. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/publish/redact.py +0 -0
  180. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/publish/traj_capture.py +0 -0
  181. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/publish/traj_report.py +0 -0
  182. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/py.typed +0 -0
  183. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/review/__init__.py +0 -0
  184. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/review/config.py +0 -0
  185. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/review/default-rubric.json +0 -0
  186. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/review/prompts.py +0 -0
  187. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/review/runner.py +0 -0
  188. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/review/scoring.py +0 -0
  189. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/review/wrapper.py +0 -0
  190. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/README.md +0 -0
  191. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/__init__.py +0 -0
  192. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/builtins.py +0 -0
  193. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/events.py +0 -0
  194. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/file_readers.py +0 -0
  195. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/llm.py +0 -0
  196. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/memory_scorer.py +0 -0
  197. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/node.py +0 -0
  198. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/protocol.py +0 -0
  199. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/rubric.py +0 -0
  200. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/rubric_config.py +0 -0
  201. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rewards/validation.py +0 -0
  202. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout/__init__.py +0 -0
  203. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout/_config.py +0 -0
  204. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout/_deadline.py +0 -0
  205. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout/_results.py +0 -0
  206. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout/_setup.py +0 -0
  207. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout/_skills.py +0 -0
  208. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout/_usage.py +0 -0
  209. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout/_user_loop.py +0 -0
  210. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout/session_factory_runtime.py +0 -0
  211. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout/task_runtime.py +0 -0
  212. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout_branch.py +0 -0
  213. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/rollout_planes.py +0 -0
  214. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/runtime.py +0 -0
  215. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/__init__.py +0 -0
  216. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/_base.py +0 -0
  217. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/_cache_reclaim.py +0 -0
  218. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/_compose.py +0 -0
  219. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/_compose_files/docker-compose-base.yaml +0 -0
  220. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/_compose_files/docker-compose-build.yaml +0 -0
  221. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/_compose_files/docker-compose-net-admin.yaml +0 -0
  222. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/_compose_files/docker-compose-no-network.yaml +0 -0
  223. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/_compose_files/docker-compose-prebuilt.yaml +0 -0
  224. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/_egress_denylist_proxy.py +0 -0
  225. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/_sdk_ops.py +0 -0
  226. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/agentcore.py +0 -0
  227. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/agentcore_builder.py +0 -0
  228. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/agentcore_image.py +0 -0
  229. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/agentcore_provisioning.py +0 -0
  230. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/agentcore_reaper.py +0 -0
  231. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/agentcore_sealed.py +0 -0
  232. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/apple_container.py +0 -0
  233. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/daytona.py +0 -0
  234. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/daytona_dind.py +0 -0
  235. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/daytona_pty.py +0 -0
  236. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/daytona_reaper.py +0 -0
  237. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/daytona_strategies.py +0 -0
  238. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/docker.py +0 -0
  239. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/egress_denylist.py +0 -0
  240. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/lockdown.py +0 -0
  241. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/metadata.py +0 -0
  242. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/modal_impl.py +0 -0
  243. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/process/__init__.py +0 -0
  244. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/process/_base.py +0 -0
  245. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/process/agentcore.py +0 -0
  246. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/process/apple.py +0 -0
  247. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/process/daytona.py +0 -0
  248. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/process/docker.py +0 -0
  249. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/protocol.py +0 -0
  250. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/providers.py +0 -0
  251. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/services.py +0 -0
  252. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/setup.py +0 -0
  253. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/snapshot.py +0 -0
  254. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sandbox/user.py +0 -0
  255. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/scenes.py +0 -0
  256. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/sdk.py +0 -0
  257. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/self_gen.py +0 -0
  258. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/skill_eval/__init__.py +0 -0
  259. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/skill_eval/_core.py +0 -0
  260. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/skill_eval/gepa_export.py +0 -0
  261. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/skill_eval/schema.py +0 -0
  262. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/skill_policy.py +0 -0
  263. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/skills.py +0 -0
  264. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/__init__.py +0 -0
  265. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/_document_evidence.py +0 -0
  266. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/_document_normalize.py +0 -0
  267. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/_document_parse.py +0 -0
  268. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/_document_profiles.py +0 -0
  269. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/acceptance_live.py +0 -0
  270. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/acceptance_live_model.py +0 -0
  271. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/acceptance_live_report.py +0 -0
  272. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/acceptance_live_validation.py +0 -0
  273. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/config.py +0 -0
  274. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/discovery.py +0 -0
  275. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/document.py +0 -0
  276. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/env.py +0 -0
  277. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/export.py +0 -0
  278. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/imports.py +0 -0
  279. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/output_format.py +0 -0
  280. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/package.py +0 -0
  281. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/paths.py +0 -0
  282. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/prompts.py +0 -0
  283. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/runtime_capabilities.py +0 -0
  284. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/runtime_view.py +0 -0
  285. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/task.py +0 -0
  286. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/verifier.py +0 -0
  287. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/verifier_core.py +0 -0
  288. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/verifier_document.py +0 -0
  289. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/verifier_errors.py +0 -0
  290. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/verifier_judge_inputs.py +0 -0
  291. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/verifier_ors_episode.py +0 -0
  292. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/verifier_reward_kit.py +0 -0
  293. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/verifier_scan.py +0 -0
  294. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/task/verifier_script_strategy.py +0 -0
  295. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/templates/__init__.py +0 -0
  296. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/templates/judge.py.tmpl +0 -0
  297. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/templates/test.sh.tmpl +0 -0
  298. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/traces/__init__.py +0 -0
  299. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/traces/huggingface.py +0 -0
  300. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/traces/local.py +0 -0
  301. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/traces/models.py +0 -0
  302. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/traces/parsers.py +0 -0
  303. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/traces/task_gen.py +0 -0
  304. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/training/__init__.py +0 -0
  305. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/training/backends/__init__.py +0 -0
  306. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/training/backends/prime_rl.py +0 -0
  307. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/training/run_manifest.py +0 -0
  308. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/__init__.py +0 -0
  309. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/_export_common.py +0 -0
  310. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/_llm_capture.py +0 -0
  311. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/call_purpose.py +0 -0
  312. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/export.py +0 -0
  313. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/export_adp.py +0 -0
  314. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/export_atif.py +0 -0
  315. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/export_prime_sft.py +0 -0
  316. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/export_trl_sft.py +0 -0
  317. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/metrics.py +0 -0
  318. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/results.py +0 -0
  319. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/sessions.py +0 -0
  320. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/tree.py +0 -0
  321. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/trl_sft_tokenization.py +0 -0
  322. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/types.py +0 -0
  323. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/__init__.py +0 -0
  324. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/__main__.py +0 -0
  325. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/assets/catalog.js +0 -0
  326. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/assets/fonts/OFL-google-sans-code.txt +0 -0
  327. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/assets/fonts/google-sans-code-400-latin.woff2 +0 -0
  328. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/assets/fonts/google-sans-code-600-latin.woff2 +0 -0
  329. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/assets/viewer.js +0 -0
  330. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/catalog.py +0 -0
  331. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/legacy.py +0 -0
  332. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/trajectories/viewer/server.py +0 -0
  333. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/src/benchflow/usage_tracking.py +0 -0
  334. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/__init__.py +0 -0
  335. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/acceptance_live_harness.py +0 -0
  336. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/agents/__init__.py +0 -0
  337. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/agents/test_codex_config.py +0 -0
  338. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/agents/test_manifest_dirscan.py +0 -0
  339. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/agents/test_manifest_loader.py +0 -0
  340. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/agents/test_manifest_parity.py +0 -0
  341. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/agents/test_manifest_wiring.py +0 -0
  342. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/agents/test_namespace_shorthand.py +0 -0
  343. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/agents/test_plugin_entry_points.py +0 -0
  344. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/agents/test_protocol.py +0 -0
  345. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/agents/test_remote_manifest_autoload.py +0 -0
  346. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/README.md +0 -0
  347. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/acp_smoke/environment/Dockerfile +0 -0
  348. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/acp_smoke/environment/docker-compose.yaml +0 -0
  349. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/acp_smoke/environment/skills/conformance-writer/SKILL.md +0 -0
  350. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/acp_smoke/instruction.md +0 -0
  351. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/acp_smoke/solution/solve.sh +0 -0
  352. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/acp_smoke/task.md +0 -0
  353. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/acp_smoke/task.toml +0 -0
  354. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/acp_smoke/tests/test.sh +0 -0
  355. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/conformance-results.json +0 -0
  356. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/proof_multi_agent.py +0 -0
  357. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/proof_snapshot.py +0 -0
  358. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/run_conformance.py +0 -0
  359. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conformance/self_gen_smoke_skills/skill-creator/SKILL.md +0 -0
  360. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/conftest.py +0 -0
  361. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/continue_run/__init__.py +0 -0
  362. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/continue_run/_helpers.py +0 -0
  363. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/continue_run/test_batch.py +0 -0
  364. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/continue_run/test_orchestrator.py +0 -0
  365. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/continue_run/test_replay_proxy.py +0 -0
  366. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/continue_run/test_run_folder.py +0 -0
  367. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/environment/__init__.py +0 -0
  368. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/environment/test_chibench_manifest.py +0 -0
  369. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/environment/test_clawsbench_manifest.py +0 -0
  370. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/environment/test_manifest.py +0 -0
  371. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/environment/test_manifest_env.py +0 -0
  372. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/environment/test_protocol.py +0 -0
  373. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/environment/test_readiness.py +0 -0
  374. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/hello-world-task/environment/Dockerfile +0 -0
  375. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/hello-world-task/instruction.md +0 -0
  376. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/hello-world-task/solution/solve.sh +0 -0
  377. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/hello-world-task/task.md +0 -0
  378. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/hello-world-task/task.toml +0 -0
  379. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/hello-world-task/tests/test.sh +0 -0
  380. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/test_claude.sh +0 -0
  381. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/test_codex.sh +0 -0
  382. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/test_codex_custom_provider.sh +0 -0
  383. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/test_gemini.sh +0 -0
  384. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/test_openclaw.sh +0 -0
  385. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/traces/minimal-claude.jsonl +0 -0
  386. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/examples/traces/minimal-opentraces.jsonl +0 -0
  387. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/digest/README.md +0 -0
  388. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/digest/alpha-task/environment/Dockerfile +0 -0
  389. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/digest/alpha-task/instruction.md +0 -0
  390. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/digest/alpha-task/task.toml +0 -0
  391. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/digest/alpha-task/tests/test.sh +0 -0
  392. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/digest/beta-task/data/empty.bin +0 -0
  393. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/digest/beta-task/data/unicode.txt +0 -0
  394. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/digest/beta-task/instruction.md +0 -0
  395. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/digest/beta-task/task.toml +0 -0
  396. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/digest/not-a-task/notes.txt +0 -0
  397. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/mock_acp_agent.py +0 -0
  398. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/mock_acp_agent_interleaved.py +0 -0
  399. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/mock_acp_agent_multi_turn.py +0 -0
  400. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/mock_openai_responses_server.py +0 -0
  401. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/Dockerfile +0 -0
  402. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/data/michigan_stations.txt +0 -0
  403. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/flood-detection/SKILL.md +0 -0
  404. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/nws-flood-thresholds/SKILL.md +0 -0
  405. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/usgs-data-download/SKILL.md +0 -0
  406. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/flood-risk-analysis/instruction.md +0 -0
  407. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/flood-risk-analysis/solution/solve.sh +0 -0
  408. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/flood-risk-analysis/task.toml +0 -0
  409. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test.sh +0 -0
  410. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test_outputs.py +0 -0
  411. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/Dockerfile +0 -0
  412. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/climate.csv +0 -0
  413. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/hydrology.csv +0 -0
  414. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/land_cover.csv +0 -0
  415. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/water_temperature.csv +0 -0
  416. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/contribution-analysis/SKILL.md +0 -0
  417. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/meteorology-driver-classification/SKILL.md +0 -0
  418. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/pca-decomposition/SKILL.md +0 -0
  419. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/trend-analysis/SKILL.md +0 -0
  420. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/instruction.md +0 -0
  421. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/solution/solve.sh +0 -0
  422. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/task.toml +0 -0
  423. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test.sh +0 -0
  424. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test_outputs.py +0 -0
  425. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/manifest.json +0 -0
  426. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/Dockerfile +0 -0
  427. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/r2r_simulator.py +0 -0
  428. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/finite-horizon-lqr/SKILL.md +0 -0
  429. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/integral-action-design/SKILL.md +0 -0
  430. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/mpc-horizon-tuning/SKILL.md +0 -0
  431. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/state-space-linearization/SKILL.md +0 -0
  432. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/system_config.json +0 -0
  433. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/instruction.md +0 -0
  434. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/solution/solve.sh +0 -0
  435. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/task.toml +0 -0
  436. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test.sh +0 -0
  437. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test_outputs.py +0 -0
  438. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/Dockerfile +0 -0
  439. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/generate_training_pcaps.py +0 -0
  440. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/local.rules +0 -0
  441. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/SKILL.md +0 -0
  442. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/scripts/summarize_http_requests.sh +0 -0
  443. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/SKILL.md +0 -0
  444. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/scripts/run_suricata_offline.sh +0 -0
  445. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-rules-basics/SKILL.md +0 -0
  446. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/suricata.yaml +0 -0
  447. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/instruction.md +0 -0
  448. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/solution/solve.sh +0 -0
  449. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/task.toml +0 -0
  450. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test.sh +0 -0
  451. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test_outputs.py +0 -0
  452. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/Dockerfile +0 -0
  453. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syz-extract-constants/SKILL.md +0 -0
  454. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzkaller-build-loop/SKILL.md +0 -0
  455. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzlang-ioctl-basics/SKILL.md +0 -0
  456. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/instruction.md +0 -0
  457. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/solution/solve.sh +0 -0
  458. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/task.toml +0 -0
  459. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test.sh +0 -0
  460. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test_outputs.py +0 -0
  461. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/_consistency.py +0 -0
  462. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/agent_judge.py +0 -0
  463. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/check_adapter_evidence.py +0 -0
  464. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/check_hosted_env_evidence.py +0 -0
  465. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/check_results.py +0 -0
  466. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/check_skillsbench_harbor_parity.py +0 -0
  467. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/check_trace_to_task_evidence.py +0 -0
  468. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/configs/claude-agent-acp.yaml +0 -0
  469. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/configs/codex-acp.yaml +0 -0
  470. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/configs/gemini.yaml +0 -0
  471. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/configs/harvey-lab-harness.yaml +0 -0
  472. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/configs/mimo.yaml +0 -0
  473. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/configs/openclaw.yaml +0 -0
  474. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/configs/opencode.yaml +0 -0
  475. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/configs/openhands.yaml +0 -0
  476. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/configs/pi-acp.yaml +0 -0
  477. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/deepagents_harness.py +0 -0
  478. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/rubric_checks.py +0 -0
  479. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/run.sh +0 -0
  480. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/run_suite.py +0 -0
  481. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/scenarios.py +0 -0
  482. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/integration/suites/release.yaml +0 -0
  483. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_acceptance_evidence.py +0 -0
  484. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_acceptance_live.py +0 -0
  485. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_acceptance_live_execution.py +0 -0
  486. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_acp.py +0 -0
  487. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_acp_capability_advertising.py +0 -0
  488. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_acp_mcp_servers.py +0 -0
  489. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_acp_model_config_dispatch.py +0 -0
  490. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_acp_pinned_protocol_guard.py +0 -0
  491. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_acp_setup_failure_propagation.py +0 -0
  492. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_acp_timeout_evidence.py +0 -0
  493. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_adapter_scripts.py +0 -0
  494. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_adapters.py +0 -0
  495. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agent_cli.py +0 -0
  496. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agent_env_resolution.py +0 -0
  497. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agent_gemini_defaults.py +0 -0
  498. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agent_idle_timeout_cli.py +0 -0
  499. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agent_model_decouple.py +0 -0
  500. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agent_registry.py +0 -0
  501. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agent_router.py +0 -0
  502. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agent_router_cli_e2e.py +0 -0
  503. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agent_router_scaffold.py +0 -0
  504. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agent_setup.py +0 -0
  505. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agent_spec.py +0 -0
  506. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agentcore_builder.py +0 -0
  507. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agentcore_parallel.py +0 -0
  508. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agentcore_reaper.py +0 -0
  509. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agentcore_sandbox.py +0 -0
  510. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_agentcore_transport.py +0 -0
  511. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_api_error_capture.py +0 -0
  512. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_apple_container_sandbox.py +0 -0
  513. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_bare_model_provider.py +0 -0
  514. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_base_install_imports.py +0 -0
  515. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_bedrock_thinking.py +0 -0
  516. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_benchflow_experiment_review_validator.py +0 -0
  517. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_benchmark_repos_resolve_repo_path.py +0 -0
  518. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_branch.py +0 -0
  519. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_build_context_stage.py +0 -0
  520. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_build_review_pack.py +0 -0
  521. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_capture_trajectory.py +0 -0
  522. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_check_skillsbench_harbor_parity.py +0 -0
  523. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_clawsbench_slice.py +0 -0
  524. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_cli_adopt_aliases.py +0 -0
  525. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_cli_arg_validation.py +0 -0
  526. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_cli_daytona.py +0 -0
  527. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_cli_docs_drift.py +0 -0
  528. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_cli_edge_case_hardening.py +0 -0
  529. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_cli_hub_env.py +0 -0
  530. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_cli_live_progress.py +0 -0
  531. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_cli_misc.py +0 -0
  532. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_codex_review.py +0 -0
  533. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_codex_self_write_auth.py +0 -0
  534. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_config_override.py +0 -0
  535. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_config_redaction.py +0 -0
  536. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_connect_as_env.py +0 -0
  537. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_console_error_truncation.py +0 -0
  538. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_console_progress.py +0 -0
  539. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_continuallearningbench_adapter.py +0 -0
  540. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_dataset_registry.py +0 -0
  541. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_daytona_command_polling.py +0 -0
  542. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_daytona_dind_compose_up.py +0 -0
  543. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_daytona_download.py +0 -0
  544. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_daytona_litellm_runtime.py +0 -0
  545. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_daytona_poll_deadline.py +0 -0
  546. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_daytona_reap.py +0 -0
  547. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_deepagents_agent.py +0 -0
  548. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_diagnostics.py +0 -0
  549. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_docker_prune_scoping.py +0 -0
  550. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_docker_uploads.py +0 -0
  551. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_docs_examples.py +0 -0
  552. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_egress_denylist.py +0 -0
  553. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_egress_denylist_integration.py +0 -0
  554. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_egress_model_gateway.py +0 -0
  555. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_eng50_capabilities.py +0 -0
  556. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_env_registry.py +0 -0
  557. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_env_setup.py +0 -0
  558. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_environment_manifest_controls.py +0 -0
  559. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_eval_artifact_cli.py +0 -0
  560. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_eval_filters_applied.py +0 -0
  561. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_eval_lift.py +0 -0
  562. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_eval_sharding.py +0 -0
  563. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_eval_single_task_summary.py +0 -0
  564. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_eval_source_provenance.py +0 -0
  565. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_eval_worker_retry.py +0 -0
  566. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_eval_zero_task_guard.py +0 -0
  567. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_evaluation_environment_manifest.py +0 -0
  568. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_exclude_tasks.py +0 -0
  569. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_filter_credentialed_cells.py +0 -0
  570. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_harvey_lab_shim.py +0 -0
  571. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_hilbench_adapter.py +0 -0
  572. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_hosted_env.py +0 -0
  573. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_hosted_env_rollout_contract.py +0 -0
  574. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_hosted_search_policy.py +0 -0
  575. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_hub_harbor_registry.py +0 -0
  576. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_inbound_adapter_manifest.py +0 -0
  577. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_inbound_adapters.py +0 -0
  578. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_integration_agent_judge.py +0 -0
  579. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_integration_check_results.py +0 -0
  580. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_integration_consistency.py +0 -0
  581. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_integration_matrix.py +0 -0
  582. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_integration_provider_selection.py +0 -0
  583. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_integration_run_suite.py +0 -0
  584. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_integration_suite.py +0 -0
  585. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_internet_policy.py +0 -0
  586. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_job.py +0 -0
  587. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_job_sequential_shared.py +0 -0
  588. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_job_sequential_shared_resume.py +0 -0
  589. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_judge_robustness.py +0 -0
  590. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_judge_symlink_ingestion.py +0 -0
  591. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_learner_skills.py +0 -0
  592. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_learner_skills_traversal.py +0 -0
  593. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_learner_store.py +0 -0
  594. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_learner_store_persistence.py +0 -0
  595. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_litellm_config.py +0 -0
  596. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_litellm_gemini_passthrough_patch.py +0 -0
  597. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_litellm_hardening.py +0 -0
  598. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_litellm_logging.py +0 -0
  599. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_litellm_model_via_env_generic.py +0 -0
  600. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_litellm_reasoning_passthrough.py +0 -0
  601. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_litellm_runtime.py +0 -0
  602. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_litellm_smoke.py +0 -0
  603. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_live_llm_trajectory.py +0 -0
  604. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_llm_judge.py +0 -0
  605. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_llm_judge_event_tags.py +0 -0
  606. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_llm_judge_verifier.py +0 -0
  607. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_loop_strategies.py +0 -0
  608. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_loop_summary.py +0 -0
  609. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_loop_sweep.py +0 -0
  610. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_memory_scorer.py +0 -0
  611. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_metrics.py +0 -0
  612. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_mle_bench_adapter.py +0 -0
  613. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_mock_openai_responses_server.py +0 -0
  614. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_monitor_scaffold.py +0 -0
  615. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_native_acp_usage.py +0 -0
  616. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_network_denylist_config.py +0 -0
  617. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_no_cross_provider_fallback.py +0 -0
  618. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_notification_order_real.py +0 -0
  619. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_opencode_family_proxy_tracking.py +0 -0
  620. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_oracle.py +0 -0
  621. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_oracle_chokepoint.py +0 -0
  622. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_paths_safe.py +0 -0
  623. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_paths_symlink_helpers.py +0 -0
  624. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_pi_acp_launcher.py +0 -0
  625. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_pi_acp_proxy_routing.py +0 -0
  626. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_process.py +0 -0
  627. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_project_skills_layout.py +0 -0
  628. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_provider_auth_detection.py +0 -0
  629. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_providers.py +0 -0
  630. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_publish_azure_blob.py +0 -0
  631. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_publish_huggingface.py +0 -0
  632. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_reexport.py +0 -0
  633. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_registry_invariants.py +0 -0
  634. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_release_hardening_r5.py +0 -0
  635. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_release_version.py +0 -0
  636. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_release_workflow_wiring.py +0 -0
  637. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_resolve_env_helpers.py +0 -0
  638. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_review_boundaries.py +0 -0
  639. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_review_rubric.py +0 -0
  640. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_review_runtime.py +0 -0
  641. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_reward_lenient.py +0 -0
  642. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_reward_node.py +0 -0
  643. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_reward_range.py +0 -0
  644. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_reward_unified_contract.py +0 -0
  645. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rewards.py +0 -0
  646. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rewards_jsonl.py +0 -0
  647. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_architecture.py +0 -0
  648. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_branch.py +0 -0
  649. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_config_path_coercion.py +0 -0
  650. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_environment.py +0 -0
  651. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_hard_deadline.py +0 -0
  652. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_import_no_side_effects.py +0 -0
  653. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_on_ask_user_wiring.py +0 -0
  654. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_planes_contract.py +0 -0
  655. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_probe_sandbox_health.py +0 -0
  656. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_session_factory_dispatch.py +0 -0
  657. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_setup_commands.py +0 -0
  658. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rollout_upload.py +0 -0
  659. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rubric_checks.py +0 -0
  660. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_rubric_config.py +0 -0
  661. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_runtime.py +0 -0
  662. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_runtime_capabilities.py +0 -0
  663. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_runtime_config_wired.py +0 -0
  664. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_runtime_live_sandbox.py +0 -0
  665. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox.py +0 -0
  666. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_exec_secret_handling.py +0 -0
  667. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_hardening.py +0 -0
  668. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_isolation_copy_traversal.py +0 -0
  669. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_live_process.py +0 -0
  670. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_multi_service.py +0 -0
  671. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_prebuilt_validation.py +0 -0
  672. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_protocol.py +0 -0
  673. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_provider_registry_drift.py +0 -0
  674. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_setup.py +0 -0
  675. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_snapshot_contract.py +0 -0
  676. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_upload_symlink.py +0 -0
  677. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sandbox_verifier_workspace.py +0 -0
  678. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_scene.py +0 -0
  679. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_scene_outbox_trial.py +0 -0
  680. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_scene_parallel_group.py +0 -0
  681. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_scene_result_aggregation.py +0 -0
  682. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_scoring.py +0 -0
  683. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sdk_internals.py +0 -0
  684. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sdk_lockdown.py +0 -0
  685. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sdk_run_alias.py +0 -0
  686. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_sealed_channel_container.py +0 -0
  687. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_self_gen_cli.py +0 -0
  688. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_self_gen_export_error_channel.py +0 -0
  689. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_self_gen_export_failures.py +0 -0
  690. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_self_gen_orchestration.py +0 -0
  691. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_session_factory_runtime.py +0 -0
  692. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_session_request_permission_dispatch.py +0 -0
  693. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_skill_eval.py +0 -0
  694. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_skill_eval_dryrun.py +0 -0
  695. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_skill_eval_integration.py +0 -0
  696. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_skill_eval_sweep.py +0 -0
  697. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_skill_eval_traversal.py +0 -0
  698. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_skill_invocation_artifacts.py +0 -0
  699. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_skill_policy.py +0 -0
  700. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_skills.py +0 -0
  701. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_skills_dir_agent_home_link.py +0 -0
  702. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_skillsbench_conversion_conformance.py +0 -0
  703. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_skillsbench_harbor_run_suite.py +0 -0
  704. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_smoke.py +0 -0
  705. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_smoke_wiring.py +0 -0
  706. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_source_adapters.py +0 -0
  707. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_subscription_auth.py +0 -0
  708. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_task_check_eval_consistency.py +0 -0
  709. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_task_config.py +0 -0
  710. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_task_digest.py +0 -0
  711. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_task_document.py +0 -0
  712. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_task_download.py +0 -0
  713. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_task_export.py +0 -0
  714. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_task_output_format.py +0 -0
  715. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_task_package.py +0 -0
  716. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_task_runtime_primitive.py +0 -0
  717. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_tasks.py +0 -0
  718. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_token_usage_normalization.py +0 -0
  719. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_trace_import_cli.py +0 -0
  720. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_trace_task_gen_traversal.py +0 -0
  721. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_trace_to_task_evidence.py +0 -0
  722. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_traces_huggingface.py +0 -0
  723. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_traces_parsers.py +0 -0
  724. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_traces_task_gen.py +0 -0
  725. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_train_cli.py +0 -0
  726. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_train_mode_artifact_emission.py +0 -0
  727. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_train_trl_cli.py +0 -0
  728. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_traj_report.py +0 -0
  729. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_traj_staging_phases.py +0 -0
  730. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_traj_tui.py +0 -0
  731. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_traj_upload_cli.py +0 -0
  732. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_traj_upload_skill.py +0 -0
  733. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_traj_workspace.py +0 -0
  734. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_trajectory_integration.py +0 -0
  735. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_trajectory_streaming.py +0 -0
  736. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_trajectory_upload_layout.py +0 -0
  737. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_trajectory_upload_service.py +0 -0
  738. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_trial_agent_timeout_verify.py +0 -0
  739. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_trial_install_agent_timeout.py +0 -0
  740. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_trial_litellm_runtime.py +0 -0
  741. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_trl_integration.py +0 -0
  742. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_usage_litellm.py +0 -0
  743. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_usage_required.py +0 -0
  744. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_usage_tracking.py +0 -0
  745. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_user.py +0 -0
  746. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_v06_guard_ports.py +0 -0
  747. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_verifier_document.py +0 -0
  748. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_verifier_multi_container.py +0 -0
  749. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_verifier_output.py +0 -0
  750. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_verifier_output_freshness.py +0 -0
  751. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_verifier_strategies.py +0 -0
  752. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_verifier_wedge_retry.py +0 -0
  753. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_verify.py +0 -0
  754. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_viewer_confirm.py +0 -0
  755. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_workflow_action_pinning.py +0 -0
  756. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/test_yaml_config.py +0 -0
  757. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/__init__.py +0 -0
  758. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/test_export.py +0 -0
  759. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/test_export_adp.py +0 -0
  760. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/test_export_atif.py +0 -0
  761. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/test_export_common.py +0 -0
  762. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/test_export_nan_handling.py +0 -0
  763. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/test_export_prime_sft.py +0 -0
  764. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/test_redaction.py +0 -0
  765. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/test_step_granularity.py +0 -0
  766. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/test_tree.py +0 -0
  767. {benchflow-0.7.8.dev2321 → benchflow-0.7.8.dev2329}/tests/trajectories/test_viewer_browser.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.5
2
2
  Name: benchflow
3
- Version: 0.7.8.dev2321
3
+ Version: 0.7.8.dev2329
4
4
  Summary: Multi-turn agent benchmarking with ACP — run any agent, any model, any provider.
5
5
  Project-URL: Homepage, https://github.com/benchflow-ai/benchflow
6
6
  Project-URL: Repository, https://github.com/benchflow-ai/benchflow
@@ -1,6 +1,6 @@
1
1
  [project]
2
2
  name = "benchflow"
3
- version = "0.7.8.dev2321"
3
+ version = "0.7.8.dev2329"
4
4
  description = "Multi-turn agent benchmarking with ACP — run any agent, any model, any provider."
5
5
  readme = "README.md"
6
6
  requires-python = ">=3.12"
@@ -162,6 +162,10 @@ class ToolCallRecord:
162
162
  self.kind = kind
163
163
  self.status = ToolCallStatus.PENDING
164
164
  self.content: list[dict] = []
165
+ # ACP ``rawInput`` / ``rawOutput``: the agent's own view of the call.
166
+ # codex-acp puts the command and its output here and nowhere else.
167
+ self.raw_input: object | None = None
168
+ self.raw_output: object | None = None
165
169
  self.started_at = datetime.now()
166
170
  self.finished_at: datetime | None = None
167
171
 
@@ -178,6 +182,13 @@ class ToolCallRecord:
178
182
  ):
179
183
  self.finished_at = datetime.now()
180
184
 
185
+ def absorb_raw_io(self, update: dict) -> None:
186
+ """Keep the latest ``rawInput`` / ``rawOutput`` an update carries."""
187
+ if update.get("rawInput") is not None:
188
+ self.raw_input = update["rawInput"]
189
+ if update.get("rawOutput") is not None:
190
+ self.raw_output = update["rawOutput"]
191
+
181
192
 
182
193
  class ACPSession:
183
194
  """Tracks mutable state for one ACP session.
@@ -417,6 +428,20 @@ class ACPSession:
417
428
  update.get("kind", "other"), update.get("title", "")
418
429
  ),
419
430
  )
431
+ # The opening notification may already carry content (codex-acp
432
+ # sends file-change diffs this way) and raw I/O.
433
+ initial_content = update.get("content")
434
+ if isinstance(initial_content, list) and initial_content:
435
+ record.content.extend(initial_content)
436
+ record.absorb_raw_io(update)
437
+ # An opening call may already be terminal (codex-acp file edits
438
+ # arrive completed with no later update); honor its status so it
439
+ # never lingers in pending_tool_call_ids().
440
+ if update.get("status") is not None:
441
+ try:
442
+ record.update_status(ToolCallStatus(update["status"]))
443
+ except ValueError:
444
+ logger.warning(f"Unknown tool call status: {update.get('status')}")
420
445
  self._record_tool_call(record)
421
446
 
422
447
  elif update_type == "tool_call_update":
@@ -440,6 +465,7 @@ class ACPSession:
440
465
  status = ToolCallStatus.IN_PROGRESS
441
466
  content = update.get("content")
442
467
  record.update_status(status, content)
468
+ record.absorb_raw_io(update)
443
469
  if status in (ToolCallStatus.PENDING, ToolCallStatus.IN_PROGRESS):
444
470
  self._pending_tool_call_update_counts[tc_id] = (
445
471
  self._pending_tool_call_update_counts.get(tc_id, 0) + 1
@@ -70,16 +70,21 @@ def _events_to_trajectory(events: list[dict]) -> list[dict]:
70
70
  for event in events:
71
71
  if event["type"] == "tool_call":
72
72
  tc = event["record"]
73
- out.append(
74
- {
75
- "type": "tool_call",
76
- "tool_call_id": tc.tool_call_id,
77
- "kind": tc.kind,
78
- "title": tc.title,
79
- "status": tc.status.value,
80
- "content": tc.content,
81
- }
82
- )
73
+ record = {
74
+ "type": "tool_call",
75
+ "tool_call_id": tc.tool_call_id,
76
+ "kind": tc.kind,
77
+ "title": tc.title,
78
+ "status": tc.status.value,
79
+ "content": tc.content,
80
+ }
81
+ # Only present when the agent sent them, so trajectories of agents
82
+ # without raw I/O keep their exact shape.
83
+ if getattr(tc, "raw_input", None) is not None:
84
+ record["raw_input"] = tc.raw_input
85
+ if getattr(tc, "raw_output", None) is not None:
86
+ record["raw_output"] = tc.raw_output
87
+ out.append(record)
83
88
  elif event["type"] in ("user_message", "agent_message", "agent_thought"):
84
89
  out.append({"type": event["type"], "text": event["text"]})
85
90
  elif event["type"] == "agent_timeout":
@@ -114,6 +114,7 @@ BF.navigation = (() => {
114
114
  bootError("The embedded viewer data must be a JSON object.");
115
115
  return;
116
116
  }
117
+ BF.theme.init();
117
118
  if (boot.mode === "single") {
118
119
  BF.navigation.startSingle(boot.payload);
119
120
  return;
@@ -14,6 +14,7 @@ BF.detail = (() => {
14
14
  ["trace", "view-trace"],
15
15
  ["verifier", "view-verifier"],
16
16
  ["metrics", "view-metrics"],
17
+ ["rubric", "view-rubric"],
17
18
  ]);
18
19
  const STEP_KINDS = new Set(["prompt", "message", "thought", "tool", "timeout", "unknown"]);
19
20
  const TOOL_HUES = new Set(["read", "edit", "execute", "fetch", "search", "think", "skill", "other"]);
@@ -178,6 +179,9 @@ BF.detail = (() => {
178
179
  ) {
179
180
  available.push(["metrics", "Metrics"]);
180
181
  }
182
+ if (payload.rubric && typeof payload.rubric === "object") {
183
+ available.push(["rubric", "Rubric"]);
184
+ }
181
185
 
182
186
  const tabs = document.getElementById("tabs");
183
187
  tabs.textContent = "";
@@ -331,12 +335,13 @@ BF.detail = (() => {
331
335
  });
332
336
  }
333
337
 
334
- function collapsibleText(container, text, className) {
338
+ function collapsibleText(container, text, className, language = null) {
335
339
  const value = String(text);
336
340
  const lines = value.split("\n");
337
341
  const body = el("div", className);
338
342
  if (value.length <= COLLAPSE_CHARS && lines.length <= COLLAPSE_LINES) {
339
343
  textWithRedaction(body, value);
344
+ BF.highlight.paint(body, value, language);
340
345
  container.appendChild(body);
341
346
  return;
342
347
  }
@@ -354,6 +359,7 @@ BF.detail = (() => {
354
359
  const open = button.getAttribute("aria-expanded") === "true";
355
360
  body.textContent = "";
356
361
  textWithRedaction(body, open ? preview + " ..." : value);
362
+ if (!open) BF.highlight.paint(body, value, language);
357
363
  button.setAttribute("aria-expanded", open ? "false" : "true");
358
364
  button.textContent = open
359
365
  ? "\u25b8 expand (" + value.length.toLocaleString() + " chars)"
@@ -413,9 +419,10 @@ BF.detail = (() => {
413
419
  const tool = record.tool && typeof record.tool === "object" ? record.tool : {};
414
420
  const outputClass = "tout" + (toolHue === "execute" ? " term" : "");
415
421
  const content = Array.isArray(tool.content) ? tool.content : [];
416
- content.forEach((item) => {
422
+ content.forEach((item, position) => {
417
423
  const wrapper = el("div");
418
- collapsibleText(wrapper, item, outputClass);
424
+ const language = BF.highlight.languageFor(String(item), toolHue, tool.title, position);
425
+ collapsibleText(wrapper, item, outputClass, language);
419
426
  card.appendChild(wrapper);
420
427
  });
421
428
  } else if (kind === "timeout") {
@@ -581,6 +588,72 @@ BF.detail = (() => {
581
588
  if (!main.children.length) main.appendChild(el("div", "panelblock", "No verifier artifacts in this rollout."));
582
589
  }
583
590
 
591
+ function renderRubric(payload) {
592
+ const rubric = payload.rubric && typeof payload.rubric === "object" ? payload.rubric : null;
593
+ const main = document.getElementById("view-rubric");
594
+ main.textContent = "";
595
+ if (!rubric) {
596
+ main.appendChild(el("div", "panelblock", "No review report found for this rollout."));
597
+ return;
598
+ }
599
+ const scoring = rubric.scoring && typeof rubric.scoring === "object" ? rubric.scoring : {};
600
+ const head = el("div", "panelblock");
601
+ head.appendChild(el("h2", null, "Review"));
602
+ const facts = el("table", "plain");
603
+ const rows = [
604
+ ["Reviewer", rubric.reviewer_model || ""],
605
+ ["Valid", rubric.review_valid ? "yes" : "no"],
606
+ ["Verifier pass", scoring.deterministic_pass === undefined ? "" : (scoring.deterministic_pass ? "yes" : "no")],
607
+ ["Blockers", scoring.all_blockers_pass === undefined ? ""
608
+ : (scoring.all_blockers_pass ? "all pass" : "failed: " + (scoring.failed_blockers || []).join(", "))],
609
+ ["Raw quality", scoring.raw_quality === undefined ? "" : String(scoring.raw_quality)],
610
+ ["Gated quality", scoring.gated_quality === undefined ? "" : String(scoring.gated_quality)],
611
+ ["Decision", scoring.decision || ""],
612
+ ];
613
+ rows.forEach(([label, value]) => {
614
+ const row = el("tr");
615
+ row.appendChild(el("th", null, label));
616
+ const cell = el("td", null, value);
617
+ if (label === "Blockers" || label === "Verifier pass") {
618
+ cell.style.color = /fail|^no$/.test(value) ? "var(--bad-ink)" : (value ? "var(--ok-ink)" : "");
619
+ }
620
+ row.appendChild(cell);
621
+ facts.appendChild(row);
622
+ });
623
+ head.appendChild(facts);
624
+ if (rubric.summary) collapsibleText(head, rubric.summary, "body");
625
+ main.appendChild(head);
626
+
627
+ const criteria = Array.isArray(rubric.criteria) ? rubric.criteria : [];
628
+ if (criteria.length) {
629
+ const block = el("div", "panelblock");
630
+ block.appendChild(el("h2", null, "Criteria"));
631
+ const table = el("table", "plain");
632
+ const heading = el("tr");
633
+ ["Criterion", "Kind", "Verdict", "Reviewer note"].forEach((label) => heading.appendChild(el("th", null, label)));
634
+ table.appendChild(heading);
635
+ criteria.forEach((criterion) => {
636
+ const record = criterion && typeof criterion === "object" ? criterion : {};
637
+ const row = el("tr");
638
+ row.appendChild(el("td", null, record.name));
639
+ // blocker true: v0.2 blocker; false: v0.2 scored; null: legacy v0.1 (outcome only)
640
+ const scored = record.blocker === false;
641
+ const kind = record.blocker === true ? "blocker" : (scored ? "weight " + (record.weight ?? "?") : "criterion");
642
+ row.appendChild(el("td", null, kind));
643
+ const verdict = el("td", null, scored ? ((record.score ?? "?") + " / 2") : (record.outcome || ""));
644
+ if (!scored && record.outcome) {
645
+ verdict.style.color = record.outcome === "pass" ? "var(--ok-ink)"
646
+ : (record.outcome === "fail" ? "var(--bad-ink)" : "var(--muted-foreground)");
647
+ }
648
+ row.appendChild(verdict);
649
+ row.appendChild(el("td", null, record.explanation || ""));
650
+ table.appendChild(row);
651
+ });
652
+ block.appendChild(table);
653
+ main.appendChild(block);
654
+ }
655
+ }
656
+
584
657
  function renderMetrics(payload) {
585
658
  const meta = payload.meta || {};
586
659
  const main = document.getElementById("view-metrics");
@@ -662,7 +735,7 @@ BF.detail = (() => {
662
735
  }
663
736
 
664
737
  function clearDetail() {
665
- ["hdr", "tabs", "view-trace", "view-verifier", "view-metrics"].forEach((id) => {
738
+ ["hdr", "tabs", "view-trace", "view-verifier", "view-metrics", "view-rubric"].forEach((id) => {
666
739
  document.getElementById(id).textContent = "";
667
740
  });
668
741
  document.getElementById("toolbar").textContent = "";
@@ -702,6 +775,7 @@ BF.detail = (() => {
702
775
  renderTrace(payload);
703
776
  renderVerifier(payload);
704
777
  renderMetrics(payload);
778
+ renderRubric(payload);
705
779
  document.title = (payload.meta && payload.meta.task_name) || payload.rollout_name || "benchflow trajectory";
706
780
  if (options.focusHeading) requestAnimationFrame(() => heading.focus());
707
781
  }
@@ -5,6 +5,15 @@
5
5
  <meta name="viewport" content="width=device-width, initial-scale=1">
6
6
  <title>__BENCHFLOW_TITLE__</title>
7
7
  <link rel="icon" href="data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 16 16'%3E%3Ccircle cx='8' cy='8' r='6' fill='%230a0a0a'/%3E%3C/svg%3E">
8
+ <script>
9
+ (function () {
10
+ var stored = null;
11
+ try { stored = localStorage.getItem("bf-theme"); } catch (e) {}
12
+ var dark = stored ? stored === "dark"
13
+ : window.matchMedia && window.matchMedia("(prefers-color-scheme: dark)").matches;
14
+ if (dark) document.documentElement.dataset.theme = "dark";
15
+ })();
16
+ </script>
8
17
  <style>
9
18
  /*__BENCHFLOW_THEME_CSS__*/
10
19
  /*__BENCHFLOW_VIEWER_CSS__*/
@@ -16,6 +25,7 @@
16
25
  <svg viewBox="0 0 514 512" fill="currentColor" aria-hidden="true"><path fill-rule="evenodd" clip-rule="evenodd" d="M445.422 66.4597L511.882 0L389.022 293.965L295.129 387.859L0 511.882L69.3042 442.577L81.0101 454.283L89.0554 446.238L77.3493 434.532L130.65 381.232L162.469 413.051L170.514 405.006L138.695 373.187L191.995 319.887L203.701 331.593L211.746 323.547L200.04 311.841L253.34 258.541L285.16 290.36L293.205 282.315L261.386 250.496L314.686 197.196L326.392 208.902L334.437 200.856L322.731 189.15L376.031 135.85L407.851 167.669L415.896 159.624L384.077 127.805L437.377 74.5049L449.083 86.2108L457.128 78.1656L445.422 66.4597ZM399.127 389.865V299.369L513.197 26.4333V503.935L399.127 389.865ZM391.061 397.931L505.132 512.001H29.1594L300.605 397.931H391.061Z"/></svg>
17
26
  <span class="brand">BenchFlow</span>
18
27
  <span class="app">trajectory viewer</span>
28
+ <button id="theme-toggle" type="button" aria-label="toggle color theme">theme</button>
19
29
  </div>
20
30
  <main id="view-index" class="hidden" aria-label="run catalog"></main>
21
31
  <div id="content">
@@ -26,10 +36,14 @@
26
36
  <main id="view-trace" role="tabpanel"></main>
27
37
  <main id="view-verifier" role="tabpanel" class="hidden"></main>
28
38
  <main id="view-metrics" role="tabpanel" class="hidden"></main>
39
+ <main id="view-rubric" role="tabpanel" class="hidden"></main>
29
40
  </div>
30
41
  </div>
31
42
  <script id="bf-payload" type="application/json">__BENCHFLOW_PAYLOAD__</script>
32
43
  <script>
44
+ //__BENCHFLOW_VENDOR_JS__
45
+ </script>
46
+ <script>
33
47
  //__BENCHFLOW_VIEWER_JS__
34
48
  </script>
35
49
  </body>
@@ -126,4 +126,34 @@
126
126
  --warn-bg: color-mix(in srgb, var(--warning) 12%, var(--card));
127
127
  --warn-line: color-mix(in srgb, var(--warning) 28%, var(--card));
128
128
  --warn-strip: color-mix(in srgb, var(--warning) 60%, var(--card));
129
+
130
+ /* syntax highlighting palette (GitHub light); terminal blocks and the dark
131
+ theme swap in the dark palette below */
132
+ --hl-fg: #24292e; --hl-kw: #d73a49; --hl-str: #032f62; --hl-num: #005cc5; --hl-cmt: #6a737d;
133
+ --hl-fn: #6f42c1; --hl-var: #e36209; --hl-add: #22863a; --hl-add-bg: #e6ffed;
134
+ --hl-del: #b31d28; --hl-del-bg: #ffeef0;
135
+ }
136
+
137
+ /* dark theme: an override of the same tokens, applied by data-theme="dark" on
138
+ <html> (chosen from prefers-color-scheme by default, toggled from the
139
+ wordmark). Pages without the attribute render exactly as before. */
140
+ html[data-theme="dark"] {
141
+ color-scheme: dark;
142
+ --background: #0f1216; --foreground: #e6e6e6;
143
+ --card: #171b21; --card-foreground: #e6e6e6;
144
+ --primary: #e6e6e6; --primary-foreground: #111111;
145
+ --secondary: #222831; --secondary-foreground: #e6e6e6;
146
+ --muted: #222831; --muted-foreground: #9aa4b2;
147
+ --accent: #222831; --accent-foreground: #e6e6e6;
148
+ --border: #2b323c;
149
+ --ink-secondary: #c3c9d1; --faint: #6b7480; --rule-strong: #3a424d;
150
+ --code-bg: #0b0e12; --code-ink: #e6e6e6;
151
+ --kind-execute-bg: #2a2410; --kind-execute-line: #4a3c14; --kind-execute-ink: #e2b84f; --kind-execute-strip: #b58a2c;
152
+ --kind-edit-bg: #14213a; --kind-edit-line: #1f3a63; --kind-edit-ink: #8fbcf0; --kind-edit-strip: #4f83c4;
153
+ --kind-read-bg: #10281f; --kind-read-line: #1c4a37; --kind-read-ink: #7ed3ae; --kind-read-strip: #3e9c74;
154
+ --kind-agent-bg: #241c3a; --kind-agent-line: #3b2d61; --kind-agent-ink: #c6b0ee; --kind-agent-strip: #8a6bd0;
155
+ --kind-web-bg: #0f2a33; --kind-web-line: #1c4a58; --kind-web-ink: #7ecbe0; --kind-web-strip: #3f9fb8;
156
+ --hl-fg: #e6edf3; --hl-kw: #ff7b72; --hl-str: #a5d6ff; --hl-num: #79c0ff; --hl-cmt: #8b949e;
157
+ --hl-fn: #d2a8ff; --hl-var: #ffa657; --hl-add: #7ee787; --hl-add-bg: #12261e;
158
+ --hl-del: #ffa198; --hl-del-bg: #3a1618;
129
159
  }
@@ -0,0 +1,103 @@
1
+ // Color theme (light/dark) and syntax highlighting of tool content.
2
+ //
3
+ // The theme is a data attribute on <html>; template.html applies the stored
4
+ // or system preference before first paint, this module owns the toggle.
5
+ // Highlighting is deliberately conservative: a block is colored only when its
6
+ // language is known from a markdown fence, a diff signature, or the tool kind,
7
+ // never from auto-detection, so plain logs stay plain.
8
+ // Extends the BF namespace declared in viewer.js, like detail.js and catalog.js.
9
+
10
+ BF.theme = (() => {
11
+ const KEY = "bf-theme";
12
+
13
+ function current() {
14
+ return document.documentElement.dataset.theme === "dark" ? "dark" : "light";
15
+ }
16
+
17
+ function apply(theme) {
18
+ if (theme === "dark") document.documentElement.dataset.theme = "dark";
19
+ else delete document.documentElement.dataset.theme;
20
+ const button = document.getElementById("theme-toggle");
21
+ if (button) button.textContent = theme === "dark" ? "light" : "dark";
22
+ }
23
+
24
+ function toggle() {
25
+ const next = current() === "dark" ? "light" : "dark";
26
+ try { localStorage.setItem(KEY, next); } catch (e) { /* storage may be disabled */ }
27
+ apply(next);
28
+ }
29
+
30
+ function init() {
31
+ apply(current());
32
+ const button = document.getElementById("theme-toggle");
33
+ if (button) button.addEventListener("click", toggle);
34
+ }
35
+
36
+ return { init, toggle, current };
37
+ })();
38
+
39
+ BF.highlight = (() => {
40
+ const FENCE = /^```([A-Za-z0-9_+-]*)\s*\n/;
41
+ const HEREDOC = /^(.*?\b(?:python3?|python -)\b[^\n]*<<-?\s*['"]?(\w+)['"]?\s*\n)([\s\S]*?)(\n\2\b[\s\S]*)$/;
42
+ const EXTENSIONS = {
43
+ py: "python", sh: "bash", bash: "bash", json: "json", yaml: "yaml", yml: "yaml",
44
+ toml: "ini", ini: "ini", md: "markdown", c: "c", h: "c", cpp: "cpp", hpp: "cpp",
45
+ cc: "cpp", js: "javascript", mjs: "javascript", ts: "typescript", rs: "rust",
46
+ diff: "diff", patch: "diff",
47
+ };
48
+ const FENCE_ALIASES = { console: "shell", sh: "bash", shell: "shell", text: null, "": null };
49
+
50
+ function known(language) {
51
+ return language && window.hljs && hljs.getLanguage(language) ? language : null;
52
+ }
53
+
54
+ function fromFence(text) {
55
+ const match = text.match(FENCE);
56
+ if (!match) return null;
57
+ const name = match[1].toLowerCase();
58
+ return known(name in FENCE_ALIASES ? FENCE_ALIASES[name] : name);
59
+ }
60
+
61
+ function isDiff(text) {
62
+ const head = text.slice(0, 400);
63
+ return /^\*\*\* Begin Patch|^diff |^--- [^\n]*\n\+\+\+ |^@@ /m.test(head);
64
+ }
65
+
66
+ // Language for one content block of a tool card, or null to leave it plain.
67
+ function languageFor(text, hue, title, position) {
68
+ if (!window.hljs) return null;
69
+ const fenced = fromFence(text);
70
+ if (fenced) return fenced;
71
+ if (isDiff(text)) return "diff";
72
+ if (text.startsWith("```")) return null;
73
+ if (hue === "execute" && position === 0) return "bash";
74
+ if ((hue === "read" || hue === "edit") && typeof title === "string") {
75
+ const match = title.match(/\.([A-Za-z0-9]+)\s*$/);
76
+ if (match) return known(EXTENSIONS[match[1].toLowerCase()]);
77
+ }
78
+ return null;
79
+ }
80
+
81
+ function render(text, language) {
82
+ const options = { language, ignoreIllegals: true };
83
+ const heredoc = language === "bash" ? text.match(HEREDOC) : null;
84
+ if (heredoc && hljs.getLanguage("python")) {
85
+ return hljs.highlight(heredoc[1], options).value
86
+ + hljs.highlight(heredoc[3], { language: "python", ignoreIllegals: true }).value
87
+ + hljs.highlight(heredoc[4], options).value;
88
+ }
89
+ return hljs.highlight(text, options).value;
90
+ }
91
+
92
+ // Replace the block's text nodes with highlighted markup. Blocks that carry
93
+ // redaction markers keep their spans and are left uncolored.
94
+ function paint(block, text, language) {
95
+ if (!language || !window.hljs || block.querySelector(".redacted")) return;
96
+ if (block.textContent !== text) return;
97
+ block.innerHTML = render(text, language);
98
+ block.classList.add("hljs");
99
+ block.dataset.language = language;
100
+ }
101
+
102
+ return { languageFor, paint };
103
+ })();
@@ -0,0 +1,29 @@
1
+ BSD 3-Clause License
2
+
3
+ Copyright (c) 2006, Ivan Sagalaev.
4
+ All rights reserved.
5
+
6
+ Redistribution and use in source and binary forms, with or without
7
+ modification, are permitted provided that the following conditions are met:
8
+
9
+ * Redistributions of source code must retain the above copyright notice, this
10
+ list of conditions and the following disclaimer.
11
+
12
+ * Redistributions in binary form must reproduce the above copyright notice,
13
+ this list of conditions and the following disclaimer in the documentation
14
+ and/or other materials provided with the distribution.
15
+
16
+ * Neither the name of the copyright holder nor the names of its
17
+ contributors may be used to endorse or promote products derived from
18
+ this software without specific prior written permission.
19
+
20
+ THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
21
+ AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
22
+ IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
23
+ DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
24
+ FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
25
+ DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
26
+ SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
27
+ CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
28
+ OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29
+ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.