benchflow 0.7.11.dev2422__tar.gz → 0.9.1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- benchflow-0.9.1/.gitignore +198 -0
- benchflow-0.9.1/CHANGELOG.md +1809 -0
- benchflow-0.9.1/PKG-INFO +289 -0
- benchflow-0.9.1/README.md +211 -0
- benchflow-0.9.1/pyproject.toml +294 -0
- benchflow-0.9.1/src/benchflow/__init__.py +638 -0
- benchflow-0.9.1/src/benchflow/_bfx/__init__.py +45 -0
- benchflow-0.9.1/src/benchflow/_bfx/bin/bfx-aarch64 +0 -0
- benchflow-0.9.1/src/benchflow/_bfx/bin/bfx-x86_64 +0 -0
- benchflow-0.9.1/src/benchflow/_bfx/client.py +331 -0
- benchflow-0.9.1/src/benchflow/_bfx/delivery.py +875 -0
- benchflow-0.9.1/src/benchflow/_bfx/locate.py +107 -0
- benchflow-0.9.1/src/benchflow/_bfx/pins.py +18 -0
- benchflow-0.9.1/src/benchflow/_daemon.py +1404 -0
- benchflow-0.9.1/src/benchflow/_daemon_wire.py +150 -0
- benchflow-0.9.1/src/benchflow/_diagnostics.py +239 -0
- benchflow-0.9.1/src/benchflow/_image_python_paths.py +548 -0
- benchflow-0.9.1/src/benchflow/_kit_seal.py +781 -0
- benchflow-0.9.1/src/benchflow/_park.py +773 -0
- benchflow-0.9.1/src/benchflow/_proxy_zygote.py +649 -0
- benchflow-0.9.1/src/benchflow/_root_only.py +147 -0
- benchflow-0.9.1/src/benchflow/_root_python.py +134 -0
- benchflow-0.9.1/src/benchflow/_runtime_tree.py +1278 -0
- benchflow-0.9.1/src/benchflow/_types.py +106 -0
- benchflow-0.9.1/src/benchflow/_utils/archive_paths.py +83 -0
- benchflow-0.9.1/src/benchflow/_utils/artifact_names.py +46 -0
- benchflow-0.9.1/src/benchflow/_utils/benchmark_repos.py +1273 -0
- benchflow-0.9.1/src/benchflow/_utils/command_hints.py +62 -0
- benchflow-0.9.1/src/benchflow/_utils/config.py +98 -0
- benchflow-0.9.1/src/benchflow/_utils/config_keys.py +230 -0
- benchflow-0.9.1/src/benchflow/_utils/config_override.py +208 -0
- benchflow-0.9.1/src/benchflow/_utils/config_redaction.py +324 -0
- benchflow-0.9.1/src/benchflow/_utils/dataset_registry.json +632 -0
- benchflow-0.9.1/src/benchflow/_utils/dataset_registry.py +617 -0
- benchflow-0.9.1/src/benchflow/_utils/disk_space.py +153 -0
- benchflow-0.9.1/src/benchflow/_utils/env_registry.py +237 -0
- benchflow-0.9.1/src/benchflow/_utils/env_values.py +49 -0
- benchflow-0.9.1/src/benchflow/_utils/evaluation_results.py +344 -0
- benchflow-0.9.1/src/benchflow/_utils/hf_datasets.py +265 -0
- benchflow-0.9.1/src/benchflow/_utils/job_lock.py +87 -0
- benchflow-0.9.1/src/benchflow/_utils/kill_record.py +106 -0
- benchflow-0.9.1/src/benchflow/_utils/learner_memory.py +169 -0
- benchflow-0.9.1/src/benchflow/_utils/log_context.py +102 -0
- benchflow-0.9.1/src/benchflow/_utils/modal_gpu.py +59 -0
- benchflow-0.9.1/src/benchflow/_utils/path_lock_record.py +66 -0
- benchflow-0.9.1/src/benchflow/_utils/reachable_write.py +2828 -0
- benchflow-0.9.1/src/benchflow/_utils/reported_models.py +91 -0
- benchflow-0.9.1/src/benchflow/_utils/result_metadata.py +75 -0
- benchflow-0.9.1/src/benchflow/_utils/result_paths.py +128 -0
- benchflow-0.9.1/src/benchflow/_utils/sandbox_providers.py +249 -0
- benchflow-0.9.1/src/benchflow/_utils/scoring.py +966 -0
- benchflow-0.9.1/src/benchflow/_utils/session_cost.py +222 -0
- benchflow-0.9.1/src/benchflow/_utils/start_pacing.py +100 -0
- benchflow-0.9.1/src/benchflow/_utils/task_authoring/__init__.py +686 -0
- benchflow-0.9.1/src/benchflow/_utils/task_authoring/scaffolding.py +446 -0
- benchflow-0.9.1/src/benchflow/_utils/task_authoring/structural_checks.py +673 -0
- benchflow-0.9.1/src/benchflow/_utils/timing_spans.py +265 -0
- benchflow-0.9.1/src/benchflow/_utils/trial_warnings.py +36 -0
- benchflow-0.9.1/src/benchflow/_utils/trusted_path.py +179 -0
- benchflow-0.9.1/src/benchflow/_utils/yaml_loader.py +376 -0
- benchflow-0.9.1/src/benchflow/_uv_pin.py +364 -0
- benchflow-0.9.1/src/benchflow/_verifier_env.py +97 -0
- benchflow-0.9.1/src/benchflow/_warm_pool.py +339 -0
- benchflow-0.9.1/src/benchflow/acp/__init__.py +52 -0
- benchflow-0.9.1/src/benchflow/acp/client.py +671 -0
- benchflow-0.9.1/src/benchflow/acp/container_transport.py +168 -0
- benchflow-0.9.1/src/benchflow/acp/runtime.py +1127 -0
- benchflow-0.9.1/src/benchflow/acp/selection.py +30 -0
- benchflow-0.9.1/src/benchflow/acp/session.py +862 -0
- benchflow-0.9.1/src/benchflow/acp/transport.py +161 -0
- benchflow-0.9.1/src/benchflow/acp/types.py +479 -0
- benchflow-0.9.1/src/benchflow/acp/watchdog.py +367 -0
- benchflow-0.9.1/src/benchflow/adapters/__init__.py +56 -0
- benchflow-0.9.1/src/benchflow/adapters/_toolathlon.py +1222 -0
- benchflow-0.9.1/src/benchflow/adapters/_toolathlon_fake_mail.py +395 -0
- benchflow-0.9.1/src/benchflow/adapters/inbound.py +324 -0
- benchflow-0.9.1/src/benchflow/adapters/resources/mcp_atlas_judge.py +114 -0
- benchflow-0.9.1/src/benchflow/adapters/task_toml.py +146 -0
- benchflow-0.9.1/src/benchflow/agent_router.py +955 -0
- benchflow-0.9.1/src/benchflow/agent_router_scaffold.py +271 -0
- benchflow-0.9.1/src/benchflow/agent_start.py +158 -0
- benchflow-0.9.1/src/benchflow/agents/__init__.py +22 -0
- benchflow-0.9.1/src/benchflow/agents/_python_agent_pins.py +57 -0
- benchflow-0.9.1/src/benchflow/agents/antigravity_acp_shim.py +953 -0
- benchflow-0.9.1/src/benchflow/agents/antigravity_config.py +153 -0
- benchflow-0.9.1/src/benchflow/agents/codex_config.py +320 -0
- benchflow-0.9.1/src/benchflow/agents/codex_connector_policy.py +287 -0
- benchflow-0.9.1/src/benchflow/agents/credentials.py +544 -0
- benchflow-0.9.1/src/benchflow/agents/deepagents_acp_shim.py +613 -0
- benchflow-0.9.1/src/benchflow/agents/env.py +1228 -0
- benchflow-0.9.1/src/benchflow/agents/errors.py +254 -0
- benchflow-0.9.1/src/benchflow/agents/harvey_lab_acp_shim.py +810 -0
- benchflow-0.9.1/src/benchflow/agents/install.py +691 -0
- benchflow-0.9.1/src/benchflow/agents/launch_env.py +359 -0
- benchflow-0.9.1/src/benchflow/agents/login_dirs.py +71 -0
- benchflow-0.9.1/src/benchflow/agents/manifest.py +399 -0
- benchflow-0.9.1/src/benchflow/agents/muse_acp_shim.py +1175 -0
- benchflow-0.9.1/src/benchflow/agents/muse_config.py +142 -0
- benchflow-0.9.1/src/benchflow/agents/pi_acp_launcher.py +177 -0
- benchflow-0.9.1/src/benchflow/agents/providers.py +576 -0
- benchflow-0.9.1/src/benchflow/agents/registry.py +2501 -0
- benchflow-0.9.1/src/benchflow/agents/remote_manifests.py +280 -0
- benchflow-0.9.1/src/benchflow/agents/requirements/deepagents.txt +1633 -0
- benchflow-0.9.1/src/benchflow/agents/requirements/harvey-lab.txt +1109 -0
- benchflow-0.9.1/src/benchflow/agents/scripts.py +42 -0
- benchflow-0.9.1/src/benchflow/agents/usage_limits.py +336 -0
- benchflow-0.9.1/src/benchflow/batch.py +446 -0
- benchflow-0.9.1/src/benchflow/branch.py +188 -0
- benchflow-0.9.1/src/benchflow/branch_api.py +605 -0
- benchflow-0.9.1/src/benchflow/branch_artifacts.py +77 -0
- benchflow-0.9.1/src/benchflow/branch_lineage.py +390 -0
- benchflow-0.9.1/src/benchflow/branch_result.py +117 -0
- benchflow-0.9.1/src/benchflow/branch_run.py +909 -0
- benchflow-0.9.1/src/benchflow/branch_view.py +616 -0
- benchflow-0.9.1/src/benchflow/budget.py +721 -0
- benchflow-0.9.1/src/benchflow/checkpoint_retry.py +342 -0
- benchflow-0.9.1/src/benchflow/checkpoints.py +212 -0
- benchflow-0.9.1/src/benchflow/cli/_errors.py +736 -0
- benchflow-0.9.1/src/benchflow/cli/_failure_evidence.py +531 -0
- benchflow-0.9.1/src/benchflow/cli/_hosted_env.py +300 -0
- benchflow-0.9.1/src/benchflow/cli/_job_listing.py +187 -0
- benchflow-0.9.1/src/benchflow/cli/_lazy.py +242 -0
- benchflow-0.9.1/src/benchflow/cli/_live_progress.py +483 -0
- benchflow-0.9.1/src/benchflow/cli/_options.py +85 -0
- benchflow-0.9.1/src/benchflow/cli/_shared.py +813 -0
- benchflow-0.9.1/src/benchflow/cli/_termination.py +240 -0
- benchflow-0.9.1/src/benchflow/cli/adopt.py +191 -0
- benchflow-0.9.1/src/benchflow/cli/agent.py +198 -0
- benchflow-0.9.1/src/benchflow/cli/branch.py +638 -0
- benchflow-0.9.1/src/benchflow/cli/cache.py +649 -0
- benchflow-0.9.1/src/benchflow/cli/continue_cmd.py +285 -0
- benchflow-0.9.1/src/benchflow/cli/daemon.py +97 -0
- benchflow-0.9.1/src/benchflow/cli/doctor.py +824 -0
- benchflow-0.9.1/src/benchflow/cli/embodied.py +109 -0
- benchflow-0.9.1/src/benchflow/cli/eval_artifacts.py +804 -0
- benchflow-0.9.1/src/benchflow/cli/eval_lift.py +99 -0
- benchflow-0.9.1/src/benchflow/cli/eval_regrade.py +126 -0
- benchflow-0.9.1/src/benchflow/cli/explain.py +459 -0
- benchflow-0.9.1/src/benchflow/cli/hub.py +243 -0
- benchflow-0.9.1/src/benchflow/cli/main.py +3744 -0
- benchflow-0.9.1/src/benchflow/cli/new_verbs.py +789 -0
- benchflow-0.9.1/src/benchflow/cli/rescore.py +149 -0
- benchflow-0.9.1/src/benchflow/cli/results.py +519 -0
- benchflow-0.9.1/src/benchflow/cli/review.py +344 -0
- benchflow-0.9.1/src/benchflow/cli/reviewer_options.py +96 -0
- benchflow-0.9.1/src/benchflow/cli/sandbox.py +473 -0
- benchflow-0.9.1/src/benchflow/cli/skills.py +507 -0
- benchflow-0.9.1/src/benchflow/cli/tasks.py +917 -0
- benchflow-0.9.1/src/benchflow/cli/trace_import.py +454 -0
- benchflow-0.9.1/src/benchflow/cli/train.py +1095 -0
- benchflow-0.9.1/src/benchflow/cli/traj.py +1168 -0
- benchflow-0.9.1/src/benchflow/cli/verbs.py +628 -0
- benchflow-0.9.1/src/benchflow/cli_parity.py +406 -0
- benchflow-0.9.1/src/benchflow/continue_run/orchestrator.py +905 -0
- benchflow-0.9.1/src/benchflow/continue_run/run_folder.py +263 -0
- benchflow-0.9.1/src/benchflow/continue_run/sandbox_proxy.py +504 -0
- benchflow-0.9.1/src/benchflow/contracts/__init__.py +125 -0
- benchflow-0.9.1/src/benchflow/contracts/planes.py +235 -0
- benchflow-0.9.1/src/benchflow/contracts/user.py +298 -0
- benchflow-0.9.1/src/benchflow/diagnostics.py +998 -0
- benchflow-0.9.1/src/benchflow/doctor.py +2241 -0
- benchflow-0.9.1/src/benchflow/doctor_smoke.py +537 -0
- benchflow-0.9.1/src/benchflow/embodied/__init__.py +55 -0
- benchflow-0.9.1/src/benchflow/embodied/backend.py +60 -0
- benchflow-0.9.1/src/benchflow/embodied/cameras.py +66 -0
- benchflow-0.9.1/src/benchflow/embodied/export.py +175 -0
- benchflow-0.9.1/src/benchflow/embodied/protocol.py +65 -0
- benchflow-0.9.1/src/benchflow/embodied/robo.py +290 -0
- benchflow-0.9.1/src/benchflow/embodied/rollouts.py +318 -0
- benchflow-0.9.1/src/benchflow/embodied/serve.py +59 -0
- benchflow-0.9.1/src/benchflow/embodied/server.py +979 -0
- benchflow-0.9.1/src/benchflow/embodied/sidecar.py +468 -0
- benchflow-0.9.1/src/benchflow/embodied/skills.py +129 -0
- benchflow-0.9.1/src/benchflow/embodied/spec.py +712 -0
- benchflow-0.9.1/src/benchflow/embodied/templates/agent.Dockerfile +13 -0
- benchflow-0.9.1/src/benchflow/embodied/templates/docker-compose.yaml +52 -0
- benchflow-0.9.1/src/benchflow/embodied/templates/sim-entry.sh +22 -0
- benchflow-0.9.1/src/benchflow/embodied/templates/verifier/test.sh +8 -0
- benchflow-0.9.1/src/benchflow/embodied/templates/verifier/verifier.md +21 -0
- benchflow-0.9.1/src/benchflow/embodied/trials.py +68 -0
- benchflow-0.9.1/src/benchflow/embodied/verifier.py +112 -0
- benchflow-0.9.1/src/benchflow/environment/manifest_env.py +602 -0
- benchflow-0.9.1/src/benchflow/environment/protocol.py +79 -0
- benchflow-0.9.1/src/benchflow/environment/readiness.py +76 -0
- benchflow-0.9.1/src/benchflow/errors.py +67 -0
- benchflow-0.9.1/src/benchflow/eval_artifacts.py +482 -0
- benchflow-0.9.1/src/benchflow/eval_plan.py +866 -0
- benchflow-0.9.1/src/benchflow/eval_regrade.py +881 -0
- benchflow-0.9.1/src/benchflow/eval_sharding.py +608 -0
- benchflow-0.9.1/src/benchflow/eval_worker.py +195 -0
- benchflow-0.9.1/src/benchflow/evaluation.py +6251 -0
- benchflow-0.9.1/src/benchflow/experimental/mcp/hooks.py +56 -0
- benchflow-0.9.1/src/benchflow/experimental/mcp/reviewer_server.py +170 -0
- benchflow-0.9.1/src/benchflow/failures.py +652 -0
- benchflow-0.9.1/src/benchflow/hosted_env.py +1158 -0
- benchflow-0.9.1/src/benchflow/hub/__init__.py +19 -0
- benchflow-0.9.1/src/benchflow/hub/registry.py +306 -0
- benchflow-0.9.1/src/benchflow/integration_health.py +395 -0
- benchflow-0.9.1/src/benchflow/integrations/skillevaluator.py +796 -0
- benchflow-0.9.1/src/benchflow/integrations/trl/spec.py +483 -0
- benchflow-0.9.1/src/benchflow/integrity/__init__.py +78 -0
- benchflow-0.9.1/src/benchflow/integrity/access.py +611 -0
- benchflow-0.9.1/src/benchflow/integrity/agent_actions.py +708 -0
- benchflow-0.9.1/src/benchflow/integrity/authority.py +106 -0
- benchflow-0.9.1/src/benchflow/integrity/claim.py +406 -0
- benchflow-0.9.1/src/benchflow/integrity/classify.py +116 -0
- benchflow-0.9.1/src/benchflow/integrity/constants.py +204 -0
- benchflow-0.9.1/src/benchflow/integrity/contract.py +727 -0
- benchflow-0.9.1/src/benchflow/integrity/emit.py +1234 -0
- benchflow-0.9.1/src/benchflow/integrity/events.py +389 -0
- benchflow-0.9.1/src/benchflow/integrity/exec_decompose.py +1463 -0
- benchflow-0.9.1/src/benchflow/integrity/routes.py +227 -0
- benchflow-0.9.1/src/benchflow/integrity/selectors.py +122 -0
- benchflow-0.9.1/src/benchflow/integrity/trace_checker.py +871 -0
- benchflow-0.9.1/src/benchflow/integrity/trial.py +759 -0
- benchflow-0.9.1/src/benchflow/integrity/urls.py +468 -0
- benchflow-0.9.1/src/benchflow/integrity/verdict.py +162 -0
- benchflow-0.9.1/src/benchflow/job_config.py +732 -0
- benchflow-0.9.1/src/benchflow/job_export.py +1045 -0
- benchflow-0.9.1/src/benchflow/jobs.py +1912 -0
- benchflow-0.9.1/src/benchflow/key_check.py +177 -0
- benchflow-0.9.1/src/benchflow/learner_skills.py +149 -0
- benchflow-0.9.1/src/benchflow/metrics.py +519 -0
- benchflow-0.9.1/src/benchflow/models.py +450 -0
- benchflow-0.9.1/src/benchflow/monitor.py +209 -0
- benchflow-0.9.1/src/benchflow/native_harness/__init__.py +30 -0
- benchflow-0.9.1/src/benchflow/native_harness/_log_io.py +21 -0
- benchflow-0.9.1/src/benchflow/native_harness/claude_code.py +1003 -0
- benchflow-0.9.1/src/benchflow/native_harness/client.py +812 -0
- benchflow-0.9.1/src/benchflow/native_harness/codex.py +422 -0
- benchflow-0.9.1/src/benchflow/native_harness/harnesses.py +148 -0
- benchflow-0.9.1/src/benchflow/native_harness/runtime.py +210 -0
- benchflow-0.9.1/src/benchflow/native_harness/session.py +77 -0
- benchflow-0.9.1/src/benchflow/native_harness/spec.py +188 -0
- benchflow-0.9.1/src/benchflow/pass_at_k.py +482 -0
- benchflow-0.9.1/src/benchflow/providers/litellm_bedrock_patch.py +384 -0
- benchflow-0.9.1/src/benchflow/providers/litellm_bedrock_preflight.py +227 -0
- benchflow-0.9.1/src/benchflow/providers/litellm_config.py +509 -0
- benchflow-0.9.1/src/benchflow/providers/litellm_gemini_passthrough_patch.py +116 -0
- benchflow-0.9.1/src/benchflow/providers/litellm_lazy_start.py +332 -0
- benchflow-0.9.1/src/benchflow/providers/litellm_logging.py +960 -0
- benchflow-0.9.1/src/benchflow/providers/litellm_request_guard.py +1969 -0
- benchflow-0.9.1/src/benchflow/providers/litellm_runtime.py +3410 -0
- benchflow-0.9.1/src/benchflow/providers/litellm_token_capture_patch.py +145 -0
- benchflow-0.9.1/src/benchflow/providers/proxy_requirements/__init__.py +491 -0
- benchflow-0.9.1/src/benchflow/providers/proxy_requirements/litellm-proxy-vertex.txt +2369 -0
- benchflow-0.9.1/src/benchflow/providers/proxy_requirements/litellm-proxy.txt +2176 -0
- benchflow-0.9.1/src/benchflow/providers/restricted_endpoints.py +161 -0
- benchflow-0.9.1/src/benchflow/providers/restricted_model_allowlist.json +1706 -0
- benchflow-0.9.1/src/benchflow/providers/restricted_models.py +380 -0
- benchflow-0.9.1/src/benchflow/providers/runtime.py +167 -0
- benchflow-0.9.1/src/benchflow/publish/_snapshot.py +16 -0
- benchflow-0.9.1/src/benchflow/publish/huggingface.py +227 -0
- benchflow-0.9.1/src/benchflow/publish/traj_capture.py +848 -0
- benchflow-0.9.1/src/benchflow/review/automatic.py +236 -0
- benchflow-0.9.1/src/benchflow/review/config.py +387 -0
- benchflow-0.9.1/src/benchflow/review/evidence.py +1605 -0
- benchflow-0.9.1/src/benchflow/review/evidence_runtime.py +103 -0
- benchflow-0.9.1/src/benchflow/review/options.py +96 -0
- benchflow-0.9.1/src/benchflow/review/outcome.py +206 -0
- benchflow-0.9.1/src/benchflow/review/persistence.py +264 -0
- benchflow-0.9.1/src/benchflow/review/preflight.py +60 -0
- benchflow-0.9.1/src/benchflow/review/resume.py +353 -0
- benchflow-0.9.1/src/benchflow/review/runner.py +872 -0
- benchflow-0.9.1/src/benchflow/review/scoring.py +120 -0
- benchflow-0.9.1/src/benchflow/review/wrapper.py +406 -0
- benchflow-0.9.1/src/benchflow/rewards/README.md +125 -0
- benchflow-0.9.1/src/benchflow/rewards/__init__.py +103 -0
- benchflow-0.9.1/src/benchflow/rewards/_safe_evidence.py +384 -0
- benchflow-0.9.1/src/benchflow/rewards/builtins.py +542 -0
- benchflow-0.9.1/src/benchflow/rewards/file_readers.py +160 -0
- benchflow-0.9.1/src/benchflow/rewards/llm.py +325 -0
- benchflow-0.9.1/src/benchflow/rewards/node.py +165 -0
- benchflow-0.9.1/src/benchflow/rewards/protocol.py +93 -0
- benchflow-0.9.1/src/benchflow/rewards/rubric_config.py +285 -0
- benchflow-0.9.1/src/benchflow/rewards/validation.py +828 -0
- benchflow-0.9.1/src/benchflow/rollout/__init__.py +6341 -0
- benchflow-0.9.1/src/benchflow/rollout/_artifact_links.py +22 -0
- benchflow-0.9.1/src/benchflow/rollout/_artifacts.py +682 -0
- benchflow-0.9.1/src/benchflow/rollout/_config.py +662 -0
- benchflow-0.9.1/src/benchflow/rollout/_deadline.py +302 -0
- benchflow-0.9.1/src/benchflow/rollout/_recovery_submission.py +115 -0
- benchflow-0.9.1/src/benchflow/rollout/_results.py +752 -0
- benchflow-0.9.1/src/benchflow/rollout/_review.py +426 -0
- benchflow-0.9.1/src/benchflow/rollout/_separate_verifier.py +2806 -0
- benchflow-0.9.1/src/benchflow/rollout/_session_log.py +218 -0
- benchflow-0.9.1/src/benchflow/rollout/_setup.py +2604 -0
- benchflow-0.9.1/src/benchflow/rollout/_teardown_queue.py +127 -0
- benchflow-0.9.1/src/benchflow/rollout/_user_loop.py +560 -0
- benchflow-0.9.1/src/benchflow/rollout/_verifier_recovery.py +835 -0
- benchflow-0.9.1/src/benchflow/rollout/session_factory_runtime.py +264 -0
- benchflow-0.9.1/src/benchflow/rollout/task_runtime.py +337 -0
- benchflow-0.9.1/src/benchflow/rollout_branch.py +1259 -0
- benchflow-0.9.1/src/benchflow/rollout_planes.py +414 -0
- benchflow-0.9.1/src/benchflow/rubric_reviews.py +372 -0
- benchflow-0.9.1/src/benchflow/runtime.py +1082 -0
- benchflow-0.9.1/src/benchflow/sandbox/_base.py +2082 -0
- benchflow-0.9.1/src/benchflow/sandbox/_bind_targets.py +361 -0
- benchflow-0.9.1/src/benchflow/sandbox/_bounded_tar.py +56 -0
- benchflow-0.9.1/src/benchflow/sandbox/_cache_reclaim.py +103 -0
- benchflow-0.9.1/src/benchflow/sandbox/_compose.py +365 -0
- benchflow-0.9.1/src/benchflow/sandbox/_compose_build.py +283 -0
- benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-base.yaml +27 -0
- benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-kept-freezer.yaml +10 -0
- benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-no-net-raw.yaml +8 -0
- benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-no-new-privileges.yaml +9 -0
- benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-no-restart.yaml +12 -0
- benchflow-0.9.1/src/benchflow/sandbox/_compose_files/docker-compose-remote-base.yaml +26 -0
- benchflow-0.9.1/src/benchflow/sandbox/_compose_runtime.py +262 -0
- benchflow-0.9.1/src/benchflow/sandbox/_compose_teardown.py +137 -0
- benchflow-0.9.1/src/benchflow/sandbox/_dependency_options.py +582 -0
- benchflow-0.9.1/src/benchflow/sandbox/_dir_archive.py +109 -0
- benchflow-0.9.1/src/benchflow/sandbox/_direct_docker.py +1139 -0
- benchflow-0.9.1/src/benchflow/sandbox/_docker_subnets.py +1356 -0
- benchflow-0.9.1/src/benchflow/sandbox/_docker_sweep.py +503 -0
- benchflow-0.9.1/src/benchflow/sandbox/_download.py +113 -0
- benchflow-0.9.1/src/benchflow/sandbox/_egress_denylist_proxy.py +1626 -0
- benchflow-0.9.1/src/benchflow/sandbox/_engine_api.py +236 -0
- benchflow-0.9.1/src/benchflow/sandbox/_exec_channel.py +884 -0
- benchflow-0.9.1/src/benchflow/sandbox/_exec_merge.py +263 -0
- benchflow-0.9.1/src/benchflow/sandbox/_exec_output.py +79 -0
- benchflow-0.9.1/src/benchflow/sandbox/_exec_receipt.py +240 -0
- benchflow-0.9.1/src/benchflow/sandbox/_hardening_python.py +83 -0
- benchflow-0.9.1/src/benchflow/sandbox/_hook_cleanup.py +1313 -0
- benchflow-0.9.1/src/benchflow/sandbox/_hooks.py +18 -0
- benchflow-0.9.1/src/benchflow/sandbox/_host_copy.py +11 -0
- benchflow-0.9.1/src/benchflow/sandbox/_identities.py +307 -0
- benchflow-0.9.1/src/benchflow/sandbox/_in_order.py +46 -0
- benchflow-0.9.1/src/benchflow/sandbox/_inert_bootstrap.py +501 -0
- benchflow-0.9.1/src/benchflow/sandbox/_kit_cache.py +251 -0
- benchflow-0.9.1/src/benchflow/sandbox/_layer_lock.py +321 -0
- benchflow-0.9.1/src/benchflow/sandbox/_locked_path_validation.py +28 -0
- benchflow-0.9.1/src/benchflow/sandbox/_metadata_helper.py +707 -0
- benchflow-0.9.1/src/benchflow/sandbox/_mount_aliases.py +211 -0
- benchflow-0.9.1/src/benchflow/sandbox/_path_inspector_state.py +39 -0
- benchflow-0.9.1/src/benchflow/sandbox/_prepull.py +102 -0
- benchflow-0.9.1/src/benchflow/sandbox/_pull_provenance.py +183 -0
- benchflow-0.9.1/src/benchflow/sandbox/_pytest_plugin_guard.py +1810 -0
- benchflow-0.9.1/src/benchflow/sandbox/_recovery_baseline.py +142 -0
- benchflow-0.9.1/src/benchflow/sandbox/_recovery_submission.py +470 -0
- benchflow-0.9.1/src/benchflow/sandbox/_root_launch.py +550 -0
- benchflow-0.9.1/src/benchflow/sandbox/_sdk_ops.py +208 -0
- benchflow-0.9.1/src/benchflow/sandbox/_shell.py +8 -0
- benchflow-0.9.1/src/benchflow/sandbox/_snapshot_credentials.py +383 -0
- benchflow-0.9.1/src/benchflow/sandbox/_su.py +80 -0
- benchflow-0.9.1/src/benchflow/sandbox/_system_route_walk.py +238 -0
- benchflow-0.9.1/src/benchflow/sandbox/_task_route.py +41 -0
- benchflow-0.9.1/src/benchflow/sandbox/_transport.py +298 -0
- benchflow-0.9.1/src/benchflow/sandbox/_trial_volumes.py +203 -0
- benchflow-0.9.1/src/benchflow/sandbox/_verifier_runtime.py +2169 -0
- benchflow-0.9.1/src/benchflow/sandbox/_verifier_tool_state.py +360 -0
- benchflow-0.9.1/src/benchflow/sandbox/_workspace_ancestry.py +62 -0
- benchflow-0.9.1/src/benchflow/sandbox/_workspace_owner.py +146 -0
- benchflow-0.9.1/src/benchflow/sandbox/agent_exec.py +130 -0
- benchflow-0.9.1/src/benchflow/sandbox/agentcore.py +1350 -0
- benchflow-0.9.1/src/benchflow/sandbox/agentcore_builder.py +659 -0
- benchflow-0.9.1/src/benchflow/sandbox/agentcore_image.py +266 -0
- benchflow-0.9.1/src/benchflow/sandbox/agentcore_provisioning.py +497 -0
- benchflow-0.9.1/src/benchflow/sandbox/apple_container.py +877 -0
- benchflow-0.9.1/src/benchflow/sandbox/cloud_metadata.py +425 -0
- benchflow-0.9.1/src/benchflow/sandbox/daytona.py +2889 -0
- benchflow-0.9.1/src/benchflow/sandbox/daytona_content_snapshots.py +836 -0
- benchflow-0.9.1/src/benchflow/sandbox/daytona_delete.py +65 -0
- benchflow-0.9.1/src/benchflow/sandbox/daytona_dind.py +1631 -0
- benchflow-0.9.1/src/benchflow/sandbox/daytona_layers.py +584 -0
- benchflow-0.9.1/src/benchflow/sandbox/daytona_ledger.py +598 -0
- benchflow-0.9.1/src/benchflow/sandbox/daytona_pty.py +187 -0
- benchflow-0.9.1/src/benchflow/sandbox/daytona_reaper.py +611 -0
- benchflow-0.9.1/src/benchflow/sandbox/daytona_start.py +273 -0
- benchflow-0.9.1/src/benchflow/sandbox/daytona_strategies.py +1072 -0
- benchflow-0.9.1/src/benchflow/sandbox/docker.py +6219 -0
- benchflow-0.9.1/src/benchflow/sandbox/egress_denylist.py +555 -0
- benchflow-0.9.1/src/benchflow/sandbox/env_layers.py +2645 -0
- benchflow-0.9.1/src/benchflow/sandbox/firewall_power.py +1350 -0
- benchflow-0.9.1/src/benchflow/sandbox/image_build.py +235 -0
- benchflow-0.9.1/src/benchflow/sandbox/lockdown.py +13660 -0
- benchflow-0.9.1/src/benchflow/sandbox/metadata.py +57 -0
- benchflow-0.9.1/src/benchflow/sandbox/modal_impl.py +891 -0
- benchflow-0.9.1/src/benchflow/sandbox/native_agent_env.py +118 -0
- benchflow-0.9.1/src/benchflow/sandbox/native_oauth.py +260 -0
- benchflow-0.9.1/src/benchflow/sandbox/oracle_egress.py +411 -0
- benchflow-0.9.1/src/benchflow/sandbox/process/__init__.py +42 -0
- benchflow-0.9.1/src/benchflow/sandbox/process/_acp_lines.py +202 -0
- benchflow-0.9.1/src/benchflow/sandbox/process/_base.py +341 -0
- benchflow-0.9.1/src/benchflow/sandbox/process/agentcore.py +481 -0
- benchflow-0.9.1/src/benchflow/sandbox/process/apple.py +206 -0
- benchflow-0.9.1/src/benchflow/sandbox/process/daytona.py +1060 -0
- benchflow-0.9.1/src/benchflow/sandbox/process/docker.py +288 -0
- benchflow-0.9.1/src/benchflow/sandbox/process/modal.py +424 -0
- benchflow-0.9.1/src/benchflow/sandbox/protocol.py +284 -0
- benchflow-0.9.1/src/benchflow/sandbox/providers.py +54 -0
- benchflow-0.9.1/src/benchflow/sandbox/recovery_network.py +69 -0
- benchflow-0.9.1/src/benchflow/sandbox/remote_docker.py +1846 -0
- benchflow-0.9.1/src/benchflow/sandbox/services.py +126 -0
- benchflow-0.9.1/src/benchflow/sandbox/setup.py +1088 -0
- benchflow-0.9.1/src/benchflow/sandbox/snapshot.py +119 -0
- benchflow-0.9.1/src/benchflow/sandbox/verifier_layers.py +677 -0
- benchflow-0.9.1/src/benchflow/sdk.py +256 -0
- benchflow-0.9.1/src/benchflow/self_gen.py +206 -0
- benchflow-0.9.1/src/benchflow/skill_eval/_core.py +834 -0
- benchflow-0.9.1/src/benchflow/skill_eval/gepa_export.py +199 -0
- benchflow-0.9.1/src/benchflow/task/__init__.py +392 -0
- benchflow-0.9.1/src/benchflow/task/_document_normalize.py +216 -0
- benchflow-0.9.1/src/benchflow/task/_document_parse.py +636 -0
- benchflow-0.9.1/src/benchflow/task/_document_profiles.py +160 -0
- benchflow-0.9.1/src/benchflow/task/acceptance_live.py +461 -0
- benchflow-0.9.1/src/benchflow/task/artifacts.py +49 -0
- benchflow-0.9.1/src/benchflow/task/canary.py +63 -0
- benchflow-0.9.1/src/benchflow/task/compose_env.py +3127 -0
- benchflow-0.9.1/src/benchflow/task/compose_load.py +650 -0
- benchflow-0.9.1/src/benchflow/task/config.py +1449 -0
- benchflow-0.9.1/src/benchflow/task/env.py +330 -0
- benchflow-0.9.1/src/benchflow/task/equivalence.py +658 -0
- benchflow-0.9.1/src/benchflow/task/equivalence_variants.py +968 -0
- benchflow-0.9.1/src/benchflow/task/export.py +566 -0
- benchflow-0.9.1/src/benchflow/task/formats.py +191 -0
- benchflow-0.9.1/src/benchflow/task/identity_switch.py +117 -0
- benchflow-0.9.1/src/benchflow/task/imports.py +487 -0
- benchflow-0.9.1/src/benchflow/task/keep_services.py +764 -0
- benchflow-0.9.1/src/benchflow/task/package.py +174 -0
- benchflow-0.9.1/src/benchflow/task/paths.py +424 -0
- benchflow-0.9.1/src/benchflow/task/plan_validation.py +223 -0
- benchflow-0.9.1/src/benchflow/task/runtime_capabilities.py +1080 -0
- benchflow-0.9.1/src/benchflow/task/runtime_view.py +181 -0
- benchflow-0.9.1/src/benchflow/task/staging.py +415 -0
- benchflow-0.9.1/src/benchflow/task/task.py +91 -0
- benchflow-0.9.1/src/benchflow/task/tb2_keep_services.json +57 -0
- benchflow-0.9.1/src/benchflow/task/verifier.py +53 -0
- benchflow-0.9.1/src/benchflow/task/verifier_core.py +2356 -0
- benchflow-0.9.1/src/benchflow/task/verifier_criteria_runner.py +166 -0
- benchflow-0.9.1/src/benchflow/task/verifier_document.py +447 -0
- benchflow-0.9.1/src/benchflow/task/verifier_errors.py +201 -0
- benchflow-0.9.1/src/benchflow/task/verifier_judge_inputs.py +84 -0
- benchflow-0.9.1/src/benchflow/task/verifier_ors_episode.py +307 -0
- benchflow-0.9.1/src/benchflow/task/verifier_sandbox.py +399 -0
- benchflow-0.9.1/src/benchflow/task/verifier_scan.py +112 -0
- benchflow-0.9.1/src/benchflow/task/verifier_script_strategy.py +136 -0
- benchflow-0.9.1/src/benchflow/taskmd/__init__.py +49 -0
- benchflow-0.9.1/src/benchflow/taskmd/_util.py +15 -0
- benchflow-0.9.1/src/benchflow/taskmd/_vendor/VENDOR.json +19 -0
- benchflow-0.9.1/src/benchflow/taskmd/_vendor/__init__.py +21 -0
- benchflow-0.9.1/src/benchflow/taskmd/_vendor/judgeprompt.py +1617 -0
- benchflow-0.9.1/src/benchflow/taskmd/_vendor/taskmd.py +3472 -0
- benchflow-0.9.1/src/benchflow/taskmd/check.py +95 -0
- benchflow-0.9.1/src/benchflow/taskmd/family.py +293 -0
- benchflow-0.9.1/src/benchflow/taskmd/grading.py +320 -0
- benchflow-0.9.1/src/benchflow/taskmd/judging.py +1564 -0
- benchflow-0.9.1/src/benchflow/taskmd/launch.py +99 -0
- benchflow-0.9.1/src/benchflow/taskmd/materialize.py +701 -0
- benchflow-0.9.1/src/benchflow/taskmd/plan.py +1915 -0
- benchflow-0.9.1/src/benchflow/taskmd/reference.py +93 -0
- benchflow-0.9.1/src/benchflow/taskmd/trajectory.py +236 -0
- benchflow-0.9.1/src/benchflow/taskmd/verify.py +2423 -0
- benchflow-0.9.1/src/benchflow/templates/judge.py.tmpl +219 -0
- benchflow-0.9.1/src/benchflow/traces/huggingface.py +672 -0
- benchflow-0.9.1/src/benchflow/traces/parsers.py +503 -0
- benchflow-0.9.1/src/benchflow/trajectories/_capture.py +584 -0
- benchflow-0.9.1/src/benchflow/trajectories/_export_common.py +144 -0
- benchflow-0.9.1/src/benchflow/trajectories/_llm_capture.py +55 -0
- benchflow-0.9.1/src/benchflow/trajectories/_snapshot.py +57 -0
- benchflow-0.9.1/src/benchflow/trajectories/branch_row_schema.py +255 -0
- benchflow-0.9.1/src/benchflow/trajectories/export.py +295 -0
- benchflow-0.9.1/src/benchflow/trajectories/export_adp.py +271 -0
- benchflow-0.9.1/src/benchflow/trajectories/export_atif.py +471 -0
- benchflow-0.9.1/src/benchflow/trajectories/export_branch.py +721 -0
- benchflow-0.9.1/src/benchflow/trajectories/export_prime_sft.py +1620 -0
- benchflow-0.9.1/src/benchflow/trajectories/export_trl_sft.py +753 -0
- benchflow-0.9.1/src/benchflow/trajectories/results.py +925 -0
- benchflow-0.9.1/src/benchflow/trajectories/rollout_stream.py +962 -0
- benchflow-0.9.1/src/benchflow/trajectories/sft_subagents.py +586 -0
- benchflow-0.9.1/src/benchflow/trajectories/token_capture.py +538 -0
- benchflow-0.9.1/src/benchflow/trajectories/training_signal.py +631 -0
- benchflow-0.9.1/src/benchflow/trajectories/types.py +808 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/boot.js +182 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/catalog.js +400 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/detail.js +1142 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/template.html +51 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/viewer.css +362 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/assets/viewer.js +86 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/catalog.py +159 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/legacy.py +780 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/models.py +816 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/payload.py +1293 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/render.py +108 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/server.py +536 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/sources.py +191 -0
- benchflow-0.9.1/src/benchflow/trajectories/viewer/subagents.py +182 -0
- benchflow-0.9.1/src/benchflow/trust/__init__.py +9 -0
- benchflow-0.9.1/src/benchflow/trust/ingress.py +219 -0
- benchflow-0.9.1/src/benchflow/trust/state.py +1104 -0
- benchflow-0.7.11.dev2422/.gitignore +0 -190
- benchflow-0.7.11.dev2422/CHANGELOG.md +0 -1334
- benchflow-0.7.11.dev2422/PKG-INFO +0 -320
- benchflow-0.7.11.dev2422/README.md +0 -245
- benchflow-0.7.11.dev2422/pyproject.toml +0 -231
- benchflow-0.7.11.dev2422/src/benchflow/__init__.py +0 -283
- benchflow-0.7.11.dev2422/src/benchflow/_run.py +0 -34
- benchflow-0.7.11.dev2422/src/benchflow/_types.py +0 -106
- benchflow-0.7.11.dev2422/src/benchflow/_utils/benchmark_repos.py +0 -551
- benchflow-0.7.11.dev2422/src/benchflow/_utils/config.py +0 -82
- benchflow-0.7.11.dev2422/src/benchflow/_utils/config_override.py +0 -155
- benchflow-0.7.11.dev2422/src/benchflow/_utils/config_redaction.py +0 -55
- benchflow-0.7.11.dev2422/src/benchflow/_utils/dataset_registry.py +0 -250
- benchflow-0.7.11.dev2422/src/benchflow/_utils/env_registry.py +0 -236
- benchflow-0.7.11.dev2422/src/benchflow/_utils/evaluation_results.py +0 -306
- benchflow-0.7.11.dev2422/src/benchflow/_utils/hf_datasets.py +0 -244
- benchflow-0.7.11.dev2422/src/benchflow/_utils/learner_memory.py +0 -166
- benchflow-0.7.11.dev2422/src/benchflow/_utils/result_metadata.py +0 -75
- benchflow-0.7.11.dev2422/src/benchflow/_utils/result_paths.py +0 -74
- benchflow-0.7.11.dev2422/src/benchflow/_utils/scoring.py +0 -460
- benchflow-0.7.11.dev2422/src/benchflow/_utils/task_authoring/__init__.py +0 -386
- benchflow-0.7.11.dev2422/src/benchflow/_utils/task_authoring/scaffolding.py +0 -425
- benchflow-0.7.11.dev2422/src/benchflow/_utils/task_authoring/structural_checks.py +0 -367
- benchflow-0.7.11.dev2422/src/benchflow/_utils/yaml_loader.py +0 -175
- benchflow-0.7.11.dev2422/src/benchflow/acp/__init__.py +0 -22
- benchflow-0.7.11.dev2422/src/benchflow/acp/client.py +0 -437
- benchflow-0.7.11.dev2422/src/benchflow/acp/container_transport.py +0 -145
- benchflow-0.7.11.dev2422/src/benchflow/acp/runtime.py +0 -906
- benchflow-0.7.11.dev2422/src/benchflow/acp/selection.py +0 -30
- benchflow-0.7.11.dev2422/src/benchflow/acp/session.py +0 -570
- benchflow-0.7.11.dev2422/src/benchflow/acp/transport.py +0 -145
- benchflow-0.7.11.dev2422/src/benchflow/acp/types.py +0 -385
- benchflow-0.7.11.dev2422/src/benchflow/acp/watchdog.py +0 -249
- benchflow-0.7.11.dev2422/src/benchflow/adapters/__init__.py +0 -56
- benchflow-0.7.11.dev2422/src/benchflow/adapters/_toolathlon.py +0 -1121
- benchflow-0.7.11.dev2422/src/benchflow/adapters/_toolathlon_fake_mail.py +0 -398
- benchflow-0.7.11.dev2422/src/benchflow/adapters/_toolathlon_poste_users.tsv +0 -503
- benchflow-0.7.11.dev2422/src/benchflow/adapters/harbor.py +0 -148
- benchflow-0.7.11.dev2422/src/benchflow/adapters/inbound.py +0 -326
- benchflow-0.7.11.dev2422/src/benchflow/adapters/resources/mcp_atlas_judge.py +0 -107
- benchflow-0.7.11.dev2422/src/benchflow/agent_router.py +0 -953
- benchflow-0.7.11.dev2422/src/benchflow/agent_router_scaffold.py +0 -271
- benchflow-0.7.11.dev2422/src/benchflow/agents/__init__.py +0 -27
- benchflow-0.7.11.dev2422/src/benchflow/agents/antigravity_acp_shim.py +0 -874
- benchflow-0.7.11.dev2422/src/benchflow/agents/antigravity_config.py +0 -137
- benchflow-0.7.11.dev2422/src/benchflow/agents/codex_config.py +0 -179
- benchflow-0.7.11.dev2422/src/benchflow/agents/credentials.py +0 -229
- benchflow-0.7.11.dev2422/src/benchflow/agents/deepagents_acp_shim.py +0 -530
- benchflow-0.7.11.dev2422/src/benchflow/agents/env.py +0 -845
- benchflow-0.7.11.dev2422/src/benchflow/agents/errors.py +0 -7
- benchflow-0.7.11.dev2422/src/benchflow/agents/harvey_lab_acp_shim.py +0 -749
- benchflow-0.7.11.dev2422/src/benchflow/agents/install.py +0 -373
- benchflow-0.7.11.dev2422/src/benchflow/agents/manifest.py +0 -359
- benchflow-0.7.11.dev2422/src/benchflow/agents/openclaw_acp_shim.py +0 -973
- benchflow-0.7.11.dev2422/src/benchflow/agents/pi_acp_launcher.py +0 -171
- benchflow-0.7.11.dev2422/src/benchflow/agents/providers.py +0 -545
- benchflow-0.7.11.dev2422/src/benchflow/agents/registry.py +0 -1652
- benchflow-0.7.11.dev2422/src/benchflow/agents/remote_manifests.py +0 -171
- benchflow-0.7.11.dev2422/src/benchflow/branch.py +0 -74
- benchflow-0.7.11.dev2422/src/benchflow/cli/_failure_evidence.py +0 -302
- benchflow-0.7.11.dev2422/src/benchflow/cli/_hosted_env.py +0 -185
- benchflow-0.7.11.dev2422/src/benchflow/cli/_live_progress.py +0 -436
- benchflow-0.7.11.dev2422/src/benchflow/cli/_options.py +0 -33
- benchflow-0.7.11.dev2422/src/benchflow/cli/_shared.py +0 -254
- benchflow-0.7.11.dev2422/src/benchflow/cli/adopt.py +0 -190
- benchflow-0.7.11.dev2422/src/benchflow/cli/agent.py +0 -93
- benchflow-0.7.11.dev2422/src/benchflow/cli/continue_cmd.py +0 -275
- benchflow-0.7.11.dev2422/src/benchflow/cli/eval_artifacts.py +0 -350
- benchflow-0.7.11.dev2422/src/benchflow/cli/eval_lift.py +0 -95
- benchflow-0.7.11.dev2422/src/benchflow/cli/hub.py +0 -199
- benchflow-0.7.11.dev2422/src/benchflow/cli/main.py +0 -1420
- benchflow-0.7.11.dev2422/src/benchflow/cli/rescore.py +0 -116
- benchflow-0.7.11.dev2422/src/benchflow/cli/review.py +0 -278
- benchflow-0.7.11.dev2422/src/benchflow/cli/reviewer_options.py +0 -62
- benchflow-0.7.11.dev2422/src/benchflow/cli/sandbox.py +0 -243
- benchflow-0.7.11.dev2422/src/benchflow/cli/skills.py +0 -476
- benchflow-0.7.11.dev2422/src/benchflow/cli/tasks.py +0 -488
- benchflow-0.7.11.dev2422/src/benchflow/cli/trace_import.py +0 -426
- benchflow-0.7.11.dev2422/src/benchflow/cli/train.py +0 -632
- benchflow-0.7.11.dev2422/src/benchflow/cli/traj.py +0 -1123
- benchflow-0.7.11.dev2422/src/benchflow/continue_run/orchestrator.py +0 -747
- benchflow-0.7.11.dev2422/src/benchflow/continue_run/run_folder.py +0 -211
- benchflow-0.7.11.dev2422/src/benchflow/continue_run/sandbox_proxy.py +0 -472
- benchflow-0.7.11.dev2422/src/benchflow/contracts/__init__.py +0 -72
- benchflow-0.7.11.dev2422/src/benchflow/contracts/planes.py +0 -146
- benchflow-0.7.11.dev2422/src/benchflow/contracts/user.py +0 -294
- benchflow-0.7.11.dev2422/src/benchflow/diagnostics.py +0 -567
- benchflow-0.7.11.dev2422/src/benchflow/environment/manifest_env.py +0 -359
- benchflow-0.7.11.dev2422/src/benchflow/environment/protocol.py +0 -77
- benchflow-0.7.11.dev2422/src/benchflow/environment/readiness.py +0 -74
- benchflow-0.7.11.dev2422/src/benchflow/eval_artifacts.py +0 -463
- benchflow-0.7.11.dev2422/src/benchflow/eval_plan.py +0 -512
- benchflow-0.7.11.dev2422/src/benchflow/eval_sharding.py +0 -438
- benchflow-0.7.11.dev2422/src/benchflow/eval_worker.py +0 -137
- benchflow-0.7.11.dev2422/src/benchflow/evaluation.py +0 -2048
- benchflow-0.7.11.dev2422/src/benchflow/experimental/mcp/hooks.py +0 -52
- benchflow-0.7.11.dev2422/src/benchflow/experimental/mcp/reviewer_server.py +0 -141
- benchflow-0.7.11.dev2422/src/benchflow/hosted_env.py +0 -913
- benchflow-0.7.11.dev2422/src/benchflow/hub/__init__.py +0 -19
- benchflow-0.7.11.dev2422/src/benchflow/hub/harbor_registry.py +0 -289
- benchflow-0.7.11.dev2422/src/benchflow/integrations/skillevaluator.py +0 -790
- benchflow-0.7.11.dev2422/src/benchflow/integrations/trl/spec.py +0 -464
- benchflow-0.7.11.dev2422/src/benchflow/learner_skills.py +0 -142
- benchflow-0.7.11.dev2422/src/benchflow/metrics.py +0 -412
- benchflow-0.7.11.dev2422/src/benchflow/models.py +0 -245
- benchflow-0.7.11.dev2422/src/benchflow/monitor.py +0 -209
- benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_bedrock_patch.py +0 -128
- benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_bedrock_preflight.py +0 -185
- benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_config.py +0 -500
- benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_gemini_passthrough_patch.py +0 -116
- benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_logging.py +0 -655
- benchflow-0.7.11.dev2422/src/benchflow/providers/litellm_runtime.py +0 -1825
- benchflow-0.7.11.dev2422/src/benchflow/providers/runtime.py +0 -90
- benchflow-0.7.11.dev2422/src/benchflow/publish/huggingface.py +0 -223
- benchflow-0.7.11.dev2422/src/benchflow/publish/traj_capture.py +0 -825
- benchflow-0.7.11.dev2422/src/benchflow/review/automatic.py +0 -226
- benchflow-0.7.11.dev2422/src/benchflow/review/config.py +0 -373
- benchflow-0.7.11.dev2422/src/benchflow/review/evidence.py +0 -757
- benchflow-0.7.11.dev2422/src/benchflow/review/evidence_runtime.py +0 -49
- benchflow-0.7.11.dev2422/src/benchflow/review/options.py +0 -83
- benchflow-0.7.11.dev2422/src/benchflow/review/outcome.py +0 -175
- benchflow-0.7.11.dev2422/src/benchflow/review/persistence.py +0 -215
- benchflow-0.7.11.dev2422/src/benchflow/review/preflight.py +0 -53
- benchflow-0.7.11.dev2422/src/benchflow/review/resume.py +0 -174
- benchflow-0.7.11.dev2422/src/benchflow/review/runner.py +0 -810
- benchflow-0.7.11.dev2422/src/benchflow/review/scoring.py +0 -119
- benchflow-0.7.11.dev2422/src/benchflow/review/wrapper.py +0 -415
- benchflow-0.7.11.dev2422/src/benchflow/rewards/README.md +0 -125
- benchflow-0.7.11.dev2422/src/benchflow/rewards/__init__.py +0 -49
- benchflow-0.7.11.dev2422/src/benchflow/rewards/builtins.py +0 -527
- benchflow-0.7.11.dev2422/src/benchflow/rewards/file_readers.py +0 -142
- benchflow-0.7.11.dev2422/src/benchflow/rewards/llm.py +0 -307
- benchflow-0.7.11.dev2422/src/benchflow/rewards/node.py +0 -164
- benchflow-0.7.11.dev2422/src/benchflow/rewards/protocol.py +0 -89
- benchflow-0.7.11.dev2422/src/benchflow/rewards/rubric_config.py +0 -287
- benchflow-0.7.11.dev2422/src/benchflow/rewards/validation.py +0 -674
- benchflow-0.7.11.dev2422/src/benchflow/rollout/__init__.py +0 -2885
- benchflow-0.7.11.dev2422/src/benchflow/rollout/_config.py +0 -451
- benchflow-0.7.11.dev2422/src/benchflow/rollout/_deadline.py +0 -178
- benchflow-0.7.11.dev2422/src/benchflow/rollout/_results.py +0 -622
- benchflow-0.7.11.dev2422/src/benchflow/rollout/_review.py +0 -191
- benchflow-0.7.11.dev2422/src/benchflow/rollout/_separate_verifier.py +0 -651
- benchflow-0.7.11.dev2422/src/benchflow/rollout/_setup.py +0 -589
- benchflow-0.7.11.dev2422/src/benchflow/rollout/_user_loop.py +0 -556
- benchflow-0.7.11.dev2422/src/benchflow/rollout/session_factory_runtime.py +0 -187
- benchflow-0.7.11.dev2422/src/benchflow/rollout/task_runtime.py +0 -293
- benchflow-0.7.11.dev2422/src/benchflow/rollout_branch.py +0 -222
- benchflow-0.7.11.dev2422/src/benchflow/rollout_planes.py +0 -257
- benchflow-0.7.11.dev2422/src/benchflow/runtime.py +0 -471
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/_base.py +0 -498
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/_cache_reclaim.py +0 -95
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/_compose.py +0 -74
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/_compose_files/docker-compose-base.yaml +0 -17
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/_egress_denylist_proxy.py +0 -914
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/_sdk_ops.py +0 -103
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/agentcore.py +0 -1061
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/agentcore_builder.py +0 -653
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/agentcore_image.py +0 -199
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/agentcore_provisioning.py +0 -362
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/apple_container.py +0 -620
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/daytona.py +0 -976
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/daytona_dind.py +0 -850
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/daytona_pty.py +0 -142
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/daytona_reaper.py +0 -264
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/daytona_strategies.py +0 -400
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/docker.py +0 -958
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/egress_denylist.py +0 -375
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/lockdown.py +0 -1451
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/metadata.py +0 -34
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/modal_impl.py +0 -410
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/__init__.py +0 -39
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/_base.py +0 -282
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/agentcore.py +0 -413
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/apple.py +0 -135
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/daytona.py +0 -670
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/process/docker.py +0 -185
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/protocol.py +0 -195
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/providers.py +0 -149
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/services.py +0 -119
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/setup.py +0 -884
- benchflow-0.7.11.dev2422/src/benchflow/sandbox/snapshot.py +0 -107
- benchflow-0.7.11.dev2422/src/benchflow/sdk.py +0 -237
- benchflow-0.7.11.dev2422/src/benchflow/self_gen.py +0 -200
- benchflow-0.7.11.dev2422/src/benchflow/skill_eval/_core.py +0 -837
- benchflow-0.7.11.dev2422/src/benchflow/skill_eval/gepa_export.py +0 -195
- benchflow-0.7.11.dev2422/src/benchflow/task/__init__.py +0 -201
- benchflow-0.7.11.dev2422/src/benchflow/task/_document_normalize.py +0 -213
- benchflow-0.7.11.dev2422/src/benchflow/task/_document_parse.py +0 -598
- benchflow-0.7.11.dev2422/src/benchflow/task/_document_profiles.py +0 -156
- benchflow-0.7.11.dev2422/src/benchflow/task/acceptance_live.py +0 -522
- benchflow-0.7.11.dev2422/src/benchflow/task/config.py +0 -1142
- benchflow-0.7.11.dev2422/src/benchflow/task/env.py +0 -41
- benchflow-0.7.11.dev2422/src/benchflow/task/export.py +0 -547
- benchflow-0.7.11.dev2422/src/benchflow/task/imports.py +0 -238
- benchflow-0.7.11.dev2422/src/benchflow/task/package.py +0 -170
- benchflow-0.7.11.dev2422/src/benchflow/task/paths.py +0 -390
- benchflow-0.7.11.dev2422/src/benchflow/task/runtime_capabilities.py +0 -855
- benchflow-0.7.11.dev2422/src/benchflow/task/runtime_view.py +0 -170
- benchflow-0.7.11.dev2422/src/benchflow/task/task.py +0 -68
- benchflow-0.7.11.dev2422/src/benchflow/task/verifier.py +0 -167
- benchflow-0.7.11.dev2422/src/benchflow/task/verifier_core.py +0 -1236
- benchflow-0.7.11.dev2422/src/benchflow/task/verifier_document.py +0 -412
- benchflow-0.7.11.dev2422/src/benchflow/task/verifier_errors.py +0 -57
- benchflow-0.7.11.dev2422/src/benchflow/task/verifier_judge_inputs.py +0 -77
- benchflow-0.7.11.dev2422/src/benchflow/task/verifier_ors_episode.py +0 -300
- benchflow-0.7.11.dev2422/src/benchflow/task/verifier_reward_kit.py +0 -166
- benchflow-0.7.11.dev2422/src/benchflow/task/verifier_sandbox.py +0 -241
- benchflow-0.7.11.dev2422/src/benchflow/task/verifier_scan.py +0 -65
- benchflow-0.7.11.dev2422/src/benchflow/task/verifier_script_strategy.py +0 -87
- benchflow-0.7.11.dev2422/src/benchflow/templates/judge.py.tmpl +0 -213
- benchflow-0.7.11.dev2422/src/benchflow/traces/huggingface.py +0 -607
- benchflow-0.7.11.dev2422/src/benchflow/traces/parsers.py +0 -496
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/_capture.py +0 -446
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/_export_common.py +0 -116
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/_llm_capture.py +0 -50
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/_snapshot.py +0 -39
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/export.py +0 -288
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/export_adp.py +0 -264
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/export_atif.py +0 -229
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/export_prime_sft.py +0 -1335
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/export_trl_sft.py +0 -651
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/results.py +0 -717
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/types.py +0 -693
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/boot.js +0 -136
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/catalog.js +0 -331
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/detail.js +0 -784
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/template.html +0 -50
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/viewer.css +0 -353
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/assets/viewer.js +0 -67
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/catalog.py +0 -90
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/legacy.py +0 -760
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/models.py +0 -449
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/payload.py +0 -724
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/render.py +0 -102
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/server.py +0 -439
- benchflow-0.7.11.dev2422/src/benchflow/trajectories/viewer/sources.py +0 -186
- benchflow-0.7.11.dev2422/tests/__init__.py +0 -1
- benchflow-0.7.11.dev2422/tests/acceptance_live_harness.py +0 -313
- benchflow-0.7.11.dev2422/tests/agents/__init__.py +0 -1
- benchflow-0.7.11.dev2422/tests/agents/test_codex_config.py +0 -117
- benchflow-0.7.11.dev2422/tests/agents/test_manifest_dirscan.py +0 -246
- benchflow-0.7.11.dev2422/tests/agents/test_manifest_loader.py +0 -153
- benchflow-0.7.11.dev2422/tests/agents/test_manifest_parity.py +0 -265
- benchflow-0.7.11.dev2422/tests/agents/test_manifest_wiring.py +0 -158
- benchflow-0.7.11.dev2422/tests/agents/test_namespace_shorthand.py +0 -82
- benchflow-0.7.11.dev2422/tests/agents/test_plugin_entry_points.py +0 -98
- benchflow-0.7.11.dev2422/tests/agents/test_protocol.py +0 -229
- benchflow-0.7.11.dev2422/tests/agents/test_remote_manifest_autoload.py +0 -109
- benchflow-0.7.11.dev2422/tests/conformance/README.md +0 -24
- benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/environment/Dockerfile +0 -7
- benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/environment/docker-compose.yaml +0 -3
- benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/environment/skills/conformance-writer/SKILL.md +0 -16
- benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/instruction.md +0 -7
- benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/solution/solve.sh +0 -4
- benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/task.md +0 -52
- benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/task.toml +0 -18
- benchflow-0.7.11.dev2422/tests/conformance/acp_smoke/tests/test.sh +0 -13
- benchflow-0.7.11.dev2422/tests/conformance/conformance-results.json +0 -40
- benchflow-0.7.11.dev2422/tests/conformance/proof_multi_agent.py +0 -87
- benchflow-0.7.11.dev2422/tests/conformance/proof_snapshot.py +0 -85
- benchflow-0.7.11.dev2422/tests/conformance/run_conformance.py +0 -160
- benchflow-0.7.11.dev2422/tests/conformance/self_gen_smoke_skills/skill-creator/SKILL.md +0 -22
- benchflow-0.7.11.dev2422/tests/conftest.py +0 -121
- benchflow-0.7.11.dev2422/tests/continue_run/__init__.py +0 -0
- benchflow-0.7.11.dev2422/tests/continue_run/_helpers.py +0 -100
- benchflow-0.7.11.dev2422/tests/continue_run/test_batch.py +0 -111
- benchflow-0.7.11.dev2422/tests/continue_run/test_orchestrator.py +0 -303
- benchflow-0.7.11.dev2422/tests/continue_run/test_replay_proxy.py +0 -176
- benchflow-0.7.11.dev2422/tests/continue_run/test_run_folder.py +0 -97
- benchflow-0.7.11.dev2422/tests/environment/__init__.py +0 -0
- benchflow-0.7.11.dev2422/tests/environment/test_chibench_manifest.py +0 -65
- benchflow-0.7.11.dev2422/tests/environment/test_clawsbench_manifest.py +0 -41
- benchflow-0.7.11.dev2422/tests/environment/test_manifest.py +0 -171
- benchflow-0.7.11.dev2422/tests/environment/test_manifest_env.py +0 -479
- benchflow-0.7.11.dev2422/tests/environment/test_protocol.py +0 -57
- benchflow-0.7.11.dev2422/tests/environment/test_readiness.py +0 -76
- benchflow-0.7.11.dev2422/tests/examples/hello-world-task/environment/Dockerfile +0 -7
- benchflow-0.7.11.dev2422/tests/examples/hello-world-task/instruction.md +0 -5
- benchflow-0.7.11.dev2422/tests/examples/hello-world-task/solution/solve.sh +0 -2
- benchflow-0.7.11.dev2422/tests/examples/hello-world-task/task.md +0 -48
- benchflow-0.7.11.dev2422/tests/examples/hello-world-task/task.toml +0 -17
- benchflow-0.7.11.dev2422/tests/examples/hello-world-task/tests/test.sh +0 -13
- benchflow-0.7.11.dev2422/tests/examples/test_antigravity.sh +0 -69
- benchflow-0.7.11.dev2422/tests/examples/test_claude.sh +0 -191
- benchflow-0.7.11.dev2422/tests/examples/test_codex.sh +0 -238
- benchflow-0.7.11.dev2422/tests/examples/test_codex_custom_provider.sh +0 -145
- benchflow-0.7.11.dev2422/tests/examples/test_gemini.sh +0 -192
- benchflow-0.7.11.dev2422/tests/examples/test_openclaw.sh +0 -191
- benchflow-0.7.11.dev2422/tests/examples/traces/minimal-claude.jsonl +0 -3
- benchflow-0.7.11.dev2422/tests/examples/traces/minimal-opentraces.jsonl +0 -1
- benchflow-0.7.11.dev2422/tests/fixtures/digest/README.md +0 -9
- benchflow-0.7.11.dev2422/tests/fixtures/digest/alpha-task/environment/Dockerfile +0 -1
- benchflow-0.7.11.dev2422/tests/fixtures/digest/alpha-task/instruction.md +0 -3
- benchflow-0.7.11.dev2422/tests/fixtures/digest/alpha-task/task.toml +0 -4
- benchflow-0.7.11.dev2422/tests/fixtures/digest/alpha-task/tests/test.sh +0 -2
- benchflow-0.7.11.dev2422/tests/fixtures/digest/beta-task/data/empty.bin +0 -0
- benchflow-0.7.11.dev2422/tests/fixtures/digest/beta-task/data/unicode.txt +0 -1
- benchflow-0.7.11.dev2422/tests/fixtures/digest/beta-task/instruction.md +0 -1
- benchflow-0.7.11.dev2422/tests/fixtures/digest/beta-task/task.toml +0 -1
- benchflow-0.7.11.dev2422/tests/fixtures/digest/not-a-task/notes.txt +0 -1
- benchflow-0.7.11.dev2422/tests/fixtures/mock_acp_agent.py +0 -149
- benchflow-0.7.11.dev2422/tests/fixtures/mock_acp_agent_interleaved.py +0 -141
- benchflow-0.7.11.dev2422/tests/fixtures/mock_acp_agent_multi_turn.py +0 -163
- benchflow-0.7.11.dev2422/tests/fixtures/mock_openai_responses_server.py +0 -98
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/Dockerfile +0 -18
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/data/michigan_stations.txt +0 -79
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/flood-detection/SKILL.md +0 -127
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/nws-flood-thresholds/SKILL.md +0 -123
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/usgs-data-download/SKILL.md +0 -120
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/instruction.md +0 -1
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/solution/solve.sh +0 -113
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/task.toml +0 -28
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test.sh +0 -6
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test_outputs.py +0 -45
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/Dockerfile +0 -17
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/climate.csv +0 -17
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/hydrology.csv +0 -17
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/land_cover.csv +0 -17
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/water_temperature.csv +0 -17
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/contribution-analysis/SKILL.md +0 -93
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/meteorology-driver-classification/SKILL.md +0 -78
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/pca-decomposition/SKILL.md +0 -136
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/trend-analysis/SKILL.md +0 -89
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/instruction.md +0 -9
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/solution/solve.sh +0 -82
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/task.toml +0 -27
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test.sh +0 -6
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test_outputs.py +0 -32
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/manifest.json +0 -76
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/Dockerfile +0 -23
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/r2r_simulator.py +0 -205
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/finite-horizon-lqr/SKILL.md +0 -56
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/integral-action-design/SKILL.md +0 -50
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/mpc-horizon-tuning/SKILL.md +0 -48
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/state-space-linearization/SKILL.md +0 -48
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/system_config.json +0 -16
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/instruction.md +0 -51
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/solution/solve.sh +0 -237
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/task.toml +0 -29
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test.sh +0 -32
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test_outputs.py +0 -266
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/Dockerfile +0 -64
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/generate_training_pcaps.py +0 -131
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/local.rules +0 -2
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/SKILL.md +0 -57
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/scripts/summarize_http_requests.sh +0 -31
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/SKILL.md +0 -57
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/scripts/run_suricata_offline.sh +0 -27
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-rules-basics/SKILL.md +0 -130
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/suricata.yaml +0 -24
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/instruction.md +0 -11
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/solution/solve.sh +0 -80
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/task.toml +0 -27
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test.sh +0 -29
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test_outputs.py +0 -324
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/Dockerfile +0 -36
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syz-extract-constants/SKILL.md +0 -101
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzkaller-build-loop/SKILL.md +0 -78
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzlang-ioctl-basics/SKILL.md +0 -97
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/instruction.md +0 -25
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/solution/solve.sh +0 -179
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/task.toml +0 -29
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test.sh +0 -6
- benchflow-0.7.11.dev2422/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test_outputs.py +0 -212
- benchflow-0.7.11.dev2422/tests/integration/_consistency.py +0 -122
- benchflow-0.7.11.dev2422/tests/integration/agent_judge.py +0 -821
- benchflow-0.7.11.dev2422/tests/integration/check_adapter_evidence.py +0 -431
- benchflow-0.7.11.dev2422/tests/integration/check_hosted_env_evidence.py +0 -209
- benchflow-0.7.11.dev2422/tests/integration/check_results.py +0 -1336
- benchflow-0.7.11.dev2422/tests/integration/check_skillsbench_harbor_parity.py +0 -739
- benchflow-0.7.11.dev2422/tests/integration/check_trace_to_task_evidence.py +0 -353
- benchflow-0.7.11.dev2422/tests/integration/configs/antigravity.yaml +0 -23
- benchflow-0.7.11.dev2422/tests/integration/configs/claude-agent-acp.yaml +0 -23
- benchflow-0.7.11.dev2422/tests/integration/configs/codex-acp.yaml +0 -23
- benchflow-0.7.11.dev2422/tests/integration/configs/gemini.yaml +0 -23
- benchflow-0.7.11.dev2422/tests/integration/configs/harvey-lab-harness.yaml +0 -23
- benchflow-0.7.11.dev2422/tests/integration/configs/mimo.yaml +0 -32
- benchflow-0.7.11.dev2422/tests/integration/configs/openclaw.yaml +0 -23
- benchflow-0.7.11.dev2422/tests/integration/configs/opencode.yaml +0 -23
- benchflow-0.7.11.dev2422/tests/integration/configs/openhands.yaml +0 -23
- benchflow-0.7.11.dev2422/tests/integration/configs/pi-acp.yaml +0 -23
- benchflow-0.7.11.dev2422/tests/integration/deepagents_harness.py +0 -370
- benchflow-0.7.11.dev2422/tests/integration/rubric_checks.py +0 -1396
- benchflow-0.7.11.dev2422/tests/integration/run.sh +0 -210
- benchflow-0.7.11.dev2422/tests/integration/run_suite.py +0 -946
- benchflow-0.7.11.dev2422/tests/integration/scenarios.py +0 -364
- benchflow-0.7.11.dev2422/tests/integration/suites/release.yaml +0 -515
- benchflow-0.7.11.dev2422/tests/test_acceptance_evidence.py +0 -779
- benchflow-0.7.11.dev2422/tests/test_acceptance_live.py +0 -708
- benchflow-0.7.11.dev2422/tests/test_acceptance_live_execution.py +0 -645
- benchflow-0.7.11.dev2422/tests/test_acp.py +0 -2414
- benchflow-0.7.11.dev2422/tests/test_acp_buffered_timeout.py +0 -122
- benchflow-0.7.11.dev2422/tests/test_acp_capability_advertising.py +0 -184
- benchflow-0.7.11.dev2422/tests/test_acp_mcp_servers.py +0 -411
- benchflow-0.7.11.dev2422/tests/test_acp_model_config_dispatch.py +0 -271
- benchflow-0.7.11.dev2422/tests/test_acp_pinned_protocol_guard.py +0 -189
- benchflow-0.7.11.dev2422/tests/test_acp_setup_failure_propagation.py +0 -274
- benchflow-0.7.11.dev2422/tests/test_acp_timeout_evidence.py +0 -259
- benchflow-0.7.11.dev2422/tests/test_adapter_scripts.py +0 -243
- benchflow-0.7.11.dev2422/tests/test_adapters.py +0 -422
- benchflow-0.7.11.dev2422/tests/test_agent_antigravity.py +0 -552
- benchflow-0.7.11.dev2422/tests/test_agent_cli.py +0 -29
- benchflow-0.7.11.dev2422/tests/test_agent_egress_firewall.py +0 -80
- benchflow-0.7.11.dev2422/tests/test_agent_env_resolution.py +0 -132
- benchflow-0.7.11.dev2422/tests/test_agent_gemini_defaults.py +0 -91
- benchflow-0.7.11.dev2422/tests/test_agent_idle_timeout_cli.py +0 -188
- benchflow-0.7.11.dev2422/tests/test_agent_model_decouple.py +0 -113
- benchflow-0.7.11.dev2422/tests/test_agent_registry.py +0 -452
- benchflow-0.7.11.dev2422/tests/test_agent_router.py +0 -914
- benchflow-0.7.11.dev2422/tests/test_agent_router_cli_e2e.py +0 -425
- benchflow-0.7.11.dev2422/tests/test_agent_router_scaffold.py +0 -89
- benchflow-0.7.11.dev2422/tests/test_agent_setup.py +0 -882
- benchflow-0.7.11.dev2422/tests/test_agent_spec.py +0 -226
- benchflow-0.7.11.dev2422/tests/test_agentcore_builder.py +0 -818
- benchflow-0.7.11.dev2422/tests/test_agentcore_parallel.py +0 -1111
- benchflow-0.7.11.dev2422/tests/test_agentcore_reaper.py +0 -297
- benchflow-0.7.11.dev2422/tests/test_agentcore_sandbox.py +0 -679
- benchflow-0.7.11.dev2422/tests/test_agentcore_transport.py +0 -484
- benchflow-0.7.11.dev2422/tests/test_api_error_capture.py +0 -302
- benchflow-0.7.11.dev2422/tests/test_apple_container_sandbox.py +0 -578
- benchflow-0.7.11.dev2422/tests/test_automatic_review_scoring.py +0 -299
- benchflow-0.7.11.dev2422/tests/test_bare_model_provider.py +0 -437
- benchflow-0.7.11.dev2422/tests/test_base_install_imports.py +0 -108
- benchflow-0.7.11.dev2422/tests/test_bedrock_thinking.py +0 -243
- benchflow-0.7.11.dev2422/tests/test_benchflow_experiment_review_validator.py +0 -588
- benchflow-0.7.11.dev2422/tests/test_benchmark_repos_resolve_repo_path.py +0 -58
- benchflow-0.7.11.dev2422/tests/test_branch.py +0 -89
- benchflow-0.7.11.dev2422/tests/test_build_context_stage.py +0 -73
- benchflow-0.7.11.dev2422/tests/test_build_review_pack.py +0 -757
- benchflow-0.7.11.dev2422/tests/test_capture_trajectory.py +0 -899
- benchflow-0.7.11.dev2422/tests/test_check_skillsbench_harbor_parity.py +0 -429
- benchflow-0.7.11.dev2422/tests/test_clawsbench_slice.py +0 -52
- benchflow-0.7.11.dev2422/tests/test_cli_adopt_aliases.py +0 -324
- benchflow-0.7.11.dev2422/tests/test_cli_arg_validation.py +0 -463
- benchflow-0.7.11.dev2422/tests/test_cli_daytona.py +0 -147
- benchflow-0.7.11.dev2422/tests/test_cli_docs_drift.py +0 -282
- benchflow-0.7.11.dev2422/tests/test_cli_edge_case_hardening.py +0 -929
- benchflow-0.7.11.dev2422/tests/test_cli_hub_env.py +0 -177
- benchflow-0.7.11.dev2422/tests/test_cli_live_progress.py +0 -1253
- benchflow-0.7.11.dev2422/tests/test_cli_misc.py +0 -178
- benchflow-0.7.11.dev2422/tests/test_codex_bare_model_id.py +0 -113
- benchflow-0.7.11.dev2422/tests/test_codex_review.py +0 -475
- benchflow-0.7.11.dev2422/tests/test_codex_self_write_auth.py +0 -59
- benchflow-0.7.11.dev2422/tests/test_config_override.py +0 -250
- benchflow-0.7.11.dev2422/tests/test_config_redaction.py +0 -164
- benchflow-0.7.11.dev2422/tests/test_connect_as_env.py +0 -196
- benchflow-0.7.11.dev2422/tests/test_console_error_truncation.py +0 -84
- benchflow-0.7.11.dev2422/tests/test_console_progress.py +0 -164
- benchflow-0.7.11.dev2422/tests/test_continuallearningbench_adapter.py +0 -90
- benchflow-0.7.11.dev2422/tests/test_dataset_registry.py +0 -596
- benchflow-0.7.11.dev2422/tests/test_daytona_command_polling.py +0 -96
- benchflow-0.7.11.dev2422/tests/test_daytona_dind_compose_up.py +0 -232
- benchflow-0.7.11.dev2422/tests/test_daytona_download.py +0 -254
- benchflow-0.7.11.dev2422/tests/test_daytona_litellm_runtime.py +0 -121
- benchflow-0.7.11.dev2422/tests/test_daytona_poll_deadline.py +0 -222
- benchflow-0.7.11.dev2422/tests/test_daytona_reap.py +0 -573
- benchflow-0.7.11.dev2422/tests/test_deepagents_agent.py +0 -274
- benchflow-0.7.11.dev2422/tests/test_diagnostics.py +0 -151
- benchflow-0.7.11.dev2422/tests/test_docker_prune_scoping.py +0 -153
- benchflow-0.7.11.dev2422/tests/test_docker_uploads.py +0 -63
- benchflow-0.7.11.dev2422/tests/test_docs_examples.py +0 -121
- benchflow-0.7.11.dev2422/tests/test_egress_connect_authority.py +0 -417
- benchflow-0.7.11.dev2422/tests/test_egress_denylist.py +0 -580
- benchflow-0.7.11.dev2422/tests/test_egress_denylist_integration.py +0 -316
- benchflow-0.7.11.dev2422/tests/test_egress_dynamic_certs.py +0 -115
- benchflow-0.7.11.dev2422/tests/test_egress_model_gateway.py +0 -146
- benchflow-0.7.11.dev2422/tests/test_eng50_capabilities.py +0 -164
- benchflow-0.7.11.dev2422/tests/test_env_registry.py +0 -297
- benchflow-0.7.11.dev2422/tests/test_env_setup.py +0 -550
- benchflow-0.7.11.dev2422/tests/test_environment_manifest_controls.py +0 -299
- benchflow-0.7.11.dev2422/tests/test_eval_artifact_cli.py +0 -535
- benchflow-0.7.11.dev2422/tests/test_eval_filters_applied.py +0 -158
- benchflow-0.7.11.dev2422/tests/test_eval_lift.py +0 -292
- benchflow-0.7.11.dev2422/tests/test_eval_sharding.py +0 -211
- benchflow-0.7.11.dev2422/tests/test_eval_single_task_summary.py +0 -160
- benchflow-0.7.11.dev2422/tests/test_eval_source_provenance.py +0 -776
- benchflow-0.7.11.dev2422/tests/test_eval_worker_retry.py +0 -76
- benchflow-0.7.11.dev2422/tests/test_eval_zero_task_guard.py +0 -116
- benchflow-0.7.11.dev2422/tests/test_evaluation_environment_manifest.py +0 -205
- benchflow-0.7.11.dev2422/tests/test_exclude_tasks.py +0 -43
- benchflow-0.7.11.dev2422/tests/test_filter_credentialed_cells.py +0 -262
- benchflow-0.7.11.dev2422/tests/test_harvey_lab_shim.py +0 -93
- benchflow-0.7.11.dev2422/tests/test_hilbench_adapter.py +0 -104
- benchflow-0.7.11.dev2422/tests/test_hosted_env.py +0 -334
- benchflow-0.7.11.dev2422/tests/test_hosted_env_rollout_contract.py +0 -399
- benchflow-0.7.11.dev2422/tests/test_hosted_search_policy.py +0 -858
- benchflow-0.7.11.dev2422/tests/test_hub_harbor_registry.py +0 -328
- benchflow-0.7.11.dev2422/tests/test_inbound_adapter_manifest.py +0 -213
- benchflow-0.7.11.dev2422/tests/test_inbound_adapters.py +0 -307
- benchflow-0.7.11.dev2422/tests/test_integration_agent_judge.py +0 -525
- benchflow-0.7.11.dev2422/tests/test_integration_check_results.py +0 -2694
- benchflow-0.7.11.dev2422/tests/test_integration_consistency.py +0 -142
- benchflow-0.7.11.dev2422/tests/test_integration_matrix.py +0 -722
- benchflow-0.7.11.dev2422/tests/test_integration_provider_selection.py +0 -57
- benchflow-0.7.11.dev2422/tests/test_integration_run_suite.py +0 -884
- benchflow-0.7.11.dev2422/tests/test_integration_suite.py +0 -494
- benchflow-0.7.11.dev2422/tests/test_internet_policy.py +0 -435
- benchflow-0.7.11.dev2422/tests/test_job.py +0 -930
- benchflow-0.7.11.dev2422/tests/test_job_sequential_shared.py +0 -597
- benchflow-0.7.11.dev2422/tests/test_job_sequential_shared_resume.py +0 -314
- benchflow-0.7.11.dev2422/tests/test_judge_robustness.py +0 -691
- benchflow-0.7.11.dev2422/tests/test_judge_symlink_ingestion.py +0 -64
- benchflow-0.7.11.dev2422/tests/test_learner_skills.py +0 -131
- benchflow-0.7.11.dev2422/tests/test_learner_skills_traversal.py +0 -91
- benchflow-0.7.11.dev2422/tests/test_learner_store.py +0 -257
- benchflow-0.7.11.dev2422/tests/test_learner_store_persistence.py +0 -138
- benchflow-0.7.11.dev2422/tests/test_litellm_config.py +0 -358
- benchflow-0.7.11.dev2422/tests/test_litellm_gemini_passthrough_patch.py +0 -63
- benchflow-0.7.11.dev2422/tests/test_litellm_hardening.py +0 -1125
- benchflow-0.7.11.dev2422/tests/test_litellm_logging.py +0 -704
- benchflow-0.7.11.dev2422/tests/test_litellm_model_via_env_generic.py +0 -87
- benchflow-0.7.11.dev2422/tests/test_litellm_reasoning_passthrough.py +0 -60
- benchflow-0.7.11.dev2422/tests/test_litellm_runtime.py +0 -853
- benchflow-0.7.11.dev2422/tests/test_litellm_smoke.py +0 -160
- benchflow-0.7.11.dev2422/tests/test_live_llm_trajectory.py +0 -661
- benchflow-0.7.11.dev2422/tests/test_llm_judge.py +0 -943
- benchflow-0.7.11.dev2422/tests/test_llm_judge_event_tags.py +0 -211
- benchflow-0.7.11.dev2422/tests/test_llm_judge_verifier.py +0 -734
- benchflow-0.7.11.dev2422/tests/test_loop_strategies.py +0 -576
- benchflow-0.7.11.dev2422/tests/test_loop_summary.py +0 -153
- benchflow-0.7.11.dev2422/tests/test_loop_sweep.py +0 -512
- benchflow-0.7.11.dev2422/tests/test_memory_scorer.py +0 -386
- benchflow-0.7.11.dev2422/tests/test_metrics.py +0 -454
- benchflow-0.7.11.dev2422/tests/test_mle_bench_adapter.py +0 -519
- benchflow-0.7.11.dev2422/tests/test_mock_openai_responses_server.py +0 -73
- benchflow-0.7.11.dev2422/tests/test_monitor_scaffold.py +0 -133
- benchflow-0.7.11.dev2422/tests/test_native_acp_usage.py +0 -276
- benchflow-0.7.11.dev2422/tests/test_network_denylist_config.py +0 -305
- benchflow-0.7.11.dev2422/tests/test_no_cross_provider_fallback.py +0 -84
- benchflow-0.7.11.dev2422/tests/test_notification_order_real.py +0 -126
- benchflow-0.7.11.dev2422/tests/test_opencode_family_proxy_tracking.py +0 -152
- benchflow-0.7.11.dev2422/tests/test_oracle.py +0 -162
- benchflow-0.7.11.dev2422/tests/test_oracle_chokepoint.py +0 -1194
- benchflow-0.7.11.dev2422/tests/test_paths_safe.py +0 -102
- benchflow-0.7.11.dev2422/tests/test_paths_symlink_helpers.py +0 -94
- benchflow-0.7.11.dev2422/tests/test_pi_acp_launcher.py +0 -405
- benchflow-0.7.11.dev2422/tests/test_pi_acp_proxy_routing.py +0 -46
- benchflow-0.7.11.dev2422/tests/test_process.py +0 -1096
- benchflow-0.7.11.dev2422/tests/test_project_skills_layout.py +0 -20
- benchflow-0.7.11.dev2422/tests/test_provider_auth_detection.py +0 -412
- benchflow-0.7.11.dev2422/tests/test_providers.py +0 -554
- benchflow-0.7.11.dev2422/tests/test_publish_azure_blob.py +0 -777
- benchflow-0.7.11.dev2422/tests/test_publish_huggingface.py +0 -147
- benchflow-0.7.11.dev2422/tests/test_redacted_snapshot.py +0 -222
- benchflow-0.7.11.dev2422/tests/test_reexport.py +0 -101
- benchflow-0.7.11.dev2422/tests/test_registry_invariants.py +0 -551
- benchflow-0.7.11.dev2422/tests/test_release_hardening_r5.py +0 -103
- benchflow-0.7.11.dev2422/tests/test_release_version.py +0 -132
- benchflow-0.7.11.dev2422/tests/test_release_workflow_wiring.py +0 -423
- benchflow-0.7.11.dev2422/tests/test_resolve_env_helpers.py +0 -1210
- benchflow-0.7.11.dev2422/tests/test_review_automatic.py +0 -380
- benchflow-0.7.11.dev2422/tests/test_review_boundaries.py +0 -607
- benchflow-0.7.11.dev2422/tests/test_review_evidence.py +0 -640
- benchflow-0.7.11.dev2422/tests/test_review_evidence_runtime.py +0 -107
- benchflow-0.7.11.dev2422/tests/test_review_lifecycle.py +0 -126
- benchflow-0.7.11.dev2422/tests/test_review_resume.py +0 -393
- benchflow-0.7.11.dev2422/tests/test_review_rubric.py +0 -850
- benchflow-0.7.11.dev2422/tests/test_review_runtime.py +0 -892
- benchflow-0.7.11.dev2422/tests/test_review_runtime_automatic.py +0 -300
- benchflow-0.7.11.dev2422/tests/test_review_snapshot.py +0 -102
- benchflow-0.7.11.dev2422/tests/test_reviewer_options.py +0 -425
- benchflow-0.7.11.dev2422/tests/test_reward_lenient.py +0 -151
- benchflow-0.7.11.dev2422/tests/test_reward_node.py +0 -145
- benchflow-0.7.11.dev2422/tests/test_reward_range.py +0 -284
- benchflow-0.7.11.dev2422/tests/test_reward_unified_contract.py +0 -171
- benchflow-0.7.11.dev2422/tests/test_rewards.py +0 -442
- benchflow-0.7.11.dev2422/tests/test_rewards_jsonl.py +0 -174
- benchflow-0.7.11.dev2422/tests/test_rollout_architecture.py +0 -58
- benchflow-0.7.11.dev2422/tests/test_rollout_branch.py +0 -451
- benchflow-0.7.11.dev2422/tests/test_rollout_config_path_coercion.py +0 -96
- benchflow-0.7.11.dev2422/tests/test_rollout_environment.py +0 -50
- benchflow-0.7.11.dev2422/tests/test_rollout_hard_deadline.py +0 -200
- benchflow-0.7.11.dev2422/tests/test_rollout_import_no_side_effects.py +0 -194
- benchflow-0.7.11.dev2422/tests/test_rollout_on_ask_user_wiring.py +0 -299
- benchflow-0.7.11.dev2422/tests/test_rollout_planes_contract.py +0 -121
- benchflow-0.7.11.dev2422/tests/test_rollout_probe_sandbox_health.py +0 -101
- benchflow-0.7.11.dev2422/tests/test_rollout_session_factory_dispatch.py +0 -301
- benchflow-0.7.11.dev2422/tests/test_rollout_setup_commands.py +0 -145
- benchflow-0.7.11.dev2422/tests/test_rollout_upload.py +0 -1038
- benchflow-0.7.11.dev2422/tests/test_root_helpers_isolated.py +0 -175
- benchflow-0.7.11.dev2422/tests/test_rubric_checks.py +0 -415
- benchflow-0.7.11.dev2422/tests/test_rubric_config.py +0 -371
- benchflow-0.7.11.dev2422/tests/test_runtime.py +0 -170
- benchflow-0.7.11.dev2422/tests/test_runtime_capabilities.py +0 -1129
- benchflow-0.7.11.dev2422/tests/test_runtime_config_wired.py +0 -210
- benchflow-0.7.11.dev2422/tests/test_runtime_live_sandbox.py +0 -257
- benchflow-0.7.11.dev2422/tests/test_sandbox.py +0 -602
- benchflow-0.7.11.dev2422/tests/test_sandbox_exec_secret_handling.py +0 -316
- benchflow-0.7.11.dev2422/tests/test_sandbox_hardening.py +0 -1830
- benchflow-0.7.11.dev2422/tests/test_sandbox_isolation_copy_traversal.py +0 -102
- benchflow-0.7.11.dev2422/tests/test_sandbox_live_process.py +0 -224
- benchflow-0.7.11.dev2422/tests/test_sandbox_multi_service.py +0 -800
- benchflow-0.7.11.dev2422/tests/test_sandbox_prebuilt_validation.py +0 -157
- benchflow-0.7.11.dev2422/tests/test_sandbox_protocol.py +0 -222
- benchflow-0.7.11.dev2422/tests/test_sandbox_provider_registry_drift.py +0 -119
- benchflow-0.7.11.dev2422/tests/test_sandbox_setup.py +0 -250
- benchflow-0.7.11.dev2422/tests/test_sandbox_snapshot_contract.py +0 -251
- benchflow-0.7.11.dev2422/tests/test_sandbox_upload_symlink.py +0 -221
- benchflow-0.7.11.dev2422/tests/test_sandbox_verifier_workspace.py +0 -179
- benchflow-0.7.11.dev2422/tests/test_scene.py +0 -102
- benchflow-0.7.11.dev2422/tests/test_scene_outbox_trial.py +0 -432
- benchflow-0.7.11.dev2422/tests/test_scene_parallel_group.py +0 -51
- benchflow-0.7.11.dev2422/tests/test_scene_result_aggregation.py +0 -189
- benchflow-0.7.11.dev2422/tests/test_scoring.py +0 -317
- benchflow-0.7.11.dev2422/tests/test_sdk_internals.py +0 -926
- benchflow-0.7.11.dev2422/tests/test_sdk_lockdown.py +0 -1012
- benchflow-0.7.11.dev2422/tests/test_sdk_run_alias.py +0 -81
- benchflow-0.7.11.dev2422/tests/test_sealed_channel_container.py +0 -264
- benchflow-0.7.11.dev2422/tests/test_self_gen_cli.py +0 -59
- benchflow-0.7.11.dev2422/tests/test_self_gen_export_error_channel.py +0 -202
- benchflow-0.7.11.dev2422/tests/test_self_gen_export_failures.py +0 -195
- benchflow-0.7.11.dev2422/tests/test_self_gen_orchestration.py +0 -408
- benchflow-0.7.11.dev2422/tests/test_separate_verifier.py +0 -1121
- benchflow-0.7.11.dev2422/tests/test_session_factory_runtime.py +0 -380
- benchflow-0.7.11.dev2422/tests/test_session_request_permission_dispatch.py +0 -294
- benchflow-0.7.11.dev2422/tests/test_skill_eval.py +0 -647
- benchflow-0.7.11.dev2422/tests/test_skill_eval_dryrun.py +0 -399
- benchflow-0.7.11.dev2422/tests/test_skill_eval_integration.py +0 -356
- benchflow-0.7.11.dev2422/tests/test_skill_eval_sweep.py +0 -461
- benchflow-0.7.11.dev2422/tests/test_skill_eval_traversal.py +0 -135
- benchflow-0.7.11.dev2422/tests/test_skill_invocation_artifacts.py +0 -397
- benchflow-0.7.11.dev2422/tests/test_skill_policy.py +0 -234
- benchflow-0.7.11.dev2422/tests/test_skillevaluator_integration.py +0 -960
- benchflow-0.7.11.dev2422/tests/test_skills.py +0 -138
- benchflow-0.7.11.dev2422/tests/test_skills_dir_agent_home_link.py +0 -146
- benchflow-0.7.11.dev2422/tests/test_skillsbench_conversion_conformance.py +0 -116
- benchflow-0.7.11.dev2422/tests/test_skillsbench_harbor_run_suite.py +0 -103
- benchflow-0.7.11.dev2422/tests/test_smoke.py +0 -245
- benchflow-0.7.11.dev2422/tests/test_smoke_wiring.py +0 -208
- benchflow-0.7.11.dev2422/tests/test_source_adapters.py +0 -1190
- benchflow-0.7.11.dev2422/tests/test_subscription_auth.py +0 -562
- benchflow-0.7.11.dev2422/tests/test_task_check_eval_consistency.py +0 -500
- benchflow-0.7.11.dev2422/tests/test_task_config.py +0 -483
- benchflow-0.7.11.dev2422/tests/test_task_digest.py +0 -185
- benchflow-0.7.11.dev2422/tests/test_task_document.py +0 -1389
- benchflow-0.7.11.dev2422/tests/test_task_download.py +0 -898
- benchflow-0.7.11.dev2422/tests/test_task_export.py +0 -586
- benchflow-0.7.11.dev2422/tests/test_task_output_format.py +0 -67
- benchflow-0.7.11.dev2422/tests/test_task_package.py +0 -452
- benchflow-0.7.11.dev2422/tests/test_task_runtime_primitive.py +0 -379
- benchflow-0.7.11.dev2422/tests/test_tasks.py +0 -463
- benchflow-0.7.11.dev2422/tests/test_token_usage_normalization.py +0 -158
- benchflow-0.7.11.dev2422/tests/test_tool_call_raw_io.py +0 -344
- benchflow-0.7.11.dev2422/tests/test_trace_import_cli.py +0 -112
- benchflow-0.7.11.dev2422/tests/test_trace_task_gen_traversal.py +0 -123
- benchflow-0.7.11.dev2422/tests/test_trace_to_task_evidence.py +0 -165
- benchflow-0.7.11.dev2422/tests/test_traces_huggingface.py +0 -130
- benchflow-0.7.11.dev2422/tests/test_traces_parsers.py +0 -470
- benchflow-0.7.11.dev2422/tests/test_traces_task_gen.py +0 -732
- benchflow-0.7.11.dev2422/tests/test_train_cli.py +0 -2260
- benchflow-0.7.11.dev2422/tests/test_train_mode_artifact_emission.py +0 -1412
- benchflow-0.7.11.dev2422/tests/test_train_trl_cli.py +0 -586
- benchflow-0.7.11.dev2422/tests/test_traj_report.py +0 -526
- benchflow-0.7.11.dev2422/tests/test_traj_staging_phases.py +0 -242
- benchflow-0.7.11.dev2422/tests/test_traj_tui.py +0 -185
- benchflow-0.7.11.dev2422/tests/test_traj_upload_cli.py +0 -1407
- benchflow-0.7.11.dev2422/tests/test_traj_upload_skill.py +0 -105
- benchflow-0.7.11.dev2422/tests/test_traj_workspace.py +0 -418
- benchflow-0.7.11.dev2422/tests/test_trajectory_integration.py +0 -261
- benchflow-0.7.11.dev2422/tests/test_trajectory_streaming.py +0 -552
- benchflow-0.7.11.dev2422/tests/test_trajectory_upload_layout.py +0 -77
- benchflow-0.7.11.dev2422/tests/test_trajectory_upload_service.py +0 -1934
- benchflow-0.7.11.dev2422/tests/test_trial_agent_timeout_verify.py +0 -92
- benchflow-0.7.11.dev2422/tests/test_trial_install_agent_timeout.py +0 -361
- benchflow-0.7.11.dev2422/tests/test_trial_litellm_runtime.py +0 -119
- benchflow-0.7.11.dev2422/tests/test_trl_integration.py +0 -374
- benchflow-0.7.11.dev2422/tests/test_usage_litellm.py +0 -315
- benchflow-0.7.11.dev2422/tests/test_usage_required.py +0 -70
- benchflow-0.7.11.dev2422/tests/test_usage_tracking.py +0 -229
- benchflow-0.7.11.dev2422/tests/test_user.py +0 -1216
- benchflow-0.7.11.dev2422/tests/test_v06_guard_ports.py +0 -160
- benchflow-0.7.11.dev2422/tests/test_verifier_document.py +0 -342
- benchflow-0.7.11.dev2422/tests/test_verifier_multi_container.py +0 -331
- benchflow-0.7.11.dev2422/tests/test_verifier_output.py +0 -355
- benchflow-0.7.11.dev2422/tests/test_verifier_output_freshness.py +0 -114
- benchflow-0.7.11.dev2422/tests/test_verifier_strategies.py +0 -505
- benchflow-0.7.11.dev2422/tests/test_verifier_user_config.py +0 -94
- benchflow-0.7.11.dev2422/tests/test_verifier_wedge_retry.py +0 -114
- benchflow-0.7.11.dev2422/tests/test_verify.py +0 -1226
- benchflow-0.7.11.dev2422/tests/test_viewer_confirm.py +0 -679
- benchflow-0.7.11.dev2422/tests/test_workflow_action_pinning.py +0 -121
- benchflow-0.7.11.dev2422/tests/test_yaml_config.py +0 -678
- benchflow-0.7.11.dev2422/tests/trajectories/__init__.py +0 -0
- benchflow-0.7.11.dev2422/tests/trajectories/test_export.py +0 -157
- benchflow-0.7.11.dev2422/tests/trajectories/test_export_adp.py +0 -371
- benchflow-0.7.11.dev2422/tests/trajectories/test_export_atif.py +0 -275
- benchflow-0.7.11.dev2422/tests/trajectories/test_export_common.py +0 -91
- benchflow-0.7.11.dev2422/tests/trajectories/test_export_nan_handling.py +0 -101
- benchflow-0.7.11.dev2422/tests/trajectories/test_export_prime_sft.py +0 -1221
- benchflow-0.7.11.dev2422/tests/trajectories/test_redaction.py +0 -1134
- benchflow-0.7.11.dev2422/tests/trajectories/test_step_granularity.py +0 -201
- benchflow-0.7.11.dev2422/tests/trajectories/test_tree.py +0 -159
- benchflow-0.7.11.dev2422/tests/trajectories/test_viewer_acp_renderer.py +0 -922
- benchflow-0.7.11.dev2422/tests/trajectories/test_viewer_browser.py +0 -847
- benchflow-0.7.11.dev2422/tests/trajectories/test_viewer_rubric.py +0 -227
- benchflow-0.7.11.dev2422/tests/trajectories/test_viewer_theme.py +0 -59
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/LICENSE +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_dotenv.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_paths.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/build_context_stage.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/content_address.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/json_safe.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/live_activity.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/reward_events.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/source_provenance.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/task_authoring/_evidence_paths.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/task_authoring/acceptance_evidence.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/_utils/text.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/acp/timeout_cleanup.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/_toolathlon_container.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/_toolathlon_services.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/inspect_ai.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/ors.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/resources/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/resources/mcp_atlas_bridge.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/adapters/source.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/agent_router_guide.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/agent_router_parity.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/agents/protocol.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/cli/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/cli/_traj_tui.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/cli/_traj_upload_ui.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/cli/environment.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/cli/monitor.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/continue_run/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/continue_run/batch.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/continue_run/replay_proxy.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/demo_task/environment/Dockerfile +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/demo_task/instruction.md +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/demo_task/task.md +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/demo_task/task.toml +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/demo_task/tests/test.sh +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/environment/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/environment/_registry/env0@outage.toml +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/environment/_registry/env0@prod.toml +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/environment/manifest.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/eval_lift.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/experimental/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/experimental/mcp/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/integrations/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/integrations/trl/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/learner_store.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/loop_strategies.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/loop_sweep.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/providers/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/_progress.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/azure_blob.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/broker.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/redact.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/publish/traj_report.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/py.typed +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/review/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/review/default-rubric.json +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/review/prompts.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/rewards/events.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/rewards/memory_scorer.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/rewards/rubric.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/rollout/_skills.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/rollout/_usage.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/_compose_files/docker-compose-build.yaml +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/_compose_files/docker-compose-net-admin.yaml +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/_compose_files/docker-compose-no-network.yaml +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/_compose_files/docker-compose-prebuilt.yaml +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/agentcore_reaper.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/agentcore_sealed.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/sandbox/user.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/scenes.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/skill_eval/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/skill_eval/schema.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/skill_policy.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/skills.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/_document_evidence.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/acceptance_live_model.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/acceptance_live_report.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/acceptance_live_validation.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/discovery.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/document.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/output_format.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/task/prompts.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/templates/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/templates/test.sh.tmpl +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/traces/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/traces/local.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/traces/models.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/traces/task_gen.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/training/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/training/backends/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/training/backends/prime_rl.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/training/run_manifest.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/call_purpose.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/metrics.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/sessions.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/tree.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/trl_sft_tokenization.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/__init__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/__main__.py +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/fonts/OFL-google-sans-code.txt +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/fonts/google-sans-code-400-latin.woff2 +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/fonts/google-sans-code-600-latin.woff2 +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/theme.css +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/theme.js +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/vendor/LICENSE.highlight.js +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/trajectories/viewer/assets/vendor/highlight.min.js +0 -0
- {benchflow-0.7.11.dev2422 → benchflow-0.9.1}/src/benchflow/usage_tracking.py +0 -0
|
@@ -0,0 +1,198 @@
|
|
|
1
|
+
# Byte-compiled / optimized / DLL files
|
|
2
|
+
__pycache__/
|
|
3
|
+
*.py[cod]
|
|
4
|
+
*$py.class
|
|
5
|
+
|
|
6
|
+
# C extensions
|
|
7
|
+
*.so
|
|
8
|
+
|
|
9
|
+
# Distribution / packaging
|
|
10
|
+
.Python
|
|
11
|
+
build/
|
|
12
|
+
develop-eggs/
|
|
13
|
+
dist/
|
|
14
|
+
downloads/
|
|
15
|
+
eggs/
|
|
16
|
+
.eggs/
|
|
17
|
+
lib/
|
|
18
|
+
lib64/
|
|
19
|
+
parts/
|
|
20
|
+
sdist/
|
|
21
|
+
var/
|
|
22
|
+
wheels/
|
|
23
|
+
share/python-wheels/
|
|
24
|
+
*.egg-info/
|
|
25
|
+
.installed.cfg
|
|
26
|
+
*.egg
|
|
27
|
+
MANIFEST
|
|
28
|
+
|
|
29
|
+
# PyInstaller
|
|
30
|
+
# Usually these files are written by a python script from a template
|
|
31
|
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
|
32
|
+
*.manifest
|
|
33
|
+
*.spec
|
|
34
|
+
|
|
35
|
+
# Installer logs
|
|
36
|
+
pip-log.txt
|
|
37
|
+
pip-delete-this-directory.txt
|
|
38
|
+
|
|
39
|
+
# Unit test / coverage reports
|
|
40
|
+
htmlcov/
|
|
41
|
+
.tox/
|
|
42
|
+
.nox/
|
|
43
|
+
.coverage
|
|
44
|
+
.coverage.*
|
|
45
|
+
.cache
|
|
46
|
+
nosetests.xml
|
|
47
|
+
coverage.xml
|
|
48
|
+
*.cover
|
|
49
|
+
*.py,cover
|
|
50
|
+
.hypothesis/
|
|
51
|
+
.pytest_cache/
|
|
52
|
+
cover/
|
|
53
|
+
|
|
54
|
+
# Translations
|
|
55
|
+
*.mo
|
|
56
|
+
*.pot
|
|
57
|
+
|
|
58
|
+
# Django stuff:
|
|
59
|
+
*.log
|
|
60
|
+
local_settings.py
|
|
61
|
+
db.sqlite3
|
|
62
|
+
db.sqlite3-journal
|
|
63
|
+
|
|
64
|
+
# Flask stuff:
|
|
65
|
+
instance/
|
|
66
|
+
.webassets-cache
|
|
67
|
+
|
|
68
|
+
# Scrapy stuff:
|
|
69
|
+
.scrapy
|
|
70
|
+
|
|
71
|
+
# Sphinx documentation
|
|
72
|
+
docs/_build/
|
|
73
|
+
|
|
74
|
+
# PyBuilder
|
|
75
|
+
.pybuilder/
|
|
76
|
+
target/
|
|
77
|
+
|
|
78
|
+
# Jupyter Notebook
|
|
79
|
+
.ipynb_checkpoints
|
|
80
|
+
|
|
81
|
+
# IPython
|
|
82
|
+
profile_default/
|
|
83
|
+
ipython_config.py
|
|
84
|
+
|
|
85
|
+
# pyenv
|
|
86
|
+
# For a library or package, you might want to ignore these files since the code is
|
|
87
|
+
# intended to run in multiple environments; otherwise, check them in:
|
|
88
|
+
# .python-version
|
|
89
|
+
|
|
90
|
+
# pipenv
|
|
91
|
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
|
92
|
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
|
93
|
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
|
94
|
+
# install all needed dependencies.
|
|
95
|
+
#Pipfile.lock
|
|
96
|
+
|
|
97
|
+
# UV
|
|
98
|
+
# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
|
|
99
|
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
|
100
|
+
# commonly ignored for libraries.
|
|
101
|
+
#uv.lock
|
|
102
|
+
|
|
103
|
+
# poetry
|
|
104
|
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
|
105
|
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
|
106
|
+
# commonly ignored for libraries.
|
|
107
|
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
|
108
|
+
#poetry.lock
|
|
109
|
+
|
|
110
|
+
# pdm
|
|
111
|
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
|
112
|
+
#pdm.lock
|
|
113
|
+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
|
114
|
+
# in version control.
|
|
115
|
+
# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
|
|
116
|
+
.pdm.toml
|
|
117
|
+
.pdm-python
|
|
118
|
+
.pdm-build/
|
|
119
|
+
|
|
120
|
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
|
121
|
+
__pypackages__/
|
|
122
|
+
|
|
123
|
+
# Celery stuff
|
|
124
|
+
celerybeat-schedule
|
|
125
|
+
celerybeat.pid
|
|
126
|
+
|
|
127
|
+
# SageMath parsed files
|
|
128
|
+
*.sage.py
|
|
129
|
+
|
|
130
|
+
# Environments
|
|
131
|
+
.env
|
|
132
|
+
.venv
|
|
133
|
+
.venvs/
|
|
134
|
+
env/
|
|
135
|
+
venv/
|
|
136
|
+
ENV/
|
|
137
|
+
env.bak/
|
|
138
|
+
venv.bak/
|
|
139
|
+
|
|
140
|
+
# Spyder project settings
|
|
141
|
+
.spyderproject
|
|
142
|
+
.spyproject
|
|
143
|
+
|
|
144
|
+
# Rope project settings
|
|
145
|
+
.ropeproject
|
|
146
|
+
|
|
147
|
+
# mkdocs documentation
|
|
148
|
+
/site
|
|
149
|
+
|
|
150
|
+
# mypy
|
|
151
|
+
.mypy_cache/
|
|
152
|
+
.dmypy.json
|
|
153
|
+
dmypy.json
|
|
154
|
+
|
|
155
|
+
# Pyre type checker
|
|
156
|
+
.pyre/
|
|
157
|
+
|
|
158
|
+
# pytype static type analyzer
|
|
159
|
+
.pytype/
|
|
160
|
+
|
|
161
|
+
# Cython debug symbols
|
|
162
|
+
cython_debug/
|
|
163
|
+
|
|
164
|
+
# PyCharm
|
|
165
|
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
|
166
|
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
|
167
|
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
|
168
|
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
|
169
|
+
#.idea/
|
|
170
|
+
|
|
171
|
+
# PyPI configuration file
|
|
172
|
+
.pypirc
|
|
173
|
+
|
|
174
|
+
.DS_Store
|
|
175
|
+
# benchflow
|
|
176
|
+
.cache/
|
|
177
|
+
|
|
178
|
+
trials/
|
|
179
|
+
jobs/
|
|
180
|
+
# The docs' Jobs chapter is not run output.
|
|
181
|
+
!docs/jobs/
|
|
182
|
+
.jobs/
|
|
183
|
+
dogfood/
|
|
184
|
+
tmp/
|
|
185
|
+
.local/
|
|
186
|
+
src/benchflow/adapters/_toolathlon_canvas_tokens.json
|
|
187
|
+
.claude/settings.local.json
|
|
188
|
+
tests/.smoke-jobs/
|
|
189
|
+
context/
|
|
190
|
+
tutorials/
|
|
191
|
+
.playwright-mcp/
|
|
192
|
+
/.claude/handoffs
|
|
193
|
+
|
|
194
|
+
# task.md draft 2 fixtures are verbatim copies; their logs are evidence, not output.
|
|
195
|
+
!tests/fixtures/taskmd/**/*.log
|
|
196
|
+
|
|
197
|
+
# bfx binaries are built (make bfx) or come with the wheel; never committed.
|
|
198
|
+
src/benchflow/_bfx/bin/
|