benchflow 0.7.8.dev2342__tar.gz → 0.7.8.dev2347__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-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/PKG-INFO +1 -1
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/pyproject.toml +1 -1
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/agentcore.py +98 -10
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agentcore_parallel.py +155 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agentcore_sandbox.py +101 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/.gitignore +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/CHANGELOG.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/LICENSE +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/README.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_dotenv.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_paths.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_run.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_types.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/benchmark_repos.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/build_context_stage.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/config_override.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/config_redaction.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/content_address.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/dataset_registry.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/env_registry.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/evaluation_results.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/hf_datasets.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/json_safe.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/learner_memory.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/live_activity.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/result_metadata.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/result_paths.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/reward_events.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/scoring.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/source_provenance.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/task_authoring/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/task_authoring/_evidence_paths.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/task_authoring/acceptance_evidence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/task_authoring/scaffolding.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/task_authoring/structural_checks.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/text.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/yaml_loader.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/acp/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/acp/client.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/acp/container_transport.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/acp/runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/acp/selection.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/acp/session.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/acp/timeout_cleanup.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/acp/transport.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/acp/types.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/acp/watchdog.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/_toolathlon.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/_toolathlon_container.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/_toolathlon_fake_mail.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/_toolathlon_poste_users.tsv +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/_toolathlon_services.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/harbor.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/inbound.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/inspect_ai.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/ors.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/resources/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/resources/mcp_atlas_bridge.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/resources/mcp_atlas_judge.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/source.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agent_router.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agent_router_guide.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agent_router_parity.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agent_router_scaffold.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/codex_config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/credentials.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/deepagents_acp_shim.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/env.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/errors.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/harvey_lab_acp_shim.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/install.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/manifest.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/openclaw_acp_shim.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/pi_acp_launcher.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/protocol.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/providers.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/registry.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/remote_manifests.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/branch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/_failure_evidence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/_hosted_env.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/_live_progress.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/_options.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/_shared.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/_traj_tui.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/_traj_upload_ui.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/adopt.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/agent.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/continue_cmd.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/environment.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/eval_artifacts.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/eval_lift.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/hub.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/main.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/monitor.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/rescore.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/review.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/reviewer_options.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/sandbox.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/skills.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/tasks.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/trace_import.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/train.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/cli/traj.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/continue_run/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/continue_run/batch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/continue_run/orchestrator.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/continue_run/replay_proxy.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/continue_run/run_folder.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/continue_run/sandbox_proxy.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/contracts/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/contracts/planes.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/contracts/user.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/demo_task/environment/Dockerfile +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/demo_task/instruction.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/demo_task/task.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/demo_task/task.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/demo_task/tests/test.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/diagnostics.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/environment/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/environment/_registry/env0@outage.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/environment/_registry/env0@prod.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/environment/manifest.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/environment/manifest_env.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/environment/protocol.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/environment/readiness.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/eval_artifacts.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/eval_lift.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/eval_plan.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/eval_sharding.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/eval_worker.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/evaluation.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/experimental/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/experimental/mcp/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/experimental/mcp/hooks.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/experimental/mcp/reviewer_server.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/hosted_env.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/hub/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/hub/harbor_registry.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/integrations/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/integrations/trl/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/integrations/trl/spec.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/learner_skills.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/learner_store.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/loop_strategies.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/loop_sweep.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/metrics.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/models.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/monitor.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/providers/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/providers/litellm_bedrock_patch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/providers/litellm_bedrock_preflight.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/providers/litellm_config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/providers/litellm_gemini_passthrough_patch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/providers/litellm_logging.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/providers/litellm_runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/providers/runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/publish/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/publish/_progress.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/publish/azure_blob.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/publish/broker.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/publish/huggingface.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/publish/redact.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/publish/traj_capture.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/publish/traj_report.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/py.typed +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/automatic.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/default-rubric.json +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/evidence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/options.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/outcome.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/persistence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/preflight.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/prompts.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/resume.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/runner.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/scoring.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/review/wrapper.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/README.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/builtins.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/events.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/file_readers.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/llm.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/memory_scorer.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/node.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/protocol.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/rubric.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/rubric_config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rewards/validation.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout/_config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout/_deadline.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout/_results.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout/_review.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout/_setup.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout/_skills.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout/_usage.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout/_user_loop.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout/session_factory_runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout/task_runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout_branch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/rollout_planes.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/_base.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/_cache_reclaim.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/_compose.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/_compose_files/docker-compose-base.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/_compose_files/docker-compose-build.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/_compose_files/docker-compose-net-admin.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/_compose_files/docker-compose-no-network.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/_compose_files/docker-compose-prebuilt.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/_egress_denylist_proxy.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/_sdk_ops.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/agentcore_builder.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/agentcore_image.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/agentcore_provisioning.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/agentcore_reaper.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/agentcore_sealed.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/apple_container.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/daytona.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/daytona_dind.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/daytona_pty.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/daytona_reaper.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/daytona_strategies.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/docker.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/egress_denylist.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/lockdown.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/metadata.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/modal_impl.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/process/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/process/_base.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/process/agentcore.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/process/apple.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/process/daytona.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/process/docker.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/protocol.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/providers.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/services.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/setup.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/snapshot.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sandbox/user.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/scenes.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/sdk.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/self_gen.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/skill_eval/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/skill_eval/_core.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/skill_eval/gepa_export.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/skill_eval/schema.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/skill_policy.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/skills.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/_document_evidence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/_document_normalize.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/_document_parse.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/_document_profiles.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/acceptance_live.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/acceptance_live_model.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/acceptance_live_report.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/acceptance_live_validation.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/discovery.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/document.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/env.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/export.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/imports.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/output_format.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/package.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/paths.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/prompts.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/runtime_capabilities.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/runtime_view.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/task.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/verifier.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/verifier_core.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/verifier_document.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/verifier_errors.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/verifier_judge_inputs.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/verifier_ors_episode.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/verifier_reward_kit.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/verifier_scan.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/task/verifier_script_strategy.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/templates/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/templates/judge.py.tmpl +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/templates/test.sh.tmpl +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/traces/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/traces/huggingface.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/traces/local.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/traces/models.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/traces/parsers.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/traces/task_gen.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/training/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/training/backends/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/training/backends/prime_rl.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/training/run_manifest.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/_capture.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/_export_common.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/_llm_capture.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/_snapshot.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/call_purpose.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/export.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/export_adp.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/export_atif.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/export_prime_sft.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/export_trl_sft.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/metrics.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/results.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/sessions.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/tree.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/trl_sft_tokenization.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/types.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/__main__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/boot.js +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/catalog.js +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/detail.js +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/fonts/OFL-google-sans-code.txt +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/fonts/google-sans-code-400-latin.woff2 +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/fonts/google-sans-code-600-latin.woff2 +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/template.html +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/theme.css +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/theme.js +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/vendor/LICENSE.highlight.js +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/vendor/highlight.min.js +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/viewer.css +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/assets/viewer.js +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/catalog.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/legacy.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/models.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/payload.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/render.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/server.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/trajectories/viewer/sources.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/usage_tracking.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/acceptance_live_harness.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/agents/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/agents/test_codex_config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/agents/test_manifest_dirscan.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/agents/test_manifest_loader.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/agents/test_manifest_parity.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/agents/test_manifest_wiring.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/agents/test_namespace_shorthand.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/agents/test_plugin_entry_points.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/agents/test_protocol.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/agents/test_remote_manifest_autoload.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/README.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/acp_smoke/environment/Dockerfile +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/acp_smoke/environment/docker-compose.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/acp_smoke/environment/skills/conformance-writer/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/acp_smoke/instruction.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/acp_smoke/solution/solve.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/acp_smoke/task.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/acp_smoke/task.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/acp_smoke/tests/test.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/conformance-results.json +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/proof_multi_agent.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/proof_snapshot.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/run_conformance.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conformance/self_gen_smoke_skills/skill-creator/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/conftest.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/continue_run/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/continue_run/_helpers.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/continue_run/test_batch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/continue_run/test_orchestrator.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/continue_run/test_replay_proxy.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/continue_run/test_run_folder.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/environment/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/environment/test_chibench_manifest.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/environment/test_clawsbench_manifest.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/environment/test_manifest.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/environment/test_manifest_env.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/environment/test_protocol.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/environment/test_readiness.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/hello-world-task/environment/Dockerfile +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/hello-world-task/instruction.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/hello-world-task/solution/solve.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/hello-world-task/task.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/hello-world-task/task.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/hello-world-task/tests/test.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/test_claude.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/test_codex.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/test_codex_custom_provider.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/test_gemini.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/test_openclaw.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/traces/minimal-claude.jsonl +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/examples/traces/minimal-opentraces.jsonl +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/digest/README.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/digest/alpha-task/environment/Dockerfile +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/digest/alpha-task/instruction.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/digest/alpha-task/task.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/digest/alpha-task/tests/test.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/digest/beta-task/data/empty.bin +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/digest/beta-task/data/unicode.txt +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/digest/beta-task/instruction.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/digest/beta-task/task.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/digest/not-a-task/notes.txt +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/mock_acp_agent.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/mock_acp_agent_interleaved.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/mock_acp_agent_multi_turn.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/mock_openai_responses_server.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/Dockerfile +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/data/michigan_stations.txt +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/flood-detection/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/nws-flood-thresholds/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/usgs-data-download/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/flood-risk-analysis/instruction.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/flood-risk-analysis/solution/solve.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/flood-risk-analysis/task.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test_outputs.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/Dockerfile +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/climate.csv +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/hydrology.csv +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/land_cover.csv +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/water_temperature.csv +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/contribution-analysis/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/meteorology-driver-classification/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/pca-decomposition/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/trend-analysis/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/instruction.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/solution/solve.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/task.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test_outputs.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/manifest.json +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/Dockerfile +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/r2r_simulator.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/finite-horizon-lqr/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/integral-action-design/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/mpc-horizon-tuning/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/state-space-linearization/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/system_config.json +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/instruction.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/solution/solve.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/task.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test_outputs.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/Dockerfile +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/generate_training_pcaps.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/local.rules +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/scripts/summarize_http_requests.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/scripts/run_suricata_offline.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-rules-basics/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/suricata.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/instruction.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/solution/solve.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/task.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test_outputs.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/Dockerfile +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syz-extract-constants/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzkaller-build-loop/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzlang-ioctl-basics/SKILL.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/instruction.md +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/solution/solve.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/task.toml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test_outputs.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/_consistency.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/agent_judge.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/check_adapter_evidence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/check_hosted_env_evidence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/check_results.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/check_skillsbench_harbor_parity.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/check_trace_to_task_evidence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/configs/claude-agent-acp.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/configs/codex-acp.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/configs/gemini.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/configs/harvey-lab-harness.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/configs/mimo.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/configs/openclaw.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/configs/opencode.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/configs/openhands.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/configs/pi-acp.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/deepagents_harness.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/rubric_checks.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/run.sh +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/run_suite.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/scenarios.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/integration/suites/release.yaml +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_acceptance_evidence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_acceptance_live.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_acceptance_live_execution.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_acp.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_acp_buffered_timeout.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_acp_capability_advertising.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_acp_mcp_servers.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_acp_model_config_dispatch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_acp_pinned_protocol_guard.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_acp_setup_failure_propagation.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_acp_timeout_evidence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_adapter_scripts.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_adapters.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_cli.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_egress_firewall.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_env_resolution.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_gemini_defaults.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_idle_timeout_cli.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_model_decouple.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_registry.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_router.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_router_cli_e2e.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_router_scaffold.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_setup.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agent_spec.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agentcore_builder.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agentcore_reaper.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_agentcore_transport.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_api_error_capture.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_apple_container_sandbox.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_automatic_review_scoring.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_bare_model_provider.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_base_install_imports.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_bedrock_thinking.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_benchflow_experiment_review_validator.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_benchmark_repos_resolve_repo_path.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_branch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_build_context_stage.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_build_review_pack.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_capture_trajectory.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_check_skillsbench_harbor_parity.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_clawsbench_slice.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_cli_adopt_aliases.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_cli_arg_validation.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_cli_daytona.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_cli_docs_drift.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_cli_edge_case_hardening.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_cli_hub_env.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_cli_live_progress.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_cli_misc.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_codex_review.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_codex_self_write_auth.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_config_override.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_config_redaction.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_connect_as_env.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_console_error_truncation.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_console_progress.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_continuallearningbench_adapter.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_dataset_registry.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_daytona_command_polling.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_daytona_dind_compose_up.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_daytona_download.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_daytona_litellm_runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_daytona_poll_deadline.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_daytona_reap.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_deepagents_agent.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_diagnostics.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_docker_prune_scoping.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_docker_uploads.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_docs_examples.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_egress_connect_authority.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_egress_denylist.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_egress_denylist_integration.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_egress_dynamic_certs.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_egress_model_gateway.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_eng50_capabilities.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_env_registry.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_env_setup.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_environment_manifest_controls.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_eval_artifact_cli.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_eval_filters_applied.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_eval_lift.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_eval_sharding.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_eval_single_task_summary.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_eval_source_provenance.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_eval_worker_retry.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_eval_zero_task_guard.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_evaluation_environment_manifest.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_exclude_tasks.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_filter_credentialed_cells.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_harvey_lab_shim.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_hilbench_adapter.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_hosted_env.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_hosted_env_rollout_contract.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_hosted_search_policy.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_hub_harbor_registry.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_inbound_adapter_manifest.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_inbound_adapters.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_integration_agent_judge.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_integration_check_results.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_integration_consistency.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_integration_matrix.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_integration_provider_selection.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_integration_run_suite.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_integration_suite.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_internet_policy.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_job.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_job_sequential_shared.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_job_sequential_shared_resume.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_judge_robustness.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_judge_symlink_ingestion.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_learner_skills.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_learner_skills_traversal.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_learner_store.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_learner_store_persistence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_litellm_config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_litellm_gemini_passthrough_patch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_litellm_hardening.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_litellm_logging.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_litellm_model_via_env_generic.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_litellm_reasoning_passthrough.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_litellm_runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_litellm_smoke.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_live_llm_trajectory.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_llm_judge.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_llm_judge_event_tags.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_llm_judge_verifier.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_loop_strategies.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_loop_summary.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_loop_sweep.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_memory_scorer.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_metrics.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_mle_bench_adapter.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_mock_openai_responses_server.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_monitor_scaffold.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_native_acp_usage.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_network_denylist_config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_no_cross_provider_fallback.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_notification_order_real.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_opencode_family_proxy_tracking.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_oracle.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_oracle_chokepoint.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_paths_safe.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_paths_symlink_helpers.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_pi_acp_launcher.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_pi_acp_proxy_routing.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_process.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_project_skills_layout.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_provider_auth_detection.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_providers.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_publish_azure_blob.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_publish_huggingface.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_redacted_snapshot.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_reexport.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_registry_invariants.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_release_hardening_r5.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_release_version.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_release_workflow_wiring.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_resolve_env_helpers.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_review_automatic.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_review_boundaries.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_review_evidence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_review_lifecycle.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_review_resume.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_review_rubric.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_review_runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_review_runtime_automatic.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_review_snapshot.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_reviewer_options.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_reward_lenient.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_reward_node.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_reward_range.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_reward_unified_contract.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rewards.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rewards_jsonl.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_architecture.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_branch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_config_path_coercion.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_environment.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_hard_deadline.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_import_no_side_effects.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_on_ask_user_wiring.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_planes_contract.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_probe_sandbox_health.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_session_factory_dispatch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_setup_commands.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rollout_upload.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rubric_checks.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_rubric_config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_runtime_capabilities.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_runtime_config_wired.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_runtime_live_sandbox.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_exec_secret_handling.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_hardening.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_isolation_copy_traversal.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_live_process.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_multi_service.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_prebuilt_validation.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_protocol.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_provider_registry_drift.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_setup.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_snapshot_contract.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_upload_symlink.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sandbox_verifier_workspace.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_scene.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_scene_outbox_trial.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_scene_parallel_group.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_scene_result_aggregation.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_scoring.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sdk_internals.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sdk_lockdown.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sdk_run_alias.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_sealed_channel_container.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_self_gen_cli.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_self_gen_export_error_channel.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_self_gen_export_failures.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_self_gen_orchestration.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_session_factory_runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_session_request_permission_dispatch.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_skill_eval.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_skill_eval_dryrun.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_skill_eval_integration.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_skill_eval_sweep.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_skill_eval_traversal.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_skill_invocation_artifacts.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_skill_policy.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_skills.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_skills_dir_agent_home_link.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_skillsbench_conversion_conformance.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_skillsbench_harbor_run_suite.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_smoke.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_smoke_wiring.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_source_adapters.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_subscription_auth.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_task_check_eval_consistency.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_task_config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_task_digest.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_task_document.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_task_download.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_task_export.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_task_output_format.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_task_package.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_task_runtime_primitive.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_tasks.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_token_usage_normalization.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_tool_call_raw_io.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_trace_import_cli.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_trace_task_gen_traversal.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_trace_to_task_evidence.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_traces_huggingface.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_traces_parsers.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_traces_task_gen.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_train_cli.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_train_mode_artifact_emission.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_train_trl_cli.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_traj_report.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_traj_staging_phases.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_traj_tui.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_traj_upload_cli.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_traj_upload_skill.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_traj_workspace.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_trajectory_integration.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_trajectory_streaming.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_trajectory_upload_layout.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_trajectory_upload_service.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_trial_agent_timeout_verify.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_trial_install_agent_timeout.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_trial_litellm_runtime.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_trl_integration.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_usage_litellm.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_usage_required.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_usage_tracking.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_user.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_v06_guard_ports.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_verifier_document.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_verifier_multi_container.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_verifier_output.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_verifier_output_freshness.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_verifier_strategies.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_verifier_wedge_retry.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_verify.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_viewer_confirm.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_workflow_action_pinning.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/test_yaml_config.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/__init__.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_export.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_export_adp.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_export_atif.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_export_common.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_export_nan_handling.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_export_prime_sft.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_redaction.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_step_granularity.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_tree.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_viewer_acp_renderer.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_viewer_browser.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_viewer_rubric.py +0 -0
- {benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/tests/trajectories/test_viewer_theme.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: benchflow
|
|
3
|
-
Version: 0.7.8.
|
|
3
|
+
Version: 0.7.8.dev2347
|
|
4
4
|
Summary: Multi-turn agent benchmarking with ACP — run any agent, any model, any provider.
|
|
5
5
|
Project-URL: Homepage, https://github.com/benchflow-ai/benchflow
|
|
6
6
|
Project-URL: Repository, https://github.com/benchflow-ai/benchflow
|
|
@@ -50,6 +50,7 @@ import hashlib
|
|
|
50
50
|
import io
|
|
51
51
|
import json
|
|
52
52
|
import os
|
|
53
|
+
import re
|
|
53
54
|
import shlex
|
|
54
55
|
import tarfile
|
|
55
56
|
import threading
|
|
@@ -92,7 +93,11 @@ _MAX_DOWNLOAD_BYTES = 64 * 1024 * 1024
|
|
|
92
93
|
# whatever the service currently defaults to.
|
|
93
94
|
_PROTOCOL_CONFIGURATION = {"serverProtocol": "HTTP"}
|
|
94
95
|
#: AgentCore offers PUBLIC or VPC only; see the registry's enforces_no_network.
|
|
95
|
-
|
|
96
|
+
_NETWORK_MODES = ("PUBLIC", "VPC")
|
|
97
|
+
#: ``VpcConfig`` caps both lists at 16 and pins the id shapes.
|
|
98
|
+
_MAX_VPC_IDS = 16
|
|
99
|
+
_SUBNET_ID = re.compile(r"^subnet-[0-9a-zA-Z]{8,17}$")
|
|
100
|
+
_SECURITY_GROUP_ID = re.compile(r"^sg-[0-9a-zA-Z]{8,17}$")
|
|
96
101
|
|
|
97
102
|
# Environment overrides.
|
|
98
103
|
_ENV_REGION = "BENCHFLOW_AGENTCORE_REGION"
|
|
@@ -100,6 +105,9 @@ _ENV_ROLE_ARN = "BENCHFLOW_AGENTCORE_ROLE_ARN"
|
|
|
100
105
|
_ENV_ECR_REPOSITORY = "BENCHFLOW_AGENTCORE_ECR_REPOSITORY"
|
|
101
106
|
_ENV_IDLE_TIMEOUT = "BENCHFLOW_AGENTCORE_IDLE_TIMEOUT_SEC"
|
|
102
107
|
_ENV_MAX_LIFETIME = "BENCHFLOW_AGENTCORE_MAX_LIFETIME_SEC"
|
|
108
|
+
_ENV_NETWORK_MODE = "BENCHFLOW_AGENTCORE_NETWORK_MODE"
|
|
109
|
+
_ENV_SUBNETS = "BENCHFLOW_AGENTCORE_SUBNETS"
|
|
110
|
+
_ENV_SECURITY_GROUPS = "BENCHFLOW_AGENTCORE_SECURITY_GROUPS"
|
|
103
111
|
|
|
104
112
|
|
|
105
113
|
class AgentCoreSandbox(BaseSandbox):
|
|
@@ -314,7 +322,7 @@ class AgentCoreSandbox(BaseSandbox):
|
|
|
314
322
|
contract = {
|
|
315
323
|
"imageDigest": image_digest,
|
|
316
324
|
"lifecycleConfiguration": self._lifecycle_configuration(),
|
|
317
|
-
"networkConfiguration":
|
|
325
|
+
"networkConfiguration": self._network_configuration(),
|
|
318
326
|
"protocolConfiguration": _PROTOCOL_CONFIGURATION,
|
|
319
327
|
"roleArn": self._require_role_arn(),
|
|
320
328
|
}
|
|
@@ -341,7 +349,7 @@ class AgentCoreSandbox(BaseSandbox):
|
|
|
341
349
|
"containerConfiguration": {"containerUri": image_uri}
|
|
342
350
|
},
|
|
343
351
|
roleArn=self._require_role_arn(),
|
|
344
|
-
networkConfiguration=
|
|
352
|
+
networkConfiguration=self._network_configuration(),
|
|
345
353
|
protocolConfiguration=_PROTOCOL_CONFIGURATION,
|
|
346
354
|
lifecycleConfiguration=self._lifecycle_configuration(),
|
|
347
355
|
description=f"BenchFlow sandbox for {self.environment_name}",
|
|
@@ -381,7 +389,7 @@ class AgentCoreSandbox(BaseSandbox):
|
|
|
381
389
|
"containerConfiguration": {"containerUri": image_uri}
|
|
382
390
|
},
|
|
383
391
|
roleArn=self._require_role_arn(),
|
|
384
|
-
networkConfiguration=
|
|
392
|
+
networkConfiguration=self._network_configuration(),
|
|
385
393
|
protocolConfiguration=_PROTOCOL_CONFIGURATION,
|
|
386
394
|
# Omitting this resets idle/max-lifetime to the service
|
|
387
395
|
# defaults, silently discarding the caller's configured
|
|
@@ -396,7 +404,7 @@ class AgentCoreSandbox(BaseSandbox):
|
|
|
396
404
|
image_uri,
|
|
397
405
|
self._lifecycle_configuration(),
|
|
398
406
|
self._require_role_arn(),
|
|
399
|
-
|
|
407
|
+
self._network_configuration(),
|
|
400
408
|
_PROTOCOL_CONFIGURATION,
|
|
401
409
|
)
|
|
402
410
|
self.logger.info("Adopted existing AgentCore runtime %s", arn)
|
|
@@ -510,11 +518,6 @@ class AgentCoreSandbox(BaseSandbox):
|
|
|
510
518
|
# for — wrong permissions, wrong egress, or a shell that never answers.
|
|
511
519
|
for label, expected, found in (
|
|
512
520
|
("roleArn", role_arn, detail.get("roleArn")),
|
|
513
|
-
(
|
|
514
|
-
"networkConfiguration",
|
|
515
|
-
dict(network),
|
|
516
|
-
dict(detail.get("networkConfiguration") or {}),
|
|
517
|
-
),
|
|
518
521
|
(
|
|
519
522
|
"protocolConfiguration",
|
|
520
523
|
dict(protocol),
|
|
@@ -523,6 +526,25 @@ class AgentCoreSandbox(BaseSandbox):
|
|
|
523
526
|
):
|
|
524
527
|
if found != expected:
|
|
525
528
|
drifted[label] = (found, expected)
|
|
529
|
+
|
|
530
|
+
def _placement(config: dict[str, Any]) -> tuple[Any, ...]:
|
|
531
|
+
"""Only the placement BenchFlow itself pins.
|
|
532
|
+
|
|
533
|
+
``VpcConfig`` also carries service-managed members that cannot be
|
|
534
|
+
sent on create, and nothing promises the ids come back in the order
|
|
535
|
+
they were given — comparing the whole document would refuse every
|
|
536
|
+
adoption of a healthy VPC runtime.
|
|
537
|
+
"""
|
|
538
|
+
vpc = config.get("networkModeConfig") or {}
|
|
539
|
+
return (
|
|
540
|
+
config.get("networkMode"),
|
|
541
|
+
tuple(sorted(vpc.get("subnets") or ())),
|
|
542
|
+
tuple(sorted(vpc.get("securityGroups") or ())),
|
|
543
|
+
)
|
|
544
|
+
|
|
545
|
+
found_network = dict(detail.get("networkConfiguration") or {})
|
|
546
|
+
if _placement(found_network) != _placement(dict(network)):
|
|
547
|
+
drifted["networkConfiguration"] = (found_network, dict(network))
|
|
526
548
|
if drifted:
|
|
527
549
|
raise SandboxStartupError(
|
|
528
550
|
f"AgentCore runtime {runtime_id} does not match this run's "
|
|
@@ -564,6 +586,72 @@ class AgentCoreSandbox(BaseSandbox):
|
|
|
564
586
|
"maxLifetime": lifetime,
|
|
565
587
|
}
|
|
566
588
|
|
|
589
|
+
def _network_configuration(self) -> dict[str, Any]:
|
|
590
|
+
"""Where the runtime's microVMs are placed on the network.
|
|
591
|
+
|
|
592
|
+
``PUBLIC`` stays the default so existing deployments do not move, but
|
|
593
|
+
the ``VPC`` opt-in fails loudly rather than quietly: a half-configured
|
|
594
|
+
runtime that silently stays public is exactly the exposure the operator
|
|
595
|
+
set out to remove, and it is invisible once the runtime is READY.
|
|
596
|
+
"""
|
|
597
|
+
|
|
598
|
+
def _ids(name: str, pattern: re.Pattern[str], shape: str) -> list[str]:
|
|
599
|
+
raw = os.environ.get(name) or ""
|
|
600
|
+
# Canonical order and no duplicates: this list feeds the runtime
|
|
601
|
+
# contract digest, so "a,b" and "b,a" must not register two
|
|
602
|
+
# runtimes for the same infrastructure.
|
|
603
|
+
values: list[str] = sorted(
|
|
604
|
+
{item.strip() for item in raw.split(",") if item.strip()}
|
|
605
|
+
)
|
|
606
|
+
for item in values:
|
|
607
|
+
if not pattern.match(item):
|
|
608
|
+
raise ValueError(
|
|
609
|
+
f"{name} must be a comma-separated list of {shape} ids, "
|
|
610
|
+
f"got {item!r}."
|
|
611
|
+
)
|
|
612
|
+
if len(values) > _MAX_VPC_IDS:
|
|
613
|
+
raise ValueError(
|
|
614
|
+
f"{name} accepts at most {_MAX_VPC_IDS} ids, got {len(values)}."
|
|
615
|
+
)
|
|
616
|
+
return values
|
|
617
|
+
|
|
618
|
+
subnets = _ids(_ENV_SUBNETS, _SUBNET_ID, "subnet-*")
|
|
619
|
+
security_groups = _ids(_ENV_SECURITY_GROUPS, _SECURITY_GROUP_ID, "sg-*")
|
|
620
|
+
mode = (os.environ.get(_ENV_NETWORK_MODE) or "PUBLIC").strip().upper()
|
|
621
|
+
if mode not in _NETWORK_MODES:
|
|
622
|
+
raise ValueError(
|
|
623
|
+
f"{_ENV_NETWORK_MODE} must be one of {', '.join(_NETWORK_MODES)}, "
|
|
624
|
+
f"got {mode!r}."
|
|
625
|
+
)
|
|
626
|
+
if mode == "PUBLIC":
|
|
627
|
+
if subnets or security_groups:
|
|
628
|
+
raise ValueError(
|
|
629
|
+
f"{_ENV_SUBNETS}/{_ENV_SECURITY_GROUPS} are set but "
|
|
630
|
+
f"{_ENV_NETWORK_MODE} is not VPC, so the runtime would still "
|
|
631
|
+
f"be created on the public internet. Set "
|
|
632
|
+
f"{_ENV_NETWORK_MODE}=VPC to place it in the VPC."
|
|
633
|
+
)
|
|
634
|
+
return {"networkMode": "PUBLIC"}
|
|
635
|
+
missing = [
|
|
636
|
+
name
|
|
637
|
+
for name, values in (
|
|
638
|
+
(_ENV_SUBNETS, subnets),
|
|
639
|
+
(_ENV_SECURITY_GROUPS, security_groups),
|
|
640
|
+
)
|
|
641
|
+
if not values
|
|
642
|
+
]
|
|
643
|
+
if missing:
|
|
644
|
+
raise ValueError(
|
|
645
|
+
f"{_ENV_NETWORK_MODE}=VPC requires {' and '.join(missing)}."
|
|
646
|
+
)
|
|
647
|
+
return {
|
|
648
|
+
"networkMode": "VPC",
|
|
649
|
+
"networkModeConfig": {
|
|
650
|
+
"subnets": subnets,
|
|
651
|
+
"securityGroups": security_groups,
|
|
652
|
+
},
|
|
653
|
+
}
|
|
654
|
+
|
|
567
655
|
def configure_agent_timeout(self, timeout_sec: int) -> None:
|
|
568
656
|
"""Keep the remote session alive for the effective rollout budget."""
|
|
569
657
|
self._agent_timeout_sec = max(0, int(timeout_sec))
|
|
@@ -743,6 +743,161 @@ class TestAdoptionContract:
|
|
|
743
743
|
self._verify(self._detail(**{field: value}))
|
|
744
744
|
|
|
745
745
|
|
|
746
|
+
_VPC_NETWORK = {
|
|
747
|
+
"networkMode": "VPC",
|
|
748
|
+
"networkModeConfig": {
|
|
749
|
+
"subnets": ["subnet-0a1b2c3d4e5f67890"],
|
|
750
|
+
"securityGroups": ["sg-0a1b2c3d4e5f67890"],
|
|
751
|
+
},
|
|
752
|
+
}
|
|
753
|
+
|
|
754
|
+
|
|
755
|
+
class TestNetworkConfigurationReachesTheRuntime:
|
|
756
|
+
"""The configured network placement has to survive to the control plane.
|
|
757
|
+
|
|
758
|
+
``_network_configuration`` deciding VPC is worth nothing if registration
|
|
759
|
+
still sends the old constant, and the mistake is invisible: the runtime
|
|
760
|
+
reaches READY either way, just reachable from the internet.
|
|
761
|
+
"""
|
|
762
|
+
|
|
763
|
+
def _vpc_env(self, monkeypatch):
|
|
764
|
+
monkeypatch.setenv("BENCHFLOW_AGENTCORE_ROLE_ARN", "arn:aws:iam::1:role/rt")
|
|
765
|
+
monkeypatch.setenv("BENCHFLOW_AGENTCORE_NETWORK_MODE", "VPC")
|
|
766
|
+
monkeypatch.setenv("BENCHFLOW_AGENTCORE_SUBNETS", "subnet-0a1b2c3d4e5f67890")
|
|
767
|
+
monkeypatch.setenv(
|
|
768
|
+
"BENCHFLOW_AGENTCORE_SECURITY_GROUPS", "sg-0a1b2c3d4e5f67890"
|
|
769
|
+
)
|
|
770
|
+
|
|
771
|
+
def _adopt(self, found):
|
|
772
|
+
control = MagicMock()
|
|
773
|
+
control.get_agent_runtime.return_value = {
|
|
774
|
+
"agentRuntimeArtifact": {
|
|
775
|
+
"containerConfiguration": {"containerUri": "repo@sha256:a"}
|
|
776
|
+
},
|
|
777
|
+
"lifecycleConfiguration": {
|
|
778
|
+
"idleRuntimeSessionTimeout": 600,
|
|
779
|
+
"maxLifetime": 7200,
|
|
780
|
+
},
|
|
781
|
+
"roleArn": "arn:aws:iam::1:role/rt",
|
|
782
|
+
"networkConfiguration": found,
|
|
783
|
+
"protocolConfiguration": {"serverProtocol": "HTTP"},
|
|
784
|
+
}
|
|
785
|
+
AgentCoreSandbox._verify_adopted_runtime(
|
|
786
|
+
control,
|
|
787
|
+
"rt-1",
|
|
788
|
+
"repo@sha256:a",
|
|
789
|
+
{"idleRuntimeSessionTimeout": 600, "maxLifetime": 7200},
|
|
790
|
+
"arn:aws:iam::1:role/rt",
|
|
791
|
+
_VPC_NETWORK,
|
|
792
|
+
{"serverProtocol": "HTTP"},
|
|
793
|
+
)
|
|
794
|
+
|
|
795
|
+
def test_a_service_managed_member_does_not_block_adoption(self):
|
|
796
|
+
"""``VpcConfig`` carries members BenchFlow never sends.
|
|
797
|
+
|
|
798
|
+
``requireServiceS3Endpoint`` cannot even be set on create. Adoption is
|
|
799
|
+
the path every rollout after the first takes, so comparing the whole
|
|
800
|
+
document would fail a VPC matrix on everything after its first create.
|
|
801
|
+
|
|
802
|
+
Guards PR #1082 against the whole-document comparison it replaced.
|
|
803
|
+
"""
|
|
804
|
+
self._adopt(
|
|
805
|
+
{
|
|
806
|
+
"networkMode": "VPC",
|
|
807
|
+
"networkModeConfig": {
|
|
808
|
+
**_VPC_NETWORK["networkModeConfig"],
|
|
809
|
+
"requireServiceS3Endpoint": True,
|
|
810
|
+
},
|
|
811
|
+
}
|
|
812
|
+
)
|
|
813
|
+
|
|
814
|
+
def test_a_different_subnet_is_still_refused(self):
|
|
815
|
+
"""Tolerating extra members must not tolerate the wrong network."""
|
|
816
|
+
from benchflow.sandbox.protocol import SandboxStartupError
|
|
817
|
+
|
|
818
|
+
with pytest.raises(SandboxStartupError, match="does not match"):
|
|
819
|
+
self._adopt(
|
|
820
|
+
{
|
|
821
|
+
"networkMode": "VPC",
|
|
822
|
+
"networkModeConfig": {
|
|
823
|
+
"subnets": ["subnet-0987654321fedcba"],
|
|
824
|
+
"securityGroups": ["sg-0a1b2c3d4e5f67890"],
|
|
825
|
+
},
|
|
826
|
+
}
|
|
827
|
+
)
|
|
828
|
+
|
|
829
|
+
@pytest.mark.asyncio
|
|
830
|
+
async def test_registration_sends_the_configured_vpc(self, tmp_path, monkeypatch):
|
|
831
|
+
self._vpc_env(monkeypatch)
|
|
832
|
+
env = _sandbox(_make_task(tmp_path))
|
|
833
|
+
control = MagicMock()
|
|
834
|
+
control.create_agent_runtime.return_value = {
|
|
835
|
+
"agentRuntimeId": "rt-1",
|
|
836
|
+
"agentRuntimeArn": "arn:rt",
|
|
837
|
+
}
|
|
838
|
+
control.get_agent_runtime.return_value = {"status": "READY"}
|
|
839
|
+
|
|
840
|
+
with patch.object(env, "_client", return_value=control):
|
|
841
|
+
await env._create_or_adopt_runtime("bf_x", "repo@sha256:a")
|
|
842
|
+
|
|
843
|
+
sent = control.create_agent_runtime.call_args.kwargs
|
|
844
|
+
assert sent["networkConfiguration"] == _VPC_NETWORK
|
|
845
|
+
|
|
846
|
+
@pytest.mark.asyncio
|
|
847
|
+
async def test_repointing_a_stale_runtime_keeps_the_vpc(
|
|
848
|
+
self, tmp_path, monkeypatch
|
|
849
|
+
):
|
|
850
|
+
"""``update_agent_runtime`` replaces the whole config it is given.
|
|
851
|
+
|
|
852
|
+
Omitting the network here is how a VPC runtime silently reverts to
|
|
853
|
+
PUBLIC on the next image change.
|
|
854
|
+
"""
|
|
855
|
+
from botocore.exceptions import ClientError
|
|
856
|
+
|
|
857
|
+
self._vpc_env(monkeypatch)
|
|
858
|
+
env = _sandbox(_make_task(tmp_path))
|
|
859
|
+
control = MagicMock()
|
|
860
|
+
control.create_agent_runtime.side_effect = ClientError(
|
|
861
|
+
{"Error": {"Code": "ConflictException", "Message": "exists"}},
|
|
862
|
+
"CreateAgentRuntime",
|
|
863
|
+
)
|
|
864
|
+
control.get_agent_runtime.return_value = {
|
|
865
|
+
"status": "READY",
|
|
866
|
+
"agentRuntimeArtifact": {
|
|
867
|
+
"containerConfiguration": {"containerUri": "repo@sha256:b"}
|
|
868
|
+
},
|
|
869
|
+
"lifecycleConfiguration": env._lifecycle_configuration(),
|
|
870
|
+
"roleArn": "arn:aws:iam::1:role/rt",
|
|
871
|
+
"networkConfiguration": _VPC_NETWORK,
|
|
872
|
+
"protocolConfiguration": {"serverProtocol": "HTTP"},
|
|
873
|
+
}
|
|
874
|
+
|
|
875
|
+
with (
|
|
876
|
+
patch.object(env, "_client", return_value=control),
|
|
877
|
+
patch.object(
|
|
878
|
+
provisioning,
|
|
879
|
+
"find_runtime_by_name",
|
|
880
|
+
return_value=("arn:rt", "rt-1", "repo@sha256:a"),
|
|
881
|
+
),
|
|
882
|
+
):
|
|
883
|
+
await env._create_or_adopt_runtime("bf_x", "repo@sha256:b")
|
|
884
|
+
|
|
885
|
+
sent = control.update_agent_runtime.call_args.kwargs
|
|
886
|
+
assert sent["networkConfiguration"] == _VPC_NETWORK
|
|
887
|
+
|
|
888
|
+
def test_a_vpc_runtime_does_not_share_an_identity_with_a_public_one(
|
|
889
|
+
self, tmp_path, monkeypatch
|
|
890
|
+
):
|
|
891
|
+
"""Same name means the VPC run adopts the existing PUBLIC runtime."""
|
|
892
|
+
monkeypatch.setenv("BENCHFLOW_AGENTCORE_ROLE_ARN", "arn:aws:iam::1:role/rt")
|
|
893
|
+
env = _sandbox(_make_task(tmp_path))
|
|
894
|
+
public = env._runtime_contract_digest("sha256:a")
|
|
895
|
+
|
|
896
|
+
self._vpc_env(monkeypatch)
|
|
897
|
+
|
|
898
|
+
assert env._runtime_contract_digest("sha256:a") != public
|
|
899
|
+
|
|
900
|
+
|
|
746
901
|
class TestDeprecatedCleanupAliasIsSafe:
|
|
747
902
|
"""`bench environment cleanup` reaches the same destructive code.
|
|
748
903
|
|
|
@@ -530,6 +530,107 @@ class TestCapabilityGating:
|
|
|
530
530
|
)
|
|
531
531
|
|
|
532
532
|
|
|
533
|
+
class TestNetworkConfiguration:
|
|
534
|
+
"""Opting a runtime out of the public internet.
|
|
535
|
+
|
|
536
|
+
``networkMode`` accepts ``PUBLIC`` or ``VPC``. Every runtime was
|
|
537
|
+
registered ``PUBLIC``, so an agent under test was reachable from the
|
|
538
|
+
internet with no way to opt out. These pin the opt-in and, more
|
|
539
|
+
importantly, the ways it can fail open.
|
|
540
|
+
"""
|
|
541
|
+
|
|
542
|
+
_MODE = "BENCHFLOW_AGENTCORE_NETWORK_MODE"
|
|
543
|
+
_SUBNETS = "BENCHFLOW_AGENTCORE_SUBNETS"
|
|
544
|
+
_SECURITY_GROUPS = "BENCHFLOW_AGENTCORE_SECURITY_GROUPS"
|
|
545
|
+
|
|
546
|
+
def _vpc_env(self, monkeypatch):
|
|
547
|
+
monkeypatch.setenv(self._MODE, "VPC")
|
|
548
|
+
monkeypatch.setenv(self._SUBNETS, "subnet-0a1b2c3d4e5f67890")
|
|
549
|
+
monkeypatch.setenv(self._SECURITY_GROUPS, "sg-0a1b2c3d4e5f67890")
|
|
550
|
+
|
|
551
|
+
def test_the_default_is_public(self, sandbox, monkeypatch):
|
|
552
|
+
"""Unset must stay unchanged, or every existing deployment moves."""
|
|
553
|
+
for name in (self._MODE, self._SUBNETS, self._SECURITY_GROUPS):
|
|
554
|
+
monkeypatch.delenv(name, raising=False)
|
|
555
|
+
|
|
556
|
+
assert sandbox._network_configuration() == {"networkMode": "PUBLIC"}
|
|
557
|
+
|
|
558
|
+
def test_vpc_mode_carries_the_subnets_and_security_groups(
|
|
559
|
+
self, sandbox, monkeypatch
|
|
560
|
+
):
|
|
561
|
+
"""The runtime shape nests these under ``networkModeConfig``.
|
|
562
|
+
|
|
563
|
+
Browsers and code interpreters take the same ``VpcConfig`` under
|
|
564
|
+
``vpcConfig`` instead; sending that key here is a ValidationException.
|
|
565
|
+
The ids come back sorted and deduplicated because this list feeds the
|
|
566
|
+
runtime contract digest: "a,b" and "b,a" must not register two runtimes
|
|
567
|
+
for the same infrastructure.
|
|
568
|
+
"""
|
|
569
|
+
monkeypatch.setenv(self._MODE, "VPC")
|
|
570
|
+
monkeypatch.setenv(
|
|
571
|
+
self._SUBNETS,
|
|
572
|
+
"subnet-0a1b2c3d4e5f67890, subnet-01234567, subnet-01234567",
|
|
573
|
+
)
|
|
574
|
+
monkeypatch.setenv(self._SECURITY_GROUPS, "sg-0a1b2c3d4e5f67890")
|
|
575
|
+
|
|
576
|
+
assert sandbox._network_configuration() == {
|
|
577
|
+
"networkMode": "VPC",
|
|
578
|
+
"networkModeConfig": {
|
|
579
|
+
"subnets": ["subnet-01234567", "subnet-0a1b2c3d4e5f67890"],
|
|
580
|
+
"securityGroups": ["sg-0a1b2c3d4e5f67890"],
|
|
581
|
+
},
|
|
582
|
+
}
|
|
583
|
+
|
|
584
|
+
@pytest.mark.parametrize(
|
|
585
|
+
"missing",
|
|
586
|
+
["BENCHFLOW_AGENTCORE_SUBNETS", "BENCHFLOW_AGENTCORE_SECURITY_GROUPS"],
|
|
587
|
+
)
|
|
588
|
+
def test_vpc_mode_requires_both_lists(self, sandbox, monkeypatch, missing):
|
|
589
|
+
"""VPC with only half the config is rejected by the service."""
|
|
590
|
+
self._vpc_env(monkeypatch)
|
|
591
|
+
monkeypatch.delenv(missing)
|
|
592
|
+
|
|
593
|
+
with pytest.raises(ValueError, match=missing):
|
|
594
|
+
sandbox._network_configuration()
|
|
595
|
+
|
|
596
|
+
def test_vpc_resources_without_vpc_mode_are_refused(self, sandbox, monkeypatch):
|
|
597
|
+
"""Ignoring them would leave the runtime on the public internet.
|
|
598
|
+
|
|
599
|
+
The operator who sets subnets but forgets the mode believes the agent
|
|
600
|
+
is isolated. Failing open there is the whole bug this guards.
|
|
601
|
+
|
|
602
|
+
Guards PR #1082.
|
|
603
|
+
"""
|
|
604
|
+
monkeypatch.delenv(self._MODE, raising=False)
|
|
605
|
+
monkeypatch.setenv(self._SUBNETS, "subnet-0a1b2c3d4e5f67890")
|
|
606
|
+
monkeypatch.setenv(self._SECURITY_GROUPS, "sg-0a1b2c3d4e5f67890")
|
|
607
|
+
|
|
608
|
+
with pytest.raises(ValueError, match=self._MODE):
|
|
609
|
+
sandbox._network_configuration()
|
|
610
|
+
|
|
611
|
+
def test_an_unknown_mode_is_refused(self, sandbox, monkeypatch):
|
|
612
|
+
"""``no-network`` reads as isolation but is not a mode the service has."""
|
|
613
|
+
monkeypatch.setenv(self._MODE, "ISOLATED")
|
|
614
|
+
|
|
615
|
+
with pytest.raises(ValueError, match="PUBLIC"):
|
|
616
|
+
sandbox._network_configuration()
|
|
617
|
+
|
|
618
|
+
def test_a_malformed_subnet_id_is_refused(self, sandbox, monkeypatch):
|
|
619
|
+
"""Otherwise a pasted VPC id surfaces as an opaque ValidationException."""
|
|
620
|
+
self._vpc_env(monkeypatch)
|
|
621
|
+
monkeypatch.setenv(self._SUBNETS, "vpc-0a1b2c3d4e5f67890")
|
|
622
|
+
|
|
623
|
+
with pytest.raises(ValueError, match="subnet-"):
|
|
624
|
+
sandbox._network_configuration()
|
|
625
|
+
|
|
626
|
+
def test_a_malformed_security_group_id_is_refused(self, sandbox, monkeypatch):
|
|
627
|
+
self._vpc_env(monkeypatch)
|
|
628
|
+
monkeypatch.setenv(self._SECURITY_GROUPS, "0a1b2c3d4e5f67890")
|
|
629
|
+
|
|
630
|
+
with pytest.raises(ValueError, match="sg-"):
|
|
631
|
+
sandbox._network_configuration()
|
|
632
|
+
|
|
633
|
+
|
|
533
634
|
@pytest.mark.skipif(
|
|
534
635
|
os.environ.get("BENCHFLOW_AGENTCORE_LIVE_TEST") != "1",
|
|
535
636
|
reason="live AWS test; set BENCHFLOW_AGENTCORE_LIVE_TEST=1 to run",
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/build_context_stage.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/config_redaction.py
RENAMED
|
File without changes
|
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/dataset_registry.py
RENAMED
|
File without changes
|
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/evaluation_results.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/source_provenance.py
RENAMED
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/_utils/task_authoring/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/acp/container_transport.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/_toolathlon_container.py
RENAMED
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/_toolathlon_fake_mail.py
RENAMED
|
File without changes
|
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/_toolathlon_services.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/adapters/resources/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/deepagents_acp_shim.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.8.dev2342 → benchflow-0.7.8.dev2347}/src/benchflow/agents/harvey_lab_acp_shim.py
RENAMED
|
File without changes
|
|
File without changes
|