benchflow 0.7.1.dev1969__tar.gz → 0.7.1.dev1972__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-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/CHANGELOG.md +11 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/PKG-INFO +5 -1
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/README.md +4 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/pyproject.toml +1 -1
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/traj.py +63 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conftest.py +10 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_traj_upload_cli.py +80 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/.gitignore +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/LICENSE +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_dotenv.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_paths.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_run.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_types.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/benchmark_repos.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/build_context_stage.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/config.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/config_override.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/content_address.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/dataset_registry.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/env_registry.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/evaluation_results.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/hf_datasets.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/json_safe.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/learner_memory.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/live_activity.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/result_metadata.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/reward_events.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/scoring.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/source_provenance.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/task_authoring/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/task_authoring/_evidence_paths.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/task_authoring/acceptance_evidence.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/task_authoring/scaffolding.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/task_authoring/structural_checks.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/text.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/yaml_loader.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/acp/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/acp/client.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/acp/container_transport.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/acp/runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/acp/selection.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/acp/session.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/acp/transport.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/acp/types.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/_toolathlon.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/_toolathlon_container.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/_toolathlon_fake_mail.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/_toolathlon_poste_users.tsv +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/_toolathlon_services.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/harbor.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/inbound.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/inspect_ai.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/ors.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/resources/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/resources/mcp_atlas_bridge.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/resources/mcp_atlas_judge.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/source.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agent_router.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agent_router_guide.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agent_router_parity.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agent_router_scaffold.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/codex_config.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/credentials.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/deepagents_acp_shim.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/env.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/errors.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/harvey_lab_acp_shim.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/install.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/manifest.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/openclaw_acp_shim.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/pi_acp_launcher.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/protocol.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/providers.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/registry.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/remote_manifests.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/branch.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/_failure_evidence.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/_hosted_env.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/_live_progress.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/_options.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/_shared.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/_traj_upload_ui.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/adopt.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/agent.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/continue_cmd.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/environment.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/eval_artifacts.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/eval_lift.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/hub.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/main.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/monitor.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/review.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/sandbox.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/skills.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/tasks.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/trace_import.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/cli/train.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/continue_run/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/continue_run/batch.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/continue_run/orchestrator.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/continue_run/replay_proxy.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/continue_run/run_folder.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/continue_run/sandbox_proxy.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/contracts/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/contracts/planes.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/contracts/user.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/demo_task/environment/Dockerfile +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/demo_task/instruction.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/demo_task/task.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/demo_task/task.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/demo_task/tests/test.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/diagnostics.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/environment/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/environment/_registry/env0@outage.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/environment/_registry/env0@prod.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/environment/manifest.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/environment/manifest_env.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/environment/protocol.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/environment/readiness.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/eval_artifacts.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/eval_lift.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/eval_plan.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/eval_sharding.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/eval_worker.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/evaluation.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/experimental/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/experimental/mcp/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/experimental/mcp/hooks.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/experimental/mcp/reviewer_server.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/hosted_env.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/hub/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/hub/harbor_registry.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/integrations/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/integrations/trl/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/integrations/trl/spec.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/learner_skills.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/learner_store.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/loop_strategies.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/loop_sweep.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/metrics.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/models.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/monitor.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/providers/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/providers/litellm_bedrock_patch.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/providers/litellm_bedrock_preflight.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/providers/litellm_config.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/providers/litellm_logging.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/providers/litellm_runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/providers/runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/publish/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/publish/_progress.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/publish/azure_blob.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/publish/broker.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/publish/huggingface.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/publish/redact.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/publish/traj_capture.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/publish/traj_report.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/py.typed +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/review/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/review/config.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/review/default-rubric.json +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/review/prompts.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/review/runner.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/review/wrapper.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/README.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/builtins.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/events.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/file_readers.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/llm.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/memory_scorer.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/node.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/protocol.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/rubric.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/rubric_config.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rewards/validation.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout/_config.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout/_deadline.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout/_results.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout/_setup.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout/_skills.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout/_usage.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout/_user_loop.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout/session_factory_runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout/task_runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout_branch.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/rollout_planes.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/_base.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/_cache_reclaim.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/_compose.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/_compose_files/docker-compose-base.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/_compose_files/docker-compose-build.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/_compose_files/docker-compose-no-network.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/_compose_files/docker-compose-prebuilt.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/_sdk_ops.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/agentcore.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/agentcore_builder.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/agentcore_image.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/agentcore_provisioning.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/agentcore_reaper.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/agentcore_sealed.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/apple_container.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/daytona.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/daytona_dind.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/daytona_pty.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/daytona_reaper.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/daytona_strategies.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/docker.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/lockdown.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/metadata.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/modal_impl.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/process/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/process/_base.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/process/agentcore.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/process/apple.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/process/daytona.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/process/docker.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/protocol.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/providers.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/services.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/setup.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/snapshot.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sandbox/user.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/scenes.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/sdk.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/self_gen.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/skill_eval/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/skill_eval/_core.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/skill_eval/gepa_export.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/skill_eval/schema.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/skill_policy.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/skills.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/_document_evidence.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/_document_normalize.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/_document_parse.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/_document_profiles.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/acceptance_live.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/acceptance_live_model.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/acceptance_live_report.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/acceptance_live_validation.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/config.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/discovery.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/document.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/env.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/export.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/imports.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/output_format.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/package.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/paths.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/prompts.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/runtime_capabilities.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/runtime_view.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/task.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/verifier.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/verifier_core.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/verifier_document.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/verifier_errors.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/verifier_judge_inputs.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/verifier_ors_episode.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/verifier_reward_kit.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/verifier_scan.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/task/verifier_script_strategy.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/templates/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/templates/judge.py.tmpl +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/templates/test.sh.tmpl +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/traces/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/traces/huggingface.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/traces/local.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/traces/models.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/traces/parsers.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/traces/task_gen.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/training/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/training/backends/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/training/backends/prime_rl.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/training/run_manifest.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/_capture.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/_export_common.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/_llm_capture.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/call_purpose.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/export.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/export_adp.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/export_atif.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/export_prime_sft.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/export_trl_sft.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/metrics.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/results.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/sessions.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/tree.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/trl_sft_tokenization.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/types.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/trajectories/viewer.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/usage_tracking.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/acceptance_live_harness.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/agents/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/agents/test_manifest_dirscan.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/agents/test_manifest_loader.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/agents/test_manifest_parity.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/agents/test_manifest_wiring.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/agents/test_namespace_shorthand.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/agents/test_plugin_entry_points.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/agents/test_protocol.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/agents/test_remote_manifest_autoload.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/README.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/acp_smoke/environment/Dockerfile +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/acp_smoke/environment/docker-compose.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/acp_smoke/environment/skills/conformance-writer/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/acp_smoke/instruction.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/acp_smoke/solution/solve.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/acp_smoke/task.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/acp_smoke/task.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/acp_smoke/tests/test.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/conformance-results.json +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/proof_multi_agent.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/proof_snapshot.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/run_conformance.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/conformance/self_gen_smoke_skills/skill-creator/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/continue_run/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/continue_run/_helpers.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/continue_run/test_batch.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/continue_run/test_orchestrator.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/continue_run/test_replay_proxy.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/continue_run/test_run_folder.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/environment/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/environment/test_chibench_manifest.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/environment/test_clawsbench_manifest.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/environment/test_manifest.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/environment/test_manifest_env.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/environment/test_protocol.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/environment/test_readiness.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/hello-world-task/environment/Dockerfile +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/hello-world-task/instruction.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/hello-world-task/solution/solve.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/hello-world-task/task.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/hello-world-task/task.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/hello-world-task/tests/test.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/test_claude.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/test_codex.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/test_codex_custom_provider.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/test_gemini.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/test_openclaw.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/traces/minimal-claude.jsonl +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/examples/traces/minimal-opentraces.jsonl +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/digest/README.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/digest/alpha-task/environment/Dockerfile +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/digest/alpha-task/instruction.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/digest/alpha-task/task.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/digest/alpha-task/tests/test.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/digest/beta-task/data/empty.bin +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/digest/beta-task/data/unicode.txt +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/digest/beta-task/instruction.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/digest/beta-task/task.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/digest/not-a-task/notes.txt +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/mock_acp_agent.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/mock_acp_agent_interleaved.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/mock_acp_agent_multi_turn.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/mock_openai_responses_server.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/Dockerfile +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/data/michigan_stations.txt +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/flood-detection/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/nws-flood-thresholds/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/usgs-data-download/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/flood-risk-analysis/instruction.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/flood-risk-analysis/solution/solve.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/flood-risk-analysis/task.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test_outputs.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/Dockerfile +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/climate.csv +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/hydrology.csv +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/land_cover.csv +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/water_temperature.csv +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/contribution-analysis/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/meteorology-driver-classification/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/pca-decomposition/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/trend-analysis/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/instruction.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/solution/solve.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/task.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test_outputs.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/manifest.json +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/Dockerfile +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/r2r_simulator.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/finite-horizon-lqr/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/integral-action-design/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/mpc-horizon-tuning/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/state-space-linearization/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/system_config.json +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/instruction.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/solution/solve.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/task.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test_outputs.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/Dockerfile +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/generate_training_pcaps.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/local.rules +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/scripts/summarize_http_requests.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/scripts/run_suricata_offline.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-rules-basics/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/suricata.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/instruction.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/solution/solve.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/task.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test_outputs.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/Dockerfile +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syz-extract-constants/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzkaller-build-loop/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzlang-ioctl-basics/SKILL.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/instruction.md +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/solution/solve.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/task.toml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test_outputs.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/_consistency.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/agent_judge.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/check_adapter_evidence.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/check_hosted_env_evidence.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/check_results.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/check_skillsbench_harbor_parity.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/check_trace_to_task_evidence.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/configs/claude-agent-acp.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/configs/codex-acp.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/configs/gemini.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/configs/harvey-lab-harness.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/configs/mimo.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/configs/openclaw.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/configs/opencode.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/configs/openhands.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/configs/pi-acp.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/deepagents_harness.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/rubric_checks.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/run.sh +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/run_suite.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/scenarios.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/integration/suites/release.yaml +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_acceptance_evidence.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_acceptance_live.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_acceptance_live_execution.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_acp.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_acp_capability_advertising.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_acp_mcp_servers.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_acp_model_config_dispatch.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_acp_pinned_protocol_guard.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_acp_setup_failure_propagation.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_adapter_scripts.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_adapters.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agent_cli.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agent_env_resolution.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agent_gemini_defaults.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agent_idle_timeout_cli.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agent_model_decouple.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agent_registry.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agent_router.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agent_router_cli_e2e.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agent_router_scaffold.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agent_setup.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agent_spec.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agentcore_builder.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agentcore_parallel.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agentcore_reaper.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agentcore_sandbox.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_agentcore_transport.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_api_error_capture.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_apple_container_sandbox.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_bare_model_provider.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_base_install_imports.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_bedrock_thinking.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_benchflow_experiment_review_validator.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_benchmark_repos_resolve_repo_path.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_branch.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_build_context_stage.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_build_review_pack.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_capture_trajectory.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_check_skillsbench_harbor_parity.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_clawsbench_slice.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_cli_adopt_aliases.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_cli_arg_validation.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_cli_daytona.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_cli_docs_drift.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_cli_edge_case_hardening.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_cli_hub_env.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_cli_live_progress.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_cli_misc.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_codex_review.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_codex_self_write_auth.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_config_override.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_config_redaction.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_connect_as_env.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_console_error_truncation.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_console_progress.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_continuallearningbench_adapter.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_dataset_registry.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_daytona_command_polling.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_daytona_dind_compose_up.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_daytona_download.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_daytona_litellm_runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_daytona_poll_deadline.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_daytona_reap.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_deepagents_agent.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_diagnostics.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_docker_prune_scoping.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_docker_uploads.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_docs_examples.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_eng50_capabilities.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_env_registry.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_env_setup.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_environment_manifest_controls.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_eval_artifact_cli.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_eval_filters_applied.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_eval_lift.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_eval_sharding.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_eval_single_task_summary.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_eval_source_provenance.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_eval_worker_retry.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_eval_zero_task_guard.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_evaluation_environment_manifest.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_exclude_tasks.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_filter_credentialed_cells.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_harvey_lab_shim.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_hilbench_adapter.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_hosted_env.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_hosted_env_rollout_contract.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_hub_harbor_registry.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_inbound_adapter_manifest.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_inbound_adapters.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_integration_agent_judge.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_integration_check_results.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_integration_consistency.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_integration_matrix.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_integration_provider_selection.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_integration_run_suite.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_integration_suite.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_internet_policy.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_job.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_job_sequential_shared.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_job_sequential_shared_resume.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_judge_robustness.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_judge_symlink_ingestion.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_learner_skills.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_learner_skills_traversal.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_learner_store.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_learner_store_persistence.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_litellm_config.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_litellm_hardening.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_litellm_logging.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_litellm_model_via_env_generic.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_litellm_reasoning_passthrough.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_litellm_runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_litellm_smoke.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_live_llm_trajectory.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_llm_judge.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_llm_judge_event_tags.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_llm_judge_verifier.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_loop_strategies.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_loop_summary.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_loop_sweep.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_memory_scorer.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_metrics.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_mle_bench_adapter.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_mock_openai_responses_server.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_monitor_scaffold.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_native_acp_usage.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_no_cross_provider_fallback.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_notification_order_real.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_opencode_family_proxy_tracking.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_oracle.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_oracle_chokepoint.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_paths_safe.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_paths_symlink_helpers.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_pi_acp_launcher.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_pi_acp_proxy_routing.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_process.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_project_skills_layout.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_provider_auth_detection.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_providers.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_publish_azure_blob.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_reexport.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_registry_invariants.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_release_hardening_r5.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_release_version.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_release_workflow_wiring.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_resolve_env_helpers.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_review_boundaries.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_review_rubric.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_review_runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_reward_lenient.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_reward_node.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_reward_range.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_reward_unified_contract.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rewards.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rewards_jsonl.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_architecture.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_branch.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_config_path_coercion.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_environment.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_hard_deadline.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_import_no_side_effects.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_on_ask_user_wiring.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_planes_contract.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_probe_sandbox_health.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_session_factory_dispatch.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_setup_commands.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rollout_upload.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rubric_checks.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_rubric_config.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_runtime_capabilities.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_runtime_config_wired.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_runtime_live_sandbox.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_exec_secret_handling.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_hardening.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_isolation_copy_traversal.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_live_process.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_multi_service.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_prebuilt_validation.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_protocol.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_provider_registry_drift.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_setup.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_snapshot_contract.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_upload_symlink.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sandbox_verifier_workspace.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_scene.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_scene_outbox_trial.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_scene_parallel_group.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_scene_result_aggregation.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_scoring.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sdk_internals.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sdk_lockdown.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sdk_run_alias.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_sealed_channel_container.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_self_gen_cli.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_self_gen_export_error_channel.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_self_gen_export_failures.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_self_gen_orchestration.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_session_factory_runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_session_request_permission_dispatch.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_skill_eval.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_skill_eval_dryrun.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_skill_eval_integration.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_skill_eval_sweep.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_skill_eval_traversal.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_skill_invocation_artifacts.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_skill_policy.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_skills.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_skills_dir_agent_home_link.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_skillsbench_conversion_conformance.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_skillsbench_harbor_run_suite.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_smoke.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_smoke_wiring.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_source_adapters.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_subscription_auth.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_task_check_eval_consistency.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_task_config.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_task_digest.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_task_document.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_task_download.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_task_export.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_task_output_format.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_task_package.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_task_runtime_primitive.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_tasks.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_token_usage_normalization.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_trace_import_cli.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_trace_task_gen_traversal.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_trace_to_task_evidence.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_traces_huggingface.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_traces_parsers.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_traces_task_gen.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_train_cli.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_train_mode_artifact_emission.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_train_trl_cli.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_traj_report.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_traj_staging_phases.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_traj_upload_skill.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_trajectory_integration.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_trajectory_streaming.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_trajectory_upload_layout.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_trajectory_upload_service.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_trial_agent_timeout_verify.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_trial_install_agent_timeout.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_trial_litellm_runtime.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_trl_integration.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_usage_litellm.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_usage_required.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_usage_tracking.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_user.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_v06_guard_ports.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_verifier_document.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_verifier_multi_container.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_verifier_output.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_verifier_output_freshness.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_verifier_strategies.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_verifier_wedge_retry.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_verify.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_workflow_action_pinning.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/test_yaml_config.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/trajectories/__init__.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/trajectories/test_export.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/trajectories/test_export_adp.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/trajectories/test_export_atif.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/trajectories/test_export_common.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/trajectories/test_export_nan_handling.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/trajectories/test_export_prime_sft.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/trajectories/test_redaction.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/trajectories/test_step_granularity.py +0 -0
- {benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/tests/trajectories/test_tree.py +0 -0
|
@@ -2,6 +2,17 @@
|
|
|
2
2
|
|
|
3
3
|
## [Unreleased]
|
|
4
4
|
|
|
5
|
+
### Added
|
|
6
|
+
- **`bench traj setup` / `bench traj upload` print an upgrade hint when
|
|
7
|
+
outdated.** Both commands start with a lightweight PyPI latest-version
|
|
8
|
+
check (2 s timeout, completely silent on any network or parse failure) and
|
|
9
|
+
print a one-line `uv tool install --python 3.12 --upgrade --force
|
|
10
|
+
benchflow` hint when the installed version is older than the latest
|
|
11
|
+
release; dev/prereleases of a newer-or-equal base are not outdated.
|
|
12
|
+
`BENCHFLOW_SKIP_UPDATE_CHECK=1` disables the check. The
|
|
13
|
+
`benchflow-traj-upload` skill and docs now tell contributors to upgrade to
|
|
14
|
+
the latest BenchFlow (0.7.1+) before using the trajectory-upload flow.
|
|
15
|
+
|
|
5
16
|
### Changed
|
|
6
17
|
- **Trajectory contribution is a copy-paste line, plus optional setup.**
|
|
7
18
|
Contributors paste one line into their agent; the agent reads
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: benchflow
|
|
3
|
-
Version: 0.7.1.
|
|
3
|
+
Version: 0.7.1.dev1972
|
|
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
|
|
@@ -100,6 +100,10 @@ Submit my best local Claude Code or Codex session to the BenchFlow eval prize. R
|
|
|
100
100
|
The agent finds sessions on this machine, opens the viewer, and uploads after
|
|
101
101
|
you like what you see.
|
|
102
102
|
|
|
103
|
+
Be on the latest BenchFlow first — `uv tool install --python 3.12 --upgrade
|
|
104
|
+
--force benchflow`. The `bench traj` commands print a one-line upgrade hint
|
|
105
|
+
when a newer release is available.
|
|
106
|
+
|
|
103
107
|
Prefer the terminal instead? The guided upload inspects before anything leaves
|
|
104
108
|
your machine — it renders a redacted trajectory report (step counts, masked
|
|
105
109
|
secrets, preview) and asks for confirmation:
|
|
@@ -26,6 +26,10 @@ Submit my best local Claude Code or Codex session to the BenchFlow eval prize. R
|
|
|
26
26
|
The agent finds sessions on this machine, opens the viewer, and uploads after
|
|
27
27
|
you like what you see.
|
|
28
28
|
|
|
29
|
+
Be on the latest BenchFlow first — `uv tool install --python 3.12 --upgrade
|
|
30
|
+
--force benchflow`. The `bench traj` commands print a one-line upgrade hint
|
|
31
|
+
when a newer release is available.
|
|
32
|
+
|
|
29
33
|
Prefer the terminal instead? The guided upload inspects before anything leaves
|
|
30
34
|
your machine — it renders a redacted trajectory report (step counts, masked
|
|
31
35
|
secrets, preview) and asks for confirmation:
|
|
@@ -59,6 +59,67 @@ CONTRIBUTOR_PROMPT = (
|
|
|
59
59
|
"and follow it: find a session, open the viewer, upload only after I review it."
|
|
60
60
|
)
|
|
61
61
|
|
|
62
|
+
UPGRADE_COMMAND = "uv tool install --python 3.12 --upgrade --force benchflow"
|
|
63
|
+
|
|
64
|
+
|
|
65
|
+
def _fetch_latest_version() -> str | None:
|
|
66
|
+
"""Return the latest release on PyPI, or ``None`` when unavailable.
|
|
67
|
+
|
|
68
|
+
Module-level so tests monkeypatch it and never touch the network.
|
|
69
|
+
"""
|
|
70
|
+
import logging
|
|
71
|
+
|
|
72
|
+
import httpx
|
|
73
|
+
|
|
74
|
+
# The CLI configures INFO logging; keep httpx's "HTTP Request" line for
|
|
75
|
+
# this background check out of the user's terminal.
|
|
76
|
+
logger = logging.getLogger("httpx")
|
|
77
|
+
previous_level = logger.level
|
|
78
|
+
logger.setLevel(logging.WARNING)
|
|
79
|
+
try:
|
|
80
|
+
response = httpx.get("https://pypi.org/pypi/benchflow/json", timeout=2.0)
|
|
81
|
+
response.raise_for_status()
|
|
82
|
+
version = response.json()["info"]["version"]
|
|
83
|
+
finally:
|
|
84
|
+
logger.setLevel(previous_level)
|
|
85
|
+
return version if isinstance(version, str) else None
|
|
86
|
+
|
|
87
|
+
|
|
88
|
+
def _installed_version() -> str | None:
|
|
89
|
+
import importlib.metadata
|
|
90
|
+
|
|
91
|
+
try:
|
|
92
|
+
return importlib.metadata.version("benchflow")
|
|
93
|
+
except importlib.metadata.PackageNotFoundError:
|
|
94
|
+
return None
|
|
95
|
+
|
|
96
|
+
|
|
97
|
+
def _maybe_print_update_hint() -> None:
|
|
98
|
+
"""Print a one-line upgrade hint when a newer release exists on PyPI.
|
|
99
|
+
|
|
100
|
+
Best-effort only: any network, parse, or metadata failure is silent and
|
|
101
|
+
never blocks the command. ``BENCHFLOW_SKIP_UPDATE_CHECK`` disables the
|
|
102
|
+
check entirely (the test suite sets it for hermeticity).
|
|
103
|
+
"""
|
|
104
|
+
if os.environ.get("BENCHFLOW_SKIP_UPDATE_CHECK"):
|
|
105
|
+
return
|
|
106
|
+
try:
|
|
107
|
+
installed = _installed_version()
|
|
108
|
+
latest = _fetch_latest_version()
|
|
109
|
+
if installed is None or latest is None:
|
|
110
|
+
return
|
|
111
|
+
from packaging.version import Version
|
|
112
|
+
|
|
113
|
+
# Compare release tuples so a dev/prerelease of a newer (or equal)
|
|
114
|
+
# base — e.g. 0.7.1.dev0 against PyPI 0.7.0 — never counts as
|
|
115
|
+
# outdated.
|
|
116
|
+
if Version(installed).release >= Version(latest).release:
|
|
117
|
+
return
|
|
118
|
+
except Exception:
|
|
119
|
+
return
|
|
120
|
+
# Plain print keeps the hint one physical line (no Rich wrapping).
|
|
121
|
+
print(f"A newer BenchFlow ({latest}) is available — run: {UPGRADE_COMMAND}")
|
|
122
|
+
|
|
62
123
|
|
|
63
124
|
@dataclass(frozen=True)
|
|
64
125
|
class _UploadOptions:
|
|
@@ -110,6 +171,7 @@ def register_traj(app: typer.Typer) -> None:
|
|
|
110
171
|
] = False,
|
|
111
172
|
) -> None:
|
|
112
173
|
"""Install the submit skill, or print the line to paste into an agent."""
|
|
174
|
+
_maybe_print_update_hint()
|
|
113
175
|
if prompt_only:
|
|
114
176
|
_print_contributor_prompt()
|
|
115
177
|
return
|
|
@@ -184,6 +246,7 @@ def register_traj(app: typer.Typer) -> None:
|
|
|
184
246
|
] = DEFAULT_PREVIEW_STEPS,
|
|
185
247
|
) -> None:
|
|
186
248
|
"""Inspect, redact, confirm, and upload trajectory JSONL."""
|
|
249
|
+
_maybe_print_update_hint()
|
|
187
250
|
try:
|
|
188
251
|
_run_upload(
|
|
189
252
|
_UploadOptions(
|
|
@@ -33,6 +33,16 @@ def isolate_local_dotenv(monkeypatch, tmp_path) -> None:
|
|
|
33
33
|
monkeypatch.setenv("BENCHFLOW_DOTENV_PATH", str(tmp_path / ".env"))
|
|
34
34
|
|
|
35
35
|
|
|
36
|
+
@pytest.fixture(autouse=True)
|
|
37
|
+
def skip_update_check(monkeypatch) -> None:
|
|
38
|
+
"""Keep the `bench traj` PyPI latest-version check out of unit tests.
|
|
39
|
+
|
|
40
|
+
Tests that exercise the hint delete this variable and monkeypatch the
|
|
41
|
+
fetch instead of touching the network.
|
|
42
|
+
"""
|
|
43
|
+
monkeypatch.setenv("BENCHFLOW_SKIP_UPDATE_CHECK", "1")
|
|
44
|
+
|
|
45
|
+
|
|
36
46
|
@pytest.fixture
|
|
37
47
|
def hello_world_task_dir() -> Path:
|
|
38
48
|
path = REF_TASKS / "hello-world"
|
|
@@ -634,6 +634,86 @@ def test_handshake_timeout_tells_people_to_retry(tmp_path: Path) -> None:
|
|
|
634
634
|
)
|
|
635
635
|
|
|
636
636
|
|
|
637
|
+
def _enable_update_check(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
638
|
+
"""Undo the suite-wide BENCHFLOW_SKIP_UPDATE_CHECK conftest fixture."""
|
|
639
|
+
monkeypatch.delenv("BENCHFLOW_SKIP_UPDATE_CHECK", raising=False)
|
|
640
|
+
|
|
641
|
+
|
|
642
|
+
def test_outdated_install_prints_the_upgrade_hint(
|
|
643
|
+
tmp_path: Path, monkeypatch: pytest.MonkeyPatch
|
|
644
|
+
) -> None:
|
|
645
|
+
"""Guards PR #1014 (the version-check follow-up to PR #1013): an install
|
|
646
|
+
older than the PyPI latest gets one hint line on setup and upload."""
|
|
647
|
+
_enable_update_check(monkeypatch)
|
|
648
|
+
monkeypatch.setattr("benchflow.cli.traj._installed_version", lambda: "0.7.0")
|
|
649
|
+
monkeypatch.setattr("benchflow.cli.traj._fetch_latest_version", lambda: "0.7.2")
|
|
650
|
+
|
|
651
|
+
hint = (
|
|
652
|
+
"A newer BenchFlow (0.7.2) is available — run: "
|
|
653
|
+
"uv tool install --python 3.12 --upgrade --force benchflow"
|
|
654
|
+
)
|
|
655
|
+
setup_result = runner.invoke(app, ["traj", "setup", "--prompt"])
|
|
656
|
+
assert setup_result.exit_code == 0, setup_result.output
|
|
657
|
+
assert hint in click.unstyle(setup_result.output)
|
|
658
|
+
|
|
659
|
+
upload_result = runner.invoke(app, _upload_command(_trial(tmp_path), "--dry-run"))
|
|
660
|
+
assert upload_result.exit_code == 0, upload_result.output
|
|
661
|
+
assert hint in click.unstyle(upload_result.output)
|
|
662
|
+
|
|
663
|
+
|
|
664
|
+
def test_update_check_network_failure_is_silent(
|
|
665
|
+
monkeypatch: pytest.MonkeyPatch,
|
|
666
|
+
) -> None:
|
|
667
|
+
"""Guards PR #1014 (the version-check follow-up to PR #1013): a PyPI
|
|
668
|
+
failure prints nothing and leaves the exit code untouched."""
|
|
669
|
+
from benchflow.cli.traj import CONTRIBUTOR_PROMPT
|
|
670
|
+
|
|
671
|
+
_enable_update_check(monkeypatch)
|
|
672
|
+
|
|
673
|
+
def fail_fetch() -> str | None:
|
|
674
|
+
raise httpx.ConnectError("no network")
|
|
675
|
+
|
|
676
|
+
monkeypatch.setattr("benchflow.cli.traj._fetch_latest_version", fail_fetch)
|
|
677
|
+
result = runner.invoke(app, ["traj", "setup", "--prompt"])
|
|
678
|
+
|
|
679
|
+
assert result.exit_code == 0, result.output
|
|
680
|
+
assert "newer BenchFlow" not in result.output
|
|
681
|
+
assert CONTRIBUTOR_PROMPT in click.unstyle(result.output)
|
|
682
|
+
|
|
683
|
+
|
|
684
|
+
@pytest.mark.parametrize(
|
|
685
|
+
"installed", ["0.7.2", "0.8.0", "0.7.2.dev0", "0.7.3.dev1", "0.7.2rc1"]
|
|
686
|
+
)
|
|
687
|
+
def test_current_or_newer_dev_install_prints_no_hint(
|
|
688
|
+
installed: str, monkeypatch: pytest.MonkeyPatch
|
|
689
|
+
) -> None:
|
|
690
|
+
"""Guards PR #1014 (the version-check follow-up to PR #1013): up-to-date
|
|
691
|
+
installs and dev/prereleases of a newer-or-equal base are not outdated."""
|
|
692
|
+
_enable_update_check(monkeypatch)
|
|
693
|
+
monkeypatch.setattr("benchflow.cli.traj._installed_version", lambda: installed)
|
|
694
|
+
monkeypatch.setattr("benchflow.cli.traj._fetch_latest_version", lambda: "0.7.2")
|
|
695
|
+
result = runner.invoke(app, ["traj", "setup", "--prompt"])
|
|
696
|
+
|
|
697
|
+
assert result.exit_code == 0, result.output
|
|
698
|
+
assert "newer BenchFlow" not in result.output
|
|
699
|
+
|
|
700
|
+
|
|
701
|
+
def test_skip_update_check_env_var_never_fetches(
|
|
702
|
+
monkeypatch: pytest.MonkeyPatch,
|
|
703
|
+
) -> None:
|
|
704
|
+
"""Guards PR #1014 (the version-check follow-up to PR #1013): the conftest
|
|
705
|
+
hermeticity guard BENCHFLOW_SKIP_UPDATE_CHECK short-circuits the fetch."""
|
|
706
|
+
|
|
707
|
+
def fail_fetch() -> str | None:
|
|
708
|
+
raise AssertionError("update check fetched despite skip env var")
|
|
709
|
+
|
|
710
|
+
monkeypatch.setattr("benchflow.cli.traj._fetch_latest_version", fail_fetch)
|
|
711
|
+
result = runner.invoke(app, ["traj", "setup", "--prompt"])
|
|
712
|
+
|
|
713
|
+
assert result.exit_code == 0, result.output
|
|
714
|
+
assert "newer BenchFlow" not in result.output
|
|
715
|
+
|
|
716
|
+
|
|
637
717
|
def test_setup_prompt_prints_the_copy_paste_line() -> None:
|
|
638
718
|
"""The human path is one line to paste into an agent."""
|
|
639
719
|
from benchflow.cli.traj import CONTRIBUTOR_PROMPT, SKILL_RAW_URL
|
|
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-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/build_context_stage.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/dataset_registry.py
RENAMED
|
File without changes
|
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/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
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/_utils/source_provenance.py
RENAMED
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/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-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/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
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/_toolathlon_container.py
RENAMED
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/_toolathlon_fake_mail.py
RENAMED
|
File without changes
|
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/adapters/_toolathlon_services.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/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-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/deepagents_acp_shim.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/harvey_lab_acp_shim.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/openclaw_acp_shim.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/agents/remote_manifests.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
|
|
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
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/continue_run/orchestrator.py
RENAMED
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/continue_run/replay_proxy.py
RENAMED
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/continue_run/run_folder.py
RENAMED
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/continue_run/sandbox_proxy.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/demo_task/environment/Dockerfile
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-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/environment/manifest_env.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-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/experimental/mcp/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.1.dev1969 → benchflow-0.7.1.dev1972}/src/benchflow/integrations/trl/__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
|