benchflow 0.7.9.dev2399__tar.gz → 0.7.9.dev2402__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-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/PKG-INFO +1 -1
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/pyproject.toml +1 -1
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/agents/test_manifest_parity.py +52 -15
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/.gitignore +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/CHANGELOG.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/LICENSE +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/README.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_dotenv.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_paths.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_run.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_types.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/benchmark_repos.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/build_context_stage.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/config_override.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/config_redaction.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/content_address.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/dataset_registry.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/env_registry.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/evaluation_results.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/hf_datasets.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/json_safe.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/learner_memory.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/live_activity.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/result_metadata.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/result_paths.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/reward_events.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/scoring.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/source_provenance.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/task_authoring/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/task_authoring/_evidence_paths.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/task_authoring/acceptance_evidence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/task_authoring/scaffolding.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/task_authoring/structural_checks.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/text.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/yaml_loader.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/acp/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/acp/client.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/acp/container_transport.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/acp/runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/acp/selection.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/acp/session.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/acp/timeout_cleanup.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/acp/transport.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/acp/types.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/acp/watchdog.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/_toolathlon.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/_toolathlon_container.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/_toolathlon_fake_mail.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/_toolathlon_poste_users.tsv +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/_toolathlon_services.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/harbor.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/inbound.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/inspect_ai.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/ors.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/resources/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/resources/mcp_atlas_bridge.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/resources/mcp_atlas_judge.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/source.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agent_router.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agent_router_guide.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agent_router_parity.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agent_router_scaffold.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/antigravity_acp_shim.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/antigravity_config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/codex_config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/credentials.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/deepagents_acp_shim.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/env.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/errors.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/harvey_lab_acp_shim.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/install.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/manifest.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/openclaw_acp_shim.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/pi_acp_launcher.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/protocol.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/providers.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/registry.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/remote_manifests.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/branch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/_failure_evidence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/_hosted_env.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/_live_progress.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/_options.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/_shared.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/_traj_tui.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/_traj_upload_ui.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/adopt.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/agent.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/continue_cmd.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/environment.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/eval_artifacts.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/eval_lift.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/hub.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/main.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/monitor.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/rescore.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/review.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/reviewer_options.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/sandbox.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/skills.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/tasks.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/trace_import.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/train.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/cli/traj.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/continue_run/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/continue_run/batch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/continue_run/orchestrator.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/continue_run/replay_proxy.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/continue_run/run_folder.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/continue_run/sandbox_proxy.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/contracts/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/contracts/planes.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/contracts/user.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/demo_task/environment/Dockerfile +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/demo_task/instruction.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/demo_task/task.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/demo_task/task.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/demo_task/tests/test.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/diagnostics.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/environment/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/environment/_registry/env0@outage.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/environment/_registry/env0@prod.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/environment/manifest.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/environment/manifest_env.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/environment/protocol.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/environment/readiness.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/eval_artifacts.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/eval_lift.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/eval_plan.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/eval_sharding.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/eval_worker.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/evaluation.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/experimental/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/experimental/mcp/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/experimental/mcp/hooks.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/experimental/mcp/reviewer_server.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/hosted_env.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/hub/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/hub/harbor_registry.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/integrations/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/integrations/trl/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/integrations/trl/spec.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/learner_skills.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/learner_store.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/loop_strategies.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/loop_sweep.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/metrics.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/models.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/monitor.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/litellm_bedrock_patch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/litellm_bedrock_preflight.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/litellm_config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/litellm_gemini_passthrough_patch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/litellm_logging.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/litellm_runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/publish/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/publish/_progress.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/publish/azure_blob.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/publish/broker.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/publish/huggingface.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/publish/redact.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/publish/traj_capture.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/publish/traj_report.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/py.typed +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/automatic.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/default-rubric.json +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/evidence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/evidence_runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/options.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/outcome.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/persistence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/preflight.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/prompts.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/resume.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/runner.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/scoring.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/wrapper.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/README.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/builtins.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/events.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/file_readers.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/llm.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/memory_scorer.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/node.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/protocol.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/rubric.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/rubric_config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rewards/validation.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout/_config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout/_deadline.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout/_results.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout/_review.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout/_setup.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout/_skills.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout/_usage.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout/_user_loop.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout/session_factory_runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout/task_runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout_branch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/rollout_planes.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/_base.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/_cache_reclaim.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/_compose.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/_compose_files/docker-compose-base.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/_compose_files/docker-compose-build.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/_compose_files/docker-compose-net-admin.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/_compose_files/docker-compose-no-network.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/_compose_files/docker-compose-prebuilt.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/_egress_denylist_proxy.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/_sdk_ops.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/agentcore.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/agentcore_builder.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/agentcore_image.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/agentcore_provisioning.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/agentcore_reaper.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/agentcore_sealed.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/apple_container.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/daytona.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/daytona_dind.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/daytona_pty.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/daytona_reaper.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/daytona_strategies.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/docker.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/egress_denylist.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/lockdown.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/metadata.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/modal_impl.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/process/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/process/_base.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/process/agentcore.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/process/apple.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/process/daytona.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/process/docker.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/protocol.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/providers.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/services.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/setup.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/snapshot.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sandbox/user.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/scenes.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/sdk.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/self_gen.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/skill_eval/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/skill_eval/_core.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/skill_eval/gepa_export.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/skill_eval/schema.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/skill_policy.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/skills.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/_document_evidence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/_document_normalize.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/_document_parse.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/_document_profiles.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/acceptance_live.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/acceptance_live_model.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/acceptance_live_report.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/acceptance_live_validation.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/discovery.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/document.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/env.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/export.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/imports.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/output_format.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/package.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/paths.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/prompts.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/runtime_capabilities.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/runtime_view.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/task.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/verifier.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/verifier_core.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/verifier_document.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/verifier_errors.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/verifier_judge_inputs.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/verifier_ors_episode.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/verifier_reward_kit.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/verifier_scan.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/task/verifier_script_strategy.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/templates/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/templates/judge.py.tmpl +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/templates/test.sh.tmpl +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/traces/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/traces/huggingface.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/traces/local.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/traces/models.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/traces/parsers.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/traces/task_gen.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/training/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/training/backends/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/training/backends/prime_rl.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/training/run_manifest.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/_capture.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/_export_common.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/_llm_capture.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/_snapshot.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/call_purpose.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/export.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/export_adp.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/export_atif.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/export_prime_sft.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/export_trl_sft.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/metrics.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/results.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/sessions.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/tree.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/trl_sft_tokenization.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/types.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/__main__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/boot.js +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/catalog.js +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/detail.js +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/fonts/OFL-google-sans-code.txt +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/fonts/google-sans-code-400-latin.woff2 +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/fonts/google-sans-code-600-latin.woff2 +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/template.html +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/theme.css +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/theme.js +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/vendor/LICENSE.highlight.js +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/vendor/highlight.min.js +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/viewer.css +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/assets/viewer.js +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/catalog.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/legacy.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/models.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/payload.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/render.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/server.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/trajectories/viewer/sources.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/usage_tracking.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/acceptance_live_harness.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/agents/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/agents/test_codex_config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/agents/test_manifest_dirscan.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/agents/test_manifest_loader.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/agents/test_manifest_wiring.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/agents/test_namespace_shorthand.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/agents/test_plugin_entry_points.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/agents/test_protocol.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/agents/test_remote_manifest_autoload.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/README.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/acp_smoke/environment/Dockerfile +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/acp_smoke/environment/docker-compose.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/acp_smoke/environment/skills/conformance-writer/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/acp_smoke/instruction.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/acp_smoke/solution/solve.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/acp_smoke/task.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/acp_smoke/task.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/acp_smoke/tests/test.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/conformance-results.json +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/proof_multi_agent.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/proof_snapshot.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/run_conformance.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conformance/self_gen_smoke_skills/skill-creator/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/conftest.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/continue_run/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/continue_run/_helpers.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/continue_run/test_batch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/continue_run/test_orchestrator.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/continue_run/test_replay_proxy.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/continue_run/test_run_folder.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/environment/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/environment/test_chibench_manifest.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/environment/test_clawsbench_manifest.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/environment/test_manifest.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/environment/test_manifest_env.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/environment/test_protocol.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/environment/test_readiness.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/hello-world-task/environment/Dockerfile +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/hello-world-task/instruction.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/hello-world-task/solution/solve.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/hello-world-task/task.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/hello-world-task/task.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/hello-world-task/tests/test.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/test_antigravity.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/test_claude.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/test_codex.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/test_codex_custom_provider.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/test_gemini.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/test_openclaw.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/traces/minimal-claude.jsonl +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/examples/traces/minimal-opentraces.jsonl +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/digest/README.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/digest/alpha-task/environment/Dockerfile +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/digest/alpha-task/instruction.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/digest/alpha-task/task.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/digest/alpha-task/tests/test.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/digest/beta-task/data/empty.bin +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/digest/beta-task/data/unicode.txt +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/digest/beta-task/instruction.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/digest/beta-task/task.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/digest/not-a-task/notes.txt +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/mock_acp_agent.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/mock_acp_agent_interleaved.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/mock_acp_agent_multi_turn.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/mock_openai_responses_server.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/Dockerfile +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/data/michigan_stations.txt +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/flood-detection/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/nws-flood-thresholds/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/flood-risk-analysis/environment/skills/usgs-data-download/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/flood-risk-analysis/instruction.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/flood-risk-analysis/solution/solve.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/flood-risk-analysis/task.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/flood-risk-analysis/tests/test_outputs.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/Dockerfile +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/climate.csv +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/hydrology.csv +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/land_cover.csv +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/data/water_temperature.csv +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/contribution-analysis/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/meteorology-driver-classification/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/pca-decomposition/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/environment/skills/trend-analysis/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/instruction.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/solution/solve.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/task.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/lake-warming-attribution/tests/test_outputs.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/manifest.json +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/Dockerfile +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/r2r_simulator.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/finite-horizon-lqr/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/integral-action-design/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/mpc-horizon-tuning/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/skills/state-space-linearization/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/environment/system_config.json +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/instruction.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/solution/solve.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/task.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/r2r-mpc-control/tests/test_outputs.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/Dockerfile +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/generate_training_pcaps.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/local.rules +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/pcap-triage-tshark/scripts/summarize_http_requests.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-offline-evejson/scripts/run_suricata_offline.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/skills/suricata-rules-basics/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/environment/suricata.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/instruction.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/solution/solve.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/task.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/suricata-custom-exfil/tests/test_outputs.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/Dockerfile +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syz-extract-constants/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzkaller-build-loop/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/environment/skills/syzlang-ioctl-basics/SKILL.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/instruction.md +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/solution/solve.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/task.toml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/fixtures/skillsbench_slice/syzkaller-ppdev-syzlang/tests/test_outputs.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/_consistency.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/agent_judge.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/check_adapter_evidence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/check_hosted_env_evidence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/check_results.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/check_skillsbench_harbor_parity.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/check_trace_to_task_evidence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/configs/antigravity.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/configs/claude-agent-acp.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/configs/codex-acp.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/configs/gemini.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/configs/harvey-lab-harness.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/configs/mimo.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/configs/openclaw.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/configs/opencode.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/configs/openhands.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/configs/pi-acp.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/deepagents_harness.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/rubric_checks.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/run.sh +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/run_suite.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/scenarios.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/integration/suites/release.yaml +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_acceptance_evidence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_acceptance_live.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_acceptance_live_execution.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_acp.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_acp_buffered_timeout.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_acp_capability_advertising.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_acp_mcp_servers.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_acp_model_config_dispatch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_acp_pinned_protocol_guard.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_acp_setup_failure_propagation.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_acp_timeout_evidence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_adapter_scripts.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_adapters.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_antigravity.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_cli.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_egress_firewall.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_env_resolution.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_gemini_defaults.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_idle_timeout_cli.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_model_decouple.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_registry.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_router.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_router_cli_e2e.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_router_scaffold.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_setup.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agent_spec.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agentcore_builder.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agentcore_parallel.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agentcore_reaper.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agentcore_sandbox.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_agentcore_transport.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_api_error_capture.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_apple_container_sandbox.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_automatic_review_scoring.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_bare_model_provider.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_base_install_imports.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_bedrock_thinking.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_benchflow_experiment_review_validator.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_benchmark_repos_resolve_repo_path.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_branch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_build_context_stage.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_build_review_pack.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_capture_trajectory.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_check_skillsbench_harbor_parity.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_clawsbench_slice.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_cli_adopt_aliases.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_cli_arg_validation.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_cli_daytona.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_cli_docs_drift.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_cli_edge_case_hardening.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_cli_hub_env.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_cli_live_progress.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_cli_misc.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_codex_bare_model_id.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_codex_review.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_codex_self_write_auth.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_config_override.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_config_redaction.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_connect_as_env.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_console_error_truncation.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_console_progress.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_continuallearningbench_adapter.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_dataset_registry.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_daytona_command_polling.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_daytona_dind_compose_up.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_daytona_download.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_daytona_litellm_runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_daytona_poll_deadline.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_daytona_reap.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_deepagents_agent.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_diagnostics.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_docker_prune_scoping.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_docker_uploads.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_docs_examples.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_egress_connect_authority.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_egress_denylist.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_egress_denylist_integration.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_egress_dynamic_certs.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_egress_model_gateway.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_eng50_capabilities.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_env_registry.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_env_setup.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_environment_manifest_controls.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_eval_artifact_cli.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_eval_filters_applied.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_eval_lift.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_eval_sharding.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_eval_single_task_summary.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_eval_source_provenance.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_eval_worker_retry.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_eval_zero_task_guard.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_evaluation_environment_manifest.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_exclude_tasks.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_filter_credentialed_cells.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_harvey_lab_shim.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_hilbench_adapter.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_hosted_env.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_hosted_env_rollout_contract.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_hosted_search_policy.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_hub_harbor_registry.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_inbound_adapter_manifest.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_inbound_adapters.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_integration_agent_judge.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_integration_check_results.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_integration_consistency.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_integration_matrix.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_integration_provider_selection.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_integration_run_suite.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_integration_suite.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_internet_policy.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_job.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_job_sequential_shared.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_job_sequential_shared_resume.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_judge_robustness.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_judge_symlink_ingestion.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_learner_skills.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_learner_skills_traversal.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_learner_store.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_learner_store_persistence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_litellm_config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_litellm_gemini_passthrough_patch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_litellm_hardening.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_litellm_logging.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_litellm_model_via_env_generic.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_litellm_reasoning_passthrough.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_litellm_runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_litellm_smoke.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_live_llm_trajectory.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_llm_judge.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_llm_judge_event_tags.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_llm_judge_verifier.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_loop_strategies.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_loop_summary.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_loop_sweep.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_memory_scorer.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_metrics.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_mle_bench_adapter.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_mock_openai_responses_server.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_monitor_scaffold.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_native_acp_usage.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_network_denylist_config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_no_cross_provider_fallback.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_notification_order_real.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_opencode_family_proxy_tracking.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_oracle.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_oracle_chokepoint.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_paths_safe.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_paths_symlink_helpers.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_pi_acp_launcher.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_pi_acp_proxy_routing.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_process.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_project_skills_layout.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_provider_auth_detection.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_providers.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_publish_azure_blob.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_publish_huggingface.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_redacted_snapshot.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_reexport.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_registry_invariants.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_release_hardening_r5.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_release_version.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_release_workflow_wiring.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_resolve_env_helpers.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_review_automatic.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_review_boundaries.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_review_evidence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_review_evidence_runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_review_lifecycle.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_review_resume.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_review_rubric.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_review_runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_review_runtime_automatic.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_review_snapshot.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_reviewer_options.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_reward_lenient.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_reward_node.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_reward_range.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_reward_unified_contract.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rewards.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rewards_jsonl.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_architecture.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_branch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_config_path_coercion.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_environment.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_hard_deadline.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_import_no_side_effects.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_on_ask_user_wiring.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_planes_contract.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_probe_sandbox_health.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_session_factory_dispatch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_setup_commands.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rollout_upload.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rubric_checks.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_rubric_config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_runtime_capabilities.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_runtime_config_wired.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_runtime_live_sandbox.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_exec_secret_handling.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_hardening.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_isolation_copy_traversal.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_live_process.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_multi_service.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_prebuilt_validation.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_protocol.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_provider_registry_drift.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_setup.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_snapshot_contract.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_upload_symlink.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sandbox_verifier_workspace.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_scene.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_scene_outbox_trial.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_scene_parallel_group.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_scene_result_aggregation.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_scoring.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sdk_internals.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sdk_lockdown.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sdk_run_alias.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_sealed_channel_container.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_self_gen_cli.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_self_gen_export_error_channel.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_self_gen_export_failures.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_self_gen_orchestration.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_session_factory_runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_session_request_permission_dispatch.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_skill_eval.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_skill_eval_dryrun.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_skill_eval_integration.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_skill_eval_sweep.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_skill_eval_traversal.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_skill_invocation_artifacts.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_skill_policy.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_skills.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_skills_dir_agent_home_link.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_skillsbench_conversion_conformance.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_skillsbench_harbor_run_suite.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_smoke.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_smoke_wiring.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_source_adapters.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_subscription_auth.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_task_check_eval_consistency.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_task_config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_task_digest.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_task_document.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_task_download.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_task_export.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_task_output_format.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_task_package.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_task_runtime_primitive.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_tasks.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_token_usage_normalization.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_tool_call_raw_io.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_trace_import_cli.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_trace_task_gen_traversal.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_trace_to_task_evidence.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_traces_huggingface.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_traces_parsers.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_traces_task_gen.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_train_cli.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_train_mode_artifact_emission.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_train_trl_cli.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_traj_report.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_traj_staging_phases.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_traj_tui.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_traj_upload_cli.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_traj_upload_skill.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_traj_workspace.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_trajectory_integration.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_trajectory_streaming.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_trajectory_upload_layout.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_trajectory_upload_service.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_trial_agent_timeout_verify.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_trial_install_agent_timeout.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_trial_litellm_runtime.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_trl_integration.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_usage_litellm.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_usage_required.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_usage_tracking.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_user.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_v06_guard_ports.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_verifier_document.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_verifier_multi_container.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_verifier_output.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_verifier_output_freshness.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_verifier_strategies.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_verifier_wedge_retry.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_verify.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_viewer_confirm.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_workflow_action_pinning.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/test_yaml_config.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/__init__.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_export.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_export_adp.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_export_atif.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_export_common.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_export_nan_handling.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_export_prime_sft.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_redaction.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_step_granularity.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_tree.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_viewer_acp_renderer.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_viewer_browser.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_viewer_rubric.py +0 -0
- {benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/tests/trajectories/test_viewer_theme.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: benchflow
|
|
3
|
-
Version: 0.7.9.
|
|
3
|
+
Version: 0.7.9.dev2402
|
|
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
|
|
@@ -62,10 +62,23 @@ from benchflow.agents.manifest import (
|
|
|
62
62
|
)
|
|
63
63
|
from benchflow.agents.registry import AgentConfig
|
|
64
64
|
|
|
65
|
-
# The documented
|
|
66
|
-
#
|
|
67
|
-
# "module:callable" entrypoint), not data expressible as an acp-only manifest.
|
|
68
|
-
|
|
65
|
+
# The documented exceptions: core agents that ship without a manifest.
|
|
66
|
+
# * omnigent-pi is a session-factory agent wired through the #825 omnigent seam
|
|
67
|
+
# (a "module:callable" entrypoint), not data expressible as an acp-only manifest.
|
|
68
|
+
# * antigravity depends on _SHIM_ONLY fields (the web-tool and hosted-search
|
|
69
|
+
# policy, the MCP config path, the ACP effort option) that a data-only manifest
|
|
70
|
+
# cannot carry. Released 0.7.x versions have no core entry for it and would
|
|
71
|
+
# auto-load a manifest from benchflow-ai/agents@main without that policy, so a
|
|
72
|
+
# "no web" run would keep agy's server-side web search.
|
|
73
|
+
_CORE_ONLY_EXCEPTIONS = frozenset({"omnigent-pi", "antigravity"})
|
|
74
|
+
|
|
75
|
+
# Core agents that must NOT get a manifest in benchflow-ai/agents, by name or by
|
|
76
|
+
# alias. A manifest mirroring core would pass the parity checks above, but
|
|
77
|
+
# released 0.7.x versions would auto-load it from agents@main without core's
|
|
78
|
+
# _SHIM_ONLY web-tool and MCP policy (see antigravity above). Lift an entry only
|
|
79
|
+
# once that policy can travel with the manifest.
|
|
80
|
+
_MANIFEST_FORBIDDEN = frozenset({"antigravity"})
|
|
81
|
+
_MANIFEST_FORBIDDEN_ALIASES = frozenset({"antigravity", "agy"})
|
|
69
82
|
|
|
70
83
|
# Import roots so the child interpreter finds benchflow whether it is installed
|
|
71
84
|
# (CI) or only on PYTHONPATH from a worktree (dev VM) — mirrors the approach in
|
|
@@ -168,8 +181,8 @@ def test_manifest_byte_identical_to_core(agent_name: str | None) -> None:
|
|
|
168
181
|
|
|
169
182
|
|
|
170
183
|
@pytest.mark.skipif(not os.environ.get(MANIFEST_DIR_ENV), reason=_SKIP_REASON)
|
|
171
|
-
def
|
|
172
|
-
"""omnigent-pi
|
|
184
|
+
def test_only_documented_core_agents_lack_a_manifest() -> None:
|
|
185
|
+
"""omnigent-pi and antigravity are the ONLY core agents without a manifest.
|
|
173
186
|
|
|
174
187
|
Computed dynamically (core names minus manifest names) rather than hardcoded,
|
|
175
188
|
so adding a new core agent without shipping its manifest fails this gate
|
|
@@ -178,17 +191,41 @@ def test_omnigent_pi_is_sole_core_unmanifested_agent() -> None:
|
|
|
178
191
|
core = _pure_core_agents()
|
|
179
192
|
loaded = _live_manifests()
|
|
180
193
|
unmanifested = set(core) - set(loaded)
|
|
181
|
-
# SUBSET, not equality:
|
|
182
|
-
#
|
|
183
|
-
# session-factory package may be unregistered in a lean
|
|
184
|
-
# absence is fine; a *new* unmanifested core agent
|
|
185
|
-
|
|
194
|
+
# SUBSET, not equality: the exceptions are the only *tolerated* unmanifested
|
|
195
|
+
# core agents, but omnigent-pi's presence in AGENTS is import-side-effect
|
|
196
|
+
# dependent (the omnigent session-factory package may be unregistered in a lean
|
|
197
|
+
# env such as CI), so its absence is fine; a *new* unmanifested core agent
|
|
198
|
+
# still fails this gate.
|
|
199
|
+
assert unmanifested <= _CORE_ONLY_EXCEPTIONS, (
|
|
186
200
|
"unmanifested core agents mismatch: tolerated only "
|
|
187
|
-
f"{
|
|
188
|
-
|
|
189
|
-
"agent registered via the #825 omnigent seam, not a manifest.toml. Every "
|
|
201
|
+
f"{sorted(_CORE_ONLY_EXCEPTIONS)}, got {sorted(unmanifested)}. "
|
|
202
|
+
"These are the documented exceptions (see _CORE_ONLY_EXCEPTIONS). Every "
|
|
190
203
|
"other core agent must ship a manifest in benchflow-ai/agents; a new "
|
|
191
|
-
"unmanifested core agent must add one (or extend
|
|
204
|
+
"unmanifested core agent must add one (or extend the exceptions on purpose)."
|
|
205
|
+
)
|
|
206
|
+
|
|
207
|
+
|
|
208
|
+
@pytest.mark.skipif(not os.environ.get(MANIFEST_DIR_ENV), reason=_SKIP_REASON)
|
|
209
|
+
def test_core_only_agents_have_no_manifest() -> None:
|
|
210
|
+
"""No manifest may claim a forbidden core-only agent's name or alias.
|
|
211
|
+
|
|
212
|
+
The subset check above can only shrink when a manifest is added, so it would
|
|
213
|
+
stay green if someone mirrored antigravity into benchflow-ai/agents. This
|
|
214
|
+
check fails instead (see _MANIFEST_FORBIDDEN for why).
|
|
215
|
+
"""
|
|
216
|
+
loaded = _live_manifests()
|
|
217
|
+
by_name = sorted(set(loaded) & _MANIFEST_FORBIDDEN)
|
|
218
|
+
by_alias = sorted(
|
|
219
|
+
(name, alias)
|
|
220
|
+
for name, m in loaded.items()
|
|
221
|
+
for alias in m.aliases
|
|
222
|
+
if alias in _MANIFEST_FORBIDDEN_ALIASES
|
|
223
|
+
)
|
|
224
|
+
assert not by_name and not by_alias, (
|
|
225
|
+
f"forbidden manifests in benchflow-ai/agents: names {by_name}, "
|
|
226
|
+
f"aliases {by_alias}. These agents stay core-only until their _SHIM_ONLY "
|
|
227
|
+
"web-tool and MCP policy can travel with a manifest; released 0.7.x would "
|
|
228
|
+
"auto-load the manifest without it (see _MANIFEST_FORBIDDEN)."
|
|
192
229
|
)
|
|
193
230
|
|
|
194
231
|
|
|
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-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/build_context_stage.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/config_redaction.py
RENAMED
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/dataset_registry.py
RENAMED
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/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-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/_utils/source_provenance.py
RENAMED
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/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-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/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-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/_toolathlon_container.py
RENAMED
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/_toolathlon_fake_mail.py
RENAMED
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/adapters/_toolathlon_services.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/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
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/antigravity_acp_shim.py
RENAMED
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/antigravity_config.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/deepagents_acp_shim.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/harvey_lab_acp_shim.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/agents/openclaw_acp_shim.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/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
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/continue_run/orchestrator.py
RENAMED
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/continue_run/replay_proxy.py
RENAMED
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/continue_run/run_folder.py
RENAMED
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/continue_run/sandbox_proxy.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/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-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/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-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/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-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/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
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/litellm_bedrock_patch.py
RENAMED
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/litellm_config.py
RENAMED
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/litellm_logging.py
RENAMED
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/providers/litellm_runtime.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
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/default-rubric.json
RENAMED
|
File without changes
|
|
File without changes
|
{benchflow-0.7.9.dev2399 → benchflow-0.7.9.dev2402}/src/benchflow/review/evidence_runtime.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
|