.gitattributes
CONTRIBUTING.md
MANIFEST.in
README.md
THIRD_PARTY_NOTICES.md
pyproject.toml
pytest.ini
requirements-test.txt
.github/pull_request_template.md
.github/ISSUE_TEMPLATE/bug_report.yml
.github/ISSUE_TEMPLATE/feature_request.yml
.github/workflows/publish.yml
.github/workflows/tests.yml
docs/.nojekyll
docs/AGENT_COMPATIBILITY_RED_TEAM.md
docs/AGENT_EVAL_FLOW_REVIEW.md
docs/AGENT_EVAL_FLOW_VISION.md
docs/ARCHITECTURE_REUSE_REVIEW.md
docs/DATA_CONTRACT.md
docs/IMPLEMENTATION.md
docs/INTEGRATION_DECISION.md
docs/LIBRARY_OBJECT_MODEL.md
docs/LLD_ARCHITECTURE.md
docs/LLD_LEVEL_2.md
docs/LLD_REUSE_RED_TEAM.md
docs/MODULE_COMMUNICATION.md
docs/PROJECT_PLAN.md
docs/RELEASE.md
docs/UNIFIED_ASSESSMENT_FLOW.md
docs/WHAT_AGENT_EVAL_FLOW_ADDS.md
docs/WORKFLOW_EVALUATION_MODEL.md
docs/index.html
docs/assets/agent-eval-flow-banner.png
docs/assets/agent-eval-flow-banner.svg
docs/contracts/agent_eval_flow.pyi
docs/diagrams/01-pipeline.png
docs/diagrams/01-pipeline.svg
docs/diagrams/02-opensre.png
docs/diagrams/02-opensre.svg
docs/diagrams/03-openkritt.png
docs/diagrams/03-openkritt.svg
docs/diagrams/04-objectives.png
docs/diagrams/04-objectives.svg
docs/diagrams/AGENT_EVAL_FLOW_VISION.drawio
docs/diagrams/Open-in-drawio.url
docs/diagrams/build_module_map.py
docs/diagrams/build_vision.py
docs/diagrams/module-communication.drawio
docs/diagrams/module-communication.png
docs/diagrams/module-communication.svg
docs/diagrams/vision.html
docs/examples/agent-evaluation/01-opensre-walkthrough.html
docs/examples/agent-evaluation/01-opensre-walkthrough.png
docs/examples/agent-evaluation/01-opensre.html
docs/examples/agent-evaluation/01-opensre.png
docs/examples/agent-evaluation/02-openkritt-walkthrough.html
docs/examples/agent-evaluation/02-openkritt-walkthrough.png
docs/examples/agent-evaluation/02-openkritt.html
docs/examples/agent-evaluation/02-openkritt.png
docs/examples/agent-evaluation/README.md
docs/implementation/local_openkritt.md
docs/implementation/local_opensre.md
docs/implementation/native_workflow_adapters.md
docs/implementation/pypi_publishing.md
docs/implementation/runtime_evidence.md
docs/implementation/unified_assessment.md
docs/lld/ASSESSMENT_CONTRACT.md
docs/lld/README.md
docs/lld/adapters/README.md
docs/lld/evaluation/README.md
docs/lld/execution/README.md
docs/lld/objects/README.md
docs/lld/pipeline/README.md
docs/lld/reporting/README.md
docs/lld/results/README.md
docs/lld/storage/README.md
docs/research/agentcompass_a2e_integration_evidence.md
docs/research/agentcompass_a2e_lld_review.md
docs/research/foundations_and_native_integration.md
docs/research/harbor_skillevaluator_integration_evidence.md
docs/research/inspect_architecture_review.md
docs/research/nemo_integration_evidence.md
docs/research/nemo_lld_review.md
docs/research/promptfoo_mlflow_architecture_review.md
docs/research/pydantic_evals_architecture_review.md
docs/research/skill_harbor_lld_review.md
docs/research/agent_redteam/browser_use_source_probe.json
docs/research/agent_redteam/probe_browser_use_source.py
docs/research/agent_redteam/probe_swe_agent_fixture.py
docs/research/agent_redteam/swe_agent_fixture_probe.json
examples/archive_review.py
examples/assessment_review.py
examples/openkritt_attempts_report.py
examples/openkritt_local_regrade.py
examples/openkritt_local_review.py
examples/opensre_attempts_report.py
examples/opensre_local_review.py
examples/profiles.local.example.json
examples/integrations/README.openkritt-local.md
examples/integrations/__init__.py
examples/integrations/local_cli.py
examples/integrations/openkritt_local.py
examples/integrations/openkritt_observer.py
examples/integrations/openkritt_setup.py
examples/integrations/opensre_local.Dockerfile
examples/integrations/opensre_local.py
examples/integrations/opensre_local_session.py
examples/integrations/opensre_local_worker.py
examples/integrations/vertex.py
examples/workflows/README.md
examples/workflows/openkritt_flaskr_local_v1.json
examples/workflows/openkritt_flaskr_local_v1.provenance.json
examples/workflows/openkritt_flaskr_local_v2.json
examples/workflows/openkritt_flaskr_local_v2.provenance.json
scripts/smoke_wheel.py
scripts/verify_acceptance_checkpoint.py
scripts/verify_distribution.py
src/agent_eval_flow/__init__.py
src/agent_eval_flow/py.typed
src/agent_eval_flow.egg-info/PKG-INFO
src/agent_eval_flow.egg-info/SOURCES.txt
src/agent_eval_flow.egg-info/dependency_links.txt
src/agent_eval_flow.egg-info/requires.txt
src/agent_eval_flow.egg-info/top_level.txt
src/agent_eval_flow/adapters/__init__.py
src/agent_eval_flow/adapters/claude_code.py
src/agent_eval_flow/adapters/cli.py
src/agent_eval_flow/adapters/codex.py
src/agent_eval_flow/adapters/common.py
src/agent_eval_flow/adapters/configuration_files_assessment.py
src/agent_eval_flow/adapters/harbor.py
src/agent_eval_flow/adapters/harness_eval_assessment.py
src/agent_eval_flow/adapters/nat.py
src/agent_eval_flow/adapters/openkritt.py
src/agent_eval_flow/adapters/opensre.py
src/agent_eval_flow/adapters/process.py
src/agent_eval_flow/adapters/skillevaluator.py
src/agent_eval_flow/adapters/snapshot_binding_assessment.py
src/agent_eval_flow/adapters/worker.py
src/agent_eval_flow/evaluation/__init__.py
src/agent_eval_flow/evaluation/aggregation.py
src/agent_eval_flow/evaluation/assessment_projection.py
src/agent_eval_flow/evaluation/compiler.py
src/agent_eval_flow/evaluation/configuration.py
src/agent_eval_flow/evaluation/engine.py
src/agent_eval_flow/evaluation/primitives.py
src/agent_eval_flow/evaluation/runtime_checks.py
src/agent_eval_flow/evaluation/scoring.py
src/agent_eval_flow/execution/__init__.py
src/agent_eval_flow/execution/capture.py
src/agent_eval_flow/execution/configuration_assessment.py
src/agent_eval_flow/execution/dispatch_assessment.py
src/agent_eval_flow/execution/importing.py
src/agent_eval_flow/execution/planning.py
src/agent_eval_flow/execution/preflight.py
src/agent_eval_flow/execution/runner.py
src/agent_eval_flow/execution/snapshot_assessment.py
src/agent_eval_flow/execution/snapshot_binding_assessment.py
src/agent_eval_flow/objects/__init__.py
src/agent_eval_flow/objects/assessment.py
src/agent_eval_flow/objects/assessment_validation.py
src/agent_eval_flow/objects/base.py
src/agent_eval_flow/objects/candidate.py
src/agent_eval_flow/objects/dataset.py
src/agent_eval_flow/objects/errors.py
src/agent_eval_flow/objects/identity.py
src/agent_eval_flow/objects/records.py
src/agent_eval_flow/objects/runset.py
src/agent_eval_flow/objects/runtime_evidence.py
src/agent_eval_flow/objects/validation.py
src/agent_eval_flow/objects/values.py
src/agent_eval_flow/pipeline/__init__.py
src/agent_eval_flow/pipeline/api.py
src/agent_eval_flow/pipeline/assessment.py
src/agent_eval_flow/pipeline/assessment_bindings.py
src/agent_eval_flow/pipeline/assessment_preflight.py
src/agent_eval_flow/pipeline/bindings.py
src/agent_eval_flow/pipeline/preflight.py
src/agent_eval_flow/reporting/__init__.py
src/agent_eval_flow/reporting/assessment_html.py
src/agent_eval_flow/reporting/html.py
src/agent_eval_flow/reporting/templates/assessment_report.html.j2
src/agent_eval_flow/reporting/templates/report.css
src/agent_eval_flow/reporting/templates/report.html.j2
src/agent_eval_flow/results/__init__.py
src/agent_eval_flow/results/assessment_comparison.py
src/agent_eval_flow/results/assessment_query.py
src/agent_eval_flow/results/assessment_selection.py
src/agent_eval_flow/results/comparison.py
src/agent_eval_flow/results/query.py
src/agent_eval_flow/results/selection.py
src/agent_eval_flow/storage/__init__.py
src/agent_eval_flow/storage/artifacts.py
src/agent_eval_flow/storage/assessment_codec.py
src/agent_eval_flow/storage/assessment_manifests.py
src/agent_eval_flow/storage/codec.py
src/agent_eval_flow/storage/manifests.py
tests/ACCEPTANCE_MANIFEST.json
tests/BASELINE.md
tests/README.md
tests/SHOWCASE_MANIFEST.json
tests/__init__.py
tests/conftest.py
tests/adapters/test_cli_boundary.py
tests/adapters/test_configuration_assessment.py
tests/adapters/test_native_workflows.py
tests/adapters/test_opensre_native_serialization.py
tests/adapters/test_process_boundary.py
tests/adapters/test_worker_boundary.py
tests/contracts/__init__.py
tests/contracts/test_assessment_consumers.py
tests/contracts/test_assessment_objects.py
tests/contracts/test_assessment_pipeline.py
tests/contracts/test_assessment_receipts.py
tests/contracts/test_capture.py
tests/contracts/test_configuration.py
tests/contracts/test_evaluation.py
tests/contracts/test_native_jobs.py
tests/contracts/test_pipeline_runtime.py
tests/contracts/test_reducers.py
tests/contracts/test_results_storage.py
tests/e2e/BASELINE.md
tests/e2e/PROFILES.md
tests/e2e/README.md
tests/e2e/SHOWCASE.md
tests/e2e/__init__.py
tests/e2e/conftest.py
tests/e2e/profiles.example.json
tests/e2e/support.py
tests/e2e/test_archived_trajectory.py
tests/e2e/test_data_contract.py
tests/e2e/test_live_toy.py
tests/e2e/test_live_workflow.py
tests/e2e/test_runtime_evidence.py
tests/e2e/test_toy_pipeline.py
tests/e2e/cloud/test_openkritt_gcp.py
tests/e2e/cloud/test_opensre_gcp.py
tests/e2e/fixtures/openkritt/README.md
tests/e2e/fixtures/openkritt/source_manifest.json
tests/e2e/fixtures/openkritt/workflow.json
tests/e2e/fixtures/openkritt/review_target/.gitignore
tests/e2e/fixtures/openkritt/review_target/LICENSE.txt
tests/e2e/fixtures/openkritt/review_target/README.rst
tests/e2e/fixtures/openkritt/review_target/pyproject.toml
tests/e2e/fixtures/openkritt/review_target/flaskr/__init__.py
tests/e2e/fixtures/openkritt/review_target/flaskr/auth.py
tests/e2e/fixtures/openkritt/review_target/flaskr/blog.py
tests/e2e/fixtures/openkritt/review_target/flaskr/db.py
tests/e2e/fixtures/openkritt/review_target/flaskr/schema.sql
tests/e2e/fixtures/openkritt/review_target/flaskr/static/style.css
tests/e2e/fixtures/openkritt/review_target/flaskr/templates/base.html
tests/e2e/fixtures/openkritt/review_target/flaskr/templates/auth/login.html
tests/e2e/fixtures/openkritt/review_target/flaskr/templates/auth/register.html
tests/e2e/fixtures/openkritt/review_target/flaskr/templates/blog/create.html
tests/e2e/fixtures/openkritt/review_target/flaskr/templates/blog/index.html
tests/e2e/fixtures/openkritt/review_target/flaskr/templates/blog/update.html
tests/e2e/fixtures/openkritt/review_target/tests/conftest.py
tests/e2e/fixtures/openkritt/review_target/tests/data.sql
tests/e2e/fixtures/openkritt/review_target/tests/test_auth.py
tests/e2e/fixtures/openkritt/review_target/tests/test_blog.py
tests/e2e/fixtures/openkritt/review_target/tests/test_db.py
tests/e2e/fixtures/openkritt/review_target/tests/test_factory.py
tests/e2e/fixtures/opensre/README.md
tests/e2e/fixtures/opensre/SOURCES.json
tests/e2e/fixtures/opensre/context.json
tests/e2e/fixtures/opensre/incident_store.py
tests/e2e/fixtures/opensre/incidents.json
tests/e2e/fixtures/opensre/upstream/HDFS_2k.log
tests/e2e/fixtures/opensre/upstream/LOGHUB_LICENSE
tests/e2e/fixtures/opensre/upstream/opensre/LICENSE
tests/e2e/fixtures/opensre/upstream/opensre/agent.py
tests/e2e/fixtures/opensre/upstream/opensre/events.py
tests/e2e/fixtures/opensre/upstream/opensre/harness.py
tests/e2e/fixtures/opensre/upstream/opensre/mixins.py
tests/e2e/fixtures/opensre/upstream/opensre/ports.py
tests/e2e/fixtures/opensre/upstream/opensre/react_loop.py
tests/e2e/fixtures/opensre/upstream/opensre/turn_results.py
tests/e2e/fixtures/sweagent_archive/INSPECT.md
tests/e2e/fixtures/sweagent_archive/LICENSE
tests/e2e/fixtures/sweagent_archive/PROVENANCE.json
tests/e2e/fixtures/sweagent_archive/README.md
tests/e2e/fixtures/sweagent_archive/native-format.md
tests/e2e/fixtures/sweagent_archive/pydicom__pydicom-1458.traj
tests/e2e/fixtures/toy/SKILL.md
tests/e2e/fixtures/toy/toy_agent.py
tests/e2e/fixtures/toy/toy_tool.py
tests/e2e/fixtures/workflow/MISSION.md
tests/e2e/fixtures/workflow/README.md
tests/e2e/fixtures/workflow/SOURCE_MANIFEST.json
tests/e2e/fixtures/workflow/cases.json
tests/e2e/fixtures/workflow/investigation_tool.py
tests/e2e/fixtures/workflow/report.schema.json
tests/e2e/fixtures/workflow/downloaded/CHANGES.rst
tests/e2e/fixtures/workflow/downloaded/LICENSE.txt
tests/e2e/fixtures/workflow/downloaded/README.md
tests/e2e/fixtures/workflow/downloaded/src/markupsafe/__init__.py
tests/e2e/fixtures/workflow/downloaded/src/markupsafe/_native.py
tests/e2e/fixtures/workflow/downloaded/tests/test_escape.py
tests/integrations/PROFILES.md
tests/integrations/test_optional_libraries.py
tests/unit/test_cli_adapters.py
tests/unit/test_openkritt_lineage.py
tests/unit/test_openkritt_local_connection.py
tests/unit/test_openkritt_local_review.py
tests/unit/test_openkritt_setup.py
tests/unit/test_openkritt_workflow_variant.py
tests/unit/test_opensre_local_review.py
tests/unit/test_opensre_local_runtime.py
tests/unit/test_opensre_local_session.py
tests/unit/test_optional_adapter_mappers.py
tests/unit/test_runtime_evidence.py
tests/unit/test_runtime_evidence_report.py
tests/unit/test_showcase_recipe.py
tests/unit/test_vertex_showcase.py
tests/unit/fixtures/openkritt_scan2_lineage.json