.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/config.yml
.github/ISSUE_TEMPLATE/documentation.yml
.github/ISSUE_TEMPLATE/feature_request.yml
.github/workflows/pages.yml
.github/workflows/publish.yml
.github/workflows/tests.yml
examples/TOOLSCORE.md
examples/archive_review.py
examples/assessment_review.py
examples/deerflow_review.py
examples/gpt_researcher_review.py
examples/index.html
examples/mcp_memory_agent_review.py
examples/mcp_memory_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/toolscore_review.py
examples/assets/agent-eval-flow-banner.png
examples/assets/agent-eval-flow-banner.svg
examples/data/deerflow/DECISIONS.md
examples/data/deerflow/FRAMES-LICENSE
examples/data/deerflow/MANUAL_REVIEW.json
examples/data/deerflow/PROTOCOL.md
examples/data/deerflow/README.md
examples/data/deerflow/RUNLOG.md
examples/data/deerflow/SIMPLE-EVALS-LICENSE
examples/data/deerflow/capture.json
examples/data/gpt-researcher/GPT-RESEARCHER-LICENSE
examples/data/gpt-researcher/README.md
examples/data/gpt-researcher/SIMPLE-EVALS-LICENSE
examples/data/gpt-researcher/capture.json
examples/data/mcp-memory/DECISIONS.md
examples/data/mcp-memory/PROTOCOL.md
examples/data/mcp-memory/README.md
examples/data/mcp-memory/RUNLOG.md
examples/data/mcp-memory/agent_capture.json
examples/data/mcp-memory/capture.json
examples/deerflow_study/__init__.py
examples/deerflow_study/capacity_probe.py
examples/deerflow_study/capture.py
examples/deerflow_study/curate.py
examples/deerflow_study/detector.py
examples/deerflow_study/grade.py
examples/deerflow_study/questions.py
examples/deerflow_study/report.py
examples/deerflow_study/run_pilot.py
examples/deerflow_study/stub_tools.py
examples/deerflow_study/toolscore_view.py
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/mcp_memory_study/agent_memory_eval.py
examples/mcp_memory_study/agent_scenarios.json
examples/mcp_memory_study/memory_matrix.py
examples/reports/01-opensre-walkthrough.html
examples/reports/01-opensre-walkthrough.png
examples/reports/01-opensre.html
examples/reports/01-opensre.png
examples/reports/02-openkritt-walkthrough.html
examples/reports/02-openkritt-walkthrough.png
examples/reports/02-openkritt.html
examples/reports/02-openkritt.png
examples/reports/03-gpt-researcher.html
examples/reports/README.md
examples/reports/security-triage-repair/README.md
examples/reports/security-triage-repair/results-summary.json
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/build_report_site.py
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/tool_trace.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/evaluation/toolscore.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/tool_trace.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/toolscore.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/reporting/templates/tools_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/README.md
tests/__init__.py
tests/conftest.py
tests/fixtures_manifest.json
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/__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/test_optional_libraries.py
tests/unit/test_claude_stream_records.py
tests/unit/test_cli_adapters.py
tests/unit/test_deerflow_study.py
tests/unit/test_distribution_integrity.py
tests/unit/test_grading_clock_step.py
tests/unit/test_mcp_memory_example.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_publish_gate.py
tests/unit/test_report_site.py
tests/unit/test_runtime_evidence.py
tests/unit/test_runtime_evidence_report.py
tests/unit/test_showcase_recipe.py
tests/unit/test_toolscore_integration.py
tests/unit/test_vertex_showcase.py
tests/unit/fixtures/openkritt_scan2_lineage.json