AGENTS.md
CHANGELOG.md
CONTRIBUTING.md
LICENSE
MANIFEST.in
NOTICE
README.md
llms.txt
pixi.lock
pyproject.toml
.github/PULL_REQUEST_TEMPLATE.md
.github/workflows/benchmarks.yml
.github/workflows/publish-pypi.yml
.github/workflows/test.yml
benchmarks/__init__.py
benchmarks/audit_dataset.py
benchmarks/bench_overhead.py
benchmarks/evaluation.py
benchmarks/inference.py
benchmarks/measure.py
benchmarks/mock_evaluation.py
benchmarks/question_first.py
benchmarks/typed_judgments.py
benchmarks/data/interactive-v1.jsonl
benchmarks/data/typed-judgments-v1.jsonl
benchmarks/reports/2026-09-25-mock/artifact-manifest.json
benchmarks/reports/2026-09-25-mock/banking77-audit.json
benchmarks/reports/2026-09-25-mock/python-packages.json
benchmarks/reports/2026-09-25-mock/validation.xml
benchmarks/reports/2026-09-25-mock/complete/predictions.jsonl
benchmarks/reports/2026-09-25-mock/complete/report.json
benchmarks/reports/2026-09-25-mock/complete/report.md
benchmarks/reports/2026-09-25-mock/failed/predictions.jsonl
benchmarks/reports/2026-09-25-mock/failed/report.json
benchmarks/reports/2026-09-25-mock/failed/report.md
benchmarks/reports/2026-09-25-mock/interrupted/predictions.jsonl
benchmarks/reports/2026-09-25-mock/interrupted/report.json
benchmarks/reports/2026-09-25-mock/interrupted/report.md
docs/README.md
docs/api-evaluation.md
docs/api.md
docs/architecture.md
docs/benchmark-audit.md
docs/benchmark-protocol.md
docs/classification-benchmarks.md
docs/cli.md
docs/clm-development-results.md
docs/compatibility.md
docs/development.md
docs/diagnostics-design.md
docs/diagnostics.md
docs/engineering.md
docs/evaluation-python.md
docs/evaluation.md
docs/inference-evals.md
docs/input-recipe-investigation.md
docs/migrating.md
docs/model-contract.md
docs/orchestration-performance.md
docs/performance-history.md
docs/provider-adapters.md
docs/provider-validation.md
docs/rag-evaluation.md
docs/rag-experiments.md
docs/rag-integration-research.md
docs/release-validation.md
docs/release.md
docs/sdk-validation.md
docs/serving.md
docs/typed-judgments.md
docs/using-with-agents.md
docs/validation.md
examples/README.md
examples/__init__.py
examples/async_decisions.py
examples/benchmark_classifiers.py
examples/decision.json
examples/evaluate_late_interaction.py
examples/evaluate_rag.py
examples/evaluate_rag_async.py
examples/evaluate_rag_http.py
examples/evaluate_rag_pipeline.py
examples/evaluate_use_cases.py
examples/http_client.py
examples/local_decisions.py
examples/mock_integration.py
examples/process_jsonl.py
examples/rag_decisions.py
examples/rag_quickstart.py
examples/ranking.json
examples/rerank_documents.py
examples/retry_busy.py
examples/route_tools.py
examples/tickets.jsonl
examples/typed_judgments.py
examples/evaluations/README.md
examples/evaluations/feedback.json
examples/evaluations/rerank_documents.json
examples/evaluations/route_tools.json
examples/rag/config.json
examples/rag/dataset.json
examples/suites/support.json
kayak/__init__.py
kayak/__main__.py
kayak/_diagnostics.py
kayak/_heads.py
kayak/_http_diagnostics.py
kayak/_logging.py
kayak/bundle.py
kayak/client.py
kayak/decisions.py
kayak/errors.py
kayak/judgments.py
kayak/py.typed
kayak/ranking.py
kayak/server.py
kayak.egg-info/PKG-INFO
kayak.egg-info/SOURCES.txt
kayak.egg-info/dependency_links.txt
kayak.egg-info/entry_points.txt
kayak.egg-info/requires.txt
kayak.egg-info/top_level.txt
kayak/adapters/__init__.py
kayak/adapters/_results.py
kayak/eval/__init__.py
kayak/eval/__main__.py
kayak/eval/_banking77.py
kayak/eval/_benchmark.py
kayak/eval/_cases.py
kayak/eval/_cli.py
kayak/eval/_compare.py
kayak/eval/_comparison_cases.py
kayak/eval/_measurement.py
kayak/eval/_metrics.py
kayak/eval/_predictions.py
kayak/eval/_rag.py
kayak/eval/_rag_cli.py
kayak/eval/_rag_experiment.py
kayak/eval/_rag_reports.py
kayak/eval/_rag_runner.py
kayak/eval/_ranking.py
kayak/eval/_report.py
kayak/eval/_runner.py
kayak/eval/_schema.py
kayak/eval/_scoring.py
kayak/eval/_suite.py
kayak/models/__init__.py
kayak/models/clm-v0.1-8b.json
kayak/runtime/__init__.py
kayak/runtime/_loading.py
kayak/runtime/_model.py
kayak/runtime/_preparation.py
scripts/__init__.py
scripts/check_compatibility.py
scripts/check_provider_adapters.py
scripts/check_wheel.py
scripts/validate_model.py
scripts/compatibility/client.py
scripts/compatibility/server.py
stubs/pyperf/__init__.pyi
stubs/tokenizers/__init__.pyi
stubs/tokenizers/models.pyi
stubs/tokenizers/pre_tokenizers.pyi
tests/conftest.py
tests/test_adapters.py
tests/test_api_compatibility.py
tests/test_api_workflows.py
tests/test_async_client.py
tests/test_benchmark_source.py
tests/test_bundle.py
tests/test_candidate_reuse.py
tests/test_case_summary.py
tests/test_cli.py
tests/test_cli_service.py
tests/test_contract.py
tests/test_dataset_audit.py
tests/test_diagnostic_client.py
tests/test_diagnostic_logging.py
tests/test_diagnostics.py
tests/test_diagnostics_process.py
tests/test_distributions.py
tests/test_documentation.py
tests/test_eval_banking77.py
tests/test_eval_benchmark.py
tests/test_eval_cases.py
tests/test_eval_cli.py
tests/test_eval_integrity.py
tests/test_eval_measurement.py
tests/test_eval_metrics.py
tests/test_eval_python_workflow.py
tests/test_eval_rag.py
tests/test_eval_ranking.py
tests/test_eval_report.py
tests/test_eval_runner.py
tests/test_examples.py
tests/test_inference_evaluation.py
tests/test_judgments.py
tests/test_late_interaction_example.py
tests/test_model_info.py
tests/test_preparation.py
tests/test_properties.py
tests/test_question_first.py
tests/test_rag_cli.py
tests/test_rag_decisions_example.py
tests/test_rag_example.py
tests/test_rag_integration_examples.py
tests/test_rag_prefix.py
tests/test_rag_quickstart.py
tests/test_rag_reports.py
tests/test_rag_runner.py
tests/test_ranking.py
tests/test_released_heads.py
tests/test_retry_example.py
tests/test_reuse_failure.py
tests/test_runtime.py
tests/test_search_examples.py
tests/test_server.py
tests/test_structure.py
tests/test_typed_judgments.py
tests/test_use_case_evaluation.py
tests/test_validation_report.py
tests/fixtures/released_heads.json
tests/fixtures/api_v1/baseline.json
tests/fixtures/api_v1/request.json
tests/fixtures/api_v1/response.json