README.md
pyproject.toml
src/multiagent_eval/__init__.py
src/multiagent_eval/cli.py
src/multiagent_eval/config.py
src/multiagent_eval/cost_estimator.py
src/multiagent_eval/failure_modes.py
src/multiagent_eval/regression.py
src/multiagent_eval/sdk.py
src/multiagent_eval/security.py
src/multiagent_eval/stats.py
src/multiagent_eval.egg-info/PKG-INFO
src/multiagent_eval.egg-info/SOURCES.txt
src/multiagent_eval.egg-info/dependency_links.txt
src/multiagent_eval.egg-info/entry_points.txt
src/multiagent_eval.egg-info/requires.txt
src/multiagent_eval.egg-info/top_level.txt
src/multiagent_eval/bias_detection/__init__.py
src/multiagent_eval/bias_detection/cascade_bias.py
src/multiagent_eval/bias_detection/primacy_bias.py
src/multiagent_eval/bias_detection/tone_bias.py
src/multiagent_eval/bias_detection/verbosity_bias.py
src/multiagent_eval/core/__init__.py
src/multiagent_eval/core/llm_gateway.py
src/multiagent_eval/core/metrics.py
src/multiagent_eval/core/runner.py
src/multiagent_eval/core/state_machine.py
src/multiagent_eval/core/trace.py
src/multiagent_eval/golden_datasets/__init__.py
src/multiagent_eval/golden_datasets/annotator.py
src/multiagent_eval/golden_datasets/manager.py
src/multiagent_eval/golden_datasets/schema.py
src/multiagent_eval/integrations/__init__.py
src/multiagent_eval/integrations/autogen_adapter.py
src/multiagent_eval/integrations/base_adapter.py
src/multiagent_eval/integrations/crewai_adapter.py
src/multiagent_eval/integrations/custom_adapter.py
src/multiagent_eval/integrations/langgraph_adapter.py
src/multiagent_eval/judges/__init__.py
src/multiagent_eval/judges/base_judge.py
src/multiagent_eval/judges/consistency_judge.py
src/multiagent_eval/judges/llm_judge.py
src/multiagent_eval/judges/propagation_judge.py
src/multiagent_eval/reports/__init__.py
src/multiagent_eval/reports/dashboard.py
src/multiagent_eval/reports/html_reporter.py
src/multiagent_eval/reports/json_reporter.py
src/multiagent_eval/telemetry/__init__.py
src/multiagent_eval/telemetry/otel_tracer.py
tests/test_bias_detection.py
tests/test_golden_datasets.py
tests/test_metrics.py
tests/test_runner.py
tests/test_trace.py