LICENSE
README.md
pyproject.toml
src/magma_bench/__init__.py
src/magma_bench/__main__.py
src/magma_bench/command_line.py
src/magma_bench/launch.py
src/magma_bench/video.py
src/magma_bench.egg-info/PKG-INFO
src/magma_bench.egg-info/SOURCES.txt
src/magma_bench.egg-info/dependency_links.txt
src/magma_bench.egg-info/entry_points.txt
src/magma_bench.egg-info/requires.txt
src/magma_bench.egg-info/top_level.txt
src/magma_bench/agents/__init__.py
src/magma_bench/agents/base/__init__.py
src/magma_bench/agents/base/benchmark_agent.py
src/magma_bench/artifacts/__init__.py
src/magma_bench/artifacts/models.py
src/magma_bench/artifacts/runtime.py
src/magma_bench/data_structures/__init__.py
src/magma_bench/data_structures/benchmark.py
src/magma_bench/data_structures/running_structure.py
src/magma_bench/evalutations/__init__.py
src/magma_bench/evalutations/_log_rule_compiler.py
src/magma_bench/evalutations/_log_rule_registry.py
src/magma_bench/evalutations/_predicate_compiler.py
src/magma_bench/evalutations/_predicate_registry.py
src/magma_bench/evalutations/log_rules.py
src/magma_bench/evalutations/predicate.py
src/magma_bench/executor/__init__.py
src/magma_bench/executor/context.py
src/magma_bench/executor/episode_runtime.py
src/magma_bench/executor/eval_executor.py
src/magma_bench/loader/__init__.py
src/magma_bench/loader/group.py
src/magma_bench/loader/loader.py
src/magma_bench/results/__init__.py
src/magma_bench/results/manager.py
src/magma_bench/results/metrics.py
src/magma_bench/results/models.py
src/magma_bench/runner/__init__.py
src/magma_bench/runner/group_runner.py
src/magma_bench/runner/runner.py
tests/test_agent.py
tests/test_details.py
tests/test_results_metrics.py
tests/test_runner_answer_tools.py
tests/test_runtime_error_validation.py