LICENSE
README.md
pyproject.toml
setup.cfg
setup.py
versioneer.py
development/__init__.py
development/normalize_sandbox_fusion.py
development/utils/__init__.py
development/utils/generate_api_key.py
development/utils/subprocess_manager.py
eval_protocol/__init__.py
eval_protocol/__main__.py
eval_protocol/_version.py
eval_protocol/auth.py
eval_protocol/cli.py
eval_protocol/common_utils.py
eval_protocol/config.py
eval_protocol/evaluation.py
eval_protocol/gcp_tools.py
eval_protocol/generic_server.py
eval_protocol/mcp_env.py
eval_protocol/models.py
eval_protocol/packaging.py
eval_protocol/platform_api.py
eval_protocol/playback_policy.py
eval_protocol/pytest_utils.py
eval_protocol/resources.py
eval_protocol/reward_function.py
eval_protocol/rl_processing.py
eval_protocol/server.py
eval_protocol/typed_interface.py
eval_protocol.egg-info/PKG-INFO
eval_protocol.egg-info/SOURCES.txt
eval_protocol.egg-info/dependency_links.txt
eval_protocol.egg-info/entry_points.txt
eval_protocol.egg-info/requires.txt
eval_protocol.egg-info/top_level.txt
eval_protocol/adapters/__init__.py
eval_protocol/adapters/braintrust.py
eval_protocol/adapters/trl.py
eval_protocol/agent/__init__.py
eval_protocol/agent/models.py
eval_protocol/agent/orchestrator.py
eval_protocol/agent/resource_abc.py
eval_protocol/agent/resource_pool.py
eval_protocol/agent/task_manager.py
eval_protocol/agent/tool_registry.py
eval_protocol/agent/resources/__init__.py
eval_protocol/agent/resources/bfcl_sim_api_resource.py
eval_protocol/agent/resources/docker_resource.py
eval_protocol/agent/resources/filesystem_resource.py
eval_protocol/agent/resources/http_rollout_protocol.py
eval_protocol/agent/resources/http_rollout_resource.py
eval_protocol/agent/resources/python_state_resource.py
eval_protocol/agent/resources/sql_resource.py
eval_protocol/agent/resources/bfcl_envs/__init__.py
eval_protocol/agent/resources/bfcl_envs/gorilla_file_system.py
eval_protocol/agent/resources/bfcl_envs/math_api.py
eval_protocol/agent/resources/bfcl_envs/posting_api.py
eval_protocol/cli_commands/__init__.py
eval_protocol/cli_commands/agent_eval_cmd.py
eval_protocol/cli_commands/common.py
eval_protocol/cli_commands/deploy.py
eval_protocol/cli_commands/deploy_mcp.py
eval_protocol/cli_commands/preview.py
eval_protocol/cli_commands/run_eval_cmd.py
eval_protocol/datasets/__init__.py
eval_protocol/datasets/loader.py
eval_protocol/execution/__init__.py
eval_protocol/execution/pipeline.py
eval_protocol/generation/cache.py
eval_protocol/generation/clients.py
eval_protocol/generation/clients/base.py
eval_protocol/integrations/__init__.py
eval_protocol/integrations/braintrust.py
eval_protocol/integrations/deepeval.py
eval_protocol/integrations/openeval.py
eval_protocol/integrations/trl.py
eval_protocol/mcp/__init__.py
eval_protocol/mcp/adapter.py
eval_protocol/mcp/clients.py
eval_protocol/mcp/grid_renderer.py
eval_protocol/mcp/mcpgym.py
eval_protocol/mcp/process_manager.py
eval_protocol/mcp/simple_process_manager.py
eval_protocol/mcp/simulation_server.py
eval_protocol/mcp/client/__init__.py
eval_protocol/mcp/client/connection.py
eval_protocol/mcp/execution/__init__.py
eval_protocol/mcp/execution/base_policy.py
eval_protocol/mcp/execution/manager.py
eval_protocol/mcp/execution/policy.py
eval_protocol/mcp/session/__init__.py
eval_protocol/mcp/session/manager.py
eval_protocol/mcp_agent/__init__.py
eval_protocol/mcp_agent/config.py
eval_protocol/mcp_agent/intermediary_server.py
eval_protocol/mcp_agent/main.py
eval_protocol/mcp_agent/session.py
eval_protocol/mcp_agent/orchestration/__init__.py
eval_protocol/mcp_agent/orchestration/base_client.py
eval_protocol/mcp_agent/orchestration/local_docker_client.py
eval_protocol/mcp_agent/orchestration/remote_http_client.py
eval_protocol/mcp_agent/orchestration/stdio_mcp_client_helper.py
eval_protocol/rewards/__init__.py
eval_protocol/rewards/accuracy.py
eval_protocol/rewards/accuracy_length.py
eval_protocol/rewards/apps_coding_reward.py
eval_protocol/rewards/apps_execution_utils.py
eval_protocol/rewards/apps_testing_util.py
eval_protocol/rewards/bfcl_reward.py
eval_protocol/rewards/code_execution.py
eval_protocol/rewards/code_execution_utils.py
eval_protocol/rewards/cpp_code.py
eval_protocol/rewards/deepcoder_reward.py
eval_protocol/rewards/format.py
eval_protocol/rewards/function_calling.py
eval_protocol/rewards/json_schema.py
eval_protocol/rewards/language_consistency.py
eval_protocol/rewards/lean_prover.py
eval_protocol/rewards/length.py
eval_protocol/rewards/list_comparison_math_reward.py
eval_protocol/rewards/math.py
eval_protocol/rewards/multiple_choice_math_reward.py
eval_protocol/rewards/reasoning_steps.py
eval_protocol/rewards/repetition.py
eval_protocol/rewards/tag_count.py
eval_protocol/types/__init__.py
eval_protocol/types/types.py
eval_protocol/utils/__init__.py
eval_protocol/utils/batch_evaluation.py
eval_protocol/utils/batch_transformation.py
eval_protocol/utils/dataset_helpers.py
eval_protocol/utils/module_loader.py
eval_protocol/utils/packaging_utils.py
eval_protocol/utils/static_policy.py
tests/test_accuracy.py
tests/test_accuracy_length.py
tests/test_agent_orchestrator.py
tests/test_agent_resources.py
tests/test_auth.py
tests/test_batch_evaluation.py
tests/test_braintrust_adapter.py
tests/test_braintrust_example.py
tests/test_cli.py
tests/test_cli_agent.py
tests/test_cli_args.py
tests/test_code_execution.py
tests/test_config.py
tests/test_control_plane_separation.py
tests/test_cpp_code.py
tests/test_data_driven_task_manager.py
tests/test_deepcoder_reward.py
tests/test_deepeval_integration.py
tests/test_deploy_integration.py
tests/test_e2b_integration.py
tests/test_e2b_js_integration.py
tests/test_edge_cases.py
tests/test_eval_protocol_import.py
tests/test_evaluation.py
tests/test_evaluation_integration.py
tests/test_evaluation_preview_integration.py
tests/test_examples_end_to_end.py
tests/test_fireworks_api.py
tests/test_format.py
tests/test_fractional_code.py
tests/test_frozen_lake_http_server.py
tests/test_frozen_lake_seed_evaluation.py
tests/test_function_calling.py
tests/test_gcp_tools.py
tests/test_generic_server.py
tests/test_integration.py
tests/test_json_schema.py
tests/test_kwargs_validation.py
tests/test_language_consistency.py
tests/test_lean_prover.py
tests/test_lean_prover_runner.py
tests/test_length.py
tests/test_list_comparison_math_reward.py
tests/test_math.py
tests/test_minimal.py
tests/test_models.py
tests/test_models_rl.py
tests/test_multiple_choice_math_reward.py
tests/test_n_variant_batch_integration.py
tests/test_n_variant_integration.py
tests/test_openai_compatibility.py
tests/test_openeval_integration.py
tests/test_packaging.py
tests/test_parallel_rollouts.py
tests/test_platform_api.py
tests/test_pytest_async.py
tests/test_pytest_input_messages.py
tests/test_pytest_math_example.py
tests/test_pytest_math_format_length.py
tests/test_readiness.py
tests/test_reasoning_steps.py
tests/test_repetition.py
tests/test_repetition_debug.py
tests/test_reward_function.py
tests/test_reward_protocol_import.py
tests/test_rl_processing.py
tests/test_rollout_control_plane_integration.py
tests/test_server.py
tests/test_tag_count.py
tests/test_typed_interface.py
tests/test_typed_interface_rl.py
tests/test_url_handling.py
vendor/tau2/__init__.py
vendor/tau2/cli.py
vendor/tau2/config.py
vendor/tau2/registry.py
vendor/tau2/run.py
vendor/tau2/agent/__init__.py
vendor/tau2/agent/base.py
vendor/tau2/agent/llm_agent.py
vendor/tau2/api_service/__init__.py
vendor/tau2/api_service/api_config.py
vendor/tau2/api_service/data_model.py
vendor/tau2/api_service/simulation_service.py
vendor/tau2/data_model/__init__.py
vendor/tau2/data_model/message.py
vendor/tau2/data_model/simulation.py
vendor/tau2/data_model/tasks.py
vendor/tau2/domains/__init__.py
vendor/tau2/domains/airline/__init__.py
vendor/tau2/domains/airline/data_model.py
vendor/tau2/domains/airline/environment.py
vendor/tau2/domains/airline/tools.py
vendor/tau2/domains/airline/utils.py
vendor/tau2/domains/mock/__init__.py
vendor/tau2/domains/mock/data_model.py
vendor/tau2/domains/mock/environment.py
vendor/tau2/domains/mock/tools.py
vendor/tau2/domains/mock/utils.py
vendor/tau2/domains/retail/__init__.py
vendor/tau2/domains/retail/data_model.py
vendor/tau2/domains/retail/environment.py
vendor/tau2/domains/retail/tools.py
vendor/tau2/domains/retail/utils.py
vendor/tau2/domains/telecom/__init__.py
vendor/tau2/domains/telecom/data_model.py
vendor/tau2/domains/telecom/environment.py
vendor/tau2/domains/telecom/tools.py
vendor/tau2/domains/telecom/user_data_model.py
vendor/tau2/domains/telecom/user_tools.py
vendor/tau2/domains/telecom/utils.py
vendor/tau2/domains/telecom/tasks/__init__.py
vendor/tau2/domains/telecom/tasks/const.py
vendor/tau2/domains/telecom/tasks/create_tasks.py
vendor/tau2/domains/telecom/tasks/manager.py
vendor/tau2/domains/telecom/tasks/mms_issues.py
vendor/tau2/domains/telecom/tasks/mobile_data_issues.py
vendor/tau2/domains/telecom/tasks/service_issues.py
vendor/tau2/domains/telecom/tasks/utils.py
vendor/tau2/environment/__init__.py
vendor/tau2/environment/db.py
vendor/tau2/environment/environment.py
vendor/tau2/environment/server.py
vendor/tau2/environment/tool.py
vendor/tau2/environment/toolkit.py
vendor/tau2/environment/utils/interface_agent.py
vendor/tau2/evaluator/__init__.py
vendor/tau2/evaluator/evaluator.py
vendor/tau2/evaluator/evaluator_action.py
vendor/tau2/evaluator/evaluator_base.py
vendor/tau2/evaluator/evaluator_communicate.py
vendor/tau2/evaluator/evaluator_env.py
vendor/tau2/evaluator/evaluator_nl_assertions.py
vendor/tau2/metrics/__init__.py
vendor/tau2/metrics/agent_metrics.py
vendor/tau2/metrics/break_down_metrics.py
vendor/tau2/orchestrator/__init__.py
vendor/tau2/orchestrator/environment_manager.py
vendor/tau2/orchestrator/orchestrator.py
vendor/tau2/orchestrator/utils.py
vendor/tau2/scripts/__init__.py
vendor/tau2/scripts/check_data.py
vendor/tau2/scripts/show_domain_doc.py
vendor/tau2/scripts/start_servers.py
vendor/tau2/scripts/view_simulations.py
vendor/tau2/user/__init__.py
vendor/tau2/user/base.py
vendor/tau2/user/user_simulator.py
vendor/tau2/utils/__init__.py
vendor/tau2/utils/display.py
vendor/tau2/utils/io_utils.py
vendor/tau2/utils/llm_utils.py
vendor/tau2/utils/pydantic_utils.py
vendor/tau2/utils/utils.py