eval-protocol 0.2.48__tar.gz → 0.2.49__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {eval_protocol-0.2.48/eval_protocol.egg-info → eval_protocol-0.2.49}/PKG-INFO +1 -1
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/__init__.py +2 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/_version.py +3 -3
- {eval_protocol-0.2.48 → eval_protocol-0.2.49/eval_protocol.egg-info}/PKG-INFO +1 -1
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/LICENSE +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/README.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/development/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/development/normalize_sandbox_fusion.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/development/utils/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/development/utils/generate_api_key.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/development/utils/subprocess_manager.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/__main__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/base.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/bigquery.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/braintrust.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/fireworks_tracing.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/huggingface.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/langchain.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/langfuse.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/langsmith.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/openai_responses.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/trl.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/adapters/weave.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/models.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/orchestrator.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resource_abc.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resource_pool.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/bfcl_envs/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/bfcl_envs/gorilla_file_system.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/bfcl_envs/math_api.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/bfcl_envs/posting_api.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/bfcl_sim_api_resource.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/docker_resource.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/filesystem_resource.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/python_state_resource.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/sql_resource.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/task_manager.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/tool_registry.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/auth.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/data/airline_dataset.jsonl +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/data/retail_dataset.jsonl +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/test_aime25.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/test_frozen_lake.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/test_gpqa.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/test_livebench_data_analysis.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/test_tau_bench_airline.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/test_tau_bench_retail.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/cli.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/cli_commands/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/cli_commands/agent_eval_cmd.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/cli_commands/common.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/cli_commands/deploy.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/cli_commands/deploy_mcp.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/cli_commands/logs.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/cli_commands/preview.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/cli_commands/run_eval_cmd.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/cli_commands/upload.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/common_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/config.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/data_loader/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/data_loader/dynamic_data_loader.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/data_loader/factory_data_loader.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/data_loader/inline_data_loader.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/data_loader/models.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/dataset_logger/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/dataset_logger/dataset_logger.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/dataset_logger/local_fs_dataset_logger_adapter.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/dataset_logger/sqlite_dataset_logger_adapter.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/dataset_logger/sqlite_evaluation_row_store.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/datasets/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/datasets/loader.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/directory_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/evaluation.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/event_bus/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/event_bus/event_bus.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/event_bus/logger.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/event_bus/sqlite_event_bus.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/event_bus/sqlite_event_bus_database.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/execution/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/execution/pipeline.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/gcp_tools.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/generation/cache.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/generation/clients/base.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/generation/clients.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/generic_server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/get_pep440_version.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/human_id/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/human_id/dictionary.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/integrations/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/integrations/deepeval.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/integrations/openeval.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/integrations/trl.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/log_utils/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/log_utils/elasticsearch_client.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/log_utils/elasticsearch_direct_http_handler.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/log_utils/elasticsearch_index_manager.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/log_utils/fireworks_tracing_http_handler.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/log_utils/rollout_id_filter.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/log_utils/util.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/logging_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/adapter.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/client/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/client/connection.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/clients.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/execution/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/execution/base_policy.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/execution/manager.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/execution/policy.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/grid_renderer.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/mcp_multi_client.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/mcpgym.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/process_manager.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/session/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/session/manager.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/simple_process_manager.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp/simulation_server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_agent/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_agent/config.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_agent/main.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_agent/orchestration/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_agent/orchestration/base_client.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_agent/orchestration/local_docker_client.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_agent/orchestration/stdio_mcp_client_helper.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_env.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/frozen_lake/frozen_lake_adapter.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/frozen_lake/frozen_lake_mcp.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/frozen_lake/server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/README.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/airplane_environment/airline_environment.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/mock_environment/mock_environment.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/retail_environment/retail_environment.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/tau2_mcp.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/tests/system_prompts/airline_agent_system_prompt.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/tests/system_prompts/mock_agent_system_prompt.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/tests/system_prompts/retail_agent_system_prompt.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/tests/test_tau2_e2e.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/models.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/packaging.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/platform_api.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/playback_policy.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/default_agent_rollout_processor.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/default_dataset_adapter.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/default_langchain_rollout_processor.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/default_mcp_gym_rollout_processor.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/default_no_op_rollout_processor.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/default_pydantic_ai_rollout_processor.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/default_single_turn_rollout_process.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/dual_mode_wrapper.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/elasticsearch_setup.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/evaluation_test.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/evaluation_test_postprocess.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/exception_config.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/execution.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/generate_parameter_combinations.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/handle_persist_flow.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/parameterize.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/plugin.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/remote_rollout_processor.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/rollout_processor.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/store_experiment_link.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/store_results_url.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/types.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/validate_signature.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/quickstart/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/quickstart/llm_judge.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/quickstart/llm_judge_braintrust.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/quickstart/llm_judge_langfuse.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/quickstart/llm_judge_langsmith.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/quickstart/llm_judge_openai_responses.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/quickstart/utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/resources.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/reward_function.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/accuracy.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/accuracy_length.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/apps_coding_reward.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/apps_execution_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/apps_testing_util.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/bfcl_reward.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/code_execution.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/code_execution_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/cpp_code.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/deepcoder_reward.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/format.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/function_calling.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/json_schema.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/language_consistency.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/lean_prover.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/length.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/list_comparison_math_reward.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/math.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/multiple_choice_math_reward.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/reasoning_steps.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/repetition.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/tag_count.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rl_processing.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/stats/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/stats/confidence_intervals.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/typed_interface.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/types/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/types/errors.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/types/remote_rollout_processor.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/types/types.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/batch_evaluation.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/batch_transformation.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/browser_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/check_server_status.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/dataset_helpers.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/logs_models.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/logs_server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/module_loader.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/packaging_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/show_results_url.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/static_policy.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/subprocess_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/utils/vite_server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol.egg-info/SOURCES.txt +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol.egg-info/dependency_links.txt +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol.egg-info/entry_points.txt +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol.egg-info/requires.txt +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol.egg-info/top_level.txt +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/pyproject.toml +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/setup.cfg +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/setup.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_accuracy.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_accuracy_length.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_adapters_e2e.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_agent_orchestrator.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_agent_resources.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_auth.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_batch_evaluation.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_cli.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_cli_agent.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_cli_args.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_code_execution.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_config.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_control_plane_separation.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_cpp_code.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_data_driven_task_manager.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_deepcoder_reward.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_deepeval_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_deploy_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_directory_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_e2b_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_e2b_js_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_edge_cases.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_eval_protocol_import.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_evaluation.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_evaluation_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_evaluation_postprocess.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_evaluation_preview_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_event_bus.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_event_bus_helper.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_examples_end_to_end.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_fireworks_api.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_format.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_fractional_code.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_function_calling.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_gcp_tools.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_generic_server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_human_id.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_json_schema.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_kwargs_validation.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_language_consistency.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_lean_prover.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_lean_prover_runner.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_length.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_list_comparison_math_reward.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_logs_server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_logs_server_simple.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_math.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_minimal.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_models.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_models_rl.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_multiple_choice_math_reward.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_n_variant_batch_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_n_variant_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_openai_compatibility.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_openeval_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_packaging.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_parallel_rollouts.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_platform_api.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_quickstart_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_readiness.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_reasoning_steps.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_repetition.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_repetition_debug.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_retry_mechanism.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_reward_function.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_reward_protocol_import.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_rl_processing.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_rollout_control_plane_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_show_results_url.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_status_migration_changes.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_status_migration_integration.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_status_model.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_tag_count.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_tau_bench_airline_smoke.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_typed_interface.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_typed_interface_rl.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_upload_entrypoint.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_url_handling.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/tests/test_vite_server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/agent/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/agent/base.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/agent/llm_agent.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/api_service/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/api_service/api_config.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/api_service/data_model.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/api_service/simulation_service.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/cli.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/config.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data/domains/airline/policy.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data/domains/mock/policy.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data/domains/mock/policy_solo.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data/domains/retail/policy.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data/domains/telecom/main_policy.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data/domains/telecom/main_policy_solo.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data/domains/telecom/tech_support_manual.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data/domains/telecom/tech_support_workflow.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data/domains/telecom/tech_support_workflow_solo.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data/user_simulator/simulation_guidelines.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data/user_simulator/simulation_guidelines_tools.md +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data_model/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data_model/message.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data_model/simulation.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/data_model/tasks.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/airline/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/airline/data_model.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/airline/environment.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/airline/tools.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/airline/utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/mock/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/mock/data_model.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/mock/environment.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/mock/tools.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/mock/utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/retail/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/retail/data_model.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/retail/environment.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/retail/tools.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/retail/utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/data_model.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/environment.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/tasks/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/tasks/const.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/tasks/create_tasks.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/tasks/manager.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/tasks/mms_issues.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/tasks/mobile_data_issues.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/tasks/service_issues.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/tasks/utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/tools.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/user_data_model.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/user_tools.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/domains/telecom/utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/environment/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/environment/db.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/environment/environment.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/environment/server.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/environment/tool.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/environment/toolkit.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/environment/utils/interface_agent.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/evaluator/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/evaluator/evaluator.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/evaluator/evaluator_action.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/evaluator/evaluator_base.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/evaluator/evaluator_communicate.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/evaluator/evaluator_env.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/evaluator/evaluator_nl_assertions.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/metrics/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/metrics/agent_metrics.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/metrics/break_down_metrics.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/orchestrator/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/orchestrator/environment_manager.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/orchestrator/orchestrator.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/orchestrator/utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/registry.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/run.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/scripts/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/scripts/check_data.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/scripts/show_domain_doc.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/scripts/start_servers.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/scripts/view_simulations.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/user/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/user/base.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/user/user_simulator.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/utils/__init__.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/utils/display.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/utils/io_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/utils/llm_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/utils/pydantic_utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vendor/tau2/utils/utils.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/versioneer.py +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vite-app/dist/assets/favicon-BkAAWQga.png +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vite-app/dist/assets/index-34WaHH5W.css +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vite-app/dist/assets/index-DOPsfOMT.js +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vite-app/dist/assets/index-DOPsfOMT.js.map +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vite-app/dist/assets/logo-light-BprIBJQW.png +0 -0
- {eval_protocol-0.2.48 → eval_protocol-0.2.49}/vite-app/dist/index.html +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: eval-protocol
|
|
3
|
-
Version: 0.2.
|
|
3
|
+
Version: 0.2.49
|
|
4
4
|
Summary: The official Python SDK for Eval Protocol (EP.) EP is an open protocol that standardizes how developers author evals for large language model (LLM) applications.
|
|
5
5
|
Author-email: Fireworks AI <info@fireworks.ai>
|
|
6
6
|
License-Expression: MIT
|
|
@@ -31,6 +31,7 @@ from .reward_function import RewardFunction
|
|
|
31
31
|
from .typed_interface import reward_function
|
|
32
32
|
from .quickstart import aha_judge, multi_turn_assistant_to_ground_truth, assistant_to_ground_truth
|
|
33
33
|
from .pytest import evaluation_test, SingleTurnRolloutProcessor, RemoteRolloutProcessor
|
|
34
|
+
from .pytest.remote_rollout_processor import create_elasticsearch_config_from_env
|
|
34
35
|
from .pytest.parameterize import DefaultParameterIdGenerator
|
|
35
36
|
from .log_utils.elasticsearch_direct_http_handler import ElasticsearchDirectHttpHandler
|
|
36
37
|
from .log_utils.rollout_id_filter import RolloutIdFilter
|
|
@@ -76,6 +77,7 @@ except ImportError:
|
|
|
76
77
|
warnings.filterwarnings("default", category=DeprecationWarning, module="eval_protocol")
|
|
77
78
|
|
|
78
79
|
__all__ = [
|
|
80
|
+
"create_elasticsearch_config_from_env",
|
|
79
81
|
"ElasticsearchConfig",
|
|
80
82
|
"ElasticsearchDirectHttpHandler",
|
|
81
83
|
"RolloutIdFilter",
|
|
@@ -8,11 +8,11 @@ import json
|
|
|
8
8
|
|
|
9
9
|
version_json = '''
|
|
10
10
|
{
|
|
11
|
-
"date": "2025-10-
|
|
11
|
+
"date": "2025-10-10T15:31:44-0700",
|
|
12
12
|
"dirty": false,
|
|
13
13
|
"error": null,
|
|
14
|
-
"full-revisionid": "
|
|
15
|
-
"version": "0.2.
|
|
14
|
+
"full-revisionid": "ac4fbbbf47d1ec261cb561d66a02e27778f29266",
|
|
15
|
+
"version": "0.2.49"
|
|
16
16
|
}
|
|
17
17
|
''' # END VERSION_JSON
|
|
18
18
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: eval-protocol
|
|
3
|
-
Version: 0.2.
|
|
3
|
+
Version: 0.2.49
|
|
4
4
|
Summary: The official Python SDK for Eval Protocol (EP.) EP is an open protocol that standardizes how developers author evals for large language model (LLM) applications.
|
|
5
5
|
Author-email: Fireworks AI <info@fireworks.ai>
|
|
6
6
|
License-Expression: MIT
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/bfcl_envs/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/bfcl_envs/math_api.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/bfcl_envs/posting_api.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/bfcl_sim_api_resource.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/docker_resource.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/filesystem_resource.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/agent/resources/python_state_resource.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/data/airline_dataset.jsonl
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/data/retail_dataset.jsonl
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/test_tau_bench_airline.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/benchmarks/test_tau_bench_retail.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/data_loader/dynamic_data_loader.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/data_loader/factory_data_loader.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/data_loader/inline_data_loader.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/dataset_logger/dataset_logger.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/event_bus/sqlite_event_bus_database.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/log_utils/elasticsearch_client.py
RENAMED
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/log_utils/elasticsearch_index_manager.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_agent/orchestration/__init__.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_agent/orchestration/base_client.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/frozen_lake/server.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/mcp_servers/tau2/tests/test_tau2_e2e.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/default_dataset_adapter.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/evaluation_test_postprocess.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/pytest/remote_rollout_processor.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/quickstart/llm_judge_braintrust.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/quickstart/llm_judge_langfuse.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/quickstart/llm_judge_langsmith.py
RENAMED
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/quickstart/llm_judge_openai_responses.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/list_comparison_math_reward.py
RENAMED
|
File without changes
|
|
File without changes
|
{eval_protocol-0.2.48 → eval_protocol-0.2.49}/eval_protocol/rewards/multiple_choice_math_reward.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|