Skip to content

Conversation

pan-x-c
Copy link
Collaborator

@pan-x-c pan-x-c commented Oct 20, 2025

Description

  1. use class property can_reset, can_repeat, is_async to replace instance property resettable, repeatable, asynchronous
  2. asychronous workflows use openai.AsyncOpenAI auxiliary models
  3. move rollout_args into SimpleWorkflow

Checklist

Please check the following items before code is ready to be reviewed.

  • Code has passed all tests
  • Docstrings have been added/updated in Google Style
  • Documentation has been updated
  • Code is ready for review

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Oct 20, 2025

/unittest-all

Copy link
Contributor

Summary of Changes

Hello @pan-x-c, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly simplifies the interface for defining workflow behaviors by migrating key properties from instance-level methods to class-level attributes. This change enhances clarity and consistency in workflow declarations, particularly for features like resettability, repeatability, and asynchronous execution. Concurrently, the underlying system for managing auxiliary models has been improved to correctly provision synchronous or asynchronous OpenAI clients based on the workflow's declared asynchronous nature, ensuring proper integration and functionality.

Highlights

  • Workflow Interface Simplification: The pull request refactors workflow capabilities such as resettable, repeatable, and asynchronous from instance properties to class properties named can_reset, can_repeat, and is_async respectively. This change streamlines the workflow definition by making these characteristics static and declared directly within the class.
  • Asynchronous Model Handling: Asynchronous workflows are now explicitly configured to use openai.AsyncOpenAI auxiliary models. The WorkflowRunner has been updated to dynamically provide either synchronous (openai.OpenAI) or asynchronous (openai.AsyncOpenAI) clients to workflows based on their is_async class property.
  • Documentation and Test Updates: All relevant documentation (both English and Chinese) and test files have been updated to reflect the new class property interface. This includes modifying example code snippets and test assertions to align with the simplified workflow definitions and the new Experience object return type for run and run_async methods.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request does a great job of simplifying the workflow interface by replacing instance properties with class properties (can_reset, can_repeat, is_async) and moving rollout_args into SimpleWorkflow. The changes are applied consistently across a large number of files, including documentation and tests.

However, the refactoring of rollout_args has introduced a critical issue in several workflow classes that inherit from Workflow but not SimpleWorkflow. These classes still attempt to access self.rollout_args, which no longer exists in the base Workflow class, and will cause runtime errors. I've left specific comments on the affected files with suggestions on how to fix this.

Once these issues are addressed, this will be a solid improvement to the codebase.

Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
160 157 0 3 0 0 3.5s

Skipped

Tests Status
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_std_grpo 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_step_wise_grpo_advantage 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_duplicate_grpo 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_advantage 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_correct_bias 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_reward_std 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_step_wise_grpo_advantage 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_dpo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_gspo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_mix_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_opmd_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_ppo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_sft_policy_loss 1ms
tests/buffer/experience_pipeline_test.py::TestExperiencePipeline::test_experience_pipeline 13ms
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_experience_buffer 4ms
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_0_sft 6ms
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_1_dpo 6ms
tests/buffer/file_test.py::TestFileBuffer::test_file_reader 1ms
tests/buffer/file_test.py::TestFileBuffer::test_file_writer 3ms
tests/buffer/formatter_test.py::TestFormatter::test_dpo_messages_formatter 1ms
tests/buffer/formatter_test.py::TestFormatter::test_dpo_plaintext_formatter 1ms
tests/buffer/formatter_test.py::TestFormatter::test_multi_modal_sft_formatter 1ms
tests/buffer/formatter_test.py::TestFormatter::test_sft_messages_formatter 1ms
tests/buffer/formatter_test.py::TestFormatter::test_sft_plaintext_formatter 1ms
tests/buffer/formatter_test.py::TestFormatter::test_task_formatter 1ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_buffer_reuse 8ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_capacity 4ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_reuse_count_control 6ms
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_0_queue 5ms
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_1_priority_queue 5ms
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_capacity 6ms
tests/buffer/reward_shaping_mapper_test.py::TestRewardShapingMapper::test_basic_usage 1ms
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_buffer_read_write 4ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_0 1ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_1 3ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_2 1ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_3 3ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_4 1ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_5 4ms
tests/cli/launcher_test.py::TestLauncherMain::test_debug_mode 35ms
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_command 7ms
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_in_dlc 1ms
tests/cli/launcher_test.py::TestLauncherMain::test_main_studio_command 1ms
tests/cli/launcher_test.py::TestLauncherMain::test_multi_stage_run 1ms
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 32ms
tests/common/config_test.py::TestConfig::test_config_flatten 1ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 1ms
tests/common/config_test.py::TestConfig::test_load_default_config 4ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 1ms
tests/common/experience_test.py::TestEID::test_eid_properties 1ms
tests/common/experience_test.py::TestExperience::test_action_mask_and_logprobs_type 1ms
tests/common/experience_test.py::TestExperience::test_assertions 1ms
tests/common/experience_test.py::TestExperience::test_dpo_experience 1ms
tests/common/experience_test.py::TestExperience::test_gather 1ms
tests/common/experience_test.py::TestExperience::test_hf_datasets_conversion 1ms
tests/common/experience_test.py::TestExperience::test_multi_turn_experience 1ms
tests/common/experience_test.py::TestExperience::test_serialize_deserialize 1ms
tests/common/experience_test.py::TestExperience::test_single_turn_experience 1ms
tests/common/experience_test.py::TestExperience::test_to_dict 1ms
tests/common/experience_test.py::TestExperienceConversion::test_batch_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_dpo_experience_batch_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_experience_model_experience_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_gather_experiences_with_custom_fields 1ms
tests/common/experience_test.py::TestExperienceConversion::test_multiturn_experience_batch_converstion 1ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate 56ms
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 35ms
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 46ms
tests/common/vllm_test.py::TestModelLen_0::test_model_len 21ms
tests/common/vllm_test.py::TestModelLen_1::test_model_len 20ms
tests/common/vllm_test.py::TestAPIServer::test_api 24ms
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 24ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask 1ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 1ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 22ms
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 20ms
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 58ms
tests/explorer/explorer_test.py::TestExplorerCountdownNoEval::test_explorer 57ms
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 206ms
tests/explorer/explorer_test.py::ServeTest::test_serve 68ms
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 5ms
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 5ms
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results 24ms
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 5ms
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 5ms
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 15ms
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 9ms
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 8ms
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 5ms
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 8ms
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 14ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_0 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_1 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_0 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_1 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_raise_error 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_stop_at_max_env_steps 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_gsm8k_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_rm_gallery_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_1 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_1 1ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_0::test_multi_turn_workflow 19ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 19ms
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter ⏭️ 1ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 1ms
tests/manager/synchronizer_test.py::TestSynchronizerExit::test_synchronizer 30ms
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_0::test_synchronizer 77ms
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_1::test_synchronizer 77ms
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_2::test_synchronizer 123ms
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_3::test_synchronizer 113ms
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_0::test_synchronizer 72ms
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_1::test_synchronizer 72ms
tests/service/data_juicer_test.py::TestDataJuicer::test_config 1ms
tests/service/data_juicer_test.py::TestDataJuicer::test_server_start 21ms
tests/service/data_juicer_test.py::TestDataJuicerExperiencePipeline::test_data_juicer_operators 23ms
tests/service/data_juicer_test.py::TestDataJuicerTaskPipeline::test_data_juicer_task_pipeline 14ms
tests/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer 142ms
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 267ms
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 60ms
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 54ms
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 52ms
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 56ms
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 62ms
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer 104ms
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 40ms
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 36ms
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 36ms
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 75ms
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 75ms
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 149ms
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 98ms
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 311ms
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 57ms
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer ⏭️ 1ms
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer ⏭️ 1ms
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 156ms
tests/utils/eval_utils_test.py::TestComputeScore::test_both_boxed_and_equivalent 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_both_boxed_and_not_equivalent 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_empty_ground_truth 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_empty_solution_string 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_multiple_boxed_answers_in_solution 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_boxed_truth_raw_and_equivalent 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_boxed_truth_raw_and_not_equivalent 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_not_boxed 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_raw_and_ground_truth_boxed_equivalent 1ms
tests/utils/eval_utils_test.py::TestMathEvalUtils::test_extract_answer 1ms
tests/utils/eval_utils_test.py::TestMathEvalUtils::test_verify_math_answer 1ms
tests/utils/eval_utils_test.py::TestEvalUtils::test_is_equiv 1ms
tests/utils/log_test.py::LogTest::test_actor_log 5ms
tests/utils/log_test.py::LogTest::test_group_by_node 4ms
tests/utils/log_test.py::LogTest::test_no_actor_log 1ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_local 1ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_remote 9ms
tests/utils/plugin_test.py::TestPluginLoader::test_passing_custom_class 5ms

Github Test Reporter by CTRF 💚

@hiyuchang
Copy link
Collaborator

Minor comment, Others LGTM

@pan-x-c pan-x-c requested a review from Copilot October 21, 2025 03:15
Copy link

@Copilot Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR refactors the Workflow interface to replace instance properties with class properties for workflow configuration, and ensures asynchronous workflows receive async-compatible auxiliary model clients.

Key Changes:

  • Replaced instance properties (resettable, repeatable, asynchronous) with class properties (can_reset, can_repeat, is_async)
  • Asynchronous workflows now receive openai.AsyncOpenAI clients instead of openai.OpenAI clients for auxiliary models
  • Moved rollout_args property from base Workflow class to SimpleWorkflow class

Reviewed Changes

Copilot reviewed 24 out of 24 changed files in this pull request and generated no comments.

Show a summary per file
File Description
trinity/explorer/workflow_runner.py Added async client list and conditional logic to pass appropriate client type based on workflow's is_async property
trinity/common/workflows/workflow.py Replaced instance properties with class properties; deprecated old properties; moved rollout_args to SimpleWorkflow
trinity/common/workflows/step_wise_workflow.py Removed overridden property methods in favor of class properties
trinity/common/workflows/simple_mm_workflow.py Replaced asynchronous property with is_async class property
trinity/common/workflows/math_ruler_workflow.py Replaced asynchronous property with is_async class property
trinity/common/workflows/math_rm_workflow.py Replaced asynchronous property with is_async class property
trinity/common/workflows/eval_workflow.py Removed overridden property methods; added is_async class property
trinity/common/workflows/envs/webshop/webshop_workflow.py Replaced property methods with class properties
trinity/common/workflows/envs/sciworld/sciworld_workflow.py Replaced asynchronous property with is_async class property
trinity/common/workflows/envs/email_searcher/workflow.py Replaced property methods with class properties; updated rollout_args access pattern
trinity/common/workflows/envs/alfworld/alfworld_workflow.py Replaced asynchronous property with is_async class property
trinity/common/workflows/envs/alfworld/RAFT_reflect_alfworld_workflow.py Removed asynchronous property method
trinity/common/workflows/envs/alfworld/RAFT_alfworld_workflow.py Replaced property methods with class properties
trinity/common/workflows/envs/agentscope/agentscopev1_search_workflow.py Replaced property methods with class properties; updated rollout_args access pattern
trinity/common/workflows/envs/agentscope/agentscopev1_react_workflow.py Replaced property methods with class properties; updated rollout_args access pattern
trinity/common/workflows/envs/agentscope/agentscopev0_react_workflow.py Replaced property method with class property; updated rollout_args access pattern
trinity/common/workflows/customized_toolcall_workflows.py Replaced asynchronous property with is_async class property
trinity/common/workflows/customized_math_workflows.py Replaced asynchronous property with is_async class property
trinity/common/workflows/agentscope_workflow.py Removed property methods; added is_async class property
trinity/common/workflows/agentscope/react/react_workflow.py Replaced property methods with class property; updated rollout_args access pattern
tests/explorer/workflow_test.py Updated test workflows to use class properties; added validation for auxiliary_models client types
tests/explorer/scheduler_test.py Updated test workflows to use class properties
docs/sphinx_doc/source_zh/tutorial/develop_workflow.md Updated documentation to reflect class property usage
docs/sphinx_doc/source/tutorial/develop_workflow.md Updated documentation to reflect class property usage

Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.

@pan-x-c pan-x-c merged commit e3ba954 into modelscope:main Oct 21, 2025
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants