Fix process_messages_to_experience in MultiTurnWorkflow

[hiyuchang]

Description

As the title says.

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

[gemini-code-assist]

Summary of Changes

Hello @hiyuchang, 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 introduces significant refactoring to align experience processing with asynchronous programming patterns. The core change involves converting the process_messages_to_experience function into an asynchronous operation, renaming it to process_messages_to_experience_async, and updating all its usages across different workflow implementations. This ensures that the experience generation process can leverage Python's asyncio capabilities, improving concurrency and potentially performance in environments that utilize asynchronous models.

Highlights

• Asynchronous Function Renaming: The function process_messages_to_experience has been renamed to process_messages_to_experience_async to reflect its new asynchronous nature.
• Asynchronous Implementation: The process_messages_to_experience_async function, along with its internal call to model.convert_messages_to_experience_async, has been updated to be an async function, requiring await when called.
• Workflow Class Integration: A new async method, process_messages_to_experience_async, has been added to the base Workflow class, encapsulating the logic for converting messages to experience asynchronously.
• Call Site Updates: All instances where the original process_messages_to_experience was called across various workflow environments (Alfworld, Frozen Lake, Sciworld, Webshop) have been updated to call the new process_messages_to_experience_async with the await keyword.
• Type Casting for Rewards: In some workflow environments (Frozen Lake, Webshop), the reward parameter passed to process_messages_to_experience_async is now explicitly cast to a float to ensure type consistency.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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. ↩

[gemini-code-assist]

Code Review

This pull request introduces an asynchronous version of the process_messages_to_experience method, named process_messages_to_experience_async, and updates several workflow files to use this new async method, including RAFT_alfworld_workflow.py, RAFT_reflect_alfworld_workflow.py, RAFT_utils.py, alfworld_workflow.py, frozen_lake/workflow.py, sciworld_workflow.py, webshop_workflow.py, and workflow_test.py. The reviewer commented that the new process_messages_to_experience_async method duplicates most of the logic from its synchronous counterpart and suggested refactoring the common logic into a private helper method to improve maintainability and reduce code duplication.

[hiyuchang]

/unittest-module-explorer

[github-actions]

Summary

Tests 📝	Passed ✅	Failed ❌	Skipped ⏭️	Other ❓	Flaky 🍂	Duration ⏱️
48	47	0	1	0	0	12m 35s

Skipped

Tests	Status
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter_v1	skipped ⏭️

Tests

Test Name	Status	Flaky	Duration
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer	✅		1m 35s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer	✅		1m 21s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer	✅		3m 31s
tests/explorer/explorer_test.py::ServeTest::test_serve	✅		1m 26s
tests/explorer/proxy_test.py::RecorderTest::test_recorder	✅		64ms
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow	✅		4.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations	✅		4.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout	✅		12.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results	✅		20.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0	✅		4.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1	✅		4.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0	✅		4.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1	✅		4.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution	✅		4.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow	✅		4.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_min_wait	✅		8.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods	✅		14.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop	✅		7.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks	✅		7.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid	✅		24.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all	✅		7.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch	✅		13.4s
tests/explorer/scheduler_test.py::TestRunnerStateCollection::test_runner_state_collection	✅		9.2s
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	✅		602ms
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	✅		1.0s
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	✅		1.0s
tests/explorer/workflow_test.py::WorkflowTest::test_gsm8k_workflow	✅		25ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow	✅		16ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow	✅		129ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow	✅		2ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow	✅		10ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow	✅		7ms
tests/explorer/workflow_test.py::WorkflowTest::test_rm_gallery_workflow	✅		132ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_0	✅		1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_1	✅		100ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_0	✅		1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_1	✅		201ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_0::test_multi_turn_workflow	✅		21.0s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow	✅		56.9s
tests/explorer/workflow_test.py::TestWorkflowStateRecording::test_workflow_state_recording	✅		4.0s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter_v0	✅		706ms
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter_v1	⏭️		1ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner	✅		156ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_get_state	✅		8.0s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_with_openai	✅		22.5s

Github Test Reporter by CTRF 💚